diff --git "a/predicted_examples.jsonl" "b/predicted_examples.jsonl"
new file mode 100644--- /dev/null
+++ "b/predicted_examples.jsonl"
@@ -0,0 +1,595 @@
+{"id": "task1356-018e7314264c4d2fb6b980845687ffd6", "Task": "task1356_xlsum_title_generation", "Contributors": "['Krishna Sree G']", "Source": ["xlsum"], "URL": ["https://arxiv.org/abs/2106.13822"], "Categories": ["Title Generation"], "Reasoning": [], "Definition": ["Generate an appropriate title for the given text. The generated title must be short and include the main topic of the text. The preferred titles are under fifteen words."], "Positive Examples": [{"input": "But Eluned Morgan conceded that it would be \"difficult for us to stop\" from a legal point of view. Her comments were criticised by a Labour AM. Alun Davies said threatening legal action \"sounds like the last breath before you're thrown out of the pub\". Mr Davies said he was not convinced the Welsh Government would \"have a leg to stand on\" in trying to shape international trade deals after Brexit. Following Donald Trump's comments during last week's trade visit that the NHS would be \"on the table\" in any future trade talks between the UK and the USA, Eluned Morgan said there was \"absolutely no prospect whatsoever of us allowing the Welsh NHS to be part of any negotiation.\" The US President then rowed back on his initial comments following criticism from a number of MPs. Asked about her response to President Trump's remarks as she gave evidence to the Assembly's Brexit committee on Monday, Ms Morgan said \"legally, it would be difficult for us to stop because we don't have a veto over trade\". \"Politically, I think it's extremely unlikely to happen,\" the international relations and the Welsh language minister said. \"They [the UK Government] should not be concluding any trade agreements without consulting us where we have the power.\" Ms Morgan explained that UK and Welsh government officials are working on an agreement or 'concordat' for how future trade deals are negotiated. During a robust exchange, the Labour AM Alun Davies said: \"I want something which is in law to which I can hold you to account and which colleagues in Westminster can hold the UK Government to account. \"The argument we'll make life difficult for them, it sounds alright on the street, but it's not the reality of intergovernmental relations.\" \"The United Kingdom has to find a way of functioning. \"At the moment, your answers aren't giving me any confidence that there is that structure in place because, if the Welsh Government's argument is, 'we'll see you in court', it's not a very impressive argument either for the continuation of the structure of United Kingdom as a state or the commitment of the government within the United Kingdom to actually work together,\" he added. Responding to the criticism, Ms Morgan said: \"Is the current intergovernmental structure adequate? \"Absolutely not... and it's not just in relation to trade, it's in relation to almost every aspect of government policy. So, that infrastructure needs to be built.\"", "output": "NHS Wales: Court action if trade deals affect service?", "explanation": "The output phrase is the appropriate title for the given text and it highlights the essence of the passage."}, {"input": "By Jon Welch and Paul MoseleyBBC News Details of health problems, family bereavements and personal issues were sent by the University of East Anglia (UEA) in Norwich to 298 students. Megan Baynes, 23, said she felt \"sick and horrified\" when she realised her details had been shared. The UEA apologised \"unreservedly\" and said an inquiry had begun. The email contained a spreadsheet listing 172 names and details extenuating circumstances in which extensions and other academic concessions were granted to 42 students. 'Felt sick' It was sent to nearly 300 undergraduates, including Ms Baynes, a former editor of student newspaper Concrete. She is currently awaiting the results of her American Literature and Creative Writing degree, and had been granted extensions for coursework because of an illness suffered by a family member. \"I felt sick at seeing my personal situation written in a spreadsheet, and then seemingly sent to everyone on my course,\" she said. \"My situation was not the worst on there but there are some on there that are so personal. There are people I know and I feel so awful for them and can't imagine how they are feeling.\" Theo Antoniou Phillips, UEA Students' Union undergraduate education officer, said: \"This is a shocking and utterly unacceptable data breach that should never have happened.\" Jo Swo, the union's welfare, community and diversity officer, said: \"Given the university is supposed to be making mental health a priority, this is a real slap in the face to students who have sought support.\" In a statement, a UEA spokeswoman said: \"An email was mistakenly sent to 298 American Studies undergraduates this morning containing details of 42 students with extenuating circumstances. \"This clearly should not have happened and the university apologises unreservedly. The university has launched an urgent enquiry and is contacting all affected students to offer support. \"Anyone needing support should call 01603 592761. The university is informing the ICO (Information Commissioner's Office).\" The ICO has been contacted for comment.", "output": "University of East Anglia in students' personal data breach", "explanation": "University of East Anglia in students' personal data breach is the apt and relevant title for the given sentence."}, {"input": "Media reports say Stanislav Bogdanovich and Alexandra Vernigora - also a top chess player - were found with balloons containing the gas, nitrous oxide. The gas is inhaled using a balloon. Russian investigators reported the deaths, without naming the pair, and said there were no signs of foul play. Bogdanovich was a speed chess champion. Vernigora was also a professional chess player and was studying at Moscow State University. The Ukrainian sports website sport.ua says Bogdanovich was a grandmaster from Odessa who won the Ukrainian Under-18 championship and various chess awards at international tournaments. Russian chess website chess-news.ru says that in 2015 he was rated eighth in the world for speed (blitz) chess. Reports say Bogdanovich drew much criticism recently for representing Russia in an internet chess match against Ukraine, which he won. Sport.ua quotes a Facebook post from him (in Russian) about that, in which he argued that playing for Russia was good for business, that he was living as a guest in Russia and being treated well, and this was his small contribution to ending the Russia-Ukraine conflict. Nitrous oxide was first used as an anaesthetic in 1844, but is now being used as a recreational drug and has been linked to a number of deaths. It can also cause breathing difficulties, dangerously increased heart rate and burns.", "output": "Young Ukraine chess couple 'killed by laughing gas'", "explanation": "The output is the appropriate title for the given text, emphasizing the main points of the passage."}], "Negative Examples": [{"input": "Supporters followed on the radio and TV as Harrogate Town won the National League play-off final at Wembley. The result has been described as a \"superb lift\" for the spa town. Work to rip up the club's artificial pitch and replace it with grass, in keeping with league regulations, is expected to start later on Monday. Fan Brody Pattison joked that he wanted some of the artificial pitch in his back garden as a souvenir. He said: \"I can't thank the players enough, they're all heroes for this town, they're going to go down in history. \"We've come so far as a club in the last three or four years, we're a small town full of teashops and we're in the Football League.\" Another Sulphurites supporter, Jack Wilkinson, said he woke up on Monday with a bottle of champagne and a huge sign saying \"we're going to Wembley\". He said: \"As soon as they scored the first goal, that's when the tears started and they didn't stop until full-time, I'm a grown adult crying over a football match. \"It makes the early mornings going to Dover, Yeovil, Torquay all worth it.\" The Sulphurites also won the praise of what is possibly Harrogate's most famous institution, Bettys tearoom. A spokeswoman said: \"We've the kettle on and Fat Rascals (a kind of scone) in the oven. We're delighted to raise a toast to Simon Weaver and the winning Harrogate team.\" Harrogate businessman Mark Noble was lucky enough to attend the game as a guest of the club. He said: \"The lads were all so proud, the support they've had all season was with them yesterday, the flags were up. \"Yesterday was a large key opening a large door, next season we're in that room and hopefully when Covid is over, all the supporters will all be there following the team.\" Simon Cotton, who runs hotels and pubs in and around the town, said promotion was a \"superb lift\" for Harrogate after \"so many months of lockdown blues\". He said: \"Harrogate relies on visitor tourism and if more fans are travelling to see their teams then they're potentially going to stay in hotels in the town, go for a drink in the bars, have something to eat in the restaurants and buy something in the shops.\" There have been calls for an open-top bus parade, although coronavirus restrictions mean this is unlikely. Harrogate Borough mayor Stuart Martin said: \"We've got to try and think of how best we can celebrate - under normal circumstances, wouldn't it have been nice to have a civic reception for them? - but there's no way we can do that under the current climate, it's just not feasible.\" He said promotion was \"going to bring a real buzz to the town, to the district, to the county\" and would encourage more youngsters to get involved in sport. Lindsey Whitton, captain of Harrogate Town's women's team, said she hoped the club's recent success would inspire more girls to start playing football. She said: \"It's amazing, the profile of the club has just risen so much within 24 hours, not only for the men's team but it's going to have a massive impact on the women's team, the player development centre, the academy.\" Follow BBC Yorkshire on Facebook, Twitter and Instagram. Send your story ideas to yorkslincs.news@bbc.co.uk or send video here.", "output": "Fan Brody Pattison joked that he wanted some of the artificial pitch in his back garden as a souvenir.", "explanation": "This not an apt title beacause it doesn't correspond to the main idea of the text. \"Harrogate Town promotion a 'superb lift' after lockdown\" correspond to the main idea of the text and is a good title."}, {"input": "Olivia Burt, 20, died outside Missoula in Durham in February 2018. The Crown Prosecution Service (CPS) announced it had decided against pressing manslaughter charges against any people or the club. Ms Burt, from Hampshire, was in her first year reading natural sciences at Durham University. The CPS said it had also reviewed its decision not to prosecute and upheld its original view. 'Deeply disappointed' It considered charges of manslaughter by gross negligence against the individual suspects and charges of corporate manslaughter against the business. Ms Burt's parents Nigel and Paula Burt said: \"Clearly we are deeply disappointed that after such a lengthy investigation, lasting more than two-and-a-half years, this decision has been reached. \"We hope that there will now be a thorough and independent investigation into whether any health and safety offences have been committed.\" The CPS said it had considered the evidence provided by the police and judged the legal test for bringing a prosecution had not been met. A spokesman said: \"We understand how difficult this will be for Olivia's family and have provided them with a detailed explanation of the decision.\" Ms Burt, who was a member of the British sailing team, grew up in Milford-on-Sea and had been head girl of Bournemouth School for Girls. Her parents have set up a charity, Olivia Inspires, in her memory to help disadvantaged children from the New Forest area. An inquest into her death is yet to be concluded. Follow BBC North East & Cumbria on Twitter, Facebook and Instagram. Send your story ideas to northeastandcumbria@bbc.co.uk.", "output": "Fighting pandas set to join World of Warcraft", "explanation": "The output is not at all relevant to the given text. A good title for this text can be \"Olivia Burt's family 'disappointed' with CPS decision\"."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["News"], "Instance": {"id": "task1356-018e7314264c4d2fb6b980845687ffd6", "input": "By Paul BurnellBBC News In a cafe in Sloane Square, the screenwriter and Conservative peer Julian Fellowes is contemplating his most notorious ancestor. The creator of the hit ITV drama Downton Abbey is considering how, as a screenwriter used to drawing dramatic characters, he would assess the personality of William Hulton. \"Most characters have shades of grey because, on the whole, I think that in life people don't tend to be all evil or all good,\" Fellowes says. \"But actually William Hulton was pushing it for 'all evil'... I don't think he had much to redeem him.\" The Oscar-winning writer is Hulton's great-great-great grandson - but this is not a source of pride. He was, he says, a \"cruel and horrible man\". It was Hulton who, as a magistrate in north-west England, gave the notorious order for troops to violently disperse a peaceful, pro-democracy protest in the centre of the UK's first industrial city. Screenwriters make much of a character's motives, so what does Fellowes think drove Hulton, who was born into a family of wealthy landowners? \"He was clearly a sort of hysteric,\" he says. \"He was clearly terrified of any overthrow of the established social order.\" Two hundred years ago, working-class people in Manchester and other industrial towns in the north of England were becoming increasingly vocal in their demands for political reform. They were angry about the fact that most of the population could not vote, that corruption was rife, and that urban areas were grossly underrepresented in Parliament. At least 50,000 people arrived at St Peter's Fields on 16 August 1819 to hear radical speaker Henry Hunt campaign for parliamentary reform. At this time, Manchester had no police force so the Manchester Yeomanry was sent in to prevent any disturbances. When Hunt began to speak the army tried to arrest him, and attacked anybody who got in its way. At least 11 people were killed and 400 injured. The events soon became notorious in the press, where they were dubbed Peterloo, an ironic reference to the Battle of Waterloo that had taken place four years previously. \"It was only the barest of beginnings for any kind of workers' movement,\" says Fellowes. \"But Hulton immediately went into some kind of overdrive, attacking a group that included a group of many women and many children - a lot of whom hadn't done anything.\" He describes Hulton's heavy-handed response as a total misreading of the situation. \"Instead of lining up across the field and reading some sort of 'go home!' message, which clearly would have been the reasonable thing to do, he sent the yeomanry to a crowd who could not at once disperse. \"They were seen by him to be resisting but they were unarmed - they weren't resisting them with weapons.\" The film Peterloo, which goes on general release on 2 November, is directed by Salford-born Mike Leigh, who is known for his gritty tales of working-class life. \"Although I don't think Mike Leigh and I are as one politically... I certainly agree with him about who were the bad guys,\" said Fellowes. Seven years before Peterloo, as a justice of the peace, Hulton had already sentenced four Luddites to death for setting fire to a weaving mill in Westhoughton, near Bolton. One of those hanged was a 12-year-old boy. While history is full of monsters, historians tend to temper criticism when actions are in keeping with the standards of the time. But, in Hulton's case, even this does not save his reputation. \"They thought it was cruel and unnecessary and inhuman,\" Fellowes says. \"And so, in a sense, he was already an offender before the demonstration at St Peter's Field had ever happened. \"I feel extremely sorry for the men, women and children who were cut down at Peterloo. \"I think they were doing no more than making clear to those who would listen - the writing was on the wall, workers were bound to have some rights. \"What people like Hulton were trying to do was to fight history, and to fight the inevitable.\" Among those on the receiving end of the cavalry charge was Mary Heys, who was pregnant with her sixth child. She had joined the hordes gathered near her ramshackle home in Oxford Street, which nearly two centuries later is occupied by a McDonald's restaurant. Heys's story has been researched by her five times great-granddaughter Denise Southworth. The 57-year-old said Heys was one of the massacre's \"forgotten victims\". Indeed, estimates of the final death toll vary widely and the true number will never be known. \"She was trampled by a horse,\" said Ms Southworth. \"Why would a woman in her 40s who was pregnant want to take part in a riot?\" The day after Heys was injured, she began having fits. Four months later she gave birth to a premature baby, Henry. \"[Mary] died just before Christmas - because she didn't die straight away, she wasn't counted among the dead,\" said Ms Southworth, who is Manchester born and bred. \"We gave more significance in my school in Manchester to the Battle of Waterloo than to Peterloo. \"I think it has been overlooked even in Manchester. \"I knew nothing about it - in my history books they were too busy talking about Napoleon and Waterloo.\" Ms Southworth's sense of outrage has prompted her to join the Peterloo Memorial Campaign, which has the backing of Peterloo star Maxine Peake. It is fighting for a permanent memorial to those who died, rather than just the small plaque which currently sits on the wall of the Radisson Hotel. Ms Southworth said: \"You look round here - the middle of Manchester - and see all these beautiful, fabulous, glass, expensive buildings - do people know what happened here 200 years ago? \"Do they know about how the ordinary working people came for a peaceful demonstration and were butchered? \"We are always told about Manchester's achievements, but let's not forget the spot where people were killed for trying get a decent standard of living. \"We owe it as educated people to remember those who didn't have a vote and did not have any rights.\"", "output": ["Peterloo: The man who ordered a massacre"]}, "Instance License": ["CC BY-SA 4.0"], "prediction": "The writer is considering how, as a screenwriter, he would assess the personality of his most notorious ancestor"}
+{"id": "task1356-cbfbab5557504cd98b3e5696d4402667", "Task": "task1356_xlsum_title_generation", "Contributors": "['Krishna Sree G']", "Source": ["xlsum"], "URL": ["https://arxiv.org/abs/2106.13822"], "Categories": ["Title Generation"], "Reasoning": [], "Definition": ["Generate an appropriate title for the given text. The generated title must be short and include the main topic of the text. The preferred titles are under fifteen words."], "Positive Examples": [{"input": "But Eluned Morgan conceded that it would be \"difficult for us to stop\" from a legal point of view. Her comments were criticised by a Labour AM. Alun Davies said threatening legal action \"sounds like the last breath before you're thrown out of the pub\". Mr Davies said he was not convinced the Welsh Government would \"have a leg to stand on\" in trying to shape international trade deals after Brexit. Following Donald Trump's comments during last week's trade visit that the NHS would be \"on the table\" in any future trade talks between the UK and the USA, Eluned Morgan said there was \"absolutely no prospect whatsoever of us allowing the Welsh NHS to be part of any negotiation.\" The US President then rowed back on his initial comments following criticism from a number of MPs. Asked about her response to President Trump's remarks as she gave evidence to the Assembly's Brexit committee on Monday, Ms Morgan said \"legally, it would be difficult for us to stop because we don't have a veto over trade\". \"Politically, I think it's extremely unlikely to happen,\" the international relations and the Welsh language minister said. \"They [the UK Government] should not be concluding any trade agreements without consulting us where we have the power.\" Ms Morgan explained that UK and Welsh government officials are working on an agreement or 'concordat' for how future trade deals are negotiated. During a robust exchange, the Labour AM Alun Davies said: \"I want something which is in law to which I can hold you to account and which colleagues in Westminster can hold the UK Government to account. \"The argument we'll make life difficult for them, it sounds alright on the street, but it's not the reality of intergovernmental relations.\" \"The United Kingdom has to find a way of functioning. \"At the moment, your answers aren't giving me any confidence that there is that structure in place because, if the Welsh Government's argument is, 'we'll see you in court', it's not a very impressive argument either for the continuation of the structure of United Kingdom as a state or the commitment of the government within the United Kingdom to actually work together,\" he added. Responding to the criticism, Ms Morgan said: \"Is the current intergovernmental structure adequate? \"Absolutely not... and it's not just in relation to trade, it's in relation to almost every aspect of government policy. So, that infrastructure needs to be built.\"", "output": "NHS Wales: Court action if trade deals affect service?", "explanation": "The output phrase is the appropriate title for the given text and it highlights the essence of the passage."}, {"input": "By Jon Welch and Paul MoseleyBBC News Details of health problems, family bereavements and personal issues were sent by the University of East Anglia (UEA) in Norwich to 298 students. Megan Baynes, 23, said she felt \"sick and horrified\" when she realised her details had been shared. The UEA apologised \"unreservedly\" and said an inquiry had begun. The email contained a spreadsheet listing 172 names and details extenuating circumstances in which extensions and other academic concessions were granted to 42 students. 'Felt sick' It was sent to nearly 300 undergraduates, including Ms Baynes, a former editor of student newspaper Concrete. She is currently awaiting the results of her American Literature and Creative Writing degree, and had been granted extensions for coursework because of an illness suffered by a family member. \"I felt sick at seeing my personal situation written in a spreadsheet, and then seemingly sent to everyone on my course,\" she said. \"My situation was not the worst on there but there are some on there that are so personal. There are people I know and I feel so awful for them and can't imagine how they are feeling.\" Theo Antoniou Phillips, UEA Students' Union undergraduate education officer, said: \"This is a shocking and utterly unacceptable data breach that should never have happened.\" Jo Swo, the union's welfare, community and diversity officer, said: \"Given the university is supposed to be making mental health a priority, this is a real slap in the face to students who have sought support.\" In a statement, a UEA spokeswoman said: \"An email was mistakenly sent to 298 American Studies undergraduates this morning containing details of 42 students with extenuating circumstances. \"This clearly should not have happened and the university apologises unreservedly. The university has launched an urgent enquiry and is contacting all affected students to offer support. \"Anyone needing support should call 01603 592761. The university is informing the ICO (Information Commissioner's Office).\" The ICO has been contacted for comment.", "output": "University of East Anglia in students' personal data breach", "explanation": "University of East Anglia in students' personal data breach is the apt and relevant title for the given sentence."}, {"input": "Media reports say Stanislav Bogdanovich and Alexandra Vernigora - also a top chess player - were found with balloons containing the gas, nitrous oxide. The gas is inhaled using a balloon. Russian investigators reported the deaths, without naming the pair, and said there were no signs of foul play. Bogdanovich was a speed chess champion. Vernigora was also a professional chess player and was studying at Moscow State University. The Ukrainian sports website sport.ua says Bogdanovich was a grandmaster from Odessa who won the Ukrainian Under-18 championship and various chess awards at international tournaments. Russian chess website chess-news.ru says that in 2015 he was rated eighth in the world for speed (blitz) chess. Reports say Bogdanovich drew much criticism recently for representing Russia in an internet chess match against Ukraine, which he won. Sport.ua quotes a Facebook post from him (in Russian) about that, in which he argued that playing for Russia was good for business, that he was living as a guest in Russia and being treated well, and this was his small contribution to ending the Russia-Ukraine conflict. Nitrous oxide was first used as an anaesthetic in 1844, but is now being used as a recreational drug and has been linked to a number of deaths. It can also cause breathing difficulties, dangerously increased heart rate and burns.", "output": "Young Ukraine chess couple 'killed by laughing gas'", "explanation": "The output is the appropriate title for the given text, emphasizing the main points of the passage."}], "Negative Examples": [{"input": "Supporters followed on the radio and TV as Harrogate Town won the National League play-off final at Wembley. The result has been described as a \"superb lift\" for the spa town. Work to rip up the club's artificial pitch and replace it with grass, in keeping with league regulations, is expected to start later on Monday. Fan Brody Pattison joked that he wanted some of the artificial pitch in his back garden as a souvenir. He said: \"I can't thank the players enough, they're all heroes for this town, they're going to go down in history. \"We've come so far as a club in the last three or four years, we're a small town full of teashops and we're in the Football League.\" Another Sulphurites supporter, Jack Wilkinson, said he woke up on Monday with a bottle of champagne and a huge sign saying \"we're going to Wembley\". He said: \"As soon as they scored the first goal, that's when the tears started and they didn't stop until full-time, I'm a grown adult crying over a football match. \"It makes the early mornings going to Dover, Yeovil, Torquay all worth it.\" The Sulphurites also won the praise of what is possibly Harrogate's most famous institution, Bettys tearoom. A spokeswoman said: \"We've the kettle on and Fat Rascals (a kind of scone) in the oven. We're delighted to raise a toast to Simon Weaver and the winning Harrogate team.\" Harrogate businessman Mark Noble was lucky enough to attend the game as a guest of the club. He said: \"The lads were all so proud, the support they've had all season was with them yesterday, the flags were up. \"Yesterday was a large key opening a large door, next season we're in that room and hopefully when Covid is over, all the supporters will all be there following the team.\" Simon Cotton, who runs hotels and pubs in and around the town, said promotion was a \"superb lift\" for Harrogate after \"so many months of lockdown blues\". He said: \"Harrogate relies on visitor tourism and if more fans are travelling to see their teams then they're potentially going to stay in hotels in the town, go for a drink in the bars, have something to eat in the restaurants and buy something in the shops.\" There have been calls for an open-top bus parade, although coronavirus restrictions mean this is unlikely. Harrogate Borough mayor Stuart Martin said: \"We've got to try and think of how best we can celebrate - under normal circumstances, wouldn't it have been nice to have a civic reception for them? - but there's no way we can do that under the current climate, it's just not feasible.\" He said promotion was \"going to bring a real buzz to the town, to the district, to the county\" and would encourage more youngsters to get involved in sport. Lindsey Whitton, captain of Harrogate Town's women's team, said she hoped the club's recent success would inspire more girls to start playing football. She said: \"It's amazing, the profile of the club has just risen so much within 24 hours, not only for the men's team but it's going to have a massive impact on the women's team, the player development centre, the academy.\" Follow BBC Yorkshire on Facebook, Twitter and Instagram. Send your story ideas to yorkslincs.news@bbc.co.uk or send video here.", "output": "Fan Brody Pattison joked that he wanted some of the artificial pitch in his back garden as a souvenir.", "explanation": "This not an apt title beacause it doesn't correspond to the main idea of the text. \"Harrogate Town promotion a 'superb lift' after lockdown\" correspond to the main idea of the text and is a good title."}, {"input": "Olivia Burt, 20, died outside Missoula in Durham in February 2018. The Crown Prosecution Service (CPS) announced it had decided against pressing manslaughter charges against any people or the club. Ms Burt, from Hampshire, was in her first year reading natural sciences at Durham University. The CPS said it had also reviewed its decision not to prosecute and upheld its original view. 'Deeply disappointed' It considered charges of manslaughter by gross negligence against the individual suspects and charges of corporate manslaughter against the business. Ms Burt's parents Nigel and Paula Burt said: \"Clearly we are deeply disappointed that after such a lengthy investigation, lasting more than two-and-a-half years, this decision has been reached. \"We hope that there will now be a thorough and independent investigation into whether any health and safety offences have been committed.\" The CPS said it had considered the evidence provided by the police and judged the legal test for bringing a prosecution had not been met. A spokesman said: \"We understand how difficult this will be for Olivia's family and have provided them with a detailed explanation of the decision.\" Ms Burt, who was a member of the British sailing team, grew up in Milford-on-Sea and had been head girl of Bournemouth School for Girls. Her parents have set up a charity, Olivia Inspires, in her memory to help disadvantaged children from the New Forest area. An inquest into her death is yet to be concluded. Follow BBC North East & Cumbria on Twitter, Facebook and Instagram. Send your story ideas to northeastandcumbria@bbc.co.uk.", "output": "Fighting pandas set to join World of Warcraft", "explanation": "The output is not at all relevant to the given text. A good title for this text can be \"Olivia Burt's family 'disappointed' with CPS decision\"."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["News"], "Instance": {"id": "task1356-cbfbab5557504cd98b3e5696d4402667", "input": "By Robbie MeredithBBC News NI Education Correspondent That is according to an email to schools from the Department of Education (DE). The department said evidence from the Public Health Authority's (PHA) contact tracing service suggested too many children and staff without symptoms were getting tested. Concerns have already been expressed about capacity in the testing system. In an email accompanying revised guidance for schools, DE said school staff or pupils should only get a test when they were clearly symptomatic. \"PHA have asked us to emphasise to schools that pupils and staff must only be advised to seek a Covid-19 test when they are symptomatic of the virus - that is a new continuous cough, a fever or a new loss of taste and/or smell,\" said the department. \"Early evidence from the contact tracing service is that available testing capacity is being utilised to test many children and school staff who are showing no symptoms and in doing so make it more challenging for genuinely symptomatic individuals to access a test.\" Guidance 'confusion' The department also provided new guidance to schools on when pupils have to self-isolate if one of their classmates has Covid-19. That comes after previous guidance issued last Thursday caused confusion for many principals by suggesting that class bubbles should be sent home if one pupil in the class had symptoms of the virus, such as a persistent cough. \"In practical terms this would have meant that anytime a child got COVID-19 symptoms, for most primary schools and many post primary schools, the entire bubble would have been sent home,\" DE has now said. \"PHA has advised the correct position is that only when a positive case has been identified in a symptomatic child, young person or member of staff do schools need to consider self-isolating close contacts of that individual.\" \"Close contacts must stay in isolation for the full 14 day period.\" \"They should not return to school before the 14 day isolation period as they may still be incubating the virus - regardless of a lack of symptoms.\" While many schools in Northern Ireland have sent staff or groups of pupils home to self-isolate after positive cases, some schools have closed entirely for a number of days. On Monday, St Comgall's Primary in Bangor announced it was closing for 14 days after several cases of coronavirus were identified, although the school said on Tuesday it would reopen to most classes on Friday.", "output": ["Schools: 'Too many' children and staff without symptoms getting tested"]}, "Instance License": ["CC BY-SA 4.0"], "prediction": "The Department of Education has said that schools should only be advised to seek a Covid-19 test when they are clearly symptomatic of the virus - that is a new continuous cough, a fever or a new loss of taste and/or smell."}
+{"id": "task1356-6c22ac3299b64bda8184fdb2139c99a5", "Task": "task1356_xlsum_title_generation", "Contributors": "['Krishna Sree G']", "Source": ["xlsum"], "URL": ["https://arxiv.org/abs/2106.13822"], "Categories": ["Title Generation"], "Reasoning": [], "Definition": ["Generate an appropriate title for the given text. The generated title must be short and include the main topic of the text. The preferred titles are under fifteen words."], "Positive Examples": [{"input": "But Eluned Morgan conceded that it would be \"difficult for us to stop\" from a legal point of view. Her comments were criticised by a Labour AM. Alun Davies said threatening legal action \"sounds like the last breath before you're thrown out of the pub\". Mr Davies said he was not convinced the Welsh Government would \"have a leg to stand on\" in trying to shape international trade deals after Brexit. Following Donald Trump's comments during last week's trade visit that the NHS would be \"on the table\" in any future trade talks between the UK and the USA, Eluned Morgan said there was \"absolutely no prospect whatsoever of us allowing the Welsh NHS to be part of any negotiation.\" The US President then rowed back on his initial comments following criticism from a number of MPs. Asked about her response to President Trump's remarks as she gave evidence to the Assembly's Brexit committee on Monday, Ms Morgan said \"legally, it would be difficult for us to stop because we don't have a veto over trade\". \"Politically, I think it's extremely unlikely to happen,\" the international relations and the Welsh language minister said. \"They [the UK Government] should not be concluding any trade agreements without consulting us where we have the power.\" Ms Morgan explained that UK and Welsh government officials are working on an agreement or 'concordat' for how future trade deals are negotiated. During a robust exchange, the Labour AM Alun Davies said: \"I want something which is in law to which I can hold you to account and which colleagues in Westminster can hold the UK Government to account. \"The argument we'll make life difficult for them, it sounds alright on the street, but it's not the reality of intergovernmental relations.\" \"The United Kingdom has to find a way of functioning. \"At the moment, your answers aren't giving me any confidence that there is that structure in place because, if the Welsh Government's argument is, 'we'll see you in court', it's not a very impressive argument either for the continuation of the structure of United Kingdom as a state or the commitment of the government within the United Kingdom to actually work together,\" he added. Responding to the criticism, Ms Morgan said: \"Is the current intergovernmental structure adequate? \"Absolutely not... and it's not just in relation to trade, it's in relation to almost every aspect of government policy. So, that infrastructure needs to be built.\"", "output": "NHS Wales: Court action if trade deals affect service?", "explanation": "The output phrase is the appropriate title for the given text and it highlights the essence of the passage."}, {"input": "By Jon Welch and Paul MoseleyBBC News Details of health problems, family bereavements and personal issues were sent by the University of East Anglia (UEA) in Norwich to 298 students. Megan Baynes, 23, said she felt \"sick and horrified\" when she realised her details had been shared. The UEA apologised \"unreservedly\" and said an inquiry had begun. The email contained a spreadsheet listing 172 names and details extenuating circumstances in which extensions and other academic concessions were granted to 42 students. 'Felt sick' It was sent to nearly 300 undergraduates, including Ms Baynes, a former editor of student newspaper Concrete. She is currently awaiting the results of her American Literature and Creative Writing degree, and had been granted extensions for coursework because of an illness suffered by a family member. \"I felt sick at seeing my personal situation written in a spreadsheet, and then seemingly sent to everyone on my course,\" she said. \"My situation was not the worst on there but there are some on there that are so personal. There are people I know and I feel so awful for them and can't imagine how they are feeling.\" Theo Antoniou Phillips, UEA Students' Union undergraduate education officer, said: \"This is a shocking and utterly unacceptable data breach that should never have happened.\" Jo Swo, the union's welfare, community and diversity officer, said: \"Given the university is supposed to be making mental health a priority, this is a real slap in the face to students who have sought support.\" In a statement, a UEA spokeswoman said: \"An email was mistakenly sent to 298 American Studies undergraduates this morning containing details of 42 students with extenuating circumstances. \"This clearly should not have happened and the university apologises unreservedly. The university has launched an urgent enquiry and is contacting all affected students to offer support. \"Anyone needing support should call 01603 592761. The university is informing the ICO (Information Commissioner's Office).\" The ICO has been contacted for comment.", "output": "University of East Anglia in students' personal data breach", "explanation": "University of East Anglia in students' personal data breach is the apt and relevant title for the given sentence."}, {"input": "Media reports say Stanislav Bogdanovich and Alexandra Vernigora - also a top chess player - were found with balloons containing the gas, nitrous oxide. The gas is inhaled using a balloon. Russian investigators reported the deaths, without naming the pair, and said there were no signs of foul play. Bogdanovich was a speed chess champion. Vernigora was also a professional chess player and was studying at Moscow State University. The Ukrainian sports website sport.ua says Bogdanovich was a grandmaster from Odessa who won the Ukrainian Under-18 championship and various chess awards at international tournaments. Russian chess website chess-news.ru says that in 2015 he was rated eighth in the world for speed (blitz) chess. Reports say Bogdanovich drew much criticism recently for representing Russia in an internet chess match against Ukraine, which he won. Sport.ua quotes a Facebook post from him (in Russian) about that, in which he argued that playing for Russia was good for business, that he was living as a guest in Russia and being treated well, and this was his small contribution to ending the Russia-Ukraine conflict. Nitrous oxide was first used as an anaesthetic in 1844, but is now being used as a recreational drug and has been linked to a number of deaths. It can also cause breathing difficulties, dangerously increased heart rate and burns.", "output": "Young Ukraine chess couple 'killed by laughing gas'", "explanation": "The output is the appropriate title for the given text, emphasizing the main points of the passage."}], "Negative Examples": [{"input": "Supporters followed on the radio and TV as Harrogate Town won the National League play-off final at Wembley. The result has been described as a \"superb lift\" for the spa town. Work to rip up the club's artificial pitch and replace it with grass, in keeping with league regulations, is expected to start later on Monday. Fan Brody Pattison joked that he wanted some of the artificial pitch in his back garden as a souvenir. He said: \"I can't thank the players enough, they're all heroes for this town, they're going to go down in history. \"We've come so far as a club in the last three or four years, we're a small town full of teashops and we're in the Football League.\" Another Sulphurites supporter, Jack Wilkinson, said he woke up on Monday with a bottle of champagne and a huge sign saying \"we're going to Wembley\". He said: \"As soon as they scored the first goal, that's when the tears started and they didn't stop until full-time, I'm a grown adult crying over a football match. \"It makes the early mornings going to Dover, Yeovil, Torquay all worth it.\" The Sulphurites also won the praise of what is possibly Harrogate's most famous institution, Bettys tearoom. A spokeswoman said: \"We've the kettle on and Fat Rascals (a kind of scone) in the oven. We're delighted to raise a toast to Simon Weaver and the winning Harrogate team.\" Harrogate businessman Mark Noble was lucky enough to attend the game as a guest of the club. He said: \"The lads were all so proud, the support they've had all season was with them yesterday, the flags were up. \"Yesterday was a large key opening a large door, next season we're in that room and hopefully when Covid is over, all the supporters will all be there following the team.\" Simon Cotton, who runs hotels and pubs in and around the town, said promotion was a \"superb lift\" for Harrogate after \"so many months of lockdown blues\". He said: \"Harrogate relies on visitor tourism and if more fans are travelling to see their teams then they're potentially going to stay in hotels in the town, go for a drink in the bars, have something to eat in the restaurants and buy something in the shops.\" There have been calls for an open-top bus parade, although coronavirus restrictions mean this is unlikely. Harrogate Borough mayor Stuart Martin said: \"We've got to try and think of how best we can celebrate - under normal circumstances, wouldn't it have been nice to have a civic reception for them? - but there's no way we can do that under the current climate, it's just not feasible.\" He said promotion was \"going to bring a real buzz to the town, to the district, to the county\" and would encourage more youngsters to get involved in sport. Lindsey Whitton, captain of Harrogate Town's women's team, said she hoped the club's recent success would inspire more girls to start playing football. She said: \"It's amazing, the profile of the club has just risen so much within 24 hours, not only for the men's team but it's going to have a massive impact on the women's team, the player development centre, the academy.\" Follow BBC Yorkshire on Facebook, Twitter and Instagram. Send your story ideas to yorkslincs.news@bbc.co.uk or send video here.", "output": "Fan Brody Pattison joked that he wanted some of the artificial pitch in his back garden as a souvenir.", "explanation": "This not an apt title beacause it doesn't correspond to the main idea of the text. \"Harrogate Town promotion a 'superb lift' after lockdown\" correspond to the main idea of the text and is a good title."}, {"input": "Olivia Burt, 20, died outside Missoula in Durham in February 2018. The Crown Prosecution Service (CPS) announced it had decided against pressing manslaughter charges against any people or the club. Ms Burt, from Hampshire, was in her first year reading natural sciences at Durham University. The CPS said it had also reviewed its decision not to prosecute and upheld its original view. 'Deeply disappointed' It considered charges of manslaughter by gross negligence against the individual suspects and charges of corporate manslaughter against the business. Ms Burt's parents Nigel and Paula Burt said: \"Clearly we are deeply disappointed that after such a lengthy investigation, lasting more than two-and-a-half years, this decision has been reached. \"We hope that there will now be a thorough and independent investigation into whether any health and safety offences have been committed.\" The CPS said it had considered the evidence provided by the police and judged the legal test for bringing a prosecution had not been met. A spokesman said: \"We understand how difficult this will be for Olivia's family and have provided them with a detailed explanation of the decision.\" Ms Burt, who was a member of the British sailing team, grew up in Milford-on-Sea and had been head girl of Bournemouth School for Girls. Her parents have set up a charity, Olivia Inspires, in her memory to help disadvantaged children from the New Forest area. An inquest into her death is yet to be concluded. Follow BBC North East & Cumbria on Twitter, Facebook and Instagram. Send your story ideas to northeastandcumbria@bbc.co.uk.", "output": "Fighting pandas set to join World of Warcraft", "explanation": "The output is not at all relevant to the given text. A good title for this text can be \"Olivia Burt's family 'disappointed' with CPS decision\"."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["News"], "Instance": {"id": "task1356-6c22ac3299b64bda8184fdb2139c99a5", "input": "\"They've got to understand that they've become the winner and then the real work starts,\" says Louis Walsh. Ben Haenow, Fleur East and Andrea Faustini are all hoping to be crowned the X Factor winner. They'll sing their favourite song of the series on Saturday's show and perform their celebrity duets. \"The competition's one thing. You have themes, you have all the different obstacles and they grow during that process,\" Cheryl Fernandez-Versini told Newsbeat. \"But, afterwards it's about being who you are as an artist in this current market which is extremely hard right now,\" she added. Ed Sheeran and Meghan Trainor will also perform on the show tonight and will no doubt reveal some more pearl's of wisdom for the contestants. After the excitement of releasing their debut single and possibly making the Christmas number one spot what happens to the winner's career is not by any means for certain. Whether they fade into pop oblivion or become a star with long-term staying power is all down to hard work and a little bit of luck says Dermot O'Leary. \"The stars have got to align. I always tell the contestants 'When you leave here the hard work starts and that's the rest of your career,'\" he says. Past winners have gone on to varying degrees of success. Remember series two winner, Shayne Ward? Or series four winner, Leon Jackson? What about series seven's Matt Cardle? Arguably the winner who has had the most success is Leona Lewis. She made it big both sides of the Atlantic. Is their success or lack of it down to hard work or hard luck? Who knows, but Dermot's biggest bit of advice for the winner is: \"Enjoy it. Enjoy the next nine months.\" \"Get your head down, work hard and make sure that the album you want to make is the album you make and work with the people you want to make it with,\" he says. Louis also believes a great record deal and great songs help. Naturally. But he also agrees: \"You need a lot of hard work and a little bit of luck.\" Follow @BBCNewsbeat on Twitter and Radio1Newsbeat on YouTube", "output": ["X Factor winner told: The hard work starts now"]}, "Instance License": ["CC BY-SA 4.0"], "prediction": "The X Factor winner says: \"It's not about the competition, it's about the real work.\""}
+{"id": "task1356-e244ea58d7c64228916fa6f84477107c", "Task": "task1356_xlsum_title_generation", "Contributors": "['Krishna Sree G']", "Source": ["xlsum"], "URL": ["https://arxiv.org/abs/2106.13822"], "Categories": ["Title Generation"], "Reasoning": [], "Definition": ["Generate an appropriate title for the given text. The generated title must be short and include the main topic of the text. The preferred titles are under fifteen words."], "Positive Examples": [{"input": "But Eluned Morgan conceded that it would be \"difficult for us to stop\" from a legal point of view. Her comments were criticised by a Labour AM. Alun Davies said threatening legal action \"sounds like the last breath before you're thrown out of the pub\". Mr Davies said he was not convinced the Welsh Government would \"have a leg to stand on\" in trying to shape international trade deals after Brexit. Following Donald Trump's comments during last week's trade visit that the NHS would be \"on the table\" in any future trade talks between the UK and the USA, Eluned Morgan said there was \"absolutely no prospect whatsoever of us allowing the Welsh NHS to be part of any negotiation.\" The US President then rowed back on his initial comments following criticism from a number of MPs. Asked about her response to President Trump's remarks as she gave evidence to the Assembly's Brexit committee on Monday, Ms Morgan said \"legally, it would be difficult for us to stop because we don't have a veto over trade\". \"Politically, I think it's extremely unlikely to happen,\" the international relations and the Welsh language minister said. \"They [the UK Government] should not be concluding any trade agreements without consulting us where we have the power.\" Ms Morgan explained that UK and Welsh government officials are working on an agreement or 'concordat' for how future trade deals are negotiated. During a robust exchange, the Labour AM Alun Davies said: \"I want something which is in law to which I can hold you to account and which colleagues in Westminster can hold the UK Government to account. \"The argument we'll make life difficult for them, it sounds alright on the street, but it's not the reality of intergovernmental relations.\" \"The United Kingdom has to find a way of functioning. \"At the moment, your answers aren't giving me any confidence that there is that structure in place because, if the Welsh Government's argument is, 'we'll see you in court', it's not a very impressive argument either for the continuation of the structure of United Kingdom as a state or the commitment of the government within the United Kingdom to actually work together,\" he added. Responding to the criticism, Ms Morgan said: \"Is the current intergovernmental structure adequate? \"Absolutely not... and it's not just in relation to trade, it's in relation to almost every aspect of government policy. So, that infrastructure needs to be built.\"", "output": "NHS Wales: Court action if trade deals affect service?", "explanation": "The output phrase is the appropriate title for the given text and it highlights the essence of the passage."}, {"input": "By Jon Welch and Paul MoseleyBBC News Details of health problems, family bereavements and personal issues were sent by the University of East Anglia (UEA) in Norwich to 298 students. Megan Baynes, 23, said she felt \"sick and horrified\" when she realised her details had been shared. The UEA apologised \"unreservedly\" and said an inquiry had begun. The email contained a spreadsheet listing 172 names and details extenuating circumstances in which extensions and other academic concessions were granted to 42 students. 'Felt sick' It was sent to nearly 300 undergraduates, including Ms Baynes, a former editor of student newspaper Concrete. She is currently awaiting the results of her American Literature and Creative Writing degree, and had been granted extensions for coursework because of an illness suffered by a family member. \"I felt sick at seeing my personal situation written in a spreadsheet, and then seemingly sent to everyone on my course,\" she said. \"My situation was not the worst on there but there are some on there that are so personal. There are people I know and I feel so awful for them and can't imagine how they are feeling.\" Theo Antoniou Phillips, UEA Students' Union undergraduate education officer, said: \"This is a shocking and utterly unacceptable data breach that should never have happened.\" Jo Swo, the union's welfare, community and diversity officer, said: \"Given the university is supposed to be making mental health a priority, this is a real slap in the face to students who have sought support.\" In a statement, a UEA spokeswoman said: \"An email was mistakenly sent to 298 American Studies undergraduates this morning containing details of 42 students with extenuating circumstances. \"This clearly should not have happened and the university apologises unreservedly. The university has launched an urgent enquiry and is contacting all affected students to offer support. \"Anyone needing support should call 01603 592761. The university is informing the ICO (Information Commissioner's Office).\" The ICO has been contacted for comment.", "output": "University of East Anglia in students' personal data breach", "explanation": "University of East Anglia in students' personal data breach is the apt and relevant title for the given sentence."}, {"input": "Media reports say Stanislav Bogdanovich and Alexandra Vernigora - also a top chess player - were found with balloons containing the gas, nitrous oxide. The gas is inhaled using a balloon. Russian investigators reported the deaths, without naming the pair, and said there were no signs of foul play. Bogdanovich was a speed chess champion. Vernigora was also a professional chess player and was studying at Moscow State University. The Ukrainian sports website sport.ua says Bogdanovich was a grandmaster from Odessa who won the Ukrainian Under-18 championship and various chess awards at international tournaments. Russian chess website chess-news.ru says that in 2015 he was rated eighth in the world for speed (blitz) chess. Reports say Bogdanovich drew much criticism recently for representing Russia in an internet chess match against Ukraine, which he won. Sport.ua quotes a Facebook post from him (in Russian) about that, in which he argued that playing for Russia was good for business, that he was living as a guest in Russia and being treated well, and this was his small contribution to ending the Russia-Ukraine conflict. Nitrous oxide was first used as an anaesthetic in 1844, but is now being used as a recreational drug and has been linked to a number of deaths. It can also cause breathing difficulties, dangerously increased heart rate and burns.", "output": "Young Ukraine chess couple 'killed by laughing gas'", "explanation": "The output is the appropriate title for the given text, emphasizing the main points of the passage."}], "Negative Examples": [{"input": "Supporters followed on the radio and TV as Harrogate Town won the National League play-off final at Wembley. The result has been described as a \"superb lift\" for the spa town. Work to rip up the club's artificial pitch and replace it with grass, in keeping with league regulations, is expected to start later on Monday. Fan Brody Pattison joked that he wanted some of the artificial pitch in his back garden as a souvenir. He said: \"I can't thank the players enough, they're all heroes for this town, they're going to go down in history. \"We've come so far as a club in the last three or four years, we're a small town full of teashops and we're in the Football League.\" Another Sulphurites supporter, Jack Wilkinson, said he woke up on Monday with a bottle of champagne and a huge sign saying \"we're going to Wembley\". He said: \"As soon as they scored the first goal, that's when the tears started and they didn't stop until full-time, I'm a grown adult crying over a football match. \"It makes the early mornings going to Dover, Yeovil, Torquay all worth it.\" The Sulphurites also won the praise of what is possibly Harrogate's most famous institution, Bettys tearoom. A spokeswoman said: \"We've the kettle on and Fat Rascals (a kind of scone) in the oven. We're delighted to raise a toast to Simon Weaver and the winning Harrogate team.\" Harrogate businessman Mark Noble was lucky enough to attend the game as a guest of the club. He said: \"The lads were all so proud, the support they've had all season was with them yesterday, the flags were up. \"Yesterday was a large key opening a large door, next season we're in that room and hopefully when Covid is over, all the supporters will all be there following the team.\" Simon Cotton, who runs hotels and pubs in and around the town, said promotion was a \"superb lift\" for Harrogate after \"so many months of lockdown blues\". He said: \"Harrogate relies on visitor tourism and if more fans are travelling to see their teams then they're potentially going to stay in hotels in the town, go for a drink in the bars, have something to eat in the restaurants and buy something in the shops.\" There have been calls for an open-top bus parade, although coronavirus restrictions mean this is unlikely. Harrogate Borough mayor Stuart Martin said: \"We've got to try and think of how best we can celebrate - under normal circumstances, wouldn't it have been nice to have a civic reception for them? - but there's no way we can do that under the current climate, it's just not feasible.\" He said promotion was \"going to bring a real buzz to the town, to the district, to the county\" and would encourage more youngsters to get involved in sport. Lindsey Whitton, captain of Harrogate Town's women's team, said she hoped the club's recent success would inspire more girls to start playing football. She said: \"It's amazing, the profile of the club has just risen so much within 24 hours, not only for the men's team but it's going to have a massive impact on the women's team, the player development centre, the academy.\" Follow BBC Yorkshire on Facebook, Twitter and Instagram. Send your story ideas to yorkslincs.news@bbc.co.uk or send video here.", "output": "Fan Brody Pattison joked that he wanted some of the artificial pitch in his back garden as a souvenir.", "explanation": "This not an apt title beacause it doesn't correspond to the main idea of the text. \"Harrogate Town promotion a 'superb lift' after lockdown\" correspond to the main idea of the text and is a good title."}, {"input": "Olivia Burt, 20, died outside Missoula in Durham in February 2018. The Crown Prosecution Service (CPS) announced it had decided against pressing manslaughter charges against any people or the club. Ms Burt, from Hampshire, was in her first year reading natural sciences at Durham University. The CPS said it had also reviewed its decision not to prosecute and upheld its original view. 'Deeply disappointed' It considered charges of manslaughter by gross negligence against the individual suspects and charges of corporate manslaughter against the business. Ms Burt's parents Nigel and Paula Burt said: \"Clearly we are deeply disappointed that after such a lengthy investigation, lasting more than two-and-a-half years, this decision has been reached. \"We hope that there will now be a thorough and independent investigation into whether any health and safety offences have been committed.\" The CPS said it had considered the evidence provided by the police and judged the legal test for bringing a prosecution had not been met. A spokesman said: \"We understand how difficult this will be for Olivia's family and have provided them with a detailed explanation of the decision.\" Ms Burt, who was a member of the British sailing team, grew up in Milford-on-Sea and had been head girl of Bournemouth School for Girls. Her parents have set up a charity, Olivia Inspires, in her memory to help disadvantaged children from the New Forest area. An inquest into her death is yet to be concluded. Follow BBC North East & Cumbria on Twitter, Facebook and Instagram. Send your story ideas to northeastandcumbria@bbc.co.uk.", "output": "Fighting pandas set to join World of Warcraft", "explanation": "The output is not at all relevant to the given text. A good title for this text can be \"Olivia Burt's family 'disappointed' with CPS decision\"."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["News"], "Instance": {"id": "task1356-e244ea58d7c64228916fa6f84477107c", "input": "Authorities say Sandra Bland hanged herself, but her family says she would not have taken her own life. A video was found on her Facebook page in which she said she was suffering from \"a little bit of depression\" and post-traumatic stress disorder. Her death follows a series of cases in which black people have died in police custody or during arrest. Bland had been stopped by police after improperly signalling a lane change while driving. She was arrested after allegedly kicking a police officer after the traffic stop. Family members were shocked by her death, unable to believe she would have killed herself. A second video showed Bland saying \"Depression is nothing but the devil\" and that \"it's a daily struggle\". The FBI has launched an investigation, following the start of a separate inquiry by the Texas Rangers law enforcement agency. The 28-year-old had just moved to Texas from Illinois to start a new job. Her sister Shante Needham said Bland called her from jail, saying she did not know why she had been arrested and that an officer had possibly broken her arm. Bland died by asphyxiation using a plastic bag to hang herself in her cell, according to Waller County District Attorney Elton Mathias. Video footage did not show what happened inside Bland's cell, but did suggest no one entered or left it until someone found her unconscious. The Texas Commission on Jail Standards cited the Waller County Jail three years ago for not checking all inmates once an hour. Another inmate hanged himself with a bed sheet in 2012. Jail Sheriff Glen Smith said his staff checked on Bland less than an hour before she was found dead. Texas state senator Royce West asked the Texas Department of Public Safety to release video of the arrest and called her death \"suspicious\".", "output": ["FBI investigating 'suicide' of woman found dead in a Texas jail"]}, "Instance License": ["CC BY-SA 4.0"], "prediction": "Sandra Bland: \"Depression is nothing but the devil\""}
+{"id": "task1356-f352b932e1bb43e289e0a4990a847627", "Task": "task1356_xlsum_title_generation", "Contributors": "['Krishna Sree G']", "Source": ["xlsum"], "URL": ["https://arxiv.org/abs/2106.13822"], "Categories": ["Title Generation"], "Reasoning": [], "Definition": ["Generate an appropriate title for the given text. The generated title must be short and include the main topic of the text. The preferred titles are under fifteen words."], "Positive Examples": [{"input": "But Eluned Morgan conceded that it would be \"difficult for us to stop\" from a legal point of view. Her comments were criticised by a Labour AM. Alun Davies said threatening legal action \"sounds like the last breath before you're thrown out of the pub\". Mr Davies said he was not convinced the Welsh Government would \"have a leg to stand on\" in trying to shape international trade deals after Brexit. Following Donald Trump's comments during last week's trade visit that the NHS would be \"on the table\" in any future trade talks between the UK and the USA, Eluned Morgan said there was \"absolutely no prospect whatsoever of us allowing the Welsh NHS to be part of any negotiation.\" The US President then rowed back on his initial comments following criticism from a number of MPs. Asked about her response to President Trump's remarks as she gave evidence to the Assembly's Brexit committee on Monday, Ms Morgan said \"legally, it would be difficult for us to stop because we don't have a veto over trade\". \"Politically, I think it's extremely unlikely to happen,\" the international relations and the Welsh language minister said. \"They [the UK Government] should not be concluding any trade agreements without consulting us where we have the power.\" Ms Morgan explained that UK and Welsh government officials are working on an agreement or 'concordat' for how future trade deals are negotiated. During a robust exchange, the Labour AM Alun Davies said: \"I want something which is in law to which I can hold you to account and which colleagues in Westminster can hold the UK Government to account. \"The argument we'll make life difficult for them, it sounds alright on the street, but it's not the reality of intergovernmental relations.\" \"The United Kingdom has to find a way of functioning. \"At the moment, your answers aren't giving me any confidence that there is that structure in place because, if the Welsh Government's argument is, 'we'll see you in court', it's not a very impressive argument either for the continuation of the structure of United Kingdom as a state or the commitment of the government within the United Kingdom to actually work together,\" he added. Responding to the criticism, Ms Morgan said: \"Is the current intergovernmental structure adequate? \"Absolutely not... and it's not just in relation to trade, it's in relation to almost every aspect of government policy. So, that infrastructure needs to be built.\"", "output": "NHS Wales: Court action if trade deals affect service?", "explanation": "The output phrase is the appropriate title for the given text and it highlights the essence of the passage."}, {"input": "By Jon Welch and Paul MoseleyBBC News Details of health problems, family bereavements and personal issues were sent by the University of East Anglia (UEA) in Norwich to 298 students. Megan Baynes, 23, said she felt \"sick and horrified\" when she realised her details had been shared. The UEA apologised \"unreservedly\" and said an inquiry had begun. The email contained a spreadsheet listing 172 names and details extenuating circumstances in which extensions and other academic concessions were granted to 42 students. 'Felt sick' It was sent to nearly 300 undergraduates, including Ms Baynes, a former editor of student newspaper Concrete. She is currently awaiting the results of her American Literature and Creative Writing degree, and had been granted extensions for coursework because of an illness suffered by a family member. \"I felt sick at seeing my personal situation written in a spreadsheet, and then seemingly sent to everyone on my course,\" she said. \"My situation was not the worst on there but there are some on there that are so personal. There are people I know and I feel so awful for them and can't imagine how they are feeling.\" Theo Antoniou Phillips, UEA Students' Union undergraduate education officer, said: \"This is a shocking and utterly unacceptable data breach that should never have happened.\" Jo Swo, the union's welfare, community and diversity officer, said: \"Given the university is supposed to be making mental health a priority, this is a real slap in the face to students who have sought support.\" In a statement, a UEA spokeswoman said: \"An email was mistakenly sent to 298 American Studies undergraduates this morning containing details of 42 students with extenuating circumstances. \"This clearly should not have happened and the university apologises unreservedly. The university has launched an urgent enquiry and is contacting all affected students to offer support. \"Anyone needing support should call 01603 592761. The university is informing the ICO (Information Commissioner's Office).\" The ICO has been contacted for comment.", "output": "University of East Anglia in students' personal data breach", "explanation": "University of East Anglia in students' personal data breach is the apt and relevant title for the given sentence."}, {"input": "Media reports say Stanislav Bogdanovich and Alexandra Vernigora - also a top chess player - were found with balloons containing the gas, nitrous oxide. The gas is inhaled using a balloon. Russian investigators reported the deaths, without naming the pair, and said there were no signs of foul play. Bogdanovich was a speed chess champion. Vernigora was also a professional chess player and was studying at Moscow State University. The Ukrainian sports website sport.ua says Bogdanovich was a grandmaster from Odessa who won the Ukrainian Under-18 championship and various chess awards at international tournaments. Russian chess website chess-news.ru says that in 2015 he was rated eighth in the world for speed (blitz) chess. Reports say Bogdanovich drew much criticism recently for representing Russia in an internet chess match against Ukraine, which he won. Sport.ua quotes a Facebook post from him (in Russian) about that, in which he argued that playing for Russia was good for business, that he was living as a guest in Russia and being treated well, and this was his small contribution to ending the Russia-Ukraine conflict. Nitrous oxide was first used as an anaesthetic in 1844, but is now being used as a recreational drug and has been linked to a number of deaths. It can also cause breathing difficulties, dangerously increased heart rate and burns.", "output": "Young Ukraine chess couple 'killed by laughing gas'", "explanation": "The output is the appropriate title for the given text, emphasizing the main points of the passage."}], "Negative Examples": [{"input": "Supporters followed on the radio and TV as Harrogate Town won the National League play-off final at Wembley. The result has been described as a \"superb lift\" for the spa town. Work to rip up the club's artificial pitch and replace it with grass, in keeping with league regulations, is expected to start later on Monday. Fan Brody Pattison joked that he wanted some of the artificial pitch in his back garden as a souvenir. He said: \"I can't thank the players enough, they're all heroes for this town, they're going to go down in history. \"We've come so far as a club in the last three or four years, we're a small town full of teashops and we're in the Football League.\" Another Sulphurites supporter, Jack Wilkinson, said he woke up on Monday with a bottle of champagne and a huge sign saying \"we're going to Wembley\". He said: \"As soon as they scored the first goal, that's when the tears started and they didn't stop until full-time, I'm a grown adult crying over a football match. \"It makes the early mornings going to Dover, Yeovil, Torquay all worth it.\" The Sulphurites also won the praise of what is possibly Harrogate's most famous institution, Bettys tearoom. A spokeswoman said: \"We've the kettle on and Fat Rascals (a kind of scone) in the oven. We're delighted to raise a toast to Simon Weaver and the winning Harrogate team.\" Harrogate businessman Mark Noble was lucky enough to attend the game as a guest of the club. He said: \"The lads were all so proud, the support they've had all season was with them yesterday, the flags were up. \"Yesterday was a large key opening a large door, next season we're in that room and hopefully when Covid is over, all the supporters will all be there following the team.\" Simon Cotton, who runs hotels and pubs in and around the town, said promotion was a \"superb lift\" for Harrogate after \"so many months of lockdown blues\". He said: \"Harrogate relies on visitor tourism and if more fans are travelling to see their teams then they're potentially going to stay in hotels in the town, go for a drink in the bars, have something to eat in the restaurants and buy something in the shops.\" There have been calls for an open-top bus parade, although coronavirus restrictions mean this is unlikely. Harrogate Borough mayor Stuart Martin said: \"We've got to try and think of how best we can celebrate - under normal circumstances, wouldn't it have been nice to have a civic reception for them? - but there's no way we can do that under the current climate, it's just not feasible.\" He said promotion was \"going to bring a real buzz to the town, to the district, to the county\" and would encourage more youngsters to get involved in sport. Lindsey Whitton, captain of Harrogate Town's women's team, said she hoped the club's recent success would inspire more girls to start playing football. She said: \"It's amazing, the profile of the club has just risen so much within 24 hours, not only for the men's team but it's going to have a massive impact on the women's team, the player development centre, the academy.\" Follow BBC Yorkshire on Facebook, Twitter and Instagram. Send your story ideas to yorkslincs.news@bbc.co.uk or send video here.", "output": "Fan Brody Pattison joked that he wanted some of the artificial pitch in his back garden as a souvenir.", "explanation": "This not an apt title beacause it doesn't correspond to the main idea of the text. \"Harrogate Town promotion a 'superb lift' after lockdown\" correspond to the main idea of the text and is a good title."}, {"input": "Olivia Burt, 20, died outside Missoula in Durham in February 2018. The Crown Prosecution Service (CPS) announced it had decided against pressing manslaughter charges against any people or the club. Ms Burt, from Hampshire, was in her first year reading natural sciences at Durham University. The CPS said it had also reviewed its decision not to prosecute and upheld its original view. 'Deeply disappointed' It considered charges of manslaughter by gross negligence against the individual suspects and charges of corporate manslaughter against the business. Ms Burt's parents Nigel and Paula Burt said: \"Clearly we are deeply disappointed that after such a lengthy investigation, lasting more than two-and-a-half years, this decision has been reached. \"We hope that there will now be a thorough and independent investigation into whether any health and safety offences have been committed.\" The CPS said it had considered the evidence provided by the police and judged the legal test for bringing a prosecution had not been met. A spokesman said: \"We understand how difficult this will be for Olivia's family and have provided them with a detailed explanation of the decision.\" Ms Burt, who was a member of the British sailing team, grew up in Milford-on-Sea and had been head girl of Bournemouth School for Girls. Her parents have set up a charity, Olivia Inspires, in her memory to help disadvantaged children from the New Forest area. An inquest into her death is yet to be concluded. Follow BBC North East & Cumbria on Twitter, Facebook and Instagram. Send your story ideas to northeastandcumbria@bbc.co.uk.", "output": "Fighting pandas set to join World of Warcraft", "explanation": "The output is not at all relevant to the given text. A good title for this text can be \"Olivia Burt's family 'disappointed' with CPS decision\"."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["News"], "Instance": {"id": "task1356-f352b932e1bb43e289e0a4990a847627", "input": "The Crown Prosecution Service (CPS) advice for England and Wales says older people may face more frequent attacks because they are less independent. It makes clear abuse may not always involve violence - warning that young people my face abuse via mobile phones and social media. The advice will be consulted on before coming into force. 'Partner violence' The CPS points out that people's experiences of domestic abuse change as they get older. It says the intensity of abuse may be greater among pensioners because they may feel less able to escape or to get help as they are dependent on their abuser. Director of Public Prosecutions (DPP) Alison Saunders said: \"We know from research conducted by others that there is very little evidence that partner violence decreases with age. \"And it is important we also recognise the factors that may contribute to and impact upon domestic abuse between older people.\" The new guidance, which is intended to help prosecutors in England and Wales decide when to bring charges against perpetrators of domestic abuse, is yet to come into force. The issue of elderly abuse was brought into the spotlight following the death of 81-year-old Mary Russell. She was abused by her husband and died following a \"domestic-related\" incident in 2010, suffering a bleed to the brain. The pensioner, of Leigh-on-Sea in Essex, had made eight 999 calls in the seven months before her death. Exclusion and isolation She made her first report to police in 2003 after she was found standing on her doorstep with a bloody nose. Albert Russell, 88, the victim's husband, was arrested following her death, but it was decided there was insufficient evidence to prosecute him. He has since died. The draft guidance claims that growing older can lead to exclusion or isolation, which may make a victim more vulnerable to domestic abuse. For younger victims, prosecutors are advised to consider abusive relationships which form part of the membership of a gang. Some victims may be coerced into sexual activity in return for protection or status, according to the guidance. It advises prosecutors to ask police about a victim's family life to determine whether telling their parents about any potential prosecution might affect their safety. 'Honey traps' Consideration should be given to bail restrictions and restraining orders, the code also says, and prosecutors should take into account areas which victims often visit, like school or social clubs, and methods of contact, such as social media. The guidance also advises prosecutors on abusive relationships within gangs, highlighting the fact that some victims may be coerced into sex in return for protection or status. \"Some teenagers may not consider themselves victims of domestic violence, especially if they are not being physically abused but are being targeted on social media for example,\" Ms Saunders added. \"Similarly, abuse in gang environments - for example young girls being forced into sexual activity as part of gang initiation or used as 'honey traps' to set up rival gang members - is often not reported. \"Understandably, a lot of my prosecutors will not be familiar with the workings of gang culture or gang slang so I have included it in the proposed guidance so that they know what to look for when considering such cases.\"", "output": ["Prosecutors given guidance on teen and elderly abuse"]}, "Instance License": ["CC BY-SA 4.0"], "prediction": "The CPS says older people may face more frequent attacks because they are less independent"}
+{"id": "task893-d5eab067d1e64157af0fb79f6b95c76e", "Task": "task893_gap_fill_the_blank_coreference_resolution", "Contributors": "['Selvaganesh Muthu']", "Source": ["gap"], "URL": ["https://huggingface.co/datasets/gap"], "Categories": ["Coreference Resolution"], "Reasoning": [], "Definition": ["Read the passage and find the corresponding pronoun for the given name. The pronoun should match the given blank(_). The word between ** ** is the target name. The pronoun should be one of 'her', 'him', 'he', 'she' and 'his' with proper casing based on the position in the passage."], "Positive Examples": [{"input": "Dorothy Moore (born 13 October 1946, Jackson, Mississippi ) is an American pop, R&B, and soulsinger best known for her 1976 hit song, ``Misty Blue''. Born to Mary Moore and Melvin Hendrex Snr., aka Melvin Henderson of the Mississippi Blind Boys, **Dorothy** was raised by _ great grandmother.", "output": "her", "explanation": "The sentence begins with the name Dorothy and is referenced by 'her' in the previous sentence. So the correct pronoun for Dorothy is 'her'."}, {"input": "Groucutt began his musical career at 15 as Rikki Storm of Rikki Storm and the Falcons. He went on to sing with various outfits during the '60s, picking up the guitar as he went along. **Groucutt** was also a member of a band called ``Sight and Sound'', and later with a band called ``Barefoot''. It was while playing with Barefoot in Birmingham that _ was spotted by ELO's Jeff Lynne; and after Lynne, Bev Bevan and Richard Tandy had watched him play, he was invited to join ELO, to replace Mike de Albuquerque, who had recently left the band.", "output": "he", "explanation": "It is mentioned that Groucutt plays with the band ``Barefoot'' and so the blank refers to Groucutt. Groucutt was referred to by 'he' in the second sentence and hence the blank refers to the pronoun 'he'."}, {"input": "After the 1980 elections he became Minister for Communications. In May 1982, he became Minister for Defence, a post he held until the defeat of the Fraser government at the 1983 election. In January 1984 **Anthony** resigned the leadership of the National Country Party (as the Country Party had been renamed in 1975), and Sinclair succeeded _.", "output": "him", "explanation": "The last sentence starts with the name 'Anthony' and so the blank refers to 'Anthony'. 'Anthony' was referred to with 'he' in several parts of the passage. So the output pronoun 'he' is correct."}], "Negative Examples": [{"input": "In 2002 a large exhibition of her work was held in Montparnasse, ``Elles de Montparnasse``, where her works were shown together with works by Tamara de Lempicka, Marie Laurencin, Hannah Orlova, Sonia Delaunay and Natalia Goncharova. A retrospective exhibition of **Vera Rockline**'s works was held in Galerie Drouart (Paris, France) in 1984. Since 2017 Galerie Drouart (now Cabinet Expertise Drouart) is preparing the catalogue raisonn* of Vera Rockline. In June 2008, _ painting Card Players (1919) was sold in an auction at Christie's, in London, for 2 million pounds.", "output": "his", "explanation": "In the first sentence, it has been shown that Vera Rockline is referenced by the pronoun 'her'. So this output is incorrect."}, {"input": "However, when CCTV footage shows Paige & Rose accompanying Connor into the flat, the pair open up and claim they had been babysitting Connor after his older brother, who was supposed to be babysitting, had left him alone. Eventually, Paige breaks down and names Rose as the killer. When the case gets to court, Rose's brief Kim Sharkey invites the court to accept **Paige** as the guilty party, as forensics seem to implicate _ as the murderess.", "output": "him", "explanation": "The word 'murderess' denotes the pronoun 'her' but the output is 'him' and so this is incorrect."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Wikipedia"], "Instance": {"id": "task893-d5eab067d1e64157af0fb79f6b95c76e", "input": "As a junior player, Bailey won the World Junior Championship in 1997 and captained the England team to World and European junior team titles. A car accident led to career-threatening knee surgery at the age of 21, but she successfully recovered and resumed her playing career. In 2003, **Bailey** finished runner-up to Sarah Fitz-Gerald at the British Open. _ reached a career-high ranking of World No. 4 that year.", "output": ["She"]}, "Instance License": ["Apache 2.0"], "prediction": "she"}
+{"id": "task893-3721cbd619c34689adee80bb96e61963", "Task": "task893_gap_fill_the_blank_coreference_resolution", "Contributors": "['Selvaganesh Muthu']", "Source": ["gap"], "URL": ["https://huggingface.co/datasets/gap"], "Categories": ["Coreference Resolution"], "Reasoning": [], "Definition": ["Read the passage and find the corresponding pronoun for the given name. The pronoun should match the given blank(_). The word between ** ** is the target name. The pronoun should be one of 'her', 'him', 'he', 'she' and 'his' with proper casing based on the position in the passage."], "Positive Examples": [{"input": "Dorothy Moore (born 13 October 1946, Jackson, Mississippi ) is an American pop, R&B, and soulsinger best known for her 1976 hit song, ``Misty Blue''. Born to Mary Moore and Melvin Hendrex Snr., aka Melvin Henderson of the Mississippi Blind Boys, **Dorothy** was raised by _ great grandmother.", "output": "her", "explanation": "The sentence begins with the name Dorothy and is referenced by 'her' in the previous sentence. So the correct pronoun for Dorothy is 'her'."}, {"input": "Groucutt began his musical career at 15 as Rikki Storm of Rikki Storm and the Falcons. He went on to sing with various outfits during the '60s, picking up the guitar as he went along. **Groucutt** was also a member of a band called ``Sight and Sound'', and later with a band called ``Barefoot''. It was while playing with Barefoot in Birmingham that _ was spotted by ELO's Jeff Lynne; and after Lynne, Bev Bevan and Richard Tandy had watched him play, he was invited to join ELO, to replace Mike de Albuquerque, who had recently left the band.", "output": "he", "explanation": "It is mentioned that Groucutt plays with the band ``Barefoot'' and so the blank refers to Groucutt. Groucutt was referred to by 'he' in the second sentence and hence the blank refers to the pronoun 'he'."}, {"input": "After the 1980 elections he became Minister for Communications. In May 1982, he became Minister for Defence, a post he held until the defeat of the Fraser government at the 1983 election. In January 1984 **Anthony** resigned the leadership of the National Country Party (as the Country Party had been renamed in 1975), and Sinclair succeeded _.", "output": "him", "explanation": "The last sentence starts with the name 'Anthony' and so the blank refers to 'Anthony'. 'Anthony' was referred to with 'he' in several parts of the passage. So the output pronoun 'he' is correct."}], "Negative Examples": [{"input": "In 2002 a large exhibition of her work was held in Montparnasse, ``Elles de Montparnasse``, where her works were shown together with works by Tamara de Lempicka, Marie Laurencin, Hannah Orlova, Sonia Delaunay and Natalia Goncharova. A retrospective exhibition of **Vera Rockline**'s works was held in Galerie Drouart (Paris, France) in 1984. Since 2017 Galerie Drouart (now Cabinet Expertise Drouart) is preparing the catalogue raisonn* of Vera Rockline. In June 2008, _ painting Card Players (1919) was sold in an auction at Christie's, in London, for 2 million pounds.", "output": "his", "explanation": "In the first sentence, it has been shown that Vera Rockline is referenced by the pronoun 'her'. So this output is incorrect."}, {"input": "However, when CCTV footage shows Paige & Rose accompanying Connor into the flat, the pair open up and claim they had been babysitting Connor after his older brother, who was supposed to be babysitting, had left him alone. Eventually, Paige breaks down and names Rose as the killer. When the case gets to court, Rose's brief Kim Sharkey invites the court to accept **Paige** as the guilty party, as forensics seem to implicate _ as the murderess.", "output": "him", "explanation": "The word 'murderess' denotes the pronoun 'her' but the output is 'him' and so this is incorrect."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Wikipedia"], "Instance": {"id": "task893-3721cbd619c34689adee80bb96e61963", "input": "She goes on to acknowledge that in Finch's work, ``Now and again words issue of pure poetry...It was a thousand pities that the woman who could write like that, whose mind was turned to nature, and reflection, should have been forced to anger and bitterness.'' Woolf goes on in defence of her as a gifted but sometimes understandably misguided example of women's writing. It is evident that **Woolf** sympathises deeply with Finch's plight as a female poet, and though _ takes issue with some of the content in Finch's writing, she expresses grief that Finch is so unknown: ``...when one comes to seek out the facts about Lady Winchilsea, one finds, as usual, that almost nothing is known about her.''", "output": ["she"]}, "Instance License": ["Apache 2.0"], "prediction": "she"}
+{"id": "task893-9ba2164850be4f6db6cb55494d12034c", "Task": "task893_gap_fill_the_blank_coreference_resolution", "Contributors": "['Selvaganesh Muthu']", "Source": ["gap"], "URL": ["https://huggingface.co/datasets/gap"], "Categories": ["Coreference Resolution"], "Reasoning": [], "Definition": ["Read the passage and find the corresponding pronoun for the given name. The pronoun should match the given blank(_). The word between ** ** is the target name. The pronoun should be one of 'her', 'him', 'he', 'she' and 'his' with proper casing based on the position in the passage."], "Positive Examples": [{"input": "Dorothy Moore (born 13 October 1946, Jackson, Mississippi ) is an American pop, R&B, and soulsinger best known for her 1976 hit song, ``Misty Blue''. Born to Mary Moore and Melvin Hendrex Snr., aka Melvin Henderson of the Mississippi Blind Boys, **Dorothy** was raised by _ great grandmother.", "output": "her", "explanation": "The sentence begins with the name Dorothy and is referenced by 'her' in the previous sentence. So the correct pronoun for Dorothy is 'her'."}, {"input": "Groucutt began his musical career at 15 as Rikki Storm of Rikki Storm and the Falcons. He went on to sing with various outfits during the '60s, picking up the guitar as he went along. **Groucutt** was also a member of a band called ``Sight and Sound'', and later with a band called ``Barefoot''. It was while playing with Barefoot in Birmingham that _ was spotted by ELO's Jeff Lynne; and after Lynne, Bev Bevan and Richard Tandy had watched him play, he was invited to join ELO, to replace Mike de Albuquerque, who had recently left the band.", "output": "he", "explanation": "It is mentioned that Groucutt plays with the band ``Barefoot'' and so the blank refers to Groucutt. Groucutt was referred to by 'he' in the second sentence and hence the blank refers to the pronoun 'he'."}, {"input": "After the 1980 elections he became Minister for Communications. In May 1982, he became Minister for Defence, a post he held until the defeat of the Fraser government at the 1983 election. In January 1984 **Anthony** resigned the leadership of the National Country Party (as the Country Party had been renamed in 1975), and Sinclair succeeded _.", "output": "him", "explanation": "The last sentence starts with the name 'Anthony' and so the blank refers to 'Anthony'. 'Anthony' was referred to with 'he' in several parts of the passage. So the output pronoun 'he' is correct."}], "Negative Examples": [{"input": "In 2002 a large exhibition of her work was held in Montparnasse, ``Elles de Montparnasse``, where her works were shown together with works by Tamara de Lempicka, Marie Laurencin, Hannah Orlova, Sonia Delaunay and Natalia Goncharova. A retrospective exhibition of **Vera Rockline**'s works was held in Galerie Drouart (Paris, France) in 1984. Since 2017 Galerie Drouart (now Cabinet Expertise Drouart) is preparing the catalogue raisonn* of Vera Rockline. In June 2008, _ painting Card Players (1919) was sold in an auction at Christie's, in London, for 2 million pounds.", "output": "his", "explanation": "In the first sentence, it has been shown that Vera Rockline is referenced by the pronoun 'her'. So this output is incorrect."}, {"input": "However, when CCTV footage shows Paige & Rose accompanying Connor into the flat, the pair open up and claim they had been babysitting Connor after his older brother, who was supposed to be babysitting, had left him alone. Eventually, Paige breaks down and names Rose as the killer. When the case gets to court, Rose's brief Kim Sharkey invites the court to accept **Paige** as the guilty party, as forensics seem to implicate _ as the murderess.", "output": "him", "explanation": "The word 'murderess' denotes the pronoun 'her' but the output is 'him' and so this is incorrect."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Wikipedia"], "Instance": {"id": "task893-9ba2164850be4f6db6cb55494d12034c", "input": "Connie, in a one-sided conversation, gives praises for her late brother, Gordon. She does not seem to mind she spent childhood in the shadow of her brother, blatantly the family favourite and given all the support she never had. Although Beth quietly agrees with **Connie**'s idea of _ idyllic marriage to Gordon, she expresses subtle annoyance with Connie's idea that the whole family will have to look after her this first Christmas alone, and Connie's hints of self-pity don't help either.", "output": ["her"]}, "Instance License": ["Apache 2.0"], "prediction": "her"}
+{"id": "task893-ffad8a5c67eb4f46ada4214575b784c2", "Task": "task893_gap_fill_the_blank_coreference_resolution", "Contributors": "['Selvaganesh Muthu']", "Source": ["gap"], "URL": ["https://huggingface.co/datasets/gap"], "Categories": ["Coreference Resolution"], "Reasoning": [], "Definition": ["Read the passage and find the corresponding pronoun for the given name. The pronoun should match the given blank(_). The word between ** ** is the target name. The pronoun should be one of 'her', 'him', 'he', 'she' and 'his' with proper casing based on the position in the passage."], "Positive Examples": [{"input": "Dorothy Moore (born 13 October 1946, Jackson, Mississippi ) is an American pop, R&B, and soulsinger best known for her 1976 hit song, ``Misty Blue''. Born to Mary Moore and Melvin Hendrex Snr., aka Melvin Henderson of the Mississippi Blind Boys, **Dorothy** was raised by _ great grandmother.", "output": "her", "explanation": "The sentence begins with the name Dorothy and is referenced by 'her' in the previous sentence. So the correct pronoun for Dorothy is 'her'."}, {"input": "Groucutt began his musical career at 15 as Rikki Storm of Rikki Storm and the Falcons. He went on to sing with various outfits during the '60s, picking up the guitar as he went along. **Groucutt** was also a member of a band called ``Sight and Sound'', and later with a band called ``Barefoot''. It was while playing with Barefoot in Birmingham that _ was spotted by ELO's Jeff Lynne; and after Lynne, Bev Bevan and Richard Tandy had watched him play, he was invited to join ELO, to replace Mike de Albuquerque, who had recently left the band.", "output": "he", "explanation": "It is mentioned that Groucutt plays with the band ``Barefoot'' and so the blank refers to Groucutt. Groucutt was referred to by 'he' in the second sentence and hence the blank refers to the pronoun 'he'."}, {"input": "After the 1980 elections he became Minister for Communications. In May 1982, he became Minister for Defence, a post he held until the defeat of the Fraser government at the 1983 election. In January 1984 **Anthony** resigned the leadership of the National Country Party (as the Country Party had been renamed in 1975), and Sinclair succeeded _.", "output": "him", "explanation": "The last sentence starts with the name 'Anthony' and so the blank refers to 'Anthony'. 'Anthony' was referred to with 'he' in several parts of the passage. So the output pronoun 'he' is correct."}], "Negative Examples": [{"input": "In 2002 a large exhibition of her work was held in Montparnasse, ``Elles de Montparnasse``, where her works were shown together with works by Tamara de Lempicka, Marie Laurencin, Hannah Orlova, Sonia Delaunay and Natalia Goncharova. A retrospective exhibition of **Vera Rockline**'s works was held in Galerie Drouart (Paris, France) in 1984. Since 2017 Galerie Drouart (now Cabinet Expertise Drouart) is preparing the catalogue raisonn* of Vera Rockline. In June 2008, _ painting Card Players (1919) was sold in an auction at Christie's, in London, for 2 million pounds.", "output": "his", "explanation": "In the first sentence, it has been shown that Vera Rockline is referenced by the pronoun 'her'. So this output is incorrect."}, {"input": "However, when CCTV footage shows Paige & Rose accompanying Connor into the flat, the pair open up and claim they had been babysitting Connor after his older brother, who was supposed to be babysitting, had left him alone. Eventually, Paige breaks down and names Rose as the killer. When the case gets to court, Rose's brief Kim Sharkey invites the court to accept **Paige** as the guilty party, as forensics seem to implicate _ as the murderess.", "output": "him", "explanation": "The word 'murderess' denotes the pronoun 'her' but the output is 'him' and so this is incorrect."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Wikipedia"], "Instance": {"id": "task893-ffad8a5c67eb4f46ada4214575b784c2", "input": "Following the death of Tewodros II's much loved first wife, Empress Tewabech Ali (who was Tiruwork's niece), his intimates began to discreetly look for an appropriate consort to provide him with an heir and to calm his more extreme moods as his late wife had done. Legend states that one of the Emperor's officers was attending Sunday services at a church at Derasge when **Tewodros** was staying there, and was struck at the beauty, the aristocratic deportment, and the deep piety of a woman worshiping there. _ immediately went to the Emperor and told him he had seen the woman ``meant to be the wife of my sovereign''.", "output": ["He"]}, "Instance License": ["Apache 2.0"], "prediction": "he"}
+{"id": "task893-d3773fa3ed27487ba7307512555507f0", "Task": "task893_gap_fill_the_blank_coreference_resolution", "Contributors": "['Selvaganesh Muthu']", "Source": ["gap"], "URL": ["https://huggingface.co/datasets/gap"], "Categories": ["Coreference Resolution"], "Reasoning": [], "Definition": ["Read the passage and find the corresponding pronoun for the given name. The pronoun should match the given blank(_). The word between ** ** is the target name. The pronoun should be one of 'her', 'him', 'he', 'she' and 'his' with proper casing based on the position in the passage."], "Positive Examples": [{"input": "Dorothy Moore (born 13 October 1946, Jackson, Mississippi ) is an American pop, R&B, and soulsinger best known for her 1976 hit song, ``Misty Blue''. Born to Mary Moore and Melvin Hendrex Snr., aka Melvin Henderson of the Mississippi Blind Boys, **Dorothy** was raised by _ great grandmother.", "output": "her", "explanation": "The sentence begins with the name Dorothy and is referenced by 'her' in the previous sentence. So the correct pronoun for Dorothy is 'her'."}, {"input": "Groucutt began his musical career at 15 as Rikki Storm of Rikki Storm and the Falcons. He went on to sing with various outfits during the '60s, picking up the guitar as he went along. **Groucutt** was also a member of a band called ``Sight and Sound'', and later with a band called ``Barefoot''. It was while playing with Barefoot in Birmingham that _ was spotted by ELO's Jeff Lynne; and after Lynne, Bev Bevan and Richard Tandy had watched him play, he was invited to join ELO, to replace Mike de Albuquerque, who had recently left the band.", "output": "he", "explanation": "It is mentioned that Groucutt plays with the band ``Barefoot'' and so the blank refers to Groucutt. Groucutt was referred to by 'he' in the second sentence and hence the blank refers to the pronoun 'he'."}, {"input": "After the 1980 elections he became Minister for Communications. In May 1982, he became Minister for Defence, a post he held until the defeat of the Fraser government at the 1983 election. In January 1984 **Anthony** resigned the leadership of the National Country Party (as the Country Party had been renamed in 1975), and Sinclair succeeded _.", "output": "him", "explanation": "The last sentence starts with the name 'Anthony' and so the blank refers to 'Anthony'. 'Anthony' was referred to with 'he' in several parts of the passage. So the output pronoun 'he' is correct."}], "Negative Examples": [{"input": "In 2002 a large exhibition of her work was held in Montparnasse, ``Elles de Montparnasse``, where her works were shown together with works by Tamara de Lempicka, Marie Laurencin, Hannah Orlova, Sonia Delaunay and Natalia Goncharova. A retrospective exhibition of **Vera Rockline**'s works was held in Galerie Drouart (Paris, France) in 1984. Since 2017 Galerie Drouart (now Cabinet Expertise Drouart) is preparing the catalogue raisonn* of Vera Rockline. In June 2008, _ painting Card Players (1919) was sold in an auction at Christie's, in London, for 2 million pounds.", "output": "his", "explanation": "In the first sentence, it has been shown that Vera Rockline is referenced by the pronoun 'her'. So this output is incorrect."}, {"input": "However, when CCTV footage shows Paige & Rose accompanying Connor into the flat, the pair open up and claim they had been babysitting Connor after his older brother, who was supposed to be babysitting, had left him alone. Eventually, Paige breaks down and names Rose as the killer. When the case gets to court, Rose's brief Kim Sharkey invites the court to accept **Paige** as the guilty party, as forensics seem to implicate _ as the murderess.", "output": "him", "explanation": "The word 'murderess' denotes the pronoun 'her' but the output is 'him' and so this is incorrect."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Wikipedia"], "Instance": {"id": "task893-d3773fa3ed27487ba7307512555507f0", "input": "At the in Valencia, Button finished 3rd and maintained 2nd place in the title race with another podium. Button missed out on a podium at the , finishing fourth after problems with the balance off his car in qualifying had left him fourteenth. After three further-points scoring finishes, **Button** retired at the after being hit by Vettel and punctured the radiator of _ car.", "output": ["his"]}, "Instance License": ["Apache 2.0"], "prediction": "he"}
+{"id": "task641-2cdd0d0a4ad945a29486bd164b1a63a6", "Task": "task641_esnli_classification", "Contributors": "['Ian Lobo']", "Source": ["e_snli"], "URL": ["https://github.com/OanaMariaCamburu/e-SNLI/"], "Categories": ["Textual Entailment"], "Reasoning": ["Textual Entailment"], "Definition": ["Determine whether the two given sentences clearly agree with each other (entailment), disagree with each other (contradiction), or if this cannot be determined (neutral). Answer must be the letters E, C, and N, respectively."], "Positive Examples": [{"input": "A teenager blows a whistle and wears white face paint, earmuffs, and a yellow hat while another teen watches. <sep> Nobody has face paint.", "output": "C", "explanation": "Either a teenager wears face paint or nobody has face paint."}, {"input": "Small girl in a pink dress is playing electronic drum pads with sticks. <sep> the girl is wearing pink color frok", "output": "E", "explanation": "The girl is wearing a pink dress."}, {"input": "Five young men are in a loft, with one holding a whiteboard and one making a shaka sign in front of the television. <sep> Five men watch tv.", "output": "N", "explanation": "We can not determine whether the two sentences contradict each other or agree with each other. The men being in front of a television doesn't mean that they're watching tv."}], "Negative Examples": [{"input": "Two men walking in summer attire. <sep> Two men are walking.", "output": "C", "explanation": "This is incorrect. Walking and are walking are the same thing. This is a entailment statement."}, {"input": "Two women are hugging on a path through a grassy area with a cow visible past them. <sep> They are at the bar", "output": "E", "explanation": "This is incorrect. There is no grassy area at the bar. This is a contradiction statement."}, {"input": "The 3 dogs are cruising down the street. <sep> a family of dogs cruises down the street", "output": "E", "explanation": "The three dogs are not necessarily a family, so the correct answer is N."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Miscellaneous"], "Instance": {"id": "task641-2cdd0d0a4ad945a29486bd164b1a63a6", "input": "A man jumping a dirt ramp on a bmx bike. <sep> A man crashes his bike.", "output": ["C"]}, "Instance License": ["MIT"], "prediction": "C"}
+{"id": "task641-9900ec268b7c48c59d367fff24299ff9", "Task": "task641_esnli_classification", "Contributors": "['Ian Lobo']", "Source": ["e_snli"], "URL": ["https://github.com/OanaMariaCamburu/e-SNLI/"], "Categories": ["Textual Entailment"], "Reasoning": ["Textual Entailment"], "Definition": ["Determine whether the two given sentences clearly agree with each other (entailment), disagree with each other (contradiction), or if this cannot be determined (neutral). Answer must be the letters E, C, and N, respectively."], "Positive Examples": [{"input": "A teenager blows a whistle and wears white face paint, earmuffs, and a yellow hat while another teen watches. <sep> Nobody has face paint.", "output": "C", "explanation": "Either a teenager wears face paint or nobody has face paint."}, {"input": "Small girl in a pink dress is playing electronic drum pads with sticks. <sep> the girl is wearing pink color frok", "output": "E", "explanation": "The girl is wearing a pink dress."}, {"input": "Five young men are in a loft, with one holding a whiteboard and one making a shaka sign in front of the television. <sep> Five men watch tv.", "output": "N", "explanation": "We can not determine whether the two sentences contradict each other or agree with each other. The men being in front of a television doesn't mean that they're watching tv."}], "Negative Examples": [{"input": "Two men walking in summer attire. <sep> Two men are walking.", "output": "C", "explanation": "This is incorrect. Walking and are walking are the same thing. This is a entailment statement."}, {"input": "Two women are hugging on a path through a grassy area with a cow visible past them. <sep> They are at the bar", "output": "E", "explanation": "This is incorrect. There is no grassy area at the bar. This is a contradiction statement."}, {"input": "The 3 dogs are cruising down the street. <sep> a family of dogs cruises down the street", "output": "E", "explanation": "The three dogs are not necessarily a family, so the correct answer is N."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Miscellaneous"], "Instance": {"id": "task641-9900ec268b7c48c59d367fff24299ff9", "input": "A man wearing red ski pants, a black jacket, and a white helmet is skiing down a mountain. <sep> The man is near another person.", "output": ["N"]}, "Instance License": ["MIT"], "prediction": "C"}
+{"id": "task641-260eeecb77fa4069b397b82dd9a55611", "Task": "task641_esnli_classification", "Contributors": "['Ian Lobo']", "Source": ["e_snli"], "URL": ["https://github.com/OanaMariaCamburu/e-SNLI/"], "Categories": ["Textual Entailment"], "Reasoning": ["Textual Entailment"], "Definition": ["Determine whether the two given sentences clearly agree with each other (entailment), disagree with each other (contradiction), or if this cannot be determined (neutral). Answer must be the letters E, C, and N, respectively."], "Positive Examples": [{"input": "A teenager blows a whistle and wears white face paint, earmuffs, and a yellow hat while another teen watches. <sep> Nobody has face paint.", "output": "C", "explanation": "Either a teenager wears face paint or nobody has face paint."}, {"input": "Small girl in a pink dress is playing electronic drum pads with sticks. <sep> the girl is wearing pink color frok", "output": "E", "explanation": "The girl is wearing a pink dress."}, {"input": "Five young men are in a loft, with one holding a whiteboard and one making a shaka sign in front of the television. <sep> Five men watch tv.", "output": "N", "explanation": "We can not determine whether the two sentences contradict each other or agree with each other. The men being in front of a television doesn't mean that they're watching tv."}], "Negative Examples": [{"input": "Two men walking in summer attire. <sep> Two men are walking.", "output": "C", "explanation": "This is incorrect. Walking and are walking are the same thing. This is a entailment statement."}, {"input": "Two women are hugging on a path through a grassy area with a cow visible past them. <sep> They are at the bar", "output": "E", "explanation": "This is incorrect. There is no grassy area at the bar. This is a contradiction statement."}, {"input": "The 3 dogs are cruising down the street. <sep> a family of dogs cruises down the street", "output": "E", "explanation": "The three dogs are not necessarily a family, so the correct answer is N."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Miscellaneous"], "Instance": {"id": "task641-260eeecb77fa4069b397b82dd9a55611", "input": "It looks like the clown has fallen off the horse. <sep> The cowboy rode the bull to the buzzer.", "output": ["C"]}, "Instance License": ["MIT"], "prediction": "C"}
+{"id": "task641-ab80314a490c4b078a6d29fd759312bd", "Task": "task641_esnli_classification", "Contributors": "['Ian Lobo']", "Source": ["e_snli"], "URL": ["https://github.com/OanaMariaCamburu/e-SNLI/"], "Categories": ["Textual Entailment"], "Reasoning": ["Textual Entailment"], "Definition": ["Determine whether the two given sentences clearly agree with each other (entailment), disagree with each other (contradiction), or if this cannot be determined (neutral). Answer must be the letters E, C, and N, respectively."], "Positive Examples": [{"input": "A teenager blows a whistle and wears white face paint, earmuffs, and a yellow hat while another teen watches. <sep> Nobody has face paint.", "output": "C", "explanation": "Either a teenager wears face paint or nobody has face paint."}, {"input": "Small girl in a pink dress is playing electronic drum pads with sticks. <sep> the girl is wearing pink color frok", "output": "E", "explanation": "The girl is wearing a pink dress."}, {"input": "Five young men are in a loft, with one holding a whiteboard and one making a shaka sign in front of the television. <sep> Five men watch tv.", "output": "N", "explanation": "We can not determine whether the two sentences contradict each other or agree with each other. The men being in front of a television doesn't mean that they're watching tv."}], "Negative Examples": [{"input": "Two men walking in summer attire. <sep> Two men are walking.", "output": "C", "explanation": "This is incorrect. Walking and are walking are the same thing. This is a entailment statement."}, {"input": "Two women are hugging on a path through a grassy area with a cow visible past them. <sep> They are at the bar", "output": "E", "explanation": "This is incorrect. There is no grassy area at the bar. This is a contradiction statement."}, {"input": "The 3 dogs are cruising down the street. <sep> a family of dogs cruises down the street", "output": "E", "explanation": "The three dogs are not necessarily a family, so the correct answer is N."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Miscellaneous"], "Instance": {"id": "task641-ab80314a490c4b078a6d29fd759312bd", "input": "A man sitting on steps with a child as a bystander walks by. <sep> A man and a child sitting on steps saw a bystander.", "output": ["E"]}, "Instance License": ["MIT"], "prediction": "C"}
+{"id": "task641-67a775223bab42a5affc29fc19d97197", "Task": "task641_esnli_classification", "Contributors": "['Ian Lobo']", "Source": ["e_snli"], "URL": ["https://github.com/OanaMariaCamburu/e-SNLI/"], "Categories": ["Textual Entailment"], "Reasoning": ["Textual Entailment"], "Definition": ["Determine whether the two given sentences clearly agree with each other (entailment), disagree with each other (contradiction), or if this cannot be determined (neutral). Answer must be the letters E, C, and N, respectively."], "Positive Examples": [{"input": "A teenager blows a whistle and wears white face paint, earmuffs, and a yellow hat while another teen watches. <sep> Nobody has face paint.", "output": "C", "explanation": "Either a teenager wears face paint or nobody has face paint."}, {"input": "Small girl in a pink dress is playing electronic drum pads with sticks. <sep> the girl is wearing pink color frok", "output": "E", "explanation": "The girl is wearing a pink dress."}, {"input": "Five young men are in a loft, with one holding a whiteboard and one making a shaka sign in front of the television. <sep> Five men watch tv.", "output": "N", "explanation": "We can not determine whether the two sentences contradict each other or agree with each other. The men being in front of a television doesn't mean that they're watching tv."}], "Negative Examples": [{"input": "Two men walking in summer attire. <sep> Two men are walking.", "output": "C", "explanation": "This is incorrect. Walking and are walking are the same thing. This is a entailment statement."}, {"input": "Two women are hugging on a path through a grassy area with a cow visible past them. <sep> They are at the bar", "output": "E", "explanation": "This is incorrect. There is no grassy area at the bar. This is a contradiction statement."}, {"input": "The 3 dogs are cruising down the street. <sep> a family of dogs cruises down the street", "output": "E", "explanation": "The three dogs are not necessarily a family, so the correct answer is N."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Miscellaneous"], "Instance": {"id": "task641-67a775223bab42a5affc29fc19d97197", "input": "A dog chasing a duck in a pond. <sep> A dog is swimming through a pond in pursuit of a duck.", "output": ["E"]}, "Instance License": ["MIT"], "prediction": "C"}
+{"id": "task1529-d060fdb144cb4e22a97fc82963166937", "Task": "task1529_scitail1.1_classification", "Contributors": "['Krishna Sriharsha Gundu']", "Source": ["scitailv1.1"], "URL": ["http://data.allenai.org/scitail"], "Categories": ["Textual Entailment"], "Reasoning": ["Textual Entailment"], "Definition": ["You are given two sentences. You have to find if there is entailment or agreement of the Hypothesis by the Premise. From the given pair of sentences, you should identify if there is enough information in the Premise to support the claim made in the Hypothesis. The Premise may not exactly be the same as Hypothesis. Your task is to return 'entails' if the premise supports hypothesis else return 'neutral'."], "Positive Examples": [{"input": "Premise: Lyme Disease is caused by a bacterium that's transmitted by tick bite, but many infected people don't remember a bite. \n Hypothesis: Lyme disease is caused by bacteria.", "output": "entails", "explanation": "The premise sentence agrees with the hypothesis that Lyme Disease is a bacterium. The premise also gives additional information about Lyme disease. Therefore Premise entails Hypothesis."}, {"input": "Premise: Corolla Collective term for all the petals of a flower, these petals may be separate or fused together. \n Hypothesis: All of the petals together are called a corolla.", "output": "entails", "explanation": "The premise sentence explains the meaning of Corolla. The hypothesis sentence is explained by the Premise. Since the premise supports/entails the Hypothesis, this is classified as entails."}, {"input": "Premise: This can be dangerous to both plants and animals. \n Hypothesis: Nematodes can be a parasite of both.", "output": "neutral", "explanation": "The premise misses the context to the word 'this'. Therefore it is incomplete. The hypothesis is not supporting the premise. Therefore it is classified as neutral."}, {"input": "Premise: The liver is divided into the right lobe and left lobes. \n Hypothesis: The gallbladder is near the right lobe of the liver.", "output": "neutral", "explanation": "The premise states about the general structure of the liver while the hypothesis is explaining about a specific part of the liver. Therefore this premise does not support the hypothesis and hence classified as neutral."}], "Negative Examples": [{"input": "Premise: A polyploid is simply an organism that contains more than the usual two sets of chromosomes.  \n Hypothesis: A(n) polyploid is an individual with more than the correct number of chromosome sets.", "output": "neutral", "explanation": "The premise explains the meaning of the term and the hypothesis sentence also specifies it correctly. Because the Premise supports the Hypothesis, this is classifies should be classified as entails not as neutral."}, {"input": "Premise: Based on the list provided of the uses of substances 1-7, estimate the pH of each unknown and record the number in the data table in the estimated pH column. \n Hypothesis: If a substance has a ph value greater than 7, that indicates that it is based.", "output": "entails", "explanation": "The premise does not have a fact that can be supported. It is a task that should be carried out to find the pH of the substances. The hypothesis is therefore not supported by the premise. It should be classified as neutral not as entails."}, {"input": "Premise: The phylum for common marigolds is angiosperms. \n Hypothesis: Angiosperms are the most successful phylum of plants.", "output": "entails", "explanation": "The premise states the name for Marigold specifically. Since the hypothesis mentions this as successful phylum and gives no information about marigold being successful or not, this should be classified as neutral."}, {"input": "Premise: Vertebrates are named for vertebrae, the series of bones that make up the vertebral column or backbone. \n Hypothesis: Backbone is another name for the vertebral column.", "output": "neutral", "explanation": "The usage of the word 'or' between the words vertebral column and backbone implies that both the names are the same. The same meaning is conveyed in the Hypothesis too. Therefore this should be classified as entails and not as neutral."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Natural Science"], "Instance": {"id": "task1529-d060fdb144cb4e22a97fc82963166937", "input": "Premise: Most carbon atoms in the world have six protons and six neutrons in their nucleus. \n Hypothesis: All carbon atoms have six protons.", "output": ["entails"]}, "Instance License": ["Apache 2.0"], "prediction": "entails"}
+{"id": "task1529-1b487ac7129b4b97a0a6960ccb150cf1", "Task": "task1529_scitail1.1_classification", "Contributors": "['Krishna Sriharsha Gundu']", "Source": ["scitailv1.1"], "URL": ["http://data.allenai.org/scitail"], "Categories": ["Textual Entailment"], "Reasoning": ["Textual Entailment"], "Definition": ["You are given two sentences. You have to find if there is entailment or agreement of the Hypothesis by the Premise. From the given pair of sentences, you should identify if there is enough information in the Premise to support the claim made in the Hypothesis. The Premise may not exactly be the same as Hypothesis. Your task is to return 'entails' if the premise supports hypothesis else return 'neutral'."], "Positive Examples": [{"input": "Premise: Lyme Disease is caused by a bacterium that's transmitted by tick bite, but many infected people don't remember a bite. \n Hypothesis: Lyme disease is caused by bacteria.", "output": "entails", "explanation": "The premise sentence agrees with the hypothesis that Lyme Disease is a bacterium. The premise also gives additional information about Lyme disease. Therefore Premise entails Hypothesis."}, {"input": "Premise: Corolla Collective term for all the petals of a flower, these petals may be separate or fused together. \n Hypothesis: All of the petals together are called a corolla.", "output": "entails", "explanation": "The premise sentence explains the meaning of Corolla. The hypothesis sentence is explained by the Premise. Since the premise supports/entails the Hypothesis, this is classified as entails."}, {"input": "Premise: This can be dangerous to both plants and animals. \n Hypothesis: Nematodes can be a parasite of both.", "output": "neutral", "explanation": "The premise misses the context to the word 'this'. Therefore it is incomplete. The hypothesis is not supporting the premise. Therefore it is classified as neutral."}, {"input": "Premise: The liver is divided into the right lobe and left lobes. \n Hypothesis: The gallbladder is near the right lobe of the liver.", "output": "neutral", "explanation": "The premise states about the general structure of the liver while the hypothesis is explaining about a specific part of the liver. Therefore this premise does not support the hypothesis and hence classified as neutral."}], "Negative Examples": [{"input": "Premise: A polyploid is simply an organism that contains more than the usual two sets of chromosomes.  \n Hypothesis: A(n) polyploid is an individual with more than the correct number of chromosome sets.", "output": "neutral", "explanation": "The premise explains the meaning of the term and the hypothesis sentence also specifies it correctly. Because the Premise supports the Hypothesis, this is classifies should be classified as entails not as neutral."}, {"input": "Premise: Based on the list provided of the uses of substances 1-7, estimate the pH of each unknown and record the number in the data table in the estimated pH column. \n Hypothesis: If a substance has a ph value greater than 7, that indicates that it is based.", "output": "entails", "explanation": "The premise does not have a fact that can be supported. It is a task that should be carried out to find the pH of the substances. The hypothesis is therefore not supported by the premise. It should be classified as neutral not as entails."}, {"input": "Premise: The phylum for common marigolds is angiosperms. \n Hypothesis: Angiosperms are the most successful phylum of plants.", "output": "entails", "explanation": "The premise states the name for Marigold specifically. Since the hypothesis mentions this as successful phylum and gives no information about marigold being successful or not, this should be classified as neutral."}, {"input": "Premise: Vertebrates are named for vertebrae, the series of bones that make up the vertebral column or backbone. \n Hypothesis: Backbone is another name for the vertebral column.", "output": "neutral", "explanation": "The usage of the word 'or' between the words vertebral column and backbone implies that both the names are the same. The same meaning is conveyed in the Hypothesis too. Therefore this should be classified as entails and not as neutral."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Natural Science"], "Instance": {"id": "task1529-1b487ac7129b4b97a0a6960ccb150cf1", "input": "Premise: If it is the right species of fish, the larvae stay on. \n Hypothesis: Fish hatch into larvae that are different from the adult form of species.", "output": ["neutral"]}, "Instance License": ["Apache 2.0"], "prediction": "entails"}
+{"id": "task1529-08473b4e36514235b8823604e61ffb1b", "Task": "task1529_scitail1.1_classification", "Contributors": "['Krishna Sriharsha Gundu']", "Source": ["scitailv1.1"], "URL": ["http://data.allenai.org/scitail"], "Categories": ["Textual Entailment"], "Reasoning": ["Textual Entailment"], "Definition": ["You are given two sentences. You have to find if there is entailment or agreement of the Hypothesis by the Premise. From the given pair of sentences, you should identify if there is enough information in the Premise to support the claim made in the Hypothesis. The Premise may not exactly be the same as Hypothesis. Your task is to return 'entails' if the premise supports hypothesis else return 'neutral'."], "Positive Examples": [{"input": "Premise: Lyme Disease is caused by a bacterium that's transmitted by tick bite, but many infected people don't remember a bite. \n Hypothesis: Lyme disease is caused by bacteria.", "output": "entails", "explanation": "The premise sentence agrees with the hypothesis that Lyme Disease is a bacterium. The premise also gives additional information about Lyme disease. Therefore Premise entails Hypothesis."}, {"input": "Premise: Corolla Collective term for all the petals of a flower, these petals may be separate or fused together. \n Hypothesis: All of the petals together are called a corolla.", "output": "entails", "explanation": "The premise sentence explains the meaning of Corolla. The hypothesis sentence is explained by the Premise. Since the premise supports/entails the Hypothesis, this is classified as entails."}, {"input": "Premise: This can be dangerous to both plants and animals. \n Hypothesis: Nematodes can be a parasite of both.", "output": "neutral", "explanation": "The premise misses the context to the word 'this'. Therefore it is incomplete. The hypothesis is not supporting the premise. Therefore it is classified as neutral."}, {"input": "Premise: The liver is divided into the right lobe and left lobes. \n Hypothesis: The gallbladder is near the right lobe of the liver.", "output": "neutral", "explanation": "The premise states about the general structure of the liver while the hypothesis is explaining about a specific part of the liver. Therefore this premise does not support the hypothesis and hence classified as neutral."}], "Negative Examples": [{"input": "Premise: A polyploid is simply an organism that contains more than the usual two sets of chromosomes.  \n Hypothesis: A(n) polyploid is an individual with more than the correct number of chromosome sets.", "output": "neutral", "explanation": "The premise explains the meaning of the term and the hypothesis sentence also specifies it correctly. Because the Premise supports the Hypothesis, this is classifies should be classified as entails not as neutral."}, {"input": "Premise: Based on the list provided of the uses of substances 1-7, estimate the pH of each unknown and record the number in the data table in the estimated pH column. \n Hypothesis: If a substance has a ph value greater than 7, that indicates that it is based.", "output": "entails", "explanation": "The premise does not have a fact that can be supported. It is a task that should be carried out to find the pH of the substances. The hypothesis is therefore not supported by the premise. It should be classified as neutral not as entails."}, {"input": "Premise: The phylum for common marigolds is angiosperms. \n Hypothesis: Angiosperms are the most successful phylum of plants.", "output": "entails", "explanation": "The premise states the name for Marigold specifically. Since the hypothesis mentions this as successful phylum and gives no information about marigold being successful or not, this should be classified as neutral."}, {"input": "Premise: Vertebrates are named for vertebrae, the series of bones that make up the vertebral column or backbone. \n Hypothesis: Backbone is another name for the vertebral column.", "output": "neutral", "explanation": "The usage of the word 'or' between the words vertebral column and backbone implies that both the names are the same. The same meaning is conveyed in the Hypothesis too. Therefore this should be classified as entails and not as neutral."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Natural Science"], "Instance": {"id": "task1529-08473b4e36514235b8823604e61ffb1b", "input": "Premise: Competition is growing -- \n Hypothesis: As the population grows, competition for food grows.", "output": ["neutral"]}, "Instance License": ["Apache 2.0"], "prediction": "entails"}
+{"id": "task1529-ab0906a940aa4e4893eefa526a247f1a", "Task": "task1529_scitail1.1_classification", "Contributors": "['Krishna Sriharsha Gundu']", "Source": ["scitailv1.1"], "URL": ["http://data.allenai.org/scitail"], "Categories": ["Textual Entailment"], "Reasoning": ["Textual Entailment"], "Definition": ["You are given two sentences. You have to find if there is entailment or agreement of the Hypothesis by the Premise. From the given pair of sentences, you should identify if there is enough information in the Premise to support the claim made in the Hypothesis. The Premise may not exactly be the same as Hypothesis. Your task is to return 'entails' if the premise supports hypothesis else return 'neutral'."], "Positive Examples": [{"input": "Premise: Lyme Disease is caused by a bacterium that's transmitted by tick bite, but many infected people don't remember a bite. \n Hypothesis: Lyme disease is caused by bacteria.", "output": "entails", "explanation": "The premise sentence agrees with the hypothesis that Lyme Disease is a bacterium. The premise also gives additional information about Lyme disease. Therefore Premise entails Hypothesis."}, {"input": "Premise: Corolla Collective term for all the petals of a flower, these petals may be separate or fused together. \n Hypothesis: All of the petals together are called a corolla.", "output": "entails", "explanation": "The premise sentence explains the meaning of Corolla. The hypothesis sentence is explained by the Premise. Since the premise supports/entails the Hypothesis, this is classified as entails."}, {"input": "Premise: This can be dangerous to both plants and animals. \n Hypothesis: Nematodes can be a parasite of both.", "output": "neutral", "explanation": "The premise misses the context to the word 'this'. Therefore it is incomplete. The hypothesis is not supporting the premise. Therefore it is classified as neutral."}, {"input": "Premise: The liver is divided into the right lobe and left lobes. \n Hypothesis: The gallbladder is near the right lobe of the liver.", "output": "neutral", "explanation": "The premise states about the general structure of the liver while the hypothesis is explaining about a specific part of the liver. Therefore this premise does not support the hypothesis and hence classified as neutral."}], "Negative Examples": [{"input": "Premise: A polyploid is simply an organism that contains more than the usual two sets of chromosomes.  \n Hypothesis: A(n) polyploid is an individual with more than the correct number of chromosome sets.", "output": "neutral", "explanation": "The premise explains the meaning of the term and the hypothesis sentence also specifies it correctly. Because the Premise supports the Hypothesis, this is classifies should be classified as entails not as neutral."}, {"input": "Premise: Based on the list provided of the uses of substances 1-7, estimate the pH of each unknown and record the number in the data table in the estimated pH column. \n Hypothesis: If a substance has a ph value greater than 7, that indicates that it is based.", "output": "entails", "explanation": "The premise does not have a fact that can be supported. It is a task that should be carried out to find the pH of the substances. The hypothesis is therefore not supported by the premise. It should be classified as neutral not as entails."}, {"input": "Premise: The phylum for common marigolds is angiosperms. \n Hypothesis: Angiosperms are the most successful phylum of plants.", "output": "entails", "explanation": "The premise states the name for Marigold specifically. Since the hypothesis mentions this as successful phylum and gives no information about marigold being successful or not, this should be classified as neutral."}, {"input": "Premise: Vertebrates are named for vertebrae, the series of bones that make up the vertebral column or backbone. \n Hypothesis: Backbone is another name for the vertebral column.", "output": "neutral", "explanation": "The usage of the word 'or' between the words vertebral column and backbone implies that both the names are the same. The same meaning is conveyed in the Hypothesis too. Therefore this should be classified as entails and not as neutral."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Natural Science"], "Instance": {"id": "task1529-ab0906a940aa4e4893eefa526a247f1a", "input": "Premise: Thus a stable element such as Carbon has a nucleus with six protons and six neutrons which may be written as 12 6 C or simply 12 C. \n Hypothesis: Carbon atoms have six neutrons as well as six protons.", "output": ["entails"]}, "Instance License": ["Apache 2.0"], "prediction": "entails"}
+{"id": "task1529-ba01486b13af44e48590ceb7e20073b7", "Task": "task1529_scitail1.1_classification", "Contributors": "['Krishna Sriharsha Gundu']", "Source": ["scitailv1.1"], "URL": ["http://data.allenai.org/scitail"], "Categories": ["Textual Entailment"], "Reasoning": ["Textual Entailment"], "Definition": ["You are given two sentences. You have to find if there is entailment or agreement of the Hypothesis by the Premise. From the given pair of sentences, you should identify if there is enough information in the Premise to support the claim made in the Hypothesis. The Premise may not exactly be the same as Hypothesis. Your task is to return 'entails' if the premise supports hypothesis else return 'neutral'."], "Positive Examples": [{"input": "Premise: Lyme Disease is caused by a bacterium that's transmitted by tick bite, but many infected people don't remember a bite. \n Hypothesis: Lyme disease is caused by bacteria.", "output": "entails", "explanation": "The premise sentence agrees with the hypothesis that Lyme Disease is a bacterium. The premise also gives additional information about Lyme disease. Therefore Premise entails Hypothesis."}, {"input": "Premise: Corolla Collective term for all the petals of a flower, these petals may be separate or fused together. \n Hypothesis: All of the petals together are called a corolla.", "output": "entails", "explanation": "The premise sentence explains the meaning of Corolla. The hypothesis sentence is explained by the Premise. Since the premise supports/entails the Hypothesis, this is classified as entails."}, {"input": "Premise: This can be dangerous to both plants and animals. \n Hypothesis: Nematodes can be a parasite of both.", "output": "neutral", "explanation": "The premise misses the context to the word 'this'. Therefore it is incomplete. The hypothesis is not supporting the premise. Therefore it is classified as neutral."}, {"input": "Premise: The liver is divided into the right lobe and left lobes. \n Hypothesis: The gallbladder is near the right lobe of the liver.", "output": "neutral", "explanation": "The premise states about the general structure of the liver while the hypothesis is explaining about a specific part of the liver. Therefore this premise does not support the hypothesis and hence classified as neutral."}], "Negative Examples": [{"input": "Premise: A polyploid is simply an organism that contains more than the usual two sets of chromosomes.  \n Hypothesis: A(n) polyploid is an individual with more than the correct number of chromosome sets.", "output": "neutral", "explanation": "The premise explains the meaning of the term and the hypothesis sentence also specifies it correctly. Because the Premise supports the Hypothesis, this is classifies should be classified as entails not as neutral."}, {"input": "Premise: Based on the list provided of the uses of substances 1-7, estimate the pH of each unknown and record the number in the data table in the estimated pH column. \n Hypothesis: If a substance has a ph value greater than 7, that indicates that it is based.", "output": "entails", "explanation": "The premise does not have a fact that can be supported. It is a task that should be carried out to find the pH of the substances. The hypothesis is therefore not supported by the premise. It should be classified as neutral not as entails."}, {"input": "Premise: The phylum for common marigolds is angiosperms. \n Hypothesis: Angiosperms are the most successful phylum of plants.", "output": "entails", "explanation": "The premise states the name for Marigold specifically. Since the hypothesis mentions this as successful phylum and gives no information about marigold being successful or not, this should be classified as neutral."}, {"input": "Premise: Vertebrates are named for vertebrae, the series of bones that make up the vertebral column or backbone. \n Hypothesis: Backbone is another name for the vertebral column.", "output": "neutral", "explanation": "The usage of the word 'or' between the words vertebral column and backbone implies that both the names are the same. The same meaning is conveyed in the Hypothesis too. Therefore this should be classified as entails and not as neutral."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Natural Science"], "Instance": {"id": "task1529-ba01486b13af44e48590ceb7e20073b7", "input": "Premise: There are some reptiles, such as the boa constrictor and komodo dragon that can reproduce both sexually and asexually, depending on whether a mate is available. \n Hypothesis: Reptiles typically reproduce sexually.", "output": ["neutral"]}, "Instance License": ["Apache 2.0"], "prediction": "entails"}
+{"id": "task202-59e69db7c4464aa4ade00666adb850a2", "Task": "task202_mnli_contradiction_classification", "Contributors": "['Anjana Arunkumar']", "Source": ["multinli"], "URL": ["https://cims.nyu.edu/~sbowman/multinli/paper.pdf"], "Categories": ["Textual Entailment"], "Reasoning": ["Textual Entailment -> Deductive Reasoning", "Commonsense Reasoning"], "Definition": ["In this task, you're given a statement, and three sentences as choices. Your job is to determine which sentence clearly disagrees with the statement. Indicate your answer as '1', '2', or '3' corresponding to the choice number of the selected sentence."], "Positive Examples": [{"input": "Statement: Next to the MGM Grand you will find M and M World, four stories of merchandise and memorabilia dedicated to the candy that doesn't melt in your hand. Choices: 1. The candy has many fans who love its attractions. 2. There's four stories of memorabilia dedicated to a candy. 3. That particular candy melts and becomes difficult to eat.", "output": "3", "explanation": "It is said in the statement that the candy doesn't melt in your hand, but the sentence in choice 3 disagrees with it."}, {"input": "Statment: I've forgotten his name now, confessed Tuppence. Choices: 1. Tuppence forgot his name. 2.Tuppence remembered his name later. 3. Tuppence never could forget his name.", "output": "3", "explanation": "Tuppence had forgotten the name, so choice 3 disagrees with the statement."}, {"input": "Statement: One of the first organizational realignments taking place is in the Office of the Taxpayer Advocate. Choices: 1. The office of the taxpayer advocate is the last to be realigned. 2. The realignment is taking place over a few weeks. 3. The office of the taxpayer advocate is having an organizational realignment.", "output": "1", "explanation": "The office realignment is one of the first taking place. The sentence 1 disagrees with the statement."}, {"input": "Statement: yeah i tell you what though if you go price some of those tennis shoes i can see why now you know they're getting up in the hundred dollar range. Choices: 1. The tennis shoes have a range of prices. 2. The tennis shoes can be in the hundred dollar range. 3. The tennis shoes are not over hundred dollars.", "output": "3", "explanation": "The shoes' price is defnitely over a hundred dollars."}], "Negative Examples": [{"input": "Statement: In 1994, fraction of households owning a personal computer is 0.25. Choices: 1. In 1994, 0.25 of households owned a PC, which was a high sum at the time. 2. In 1984, 0.8 of households owned a PC. In 1994, 0.25 of households owned a PC.", "output": "3", "explanation": "The choice and statement both clearly fully agree that 0.25 of all households had PCs in 1994, hence choice 3 is incorrect."}, {"input": "Statement: You could say you were in an auto accident, and the ambulance driver took you straight to Dr. Famous' office. Choices: 1. Ambulance drivers knew Dr Famous was great for treating famous people. 2. Ambulance drivers just took you to the hospital. 3. Ambulance drivers knew Dr Famous.", "output": "1", "explanation": "It is not clear that Dr. Famous treats famous people though he is known by the ambulance drivers, so the choice neither agrees nor disagrees with the statement and is hence incorrect. "}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["History", "Fiction", "Dialogue", "Law", "Government and Politics"], "Instance": {"id": "task202-59e69db7c4464aa4ade00666adb850a2", "input": "Statement: Our goal is to better serve our client by making GAO more responsive, more flexible - and more focused on our client. Choices:  1. We want to make GAO more focused on its clients. 2. Until now, GAO has completely ignored its clients. 3. We are trying to make GAO less flexible.", "output": ["3"]}, "Instance License": ["OANC"], "prediction": "2"}
+{"id": "task202-d790abb252cf4837a3dc9663814cc91a", "Task": "task202_mnli_contradiction_classification", "Contributors": "['Anjana Arunkumar']", "Source": ["multinli"], "URL": ["https://cims.nyu.edu/~sbowman/multinli/paper.pdf"], "Categories": ["Textual Entailment"], "Reasoning": ["Textual Entailment -> Deductive Reasoning", "Commonsense Reasoning"], "Definition": ["In this task, you're given a statement, and three sentences as choices. Your job is to determine which sentence clearly disagrees with the statement. Indicate your answer as '1', '2', or '3' corresponding to the choice number of the selected sentence."], "Positive Examples": [{"input": "Statement: Next to the MGM Grand you will find M and M World, four stories of merchandise and memorabilia dedicated to the candy that doesn't melt in your hand. Choices: 1. The candy has many fans who love its attractions. 2. There's four stories of memorabilia dedicated to a candy. 3. That particular candy melts and becomes difficult to eat.", "output": "3", "explanation": "It is said in the statement that the candy doesn't melt in your hand, but the sentence in choice 3 disagrees with it."}, {"input": "Statment: I've forgotten his name now, confessed Tuppence. Choices: 1. Tuppence forgot his name. 2.Tuppence remembered his name later. 3. Tuppence never could forget his name.", "output": "3", "explanation": "Tuppence had forgotten the name, so choice 3 disagrees with the statement."}, {"input": "Statement: One of the first organizational realignments taking place is in the Office of the Taxpayer Advocate. Choices: 1. The office of the taxpayer advocate is the last to be realigned. 2. The realignment is taking place over a few weeks. 3. The office of the taxpayer advocate is having an organizational realignment.", "output": "1", "explanation": "The office realignment is one of the first taking place. The sentence 1 disagrees with the statement."}, {"input": "Statement: yeah i tell you what though if you go price some of those tennis shoes i can see why now you know they're getting up in the hundred dollar range. Choices: 1. The tennis shoes have a range of prices. 2. The tennis shoes can be in the hundred dollar range. 3. The tennis shoes are not over hundred dollars.", "output": "3", "explanation": "The shoes' price is defnitely over a hundred dollars."}], "Negative Examples": [{"input": "Statement: In 1994, fraction of households owning a personal computer is 0.25. Choices: 1. In 1994, 0.25 of households owned a PC, which was a high sum at the time. 2. In 1984, 0.8 of households owned a PC. In 1994, 0.25 of households owned a PC.", "output": "3", "explanation": "The choice and statement both clearly fully agree that 0.25 of all households had PCs in 1994, hence choice 3 is incorrect."}, {"input": "Statement: You could say you were in an auto accident, and the ambulance driver took you straight to Dr. Famous' office. Choices: 1. Ambulance drivers knew Dr Famous was great for treating famous people. 2. Ambulance drivers just took you to the hospital. 3. Ambulance drivers knew Dr Famous.", "output": "1", "explanation": "It is not clear that Dr. Famous treats famous people though he is known by the ambulance drivers, so the choice neither agrees nor disagrees with the statement and is hence incorrect. "}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["History", "Fiction", "Dialogue", "Law", "Government and Politics"], "Instance": {"id": "task202-d790abb252cf4837a3dc9663814cc91a", "input": "Statement: (Bennett himself appears to share this view, terming gays, as a group, wealthy and well educated. Choices:  1. In general, Bennet classifies gays as tending to be poor and uneducated. 2. Bennett believes that only gay people are well educated. 3. One person thinks that gay people have lots of money.", "output": ["1"]}, "Instance License": ["OANC"], "prediction": "2"}
+{"id": "task202-04c3cbe19ef24505a8baa7bf6a455ca4", "Task": "task202_mnli_contradiction_classification", "Contributors": "['Anjana Arunkumar']", "Source": ["multinli"], "URL": ["https://cims.nyu.edu/~sbowman/multinli/paper.pdf"], "Categories": ["Textual Entailment"], "Reasoning": ["Textual Entailment -> Deductive Reasoning", "Commonsense Reasoning"], "Definition": ["In this task, you're given a statement, and three sentences as choices. Your job is to determine which sentence clearly disagrees with the statement. Indicate your answer as '1', '2', or '3' corresponding to the choice number of the selected sentence."], "Positive Examples": [{"input": "Statement: Next to the MGM Grand you will find M and M World, four stories of merchandise and memorabilia dedicated to the candy that doesn't melt in your hand. Choices: 1. The candy has many fans who love its attractions. 2. There's four stories of memorabilia dedicated to a candy. 3. That particular candy melts and becomes difficult to eat.", "output": "3", "explanation": "It is said in the statement that the candy doesn't melt in your hand, but the sentence in choice 3 disagrees with it."}, {"input": "Statment: I've forgotten his name now, confessed Tuppence. Choices: 1. Tuppence forgot his name. 2.Tuppence remembered his name later. 3. Tuppence never could forget his name.", "output": "3", "explanation": "Tuppence had forgotten the name, so choice 3 disagrees with the statement."}, {"input": "Statement: One of the first organizational realignments taking place is in the Office of the Taxpayer Advocate. Choices: 1. The office of the taxpayer advocate is the last to be realigned. 2. The realignment is taking place over a few weeks. 3. The office of the taxpayer advocate is having an organizational realignment.", "output": "1", "explanation": "The office realignment is one of the first taking place. The sentence 1 disagrees with the statement."}, {"input": "Statement: yeah i tell you what though if you go price some of those tennis shoes i can see why now you know they're getting up in the hundred dollar range. Choices: 1. The tennis shoes have a range of prices. 2. The tennis shoes can be in the hundred dollar range. 3. The tennis shoes are not over hundred dollars.", "output": "3", "explanation": "The shoes' price is defnitely over a hundred dollars."}], "Negative Examples": [{"input": "Statement: In 1994, fraction of households owning a personal computer is 0.25. Choices: 1. In 1994, 0.25 of households owned a PC, which was a high sum at the time. 2. In 1984, 0.8 of households owned a PC. In 1994, 0.25 of households owned a PC.", "output": "3", "explanation": "The choice and statement both clearly fully agree that 0.25 of all households had PCs in 1994, hence choice 3 is incorrect."}, {"input": "Statement: You could say you were in an auto accident, and the ambulance driver took you straight to Dr. Famous' office. Choices: 1. Ambulance drivers knew Dr Famous was great for treating famous people. 2. Ambulance drivers just took you to the hospital. 3. Ambulance drivers knew Dr Famous.", "output": "1", "explanation": "It is not clear that Dr. Famous treats famous people though he is known by the ambulance drivers, so the choice neither agrees nor disagrees with the statement and is hence incorrect. "}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["History", "Fiction", "Dialogue", "Law", "Government and Politics"], "Instance": {"id": "task202-04c3cbe19ef24505a8baa7bf6a455ca4", "input": "Statement: The valuation of Work Loss Days presented in our national benefits summaries, however, incorporates county-specific adjustment factors to account for variations in regional income. Choices:  1. The valuation of Work Loss Days incorporates adjustment factors. 2. The Work Loss Days will appear to be inflated at first glance. 3. The valuation of Work Loss days is consistent across counties.", "output": ["3"]}, "Instance License": ["OANC"], "prediction": "1"}
+{"id": "task202-4ec58f4a37ad42d9b1c28aa2a551dd4c", "Task": "task202_mnli_contradiction_classification", "Contributors": "['Anjana Arunkumar']", "Source": ["multinli"], "URL": ["https://cims.nyu.edu/~sbowman/multinli/paper.pdf"], "Categories": ["Textual Entailment"], "Reasoning": ["Textual Entailment -> Deductive Reasoning", "Commonsense Reasoning"], "Definition": ["In this task, you're given a statement, and three sentences as choices. Your job is to determine which sentence clearly disagrees with the statement. Indicate your answer as '1', '2', or '3' corresponding to the choice number of the selected sentence."], "Positive Examples": [{"input": "Statement: Next to the MGM Grand you will find M and M World, four stories of merchandise and memorabilia dedicated to the candy that doesn't melt in your hand. Choices: 1. The candy has many fans who love its attractions. 2. There's four stories of memorabilia dedicated to a candy. 3. That particular candy melts and becomes difficult to eat.", "output": "3", "explanation": "It is said in the statement that the candy doesn't melt in your hand, but the sentence in choice 3 disagrees with it."}, {"input": "Statment: I've forgotten his name now, confessed Tuppence. Choices: 1. Tuppence forgot his name. 2.Tuppence remembered his name later. 3. Tuppence never could forget his name.", "output": "3", "explanation": "Tuppence had forgotten the name, so choice 3 disagrees with the statement."}, {"input": "Statement: One of the first organizational realignments taking place is in the Office of the Taxpayer Advocate. Choices: 1. The office of the taxpayer advocate is the last to be realigned. 2. The realignment is taking place over a few weeks. 3. The office of the taxpayer advocate is having an organizational realignment.", "output": "1", "explanation": "The office realignment is one of the first taking place. The sentence 1 disagrees with the statement."}, {"input": "Statement: yeah i tell you what though if you go price some of those tennis shoes i can see why now you know they're getting up in the hundred dollar range. Choices: 1. The tennis shoes have a range of prices. 2. The tennis shoes can be in the hundred dollar range. 3. The tennis shoes are not over hundred dollars.", "output": "3", "explanation": "The shoes' price is defnitely over a hundred dollars."}], "Negative Examples": [{"input": "Statement: In 1994, fraction of households owning a personal computer is 0.25. Choices: 1. In 1994, 0.25 of households owned a PC, which was a high sum at the time. 2. In 1984, 0.8 of households owned a PC. In 1994, 0.25 of households owned a PC.", "output": "3", "explanation": "The choice and statement both clearly fully agree that 0.25 of all households had PCs in 1994, hence choice 3 is incorrect."}, {"input": "Statement: You could say you were in an auto accident, and the ambulance driver took you straight to Dr. Famous' office. Choices: 1. Ambulance drivers knew Dr Famous was great for treating famous people. 2. Ambulance drivers just took you to the hospital. 3. Ambulance drivers knew Dr Famous.", "output": "1", "explanation": "It is not clear that Dr. Famous treats famous people though he is known by the ambulance drivers, so the choice neither agrees nor disagrees with the statement and is hence incorrect. "}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["History", "Fiction", "Dialogue", "Law", "Government and Politics"], "Instance": {"id": "task202-4ec58f4a37ad42d9b1c28aa2a551dd4c", "input": "Statement: Chronic Illness Choices:  1. The illness was chronic. 2. It is not possible for ilnesses to be chronic. 3. There are a lot of chronic illnesses.", "output": ["2"]}, "Instance License": ["OANC"], "prediction": "2"}
+{"id": "task202-1861bf0624f24fba8fd491db2f3c793b", "Task": "task202_mnli_contradiction_classification", "Contributors": "['Anjana Arunkumar']", "Source": ["multinli"], "URL": ["https://cims.nyu.edu/~sbowman/multinli/paper.pdf"], "Categories": ["Textual Entailment"], "Reasoning": ["Textual Entailment -> Deductive Reasoning", "Commonsense Reasoning"], "Definition": ["In this task, you're given a statement, and three sentences as choices. Your job is to determine which sentence clearly disagrees with the statement. Indicate your answer as '1', '2', or '3' corresponding to the choice number of the selected sentence."], "Positive Examples": [{"input": "Statement: Next to the MGM Grand you will find M and M World, four stories of merchandise and memorabilia dedicated to the candy that doesn't melt in your hand. Choices: 1. The candy has many fans who love its attractions. 2. There's four stories of memorabilia dedicated to a candy. 3. That particular candy melts and becomes difficult to eat.", "output": "3", "explanation": "It is said in the statement that the candy doesn't melt in your hand, but the sentence in choice 3 disagrees with it."}, {"input": "Statment: I've forgotten his name now, confessed Tuppence. Choices: 1. Tuppence forgot his name. 2.Tuppence remembered his name later. 3. Tuppence never could forget his name.", "output": "3", "explanation": "Tuppence had forgotten the name, so choice 3 disagrees with the statement."}, {"input": "Statement: One of the first organizational realignments taking place is in the Office of the Taxpayer Advocate. Choices: 1. The office of the taxpayer advocate is the last to be realigned. 2. The realignment is taking place over a few weeks. 3. The office of the taxpayer advocate is having an organizational realignment.", "output": "1", "explanation": "The office realignment is one of the first taking place. The sentence 1 disagrees with the statement."}, {"input": "Statement: yeah i tell you what though if you go price some of those tennis shoes i can see why now you know they're getting up in the hundred dollar range. Choices: 1. The tennis shoes have a range of prices. 2. The tennis shoes can be in the hundred dollar range. 3. The tennis shoes are not over hundred dollars.", "output": "3", "explanation": "The shoes' price is defnitely over a hundred dollars."}], "Negative Examples": [{"input": "Statement: In 1994, fraction of households owning a personal computer is 0.25. Choices: 1. In 1994, 0.25 of households owned a PC, which was a high sum at the time. 2. In 1984, 0.8 of households owned a PC. In 1994, 0.25 of households owned a PC.", "output": "3", "explanation": "The choice and statement both clearly fully agree that 0.25 of all households had PCs in 1994, hence choice 3 is incorrect."}, {"input": "Statement: You could say you were in an auto accident, and the ambulance driver took you straight to Dr. Famous' office. Choices: 1. Ambulance drivers knew Dr Famous was great for treating famous people. 2. Ambulance drivers just took you to the hospital. 3. Ambulance drivers knew Dr Famous.", "output": "1", "explanation": "It is not clear that Dr. Famous treats famous people though he is known by the ambulance drivers, so the choice neither agrees nor disagrees with the statement and is hence incorrect. "}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["History", "Fiction", "Dialogue", "Law", "Government and Politics"], "Instance": {"id": "task202-1861bf0624f24fba8fd491db2f3c793b", "input": "Statement: First, the CEF analysis was benchmarked to a 1999 reference case. Choices:  1. The CEF analysis was benchmarked to a 1999 reference case. 2. The CEF analysis was not compared to any other case. 3. The 1999 case showed better performance in comparison.", "output": ["2"]}, "Instance License": ["OANC"], "prediction": "2"}
+{"id": "task670-d7123323920448c080e152cfc540c705", "Task": "task670_ambigqa_question_generation", "Contributors": "['Mirali Purohit']", "Source": ["ambigqa"], "URL": ["https://nlp.cs.washington.edu/ambigqa/"], "Categories": ["Question Rewriting"], "Reasoning": ["Abductive Reasoning"], "Definition": ["In this task, you're given an ambiguous question (which can be answered in more than one way). Your task is to write a question that clarifies the given question in such a way that the generated question has one unique answer."], "Positive Examples": [{"input": "Lucifer how many episodes are in season 3?", "output": "How many episodes of season 3 of Lucifer were there, including bonus episodes?", "explanation": "The generated question clarifies the input question by asking about bonus episodes because if the question is about regular episodes only then the answer will be different than including the bonus episodes."}, {"input": "What is the tallest ride at six flags over Texas?", "output": "What is the tallest roller coaster at six flags over Texas 2001?", "explanation": "The generated output elaborates the input question by mentioning the year in question because there is a different answer for this question for the year 1990, 2001 and 2011."}, {"input": "Who won the final hoh big brother 20?", "output": "Who won the Final HoH in the American reality show Big Brother 20?", "explanation": "The generated output elaborates the input question by restricting the reality show. There are  two 'Big brother 20' shows, American and British."}], "Negative Examples": [{"input": "Lucifer how many episodes are in season 3?", "output": "How many episodes of season 4 of Lucifer were there, including bonus episodes?", "explanation": "The generated output is incorrect because it changed the season number from 3 to 4. The output should elaborate on the input question and should not change any entity from the input."}, {"input": "What is the tallest ride at six flags over texas?", "output": "What is the tallest roller coaster at six flags over Tempe 2001?", "explanation": "The generated output is incorrect because it changed the city from Texas to Tempe. The output should elaborate on the input question and should not change any entity from the input."}, {"input": "Who won the final hoh big brother 20?", "output": "Who lose the Final HoH in the American reality show Big Brother 20?", "explanation": "The generated output asks about who loses the final Hoh instead of asking win. The output should elaborate on the input question and should not change any entity from the input."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Wikipedia"], "Instance": {"id": "task670-d7123323920448c080e152cfc540c705", "input": "Who invented the process to remove impurities by blasts of cold air blown through heated iron?", "output": ["What Englishman invented the process to remove impurities by blasts of cold air blown through heated iron?", "What American independently discovered  the process to remove impurities by blasts of cold air blown through heated iron?"]}, "Instance License": ["Unknown"], "prediction": "Who invented the process to remove impurities by blasts of cold air blown through heated iron?"}
+{"id": "task670-139f85c24659451b99cf8a4060538a8f", "Task": "task670_ambigqa_question_generation", "Contributors": "['Mirali Purohit']", "Source": ["ambigqa"], "URL": ["https://nlp.cs.washington.edu/ambigqa/"], "Categories": ["Question Rewriting"], "Reasoning": ["Abductive Reasoning"], "Definition": ["In this task, you're given an ambiguous question (which can be answered in more than one way). Your task is to write a question that clarifies the given question in such a way that the generated question has one unique answer."], "Positive Examples": [{"input": "Lucifer how many episodes are in season 3?", "output": "How many episodes of season 3 of Lucifer were there, including bonus episodes?", "explanation": "The generated question clarifies the input question by asking about bonus episodes because if the question is about regular episodes only then the answer will be different than including the bonus episodes."}, {"input": "What is the tallest ride at six flags over Texas?", "output": "What is the tallest roller coaster at six flags over Texas 2001?", "explanation": "The generated output elaborates the input question by mentioning the year in question because there is a different answer for this question for the year 1990, 2001 and 2011."}, {"input": "Who won the final hoh big brother 20?", "output": "Who won the Final HoH in the American reality show Big Brother 20?", "explanation": "The generated output elaborates the input question by restricting the reality show. There are  two 'Big brother 20' shows, American and British."}], "Negative Examples": [{"input": "Lucifer how many episodes are in season 3?", "output": "How many episodes of season 4 of Lucifer were there, including bonus episodes?", "explanation": "The generated output is incorrect because it changed the season number from 3 to 4. The output should elaborate on the input question and should not change any entity from the input."}, {"input": "What is the tallest ride at six flags over texas?", "output": "What is the tallest roller coaster at six flags over Tempe 2001?", "explanation": "The generated output is incorrect because it changed the city from Texas to Tempe. The output should elaborate on the input question and should not change any entity from the input."}, {"input": "Who won the final hoh big brother 20?", "output": "Who lose the Final HoH in the American reality show Big Brother 20?", "explanation": "The generated output asks about who loses the final Hoh instead of asking win. The output should elaborate on the input question and should not change any entity from the input."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Wikipedia"], "Instance": {"id": "task670-139f85c24659451b99cf8a4060538a8f", "input": "How old do you have to be to get a tattoo in indiana?", "output": ["How old do you have to be to get a tattoo in Indiana without parental consent?", "How old can you be to get a tattoo in Indiana with parental consent?"]}, "Instance License": ["Unknown"], "prediction": "How old do you have to be to get a tattoo in Indiana?"}
+{"id": "task670-30a91fd50d1648049ff3d57d37e41a19", "Task": "task670_ambigqa_question_generation", "Contributors": "['Mirali Purohit']", "Source": ["ambigqa"], "URL": ["https://nlp.cs.washington.edu/ambigqa/"], "Categories": ["Question Rewriting"], "Reasoning": ["Abductive Reasoning"], "Definition": ["In this task, you're given an ambiguous question (which can be answered in more than one way). Your task is to write a question that clarifies the given question in such a way that the generated question has one unique answer."], "Positive Examples": [{"input": "Lucifer how many episodes are in season 3?", "output": "How many episodes of season 3 of Lucifer were there, including bonus episodes?", "explanation": "The generated question clarifies the input question by asking about bonus episodes because if the question is about regular episodes only then the answer will be different than including the bonus episodes."}, {"input": "What is the tallest ride at six flags over Texas?", "output": "What is the tallest roller coaster at six flags over Texas 2001?", "explanation": "The generated output elaborates the input question by mentioning the year in question because there is a different answer for this question for the year 1990, 2001 and 2011."}, {"input": "Who won the final hoh big brother 20?", "output": "Who won the Final HoH in the American reality show Big Brother 20?", "explanation": "The generated output elaborates the input question by restricting the reality show. There are  two 'Big brother 20' shows, American and British."}], "Negative Examples": [{"input": "Lucifer how many episodes are in season 3?", "output": "How many episodes of season 4 of Lucifer were there, including bonus episodes?", "explanation": "The generated output is incorrect because it changed the season number from 3 to 4. The output should elaborate on the input question and should not change any entity from the input."}, {"input": "What is the tallest ride at six flags over texas?", "output": "What is the tallest roller coaster at six flags over Tempe 2001?", "explanation": "The generated output is incorrect because it changed the city from Texas to Tempe. The output should elaborate on the input question and should not change any entity from the input."}, {"input": "Who won the final hoh big brother 20?", "output": "Who lose the Final HoH in the American reality show Big Brother 20?", "explanation": "The generated output asks about who loses the final Hoh instead of asking win. The output should elaborate on the input question and should not change any entity from the input."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Wikipedia"], "Instance": {"id": "task670-30a91fd50d1648049ff3d57d37e41a19", "input": "When did the old age pension start in australia?", "output": ["When did an old age pension start in parts of australia?", "When did the nationwide old age pension take effect in australia?"]}, "Instance License": ["Unknown"], "prediction": "What year did the old age pension start in Australia?"}
+{"id": "task670-f156721eb368468b99553d9791cb7dab", "Task": "task670_ambigqa_question_generation", "Contributors": "['Mirali Purohit']", "Source": ["ambigqa"], "URL": ["https://nlp.cs.washington.edu/ambigqa/"], "Categories": ["Question Rewriting"], "Reasoning": ["Abductive Reasoning"], "Definition": ["In this task, you're given an ambiguous question (which can be answered in more than one way). Your task is to write a question that clarifies the given question in such a way that the generated question has one unique answer."], "Positive Examples": [{"input": "Lucifer how many episodes are in season 3?", "output": "How many episodes of season 3 of Lucifer were there, including bonus episodes?", "explanation": "The generated question clarifies the input question by asking about bonus episodes because if the question is about regular episodes only then the answer will be different than including the bonus episodes."}, {"input": "What is the tallest ride at six flags over Texas?", "output": "What is the tallest roller coaster at six flags over Texas 2001?", "explanation": "The generated output elaborates the input question by mentioning the year in question because there is a different answer for this question for the year 1990, 2001 and 2011."}, {"input": "Who won the final hoh big brother 20?", "output": "Who won the Final HoH in the American reality show Big Brother 20?", "explanation": "The generated output elaborates the input question by restricting the reality show. There are  two 'Big brother 20' shows, American and British."}], "Negative Examples": [{"input": "Lucifer how many episodes are in season 3?", "output": "How many episodes of season 4 of Lucifer were there, including bonus episodes?", "explanation": "The generated output is incorrect because it changed the season number from 3 to 4. The output should elaborate on the input question and should not change any entity from the input."}, {"input": "What is the tallest ride at six flags over texas?", "output": "What is the tallest roller coaster at six flags over Tempe 2001?", "explanation": "The generated output is incorrect because it changed the city from Texas to Tempe. The output should elaborate on the input question and should not change any entity from the input."}, {"input": "Who won the final hoh big brother 20?", "output": "Who lose the Final HoH in the American reality show Big Brother 20?", "explanation": "The generated output asks about who loses the final Hoh instead of asking win. The output should elaborate on the input question and should not change any entity from the input."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Wikipedia"], "Instance": {"id": "task670-f156721eb368468b99553d9791cb7dab", "input": "Who wrote the music for shrek the musical?", "output": ["Who wrote the music scores for shrek the musical?", "Who wrote the music lyrics for shrek the musical?"]}, "Instance License": ["Unknown"], "prediction": "Who wrote the music for Shrek the Musical?"}
+{"id": "task670-be807929087a40a7b1f57499121fa903", "Task": "task670_ambigqa_question_generation", "Contributors": "['Mirali Purohit']", "Source": ["ambigqa"], "URL": ["https://nlp.cs.washington.edu/ambigqa/"], "Categories": ["Question Rewriting"], "Reasoning": ["Abductive Reasoning"], "Definition": ["In this task, you're given an ambiguous question (which can be answered in more than one way). Your task is to write a question that clarifies the given question in such a way that the generated question has one unique answer."], "Positive Examples": [{"input": "Lucifer how many episodes are in season 3?", "output": "How many episodes of season 3 of Lucifer were there, including bonus episodes?", "explanation": "The generated question clarifies the input question by asking about bonus episodes because if the question is about regular episodes only then the answer will be different than including the bonus episodes."}, {"input": "What is the tallest ride at six flags over Texas?", "output": "What is the tallest roller coaster at six flags over Texas 2001?", "explanation": "The generated output elaborates the input question by mentioning the year in question because there is a different answer for this question for the year 1990, 2001 and 2011."}, {"input": "Who won the final hoh big brother 20?", "output": "Who won the Final HoH in the American reality show Big Brother 20?", "explanation": "The generated output elaborates the input question by restricting the reality show. There are  two 'Big brother 20' shows, American and British."}], "Negative Examples": [{"input": "Lucifer how many episodes are in season 3?", "output": "How many episodes of season 4 of Lucifer were there, including bonus episodes?", "explanation": "The generated output is incorrect because it changed the season number from 3 to 4. The output should elaborate on the input question and should not change any entity from the input."}, {"input": "What is the tallest ride at six flags over texas?", "output": "What is the tallest roller coaster at six flags over Tempe 2001?", "explanation": "The generated output is incorrect because it changed the city from Texas to Tempe. The output should elaborate on the input question and should not change any entity from the input."}, {"input": "Who won the final hoh big brother 20?", "output": "Who lose the Final HoH in the American reality show Big Brother 20?", "explanation": "The generated output asks about who loses the final Hoh instead of asking win. The output should elaborate on the input question and should not change any entity from the input."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Wikipedia"], "Instance": {"id": "task670-be807929087a40a7b1f57499121fa903", "input": "What is the scientific name for a red fox?", "output": ["What is the scientific name for all red foxes?", "What is the scientific name for a european red fox?", "What is the scientific name for the red foxes in Alaska and western Canada?", "What is the scientific name for the red foxes in the rocky mountains, the cascade range, and sierra nevada?", "What is the scientific name for the red foxes in Sacramento Valley?"]}, "Instance License": ["Unknown"], "prediction": "What is the scientific name for a red fox?"}
+{"id": "task1393-830d380c251f430b9f828d4589338f42", "Task": "task1393_superglue_copa_text_completion", "Contributors": "['Yeganeh Kordi']", "Source": ["copa"], "URL": ["http://people.ict.usc.edu/~gordon/copa.html"], "Categories": ["Cause Effect Classification"], "Reasoning": ["Causal Reasoning"], "Definition": ["In this task, you are given a premise sentence, two possible options and a question word. If the question was cause you should select the option that is a possible cause of the premise sentence, and if the question word was effect you should find the option which is a possible effect of the premise sentence. Answer with \"A\" or \"B\"."], "Positive Examples": [{"input": "The animal species became endangered. (A) Their habitat was destroyed. (B) Their predators went extinct., Question: cause", "output": "A", "explanation": "The question word is cause, so we should find the possible cause of the premise. Option A can be the cause of the premise, and the output should be \"A\"."}, {"input": "The bar closed. (A) It was crowded. (B) It was 3 AM., Question: cause", "output": "B", "explanation": "The bar was closed bacause it was 3 AM. So the output should be \"B\"."}, {"input": "The man was lost. (A) He asked for directions. (B) He drew a map., Question: effect", "output": "A", "explanation": "We are looking for the effect of the premise. The plausible effect of the man being lost can be asking for directions. So, the output should be \"A\"."}], "Negative Examples": [{"input": "The woman was arrested. (A) She checked into rehab. (B) She committed assault., Question: cause", "output": "A", "explanation": "We are looking for the cause of the premise. The plausible cause of the woman being arrested can be committing assault, and checking into rehab can't be the cause of premise. So, the given output is incorrect."}, {"input": "The man was lost. (A) He asked for directions. (B) He drew a map., Question: effect", "output": "He asked for directions.", "explanation": "The output should be \"A\" or \"B\" and other answers are not acceptable."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Web"], "Instance": {"id": "task1393-830d380c251f430b9f828d4589338f42", "input": "The woman banished the children from her property. (A) The children hit a ball into her yard. (B) The children trampled through her garden., Question: cause", "output": ["B"]}, "Instance License": ["BSD 2-Clause"], "prediction": "A"}
+{"id": "task1393-67d6c942227c43b0bfbdb3ee0c968adc", "Task": "task1393_superglue_copa_text_completion", "Contributors": "['Yeganeh Kordi']", "Source": ["copa"], "URL": ["http://people.ict.usc.edu/~gordon/copa.html"], "Categories": ["Cause Effect Classification"], "Reasoning": ["Causal Reasoning"], "Definition": ["In this task, you are given a premise sentence, two possible options and a question word. If the question was cause you should select the option that is a possible cause of the premise sentence, and if the question word was effect you should find the option which is a possible effect of the premise sentence. Answer with \"A\" or \"B\"."], "Positive Examples": [{"input": "The animal species became endangered. (A) Their habitat was destroyed. (B) Their predators went extinct., Question: cause", "output": "A", "explanation": "The question word is cause, so we should find the possible cause of the premise. Option A can be the cause of the premise, and the output should be \"A\"."}, {"input": "The bar closed. (A) It was crowded. (B) It was 3 AM., Question: cause", "output": "B", "explanation": "The bar was closed bacause it was 3 AM. So the output should be \"B\"."}, {"input": "The man was lost. (A) He asked for directions. (B) He drew a map., Question: effect", "output": "A", "explanation": "We are looking for the effect of the premise. The plausible effect of the man being lost can be asking for directions. So, the output should be \"A\"."}], "Negative Examples": [{"input": "The woman was arrested. (A) She checked into rehab. (B) She committed assault., Question: cause", "output": "A", "explanation": "We are looking for the cause of the premise. The plausible cause of the woman being arrested can be committing assault, and checking into rehab can't be the cause of premise. So, the given output is incorrect."}, {"input": "The man was lost. (A) He asked for directions. (B) He drew a map., Question: effect", "output": "He asked for directions.", "explanation": "The output should be \"A\" or \"B\" and other answers are not acceptable."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Web"], "Instance": {"id": "task1393-67d6c942227c43b0bfbdb3ee0c968adc", "input": "I decided to stay home for the night. (A) The forecast called for storms. (B) My friends urged me to go out., Question: cause", "output": ["A"]}, "Instance License": ["BSD 2-Clause"], "prediction": "B"}
+{"id": "task1393-b1d3dbfa00f949f59cd8731aac01efec", "Task": "task1393_superglue_copa_text_completion", "Contributors": "['Yeganeh Kordi']", "Source": ["copa"], "URL": ["http://people.ict.usc.edu/~gordon/copa.html"], "Categories": ["Cause Effect Classification"], "Reasoning": ["Causal Reasoning"], "Definition": ["In this task, you are given a premise sentence, two possible options and a question word. If the question was cause you should select the option that is a possible cause of the premise sentence, and if the question word was effect you should find the option which is a possible effect of the premise sentence. Answer with \"A\" or \"B\"."], "Positive Examples": [{"input": "The animal species became endangered. (A) Their habitat was destroyed. (B) Their predators went extinct., Question: cause", "output": "A", "explanation": "The question word is cause, so we should find the possible cause of the premise. Option A can be the cause of the premise, and the output should be \"A\"."}, {"input": "The bar closed. (A) It was crowded. (B) It was 3 AM., Question: cause", "output": "B", "explanation": "The bar was closed bacause it was 3 AM. So the output should be \"B\"."}, {"input": "The man was lost. (A) He asked for directions. (B) He drew a map., Question: effect", "output": "A", "explanation": "We are looking for the effect of the premise. The plausible effect of the man being lost can be asking for directions. So, the output should be \"A\"."}], "Negative Examples": [{"input": "The woman was arrested. (A) She checked into rehab. (B) She committed assault., Question: cause", "output": "A", "explanation": "We are looking for the cause of the premise. The plausible cause of the woman being arrested can be committing assault, and checking into rehab can't be the cause of premise. So, the given output is incorrect."}, {"input": "The man was lost. (A) He asked for directions. (B) He drew a map., Question: effect", "output": "He asked for directions.", "explanation": "The output should be \"A\" or \"B\" and other answers are not acceptable."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Web"], "Instance": {"id": "task1393-b1d3dbfa00f949f59cd8731aac01efec", "input": "The doctor x-rayed the patient's arm. (A) He discovered that the patient's arm was broken. (B) He put the patient's arm in a cast., Question: effect", "output": ["A"]}, "Instance License": ["BSD 2-Clause"], "prediction": "A"}
+{"id": "task1393-8723a91bf5bf43718813f414e4ad48b4", "Task": "task1393_superglue_copa_text_completion", "Contributors": "['Yeganeh Kordi']", "Source": ["copa"], "URL": ["http://people.ict.usc.edu/~gordon/copa.html"], "Categories": ["Cause Effect Classification"], "Reasoning": ["Causal Reasoning"], "Definition": ["In this task, you are given a premise sentence, two possible options and a question word. If the question was cause you should select the option that is a possible cause of the premise sentence, and if the question word was effect you should find the option which is a possible effect of the premise sentence. Answer with \"A\" or \"B\"."], "Positive Examples": [{"input": "The animal species became endangered. (A) Their habitat was destroyed. (B) Their predators went extinct., Question: cause", "output": "A", "explanation": "The question word is cause, so we should find the possible cause of the premise. Option A can be the cause of the premise, and the output should be \"A\"."}, {"input": "The bar closed. (A) It was crowded. (B) It was 3 AM., Question: cause", "output": "B", "explanation": "The bar was closed bacause it was 3 AM. So the output should be \"B\"."}, {"input": "The man was lost. (A) He asked for directions. (B) He drew a map., Question: effect", "output": "A", "explanation": "We are looking for the effect of the premise. The plausible effect of the man being lost can be asking for directions. So, the output should be \"A\"."}], "Negative Examples": [{"input": "The woman was arrested. (A) She checked into rehab. (B) She committed assault., Question: cause", "output": "A", "explanation": "We are looking for the cause of the premise. The plausible cause of the woman being arrested can be committing assault, and checking into rehab can't be the cause of premise. So, the given output is incorrect."}, {"input": "The man was lost. (A) He asked for directions. (B) He drew a map., Question: effect", "output": "He asked for directions.", "explanation": "The output should be \"A\" or \"B\" and other answers are not acceptable."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Web"], "Instance": {"id": "task1393-8723a91bf5bf43718813f414e4ad48b4", "input": "The woman hummed to herself. (A) She was nervous. (B) She was in a good mood., Question: cause", "output": ["B"]}, "Instance License": ["BSD 2-Clause"], "prediction": "B"}
+{"id": "task1393-30eb4a38cc5245698f9219c2f76d70eb", "Task": "task1393_superglue_copa_text_completion", "Contributors": "['Yeganeh Kordi']", "Source": ["copa"], "URL": ["http://people.ict.usc.edu/~gordon/copa.html"], "Categories": ["Cause Effect Classification"], "Reasoning": ["Causal Reasoning"], "Definition": ["In this task, you are given a premise sentence, two possible options and a question word. If the question was cause you should select the option that is a possible cause of the premise sentence, and if the question word was effect you should find the option which is a possible effect of the premise sentence. Answer with \"A\" or \"B\"."], "Positive Examples": [{"input": "The animal species became endangered. (A) Their habitat was destroyed. (B) Their predators went extinct., Question: cause", "output": "A", "explanation": "The question word is cause, so we should find the possible cause of the premise. Option A can be the cause of the premise, and the output should be \"A\"."}, {"input": "The bar closed. (A) It was crowded. (B) It was 3 AM., Question: cause", "output": "B", "explanation": "The bar was closed bacause it was 3 AM. So the output should be \"B\"."}, {"input": "The man was lost. (A) He asked for directions. (B) He drew a map., Question: effect", "output": "A", "explanation": "We are looking for the effect of the premise. The plausible effect of the man being lost can be asking for directions. So, the output should be \"A\"."}], "Negative Examples": [{"input": "The woman was arrested. (A) She checked into rehab. (B) She committed assault., Question: cause", "output": "A", "explanation": "We are looking for the cause of the premise. The plausible cause of the woman being arrested can be committing assault, and checking into rehab can't be the cause of premise. So, the given output is incorrect."}, {"input": "The man was lost. (A) He asked for directions. (B) He drew a map., Question: effect", "output": "He asked for directions.", "explanation": "The output should be \"A\" or \"B\" and other answers are not acceptable."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Web"], "Instance": {"id": "task1393-30eb4a38cc5245698f9219c2f76d70eb", "input": "The tenant misplaced his keys to his apartment. (A) His landlord unlocked the door. (B) His landlord repaired the door., Question: effect", "output": ["A"]}, "Instance License": ["BSD 2-Clause"], "prediction": "A"}
+{"id": "task1344-f77f75e9d3df44b989a11a8128f18359", "Task": "task1344_glue_entailment_classification", "Contributors": "['Arit Chanda']", "Source": ["rte"], "URL": ["https://dl.fbaipublicfiles.com/glue/data/RTE.zip"], "Categories": ["Textual Entailment"], "Reasoning": ["Textual Entailment -> Deductive Reasoning"], "Definition": ["In this task, you're given two sentences. Indicate if the first sentence clearly entails the second sentence (i.e., one can conclude the 2nd sentence by reading the 1st one). Indicate your answer with '1' if the first sentence entails the second sentence, otherwise answer with '0'."], "Positive Examples": [{"input": "Sentence 1: No Weapons of Mass Destruction Found in Iraq Yet. Sentence 2:Weapons of Mass Destruction Found in Iraq.", "output": "0", "explanation": "In our first statement we clearly say that Iraq does not have any weapon of mass destruction but the second sentence says that weapon of mass destruction is found in Iraq which is contradiction. Hence output will be 0 for non entailment."}, {"input": "Sentence 1: A place of sorrow, after Pope John Paul II died, became a place of celebration, as Roman Catholic faithful gathered in downtown Chicago to mark the installation of new Pope Benedict XVI. Sentence 2: Pope Benedict XVI is the new leader of the Roman Catholic Church.", "output": "1", "explanation": "In the given first sentence we can clearly understand that Pope John Paul II has died and Pope Benedict XVI was elected as the next Pope which is what the second statement also says. Hence, our output will be 1 for entailment"}, {"input": "Sentence 1: Herceptin was already approved to treat the sickest breast cancer patients, and the company said, Monday, it will discuss with federal regulators the possibility of prescribing the drug for more breast cancer patients. Sentence 2: Herceptin can be used to treat breast cancer.", "output": "1", "explanation": "In this example, our first sentence says that the Herceptin was already an approved drug for treating breast cancer patients and the same is said by Sentence 2 as well. So our output will be 1 for entailment."}, {"input": "Sentence 1: Nearly 4 million children who have at least one parent who entered the U.S. illegally were born in the United States and are U.S. citizens as a result, according to the study conducted by the Pew Hispanic Center. That's about three quarters of the estimated 5.5 million children of illegal immigrants inside the United States, according to the study. About 1.8 million children of undocumented immigrants live in poverty, the study found. Sentence 2: Three quarters of U.S. illegal immigrants have children.", "output": "0", "explanation": "In the first sentence it is written that from the total of 5.5 million children of illegal immigrants nearly three quaters were born here in U.S. There is no mention of the count of how many illegal immigrants have children in the first statement. Hence, the output will be 0 for non entailment"}], "Negative Examples": [{"input": "Sentence 1: Valero Energy Corp., on Monday, said it found \"extensive\" additional damage at its 250,000-barrel-per-day Port Arthur refinery. Sentence 2: Valero Energy Corp. produces 250,000 barrels per day.", "output": "0", "explanation": "The first statement mentions that there was damage found in the 250,000 barrel-per-day Port Aurthur refinery. Which means that they produce 250,000 barrels a day. Hence the output should have been 1 for entailment"}, {"input": "Sentence 1: A man is due in court later charged with the murder 26 years ago of a teenager whose case was the first to be featured on BBC One's Crimewatch. Colette Aram, 16, was walking to her boyfriend's house in Keyworth, Nottinghamshire, on 30 October 1983 when she disappeared. Her body was later found in a field close to her home. Paul Stewart Hutchinson, 50, has been charged with murder and is due before Nottingham magistrates later. Sentence 2: Paul Stewart Hutchinson is accused of having stabbed a girl.", "output": "1", "explanation": "In this example our first sentence only mentions that Paul Stewart Hutchinson has murdered the girl. There is no information in the statement about the how she was killed and so since the second statement mentions she was stabbed our statement does not entail. So output should have been 0."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Books", "Dialogue"], "Instance": {"id": "task1344-f77f75e9d3df44b989a11a8128f18359", "input": "Sentence 1: The disputed waters lie close to the Sipadan and Ligitan islands, which Indonesia lost to Malaysia in a legal battle in the International Court of Justice in December 2002. Sentence 2: There is a territorial waters dispute.", "output": ["1"]}, "Instance License": ["Unknown"], "prediction": "1"}
+{"id": "task1344-53b51ed7532e485aafb2d4ce0e8ea21c", "Task": "task1344_glue_entailment_classification", "Contributors": "['Arit Chanda']", "Source": ["rte"], "URL": ["https://dl.fbaipublicfiles.com/glue/data/RTE.zip"], "Categories": ["Textual Entailment"], "Reasoning": ["Textual Entailment -> Deductive Reasoning"], "Definition": ["In this task, you're given two sentences. Indicate if the first sentence clearly entails the second sentence (i.e., one can conclude the 2nd sentence by reading the 1st one). Indicate your answer with '1' if the first sentence entails the second sentence, otherwise answer with '0'."], "Positive Examples": [{"input": "Sentence 1: No Weapons of Mass Destruction Found in Iraq Yet. Sentence 2:Weapons of Mass Destruction Found in Iraq.", "output": "0", "explanation": "In our first statement we clearly say that Iraq does not have any weapon of mass destruction but the second sentence says that weapon of mass destruction is found in Iraq which is contradiction. Hence output will be 0 for non entailment."}, {"input": "Sentence 1: A place of sorrow, after Pope John Paul II died, became a place of celebration, as Roman Catholic faithful gathered in downtown Chicago to mark the installation of new Pope Benedict XVI. Sentence 2: Pope Benedict XVI is the new leader of the Roman Catholic Church.", "output": "1", "explanation": "In the given first sentence we can clearly understand that Pope John Paul II has died and Pope Benedict XVI was elected as the next Pope which is what the second statement also says. Hence, our output will be 1 for entailment"}, {"input": "Sentence 1: Herceptin was already approved to treat the sickest breast cancer patients, and the company said, Monday, it will discuss with federal regulators the possibility of prescribing the drug for more breast cancer patients. Sentence 2: Herceptin can be used to treat breast cancer.", "output": "1", "explanation": "In this example, our first sentence says that the Herceptin was already an approved drug for treating breast cancer patients and the same is said by Sentence 2 as well. So our output will be 1 for entailment."}, {"input": "Sentence 1: Nearly 4 million children who have at least one parent who entered the U.S. illegally were born in the United States and are U.S. citizens as a result, according to the study conducted by the Pew Hispanic Center. That's about three quarters of the estimated 5.5 million children of illegal immigrants inside the United States, according to the study. About 1.8 million children of undocumented immigrants live in poverty, the study found. Sentence 2: Three quarters of U.S. illegal immigrants have children.", "output": "0", "explanation": "In the first sentence it is written that from the total of 5.5 million children of illegal immigrants nearly three quaters were born here in U.S. There is no mention of the count of how many illegal immigrants have children in the first statement. Hence, the output will be 0 for non entailment"}], "Negative Examples": [{"input": "Sentence 1: Valero Energy Corp., on Monday, said it found \"extensive\" additional damage at its 250,000-barrel-per-day Port Arthur refinery. Sentence 2: Valero Energy Corp. produces 250,000 barrels per day.", "output": "0", "explanation": "The first statement mentions that there was damage found in the 250,000 barrel-per-day Port Aurthur refinery. Which means that they produce 250,000 barrels a day. Hence the output should have been 1 for entailment"}, {"input": "Sentence 1: A man is due in court later charged with the murder 26 years ago of a teenager whose case was the first to be featured on BBC One's Crimewatch. Colette Aram, 16, was walking to her boyfriend's house in Keyworth, Nottinghamshire, on 30 October 1983 when she disappeared. Her body was later found in a field close to her home. Paul Stewart Hutchinson, 50, has been charged with murder and is due before Nottingham magistrates later. Sentence 2: Paul Stewart Hutchinson is accused of having stabbed a girl.", "output": "1", "explanation": "In this example our first sentence only mentions that Paul Stewart Hutchinson has murdered the girl. There is no information in the statement about the how she was killed and so since the second statement mentions she was stabbed our statement does not entail. So output should have been 0."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Books", "Dialogue"], "Instance": {"id": "task1344-53b51ed7532e485aafb2d4ce0e8ea21c", "input": "Sentence 1: Anna Nobili is no ordinary nun. The 38-year-old used to be a lap-dancer, and spent many years working in Italian nightclubs. She is now using her talents in a rather different way - for what she calls \"The Holy Dance\" in a performance on Tuesday evening at the Holy Cross in Jerusalem Basilica in Rome, in front of senior Catholic clerics including Archbishop Gianfranco Ravasi, head of the Vatican's Cultural Department. Miss Nobili told the BBC World Service that the transformation from podium lap dancer to nun happened gradually. Sentence 2: Anna Nobili became a nun in 2002.", "output": ["0"]}, "Instance License": ["Unknown"], "prediction": "1"}
+{"id": "task1344-d32886d71ef54a6e95ce6070c98422b9", "Task": "task1344_glue_entailment_classification", "Contributors": "['Arit Chanda']", "Source": ["rte"], "URL": ["https://dl.fbaipublicfiles.com/glue/data/RTE.zip"], "Categories": ["Textual Entailment"], "Reasoning": ["Textual Entailment -> Deductive Reasoning"], "Definition": ["In this task, you're given two sentences. Indicate if the first sentence clearly entails the second sentence (i.e., one can conclude the 2nd sentence by reading the 1st one). Indicate your answer with '1' if the first sentence entails the second sentence, otherwise answer with '0'."], "Positive Examples": [{"input": "Sentence 1: No Weapons of Mass Destruction Found in Iraq Yet. Sentence 2:Weapons of Mass Destruction Found in Iraq.", "output": "0", "explanation": "In our first statement we clearly say that Iraq does not have any weapon of mass destruction but the second sentence says that weapon of mass destruction is found in Iraq which is contradiction. Hence output will be 0 for non entailment."}, {"input": "Sentence 1: A place of sorrow, after Pope John Paul II died, became a place of celebration, as Roman Catholic faithful gathered in downtown Chicago to mark the installation of new Pope Benedict XVI. Sentence 2: Pope Benedict XVI is the new leader of the Roman Catholic Church.", "output": "1", "explanation": "In the given first sentence we can clearly understand that Pope John Paul II has died and Pope Benedict XVI was elected as the next Pope which is what the second statement also says. Hence, our output will be 1 for entailment"}, {"input": "Sentence 1: Herceptin was already approved to treat the sickest breast cancer patients, and the company said, Monday, it will discuss with federal regulators the possibility of prescribing the drug for more breast cancer patients. Sentence 2: Herceptin can be used to treat breast cancer.", "output": "1", "explanation": "In this example, our first sentence says that the Herceptin was already an approved drug for treating breast cancer patients and the same is said by Sentence 2 as well. So our output will be 1 for entailment."}, {"input": "Sentence 1: Nearly 4 million children who have at least one parent who entered the U.S. illegally were born in the United States and are U.S. citizens as a result, according to the study conducted by the Pew Hispanic Center. That's about three quarters of the estimated 5.5 million children of illegal immigrants inside the United States, according to the study. About 1.8 million children of undocumented immigrants live in poverty, the study found. Sentence 2: Three quarters of U.S. illegal immigrants have children.", "output": "0", "explanation": "In the first sentence it is written that from the total of 5.5 million children of illegal immigrants nearly three quaters were born here in U.S. There is no mention of the count of how many illegal immigrants have children in the first statement. Hence, the output will be 0 for non entailment"}], "Negative Examples": [{"input": "Sentence 1: Valero Energy Corp., on Monday, said it found \"extensive\" additional damage at its 250,000-barrel-per-day Port Arthur refinery. Sentence 2: Valero Energy Corp. produces 250,000 barrels per day.", "output": "0", "explanation": "The first statement mentions that there was damage found in the 250,000 barrel-per-day Port Aurthur refinery. Which means that they produce 250,000 barrels a day. Hence the output should have been 1 for entailment"}, {"input": "Sentence 1: A man is due in court later charged with the murder 26 years ago of a teenager whose case was the first to be featured on BBC One's Crimewatch. Colette Aram, 16, was walking to her boyfriend's house in Keyworth, Nottinghamshire, on 30 October 1983 when she disappeared. Her body was later found in a field close to her home. Paul Stewart Hutchinson, 50, has been charged with murder and is due before Nottingham magistrates later. Sentence 2: Paul Stewart Hutchinson is accused of having stabbed a girl.", "output": "1", "explanation": "In this example our first sentence only mentions that Paul Stewart Hutchinson has murdered the girl. There is no information in the statement about the how she was killed and so since the second statement mentions she was stabbed our statement does not entail. So output should have been 0."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Books", "Dialogue"], "Instance": {"id": "task1344-d32886d71ef54a6e95ce6070c98422b9", "input": "Sentence 1: The cost of the consumer of the United States fell in June. Sentence 2: U.S. consumer spending dived in June.", "output": ["0"]}, "Instance License": ["Unknown"], "prediction": "1"}
+{"id": "task1344-750072bd154a47a8a96f4b9f3d2c9839", "Task": "task1344_glue_entailment_classification", "Contributors": "['Arit Chanda']", "Source": ["rte"], "URL": ["https://dl.fbaipublicfiles.com/glue/data/RTE.zip"], "Categories": ["Textual Entailment"], "Reasoning": ["Textual Entailment -> Deductive Reasoning"], "Definition": ["In this task, you're given two sentences. Indicate if the first sentence clearly entails the second sentence (i.e., one can conclude the 2nd sentence by reading the 1st one). Indicate your answer with '1' if the first sentence entails the second sentence, otherwise answer with '0'."], "Positive Examples": [{"input": "Sentence 1: No Weapons of Mass Destruction Found in Iraq Yet. Sentence 2:Weapons of Mass Destruction Found in Iraq.", "output": "0", "explanation": "In our first statement we clearly say that Iraq does not have any weapon of mass destruction but the second sentence says that weapon of mass destruction is found in Iraq which is contradiction. Hence output will be 0 for non entailment."}, {"input": "Sentence 1: A place of sorrow, after Pope John Paul II died, became a place of celebration, as Roman Catholic faithful gathered in downtown Chicago to mark the installation of new Pope Benedict XVI. Sentence 2: Pope Benedict XVI is the new leader of the Roman Catholic Church.", "output": "1", "explanation": "In the given first sentence we can clearly understand that Pope John Paul II has died and Pope Benedict XVI was elected as the next Pope which is what the second statement also says. Hence, our output will be 1 for entailment"}, {"input": "Sentence 1: Herceptin was already approved to treat the sickest breast cancer patients, and the company said, Monday, it will discuss with federal regulators the possibility of prescribing the drug for more breast cancer patients. Sentence 2: Herceptin can be used to treat breast cancer.", "output": "1", "explanation": "In this example, our first sentence says that the Herceptin was already an approved drug for treating breast cancer patients and the same is said by Sentence 2 as well. So our output will be 1 for entailment."}, {"input": "Sentence 1: Nearly 4 million children who have at least one parent who entered the U.S. illegally were born in the United States and are U.S. citizens as a result, according to the study conducted by the Pew Hispanic Center. That's about three quarters of the estimated 5.5 million children of illegal immigrants inside the United States, according to the study. About 1.8 million children of undocumented immigrants live in poverty, the study found. Sentence 2: Three quarters of U.S. illegal immigrants have children.", "output": "0", "explanation": "In the first sentence it is written that from the total of 5.5 million children of illegal immigrants nearly three quaters were born here in U.S. There is no mention of the count of how many illegal immigrants have children in the first statement. Hence, the output will be 0 for non entailment"}], "Negative Examples": [{"input": "Sentence 1: Valero Energy Corp., on Monday, said it found \"extensive\" additional damage at its 250,000-barrel-per-day Port Arthur refinery. Sentence 2: Valero Energy Corp. produces 250,000 barrels per day.", "output": "0", "explanation": "The first statement mentions that there was damage found in the 250,000 barrel-per-day Port Aurthur refinery. Which means that they produce 250,000 barrels a day. Hence the output should have been 1 for entailment"}, {"input": "Sentence 1: A man is due in court later charged with the murder 26 years ago of a teenager whose case was the first to be featured on BBC One's Crimewatch. Colette Aram, 16, was walking to her boyfriend's house in Keyworth, Nottinghamshire, on 30 October 1983 when she disappeared. Her body was later found in a field close to her home. Paul Stewart Hutchinson, 50, has been charged with murder and is due before Nottingham magistrates later. Sentence 2: Paul Stewart Hutchinson is accused of having stabbed a girl.", "output": "1", "explanation": "In this example our first sentence only mentions that Paul Stewart Hutchinson has murdered the girl. There is no information in the statement about the how she was killed and so since the second statement mentions she was stabbed our statement does not entail. So output should have been 0."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Books", "Dialogue"], "Instance": {"id": "task1344-750072bd154a47a8a96f4b9f3d2c9839", "input": "Sentence 1: It would help the economy by putting people back to work and more money in the hands of consumers. Sentence 2: More money in the hands of consumers means more money can be spent to get the economy going.", "output": ["1"]}, "Instance License": ["Unknown"], "prediction": "1"}
+{"id": "task1344-0e29b9f1fa0c4f1386a3084d782ac7b6", "Task": "task1344_glue_entailment_classification", "Contributors": "['Arit Chanda']", "Source": ["rte"], "URL": ["https://dl.fbaipublicfiles.com/glue/data/RTE.zip"], "Categories": ["Textual Entailment"], "Reasoning": ["Textual Entailment -> Deductive Reasoning"], "Definition": ["In this task, you're given two sentences. Indicate if the first sentence clearly entails the second sentence (i.e., one can conclude the 2nd sentence by reading the 1st one). Indicate your answer with '1' if the first sentence entails the second sentence, otherwise answer with '0'."], "Positive Examples": [{"input": "Sentence 1: No Weapons of Mass Destruction Found in Iraq Yet. Sentence 2:Weapons of Mass Destruction Found in Iraq.", "output": "0", "explanation": "In our first statement we clearly say that Iraq does not have any weapon of mass destruction but the second sentence says that weapon of mass destruction is found in Iraq which is contradiction. Hence output will be 0 for non entailment."}, {"input": "Sentence 1: A place of sorrow, after Pope John Paul II died, became a place of celebration, as Roman Catholic faithful gathered in downtown Chicago to mark the installation of new Pope Benedict XVI. Sentence 2: Pope Benedict XVI is the new leader of the Roman Catholic Church.", "output": "1", "explanation": "In the given first sentence we can clearly understand that Pope John Paul II has died and Pope Benedict XVI was elected as the next Pope which is what the second statement also says. Hence, our output will be 1 for entailment"}, {"input": "Sentence 1: Herceptin was already approved to treat the sickest breast cancer patients, and the company said, Monday, it will discuss with federal regulators the possibility of prescribing the drug for more breast cancer patients. Sentence 2: Herceptin can be used to treat breast cancer.", "output": "1", "explanation": "In this example, our first sentence says that the Herceptin was already an approved drug for treating breast cancer patients and the same is said by Sentence 2 as well. So our output will be 1 for entailment."}, {"input": "Sentence 1: Nearly 4 million children who have at least one parent who entered the U.S. illegally were born in the United States and are U.S. citizens as a result, according to the study conducted by the Pew Hispanic Center. That's about three quarters of the estimated 5.5 million children of illegal immigrants inside the United States, according to the study. About 1.8 million children of undocumented immigrants live in poverty, the study found. Sentence 2: Three quarters of U.S. illegal immigrants have children.", "output": "0", "explanation": "In the first sentence it is written that from the total of 5.5 million children of illegal immigrants nearly three quaters were born here in U.S. There is no mention of the count of how many illegal immigrants have children in the first statement. Hence, the output will be 0 for non entailment"}], "Negative Examples": [{"input": "Sentence 1: Valero Energy Corp., on Monday, said it found \"extensive\" additional damage at its 250,000-barrel-per-day Port Arthur refinery. Sentence 2: Valero Energy Corp. produces 250,000 barrels per day.", "output": "0", "explanation": "The first statement mentions that there was damage found in the 250,000 barrel-per-day Port Aurthur refinery. Which means that they produce 250,000 barrels a day. Hence the output should have been 1 for entailment"}, {"input": "Sentence 1: A man is due in court later charged with the murder 26 years ago of a teenager whose case was the first to be featured on BBC One's Crimewatch. Colette Aram, 16, was walking to her boyfriend's house in Keyworth, Nottinghamshire, on 30 October 1983 when she disappeared. Her body was later found in a field close to her home. Paul Stewart Hutchinson, 50, has been charged with murder and is due before Nottingham magistrates later. Sentence 2: Paul Stewart Hutchinson is accused of having stabbed a girl.", "output": "1", "explanation": "In this example our first sentence only mentions that Paul Stewart Hutchinson has murdered the girl. There is no information in the statement about the how she was killed and so since the second statement mentions she was stabbed our statement does not entail. So output should have been 0."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Books", "Dialogue"], "Instance": {"id": "task1344-0e29b9f1fa0c4f1386a3084d782ac7b6", "input": "Sentence 1: The city continued to grow through much of the 20th century. Sentence 2: The city continued to grow, but its services deteriorated.", "output": ["0"]}, "Instance License": ["Unknown"], "prediction": "1"}
+{"id": "task288-4d0b6bf73bba4ae085059be0bd99a4e7", "Task": "task288_gigaword_summarization", "Contributors": "['Mihir Parmar']", "Source": ["gigaword"], "URL": ["https://metatext.io/datasets/gigaword"], "Categories": ["Title Generation"], "Reasoning": [], "Definition": ["In this task, you are given a text of the article. Your task is to generate a headline (title) for this article.", "Given a passage, write a short summary based on the passage."], "Positive Examples": [{"input": "australia 's current account deficit shrunk by a record #.## billion dollars -lrb- #.## billion us -rrb- in the june quarter due to soaring commodity prices , figures released monday showed .", "output": "australian current account deficit narrows sharply", "explanation": "This headline is appropriate for the given article text because the focus of this article is Australian current accounts."}, {"input": "at least two people were killed in a suspected bomb attack on a passenger bus in the strife-torn southern philippines on monday , the military said .", "output": "at least two dead in southern philippines blast", "explanation": "This article focuses on the southern Philippines blast; hence the generated title is correct."}, {"input": "four east timorese youths who scaled the french embassy 's fence here thursday , left the embassy on their way to portugal friday .", "output": "UNK latest east timorese asylum seekers leave for portugal", "explanation": "The example is correct, as it correctly summarizes the passage"}, {"input": "bosnian croat forces have begun torching homes in parts of western bosnia captured during a summer offensive but due to return to serbian control under the dayton peace agreement , un officials said friday .", "output": "croats torch homes in areas due to return to serbs", "explanation": "The example is correct, as it correctly summarizes the passage"}], "Negative Examples": [{"input": "australian shares closed down #.# percent monday following a weak lead from the united states and lower commodity prices , dealers said .", "output": "envoy urges north korea to restart nuclear disablement", "explanation": "The generated title and the article text are different. Hence, this is not the correct title."}, {"input": "south korea on monday announced sweeping tax reforms , including income and corporate tax cuts to boost growth by stimulating sluggish private consumption and business investment .", "output": "south korea announces tax are high", "explanation": "This article talks about south Korean tax cuts, but there is no indication about tax being high. So, the generated title is not correct."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["News"], "Instance": {"id": "task288-4d0b6bf73bba4ae085059be0bd99a4e7", "input": "the united nations children 's fund -lrb- unicef -rrb- has voiced concern over the plight of children in much of eastern europe where communism was abruptly dismantled and state services allowed to erode .", "output": ["unicef concerned about welfare of children in former communist states"]}, "Instance License": ["MIT"], "prediction": "united nations children's fund -lrb- unicef -rrb- has voiced concern over the plight of children in much of eastern europe."}
+{"id": "task288-2945fa7b99904acb83ab838911c5cb54", "Task": "task288_gigaword_summarization", "Contributors": "['Mihir Parmar']", "Source": ["gigaword"], "URL": ["https://metatext.io/datasets/gigaword"], "Categories": ["Title Generation"], "Reasoning": [], "Definition": ["In this task, you are given a text of the article. Your task is to generate a headline (title) for this article.", "Given a passage, write a short summary based on the passage."], "Positive Examples": [{"input": "australia 's current account deficit shrunk by a record #.## billion dollars -lrb- #.## billion us -rrb- in the june quarter due to soaring commodity prices , figures released monday showed .", "output": "australian current account deficit narrows sharply", "explanation": "This headline is appropriate for the given article text because the focus of this article is Australian current accounts."}, {"input": "at least two people were killed in a suspected bomb attack on a passenger bus in the strife-torn southern philippines on monday , the military said .", "output": "at least two dead in southern philippines blast", "explanation": "This article focuses on the southern Philippines blast; hence the generated title is correct."}, {"input": "four east timorese youths who scaled the french embassy 's fence here thursday , left the embassy on their way to portugal friday .", "output": "UNK latest east timorese asylum seekers leave for portugal", "explanation": "The example is correct, as it correctly summarizes the passage"}, {"input": "bosnian croat forces have begun torching homes in parts of western bosnia captured during a summer offensive but due to return to serbian control under the dayton peace agreement , un officials said friday .", "output": "croats torch homes in areas due to return to serbs", "explanation": "The example is correct, as it correctly summarizes the passage"}], "Negative Examples": [{"input": "australian shares closed down #.# percent monday following a weak lead from the united states and lower commodity prices , dealers said .", "output": "envoy urges north korea to restart nuclear disablement", "explanation": "The generated title and the article text are different. Hence, this is not the correct title."}, {"input": "south korea on monday announced sweeping tax reforms , including income and corporate tax cuts to boost growth by stimulating sluggish private consumption and business investment .", "output": "south korea announces tax are high", "explanation": "This article talks about south Korean tax cuts, but there is no indication about tax being high. So, the generated title is not correct."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["News"], "Instance": {"id": "task288-2945fa7b99904acb83ab838911c5cb54", "input": "french rail workers pressed on with their crippling strike for a sixth straight day wednesday to protest welfare reform plans by prime minister alain juppe , with no immediate end in sight .", "output": ["french UNK press strike stranglehold by michael thurston"]}, "Instance License": ["MIT"], "prediction": "french rail workers pressed on with their crippling strike"}
+{"id": "task288-88fc541b2817469781f4db998eadf62b", "Task": "task288_gigaword_summarization", "Contributors": "['Mihir Parmar']", "Source": ["gigaword"], "URL": ["https://metatext.io/datasets/gigaword"], "Categories": ["Title Generation"], "Reasoning": [], "Definition": ["In this task, you are given a text of the article. Your task is to generate a headline (title) for this article.", "Given a passage, write a short summary based on the passage."], "Positive Examples": [{"input": "australia 's current account deficit shrunk by a record #.## billion dollars -lrb- #.## billion us -rrb- in the june quarter due to soaring commodity prices , figures released monday showed .", "output": "australian current account deficit narrows sharply", "explanation": "This headline is appropriate for the given article text because the focus of this article is Australian current accounts."}, {"input": "at least two people were killed in a suspected bomb attack on a passenger bus in the strife-torn southern philippines on monday , the military said .", "output": "at least two dead in southern philippines blast", "explanation": "This article focuses on the southern Philippines blast; hence the generated title is correct."}, {"input": "four east timorese youths who scaled the french embassy 's fence here thursday , left the embassy on their way to portugal friday .", "output": "UNK latest east timorese asylum seekers leave for portugal", "explanation": "The example is correct, as it correctly summarizes the passage"}, {"input": "bosnian croat forces have begun torching homes in parts of western bosnia captured during a summer offensive but due to return to serbian control under the dayton peace agreement , un officials said friday .", "output": "croats torch homes in areas due to return to serbs", "explanation": "The example is correct, as it correctly summarizes the passage"}], "Negative Examples": [{"input": "australian shares closed down #.# percent monday following a weak lead from the united states and lower commodity prices , dealers said .", "output": "envoy urges north korea to restart nuclear disablement", "explanation": "The generated title and the article text are different. Hence, this is not the correct title."}, {"input": "south korea on monday announced sweeping tax reforms , including income and corporate tax cuts to boost growth by stimulating sluggish private consumption and business investment .", "output": "south korea announces tax are high", "explanation": "This article talks about south Korean tax cuts, but there is no indication about tax being high. So, the generated title is not correct."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["News"], "Instance": {"id": "task288-88fc541b2817469781f4db998eadf62b", "input": "polling stations closed at #### gmt -lrb- #### local time -rrb- friday on the first day of czech legislative elections shadowed by allegations surrounding social democrat prime minister jiri paroubek .", "output": ["polling stations close on first day of czech legislative elections"]}, "Instance License": ["MIT"], "prediction": "polling stations close at #### gmt -lrb- #### local time -rrb- friday on first day of czech legislative elections"}
+{"id": "task288-6d8ac5ea47ce4a86ba839d9c56e707cc", "Task": "task288_gigaword_summarization", "Contributors": "['Mihir Parmar']", "Source": ["gigaword"], "URL": ["https://metatext.io/datasets/gigaword"], "Categories": ["Title Generation"], "Reasoning": [], "Definition": ["In this task, you are given a text of the article. Your task is to generate a headline (title) for this article.", "Given a passage, write a short summary based on the passage."], "Positive Examples": [{"input": "australia 's current account deficit shrunk by a record #.## billion dollars -lrb- #.## billion us -rrb- in the june quarter due to soaring commodity prices , figures released monday showed .", "output": "australian current account deficit narrows sharply", "explanation": "This headline is appropriate for the given article text because the focus of this article is Australian current accounts."}, {"input": "at least two people were killed in a suspected bomb attack on a passenger bus in the strife-torn southern philippines on monday , the military said .", "output": "at least two dead in southern philippines blast", "explanation": "This article focuses on the southern Philippines blast; hence the generated title is correct."}, {"input": "four east timorese youths who scaled the french embassy 's fence here thursday , left the embassy on their way to portugal friday .", "output": "UNK latest east timorese asylum seekers leave for portugal", "explanation": "The example is correct, as it correctly summarizes the passage"}, {"input": "bosnian croat forces have begun torching homes in parts of western bosnia captured during a summer offensive but due to return to serbian control under the dayton peace agreement , un officials said friday .", "output": "croats torch homes in areas due to return to serbs", "explanation": "The example is correct, as it correctly summarizes the passage"}], "Negative Examples": [{"input": "australian shares closed down #.# percent monday following a weak lead from the united states and lower commodity prices , dealers said .", "output": "envoy urges north korea to restart nuclear disablement", "explanation": "The generated title and the article text are different. Hence, this is not the correct title."}, {"input": "south korea on monday announced sweeping tax reforms , including income and corporate tax cuts to boost growth by stimulating sluggish private consumption and business investment .", "output": "south korea announces tax are high", "explanation": "This article talks about south Korean tax cuts, but there is no indication about tax being high. So, the generated title is not correct."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["News"], "Instance": {"id": "task288-6d8ac5ea47ce4a86ba839d9c56e707cc", "input": "president robert mugabe 's pay packet will be more than doubled by july next year to a total of ###,### zimbabwe dollars -lrb- around ##,### us dollars -rrb- , the government announced saturday .", "output": ["president mugabe 's salary doubled"]}, "Instance License": ["MIT"], "prediction": "president robert mugabe's pay packet will be more than doubled by july next year"}
+{"id": "task288-3ea291e2107d46648907d2079bd0e460", "Task": "task288_gigaword_summarization", "Contributors": "['Mihir Parmar']", "Source": ["gigaword"], "URL": ["https://metatext.io/datasets/gigaword"], "Categories": ["Title Generation"], "Reasoning": [], "Definition": ["In this task, you are given a text of the article. Your task is to generate a headline (title) for this article.", "Given a passage, write a short summary based on the passage."], "Positive Examples": [{"input": "australia 's current account deficit shrunk by a record #.## billion dollars -lrb- #.## billion us -rrb- in the june quarter due to soaring commodity prices , figures released monday showed .", "output": "australian current account deficit narrows sharply", "explanation": "This headline is appropriate for the given article text because the focus of this article is Australian current accounts."}, {"input": "at least two people were killed in a suspected bomb attack on a passenger bus in the strife-torn southern philippines on monday , the military said .", "output": "at least two dead in southern philippines blast", "explanation": "This article focuses on the southern Philippines blast; hence the generated title is correct."}, {"input": "four east timorese youths who scaled the french embassy 's fence here thursday , left the embassy on their way to portugal friday .", "output": "UNK latest east timorese asylum seekers leave for portugal", "explanation": "The example is correct, as it correctly summarizes the passage"}, {"input": "bosnian croat forces have begun torching homes in parts of western bosnia captured during a summer offensive but due to return to serbian control under the dayton peace agreement , un officials said friday .", "output": "croats torch homes in areas due to return to serbs", "explanation": "The example is correct, as it correctly summarizes the passage"}], "Negative Examples": [{"input": "australian shares closed down #.# percent monday following a weak lead from the united states and lower commodity prices , dealers said .", "output": "envoy urges north korea to restart nuclear disablement", "explanation": "The generated title and the article text are different. Hence, this is not the correct title."}, {"input": "south korea on monday announced sweeping tax reforms , including income and corporate tax cuts to boost growth by stimulating sluggish private consumption and business investment .", "output": "south korea announces tax are high", "explanation": "This article talks about south Korean tax cuts, but there is no indication about tax being high. So, the generated title is not correct."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["News"], "Instance": {"id": "task288-3ea291e2107d46648907d2079bd0e460", "input": "a us citizen who spied for communist east germany was given a suspended jail sentence of ## months here friday .", "output": ["us citizen who spied for east germans given suspended sentence"]}, "Instance License": ["MIT"], "prediction": "a us citizen who spied for communist east germany was given a suspended jail sentence of ## months"}
+{"id": "task1387-b556a45e07894005a978b8937ad02194", "Task": "task1387_anli_r3_entailment", "Contributors": "['Yeganeh Kordi']", "Source": ["anli"], "URL": ["https://github.com/facebookresearch/anli"], "Categories": ["Textual Entailment"], "Reasoning": ["Textual Entailment", "Quantitative Reasoning", "Commonsense Reasoning", "Causal Reasoning"], "Definition": ["In this task, you will be presented with a premise and a hypothesis sentence. Determine whether the hypothesis sentence entails (implies), contradicts (opposes), or is neutral with respect to the given premise sentence. Please answer with \"Contradiction\", \"Neutral\", or \"Entailment\"."], "Positive Examples": [{"input": "Premise: If you can dream it, you can achieve it \u2014 unless you're a goose trying to play a very human game of rugby. In the video above, one bold bird took a chance when it ran onto a rugby field mid-play. Things got dicey when it got into a tussle with another player, but it shook it off and kept right on running. After the play ended, the players escorted the feisty goose off the pitch. It was a risky move, but the crowd chanting its name was well worth it. Video credit: Storyful / Nathan Swarbrick @swazza1990 <sep> Hypothesis: The crowd believed they knew the name of the goose running on the field.", "output": "Entailment", "explanation": "This is a good example, the hypothesis sentence entails the given premise. Because the crowd was chanting its name, the crowd must have believed they knew the goose's name."}, {"input": "Premise: Notley hopeful attacks on women politicians will fade in coming year After a politically nasty year that saw women politicians face a barrage of attacks on social media and angry demonstrators shouting to have them put behind bars, Premier Rachel Notley is optimistic there will be a return to civil discourse. In a year-end interview with CBC News, Notley reflected on 2016, a year that saw hateful social-media attacks against MLA Sandra Jansen, and chants of \u201cLock her up\u201d directed at the premier at an anti-carbon tax rally in Edmonton. <sep> Hypothesis: Notley reflected on the chants of \"lock her up\" from previous to the year 2016.", "output": "Contradiction", "explanation": "The Premise states Notley reflected on the chants from 2016, not before 2016. In this example hypothesis sentence contradicts the given premise."}, {"input": "Premise: Mazda Sales (Thailand), a unit of Japanese carmaker Mazda Motor Corp, remains bullish about its sales prospects this year despite falling figures in the first six months, the Bangkok Post reported, citing its President Hidesuke Takesue. (bit.ly/1gr7HMd) ---- NOTE: Reuters has not verified this story and does not vouch for its accuracy. (Bangkok Newsroom; Editing by Prateek Chatterjee) <sep> Hypothesis: Mazda Sales will be fired next week", "output": "Neutral", "explanation": "In this example the hypothesis can't be proven one way or the other based on the context. It's set in the future and no one knows the future. So, hypothesis sentence is neutral with respect to a given premise."}], "Negative Examples": [{"input": "Premise: Police said that a 21-year-old man was discovered after he had been shot in South Jamaica on Aug. 18 and is in critical condition. Just before 9:30 p.m., police responded to a shooting at 104-46 164th St and discovered the victim, whose name has not been released, at the scene. The victim was shot in the thigh and transported to Jamaica Hospital, where he is currently listed in critical condition. No arrests have been made in the incident. <sep> Hypothesis: The victim was less than a quarter century old", "output": "Neutral", "explanation": "The victim was 21-year-old and 21 is less than 25 (a quarter century). The hypothesis sentence entails the given premise sentence and \"Neutral\" is incorrect."}, {"input": "Premise: Hurricane Harvey has caused devastating floods in the Houston area of Texas and parts of Louisiana, home to millions of Americans. The weather disaster has overwhelmed rescuers trying to answer calls for help by stranded residents. Texas Governor Greg Abbott praised the federal government's response Sunday, and the White House said President Donald Trump is expected to travel to Houston on Tuesday to view the rescue and recovery efforts. VOA's Zlatica Hoke reports. <sep> Hypothesis: Hurricane Harvey has caused devastating floods in less than two states.", "output": "Entailment", "explanation": "The hypothesis is definitely incorrect because it caused floods in both Texas and Louisiana, which is already two states. So, the answer should be \"Contradiction\"."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Miscellaneous"], "Instance": {"id": "task1387-b556a45e07894005a978b8937ad02194", "input": "Premise: Jet Ski<br>My first time on a jet ski was fun. My uncle was on the back. I was getting too close to a rock wall. He yelled at me to stop. We both fell off. <sep> Hypothesis: My uncle drove the jet ski and i sat on the back.", "output": ["Contradiction"]}, "Instance License": ["CC BY-NC 4.0"], "prediction": "Entails"}
+{"id": "task1387-5ce5a379bece418b9bdaab94fcad85bb", "Task": "task1387_anli_r3_entailment", "Contributors": "['Yeganeh Kordi']", "Source": ["anli"], "URL": ["https://github.com/facebookresearch/anli"], "Categories": ["Textual Entailment"], "Reasoning": ["Textual Entailment", "Quantitative Reasoning", "Commonsense Reasoning", "Causal Reasoning"], "Definition": ["In this task, you will be presented with a premise and a hypothesis sentence. Determine whether the hypothesis sentence entails (implies), contradicts (opposes), or is neutral with respect to the given premise sentence. Please answer with \"Contradiction\", \"Neutral\", or \"Entailment\"."], "Positive Examples": [{"input": "Premise: If you can dream it, you can achieve it \u2014 unless you're a goose trying to play a very human game of rugby. In the video above, one bold bird took a chance when it ran onto a rugby field mid-play. Things got dicey when it got into a tussle with another player, but it shook it off and kept right on running. After the play ended, the players escorted the feisty goose off the pitch. It was a risky move, but the crowd chanting its name was well worth it. Video credit: Storyful / Nathan Swarbrick @swazza1990 <sep> Hypothesis: The crowd believed they knew the name of the goose running on the field.", "output": "Entailment", "explanation": "This is a good example, the hypothesis sentence entails the given premise. Because the crowd was chanting its name, the crowd must have believed they knew the goose's name."}, {"input": "Premise: Notley hopeful attacks on women politicians will fade in coming year After a politically nasty year that saw women politicians face a barrage of attacks on social media and angry demonstrators shouting to have them put behind bars, Premier Rachel Notley is optimistic there will be a return to civil discourse. In a year-end interview with CBC News, Notley reflected on 2016, a year that saw hateful social-media attacks against MLA Sandra Jansen, and chants of \u201cLock her up\u201d directed at the premier at an anti-carbon tax rally in Edmonton. <sep> Hypothesis: Notley reflected on the chants of \"lock her up\" from previous to the year 2016.", "output": "Contradiction", "explanation": "The Premise states Notley reflected on the chants from 2016, not before 2016. In this example hypothesis sentence contradicts the given premise."}, {"input": "Premise: Mazda Sales (Thailand), a unit of Japanese carmaker Mazda Motor Corp, remains bullish about its sales prospects this year despite falling figures in the first six months, the Bangkok Post reported, citing its President Hidesuke Takesue. (bit.ly/1gr7HMd) ---- NOTE: Reuters has not verified this story and does not vouch for its accuracy. (Bangkok Newsroom; Editing by Prateek Chatterjee) <sep> Hypothesis: Mazda Sales will be fired next week", "output": "Neutral", "explanation": "In this example the hypothesis can't be proven one way or the other based on the context. It's set in the future and no one knows the future. So, hypothesis sentence is neutral with respect to a given premise."}], "Negative Examples": [{"input": "Premise: Police said that a 21-year-old man was discovered after he had been shot in South Jamaica on Aug. 18 and is in critical condition. Just before 9:30 p.m., police responded to a shooting at 104-46 164th St and discovered the victim, whose name has not been released, at the scene. The victim was shot in the thigh and transported to Jamaica Hospital, where he is currently listed in critical condition. No arrests have been made in the incident. <sep> Hypothesis: The victim was less than a quarter century old", "output": "Neutral", "explanation": "The victim was 21-year-old and 21 is less than 25 (a quarter century). The hypothesis sentence entails the given premise sentence and \"Neutral\" is incorrect."}, {"input": "Premise: Hurricane Harvey has caused devastating floods in the Houston area of Texas and parts of Louisiana, home to millions of Americans. The weather disaster has overwhelmed rescuers trying to answer calls for help by stranded residents. Texas Governor Greg Abbott praised the federal government's response Sunday, and the White House said President Donald Trump is expected to travel to Houston on Tuesday to view the rescue and recovery efforts. VOA's Zlatica Hoke reports. <sep> Hypothesis: Hurricane Harvey has caused devastating floods in less than two states.", "output": "Entailment", "explanation": "The hypothesis is definitely incorrect because it caused floods in both Texas and Louisiana, which is already two states. So, the answer should be \"Contradiction\"."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Miscellaneous"], "Instance": {"id": "task1387-5ce5a379bece418b9bdaab94fcad85bb", "input": "Premise: How to buy essential oils<br>Think about why you want to use an essential oil. Different oils suit different needs so it's important to know what you wish to achieve by using essential oil. For example, lavender can be used in a diffuser to relax and reduce anxiety and sage essential oil can be used as an antiseptic in wounds or as an anti-inflammatory. <sep> Hypothesis: Olive oil can be used in a diffuser to relax and reduce anxiety", "output": ["Neutral"]}, "Instance License": ["CC BY-NC 4.0"], "prediction": "Entails"}
+{"id": "task1387-02350ac18e0c43dfa1ac61b0760018cd", "Task": "task1387_anli_r3_entailment", "Contributors": "['Yeganeh Kordi']", "Source": ["anli"], "URL": ["https://github.com/facebookresearch/anli"], "Categories": ["Textual Entailment"], "Reasoning": ["Textual Entailment", "Quantitative Reasoning", "Commonsense Reasoning", "Causal Reasoning"], "Definition": ["In this task, you will be presented with a premise and a hypothesis sentence. Determine whether the hypothesis sentence entails (implies), contradicts (opposes), or is neutral with respect to the given premise sentence. Please answer with \"Contradiction\", \"Neutral\", or \"Entailment\"."], "Positive Examples": [{"input": "Premise: If you can dream it, you can achieve it \u2014 unless you're a goose trying to play a very human game of rugby. In the video above, one bold bird took a chance when it ran onto a rugby field mid-play. Things got dicey when it got into a tussle with another player, but it shook it off and kept right on running. After the play ended, the players escorted the feisty goose off the pitch. It was a risky move, but the crowd chanting its name was well worth it. Video credit: Storyful / Nathan Swarbrick @swazza1990 <sep> Hypothesis: The crowd believed they knew the name of the goose running on the field.", "output": "Entailment", "explanation": "This is a good example, the hypothesis sentence entails the given premise. Because the crowd was chanting its name, the crowd must have believed they knew the goose's name."}, {"input": "Premise: Notley hopeful attacks on women politicians will fade in coming year After a politically nasty year that saw women politicians face a barrage of attacks on social media and angry demonstrators shouting to have them put behind bars, Premier Rachel Notley is optimistic there will be a return to civil discourse. In a year-end interview with CBC News, Notley reflected on 2016, a year that saw hateful social-media attacks against MLA Sandra Jansen, and chants of \u201cLock her up\u201d directed at the premier at an anti-carbon tax rally in Edmonton. <sep> Hypothesis: Notley reflected on the chants of \"lock her up\" from previous to the year 2016.", "output": "Contradiction", "explanation": "The Premise states Notley reflected on the chants from 2016, not before 2016. In this example hypothesis sentence contradicts the given premise."}, {"input": "Premise: Mazda Sales (Thailand), a unit of Japanese carmaker Mazda Motor Corp, remains bullish about its sales prospects this year despite falling figures in the first six months, the Bangkok Post reported, citing its President Hidesuke Takesue. (bit.ly/1gr7HMd) ---- NOTE: Reuters has not verified this story and does not vouch for its accuracy. (Bangkok Newsroom; Editing by Prateek Chatterjee) <sep> Hypothesis: Mazda Sales will be fired next week", "output": "Neutral", "explanation": "In this example the hypothesis can't be proven one way or the other based on the context. It's set in the future and no one knows the future. So, hypothesis sentence is neutral with respect to a given premise."}], "Negative Examples": [{"input": "Premise: Police said that a 21-year-old man was discovered after he had been shot in South Jamaica on Aug. 18 and is in critical condition. Just before 9:30 p.m., police responded to a shooting at 104-46 164th St and discovered the victim, whose name has not been released, at the scene. The victim was shot in the thigh and transported to Jamaica Hospital, where he is currently listed in critical condition. No arrests have been made in the incident. <sep> Hypothesis: The victim was less than a quarter century old", "output": "Neutral", "explanation": "The victim was 21-year-old and 21 is less than 25 (a quarter century). The hypothesis sentence entails the given premise sentence and \"Neutral\" is incorrect."}, {"input": "Premise: Hurricane Harvey has caused devastating floods in the Houston area of Texas and parts of Louisiana, home to millions of Americans. The weather disaster has overwhelmed rescuers trying to answer calls for help by stranded residents. Texas Governor Greg Abbott praised the federal government's response Sunday, and the White House said President Donald Trump is expected to travel to Houston on Tuesday to view the rescue and recovery efforts. VOA's Zlatica Hoke reports. <sep> Hypothesis: Hurricane Harvey has caused devastating floods in less than two states.", "output": "Entailment", "explanation": "The hypothesis is definitely incorrect because it caused floods in both Texas and Louisiana, which is already two states. So, the answer should be \"Contradiction\"."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Miscellaneous"], "Instance": {"id": "task1387-02350ac18e0c43dfa1ac61b0760018cd", "input": "Premise: William Friedkin (born August 29, 1935) is an American film director, producer and screenwriter best known for directing \"The French Connection\" in 1971 and \"The Exorcist\" in 1973; for the former, he won the Academy Award for Best Director. Some of his other films include \"Sorcerer\", \"Cruising\", \"To Live and Die in L.A.\", \"Jade\", \"Rules of Engagement\", \"The Hunted\", \"Bug\", and \"Killer Joe\". <sep> Hypothesis: William Friedkin is dead", "output": ["Contradiction"]}, "Instance License": ["CC BY-NC 4.0"], "prediction": "Falsehood"}
+{"id": "task1387-6ece2ddd121d4a05ac0b75928ed8f3fd", "Task": "task1387_anli_r3_entailment", "Contributors": "['Yeganeh Kordi']", "Source": ["anli"], "URL": ["https://github.com/facebookresearch/anli"], "Categories": ["Textual Entailment"], "Reasoning": ["Textual Entailment", "Quantitative Reasoning", "Commonsense Reasoning", "Causal Reasoning"], "Definition": ["In this task, you will be presented with a premise and a hypothesis sentence. Determine whether the hypothesis sentence entails (implies), contradicts (opposes), or is neutral with respect to the given premise sentence. Please answer with \"Contradiction\", \"Neutral\", or \"Entailment\"."], "Positive Examples": [{"input": "Premise: If you can dream it, you can achieve it \u2014 unless you're a goose trying to play a very human game of rugby. In the video above, one bold bird took a chance when it ran onto a rugby field mid-play. Things got dicey when it got into a tussle with another player, but it shook it off and kept right on running. After the play ended, the players escorted the feisty goose off the pitch. It was a risky move, but the crowd chanting its name was well worth it. Video credit: Storyful / Nathan Swarbrick @swazza1990 <sep> Hypothesis: The crowd believed they knew the name of the goose running on the field.", "output": "Entailment", "explanation": "This is a good example, the hypothesis sentence entails the given premise. Because the crowd was chanting its name, the crowd must have believed they knew the goose's name."}, {"input": "Premise: Notley hopeful attacks on women politicians will fade in coming year After a politically nasty year that saw women politicians face a barrage of attacks on social media and angry demonstrators shouting to have them put behind bars, Premier Rachel Notley is optimistic there will be a return to civil discourse. In a year-end interview with CBC News, Notley reflected on 2016, a year that saw hateful social-media attacks against MLA Sandra Jansen, and chants of \u201cLock her up\u201d directed at the premier at an anti-carbon tax rally in Edmonton. <sep> Hypothesis: Notley reflected on the chants of \"lock her up\" from previous to the year 2016.", "output": "Contradiction", "explanation": "The Premise states Notley reflected on the chants from 2016, not before 2016. In this example hypothesis sentence contradicts the given premise."}, {"input": "Premise: Mazda Sales (Thailand), a unit of Japanese carmaker Mazda Motor Corp, remains bullish about its sales prospects this year despite falling figures in the first six months, the Bangkok Post reported, citing its President Hidesuke Takesue. (bit.ly/1gr7HMd) ---- NOTE: Reuters has not verified this story and does not vouch for its accuracy. (Bangkok Newsroom; Editing by Prateek Chatterjee) <sep> Hypothesis: Mazda Sales will be fired next week", "output": "Neutral", "explanation": "In this example the hypothesis can't be proven one way or the other based on the context. It's set in the future and no one knows the future. So, hypothesis sentence is neutral with respect to a given premise."}], "Negative Examples": [{"input": "Premise: Police said that a 21-year-old man was discovered after he had been shot in South Jamaica on Aug. 18 and is in critical condition. Just before 9:30 p.m., police responded to a shooting at 104-46 164th St and discovered the victim, whose name has not been released, at the scene. The victim was shot in the thigh and transported to Jamaica Hospital, where he is currently listed in critical condition. No arrests have been made in the incident. <sep> Hypothesis: The victim was less than a quarter century old", "output": "Neutral", "explanation": "The victim was 21-year-old and 21 is less than 25 (a quarter century). The hypothesis sentence entails the given premise sentence and \"Neutral\" is incorrect."}, {"input": "Premise: Hurricane Harvey has caused devastating floods in the Houston area of Texas and parts of Louisiana, home to millions of Americans. The weather disaster has overwhelmed rescuers trying to answer calls for help by stranded residents. Texas Governor Greg Abbott praised the federal government's response Sunday, and the White House said President Donald Trump is expected to travel to Houston on Tuesday to view the rescue and recovery efforts. VOA's Zlatica Hoke reports. <sep> Hypothesis: Hurricane Harvey has caused devastating floods in less than two states.", "output": "Entailment", "explanation": "The hypothesis is definitely incorrect because it caused floods in both Texas and Louisiana, which is already two states. So, the answer should be \"Contradiction\"."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Miscellaneous"], "Instance": {"id": "task1387-6ece2ddd121d4a05ac0b75928ed8f3fd", "input": "Premise: TORONTO, March 7 (Reuters) - The Canadian dollar weakened to a session low against the greenback after data showed the domestic economy unexpectedly shed jobs in February. At the same time, investors were also taking in data south of the border that showed U.S. job growth accelerated last month. The Canadian dollar was at C$1.1055 to the greenback, or 90.46 U.S. cents, weaker than Thursday's close of C$1.0992, or 90.98 U.S. cents. The loonie hit a session low of C$1.1064 shortly after the data was released. <sep> Hypothesis: Toronto is the most populous city in Canada.", "output": ["Entailment"]}, "Instance License": ["CC BY-NC 4.0"], "prediction": "Neutral"}
+{"id": "task1387-7462fb43781e4a6bbaa5d5d2bb487419", "Task": "task1387_anli_r3_entailment", "Contributors": "['Yeganeh Kordi']", "Source": ["anli"], "URL": ["https://github.com/facebookresearch/anli"], "Categories": ["Textual Entailment"], "Reasoning": ["Textual Entailment", "Quantitative Reasoning", "Commonsense Reasoning", "Causal Reasoning"], "Definition": ["In this task, you will be presented with a premise and a hypothesis sentence. Determine whether the hypothesis sentence entails (implies), contradicts (opposes), or is neutral with respect to the given premise sentence. Please answer with \"Contradiction\", \"Neutral\", or \"Entailment\"."], "Positive Examples": [{"input": "Premise: If you can dream it, you can achieve it \u2014 unless you're a goose trying to play a very human game of rugby. In the video above, one bold bird took a chance when it ran onto a rugby field mid-play. Things got dicey when it got into a tussle with another player, but it shook it off and kept right on running. After the play ended, the players escorted the feisty goose off the pitch. It was a risky move, but the crowd chanting its name was well worth it. Video credit: Storyful / Nathan Swarbrick @swazza1990 <sep> Hypothesis: The crowd believed they knew the name of the goose running on the field.", "output": "Entailment", "explanation": "This is a good example, the hypothesis sentence entails the given premise. Because the crowd was chanting its name, the crowd must have believed they knew the goose's name."}, {"input": "Premise: Notley hopeful attacks on women politicians will fade in coming year After a politically nasty year that saw women politicians face a barrage of attacks on social media and angry demonstrators shouting to have them put behind bars, Premier Rachel Notley is optimistic there will be a return to civil discourse. In a year-end interview with CBC News, Notley reflected on 2016, a year that saw hateful social-media attacks against MLA Sandra Jansen, and chants of \u201cLock her up\u201d directed at the premier at an anti-carbon tax rally in Edmonton. <sep> Hypothesis: Notley reflected on the chants of \"lock her up\" from previous to the year 2016.", "output": "Contradiction", "explanation": "The Premise states Notley reflected on the chants from 2016, not before 2016. In this example hypothesis sentence contradicts the given premise."}, {"input": "Premise: Mazda Sales (Thailand), a unit of Japanese carmaker Mazda Motor Corp, remains bullish about its sales prospects this year despite falling figures in the first six months, the Bangkok Post reported, citing its President Hidesuke Takesue. (bit.ly/1gr7HMd) ---- NOTE: Reuters has not verified this story and does not vouch for its accuracy. (Bangkok Newsroom; Editing by Prateek Chatterjee) <sep> Hypothesis: Mazda Sales will be fired next week", "output": "Neutral", "explanation": "In this example the hypothesis can't be proven one way or the other based on the context. It's set in the future and no one knows the future. So, hypothesis sentence is neutral with respect to a given premise."}], "Negative Examples": [{"input": "Premise: Police said that a 21-year-old man was discovered after he had been shot in South Jamaica on Aug. 18 and is in critical condition. Just before 9:30 p.m., police responded to a shooting at 104-46 164th St and discovered the victim, whose name has not been released, at the scene. The victim was shot in the thigh and transported to Jamaica Hospital, where he is currently listed in critical condition. No arrests have been made in the incident. <sep> Hypothesis: The victim was less than a quarter century old", "output": "Neutral", "explanation": "The victim was 21-year-old and 21 is less than 25 (a quarter century). The hypothesis sentence entails the given premise sentence and \"Neutral\" is incorrect."}, {"input": "Premise: Hurricane Harvey has caused devastating floods in the Houston area of Texas and parts of Louisiana, home to millions of Americans. The weather disaster has overwhelmed rescuers trying to answer calls for help by stranded residents. Texas Governor Greg Abbott praised the federal government's response Sunday, and the White House said President Donald Trump is expected to travel to Houston on Tuesday to view the rescue and recovery efforts. VOA's Zlatica Hoke reports. <sep> Hypothesis: Hurricane Harvey has caused devastating floods in less than two states.", "output": "Entailment", "explanation": "The hypothesis is definitely incorrect because it caused floods in both Texas and Louisiana, which is already two states. So, the answer should be \"Contradiction\"."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Miscellaneous"], "Instance": {"id": "task1387-7462fb43781e4a6bbaa5d5d2bb487419", "input": "Premise: One percent of America got $89 billion last year in a tax cut, but people working hard, playing by the rules, trying to take care of their kids, family values, that we're supposed to value so much in America -- I'm tired of politicians who talk about family values and don't value families. <sep> Hypothesis: One percent of Americans had to pay 89 billion dollars less than they would have to pay if there would be no tax cut, so they got to keep a lot more money", "output": ["Entailment"]}, "Instance License": ["CC BY-NC 4.0"], "prediction": "Entails"}
+{"id": "task1664-fb7c9b321d044611970335c70dd32dfe", "Task": "task1664_winobias_text_generation", "Contributors": "['Saradhi Kiran Amarthi']", "Source": ["wino_bias"], "URL": ["https://huggingface.co/datasets/viewer/?dataset=wino_bias"], "Categories": ["Coreference Resolution"], "Reasoning": [], "Definition": ["In this task, you will be given a sentence, and you need to identify the set of coreference words. Coreferences are generally a set of words in the text that refer to the same person or thing. Your output set of coreference words must be strictly present in the given input sentence. Do not use any outside knowledge to create the set of coreference words. If there is a 'the' article before the person or thing you should include 'the' as well. Please separate the coreference words by commas in the output."], "Positive Examples": [{"input": "The developer argued with the designer because he did not like the design.", "output": "The, developer, he", "explanation": "Here the output set of coreference words 'The', 'developer, and 'he' refer to the same person, and these are coreferences. So, the output is correct."}, {"input": "The mechanic greets with the receptionist because he was in a good mood.", "output": "The, mechanic, he", "explanation": "Here the output set of coreference words 'The', 'mechanic, and 'he' refer to the same person, and these are coreferences. So, the output is correct."}, {"input": "The mechanic greets the receptionist because she was standing in front of the door.", "output": "the, receptionist, she", "explanation": "Here the output set of coreference words 'the', 'receptionist, and 'she' refer to the same person, and these are coreferences. So, the output is correct."}, {"input": "The cook is always teaching the assistant new techniques so she will one day be equal in skill.", "output": "the, assistant, she", "explanation": "Here the output set of coreference words 'the', 'assistant, and 'she' refer to the same person, and these are coreferences. So, the output is correct."}], "Negative Examples": [{"input": "The cook is always teaching the assistant new techniques because he likes to teach others.", "output": "The, assistant, others", "explanation": "Here the output set of coreference words 'The', 'assistant, and 'others' do not refer to the same person, and these are coreferences. So, the output is incorrect."}, {"input": "The farmer gave the teacher a bag of eggs because he was grateful.", "output": "The, teacher, he", "explanation": "Here the output set of coreference words 'The', 'teacher, and 'he' do not refer to the same person, and these are coreferences. So, the output is incorrect."}, {"input": "The farmer gave the teacher a bag of eggs because she helped many kids.", "output": "the, farmer, she", "explanation": "Here the output set of coreference words 'The', 'farmer, and 'she' do not refer to the same person, and these are coreferences. So, the output is incorrect."}, {"input": "The CEO bought the accountant a car because he is rich.", "output": "The, accountant, he", "explanation": "Here the output set of coreference words 'The', 'accountant, and 'he' do not refer to the same person, and these are coreferences. So, the output is incorrect."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Professions", "Commonsense"], "Instance": {"id": "task1664-fb7c9b321d044611970335c70dd32dfe", "input": "The laborer kicked the cashier because he was drunk .", "output": ["The, laborer, he"]}, "Instance License": ["MIT"], "prediction": "The, laborer, he."}
+{"id": "task1664-623176546ddb4efbbffe157b30e93fc3", "Task": "task1664_winobias_text_generation", "Contributors": "['Saradhi Kiran Amarthi']", "Source": ["wino_bias"], "URL": ["https://huggingface.co/datasets/viewer/?dataset=wino_bias"], "Categories": ["Coreference Resolution"], "Reasoning": [], "Definition": ["In this task, you will be given a sentence, and you need to identify the set of coreference words. Coreferences are generally a set of words in the text that refer to the same person or thing. Your output set of coreference words must be strictly present in the given input sentence. Do not use any outside knowledge to create the set of coreference words. If there is a 'the' article before the person or thing you should include 'the' as well. Please separate the coreference words by commas in the output."], "Positive Examples": [{"input": "The developer argued with the designer because he did not like the design.", "output": "The, developer, he", "explanation": "Here the output set of coreference words 'The', 'developer, and 'he' refer to the same person, and these are coreferences. So, the output is correct."}, {"input": "The mechanic greets with the receptionist because he was in a good mood.", "output": "The, mechanic, he", "explanation": "Here the output set of coreference words 'The', 'mechanic, and 'he' refer to the same person, and these are coreferences. So, the output is correct."}, {"input": "The mechanic greets the receptionist because she was standing in front of the door.", "output": "the, receptionist, she", "explanation": "Here the output set of coreference words 'the', 'receptionist, and 'she' refer to the same person, and these are coreferences. So, the output is correct."}, {"input": "The cook is always teaching the assistant new techniques so she will one day be equal in skill.", "output": "the, assistant, she", "explanation": "Here the output set of coreference words 'the', 'assistant, and 'she' refer to the same person, and these are coreferences. So, the output is correct."}], "Negative Examples": [{"input": "The cook is always teaching the assistant new techniques because he likes to teach others.", "output": "The, assistant, others", "explanation": "Here the output set of coreference words 'The', 'assistant, and 'others' do not refer to the same person, and these are coreferences. So, the output is incorrect."}, {"input": "The farmer gave the teacher a bag of eggs because he was grateful.", "output": "The, teacher, he", "explanation": "Here the output set of coreference words 'The', 'teacher, and 'he' do not refer to the same person, and these are coreferences. So, the output is incorrect."}, {"input": "The farmer gave the teacher a bag of eggs because she helped many kids.", "output": "the, farmer, she", "explanation": "Here the output set of coreference words 'The', 'farmer, and 'she' do not refer to the same person, and these are coreferences. So, the output is incorrect."}, {"input": "The CEO bought the accountant a car because he is rich.", "output": "The, accountant, he", "explanation": "Here the output set of coreference words 'The', 'accountant, and 'he' do not refer to the same person, and these are coreferences. So, the output is incorrect."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Professions", "Commonsense"], "Instance": {"id": "task1664-623176546ddb4efbbffe157b30e93fc3", "input": "The physician owed the cashier money because he did not pay the vodka .", "output": ["The, physician, he"]}, "Instance License": ["MIT"], "prediction": "The, physician, he."}
+{"id": "task1664-0169acdd2d694353a34b9e7563af16e9", "Task": "task1664_winobias_text_generation", "Contributors": "['Saradhi Kiran Amarthi']", "Source": ["wino_bias"], "URL": ["https://huggingface.co/datasets/viewer/?dataset=wino_bias"], "Categories": ["Coreference Resolution"], "Reasoning": [], "Definition": ["In this task, you will be given a sentence, and you need to identify the set of coreference words. Coreferences are generally a set of words in the text that refer to the same person or thing. Your output set of coreference words must be strictly present in the given input sentence. Do not use any outside knowledge to create the set of coreference words. If there is a 'the' article before the person or thing you should include 'the' as well. Please separate the coreference words by commas in the output."], "Positive Examples": [{"input": "The developer argued with the designer because he did not like the design.", "output": "The, developer, he", "explanation": "Here the output set of coreference words 'The', 'developer, and 'he' refer to the same person, and these are coreferences. So, the output is correct."}, {"input": "The mechanic greets with the receptionist because he was in a good mood.", "output": "The, mechanic, he", "explanation": "Here the output set of coreference words 'The', 'mechanic, and 'he' refer to the same person, and these are coreferences. So, the output is correct."}, {"input": "The mechanic greets the receptionist because she was standing in front of the door.", "output": "the, receptionist, she", "explanation": "Here the output set of coreference words 'the', 'receptionist, and 'she' refer to the same person, and these are coreferences. So, the output is correct."}, {"input": "The cook is always teaching the assistant new techniques so she will one day be equal in skill.", "output": "the, assistant, she", "explanation": "Here the output set of coreference words 'the', 'assistant, and 'she' refer to the same person, and these are coreferences. So, the output is correct."}], "Negative Examples": [{"input": "The cook is always teaching the assistant new techniques because he likes to teach others.", "output": "The, assistant, others", "explanation": "Here the output set of coreference words 'The', 'assistant, and 'others' do not refer to the same person, and these are coreferences. So, the output is incorrect."}, {"input": "The farmer gave the teacher a bag of eggs because he was grateful.", "output": "The, teacher, he", "explanation": "Here the output set of coreference words 'The', 'teacher, and 'he' do not refer to the same person, and these are coreferences. So, the output is incorrect."}, {"input": "The farmer gave the teacher a bag of eggs because she helped many kids.", "output": "the, farmer, she", "explanation": "Here the output set of coreference words 'The', 'farmer, and 'she' do not refer to the same person, and these are coreferences. So, the output is incorrect."}, {"input": "The CEO bought the accountant a car because he is rich.", "output": "The, accountant, he", "explanation": "Here the output set of coreference words 'The', 'accountant, and 'he' do not refer to the same person, and these are coreferences. So, the output is incorrect."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Professions", "Commonsense"], "Instance": {"id": "task1664-0169acdd2d694353a34b9e7563af16e9", "input": "The carpenter built the attendant a desk to prove his love .", "output": ["The, carpenter, his"]}, "Instance License": ["MIT"], "prediction": "The, attendant, he."}
+{"id": "task1664-2c9ee2e3973847429718e5318b8d3859", "Task": "task1664_winobias_text_generation", "Contributors": "['Saradhi Kiran Amarthi']", "Source": ["wino_bias"], "URL": ["https://huggingface.co/datasets/viewer/?dataset=wino_bias"], "Categories": ["Coreference Resolution"], "Reasoning": [], "Definition": ["In this task, you will be given a sentence, and you need to identify the set of coreference words. Coreferences are generally a set of words in the text that refer to the same person or thing. Your output set of coreference words must be strictly present in the given input sentence. Do not use any outside knowledge to create the set of coreference words. If there is a 'the' article before the person or thing you should include 'the' as well. Please separate the coreference words by commas in the output."], "Positive Examples": [{"input": "The developer argued with the designer because he did not like the design.", "output": "The, developer, he", "explanation": "Here the output set of coreference words 'The', 'developer, and 'he' refer to the same person, and these are coreferences. So, the output is correct."}, {"input": "The mechanic greets with the receptionist because he was in a good mood.", "output": "The, mechanic, he", "explanation": "Here the output set of coreference words 'The', 'mechanic, and 'he' refer to the same person, and these are coreferences. So, the output is correct."}, {"input": "The mechanic greets the receptionist because she was standing in front of the door.", "output": "the, receptionist, she", "explanation": "Here the output set of coreference words 'the', 'receptionist, and 'she' refer to the same person, and these are coreferences. So, the output is correct."}, {"input": "The cook is always teaching the assistant new techniques so she will one day be equal in skill.", "output": "the, assistant, she", "explanation": "Here the output set of coreference words 'the', 'assistant, and 'she' refer to the same person, and these are coreferences. So, the output is correct."}], "Negative Examples": [{"input": "The cook is always teaching the assistant new techniques because he likes to teach others.", "output": "The, assistant, others", "explanation": "Here the output set of coreference words 'The', 'assistant, and 'others' do not refer to the same person, and these are coreferences. So, the output is incorrect."}, {"input": "The farmer gave the teacher a bag of eggs because he was grateful.", "output": "The, teacher, he", "explanation": "Here the output set of coreference words 'The', 'teacher, and 'he' do not refer to the same person, and these are coreferences. So, the output is incorrect."}, {"input": "The farmer gave the teacher a bag of eggs because she helped many kids.", "output": "the, farmer, she", "explanation": "Here the output set of coreference words 'The', 'farmer, and 'she' do not refer to the same person, and these are coreferences. So, the output is incorrect."}, {"input": "The CEO bought the accountant a car because he is rich.", "output": "The, accountant, he", "explanation": "Here the output set of coreference words 'The', 'accountant, and 'he' do not refer to the same person, and these are coreferences. So, the output is incorrect."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Professions", "Commonsense"], "Instance": {"id": "task1664-2c9ee2e3973847429718e5318b8d3859", "input": "The CEO reminded the housekeeper to sweep up because she often forget .", "output": ["the, housekeeper, she"]}, "Instance License": ["MIT"], "prediction": "The, CEO, she."}
+{"id": "task1664-553d197a5760446ba56fba4102d985de", "Task": "task1664_winobias_text_generation", "Contributors": "['Saradhi Kiran Amarthi']", "Source": ["wino_bias"], "URL": ["https://huggingface.co/datasets/viewer/?dataset=wino_bias"], "Categories": ["Coreference Resolution"], "Reasoning": [], "Definition": ["In this task, you will be given a sentence, and you need to identify the set of coreference words. Coreferences are generally a set of words in the text that refer to the same person or thing. Your output set of coreference words must be strictly present in the given input sentence. Do not use any outside knowledge to create the set of coreference words. If there is a 'the' article before the person or thing you should include 'the' as well. Please separate the coreference words by commas in the output."], "Positive Examples": [{"input": "The developer argued with the designer because he did not like the design.", "output": "The, developer, he", "explanation": "Here the output set of coreference words 'The', 'developer, and 'he' refer to the same person, and these are coreferences. So, the output is correct."}, {"input": "The mechanic greets with the receptionist because he was in a good mood.", "output": "The, mechanic, he", "explanation": "Here the output set of coreference words 'The', 'mechanic, and 'he' refer to the same person, and these are coreferences. So, the output is correct."}, {"input": "The mechanic greets the receptionist because she was standing in front of the door.", "output": "the, receptionist, she", "explanation": "Here the output set of coreference words 'the', 'receptionist, and 'she' refer to the same person, and these are coreferences. So, the output is correct."}, {"input": "The cook is always teaching the assistant new techniques so she will one day be equal in skill.", "output": "the, assistant, she", "explanation": "Here the output set of coreference words 'the', 'assistant, and 'she' refer to the same person, and these are coreferences. So, the output is correct."}], "Negative Examples": [{"input": "The cook is always teaching the assistant new techniques because he likes to teach others.", "output": "The, assistant, others", "explanation": "Here the output set of coreference words 'The', 'assistant, and 'others' do not refer to the same person, and these are coreferences. So, the output is incorrect."}, {"input": "The farmer gave the teacher a bag of eggs because he was grateful.", "output": "The, teacher, he", "explanation": "Here the output set of coreference words 'The', 'teacher, and 'he' do not refer to the same person, and these are coreferences. So, the output is incorrect."}, {"input": "The farmer gave the teacher a bag of eggs because she helped many kids.", "output": "the, farmer, she", "explanation": "Here the output set of coreference words 'The', 'farmer, and 'she' do not refer to the same person, and these are coreferences. So, the output is incorrect."}, {"input": "The CEO bought the accountant a car because he is rich.", "output": "The, accountant, he", "explanation": "Here the output set of coreference words 'The', 'accountant, and 'he' do not refer to the same person, and these are coreferences. So, the output is incorrect."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Professions", "Commonsense"], "Instance": {"id": "task1664-553d197a5760446ba56fba4102d985de", "input": "When the supervisor splashed the editor  he got in trouble .", "output": ["the, supervisor, he"]}, "Instance License": ["MIT"], "prediction": "The, supervisor, he."}
+{"id": "task1161-052a1b62fb3e425db9d9fc8b71953341", "Task": "task1161_coda19_title_generation", "Contributors": "['Ishan Purohit']", "Source": ["coda_19"], "URL": ["https://github.com/windx0303/CODA-19/tree/master/data"], "Categories": ["Title Generation"], "Reasoning": [], "Definition": ["In this task, you're given a paragraph from the research paper and your task is to generate a suitable title for the research paper based on the given paper. Under 100 words is a good title length."], "Positive Examples": [{"input": "The severe acute respiratory syndrome (SARS) epidemic originating from China in 2002 was caused by a previously uncharacterized coronavirus that could be identified by specific RT-PCR amplification. Efforts to control future SARS outbreaks depend on the accurate and early identification of SARS-CoV infected patients. A real-time fluorogenic RT-PCR assay based on the 3 -noncoding region (3 -NCR) of SARS-CoV genome was developed as a quantitative SARS diagnostic tool. The ideal amplification efficiency of a sensitive SARS-CoV RT-PCR assay should yield an E value (PCR product concentration increase per amplification cycle) equal to 2.0. It was demonstrated that the 3 -NCR SARS-CoV based RT-PCR reactions could be formulated to reach excellent E values of 1.81, or 91% amplification efficacy. The SARS-CoV cDNA preparations derived from viral RNA extract and the cloned recombinant plasmid both exhibit the identical amplification characteristics, i.e. amplification efficacy using the same PCR formulation developed in this study. The viral genomic copy (or genomic equivalences, GE) per infectious unit (GE/pfu) of SARS-CoV used in this study was also established to be approximate 1200-1600:1. The assay's detection sensitivity could reach 0.005 pfu or 6-8 GE per assay. It was preliminarily demonstrated that the assay could efficiently detect SARS-CoV from clinical specimens of SARS probable and suspected patients identified in Taiwan. The 3 -NCR based SARS-CoV assay demonstrated 100% diagnostic specificity testing samples of patients with acute respiratory disease from a non-SARS epidemic region.", "output": "Development and evaluation of an efficient 3 -noncoding region-based SARS coronavirus (SARS-CoV) RT-PCR assay for detection of SARS-CoV", "explanation": "It's a correct title because the paragraph described the development of 3 -noncoding region of SARS-CoV genome and assay efficiently detecting SARS-CoV from clinical specimens."}, {"input": "Deubiquitinating enzymes (DUBs) are cysteine protease proteins that reverse the ubiquitination by removing ubiquitins from the target protein. With over 100 DUBs identified and categorized into at least 7 families, many DUBs interact with one or more cytokines, influencing cellular processes, such as antiviral responses, inflammatory responses, apoptosis, etc. While some DUBs influence cytokine pathway or production, some DUBs are cytokine-inducible. In this article, we summarize a list of DUBs, their interaction with cytokines, target proteins and mechanisms of action.", "output": "Regulatory interplay between deubiquitinating enzymes and cytokines", "explanation": "It's a correct title because the paragraph talks about the interaction of deubiquitinating and cytokines that are mentioned in the title."}, {"input": "A novel bat-origin coronavirus emerged in Wuhan, China in December 2019 and continues to spread across China and the world. At the time of writing, a massive global response has been implemented to control the disease as it spreads from person to person. Yet the high-risk human-wildlife interactions and interfaces that led to the emergence of SARS-CoV and of 2019-nCoV continue to exist in emerging disease hotspots globally. To prevent the next epidemic and pandemic related to these interfaces, we call for research and investment in three areas: 1) surveillance among wildlife to identify the high-risk pathogens they carry; 2) surveillance among people who have contact with wildlife to identify early spillover events; and 3) improvement of market biosecurity regarding the wildlife trade. As the emergence of a novel virus anywhere can impact the furthest reaches of our connected world, international collaboration among scientists is essential to address these risks and prevent the next pandemic.", "output": "A strategy to prevent future epidemics similar to the 2019-nCoV outbreak", "explanation": "It's a correct title because the paragraph talks about how to prevent future epidemic and to address the risks."}], "Negative Examples": [{"input": "Linking autoimmune orchitis models to human disease \u2022 Immunopathological sequelae of vasectomy \u2022 Conclusions and future perspectives BACKGROUND: Infection and inflammation of the reproductive tract are significant causes of male factor infertility. Ascending infections caused by sexually transmitted bacteria or urinary tract pathogens represent the most frequent aetiology of epididymo-orchitis, but viral, haematogenous dissemination is also a contributory factor. Limitations in adequate diagnosis and therapy reflect an obvious need for further understanding of human epididymal and testicular immunopathologies and their contribution to infertility. A major obstacle for advancing our knowledge is the limited access to suitable tissue samples. Similarly, the key events in the inflammatory or autoimmune pathologies affecting human male fertility are poorly amenable to close examination. Moreover, the disease processes generally have occurred long before the patient attends the clinic for fertility assessment. In this regard, data obtained from experimental animal models and respective comparative analyses have shown promise to overcome these restrictions in humans.", "output": "dsRNA sensors and plasmacytoid dendritic cells in host defense and autoimmunity The primary response to viral detection: type I interferons", "explanation": "It's an incorrect title because paragraphs because the tasks talk about Infectious, inflammatory and male factor infertility and how do rodent models inform clinical practice?"}, {"input": "This review presents a brief outline and novel developments of electrophoretic separation in microfluidic chips. Distinct characteristics of microchip electrophoresis (MCE) are discussed first, in which sample injection plug, joule heat, channel turn, surface adsorption and modification are introduced, and some successful strategies and recognized conclusions are also included. Important achievements of microfluidic electrophoresis separation in small molecules, DNA and protein are then summarized. This review is aimed at researchers, who are interested in MCE and want to adopt MCE as a functional unit in their integrated microsystems.", "output": "Clinical characteristics and intrauterine vertical transmission potential of COVID-19 infection", "explanation": "It's an incorrect title because paragraph talks about Electrophoretic separations on microfluidic chips."}, {"input": "It is known that the person-to-person spreading of certain infectious diseases is related with the transmission of human exhaled air in the indoor environments, and this is suspected to be the case with the severe acute respiratory syndrome (SARS) outbreak. This paper presents the numerical analysis of the human respiration process and the transport of exhaled air by breathing, sneezing, and coughing and their potential impact on the adjacent person in a modeled room with displacement ventilation. In order to account for the influence of the thermal plume around the human body, a three-dimensional computational thermal manikin (CTM) with an accurate description of body geometry was applied. Some of the results were compared with those from former simulations and experiments. It was found that personal exposure to the exhaled air from the normal respiration process of other persons is very low in a modeled room with displacement ventilation. Personal exposure to pollution caused by sneezing or coughing is highly directional. When two occupants face each other the cross-infection may happen due to the long transport distance of the exhalation.", "output": "Association of Cytokines in Individuals Sensitive and Insensitive to Dust Mites in a Brazilian Population", "explanation": "It's an incorrect title because paragraph talks about Transient CFD simulation of the respiration process and inter-person exposure assessment."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Scientific Research Papers"], "Instance": {"id": "task1161-052a1b62fb3e425db9d9fc8b71953341", "input": "Coccidiosis is an economically significant disease of poultry caused by species of Eimeria, a parasitic protozoan. Disease can result in poor feed conversion, reduced weight gain, and can lead to the development of necrotic enteritis. For prevention of coccidiosis, poultry are commonly vaccinated with a live, sporulated oocysts mass applied with a vaccination cabinet in the hatchery. Traditionally, coccidia vaccines have been applied by coarse spray in a water based diluent, however, new technology using gel diluents has entered the US market. Gel diluents can have variable viscosities and are \"dropped\" onto chicks with an applicator bar. It is thought that gel droplets remain intact on the birds for longer than water based droplets, allowing more time for preening and ingestion of oocysts. In this experiment, the efficacy of a commercial coccidia vaccine applied with a water based diluent, a more viscous gel diluent, and a less viscous gel diluent was compared. Fecal samples were collected at multiple time points post-vaccination to quantify vaccine oocyst shedding. Shedding in the first cycle (days 5 to 8 post-vaccination) was related to the number of oocysts received from each application method, where the groups receiving higher doses shed more oocysts. However, a decrease in shedding was seen for the more viscous gel group in the second cycle (days 12 to 15 post-vaccination). Chickens were challenged with Eimeria maxima oocysts and 7 days post-challenge body weight gains and gross and microscopic lesions were recorded to evaluate protection levels for the different vaccine applications. All vaccinated groups appeared to be protected based on body weight gain and lesion scoring. The results of this project indicate that all vaccine applications are effective at protecting against Eimeria maxima challenge when using a proper dose of vaccine that allows for repeated oocyst cycling in the litter post-vaccination.", "output": ["Evaluation of a coccidia vaccine using spray and gel applications"]}, "Instance License": ["Unknown"], "prediction": "The efficacy of coccidia vaccines applied with gel diluents is compared."}
+{"id": "task1161-f43e034433b046e485e47f5582856c70", "Task": "task1161_coda19_title_generation", "Contributors": "['Ishan Purohit']", "Source": ["coda_19"], "URL": ["https://github.com/windx0303/CODA-19/tree/master/data"], "Categories": ["Title Generation"], "Reasoning": [], "Definition": ["In this task, you're given a paragraph from the research paper and your task is to generate a suitable title for the research paper based on the given paper. Under 100 words is a good title length."], "Positive Examples": [{"input": "The severe acute respiratory syndrome (SARS) epidemic originating from China in 2002 was caused by a previously uncharacterized coronavirus that could be identified by specific RT-PCR amplification. Efforts to control future SARS outbreaks depend on the accurate and early identification of SARS-CoV infected patients. A real-time fluorogenic RT-PCR assay based on the 3 -noncoding region (3 -NCR) of SARS-CoV genome was developed as a quantitative SARS diagnostic tool. The ideal amplification efficiency of a sensitive SARS-CoV RT-PCR assay should yield an E value (PCR product concentration increase per amplification cycle) equal to 2.0. It was demonstrated that the 3 -NCR SARS-CoV based RT-PCR reactions could be formulated to reach excellent E values of 1.81, or 91% amplification efficacy. The SARS-CoV cDNA preparations derived from viral RNA extract and the cloned recombinant plasmid both exhibit the identical amplification characteristics, i.e. amplification efficacy using the same PCR formulation developed in this study. The viral genomic copy (or genomic equivalences, GE) per infectious unit (GE/pfu) of SARS-CoV used in this study was also established to be approximate 1200-1600:1. The assay's detection sensitivity could reach 0.005 pfu or 6-8 GE per assay. It was preliminarily demonstrated that the assay could efficiently detect SARS-CoV from clinical specimens of SARS probable and suspected patients identified in Taiwan. The 3 -NCR based SARS-CoV assay demonstrated 100% diagnostic specificity testing samples of patients with acute respiratory disease from a non-SARS epidemic region.", "output": "Development and evaluation of an efficient 3 -noncoding region-based SARS coronavirus (SARS-CoV) RT-PCR assay for detection of SARS-CoV", "explanation": "It's a correct title because the paragraph described the development of 3 -noncoding region of SARS-CoV genome and assay efficiently detecting SARS-CoV from clinical specimens."}, {"input": "Deubiquitinating enzymes (DUBs) are cysteine protease proteins that reverse the ubiquitination by removing ubiquitins from the target protein. With over 100 DUBs identified and categorized into at least 7 families, many DUBs interact with one or more cytokines, influencing cellular processes, such as antiviral responses, inflammatory responses, apoptosis, etc. While some DUBs influence cytokine pathway or production, some DUBs are cytokine-inducible. In this article, we summarize a list of DUBs, their interaction with cytokines, target proteins and mechanisms of action.", "output": "Regulatory interplay between deubiquitinating enzymes and cytokines", "explanation": "It's a correct title because the paragraph talks about the interaction of deubiquitinating and cytokines that are mentioned in the title."}, {"input": "A novel bat-origin coronavirus emerged in Wuhan, China in December 2019 and continues to spread across China and the world. At the time of writing, a massive global response has been implemented to control the disease as it spreads from person to person. Yet the high-risk human-wildlife interactions and interfaces that led to the emergence of SARS-CoV and of 2019-nCoV continue to exist in emerging disease hotspots globally. To prevent the next epidemic and pandemic related to these interfaces, we call for research and investment in three areas: 1) surveillance among wildlife to identify the high-risk pathogens they carry; 2) surveillance among people who have contact with wildlife to identify early spillover events; and 3) improvement of market biosecurity regarding the wildlife trade. As the emergence of a novel virus anywhere can impact the furthest reaches of our connected world, international collaboration among scientists is essential to address these risks and prevent the next pandemic.", "output": "A strategy to prevent future epidemics similar to the 2019-nCoV outbreak", "explanation": "It's a correct title because the paragraph talks about how to prevent future epidemic and to address the risks."}], "Negative Examples": [{"input": "Linking autoimmune orchitis models to human disease \u2022 Immunopathological sequelae of vasectomy \u2022 Conclusions and future perspectives BACKGROUND: Infection and inflammation of the reproductive tract are significant causes of male factor infertility. Ascending infections caused by sexually transmitted bacteria or urinary tract pathogens represent the most frequent aetiology of epididymo-orchitis, but viral, haematogenous dissemination is also a contributory factor. Limitations in adequate diagnosis and therapy reflect an obvious need for further understanding of human epididymal and testicular immunopathologies and their contribution to infertility. A major obstacle for advancing our knowledge is the limited access to suitable tissue samples. Similarly, the key events in the inflammatory or autoimmune pathologies affecting human male fertility are poorly amenable to close examination. Moreover, the disease processes generally have occurred long before the patient attends the clinic for fertility assessment. In this regard, data obtained from experimental animal models and respective comparative analyses have shown promise to overcome these restrictions in humans.", "output": "dsRNA sensors and plasmacytoid dendritic cells in host defense and autoimmunity The primary response to viral detection: type I interferons", "explanation": "It's an incorrect title because paragraphs because the tasks talk about Infectious, inflammatory and male factor infertility and how do rodent models inform clinical practice?"}, {"input": "This review presents a brief outline and novel developments of electrophoretic separation in microfluidic chips. Distinct characteristics of microchip electrophoresis (MCE) are discussed first, in which sample injection plug, joule heat, channel turn, surface adsorption and modification are introduced, and some successful strategies and recognized conclusions are also included. Important achievements of microfluidic electrophoresis separation in small molecules, DNA and protein are then summarized. This review is aimed at researchers, who are interested in MCE and want to adopt MCE as a functional unit in their integrated microsystems.", "output": "Clinical characteristics and intrauterine vertical transmission potential of COVID-19 infection", "explanation": "It's an incorrect title because paragraph talks about Electrophoretic separations on microfluidic chips."}, {"input": "It is known that the person-to-person spreading of certain infectious diseases is related with the transmission of human exhaled air in the indoor environments, and this is suspected to be the case with the severe acute respiratory syndrome (SARS) outbreak. This paper presents the numerical analysis of the human respiration process and the transport of exhaled air by breathing, sneezing, and coughing and their potential impact on the adjacent person in a modeled room with displacement ventilation. In order to account for the influence of the thermal plume around the human body, a three-dimensional computational thermal manikin (CTM) with an accurate description of body geometry was applied. Some of the results were compared with those from former simulations and experiments. It was found that personal exposure to the exhaled air from the normal respiration process of other persons is very low in a modeled room with displacement ventilation. Personal exposure to pollution caused by sneezing or coughing is highly directional. When two occupants face each other the cross-infection may happen due to the long transport distance of the exhalation.", "output": "Association of Cytokines in Individuals Sensitive and Insensitive to Dust Mites in a Brazilian Population", "explanation": "It's an incorrect title because paragraph talks about Transient CFD simulation of the respiration process and inter-person exposure assessment."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Scientific Research Papers"], "Instance": {"id": "task1161-f43e034433b046e485e47f5582856c70", "input": "Facing the threats of infectious diseases, we take various actions to protect ourselves, but few studies considered an evolving system with competing strategies. In view of that, we propose an evolutionary epidemic model coupled with human behaviors, where individuals have three strategies: vaccination, self-protection and laissez faire, and could adjust their strategies according to their neighbors' strategies and payoffs at the beginning of each new season of epidemic spreading. We found a counter-intuitive phenomenon analogous to the well-known Braess's Paradox, namely a better condition may lead to worse performance. Specifically speaking, increasing the successful rate of self-protection does not necessarily reduce the epidemic size or improve the system payoff. The range and degree of the Braess's Paradox are sensitive to both the parameters characterizing the epidemic spreading and the strategy payoff, while the existence of the Braess's Paradox is insensitive to the network topologies. This phenomenon can be well explained by a mean-field approximation. Our study demonstrates an important fact that a better condition for individuals may yield a worse outcome for the society.", "output": ["Braess's Paradox in Epidemic Game: Better Condition Results in Less Payoff"]}, "Instance License": ["Unknown"], "prediction": "Evolutionary epidemic model with human behaviors"}
+{"id": "task1161-054bdc9c10d9483794b9f4e2f08d3de0", "Task": "task1161_coda19_title_generation", "Contributors": "['Ishan Purohit']", "Source": ["coda_19"], "URL": ["https://github.com/windx0303/CODA-19/tree/master/data"], "Categories": ["Title Generation"], "Reasoning": [], "Definition": ["In this task, you're given a paragraph from the research paper and your task is to generate a suitable title for the research paper based on the given paper. Under 100 words is a good title length."], "Positive Examples": [{"input": "The severe acute respiratory syndrome (SARS) epidemic originating from China in 2002 was caused by a previously uncharacterized coronavirus that could be identified by specific RT-PCR amplification. Efforts to control future SARS outbreaks depend on the accurate and early identification of SARS-CoV infected patients. A real-time fluorogenic RT-PCR assay based on the 3 -noncoding region (3 -NCR) of SARS-CoV genome was developed as a quantitative SARS diagnostic tool. The ideal amplification efficiency of a sensitive SARS-CoV RT-PCR assay should yield an E value (PCR product concentration increase per amplification cycle) equal to 2.0. It was demonstrated that the 3 -NCR SARS-CoV based RT-PCR reactions could be formulated to reach excellent E values of 1.81, or 91% amplification efficacy. The SARS-CoV cDNA preparations derived from viral RNA extract and the cloned recombinant plasmid both exhibit the identical amplification characteristics, i.e. amplification efficacy using the same PCR formulation developed in this study. The viral genomic copy (or genomic equivalences, GE) per infectious unit (GE/pfu) of SARS-CoV used in this study was also established to be approximate 1200-1600:1. The assay's detection sensitivity could reach 0.005 pfu or 6-8 GE per assay. It was preliminarily demonstrated that the assay could efficiently detect SARS-CoV from clinical specimens of SARS probable and suspected patients identified in Taiwan. The 3 -NCR based SARS-CoV assay demonstrated 100% diagnostic specificity testing samples of patients with acute respiratory disease from a non-SARS epidemic region.", "output": "Development and evaluation of an efficient 3 -noncoding region-based SARS coronavirus (SARS-CoV) RT-PCR assay for detection of SARS-CoV", "explanation": "It's a correct title because the paragraph described the development of 3 -noncoding region of SARS-CoV genome and assay efficiently detecting SARS-CoV from clinical specimens."}, {"input": "Deubiquitinating enzymes (DUBs) are cysteine protease proteins that reverse the ubiquitination by removing ubiquitins from the target protein. With over 100 DUBs identified and categorized into at least 7 families, many DUBs interact with one or more cytokines, influencing cellular processes, such as antiviral responses, inflammatory responses, apoptosis, etc. While some DUBs influence cytokine pathway or production, some DUBs are cytokine-inducible. In this article, we summarize a list of DUBs, their interaction with cytokines, target proteins and mechanisms of action.", "output": "Regulatory interplay between deubiquitinating enzymes and cytokines", "explanation": "It's a correct title because the paragraph talks about the interaction of deubiquitinating and cytokines that are mentioned in the title."}, {"input": "A novel bat-origin coronavirus emerged in Wuhan, China in December 2019 and continues to spread across China and the world. At the time of writing, a massive global response has been implemented to control the disease as it spreads from person to person. Yet the high-risk human-wildlife interactions and interfaces that led to the emergence of SARS-CoV and of 2019-nCoV continue to exist in emerging disease hotspots globally. To prevent the next epidemic and pandemic related to these interfaces, we call for research and investment in three areas: 1) surveillance among wildlife to identify the high-risk pathogens they carry; 2) surveillance among people who have contact with wildlife to identify early spillover events; and 3) improvement of market biosecurity regarding the wildlife trade. As the emergence of a novel virus anywhere can impact the furthest reaches of our connected world, international collaboration among scientists is essential to address these risks and prevent the next pandemic.", "output": "A strategy to prevent future epidemics similar to the 2019-nCoV outbreak", "explanation": "It's a correct title because the paragraph talks about how to prevent future epidemic and to address the risks."}], "Negative Examples": [{"input": "Linking autoimmune orchitis models to human disease \u2022 Immunopathological sequelae of vasectomy \u2022 Conclusions and future perspectives BACKGROUND: Infection and inflammation of the reproductive tract are significant causes of male factor infertility. Ascending infections caused by sexually transmitted bacteria or urinary tract pathogens represent the most frequent aetiology of epididymo-orchitis, but viral, haematogenous dissemination is also a contributory factor. Limitations in adequate diagnosis and therapy reflect an obvious need for further understanding of human epididymal and testicular immunopathologies and their contribution to infertility. A major obstacle for advancing our knowledge is the limited access to suitable tissue samples. Similarly, the key events in the inflammatory or autoimmune pathologies affecting human male fertility are poorly amenable to close examination. Moreover, the disease processes generally have occurred long before the patient attends the clinic for fertility assessment. In this regard, data obtained from experimental animal models and respective comparative analyses have shown promise to overcome these restrictions in humans.", "output": "dsRNA sensors and plasmacytoid dendritic cells in host defense and autoimmunity The primary response to viral detection: type I interferons", "explanation": "It's an incorrect title because paragraphs because the tasks talk about Infectious, inflammatory and male factor infertility and how do rodent models inform clinical practice?"}, {"input": "This review presents a brief outline and novel developments of electrophoretic separation in microfluidic chips. Distinct characteristics of microchip electrophoresis (MCE) are discussed first, in which sample injection plug, joule heat, channel turn, surface adsorption and modification are introduced, and some successful strategies and recognized conclusions are also included. Important achievements of microfluidic electrophoresis separation in small molecules, DNA and protein are then summarized. This review is aimed at researchers, who are interested in MCE and want to adopt MCE as a functional unit in their integrated microsystems.", "output": "Clinical characteristics and intrauterine vertical transmission potential of COVID-19 infection", "explanation": "It's an incorrect title because paragraph talks about Electrophoretic separations on microfluidic chips."}, {"input": "It is known that the person-to-person spreading of certain infectious diseases is related with the transmission of human exhaled air in the indoor environments, and this is suspected to be the case with the severe acute respiratory syndrome (SARS) outbreak. This paper presents the numerical analysis of the human respiration process and the transport of exhaled air by breathing, sneezing, and coughing and their potential impact on the adjacent person in a modeled room with displacement ventilation. In order to account for the influence of the thermal plume around the human body, a three-dimensional computational thermal manikin (CTM) with an accurate description of body geometry was applied. Some of the results were compared with those from former simulations and experiments. It was found that personal exposure to the exhaled air from the normal respiration process of other persons is very low in a modeled room with displacement ventilation. Personal exposure to pollution caused by sneezing or coughing is highly directional. When two occupants face each other the cross-infection may happen due to the long transport distance of the exhalation.", "output": "Association of Cytokines in Individuals Sensitive and Insensitive to Dust Mites in a Brazilian Population", "explanation": "It's an incorrect title because paragraph talks about Transient CFD simulation of the respiration process and inter-person exposure assessment."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Scientific Research Papers"], "Instance": {"id": "task1161-054bdc9c10d9483794b9f4e2f08d3de0", "input": "Thread-based microfluidics Point-of-care Cotton Colorimetric Electrochemical A B S T R A C T Over the past decades, researchers have been seeking attractive substrate materials to keep microfluidics improving to outbalance the drawbacks and issues. Cellulose substrates, including thread, paper and hydrogels are alternatives due to their distinct structural and mechanical properties for a number of applications. Thread have gained considerable attention and become promising powerful tool due to its advantages over paper-based systems thus finds numerous applications in the development of diagnostic systems, smart bandages and tissue engineering. To the best of our knowledge, no comprehensive review articles on the topic of thread-based microfluidics have been published and it is of significance for many scientific communities working on Microfluidics, Biosensors and Lab-on-Chip. This review gives an overview of the advances of thread-based microfluidic diagnostic devices in a variety of applications. It begins with an overall introduction of the fabrication followed by an in-depth review on the detection techniques in such devices and various applications with respect to effort and performance to date. A few perspective directions of thread-based microfluidics in its development are also discussed. Thread-based microfluidics are still at an early development stage and further improvements in terms of fabrication, analytical strategies, and function to become low-cost, low-volume and easy-to-use pointof-care (POC) diagnostic devices that can be adapted or commercialized for real world applications.", "output": ["Recent advances in thread-based microfluidics for diagnostic applications"]}, "Instance License": ["Unknown"], "prediction": "Highlights the advances of thread-based microfluidics in a variety of applications."}
+{"id": "task1161-65a10f8a12b34977b4af3f847dfe8aa1", "Task": "task1161_coda19_title_generation", "Contributors": "['Ishan Purohit']", "Source": ["coda_19"], "URL": ["https://github.com/windx0303/CODA-19/tree/master/data"], "Categories": ["Title Generation"], "Reasoning": [], "Definition": ["In this task, you're given a paragraph from the research paper and your task is to generate a suitable title for the research paper based on the given paper. Under 100 words is a good title length."], "Positive Examples": [{"input": "The severe acute respiratory syndrome (SARS) epidemic originating from China in 2002 was caused by a previously uncharacterized coronavirus that could be identified by specific RT-PCR amplification. Efforts to control future SARS outbreaks depend on the accurate and early identification of SARS-CoV infected patients. A real-time fluorogenic RT-PCR assay based on the 3 -noncoding region (3 -NCR) of SARS-CoV genome was developed as a quantitative SARS diagnostic tool. The ideal amplification efficiency of a sensitive SARS-CoV RT-PCR assay should yield an E value (PCR product concentration increase per amplification cycle) equal to 2.0. It was demonstrated that the 3 -NCR SARS-CoV based RT-PCR reactions could be formulated to reach excellent E values of 1.81, or 91% amplification efficacy. The SARS-CoV cDNA preparations derived from viral RNA extract and the cloned recombinant plasmid both exhibit the identical amplification characteristics, i.e. amplification efficacy using the same PCR formulation developed in this study. The viral genomic copy (or genomic equivalences, GE) per infectious unit (GE/pfu) of SARS-CoV used in this study was also established to be approximate 1200-1600:1. The assay's detection sensitivity could reach 0.005 pfu or 6-8 GE per assay. It was preliminarily demonstrated that the assay could efficiently detect SARS-CoV from clinical specimens of SARS probable and suspected patients identified in Taiwan. The 3 -NCR based SARS-CoV assay demonstrated 100% diagnostic specificity testing samples of patients with acute respiratory disease from a non-SARS epidemic region.", "output": "Development and evaluation of an efficient 3 -noncoding region-based SARS coronavirus (SARS-CoV) RT-PCR assay for detection of SARS-CoV", "explanation": "It's a correct title because the paragraph described the development of 3 -noncoding region of SARS-CoV genome and assay efficiently detecting SARS-CoV from clinical specimens."}, {"input": "Deubiquitinating enzymes (DUBs) are cysteine protease proteins that reverse the ubiquitination by removing ubiquitins from the target protein. With over 100 DUBs identified and categorized into at least 7 families, many DUBs interact with one or more cytokines, influencing cellular processes, such as antiviral responses, inflammatory responses, apoptosis, etc. While some DUBs influence cytokine pathway or production, some DUBs are cytokine-inducible. In this article, we summarize a list of DUBs, their interaction with cytokines, target proteins and mechanisms of action.", "output": "Regulatory interplay between deubiquitinating enzymes and cytokines", "explanation": "It's a correct title because the paragraph talks about the interaction of deubiquitinating and cytokines that are mentioned in the title."}, {"input": "A novel bat-origin coronavirus emerged in Wuhan, China in December 2019 and continues to spread across China and the world. At the time of writing, a massive global response has been implemented to control the disease as it spreads from person to person. Yet the high-risk human-wildlife interactions and interfaces that led to the emergence of SARS-CoV and of 2019-nCoV continue to exist in emerging disease hotspots globally. To prevent the next epidemic and pandemic related to these interfaces, we call for research and investment in three areas: 1) surveillance among wildlife to identify the high-risk pathogens they carry; 2) surveillance among people who have contact with wildlife to identify early spillover events; and 3) improvement of market biosecurity regarding the wildlife trade. As the emergence of a novel virus anywhere can impact the furthest reaches of our connected world, international collaboration among scientists is essential to address these risks and prevent the next pandemic.", "output": "A strategy to prevent future epidemics similar to the 2019-nCoV outbreak", "explanation": "It's a correct title because the paragraph talks about how to prevent future epidemic and to address the risks."}], "Negative Examples": [{"input": "Linking autoimmune orchitis models to human disease \u2022 Immunopathological sequelae of vasectomy \u2022 Conclusions and future perspectives BACKGROUND: Infection and inflammation of the reproductive tract are significant causes of male factor infertility. Ascending infections caused by sexually transmitted bacteria or urinary tract pathogens represent the most frequent aetiology of epididymo-orchitis, but viral, haematogenous dissemination is also a contributory factor. Limitations in adequate diagnosis and therapy reflect an obvious need for further understanding of human epididymal and testicular immunopathologies and their contribution to infertility. A major obstacle for advancing our knowledge is the limited access to suitable tissue samples. Similarly, the key events in the inflammatory or autoimmune pathologies affecting human male fertility are poorly amenable to close examination. Moreover, the disease processes generally have occurred long before the patient attends the clinic for fertility assessment. In this regard, data obtained from experimental animal models and respective comparative analyses have shown promise to overcome these restrictions in humans.", "output": "dsRNA sensors and plasmacytoid dendritic cells in host defense and autoimmunity The primary response to viral detection: type I interferons", "explanation": "It's an incorrect title because paragraphs because the tasks talk about Infectious, inflammatory and male factor infertility and how do rodent models inform clinical practice?"}, {"input": "This review presents a brief outline and novel developments of electrophoretic separation in microfluidic chips. Distinct characteristics of microchip electrophoresis (MCE) are discussed first, in which sample injection plug, joule heat, channel turn, surface adsorption and modification are introduced, and some successful strategies and recognized conclusions are also included. Important achievements of microfluidic electrophoresis separation in small molecules, DNA and protein are then summarized. This review is aimed at researchers, who are interested in MCE and want to adopt MCE as a functional unit in their integrated microsystems.", "output": "Clinical characteristics and intrauterine vertical transmission potential of COVID-19 infection", "explanation": "It's an incorrect title because paragraph talks about Electrophoretic separations on microfluidic chips."}, {"input": "It is known that the person-to-person spreading of certain infectious diseases is related with the transmission of human exhaled air in the indoor environments, and this is suspected to be the case with the severe acute respiratory syndrome (SARS) outbreak. This paper presents the numerical analysis of the human respiration process and the transport of exhaled air by breathing, sneezing, and coughing and their potential impact on the adjacent person in a modeled room with displacement ventilation. In order to account for the influence of the thermal plume around the human body, a three-dimensional computational thermal manikin (CTM) with an accurate description of body geometry was applied. Some of the results were compared with those from former simulations and experiments. It was found that personal exposure to the exhaled air from the normal respiration process of other persons is very low in a modeled room with displacement ventilation. Personal exposure to pollution caused by sneezing or coughing is highly directional. When two occupants face each other the cross-infection may happen due to the long transport distance of the exhalation.", "output": "Association of Cytokines in Individuals Sensitive and Insensitive to Dust Mites in a Brazilian Population", "explanation": "It's an incorrect title because paragraph talks about Transient CFD simulation of the respiration process and inter-person exposure assessment."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Scientific Research Papers"], "Instance": {"id": "task1161-65a10f8a12b34977b4af3f847dfe8aa1", "input": "Objective: To describe aspects found on HRCT scans of the chest in patients infected with the influenza A (H1N1) virus. Methods: We retrospectively analyzed the HRCT scans of 71 patients (38 females and 33 males) with H1N1 infection, confirmed through laboratory tests, between July and September of 2009. The HRCT scans were interpreted by two thoracic radiologists independently, and in case of disagreement, the decisions were made by consensus. Results: The most common HRCT findings were ground-glass opacities (85%), consolidation (64%), or a combination of ground-glass opacities and consolidation (58%). Other findings were airspace nodules (25%), bronchial wall thickening (25%), interlobular septal thickening (21%), crazy-paving pattern (15%), perilobular pattern (3%), and air trapping (3%). The findings were frequently bilateral (89%), with a random distribution (68%). Pleural effusion, when observed, was typically minimal. No lymphadenopathy was identified. Conclusions: The most common findings were ground-glass opacities and consolidations, or a combination of both. Involvement was commonly bilateral with no axial or craniocaudal predominance in the distribution. Although the major tomographic findings in H1N1 infection are nonspecific, it is important to recognize such findings in order to include infection with the H1N1 virus in the differential diagnosis of respiratory symptoms. Objetivo: Descrever os aspectos encontrados em TCAR do t\u00f3rax de pacientes infectados pelo v\u00edrus influenza A (H1N1). M\u00e9todos: Foram analisadas retrospectivamente as TCAR de 71 pacientes (38 femininos e 33 masculinos) com diagn\u00f3stico confirmado de influenza A (H1N1) atrav\u00e9s da identifica\u00e7\u00e3o laboratorial do v\u00edrus, estudados no per\u00edodo entre julho e setembro de 2009. A interpreta\u00e7\u00e3o das TCAR foi realizada por dois radiologistas tor\u00e1cicos de forma independente, e, em caso de discord\u00e2ncia, as decis\u00f5es foram tomadas por consenso. Resultados: Os achados de TCAR mais comuns foram opacidades em vidro fosco (85%), consolida\u00e7\u00e3o (64%) ou a combina\u00e7\u00e3o de opacidades em vidro fosco e consolida\u00e7\u00e3o (58%). Outros achados foram n\u00f3dulos do espa\u00e7o a\u00e9reo (25%), espessamento das paredes br\u00f4nquicas (25%), espessamento de septos interlobulares (21%), padr\u00e3o de pavimenta\u00e7\u00e3o em mosaico (15%), espessamento perilobular (3%) e aprisionamento a\u00e9reo (3%). As altera\u00e7\u00f5es foram frequentemente bilaterais (89%), com distribui\u00e7\u00e3o n\u00e3o espec\u00edfica (68%). Derrame pleural, quando observado, foi, em geral, de pequena monta. N\u00e3o foram observadas linfonodomegalias. Conclus\u00f5es: As altera\u00e7\u00f5es predominantes foram opacidades em vidro fosco, consolida\u00e7\u00f5es ou a combina\u00e7\u00e3o de ambas. O acometimento foi frequentemente bilateral e n\u00e3o houve predom\u00ednio quanto \u00e0 distribui\u00e7\u00e3o (axial ou craniocaudal). Apesar de inespec\u00edficos, \u00e9 importante reconhecer os principais aspectos tomogr\u00e1ficos da infec\u00e7\u00e3o por influenza A (H1N1) a fim de incluir essa possibilidade no diagn\u00f3stico diferencial de sintomas respirat\u00f3rios. Descritores: Pneumonia viral; Tomografia computadorizada por raios X; V\u00edrus da influenza A subtipo H1N1.", "output": ["Influenza A (H1N1) pneumonia: HRCT findings* Pneumonia por v\u00edrus influenza A (H1N1): aspectos na TCAR"]}, "Instance License": ["Unknown"], "prediction": "t\u00f3rax de pacientes infected with the influenza A (H1N1 virus)"}
+{"id": "task1161-7fe87d5c00574201bc671100cd36e55a", "Task": "task1161_coda19_title_generation", "Contributors": "['Ishan Purohit']", "Source": ["coda_19"], "URL": ["https://github.com/windx0303/CODA-19/tree/master/data"], "Categories": ["Title Generation"], "Reasoning": [], "Definition": ["In this task, you're given a paragraph from the research paper and your task is to generate a suitable title for the research paper based on the given paper. Under 100 words is a good title length."], "Positive Examples": [{"input": "The severe acute respiratory syndrome (SARS) epidemic originating from China in 2002 was caused by a previously uncharacterized coronavirus that could be identified by specific RT-PCR amplification. Efforts to control future SARS outbreaks depend on the accurate and early identification of SARS-CoV infected patients. A real-time fluorogenic RT-PCR assay based on the 3 -noncoding region (3 -NCR) of SARS-CoV genome was developed as a quantitative SARS diagnostic tool. The ideal amplification efficiency of a sensitive SARS-CoV RT-PCR assay should yield an E value (PCR product concentration increase per amplification cycle) equal to 2.0. It was demonstrated that the 3 -NCR SARS-CoV based RT-PCR reactions could be formulated to reach excellent E values of 1.81, or 91% amplification efficacy. The SARS-CoV cDNA preparations derived from viral RNA extract and the cloned recombinant plasmid both exhibit the identical amplification characteristics, i.e. amplification efficacy using the same PCR formulation developed in this study. The viral genomic copy (or genomic equivalences, GE) per infectious unit (GE/pfu) of SARS-CoV used in this study was also established to be approximate 1200-1600:1. The assay's detection sensitivity could reach 0.005 pfu or 6-8 GE per assay. It was preliminarily demonstrated that the assay could efficiently detect SARS-CoV from clinical specimens of SARS probable and suspected patients identified in Taiwan. The 3 -NCR based SARS-CoV assay demonstrated 100% diagnostic specificity testing samples of patients with acute respiratory disease from a non-SARS epidemic region.", "output": "Development and evaluation of an efficient 3 -noncoding region-based SARS coronavirus (SARS-CoV) RT-PCR assay for detection of SARS-CoV", "explanation": "It's a correct title because the paragraph described the development of 3 -noncoding region of SARS-CoV genome and assay efficiently detecting SARS-CoV from clinical specimens."}, {"input": "Deubiquitinating enzymes (DUBs) are cysteine protease proteins that reverse the ubiquitination by removing ubiquitins from the target protein. With over 100 DUBs identified and categorized into at least 7 families, many DUBs interact with one or more cytokines, influencing cellular processes, such as antiviral responses, inflammatory responses, apoptosis, etc. While some DUBs influence cytokine pathway or production, some DUBs are cytokine-inducible. In this article, we summarize a list of DUBs, their interaction with cytokines, target proteins and mechanisms of action.", "output": "Regulatory interplay between deubiquitinating enzymes and cytokines", "explanation": "It's a correct title because the paragraph talks about the interaction of deubiquitinating and cytokines that are mentioned in the title."}, {"input": "A novel bat-origin coronavirus emerged in Wuhan, China in December 2019 and continues to spread across China and the world. At the time of writing, a massive global response has been implemented to control the disease as it spreads from person to person. Yet the high-risk human-wildlife interactions and interfaces that led to the emergence of SARS-CoV and of 2019-nCoV continue to exist in emerging disease hotspots globally. To prevent the next epidemic and pandemic related to these interfaces, we call for research and investment in three areas: 1) surveillance among wildlife to identify the high-risk pathogens they carry; 2) surveillance among people who have contact with wildlife to identify early spillover events; and 3) improvement of market biosecurity regarding the wildlife trade. As the emergence of a novel virus anywhere can impact the furthest reaches of our connected world, international collaboration among scientists is essential to address these risks and prevent the next pandemic.", "output": "A strategy to prevent future epidemics similar to the 2019-nCoV outbreak", "explanation": "It's a correct title because the paragraph talks about how to prevent future epidemic and to address the risks."}], "Negative Examples": [{"input": "Linking autoimmune orchitis models to human disease \u2022 Immunopathological sequelae of vasectomy \u2022 Conclusions and future perspectives BACKGROUND: Infection and inflammation of the reproductive tract are significant causes of male factor infertility. Ascending infections caused by sexually transmitted bacteria or urinary tract pathogens represent the most frequent aetiology of epididymo-orchitis, but viral, haematogenous dissemination is also a contributory factor. Limitations in adequate diagnosis and therapy reflect an obvious need for further understanding of human epididymal and testicular immunopathologies and their contribution to infertility. A major obstacle for advancing our knowledge is the limited access to suitable tissue samples. Similarly, the key events in the inflammatory or autoimmune pathologies affecting human male fertility are poorly amenable to close examination. Moreover, the disease processes generally have occurred long before the patient attends the clinic for fertility assessment. In this regard, data obtained from experimental animal models and respective comparative analyses have shown promise to overcome these restrictions in humans.", "output": "dsRNA sensors and plasmacytoid dendritic cells in host defense and autoimmunity The primary response to viral detection: type I interferons", "explanation": "It's an incorrect title because paragraphs because the tasks talk about Infectious, inflammatory and male factor infertility and how do rodent models inform clinical practice?"}, {"input": "This review presents a brief outline and novel developments of electrophoretic separation in microfluidic chips. Distinct characteristics of microchip electrophoresis (MCE) are discussed first, in which sample injection plug, joule heat, channel turn, surface adsorption and modification are introduced, and some successful strategies and recognized conclusions are also included. Important achievements of microfluidic electrophoresis separation in small molecules, DNA and protein are then summarized. This review is aimed at researchers, who are interested in MCE and want to adopt MCE as a functional unit in their integrated microsystems.", "output": "Clinical characteristics and intrauterine vertical transmission potential of COVID-19 infection", "explanation": "It's an incorrect title because paragraph talks about Electrophoretic separations on microfluidic chips."}, {"input": "It is known that the person-to-person spreading of certain infectious diseases is related with the transmission of human exhaled air in the indoor environments, and this is suspected to be the case with the severe acute respiratory syndrome (SARS) outbreak. This paper presents the numerical analysis of the human respiration process and the transport of exhaled air by breathing, sneezing, and coughing and their potential impact on the adjacent person in a modeled room with displacement ventilation. In order to account for the influence of the thermal plume around the human body, a three-dimensional computational thermal manikin (CTM) with an accurate description of body geometry was applied. Some of the results were compared with those from former simulations and experiments. It was found that personal exposure to the exhaled air from the normal respiration process of other persons is very low in a modeled room with displacement ventilation. Personal exposure to pollution caused by sneezing or coughing is highly directional. When two occupants face each other the cross-infection may happen due to the long transport distance of the exhalation.", "output": "Association of Cytokines in Individuals Sensitive and Insensitive to Dust Mites in a Brazilian Population", "explanation": "It's an incorrect title because paragraph talks about Transient CFD simulation of the respiration process and inter-person exposure assessment."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Scientific Research Papers"], "Instance": {"id": "task1161-7fe87d5c00574201bc671100cd36e55a", "input": "Biological oscillators are vital to living organisms, which use them as clocks for time-sensitive processes. However, much is unknown about mechanisms which can give rise to coherent oscillatory behavior, with few exceptions (e.g., explicitly delayed self-repressors and simple models of specific organisms' circadian clocks). We present what may be the simplest possible reliable gene network oscillator, a self-repressing gene. We show that binding cooperativity, which has not been considered in detail in this context, can combine with small numbers of intermediate steps to create coherent oscillation. We also note that noise blurs the line between oscillatory and non-oscillatory behavior.", "output": ["Oscillation, cooperativity, and intermediates in the self-repressing gene"]}, "Instance License": ["Unknown"], "prediction": "Biological oscillators are vital to living organisms, which use them as clocks for time-sensitive processes."}
+{"id": "task880-0634735279fc4b16acc05459c87d8684", "Task": "task880_schema_guided_dstc8_classification", "Contributors": "['Subba Raja Kashyap Saligrama']", "Source": ["schema_guided_dstc8"], "URL": ["https://huggingface.co/datasets/schema_guided_dstc8"], "Categories": ["Dialogue Act Recognition"], "Reasoning": ["Reasoning on Social Interactions"], "Definition": ["You are given a sentence from a conversation between a human and a virtual assistant. Your task is to classify the sentence into one of the following five action categories - INFORM, INFORM_INTENT, OFFER, REQUEST, REQUEST_ALTS. If the sentence is about informing something, generate 'INFORM'. If it is about requesting something, generate 'REQUEST'. If the sentence mentions requesting an alternative option than the one provided, generate 'REQUEST_ALTS'. Similarly, generate 'OFFER' if the sentence is offering some information. If the sentence is about showing intent to do something, generate 'INFORM_INTENT'."], "Positive Examples": [{"input": "Now seems a good moment to watch the movie.", "output": "INFORM_INTENT", "explanation": "The user is passively expressing his intent to watch a movie and asking for a suggestion"}, {"input": "Do you have a specific which you want the eating place to be located at?", "output": "REQUEST", "explanation": "The system is requesting the user for location preferences"}, {"input": "I see that at 71 Saint Peter there is a good restaurant which is in San Jose.", "output": "OFFER", "explanation": "The system is offering the information it gathered based on the details provided"}, {"input": "They do serve alcohol but there is no live music.", "output": "INFORM", "explanation": "The system is giving specific details about a restaurant. So, it comes under INFORM action"}, {"input": "There's 1 at La Boom, the event title is Americo.", "output": "OFFER", "explanation": "The system is offering an event."}, {"input": "That sounds good to me. I would like to buy 4 tickets to that event.", "output": "INFORM", "explanation": "The human is informing the system that they like 4 tickets."}, {"input": "Ok, Find me another restaurant?", "output": "REQUEST_ALTS", "explanation": "The user is asking for other alternatives than the suggested restaurant. So, it comes under REQUEST_ALTS action"}], "Negative Examples": [{"input": "Is there some other restaurant which you can suggest?", "output": "REQUEST", "explanation": "The user here is requesting for other alternatives. So, it should be REQUEST_ALTS"}, {"input": "How would you like Bazille restaurant which is situated in San Jose.", "output": "INFORM", "explanation": "The system here is offering an option to the user, not informing any details about the restaurant. So, it should be OFFER."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Dialogue"], "Instance": {"id": "task880-0634735279fc4b16acc05459c87d8684", "input": "I am looking for a song that could make me happy.", "output": ["INFORM_INTENT"]}, "Instance License": ["CC BY-SA 4.0"], "prediction": "REQUEST"}
+{"id": "task880-a1c1676a5d27458ea8fc93306a253184", "Task": "task880_schema_guided_dstc8_classification", "Contributors": "['Subba Raja Kashyap Saligrama']", "Source": ["schema_guided_dstc8"], "URL": ["https://huggingface.co/datasets/schema_guided_dstc8"], "Categories": ["Dialogue Act Recognition"], "Reasoning": ["Reasoning on Social Interactions"], "Definition": ["You are given a sentence from a conversation between a human and a virtual assistant. Your task is to classify the sentence into one of the following five action categories - INFORM, INFORM_INTENT, OFFER, REQUEST, REQUEST_ALTS. If the sentence is about informing something, generate 'INFORM'. If it is about requesting something, generate 'REQUEST'. If the sentence mentions requesting an alternative option than the one provided, generate 'REQUEST_ALTS'. Similarly, generate 'OFFER' if the sentence is offering some information. If the sentence is about showing intent to do something, generate 'INFORM_INTENT'."], "Positive Examples": [{"input": "Now seems a good moment to watch the movie.", "output": "INFORM_INTENT", "explanation": "The user is passively expressing his intent to watch a movie and asking for a suggestion"}, {"input": "Do you have a specific which you want the eating place to be located at?", "output": "REQUEST", "explanation": "The system is requesting the user for location preferences"}, {"input": "I see that at 71 Saint Peter there is a good restaurant which is in San Jose.", "output": "OFFER", "explanation": "The system is offering the information it gathered based on the details provided"}, {"input": "They do serve alcohol but there is no live music.", "output": "INFORM", "explanation": "The system is giving specific details about a restaurant. So, it comes under INFORM action"}, {"input": "There's 1 at La Boom, the event title is Americo.", "output": "OFFER", "explanation": "The system is offering an event."}, {"input": "That sounds good to me. I would like to buy 4 tickets to that event.", "output": "INFORM", "explanation": "The human is informing the system that they like 4 tickets."}, {"input": "Ok, Find me another restaurant?", "output": "REQUEST_ALTS", "explanation": "The user is asking for other alternatives than the suggested restaurant. So, it comes under REQUEST_ALTS action"}], "Negative Examples": [{"input": "Is there some other restaurant which you can suggest?", "output": "REQUEST", "explanation": "The user here is requesting for other alternatives. So, it should be REQUEST_ALTS"}, {"input": "How would you like Bazille restaurant which is situated in San Jose.", "output": "INFORM", "explanation": "The system here is offering an option to the user, not informing any details about the restaurant. So, it should be OFFER."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Dialogue"], "Instance": {"id": "task880-a1c1676a5d27458ea8fc93306a253184", "input": "Are there any other events you would like to check?", "output": ["REQUEST_ALTS"]}, "Instance License": ["CC BY-SA 4.0"], "prediction": "REQUEST"}
+{"id": "task880-ef74168bbd74404ca05ba168ac9b749a", "Task": "task880_schema_guided_dstc8_classification", "Contributors": "['Subba Raja Kashyap Saligrama']", "Source": ["schema_guided_dstc8"], "URL": ["https://huggingface.co/datasets/schema_guided_dstc8"], "Categories": ["Dialogue Act Recognition"], "Reasoning": ["Reasoning on Social Interactions"], "Definition": ["You are given a sentence from a conversation between a human and a virtual assistant. Your task is to classify the sentence into one of the following five action categories - INFORM, INFORM_INTENT, OFFER, REQUEST, REQUEST_ALTS. If the sentence is about informing something, generate 'INFORM'. If it is about requesting something, generate 'REQUEST'. If the sentence mentions requesting an alternative option than the one provided, generate 'REQUEST_ALTS'. Similarly, generate 'OFFER' if the sentence is offering some information. If the sentence is about showing intent to do something, generate 'INFORM_INTENT'."], "Positive Examples": [{"input": "Now seems a good moment to watch the movie.", "output": "INFORM_INTENT", "explanation": "The user is passively expressing his intent to watch a movie and asking for a suggestion"}, {"input": "Do you have a specific which you want the eating place to be located at?", "output": "REQUEST", "explanation": "The system is requesting the user for location preferences"}, {"input": "I see that at 71 Saint Peter there is a good restaurant which is in San Jose.", "output": "OFFER", "explanation": "The system is offering the information it gathered based on the details provided"}, {"input": "They do serve alcohol but there is no live music.", "output": "INFORM", "explanation": "The system is giving specific details about a restaurant. So, it comes under INFORM action"}, {"input": "There's 1 at La Boom, the event title is Americo.", "output": "OFFER", "explanation": "The system is offering an event."}, {"input": "That sounds good to me. I would like to buy 4 tickets to that event.", "output": "INFORM", "explanation": "The human is informing the system that they like 4 tickets."}, {"input": "Ok, Find me another restaurant?", "output": "REQUEST_ALTS", "explanation": "The user is asking for other alternatives than the suggested restaurant. So, it comes under REQUEST_ALTS action"}], "Negative Examples": [{"input": "Is there some other restaurant which you can suggest?", "output": "REQUEST", "explanation": "The user here is requesting for other alternatives. So, it should be REQUEST_ALTS"}, {"input": "How would you like Bazille restaurant which is situated in San Jose.", "output": "INFORM", "explanation": "The system here is offering an option to the user, not informing any details about the restaurant. So, it should be OFFER."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Dialogue"], "Instance": {"id": "task880-ef74168bbd74404ca05ba168ac9b749a", "input": "Do you have other suggestions?", "output": ["REQUEST_ALTS"]}, "Instance License": ["CC BY-SA 4.0"], "prediction": "REQUEST"}
+{"id": "task880-98314531ff684e29af77c4f953c5c5d0", "Task": "task880_schema_guided_dstc8_classification", "Contributors": "['Subba Raja Kashyap Saligrama']", "Source": ["schema_guided_dstc8"], "URL": ["https://huggingface.co/datasets/schema_guided_dstc8"], "Categories": ["Dialogue Act Recognition"], "Reasoning": ["Reasoning on Social Interactions"], "Definition": ["You are given a sentence from a conversation between a human and a virtual assistant. Your task is to classify the sentence into one of the following five action categories - INFORM, INFORM_INTENT, OFFER, REQUEST, REQUEST_ALTS. If the sentence is about informing something, generate 'INFORM'. If it is about requesting something, generate 'REQUEST'. If the sentence mentions requesting an alternative option than the one provided, generate 'REQUEST_ALTS'. Similarly, generate 'OFFER' if the sentence is offering some information. If the sentence is about showing intent to do something, generate 'INFORM_INTENT'."], "Positive Examples": [{"input": "Now seems a good moment to watch the movie.", "output": "INFORM_INTENT", "explanation": "The user is passively expressing his intent to watch a movie and asking for a suggestion"}, {"input": "Do you have a specific which you want the eating place to be located at?", "output": "REQUEST", "explanation": "The system is requesting the user for location preferences"}, {"input": "I see that at 71 Saint Peter there is a good restaurant which is in San Jose.", "output": "OFFER", "explanation": "The system is offering the information it gathered based on the details provided"}, {"input": "They do serve alcohol but there is no live music.", "output": "INFORM", "explanation": "The system is giving specific details about a restaurant. So, it comes under INFORM action"}, {"input": "There's 1 at La Boom, the event title is Americo.", "output": "OFFER", "explanation": "The system is offering an event."}, {"input": "That sounds good to me. I would like to buy 4 tickets to that event.", "output": "INFORM", "explanation": "The human is informing the system that they like 4 tickets."}, {"input": "Ok, Find me another restaurant?", "output": "REQUEST_ALTS", "explanation": "The user is asking for other alternatives than the suggested restaurant. So, it comes under REQUEST_ALTS action"}], "Negative Examples": [{"input": "Is there some other restaurant which you can suggest?", "output": "REQUEST", "explanation": "The user here is requesting for other alternatives. So, it should be REQUEST_ALTS"}, {"input": "How would you like Bazille restaurant which is situated in San Jose.", "output": "INFORM", "explanation": "The system here is offering an option to the user, not informing any details about the restaurant. So, it should be OFFER."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Dialogue"], "Instance": {"id": "task880-98314531ff684e29af77c4f953c5c5d0", "input": "Do you know the where the event will be and when it will start?", "output": ["REQUEST"]}, "Instance License": ["CC BY-SA 4.0"], "prediction": "REQUEST"}
+{"id": "task880-8d0054dc46e7483ca8fda5247c4b1861", "Task": "task880_schema_guided_dstc8_classification", "Contributors": "['Subba Raja Kashyap Saligrama']", "Source": ["schema_guided_dstc8"], "URL": ["https://huggingface.co/datasets/schema_guided_dstc8"], "Categories": ["Dialogue Act Recognition"], "Reasoning": ["Reasoning on Social Interactions"], "Definition": ["You are given a sentence from a conversation between a human and a virtual assistant. Your task is to classify the sentence into one of the following five action categories - INFORM, INFORM_INTENT, OFFER, REQUEST, REQUEST_ALTS. If the sentence is about informing something, generate 'INFORM'. If it is about requesting something, generate 'REQUEST'. If the sentence mentions requesting an alternative option than the one provided, generate 'REQUEST_ALTS'. Similarly, generate 'OFFER' if the sentence is offering some information. If the sentence is about showing intent to do something, generate 'INFORM_INTENT'."], "Positive Examples": [{"input": "Now seems a good moment to watch the movie.", "output": "INFORM_INTENT", "explanation": "The user is passively expressing his intent to watch a movie and asking for a suggestion"}, {"input": "Do you have a specific which you want the eating place to be located at?", "output": "REQUEST", "explanation": "The system is requesting the user for location preferences"}, {"input": "I see that at 71 Saint Peter there is a good restaurant which is in San Jose.", "output": "OFFER", "explanation": "The system is offering the information it gathered based on the details provided"}, {"input": "They do serve alcohol but there is no live music.", "output": "INFORM", "explanation": "The system is giving specific details about a restaurant. So, it comes under INFORM action"}, {"input": "There's 1 at La Boom, the event title is Americo.", "output": "OFFER", "explanation": "The system is offering an event."}, {"input": "That sounds good to me. I would like to buy 4 tickets to that event.", "output": "INFORM", "explanation": "The human is informing the system that they like 4 tickets."}, {"input": "Ok, Find me another restaurant?", "output": "REQUEST_ALTS", "explanation": "The user is asking for other alternatives than the suggested restaurant. So, it comes under REQUEST_ALTS action"}], "Negative Examples": [{"input": "Is there some other restaurant which you can suggest?", "output": "REQUEST", "explanation": "The user here is requesting for other alternatives. So, it should be REQUEST_ALTS"}, {"input": "How would you like Bazille restaurant which is situated in San Jose.", "output": "INFORM", "explanation": "The system here is offering an option to the user, not informing any details about the restaurant. So, it should be OFFER."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Dialogue"], "Instance": {"id": "task880-8d0054dc46e7483ca8fda5247c4b1861", "input": "Okay. Buy me tickets.", "output": ["INFORM_INTENT"]}, "Instance License": ["CC BY-SA 4.0"], "prediction": "INFORM_INTENT"}
+{"id": "task738-9973794d3d034a9daaf82b163af3cb07", "Task": "task738_perspectrum_classification", "Contributors": "['Pegah Alipoormolabashi']", "Source": ["perspectrum"], "URL": ["https://github.com/CogComp/perspectrum/"], "Categories": ["Textual Entailment"], "Reasoning": ["Textual Entailment"], "Definition": ["In this task you will be given a claim and a perspective. You should determine whether that perspective supports or undermines the claim. If the perspective could possibly convince someone with different view, it is supporting, otherwise it is undermining."], "Positive Examples": [{"input": "claim: Music containing lyrics that glorify violent and criminal lifestyles should be banned.\n perspective: hip hop artists have a right to free speech", "output": "undermine", "explanation": "Musicians having a right to free speech clearly undermines the claim for putting constraints on their lyrics."}, {"input": "claim: Abolish the US Electoral College.\n perspective: The electoral college weakens incentives for voting and party building.", "output": "support", "explanation": "The perspective is clearly in support of the claim as it is giving an example of problems of the Electoral College."}], "Negative Examples": [{"input": "claim: Abolish the monarchy.\n perspective: monarchy in britain led to lots of chaos in the past", "output": "undermine", "explanation": "The given perspective is supporting the claim, so this is not a correct answer."}, {"input": "claim: Gambling must be banned.\n perspective: Casinos support local communities financially.", "output": "weaken", "explanation": "The perspective is weakening the claim, but your answer should only be one of \"support\" or \"undermine\"."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Debatepedia"], "Instance": {"id": "task738-9973794d3d034a9daaf82b163af3cb07", "input": "claim: Speed limits should be reduced.\n perspective: Government have illegitimate reasons behind lowering the speed limit ", "output": ["undermine"]}, "Instance License": ["CC BY-SA"], "prediction": "support"}
+{"id": "task738-512d68c894d14aa9908553bf00c1a5db", "Task": "task738_perspectrum_classification", "Contributors": "['Pegah Alipoormolabashi']", "Source": ["perspectrum"], "URL": ["https://github.com/CogComp/perspectrum/"], "Categories": ["Textual Entailment"], "Reasoning": ["Textual Entailment"], "Definition": ["In this task you will be given a claim and a perspective. You should determine whether that perspective supports or undermines the claim. If the perspective could possibly convince someone with different view, it is supporting, otherwise it is undermining."], "Positive Examples": [{"input": "claim: Music containing lyrics that glorify violent and criminal lifestyles should be banned.\n perspective: hip hop artists have a right to free speech", "output": "undermine", "explanation": "Musicians having a right to free speech clearly undermines the claim for putting constraints on their lyrics."}, {"input": "claim: Abolish the US Electoral College.\n perspective: The electoral college weakens incentives for voting and party building.", "output": "support", "explanation": "The perspective is clearly in support of the claim as it is giving an example of problems of the Electoral College."}], "Negative Examples": [{"input": "claim: Abolish the monarchy.\n perspective: monarchy in britain led to lots of chaos in the past", "output": "undermine", "explanation": "The given perspective is supporting the claim, so this is not a correct answer."}, {"input": "claim: Gambling must be banned.\n perspective: Casinos support local communities financially.", "output": "weaken", "explanation": "The perspective is weakening the claim, but your answer should only be one of \"support\" or \"undermine\"."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Debatepedia"], "Instance": {"id": "task738-512d68c894d14aa9908553bf00c1a5db", "input": "claim: People should have a right to private education.\n perspective: Private schools are financially good for the state", "output": ["support"]}, "Instance License": ["CC BY-SA"], "prediction": "support"}
+{"id": "task738-a66a3cbb55f2489a842f916f4e119def", "Task": "task738_perspectrum_classification", "Contributors": "['Pegah Alipoormolabashi']", "Source": ["perspectrum"], "URL": ["https://github.com/CogComp/perspectrum/"], "Categories": ["Textual Entailment"], "Reasoning": ["Textual Entailment"], "Definition": ["In this task you will be given a claim and a perspective. You should determine whether that perspective supports or undermines the claim. If the perspective could possibly convince someone with different view, it is supporting, otherwise it is undermining."], "Positive Examples": [{"input": "claim: Music containing lyrics that glorify violent and criminal lifestyles should be banned.\n perspective: hip hop artists have a right to free speech", "output": "undermine", "explanation": "Musicians having a right to free speech clearly undermines the claim for putting constraints on their lyrics."}, {"input": "claim: Abolish the US Electoral College.\n perspective: The electoral college weakens incentives for voting and party building.", "output": "support", "explanation": "The perspective is clearly in support of the claim as it is giving an example of problems of the Electoral College."}], "Negative Examples": [{"input": "claim: Abolish the monarchy.\n perspective: monarchy in britain led to lots of chaos in the past", "output": "undermine", "explanation": "The given perspective is supporting the claim, so this is not a correct answer."}, {"input": "claim: Gambling must be banned.\n perspective: Casinos support local communities financially.", "output": "weaken", "explanation": "The perspective is weakening the claim, but your answer should only be one of \"support\" or \"undermine\"."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Debatepedia"], "Instance": {"id": "task738-a66a3cbb55f2489a842f916f4e119def", "input": "claim: Democracy Is the Best Form of Government.\n perspective: Promoting democracy promotes peace.", "output": ["support"]}, "Instance License": ["CC BY-SA"], "prediction": "support"}
+{"id": "task738-f186796e9e2942ea8a3a71c520c98fc5", "Task": "task738_perspectrum_classification", "Contributors": "['Pegah Alipoormolabashi']", "Source": ["perspectrum"], "URL": ["https://github.com/CogComp/perspectrum/"], "Categories": ["Textual Entailment"], "Reasoning": ["Textual Entailment"], "Definition": ["In this task you will be given a claim and a perspective. You should determine whether that perspective supports or undermines the claim. If the perspective could possibly convince someone with different view, it is supporting, otherwise it is undermining."], "Positive Examples": [{"input": "claim: Music containing lyrics that glorify violent and criminal lifestyles should be banned.\n perspective: hip hop artists have a right to free speech", "output": "undermine", "explanation": "Musicians having a right to free speech clearly undermines the claim for putting constraints on their lyrics."}, {"input": "claim: Abolish the US Electoral College.\n perspective: The electoral college weakens incentives for voting and party building.", "output": "support", "explanation": "The perspective is clearly in support of the claim as it is giving an example of problems of the Electoral College."}], "Negative Examples": [{"input": "claim: Abolish the monarchy.\n perspective: monarchy in britain led to lots of chaos in the past", "output": "undermine", "explanation": "The given perspective is supporting the claim, so this is not a correct answer."}, {"input": "claim: Gambling must be banned.\n perspective: Casinos support local communities financially.", "output": "weaken", "explanation": "The perspective is weakening the claim, but your answer should only be one of \"support\" or \"undermine\"."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Debatepedia"], "Instance": {"id": "task738-f186796e9e2942ea8a3a71c520c98fc5", "input": "claim: Deny Organs to Non-Donors.\n perspective: People may have valid religious reasons not to donate organs", "output": ["undermine"]}, "Instance License": ["CC BY-SA"], "prediction": "support"}
+{"id": "task738-bdb32a02e39441acb7642d399f79e3f1", "Task": "task738_perspectrum_classification", "Contributors": "['Pegah Alipoormolabashi']", "Source": ["perspectrum"], "URL": ["https://github.com/CogComp/perspectrum/"], "Categories": ["Textual Entailment"], "Reasoning": ["Textual Entailment"], "Definition": ["In this task you will be given a claim and a perspective. You should determine whether that perspective supports or undermines the claim. If the perspective could possibly convince someone with different view, it is supporting, otherwise it is undermining."], "Positive Examples": [{"input": "claim: Music containing lyrics that glorify violent and criminal lifestyles should be banned.\n perspective: hip hop artists have a right to free speech", "output": "undermine", "explanation": "Musicians having a right to free speech clearly undermines the claim for putting constraints on their lyrics."}, {"input": "claim: Abolish the US Electoral College.\n perspective: The electoral college weakens incentives for voting and party building.", "output": "support", "explanation": "The perspective is clearly in support of the claim as it is giving an example of problems of the Electoral College."}], "Negative Examples": [{"input": "claim: Abolish the monarchy.\n perspective: monarchy in britain led to lots of chaos in the past", "output": "undermine", "explanation": "The given perspective is supporting the claim, so this is not a correct answer."}, {"input": "claim: Gambling must be banned.\n perspective: Casinos support local communities financially.", "output": "weaken", "explanation": "The perspective is weakening the claim, but your answer should only be one of \"support\" or \"undermine\"."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Debatepedia"], "Instance": {"id": "task738-bdb32a02e39441acb7642d399f79e3f1", "input": "claim: We should expand NATO.\n perspective: NATO development was important  for international stability ", "output": ["support"]}, "Instance License": ["CC BY-SA"], "prediction": "support"}
+{"id": "task1439-7d88f45c6eff4aea9353875c972cfd7c", "Task": "task1439_doqa_cooking_isanswerable", "Contributors": "['Kuntal Kumar Pal']", "Source": ["doqa"], "URL": ["http://www.ixa.eus/node/12931"], "Categories": ["Answerability Classification"], "Reasoning": ["Reasoning on Social Interactions"], "Definition": ["Given a paragraph about cooking, and a set of conversational questions and answers about the paragraph, say whether the passage contains sufficient information to answer the follow-up question. Say Yes if it is answerable; otherwise, say No. The paragraph has the prefix 'CONTEXT:'. Each conversation question has a prefix `Q:` followed by the answer prefix `A:`, and the follow-up question has a prefix `FOLLOWUP_Q:`."], "Positive Examples": [{"input": "CONTEXT: Duck feet will render plenty of gelatin because of the amount of cartilage, same as chicken feet. Any bird's feet are a good choice.The method for making stock is pretty much the same no matter what you put into it, so yes, you can follow your favourite recipe for chicken stock and substitute duck feet. The only thing to keep in mind is that duck feet, like any other duck parts, are substantially more fatty than their chicken equivalents, so assuming you want a clear or mostly-clear stock, you'll have to spend a lot of time skimming.Alternatively you can clean the feet and other bones by boiling them in plain water for 5-10 minutes, then dumping it all out and starting over - which is what your linked recipe suggests. I don't usually do this for brown stocks because you lose a lot of flavour, but if you're starting from raw then it won't make much difference and it's an easy/lazy way to get rid of a lot of the fat at once. <sep> Q: Can I use duck feet to make duck stock A: The method for making stock is pretty much the same no matter what you put into it, so yes, you can follow your favourite recipe for chicken stock and substitute duck feet  Q: Does it add the same flavor and mouth feel? A: The only thing to keep in mind is that duck feet, like any other duck parts, are substantially more fatty than their chicken equivalents  <sep> FOLLOWUP_Q: How does this change things?", "output": "Yes", "explanation": "The question asks about how the stock can be less fatty or mostly clear. This can be infered from the previous conversation. The answer is written in the passage that if mostly clear stock is needed then one has spend a lot of time skimming."}, {"input": "CONTEXT: Simple: grate it. If you grate the nutmeg using a microplane, it should have a strong, distinctive odor you can smell from a couple feet away. If it doesn't, it's lost its flavor, throw it away and buy new. It's fairly likely you're going to end up replacing it. I've never seen nutmegs get moldy before, and I live somewhere with 80% humidity. It would have to be stored in some very poor conditions to mold. <sep>  Q: How to distinguish nutmeg freshness? A: If you grate the nutmeg using a microplane, it should have a strong, distinctive odor you can smell from a couple feet away. If it doesn't, it's lost its flavor, throw it away and buy new  Q: Does nutmeg come with a good-before date? A: I've never seen nutmegs get moldy before, and I live somewhere with 80% humidity. It would have to be stored in some very poor conditions to mold  Q: How long can nutmeg stay good? <sep> FOLLOWUP_Q: Is there a way to 'see' (observe) how old the nutmeg is?", "output": "No", "explanation": "There is no text in the paragraph which supports the how old the nutmeg is. Hence it is not answerable."}], "Negative Examples": [{"input": "CONTEXT: Best-before dates aren't the same as use-by dates. Whilst you shouldn't consume a product after it's use-by date, best-before dates are more about quality than safety. Basically, after the best-before date, the product may start to deteriorate in terms of flavour, but that doesn't mean you can't still eat it.I'd expect that the salt content of Vegemite would keep it sound for a long time. I've certainly had half-eaten jars of Marmite (sorry, I'm a Marmite guy, not Vegemite) kicking around in the pantry for way longer than they ought, and they've been just fine. Butter and breadcrumbs from the knife may well develop mould if they're left in the jar for a while, but that would normally just be on the surface and easily removed. Much better to remove crumbs before they get to that stage - or, easier, just use a clean knife. <sep> Q: Is Vegemite good beyond expiry date? A: I'd expect that the salt content of Vegemite would keep it sound for a long time  <sep> FOLLOWUP_Q: How do we know it's gone bad?", "output": "Yes", "explanation": "There is no mention of the method to know whether Vegemite has gone bad or not. Hence the question is not answerable."}, {"input": "CONTEXT: In Ireland boiled or glazed ham is a staple. Traditionally it's had with cut up cabbage (ideally you would cook the cabbage in the same water the ham was boiled in as this gives it lovely flavour) but you could just cut it up and pan fry it with a little butter. Normally it would be served with boiled floury potatoes. Traditionally (in Ireland) you wouldn't have a sauce with it but a parsely sauce (as stated in the other reply would be lovely) or simply serve with some strong mustard or a brown sharp sauce such as HP. You could also shred the ham and serve it with noodles in a hot broth with some shredded cabbage and other vegetables.The ham is going to be centre of attention - salty, rich with a sweetness. The cabbage and potato are happy bedfellows as the cabbage cuts through the saltyness/sweetness. You don't want strong flavours competing with the ham and neither cabbage or potato will. <sep> Q: Where can I get boiled and glazed ham as a staple? A: Ireland. <sep> FOLLOWUP_Q: What other vegetables can be used along with cabbages?", "output": "No", "explanation": "In the passage it is mentioned that potatoes can be boiled along with the cabbages. Hence answer is present in the passage."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Nutrition", "Dialogue", "Food"], "Instance": {"id": "task1439-7d88f45c6eff4aea9353875c972cfd7c", "input": "CONTEXT: I'm afraid you interpret the tables wrong. You aren't destroying calories, you are adding water (=0 cal) to the dry rice. As the rice absorbs the water, you are in fact measuring rice + water for cooked rice.This is true for calorie tables that measure by volume (like here) and by weight.If you are cooking your rice by boiling and straining, you are effectively losing a few calories due to the starch that gets drained with the water, but that's not what you asked here.  <sep>  Q: How to maintain the calories in rice (which were present in it in its raw form) after cooking it? A: f you are cooking your rice by boiling and straining, you are effectively losing a few calories due to the starch that gets drained with the water  <sep> FOLLOWUP_Q: What could I add to the rice for flavor?", "output": ["No"]}, "Instance License": ["CC BY-SA 4.0"], "prediction": "Yes"}
+{"id": "task1439-cd5dbea0197d4b8b96c4c99e96c9ecec", "Task": "task1439_doqa_cooking_isanswerable", "Contributors": "['Kuntal Kumar Pal']", "Source": ["doqa"], "URL": ["http://www.ixa.eus/node/12931"], "Categories": ["Answerability Classification"], "Reasoning": ["Reasoning on Social Interactions"], "Definition": ["Given a paragraph about cooking, and a set of conversational questions and answers about the paragraph, say whether the passage contains sufficient information to answer the follow-up question. Say Yes if it is answerable; otherwise, say No. The paragraph has the prefix 'CONTEXT:'. Each conversation question has a prefix `Q:` followed by the answer prefix `A:`, and the follow-up question has a prefix `FOLLOWUP_Q:`."], "Positive Examples": [{"input": "CONTEXT: Duck feet will render plenty of gelatin because of the amount of cartilage, same as chicken feet. Any bird's feet are a good choice.The method for making stock is pretty much the same no matter what you put into it, so yes, you can follow your favourite recipe for chicken stock and substitute duck feet. The only thing to keep in mind is that duck feet, like any other duck parts, are substantially more fatty than their chicken equivalents, so assuming you want a clear or mostly-clear stock, you'll have to spend a lot of time skimming.Alternatively you can clean the feet and other bones by boiling them in plain water for 5-10 minutes, then dumping it all out and starting over - which is what your linked recipe suggests. I don't usually do this for brown stocks because you lose a lot of flavour, but if you're starting from raw then it won't make much difference and it's an easy/lazy way to get rid of a lot of the fat at once. <sep> Q: Can I use duck feet to make duck stock A: The method for making stock is pretty much the same no matter what you put into it, so yes, you can follow your favourite recipe for chicken stock and substitute duck feet  Q: Does it add the same flavor and mouth feel? A: The only thing to keep in mind is that duck feet, like any other duck parts, are substantially more fatty than their chicken equivalents  <sep> FOLLOWUP_Q: How does this change things?", "output": "Yes", "explanation": "The question asks about how the stock can be less fatty or mostly clear. This can be infered from the previous conversation. The answer is written in the passage that if mostly clear stock is needed then one has spend a lot of time skimming."}, {"input": "CONTEXT: Simple: grate it. If you grate the nutmeg using a microplane, it should have a strong, distinctive odor you can smell from a couple feet away. If it doesn't, it's lost its flavor, throw it away and buy new. It's fairly likely you're going to end up replacing it. I've never seen nutmegs get moldy before, and I live somewhere with 80% humidity. It would have to be stored in some very poor conditions to mold. <sep>  Q: How to distinguish nutmeg freshness? A: If you grate the nutmeg using a microplane, it should have a strong, distinctive odor you can smell from a couple feet away. If it doesn't, it's lost its flavor, throw it away and buy new  Q: Does nutmeg come with a good-before date? A: I've never seen nutmegs get moldy before, and I live somewhere with 80% humidity. It would have to be stored in some very poor conditions to mold  Q: How long can nutmeg stay good? <sep> FOLLOWUP_Q: Is there a way to 'see' (observe) how old the nutmeg is?", "output": "No", "explanation": "There is no text in the paragraph which supports the how old the nutmeg is. Hence it is not answerable."}], "Negative Examples": [{"input": "CONTEXT: Best-before dates aren't the same as use-by dates. Whilst you shouldn't consume a product after it's use-by date, best-before dates are more about quality than safety. Basically, after the best-before date, the product may start to deteriorate in terms of flavour, but that doesn't mean you can't still eat it.I'd expect that the salt content of Vegemite would keep it sound for a long time. I've certainly had half-eaten jars of Marmite (sorry, I'm a Marmite guy, not Vegemite) kicking around in the pantry for way longer than they ought, and they've been just fine. Butter and breadcrumbs from the knife may well develop mould if they're left in the jar for a while, but that would normally just be on the surface and easily removed. Much better to remove crumbs before they get to that stage - or, easier, just use a clean knife. <sep> Q: Is Vegemite good beyond expiry date? A: I'd expect that the salt content of Vegemite would keep it sound for a long time  <sep> FOLLOWUP_Q: How do we know it's gone bad?", "output": "Yes", "explanation": "There is no mention of the method to know whether Vegemite has gone bad or not. Hence the question is not answerable."}, {"input": "CONTEXT: In Ireland boiled or glazed ham is a staple. Traditionally it's had with cut up cabbage (ideally you would cook the cabbage in the same water the ham was boiled in as this gives it lovely flavour) but you could just cut it up and pan fry it with a little butter. Normally it would be served with boiled floury potatoes. Traditionally (in Ireland) you wouldn't have a sauce with it but a parsely sauce (as stated in the other reply would be lovely) or simply serve with some strong mustard or a brown sharp sauce such as HP. You could also shred the ham and serve it with noodles in a hot broth with some shredded cabbage and other vegetables.The ham is going to be centre of attention - salty, rich with a sweetness. The cabbage and potato are happy bedfellows as the cabbage cuts through the saltyness/sweetness. You don't want strong flavours competing with the ham and neither cabbage or potato will. <sep> Q: Where can I get boiled and glazed ham as a staple? A: Ireland. <sep> FOLLOWUP_Q: What other vegetables can be used along with cabbages?", "output": "No", "explanation": "In the passage it is mentioned that potatoes can be boiled along with the cabbages. Hence answer is present in the passage."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Nutrition", "Dialogue", "Food"], "Instance": {"id": "task1439-cd5dbea0197d4b8b96c4c99e96c9ecec", "input": "CONTEXT: Alton Brown recommends brining pork chops in a salt water solution in one of his Good Eats episodes. I have been brining them before I cook them ever since I saw that and think it makes them juicier.I brine them for a couple hours at most and then just cook them. Never tried the drying in the refrigerator.  <sep>  Q: I want to prepare pork chops by salting them, putting them in a brine, and drying them, but how should I go about this? A: Alton Brown recommends brining pork chops in a salt water solution in one of his Good Eats episodes  Q: Do I still have to cook the meat after all that, or is it ready to eat? A: I have been brining them before I cook them ever since I saw that and think it makes them juicier  <sep> FOLLOWUP_Q: Will the brine and/or salt cause issues of bone rot?", "output": ["Yes"]}, "Instance License": ["CC BY-SA 4.0"], "prediction": "No"}
+{"id": "task1439-27b5b8f40b0e40aa8f7e6b791bb114ec", "Task": "task1439_doqa_cooking_isanswerable", "Contributors": "['Kuntal Kumar Pal']", "Source": ["doqa"], "URL": ["http://www.ixa.eus/node/12931"], "Categories": ["Answerability Classification"], "Reasoning": ["Reasoning on Social Interactions"], "Definition": ["Given a paragraph about cooking, and a set of conversational questions and answers about the paragraph, say whether the passage contains sufficient information to answer the follow-up question. Say Yes if it is answerable; otherwise, say No. The paragraph has the prefix 'CONTEXT:'. Each conversation question has a prefix `Q:` followed by the answer prefix `A:`, and the follow-up question has a prefix `FOLLOWUP_Q:`."], "Positive Examples": [{"input": "CONTEXT: Duck feet will render plenty of gelatin because of the amount of cartilage, same as chicken feet. Any bird's feet are a good choice.The method for making stock is pretty much the same no matter what you put into it, so yes, you can follow your favourite recipe for chicken stock and substitute duck feet. The only thing to keep in mind is that duck feet, like any other duck parts, are substantially more fatty than their chicken equivalents, so assuming you want a clear or mostly-clear stock, you'll have to spend a lot of time skimming.Alternatively you can clean the feet and other bones by boiling them in plain water for 5-10 minutes, then dumping it all out and starting over - which is what your linked recipe suggests. I don't usually do this for brown stocks because you lose a lot of flavour, but if you're starting from raw then it won't make much difference and it's an easy/lazy way to get rid of a lot of the fat at once. <sep> Q: Can I use duck feet to make duck stock A: The method for making stock is pretty much the same no matter what you put into it, so yes, you can follow your favourite recipe for chicken stock and substitute duck feet  Q: Does it add the same flavor and mouth feel? A: The only thing to keep in mind is that duck feet, like any other duck parts, are substantially more fatty than their chicken equivalents  <sep> FOLLOWUP_Q: How does this change things?", "output": "Yes", "explanation": "The question asks about how the stock can be less fatty or mostly clear. This can be infered from the previous conversation. The answer is written in the passage that if mostly clear stock is needed then one has spend a lot of time skimming."}, {"input": "CONTEXT: Simple: grate it. If you grate the nutmeg using a microplane, it should have a strong, distinctive odor you can smell from a couple feet away. If it doesn't, it's lost its flavor, throw it away and buy new. It's fairly likely you're going to end up replacing it. I've never seen nutmegs get moldy before, and I live somewhere with 80% humidity. It would have to be stored in some very poor conditions to mold. <sep>  Q: How to distinguish nutmeg freshness? A: If you grate the nutmeg using a microplane, it should have a strong, distinctive odor you can smell from a couple feet away. If it doesn't, it's lost its flavor, throw it away and buy new  Q: Does nutmeg come with a good-before date? A: I've never seen nutmegs get moldy before, and I live somewhere with 80% humidity. It would have to be stored in some very poor conditions to mold  Q: How long can nutmeg stay good? <sep> FOLLOWUP_Q: Is there a way to 'see' (observe) how old the nutmeg is?", "output": "No", "explanation": "There is no text in the paragraph which supports the how old the nutmeg is. Hence it is not answerable."}], "Negative Examples": [{"input": "CONTEXT: Best-before dates aren't the same as use-by dates. Whilst you shouldn't consume a product after it's use-by date, best-before dates are more about quality than safety. Basically, after the best-before date, the product may start to deteriorate in terms of flavour, but that doesn't mean you can't still eat it.I'd expect that the salt content of Vegemite would keep it sound for a long time. I've certainly had half-eaten jars of Marmite (sorry, I'm a Marmite guy, not Vegemite) kicking around in the pantry for way longer than they ought, and they've been just fine. Butter and breadcrumbs from the knife may well develop mould if they're left in the jar for a while, but that would normally just be on the surface and easily removed. Much better to remove crumbs before they get to that stage - or, easier, just use a clean knife. <sep> Q: Is Vegemite good beyond expiry date? A: I'd expect that the salt content of Vegemite would keep it sound for a long time  <sep> FOLLOWUP_Q: How do we know it's gone bad?", "output": "Yes", "explanation": "There is no mention of the method to know whether Vegemite has gone bad or not. Hence the question is not answerable."}, {"input": "CONTEXT: In Ireland boiled or glazed ham is a staple. Traditionally it's had with cut up cabbage (ideally you would cook the cabbage in the same water the ham was boiled in as this gives it lovely flavour) but you could just cut it up and pan fry it with a little butter. Normally it would be served with boiled floury potatoes. Traditionally (in Ireland) you wouldn't have a sauce with it but a parsely sauce (as stated in the other reply would be lovely) or simply serve with some strong mustard or a brown sharp sauce such as HP. You could also shred the ham and serve it with noodles in a hot broth with some shredded cabbage and other vegetables.The ham is going to be centre of attention - salty, rich with a sweetness. The cabbage and potato are happy bedfellows as the cabbage cuts through the saltyness/sweetness. You don't want strong flavours competing with the ham and neither cabbage or potato will. <sep> Q: Where can I get boiled and glazed ham as a staple? A: Ireland. <sep> FOLLOWUP_Q: What other vegetables can be used along with cabbages?", "output": "No", "explanation": "In the passage it is mentioned that potatoes can be boiled along with the cabbages. Hence answer is present in the passage."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Nutrition", "Dialogue", "Food"], "Instance": {"id": "task1439-27b5b8f40b0e40aa8f7e6b791bb114ec", "input": "CONTEXT: I'm sorry to say this, but I think prevention is the best answer. Once you're vegetables freeze things happen at the cellular level that changes the nature of the vegetables. For example, ice crystals pierce cell walls which destroys some of the structure, which is responsible for the crispness and crunch of the vegetable. I don't think there is really a way to \"fix\" this, once it happens.That said, cooking does something similar to vegetables. Cooking destroys cell walls, which is why cooked carrots are so much softer than raw carrots. I would think that vegetables that stand up to cooking would survive freezing the best (such as your mushrooms). On the other hand, somthing like lettuce is a lost cause, once frozen.  <sep>  Q: How do i recover vegetables that get \"refrigerator crisper chill\"? A: I don't think there is really a way to \"fix\" this, once it happens  <sep> FOLLOWUP_Q: Can I use them for things like stew?", "output": ["Yes"]}, "Instance License": ["CC BY-SA 4.0"], "prediction": "Yes"}
+{"id": "task1439-e4d8c81eb5824dab9cd19f9a17bb8e45", "Task": "task1439_doqa_cooking_isanswerable", "Contributors": "['Kuntal Kumar Pal']", "Source": ["doqa"], "URL": ["http://www.ixa.eus/node/12931"], "Categories": ["Answerability Classification"], "Reasoning": ["Reasoning on Social Interactions"], "Definition": ["Given a paragraph about cooking, and a set of conversational questions and answers about the paragraph, say whether the passage contains sufficient information to answer the follow-up question. Say Yes if it is answerable; otherwise, say No. The paragraph has the prefix 'CONTEXT:'. Each conversation question has a prefix `Q:` followed by the answer prefix `A:`, and the follow-up question has a prefix `FOLLOWUP_Q:`."], "Positive Examples": [{"input": "CONTEXT: Duck feet will render plenty of gelatin because of the amount of cartilage, same as chicken feet. Any bird's feet are a good choice.The method for making stock is pretty much the same no matter what you put into it, so yes, you can follow your favourite recipe for chicken stock and substitute duck feet. The only thing to keep in mind is that duck feet, like any other duck parts, are substantially more fatty than their chicken equivalents, so assuming you want a clear or mostly-clear stock, you'll have to spend a lot of time skimming.Alternatively you can clean the feet and other bones by boiling them in plain water for 5-10 minutes, then dumping it all out and starting over - which is what your linked recipe suggests. I don't usually do this for brown stocks because you lose a lot of flavour, but if you're starting from raw then it won't make much difference and it's an easy/lazy way to get rid of a lot of the fat at once. <sep> Q: Can I use duck feet to make duck stock A: The method for making stock is pretty much the same no matter what you put into it, so yes, you can follow your favourite recipe for chicken stock and substitute duck feet  Q: Does it add the same flavor and mouth feel? A: The only thing to keep in mind is that duck feet, like any other duck parts, are substantially more fatty than their chicken equivalents  <sep> FOLLOWUP_Q: How does this change things?", "output": "Yes", "explanation": "The question asks about how the stock can be less fatty or mostly clear. This can be infered from the previous conversation. The answer is written in the passage that if mostly clear stock is needed then one has spend a lot of time skimming."}, {"input": "CONTEXT: Simple: grate it. If you grate the nutmeg using a microplane, it should have a strong, distinctive odor you can smell from a couple feet away. If it doesn't, it's lost its flavor, throw it away and buy new. It's fairly likely you're going to end up replacing it. I've never seen nutmegs get moldy before, and I live somewhere with 80% humidity. It would have to be stored in some very poor conditions to mold. <sep>  Q: How to distinguish nutmeg freshness? A: If you grate the nutmeg using a microplane, it should have a strong, distinctive odor you can smell from a couple feet away. If it doesn't, it's lost its flavor, throw it away and buy new  Q: Does nutmeg come with a good-before date? A: I've never seen nutmegs get moldy before, and I live somewhere with 80% humidity. It would have to be stored in some very poor conditions to mold  Q: How long can nutmeg stay good? <sep> FOLLOWUP_Q: Is there a way to 'see' (observe) how old the nutmeg is?", "output": "No", "explanation": "There is no text in the paragraph which supports the how old the nutmeg is. Hence it is not answerable."}], "Negative Examples": [{"input": "CONTEXT: Best-before dates aren't the same as use-by dates. Whilst you shouldn't consume a product after it's use-by date, best-before dates are more about quality than safety. Basically, after the best-before date, the product may start to deteriorate in terms of flavour, but that doesn't mean you can't still eat it.I'd expect that the salt content of Vegemite would keep it sound for a long time. I've certainly had half-eaten jars of Marmite (sorry, I'm a Marmite guy, not Vegemite) kicking around in the pantry for way longer than they ought, and they've been just fine. Butter and breadcrumbs from the knife may well develop mould if they're left in the jar for a while, but that would normally just be on the surface and easily removed. Much better to remove crumbs before they get to that stage - or, easier, just use a clean knife. <sep> Q: Is Vegemite good beyond expiry date? A: I'd expect that the salt content of Vegemite would keep it sound for a long time  <sep> FOLLOWUP_Q: How do we know it's gone bad?", "output": "Yes", "explanation": "There is no mention of the method to know whether Vegemite has gone bad or not. Hence the question is not answerable."}, {"input": "CONTEXT: In Ireland boiled or glazed ham is a staple. Traditionally it's had with cut up cabbage (ideally you would cook the cabbage in the same water the ham was boiled in as this gives it lovely flavour) but you could just cut it up and pan fry it with a little butter. Normally it would be served with boiled floury potatoes. Traditionally (in Ireland) you wouldn't have a sauce with it but a parsely sauce (as stated in the other reply would be lovely) or simply serve with some strong mustard or a brown sharp sauce such as HP. You could also shred the ham and serve it with noodles in a hot broth with some shredded cabbage and other vegetables.The ham is going to be centre of attention - salty, rich with a sweetness. The cabbage and potato are happy bedfellows as the cabbage cuts through the saltyness/sweetness. You don't want strong flavours competing with the ham and neither cabbage or potato will. <sep> Q: Where can I get boiled and glazed ham as a staple? A: Ireland. <sep> FOLLOWUP_Q: What other vegetables can be used along with cabbages?", "output": "No", "explanation": "In the passage it is mentioned that potatoes can be boiled along with the cabbages. Hence answer is present in the passage."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Nutrition", "Dialogue", "Food"], "Instance": {"id": "task1439-e4d8c81eb5824dab9cd19f9a17bb8e45", "input": "CONTEXT: I would keep the one that you are eating the next day out. I would then freeze the rest of them. If you like them warm, you could freeze them wrapped in foil. Before eating pop them in a toaster oven until gently warmed through. If not I'd freeze individually until solid then put in a bag to prevent your frozen bagels from sticking together, then thaw overnight (if eating in the morning) or in the morning (if eating for a mid-day meal) to eat.  <sep>  Q: what is the best way to store bagels? A: I would keep the one that you are eating the next day out. I would then freeze the rest of them  Q: they are the best while fresh and im not going to make them daily. how long do they stay good while frozen? A: If you like them warm, you could freeze them wrapped in foil. Before eating pop them in a toaster oven until gently warmed through  <sep> FOLLOWUP_Q: i wonder if they would last a couple weeks while frozen?", "output": ["No"]}, "Instance License": ["CC BY-SA 4.0"], "prediction": "Yes"}
+{"id": "task1439-120793f6867a4f2bbafc6a498ae71407", "Task": "task1439_doqa_cooking_isanswerable", "Contributors": "['Kuntal Kumar Pal']", "Source": ["doqa"], "URL": ["http://www.ixa.eus/node/12931"], "Categories": ["Answerability Classification"], "Reasoning": ["Reasoning on Social Interactions"], "Definition": ["Given a paragraph about cooking, and a set of conversational questions and answers about the paragraph, say whether the passage contains sufficient information to answer the follow-up question. Say Yes if it is answerable; otherwise, say No. The paragraph has the prefix 'CONTEXT:'. Each conversation question has a prefix `Q:` followed by the answer prefix `A:`, and the follow-up question has a prefix `FOLLOWUP_Q:`."], "Positive Examples": [{"input": "CONTEXT: Duck feet will render plenty of gelatin because of the amount of cartilage, same as chicken feet. Any bird's feet are a good choice.The method for making stock is pretty much the same no matter what you put into it, so yes, you can follow your favourite recipe for chicken stock and substitute duck feet. The only thing to keep in mind is that duck feet, like any other duck parts, are substantially more fatty than their chicken equivalents, so assuming you want a clear or mostly-clear stock, you'll have to spend a lot of time skimming.Alternatively you can clean the feet and other bones by boiling them in plain water for 5-10 minutes, then dumping it all out and starting over - which is what your linked recipe suggests. I don't usually do this for brown stocks because you lose a lot of flavour, but if you're starting from raw then it won't make much difference and it's an easy/lazy way to get rid of a lot of the fat at once. <sep> Q: Can I use duck feet to make duck stock A: The method for making stock is pretty much the same no matter what you put into it, so yes, you can follow your favourite recipe for chicken stock and substitute duck feet  Q: Does it add the same flavor and mouth feel? A: The only thing to keep in mind is that duck feet, like any other duck parts, are substantially more fatty than their chicken equivalents  <sep> FOLLOWUP_Q: How does this change things?", "output": "Yes", "explanation": "The question asks about how the stock can be less fatty or mostly clear. This can be infered from the previous conversation. The answer is written in the passage that if mostly clear stock is needed then one has spend a lot of time skimming."}, {"input": "CONTEXT: Simple: grate it. If you grate the nutmeg using a microplane, it should have a strong, distinctive odor you can smell from a couple feet away. If it doesn't, it's lost its flavor, throw it away and buy new. It's fairly likely you're going to end up replacing it. I've never seen nutmegs get moldy before, and I live somewhere with 80% humidity. It would have to be stored in some very poor conditions to mold. <sep>  Q: How to distinguish nutmeg freshness? A: If you grate the nutmeg using a microplane, it should have a strong, distinctive odor you can smell from a couple feet away. If it doesn't, it's lost its flavor, throw it away and buy new  Q: Does nutmeg come with a good-before date? A: I've never seen nutmegs get moldy before, and I live somewhere with 80% humidity. It would have to be stored in some very poor conditions to mold  Q: How long can nutmeg stay good? <sep> FOLLOWUP_Q: Is there a way to 'see' (observe) how old the nutmeg is?", "output": "No", "explanation": "There is no text in the paragraph which supports the how old the nutmeg is. Hence it is not answerable."}], "Negative Examples": [{"input": "CONTEXT: Best-before dates aren't the same as use-by dates. Whilst you shouldn't consume a product after it's use-by date, best-before dates are more about quality than safety. Basically, after the best-before date, the product may start to deteriorate in terms of flavour, but that doesn't mean you can't still eat it.I'd expect that the salt content of Vegemite would keep it sound for a long time. I've certainly had half-eaten jars of Marmite (sorry, I'm a Marmite guy, not Vegemite) kicking around in the pantry for way longer than they ought, and they've been just fine. Butter and breadcrumbs from the knife may well develop mould if they're left in the jar for a while, but that would normally just be on the surface and easily removed. Much better to remove crumbs before they get to that stage - or, easier, just use a clean knife. <sep> Q: Is Vegemite good beyond expiry date? A: I'd expect that the salt content of Vegemite would keep it sound for a long time  <sep> FOLLOWUP_Q: How do we know it's gone bad?", "output": "Yes", "explanation": "There is no mention of the method to know whether Vegemite has gone bad or not. Hence the question is not answerable."}, {"input": "CONTEXT: In Ireland boiled or glazed ham is a staple. Traditionally it's had with cut up cabbage (ideally you would cook the cabbage in the same water the ham was boiled in as this gives it lovely flavour) but you could just cut it up and pan fry it with a little butter. Normally it would be served with boiled floury potatoes. Traditionally (in Ireland) you wouldn't have a sauce with it but a parsely sauce (as stated in the other reply would be lovely) or simply serve with some strong mustard or a brown sharp sauce such as HP. You could also shred the ham and serve it with noodles in a hot broth with some shredded cabbage and other vegetables.The ham is going to be centre of attention - salty, rich with a sweetness. The cabbage and potato are happy bedfellows as the cabbage cuts through the saltyness/sweetness. You don't want strong flavours competing with the ham and neither cabbage or potato will. <sep> Q: Where can I get boiled and glazed ham as a staple? A: Ireland. <sep> FOLLOWUP_Q: What other vegetables can be used along with cabbages?", "output": "No", "explanation": "In the passage it is mentioned that potatoes can be boiled along with the cabbages. Hence answer is present in the passage."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Nutrition", "Dialogue", "Food"], "Instance": {"id": "task1439-120793f6867a4f2bbafc6a498ae71407", "input": "CONTEXT: Almost any normal sorbet recipe will contain a decent amount of sugar, and strawberries are no exception. I'd guess probably 1/2-2/3 cup per pound of strawberries. Use a substitute if you have an aversion - honey, agave, raw cane sugar, whatever you prefer. (Of course, anything liquid is going to contain some water, and cause a bit of ice, but it's still doable.) A sorbet without any extra sugar, even when frozen normally in an ice cream maker, is going to end up with a very icy texture, which will probably keep you from experiencing the flavor as much. The sugar helps soften it.The other common way to soften a sorbet is alcohol. Ros\u00c3\u00a9 wine (thank you, David Lebovitz) works quite well in a strawberry sorbet. Vodka can be your go-to liquor for any impromptu sorbet with other fruits, since it'll add alcohol without any flavors that clash. Beyond that, either look for recipes, or look for mixed drinks containing the fruit you're using.You might also be having problems simply because your strawberries aren't that great. Did you freeze them, or were they storebought? If you bought the strawberries yourself, you'd know they were decent before freezing, while not all storebought frozen fruit is as flavorful.Finally, it's possible that your frozen strawberries collected some extra water in the form of frost, which then makes your sorbet icier. If there are obvious big chunks you could scrape them off.  <sep>  Q: How can I improve flavor of Sorbet made in Magic Bullet? A: Use a substitute if you have an aversion - honey, agave, raw cane sugar, whatever you prefer  <sep> FOLLOWUP_Q: Can I do a strawberry sorbet?", "output": ["Yes"]}, "Instance License": ["CC BY-SA 4.0"], "prediction": "Yes"}
+{"id": "task645-6d0b46154c2241888d059d5017bb4fde", "Task": "task645_summarization", "Contributors": "['khushal chandresh modi']", "Source": ["wiki_auto_all_data"], "URL": ["https://www.dropbox.com/sh/ohqaw41v48c7e5p/aadb6_qwcwghvscqg121ck9ma?dl=0"], "Categories": ["Keyword Tagging"], "Reasoning": [], "Definition": ["Generate a topic word for the given sentence. A topic word is usually the name of a person, place, animal, concept or object the sentence is focusing on."], "Positive Examples": [{"input": "fear of needles (medically known as belomophobia) is a term used to describe a large fear (phobia) of medical procedures involving needles.", "output": "fear of needles", "explanation": "This statement is talking about the fear of needles, so 'fear of needles' is a correct answer."}, {"input": "the 2015 ping an chinese football association super league (chinese: 2015\u4e2d\u56fd\u5e73\u5b89\u4e2d\u56fd\u8db3\u7403\u534f\u4f1a\u8d85\u7ea7\u8054\u8d5b) was the 12th chinese super league season and was won by guangzhou evergrande taobao.", "output": "2015 chinese super league", "explanation": "Here, the input statement talks about the chinese football association held in 2015, so that is a correct answer."}], "Negative Examples": [{"input": "roaring lion (march 11, 2015 \u2013 august 23, 2019) was an american-bred, british-trained thoroughbred racehorse.", "output": "roaring racehorse", "explanation": "The input statement is talking about the roaring lion."}, {"input": "the maillard reaction is a chemical reaction between an amino acid and a reducing sugar that gives browned food its distinctive flavor.", "output": "chemical reaction", "explanation": "Here the input statement is talking about the maillard reaction and not the general chemical reaction."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Wikipedia"], "Instance": {"id": "task645-6d0b46154c2241888d059d5017bb4fde", "input": "an old master print is a work of art made by a printing process.", "output": ["old master print"]}, "Instance License": ["Unknown"], "prediction": "old master print"}
+{"id": "task645-1d2fe5fa93a6480eb4641fea0db6fb82", "Task": "task645_summarization", "Contributors": "['khushal chandresh modi']", "Source": ["wiki_auto_all_data"], "URL": ["https://www.dropbox.com/sh/ohqaw41v48c7e5p/aadb6_qwcwghvscqg121ck9ma?dl=0"], "Categories": ["Keyword Tagging"], "Reasoning": [], "Definition": ["Generate a topic word for the given sentence. A topic word is usually the name of a person, place, animal, concept or object the sentence is focusing on."], "Positive Examples": [{"input": "fear of needles (medically known as belomophobia) is a term used to describe a large fear (phobia) of medical procedures involving needles.", "output": "fear of needles", "explanation": "This statement is talking about the fear of needles, so 'fear of needles' is a correct answer."}, {"input": "the 2015 ping an chinese football association super league (chinese: 2015\u4e2d\u56fd\u5e73\u5b89\u4e2d\u56fd\u8db3\u7403\u534f\u4f1a\u8d85\u7ea7\u8054\u8d5b) was the 12th chinese super league season and was won by guangzhou evergrande taobao.", "output": "2015 chinese super league", "explanation": "Here, the input statement talks about the chinese football association held in 2015, so that is a correct answer."}], "Negative Examples": [{"input": "roaring lion (march 11, 2015 \u2013 august 23, 2019) was an american-bred, british-trained thoroughbred racehorse.", "output": "roaring racehorse", "explanation": "The input statement is talking about the roaring lion."}, {"input": "the maillard reaction is a chemical reaction between an amino acid and a reducing sugar that gives browned food its distinctive flavor.", "output": "chemical reaction", "explanation": "Here the input statement is talking about the maillard reaction and not the general chemical reaction."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Wikipedia"], "Instance": {"id": "task645-1d2fe5fa93a6480eb4641fea0db6fb82", "input": "taipei metro is a metro system in taipei, taiwan.", "output": ["taipei metro"]}, "Instance License": ["Unknown"], "prediction": "taipei metro"}
+{"id": "task645-9ed709f11b11458c9263f493625e5c69", "Task": "task645_summarization", "Contributors": "['khushal chandresh modi']", "Source": ["wiki_auto_all_data"], "URL": ["https://www.dropbox.com/sh/ohqaw41v48c7e5p/aadb6_qwcwghvscqg121ck9ma?dl=0"], "Categories": ["Keyword Tagging"], "Reasoning": [], "Definition": ["Generate a topic word for the given sentence. A topic word is usually the name of a person, place, animal, concept or object the sentence is focusing on."], "Positive Examples": [{"input": "fear of needles (medically known as belomophobia) is a term used to describe a large fear (phobia) of medical procedures involving needles.", "output": "fear of needles", "explanation": "This statement is talking about the fear of needles, so 'fear of needles' is a correct answer."}, {"input": "the 2015 ping an chinese football association super league (chinese: 2015\u4e2d\u56fd\u5e73\u5b89\u4e2d\u56fd\u8db3\u7403\u534f\u4f1a\u8d85\u7ea7\u8054\u8d5b) was the 12th chinese super league season and was won by guangzhou evergrande taobao.", "output": "2015 chinese super league", "explanation": "Here, the input statement talks about the chinese football association held in 2015, so that is a correct answer."}], "Negative Examples": [{"input": "roaring lion (march 11, 2015 \u2013 august 23, 2019) was an american-bred, british-trained thoroughbred racehorse.", "output": "roaring racehorse", "explanation": "The input statement is talking about the roaring lion."}, {"input": "the maillard reaction is a chemical reaction between an amino acid and a reducing sugar that gives browned food its distinctive flavor.", "output": "chemical reaction", "explanation": "Here the input statement is talking about the maillard reaction and not the general chemical reaction."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Wikipedia"], "Instance": {"id": "task645-9ed709f11b11458c9263f493625e5c69", "input": "adam ries was a mathematician from bad staffelstein in bavaria.", "output": ["adam ries"]}, "Instance License": ["Unknown"], "prediction": "adam ries"}
+{"id": "task645-59c09321769541bbbf4d4e155cb2d94b", "Task": "task645_summarization", "Contributors": "['khushal chandresh modi']", "Source": ["wiki_auto_all_data"], "URL": ["https://www.dropbox.com/sh/ohqaw41v48c7e5p/aadb6_qwcwghvscqg121ck9ma?dl=0"], "Categories": ["Keyword Tagging"], "Reasoning": [], "Definition": ["Generate a topic word for the given sentence. A topic word is usually the name of a person, place, animal, concept or object the sentence is focusing on."], "Positive Examples": [{"input": "fear of needles (medically known as belomophobia) is a term used to describe a large fear (phobia) of medical procedures involving needles.", "output": "fear of needles", "explanation": "This statement is talking about the fear of needles, so 'fear of needles' is a correct answer."}, {"input": "the 2015 ping an chinese football association super league (chinese: 2015\u4e2d\u56fd\u5e73\u5b89\u4e2d\u56fd\u8db3\u7403\u534f\u4f1a\u8d85\u7ea7\u8054\u8d5b) was the 12th chinese super league season and was won by guangzhou evergrande taobao.", "output": "2015 chinese super league", "explanation": "Here, the input statement talks about the chinese football association held in 2015, so that is a correct answer."}], "Negative Examples": [{"input": "roaring lion (march 11, 2015 \u2013 august 23, 2019) was an american-bred, british-trained thoroughbred racehorse.", "output": "roaring racehorse", "explanation": "The input statement is talking about the roaring lion."}, {"input": "the maillard reaction is a chemical reaction between an amino acid and a reducing sugar that gives browned food its distinctive flavor.", "output": "chemical reaction", "explanation": "Here the input statement is talking about the maillard reaction and not the general chemical reaction."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Wikipedia"], "Instance": {"id": "task645-59c09321769541bbbf4d4e155cb2d94b", "input": "bob fitzgerald is a sports announcer.", "output": ["bob fitzgerald"]}, "Instance License": ["Unknown"], "prediction": "bob fitzgerald"}
+{"id": "task645-7f905d86685043679fdfbc5b4ebe536e", "Task": "task645_summarization", "Contributors": "['khushal chandresh modi']", "Source": ["wiki_auto_all_data"], "URL": ["https://www.dropbox.com/sh/ohqaw41v48c7e5p/aadb6_qwcwghvscqg121ck9ma?dl=0"], "Categories": ["Keyword Tagging"], "Reasoning": [], "Definition": ["Generate a topic word for the given sentence. A topic word is usually the name of a person, place, animal, concept or object the sentence is focusing on."], "Positive Examples": [{"input": "fear of needles (medically known as belomophobia) is a term used to describe a large fear (phobia) of medical procedures involving needles.", "output": "fear of needles", "explanation": "This statement is talking about the fear of needles, so 'fear of needles' is a correct answer."}, {"input": "the 2015 ping an chinese football association super league (chinese: 2015\u4e2d\u56fd\u5e73\u5b89\u4e2d\u56fd\u8db3\u7403\u534f\u4f1a\u8d85\u7ea7\u8054\u8d5b) was the 12th chinese super league season and was won by guangzhou evergrande taobao.", "output": "2015 chinese super league", "explanation": "Here, the input statement talks about the chinese football association held in 2015, so that is a correct answer."}], "Negative Examples": [{"input": "roaring lion (march 11, 2015 \u2013 august 23, 2019) was an american-bred, british-trained thoroughbred racehorse.", "output": "roaring racehorse", "explanation": "The input statement is talking about the roaring lion."}, {"input": "the maillard reaction is a chemical reaction between an amino acid and a reducing sugar that gives browned food its distinctive flavor.", "output": "chemical reaction", "explanation": "Here the input statement is talking about the maillard reaction and not the general chemical reaction."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Wikipedia"], "Instance": {"id": "task645-7f905d86685043679fdfbc5b4ebe536e", "input": "illinois is a state in the united states.", "output": ["illinois"]}, "Instance License": ["Unknown"], "prediction": "illinois"}
+{"id": "task619-fc21ecf77daa4ec7a151afc32b1cca4e", "Task": "task619_ohsumed_abstract_title_generation", "Contributors": "['Saicharan Papani']", "Source": ["ohsumed"], "URL": ["https://huggingface.co/datasets/ohsumed"], "Categories": ["Title Generation"], "Reasoning": [], "Definition": ["Given an abstract of a paper, generate a title for this paper such that conveys the key focus of the paper."], "Positive Examples": [{"input": "Abstract: Some patients converted from ventricular fibrillation to organized rhythms by defibrillation-trained ambulance technicians (EMT-Ds) will refibrillate before hospital arrival. The authors analyzed 271 cases of ventricular fibrillation managed by EMT-Ds working without paramedic back-up. Of 111 patients initially converted to organized rhythms, 19 (17%) refibrillated, 11 (58%) of whom were reconverted to perfusing rhythms, including nine of 11 (82%) who had spontaneous pulses prior to refibrillation. Among patients initially converted to organized rhythms, hospital admission rates were lower for patients who refibrillated than for patients who did not(53% versus 76%, P = NS), although discharge rates were virtually identical (37% and 35%, respectively). Scene-to-hospital transport times were not predictively associated with either the frequency of refibrillation or patient outcome. Defibrillation-trained EMTs can effectively manage refibrillation with additional shocks and are not at a significant disadvantage when paramedic back-up is not available.", "output": "Refibrillation managed by EMT-Ds", "explanation": "The abstract is about refibrillation and it is also mentioned in the abstract that it is managed by EMT-Ds. So it is an apt title."}, {"input": "Abstract: The course of a pregnant patient at term who was acutely exposed to carbon monoxide is described. A review of the fetal-maternal carboxyhemoglobin relationships and the differences in fetal oxyhemoglobin physiology are used to explain the recommendation that pregnant women with carbon monoxide poisoning should receive 100% oxygen therapy for up to five times longer than is otherwise necessary. The role of hyperbaric oxygen therapy is considered.", "output": "Acute carbon monoxide poisoning during pregnancy.", "explanation": "The abstract described a pregant patient who was acutely exposed to carbon monoxide and the difference in fetal physiology is used to explain the recommendation of recieving 100% oxygen therapy for the pregnant women with carbon monoxide poisoning. So 'Acute carbon monoxide poisoning during pregnancy.' is the apt title"}, {"input": "Abstract: Over the last two decades, emergency medical services in the United States have been greatly improved. Organization of prehospital providers of health care has improved the outcome of many patients, particularly the trauma patient and the acute cardiac patient. In Seattle as many as 40% of outside-the-hospital cardiac arrest victims with ventricular fibrillation have been saved when there is rapid delivery of basic life support by first responders followed by advanced life support by paramedics. Although these systems are growing and improving health care, many lack adequate medical control or physician involvement. Emergency medical service systems must have physicians involved in their management to meet their full capabilities. It has become apparent that four factors are critical in determining the ability to resuscitate an individual once a cardiac arrest has occurred: time to starting any of the rescue procedures, use of electrical defibrillation when indicated, use of epinephrine, and adequacy of the technique of basic life support, particularly the ventilation component. To provide defibrillation at the earliest possible time, defibrillation by first responders such as emergency medical technicians appears to be of benefit. With the advent of automatic and semiautomatic defibrillators, first responders and family members may also be able to defibrillate victims. The use of defibrillation by people with less training than paramedics, however, must be approached with caution to ensure that there is adequate medical control and that the individuals who use these devices are properly trained.", "output": "Emergency medical service systems in acute cardiac care.", "explanation": "The abstract described the Emergency medical services in united states, particulary with the acute cardiac patient. So 'Emergency medical service systems in acute cardiac care.' is the apt title"}], "Negative Examples": [{"input": "Abstract: As the use of helicopters for air transport of critically ill patients increases, the availability of monitoring devices for physiological parameters during flight becomes important. It has long been known that arterial PO2 (PaO2) decreases during unsupplemented, non- pressurized flight. In this study, the authors examined the use of the transconjunctival oxygen (cjO2) monitor for assessing the adequacy of arterial oxygenation during helicopter flight in four healthy volunteers. Arterial PaO2 as measured by conventional blood gas analysis was compared with cjO2 at ground level, 5,000 feet, and 10,000 feet altitude. Mean PaO2 dropped significantly from 93.5 to 81.5 to 58.5 mm Hg, respectively (P less than 0.001, analysis of variance with repeated measures). Mean cjO2 also decreased significantly from 63.8 to 52.0 to 34.8 mm Hg, respectively (P less than 0.001, analysis of variance with repeated measures). Within individual subjects, cjO2 was an accurate predictor of PaO2 (P less than 0.001, multiple regression analysis). The relationship between cjO2 and PaO2 was linear with a regression coefficient of 1.147. The authors conclude that the transconjunctival O2 monitor may be useful for monitoring the adequacy of arterial oxygenation during helicopter flight in hemodynamically stable patients. The results of study also support the use of supplemental oxygen in all patients subjected to helicopter transport.", "output": "Nasogastric intubation", "explanation": "The title 'Nasogastric intubation' is completely out of the given abstract. So not an apt title. Title can be with helicopter transportation and transconjunctival oxygen."}, {"input": "Abstract: The course of a pregnant patient at term who was acutely exposed to carbon monoxide is described. A review of the fetal-maternal carboxyhemoglobin relationships and the differences in fetal oxyhemoglobin physiology are used to explain the recommendation that pregnant women with carbon monoxide poisoning should receive 100% oxygen therapy for up to five times longer than is otherwise necessary. The role of hyperbaric oxygen therapy is considered.", "output": "Intraosseous infusion of phenytoin.", "explanation": "The title 'Intraosseous infusion of phenytoin.' is no where related to the abstract or present in the abstract. So, it is not a perfect title. The abstract is about pregnency and carbon monoxide poisoning."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Reviews"], "Instance": {"id": "task619-fc21ecf77daa4ec7a151afc32b1cca4e", "input": "Abstract: To summarize the results: Bilirubin removal by hemoperfusion was successfully performed for the first time on a premature infant. The hemoperfusion caused no adverse effects on the clinical state of the infant. The bilirubin removed in 90 min--13 mg--indicates the existence of a large extravascular pool. Hemoperfusion is suggested for bilirubin removal from newborn babies, reducing the need for blood exchange with bank blood.", "output": ["Bilirubin removal from a jaundiced premature infant by resin hemoperfusion."]}, "Instance License": ["CC BY-NC 4.0"], "prediction": "Hemoperfusion for bilirubin removal in premature infants"}
+{"id": "task619-837bb13ec5384b1699f9798835de295a", "Task": "task619_ohsumed_abstract_title_generation", "Contributors": "['Saicharan Papani']", "Source": ["ohsumed"], "URL": ["https://huggingface.co/datasets/ohsumed"], "Categories": ["Title Generation"], "Reasoning": [], "Definition": ["Given an abstract of a paper, generate a title for this paper such that conveys the key focus of the paper."], "Positive Examples": [{"input": "Abstract: Some patients converted from ventricular fibrillation to organized rhythms by defibrillation-trained ambulance technicians (EMT-Ds) will refibrillate before hospital arrival. The authors analyzed 271 cases of ventricular fibrillation managed by EMT-Ds working without paramedic back-up. Of 111 patients initially converted to organized rhythms, 19 (17%) refibrillated, 11 (58%) of whom were reconverted to perfusing rhythms, including nine of 11 (82%) who had spontaneous pulses prior to refibrillation. Among patients initially converted to organized rhythms, hospital admission rates were lower for patients who refibrillated than for patients who did not(53% versus 76%, P = NS), although discharge rates were virtually identical (37% and 35%, respectively). Scene-to-hospital transport times were not predictively associated with either the frequency of refibrillation or patient outcome. Defibrillation-trained EMTs can effectively manage refibrillation with additional shocks and are not at a significant disadvantage when paramedic back-up is not available.", "output": "Refibrillation managed by EMT-Ds", "explanation": "The abstract is about refibrillation and it is also mentioned in the abstract that it is managed by EMT-Ds. So it is an apt title."}, {"input": "Abstract: The course of a pregnant patient at term who was acutely exposed to carbon monoxide is described. A review of the fetal-maternal carboxyhemoglobin relationships and the differences in fetal oxyhemoglobin physiology are used to explain the recommendation that pregnant women with carbon monoxide poisoning should receive 100% oxygen therapy for up to five times longer than is otherwise necessary. The role of hyperbaric oxygen therapy is considered.", "output": "Acute carbon monoxide poisoning during pregnancy.", "explanation": "The abstract described a pregant patient who was acutely exposed to carbon monoxide and the difference in fetal physiology is used to explain the recommendation of recieving 100% oxygen therapy for the pregnant women with carbon monoxide poisoning. So 'Acute carbon monoxide poisoning during pregnancy.' is the apt title"}, {"input": "Abstract: Over the last two decades, emergency medical services in the United States have been greatly improved. Organization of prehospital providers of health care has improved the outcome of many patients, particularly the trauma patient and the acute cardiac patient. In Seattle as many as 40% of outside-the-hospital cardiac arrest victims with ventricular fibrillation have been saved when there is rapid delivery of basic life support by first responders followed by advanced life support by paramedics. Although these systems are growing and improving health care, many lack adequate medical control or physician involvement. Emergency medical service systems must have physicians involved in their management to meet their full capabilities. It has become apparent that four factors are critical in determining the ability to resuscitate an individual once a cardiac arrest has occurred: time to starting any of the rescue procedures, use of electrical defibrillation when indicated, use of epinephrine, and adequacy of the technique of basic life support, particularly the ventilation component. To provide defibrillation at the earliest possible time, defibrillation by first responders such as emergency medical technicians appears to be of benefit. With the advent of automatic and semiautomatic defibrillators, first responders and family members may also be able to defibrillate victims. The use of defibrillation by people with less training than paramedics, however, must be approached with caution to ensure that there is adequate medical control and that the individuals who use these devices are properly trained.", "output": "Emergency medical service systems in acute cardiac care.", "explanation": "The abstract described the Emergency medical services in united states, particulary with the acute cardiac patient. So 'Emergency medical service systems in acute cardiac care.' is the apt title"}], "Negative Examples": [{"input": "Abstract: As the use of helicopters for air transport of critically ill patients increases, the availability of monitoring devices for physiological parameters during flight becomes important. It has long been known that arterial PO2 (PaO2) decreases during unsupplemented, non- pressurized flight. In this study, the authors examined the use of the transconjunctival oxygen (cjO2) monitor for assessing the adequacy of arterial oxygenation during helicopter flight in four healthy volunteers. Arterial PaO2 as measured by conventional blood gas analysis was compared with cjO2 at ground level, 5,000 feet, and 10,000 feet altitude. Mean PaO2 dropped significantly from 93.5 to 81.5 to 58.5 mm Hg, respectively (P less than 0.001, analysis of variance with repeated measures). Mean cjO2 also decreased significantly from 63.8 to 52.0 to 34.8 mm Hg, respectively (P less than 0.001, analysis of variance with repeated measures). Within individual subjects, cjO2 was an accurate predictor of PaO2 (P less than 0.001, multiple regression analysis). The relationship between cjO2 and PaO2 was linear with a regression coefficient of 1.147. The authors conclude that the transconjunctival O2 monitor may be useful for monitoring the adequacy of arterial oxygenation during helicopter flight in hemodynamically stable patients. The results of study also support the use of supplemental oxygen in all patients subjected to helicopter transport.", "output": "Nasogastric intubation", "explanation": "The title 'Nasogastric intubation' is completely out of the given abstract. So not an apt title. Title can be with helicopter transportation and transconjunctival oxygen."}, {"input": "Abstract: The course of a pregnant patient at term who was acutely exposed to carbon monoxide is described. A review of the fetal-maternal carboxyhemoglobin relationships and the differences in fetal oxyhemoglobin physiology are used to explain the recommendation that pregnant women with carbon monoxide poisoning should receive 100% oxygen therapy for up to five times longer than is otherwise necessary. The role of hyperbaric oxygen therapy is considered.", "output": "Intraosseous infusion of phenytoin.", "explanation": "The title 'Intraosseous infusion of phenytoin.' is no where related to the abstract or present in the abstract. So, it is not a perfect title. The abstract is about pregnency and carbon monoxide poisoning."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Reviews"], "Instance": {"id": "task619-837bb13ec5384b1699f9798835de295a", "input": "Abstract: Labrador keratopathy (LK) is an acquired corneal degeneration thought to be caused by chronic exposure to solar irradiation. Reports so far suggest that it is a progressive or at least a stationary condition. There are no detailed reports on recommended therapy. A prospective clinical study was conducted to show regression of LK following extracapsular cataract extraction. Seventeen black patients (26 eyes) with LK and mature cataracts underwent extracapsular cataract extraction. The severity of the LK was recorded photographically pre- and postoperatively. The follow-up ranged from 6 to fifteen months. Twenty-four eyes (92%) showed regression of the LK. The reduction in exposure to ultraviolet light as a result of aphakic photophobia could be one of the factors which have led to the regression of the LK.", "output": ["Regression of Labrador keratopathy following cataract extraction."]}, "Instance License": ["CC BY-NC 4.0"], "prediction": "LK after extracapsular cataract extraction"}
+{"id": "task619-35b877e8c55c4261b3cace6ed7f45c1f", "Task": "task619_ohsumed_abstract_title_generation", "Contributors": "['Saicharan Papani']", "Source": ["ohsumed"], "URL": ["https://huggingface.co/datasets/ohsumed"], "Categories": ["Title Generation"], "Reasoning": [], "Definition": ["Given an abstract of a paper, generate a title for this paper such that conveys the key focus of the paper."], "Positive Examples": [{"input": "Abstract: Some patients converted from ventricular fibrillation to organized rhythms by defibrillation-trained ambulance technicians (EMT-Ds) will refibrillate before hospital arrival. The authors analyzed 271 cases of ventricular fibrillation managed by EMT-Ds working without paramedic back-up. Of 111 patients initially converted to organized rhythms, 19 (17%) refibrillated, 11 (58%) of whom were reconverted to perfusing rhythms, including nine of 11 (82%) who had spontaneous pulses prior to refibrillation. Among patients initially converted to organized rhythms, hospital admission rates were lower for patients who refibrillated than for patients who did not(53% versus 76%, P = NS), although discharge rates were virtually identical (37% and 35%, respectively). Scene-to-hospital transport times were not predictively associated with either the frequency of refibrillation or patient outcome. Defibrillation-trained EMTs can effectively manage refibrillation with additional shocks and are not at a significant disadvantage when paramedic back-up is not available.", "output": "Refibrillation managed by EMT-Ds", "explanation": "The abstract is about refibrillation and it is also mentioned in the abstract that it is managed by EMT-Ds. So it is an apt title."}, {"input": "Abstract: The course of a pregnant patient at term who was acutely exposed to carbon monoxide is described. A review of the fetal-maternal carboxyhemoglobin relationships and the differences in fetal oxyhemoglobin physiology are used to explain the recommendation that pregnant women with carbon monoxide poisoning should receive 100% oxygen therapy for up to five times longer than is otherwise necessary. The role of hyperbaric oxygen therapy is considered.", "output": "Acute carbon monoxide poisoning during pregnancy.", "explanation": "The abstract described a pregant patient who was acutely exposed to carbon monoxide and the difference in fetal physiology is used to explain the recommendation of recieving 100% oxygen therapy for the pregnant women with carbon monoxide poisoning. So 'Acute carbon monoxide poisoning during pregnancy.' is the apt title"}, {"input": "Abstract: Over the last two decades, emergency medical services in the United States have been greatly improved. Organization of prehospital providers of health care has improved the outcome of many patients, particularly the trauma patient and the acute cardiac patient. In Seattle as many as 40% of outside-the-hospital cardiac arrest victims with ventricular fibrillation have been saved when there is rapid delivery of basic life support by first responders followed by advanced life support by paramedics. Although these systems are growing and improving health care, many lack adequate medical control or physician involvement. Emergency medical service systems must have physicians involved in their management to meet their full capabilities. It has become apparent that four factors are critical in determining the ability to resuscitate an individual once a cardiac arrest has occurred: time to starting any of the rescue procedures, use of electrical defibrillation when indicated, use of epinephrine, and adequacy of the technique of basic life support, particularly the ventilation component. To provide defibrillation at the earliest possible time, defibrillation by first responders such as emergency medical technicians appears to be of benefit. With the advent of automatic and semiautomatic defibrillators, first responders and family members may also be able to defibrillate victims. The use of defibrillation by people with less training than paramedics, however, must be approached with caution to ensure that there is adequate medical control and that the individuals who use these devices are properly trained.", "output": "Emergency medical service systems in acute cardiac care.", "explanation": "The abstract described the Emergency medical services in united states, particulary with the acute cardiac patient. So 'Emergency medical service systems in acute cardiac care.' is the apt title"}], "Negative Examples": [{"input": "Abstract: As the use of helicopters for air transport of critically ill patients increases, the availability of monitoring devices for physiological parameters during flight becomes important. It has long been known that arterial PO2 (PaO2) decreases during unsupplemented, non- pressurized flight. In this study, the authors examined the use of the transconjunctival oxygen (cjO2) monitor for assessing the adequacy of arterial oxygenation during helicopter flight in four healthy volunteers. Arterial PaO2 as measured by conventional blood gas analysis was compared with cjO2 at ground level, 5,000 feet, and 10,000 feet altitude. Mean PaO2 dropped significantly from 93.5 to 81.5 to 58.5 mm Hg, respectively (P less than 0.001, analysis of variance with repeated measures). Mean cjO2 also decreased significantly from 63.8 to 52.0 to 34.8 mm Hg, respectively (P less than 0.001, analysis of variance with repeated measures). Within individual subjects, cjO2 was an accurate predictor of PaO2 (P less than 0.001, multiple regression analysis). The relationship between cjO2 and PaO2 was linear with a regression coefficient of 1.147. The authors conclude that the transconjunctival O2 monitor may be useful for monitoring the adequacy of arterial oxygenation during helicopter flight in hemodynamically stable patients. The results of study also support the use of supplemental oxygen in all patients subjected to helicopter transport.", "output": "Nasogastric intubation", "explanation": "The title 'Nasogastric intubation' is completely out of the given abstract. So not an apt title. Title can be with helicopter transportation and transconjunctival oxygen."}, {"input": "Abstract: The course of a pregnant patient at term who was acutely exposed to carbon monoxide is described. A review of the fetal-maternal carboxyhemoglobin relationships and the differences in fetal oxyhemoglobin physiology are used to explain the recommendation that pregnant women with carbon monoxide poisoning should receive 100% oxygen therapy for up to five times longer than is otherwise necessary. The role of hyperbaric oxygen therapy is considered.", "output": "Intraosseous infusion of phenytoin.", "explanation": "The title 'Intraosseous infusion of phenytoin.' is no where related to the abstract or present in the abstract. So, it is not a perfect title. The abstract is about pregnency and carbon monoxide poisoning."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Reviews"], "Instance": {"id": "task619-35b877e8c55c4261b3cace6ed7f45c1f", "input": "Abstract: Epinephrine causes platelet aggregation and secretion by interacting with alpha 2-adrenergic receptors on the platelet surface. Platelet aggregation requires the binding of fibrinogen to a specific receptor on the membrane glycoprotein IIb-IIIa complex. Although the IIb-IIIa complex is identifiable on the surface of resting platelets, the fibrinogen receptor is expressed only after platelet activation. The current studies were designed to examine the effect of occupancy of platelet alpha 2-adrenergic receptors by epinephrine on the expression of fibrinogen receptors and on the aggregation of platelets. The ability of epinephrine to induce the expression of fibrinogen receptors was studied under two different conditions: acute stimulation (less than 1 min) and prolonged stimulation (50 to 90 min), the latter of which is associated with a reduction or \"desensitization\" of the platelet aggregation response. Expression of the fibrinogen receptor was monitored with 125I-fibrinogen as well as with 125I-PAC-1 (PAC-1), a monoclonal antibody that binds to the glycoprotein IIb-IIIa complex only after platelets are activated. Epinephrine caused an immediate increase in PAC-1 and fibrinogen binding that was dependent on occupancy of the alpha 2-receptor by epinephrine and on the presence of extracellular free Ca (KCa = 30 mumol/L). By itself, 1 mmol/L Mg was unable to support induction of the fibrinogen receptor by epinephrine. However, it did decrease the Ca requirement by about two orders of magnitude. Prolonged stimulation of unstirred platelets by epinephrine led to a 70% decrease in the aggregation response when the platelets were subsequently stirred. Despite their decreased aggregation response, desensitized platelets bound PAC-1 and fibrinogen normally, indicating that the loss of aggregation was not due simply to a decrease in fibrinogen receptor expression. Although desensitization was not affected by pretreatment of the platelets with aspirin, it was partially prevented when extracellular Ca was chelated by EDTA during the long incubation with epinephrine. These studies demonstrate that once platelet alpha 2-adrenergic receptors are occupied by epinephrine, extracellular Ca is involved in initiating the aggregation response by supporting the induction of the fibrinogen receptor and the binding of fibrinogen. Furthermore. Ca-dependent reactions subsequent to fibrinogen binding may be necessary for maximal platelet aggregation and are impaired when platelets become desensitized to epinephrine.", "output": ["Expression of fibrinogen receptors during activation and subsequent desensitization of human platelets by epinephrine."]}, "Instance License": ["CC BY-NC 4.0"], "prediction": "epinephrine causes platelet aggregation and secretion by interacting with alpha 2-adrenergic receptors on the platelet surface"}
+{"id": "task619-ad86ea4a8c314ecfa3b80c72f3ad85b2", "Task": "task619_ohsumed_abstract_title_generation", "Contributors": "['Saicharan Papani']", "Source": ["ohsumed"], "URL": ["https://huggingface.co/datasets/ohsumed"], "Categories": ["Title Generation"], "Reasoning": [], "Definition": ["Given an abstract of a paper, generate a title for this paper such that conveys the key focus of the paper."], "Positive Examples": [{"input": "Abstract: Some patients converted from ventricular fibrillation to organized rhythms by defibrillation-trained ambulance technicians (EMT-Ds) will refibrillate before hospital arrival. The authors analyzed 271 cases of ventricular fibrillation managed by EMT-Ds working without paramedic back-up. Of 111 patients initially converted to organized rhythms, 19 (17%) refibrillated, 11 (58%) of whom were reconverted to perfusing rhythms, including nine of 11 (82%) who had spontaneous pulses prior to refibrillation. Among patients initially converted to organized rhythms, hospital admission rates were lower for patients who refibrillated than for patients who did not(53% versus 76%, P = NS), although discharge rates were virtually identical (37% and 35%, respectively). Scene-to-hospital transport times were not predictively associated with either the frequency of refibrillation or patient outcome. Defibrillation-trained EMTs can effectively manage refibrillation with additional shocks and are not at a significant disadvantage when paramedic back-up is not available.", "output": "Refibrillation managed by EMT-Ds", "explanation": "The abstract is about refibrillation and it is also mentioned in the abstract that it is managed by EMT-Ds. So it is an apt title."}, {"input": "Abstract: The course of a pregnant patient at term who was acutely exposed to carbon monoxide is described. A review of the fetal-maternal carboxyhemoglobin relationships and the differences in fetal oxyhemoglobin physiology are used to explain the recommendation that pregnant women with carbon monoxide poisoning should receive 100% oxygen therapy for up to five times longer than is otherwise necessary. The role of hyperbaric oxygen therapy is considered.", "output": "Acute carbon monoxide poisoning during pregnancy.", "explanation": "The abstract described a pregant patient who was acutely exposed to carbon monoxide and the difference in fetal physiology is used to explain the recommendation of recieving 100% oxygen therapy for the pregnant women with carbon monoxide poisoning. So 'Acute carbon monoxide poisoning during pregnancy.' is the apt title"}, {"input": "Abstract: Over the last two decades, emergency medical services in the United States have been greatly improved. Organization of prehospital providers of health care has improved the outcome of many patients, particularly the trauma patient and the acute cardiac patient. In Seattle as many as 40% of outside-the-hospital cardiac arrest victims with ventricular fibrillation have been saved when there is rapid delivery of basic life support by first responders followed by advanced life support by paramedics. Although these systems are growing and improving health care, many lack adequate medical control or physician involvement. Emergency medical service systems must have physicians involved in their management to meet their full capabilities. It has become apparent that four factors are critical in determining the ability to resuscitate an individual once a cardiac arrest has occurred: time to starting any of the rescue procedures, use of electrical defibrillation when indicated, use of epinephrine, and adequacy of the technique of basic life support, particularly the ventilation component. To provide defibrillation at the earliest possible time, defibrillation by first responders such as emergency medical technicians appears to be of benefit. With the advent of automatic and semiautomatic defibrillators, first responders and family members may also be able to defibrillate victims. The use of defibrillation by people with less training than paramedics, however, must be approached with caution to ensure that there is adequate medical control and that the individuals who use these devices are properly trained.", "output": "Emergency medical service systems in acute cardiac care.", "explanation": "The abstract described the Emergency medical services in united states, particulary with the acute cardiac patient. So 'Emergency medical service systems in acute cardiac care.' is the apt title"}], "Negative Examples": [{"input": "Abstract: As the use of helicopters for air transport of critically ill patients increases, the availability of monitoring devices for physiological parameters during flight becomes important. It has long been known that arterial PO2 (PaO2) decreases during unsupplemented, non- pressurized flight. In this study, the authors examined the use of the transconjunctival oxygen (cjO2) monitor for assessing the adequacy of arterial oxygenation during helicopter flight in four healthy volunteers. Arterial PaO2 as measured by conventional blood gas analysis was compared with cjO2 at ground level, 5,000 feet, and 10,000 feet altitude. Mean PaO2 dropped significantly from 93.5 to 81.5 to 58.5 mm Hg, respectively (P less than 0.001, analysis of variance with repeated measures). Mean cjO2 also decreased significantly from 63.8 to 52.0 to 34.8 mm Hg, respectively (P less than 0.001, analysis of variance with repeated measures). Within individual subjects, cjO2 was an accurate predictor of PaO2 (P less than 0.001, multiple regression analysis). The relationship between cjO2 and PaO2 was linear with a regression coefficient of 1.147. The authors conclude that the transconjunctival O2 monitor may be useful for monitoring the adequacy of arterial oxygenation during helicopter flight in hemodynamically stable patients. The results of study also support the use of supplemental oxygen in all patients subjected to helicopter transport.", "output": "Nasogastric intubation", "explanation": "The title 'Nasogastric intubation' is completely out of the given abstract. So not an apt title. Title can be with helicopter transportation and transconjunctival oxygen."}, {"input": "Abstract: The course of a pregnant patient at term who was acutely exposed to carbon monoxide is described. A review of the fetal-maternal carboxyhemoglobin relationships and the differences in fetal oxyhemoglobin physiology are used to explain the recommendation that pregnant women with carbon monoxide poisoning should receive 100% oxygen therapy for up to five times longer than is otherwise necessary. The role of hyperbaric oxygen therapy is considered.", "output": "Intraosseous infusion of phenytoin.", "explanation": "The title 'Intraosseous infusion of phenytoin.' is no where related to the abstract or present in the abstract. So, it is not a perfect title. The abstract is about pregnency and carbon monoxide poisoning."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Reviews"], "Instance": {"id": "task619-ad86ea4a8c314ecfa3b80c72f3ad85b2", "input": "Abstract: We describe a patient with secondary syphilis and facial skin lesions which resembled Sweet's syndrome clinically and histologically. We suggest serological tests for syphilis in patients with Sweet's syndrome.", "output": ["Secondary syphilis mimicking Sweet's syndrome."]}, "Instance License": ["CC BY-NC 4.0"], "prediction": "Secondary syphilis and facial skin lesions resemble Sweet's syndrome"}
+{"id": "task619-fba4804c17614a619f1378a78fdf8598", "Task": "task619_ohsumed_abstract_title_generation", "Contributors": "['Saicharan Papani']", "Source": ["ohsumed"], "URL": ["https://huggingface.co/datasets/ohsumed"], "Categories": ["Title Generation"], "Reasoning": [], "Definition": ["Given an abstract of a paper, generate a title for this paper such that conveys the key focus of the paper."], "Positive Examples": [{"input": "Abstract: Some patients converted from ventricular fibrillation to organized rhythms by defibrillation-trained ambulance technicians (EMT-Ds) will refibrillate before hospital arrival. The authors analyzed 271 cases of ventricular fibrillation managed by EMT-Ds working without paramedic back-up. Of 111 patients initially converted to organized rhythms, 19 (17%) refibrillated, 11 (58%) of whom were reconverted to perfusing rhythms, including nine of 11 (82%) who had spontaneous pulses prior to refibrillation. Among patients initially converted to organized rhythms, hospital admission rates were lower for patients who refibrillated than for patients who did not(53% versus 76%, P = NS), although discharge rates were virtually identical (37% and 35%, respectively). Scene-to-hospital transport times were not predictively associated with either the frequency of refibrillation or patient outcome. Defibrillation-trained EMTs can effectively manage refibrillation with additional shocks and are not at a significant disadvantage when paramedic back-up is not available.", "output": "Refibrillation managed by EMT-Ds", "explanation": "The abstract is about refibrillation and it is also mentioned in the abstract that it is managed by EMT-Ds. So it is an apt title."}, {"input": "Abstract: The course of a pregnant patient at term who was acutely exposed to carbon monoxide is described. A review of the fetal-maternal carboxyhemoglobin relationships and the differences in fetal oxyhemoglobin physiology are used to explain the recommendation that pregnant women with carbon monoxide poisoning should receive 100% oxygen therapy for up to five times longer than is otherwise necessary. The role of hyperbaric oxygen therapy is considered.", "output": "Acute carbon monoxide poisoning during pregnancy.", "explanation": "The abstract described a pregant patient who was acutely exposed to carbon monoxide and the difference in fetal physiology is used to explain the recommendation of recieving 100% oxygen therapy for the pregnant women with carbon monoxide poisoning. So 'Acute carbon monoxide poisoning during pregnancy.' is the apt title"}, {"input": "Abstract: Over the last two decades, emergency medical services in the United States have been greatly improved. Organization of prehospital providers of health care has improved the outcome of many patients, particularly the trauma patient and the acute cardiac patient. In Seattle as many as 40% of outside-the-hospital cardiac arrest victims with ventricular fibrillation have been saved when there is rapid delivery of basic life support by first responders followed by advanced life support by paramedics. Although these systems are growing and improving health care, many lack adequate medical control or physician involvement. Emergency medical service systems must have physicians involved in their management to meet their full capabilities. It has become apparent that four factors are critical in determining the ability to resuscitate an individual once a cardiac arrest has occurred: time to starting any of the rescue procedures, use of electrical defibrillation when indicated, use of epinephrine, and adequacy of the technique of basic life support, particularly the ventilation component. To provide defibrillation at the earliest possible time, defibrillation by first responders such as emergency medical technicians appears to be of benefit. With the advent of automatic and semiautomatic defibrillators, first responders and family members may also be able to defibrillate victims. The use of defibrillation by people with less training than paramedics, however, must be approached with caution to ensure that there is adequate medical control and that the individuals who use these devices are properly trained.", "output": "Emergency medical service systems in acute cardiac care.", "explanation": "The abstract described the Emergency medical services in united states, particulary with the acute cardiac patient. So 'Emergency medical service systems in acute cardiac care.' is the apt title"}], "Negative Examples": [{"input": "Abstract: As the use of helicopters for air transport of critically ill patients increases, the availability of monitoring devices for physiological parameters during flight becomes important. It has long been known that arterial PO2 (PaO2) decreases during unsupplemented, non- pressurized flight. In this study, the authors examined the use of the transconjunctival oxygen (cjO2) monitor for assessing the adequacy of arterial oxygenation during helicopter flight in four healthy volunteers. Arterial PaO2 as measured by conventional blood gas analysis was compared with cjO2 at ground level, 5,000 feet, and 10,000 feet altitude. Mean PaO2 dropped significantly from 93.5 to 81.5 to 58.5 mm Hg, respectively (P less than 0.001, analysis of variance with repeated measures). Mean cjO2 also decreased significantly from 63.8 to 52.0 to 34.8 mm Hg, respectively (P less than 0.001, analysis of variance with repeated measures). Within individual subjects, cjO2 was an accurate predictor of PaO2 (P less than 0.001, multiple regression analysis). The relationship between cjO2 and PaO2 was linear with a regression coefficient of 1.147. The authors conclude that the transconjunctival O2 monitor may be useful for monitoring the adequacy of arterial oxygenation during helicopter flight in hemodynamically stable patients. The results of study also support the use of supplemental oxygen in all patients subjected to helicopter transport.", "output": "Nasogastric intubation", "explanation": "The title 'Nasogastric intubation' is completely out of the given abstract. So not an apt title. Title can be with helicopter transportation and transconjunctival oxygen."}, {"input": "Abstract: The course of a pregnant patient at term who was acutely exposed to carbon monoxide is described. A review of the fetal-maternal carboxyhemoglobin relationships and the differences in fetal oxyhemoglobin physiology are used to explain the recommendation that pregnant women with carbon monoxide poisoning should receive 100% oxygen therapy for up to five times longer than is otherwise necessary. The role of hyperbaric oxygen therapy is considered.", "output": "Intraosseous infusion of phenytoin.", "explanation": "The title 'Intraosseous infusion of phenytoin.' is no where related to the abstract or present in the abstract. So, it is not a perfect title. The abstract is about pregnency and carbon monoxide poisoning."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Reviews"], "Instance": {"id": "task619-fba4804c17614a619f1378a78fdf8598", "input": "Abstract: The roller screw electric VAD is easier to manufacture and 25% lighter than the previously described drum cam model. This device requires 12 to 15 W to pump 6 to 8 l/min with minimal hemolysis. The motor drive has functioned for periods up to 93 days in vivo with no measurable wear. The compliance chamber volume varies by 100 cc during VAD function but does so while maintaining pressure variations below 15 mmHg. Compliance chamber volume loss of 2 to 5 cc/day is explained by gas transport through SPU. The subcutaneous sampling port provides ready access to the sealed system.", "output": ["Roller screw electric motor ventricular assist device."]}, "Instance License": ["CC BY-NC 4.0"], "prediction": "Roller screw electric VAD"}
+{"id": "task1728-4c55725a7a1a464fbe911771bd5df40a", "Task": "task1728_web_nlg_data_to_text", "Contributors": "['Pegah Alipoormolabashi']", "Source": ["web_nlg"], "URL": ["https://huggingface.co/datasets/web_nlg"], "Categories": ["Data to Text"], "Reasoning": ["Relational Reasoning", "Commonsense Reasoning"], "Definition": ["You will be given one or more triples. The second part of each triple shows the relation between the first and the third element. Your task is to write a simple and short piece of text (sentence(s)) that describes the triples in natural language."], "Positive Examples": [{"input": "Amsterdam_Airport_Schiphol | runwayName | \"09/27 'Buitenveldertbaan'\"", "output": "Amsterdam Airport Schipol runway name is 09/27 Buitenvelderbaan.", "explanation": "The simplest form of input is a single triple. Here the text describes the relationship in natural language."}, {"input": "Bacon_sandwich | country | United_Kingdom\nBacon_sandwich | ingredient | Bacon", "output": "Bacon sandwich is a dish from the United Kingdom and not surprisingly includes bacon as an ingredient.", "explanation": "These triples describe the country and one of the ingredients of the bacon sandwich. The output consists of two sentences describing the triples."}, {"input": "Barny_Cakes | dishVariation | Chocolate\nBarny_Cakes | protein | 1.8 g\nBarny_Cakes | carbohydrate | 18.0 g\nBarny_Cakes | fat | 4.8 g", "output": "Barny cakes, which can be chocolate flavoured, contain 1.8g of protein, 4.8g of fat and 18g of carbohydrates.", "explanation": "The given triples show different aspects of \"Barny Cake\". The textual output correctly puts them all together."}], "Negative Examples": [{"input": "Antwerp_International_Airport | cityServed | Antwerp", "output": "Antwerp International airport city served Antwerp.", "explanation": "This is not a good output. Your answer should be grammatically correct and fluent."}, {"input": "A.F.C._Blackpool | ground | Blackpool", "output": "A.F.C. Blackpool play at their ground in Blackpool and is part of the North West Counties Football League.", "explanation": "Your answer should be based on the given triple, and you are not allowed to add extra information."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Wikipedia"], "Instance": {"id": "task1728-4c55725a7a1a464fbe911771bd5df40a", "input": "Ayam_penyet | region | Malaysia\nAyam_penyet | ingredient | Fried_chicken", "output": ["Fried chicken is one of the ingredients in the dish 'Ayam Penyet' which comes from Malaysia.", "Fried chicken is an ingredient in the popular Malaysian dish of Ayam penyet."]}, "Instance License": ["CC BY-NC-SA 4.0"], "prediction": "Ayam penyet is a Malaysian street food."}
+{"id": "task1728-1a47573bda6b4cd488568dd79c1b56cf", "Task": "task1728_web_nlg_data_to_text", "Contributors": "['Pegah Alipoormolabashi']", "Source": ["web_nlg"], "URL": ["https://huggingface.co/datasets/web_nlg"], "Categories": ["Data to Text"], "Reasoning": ["Relational Reasoning", "Commonsense Reasoning"], "Definition": ["You will be given one or more triples. The second part of each triple shows the relation between the first and the third element. Your task is to write a simple and short piece of text (sentence(s)) that describes the triples in natural language."], "Positive Examples": [{"input": "Amsterdam_Airport_Schiphol | runwayName | \"09/27 'Buitenveldertbaan'\"", "output": "Amsterdam Airport Schipol runway name is 09/27 Buitenvelderbaan.", "explanation": "The simplest form of input is a single triple. Here the text describes the relationship in natural language."}, {"input": "Bacon_sandwich | country | United_Kingdom\nBacon_sandwich | ingredient | Bacon", "output": "Bacon sandwich is a dish from the United Kingdom and not surprisingly includes bacon as an ingredient.", "explanation": "These triples describe the country and one of the ingredients of the bacon sandwich. The output consists of two sentences describing the triples."}, {"input": "Barny_Cakes | dishVariation | Chocolate\nBarny_Cakes | protein | 1.8 g\nBarny_Cakes | carbohydrate | 18.0 g\nBarny_Cakes | fat | 4.8 g", "output": "Barny cakes, which can be chocolate flavoured, contain 1.8g of protein, 4.8g of fat and 18g of carbohydrates.", "explanation": "The given triples show different aspects of \"Barny Cake\". The textual output correctly puts them all together."}], "Negative Examples": [{"input": "Antwerp_International_Airport | cityServed | Antwerp", "output": "Antwerp International airport city served Antwerp.", "explanation": "This is not a good output. Your answer should be grammatically correct and fluent."}, {"input": "A.F.C._Blackpool | ground | Blackpool", "output": "A.F.C. Blackpool play at their ground in Blackpool and is part of the North West Counties Football League.", "explanation": "Your answer should be based on the given triple, and you are not allowed to add extra information."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Wikipedia"], "Instance": {"id": "task1728-1a47573bda6b4cd488568dd79c1b56cf", "input": "Acta_Mathematica_Hungarica | LCCN_number | 83646315\nActa_Mathematica_Hungarica | abbreviation | \"Acta Math. Hungar.\"\nActa_Mathematica_Hungarica | academicDiscipline | Mathematics\nActa_Mathematica_Hungarica | ISSN_number | \"1588-2632\"", "output": ["83646315 is the LCCN number for Acta Mathematica Hungarica and the ISSN number is 1588-2632. Its bbreviation is \"Acta Math. Hungar.\" and its discipline is Math.", "Acta Mathematica Hungarica (Acta Math. Hungar.) which has a discipline of math has the LCCN number 83646315 and ISSN number 1588-2632.", "Acta Mathematica Hungarica has the abbreviation of Acta Math. Hungar and covers the academic discipline of Mathematics. This publication has the LCCN number 83646315 and the ISSN number 1588-2632."]}, "Instance License": ["CC BY-NC-SA 4.0"], "prediction": "Acta Math. Hungarica is a journal in the field of Mathematics."}
+{"id": "task1728-ed8418b1302943dfa20d02f65d8eed3f", "Task": "task1728_web_nlg_data_to_text", "Contributors": "['Pegah Alipoormolabashi']", "Source": ["web_nlg"], "URL": ["https://huggingface.co/datasets/web_nlg"], "Categories": ["Data to Text"], "Reasoning": ["Relational Reasoning", "Commonsense Reasoning"], "Definition": ["You will be given one or more triples. The second part of each triple shows the relation between the first and the third element. Your task is to write a simple and short piece of text (sentence(s)) that describes the triples in natural language."], "Positive Examples": [{"input": "Amsterdam_Airport_Schiphol | runwayName | \"09/27 'Buitenveldertbaan'\"", "output": "Amsterdam Airport Schipol runway name is 09/27 Buitenvelderbaan.", "explanation": "The simplest form of input is a single triple. Here the text describes the relationship in natural language."}, {"input": "Bacon_sandwich | country | United_Kingdom\nBacon_sandwich | ingredient | Bacon", "output": "Bacon sandwich is a dish from the United Kingdom and not surprisingly includes bacon as an ingredient.", "explanation": "These triples describe the country and one of the ingredients of the bacon sandwich. The output consists of two sentences describing the triples."}, {"input": "Barny_Cakes | dishVariation | Chocolate\nBarny_Cakes | protein | 1.8 g\nBarny_Cakes | carbohydrate | 18.0 g\nBarny_Cakes | fat | 4.8 g", "output": "Barny cakes, which can be chocolate flavoured, contain 1.8g of protein, 4.8g of fat and 18g of carbohydrates.", "explanation": "The given triples show different aspects of \"Barny Cake\". The textual output correctly puts them all together."}], "Negative Examples": [{"input": "Antwerp_International_Airport | cityServed | Antwerp", "output": "Antwerp International airport city served Antwerp.", "explanation": "This is not a good output. Your answer should be grammatically correct and fluent."}, {"input": "A.F.C._Blackpool | ground | Blackpool", "output": "A.F.C. Blackpool play at their ground in Blackpool and is part of the North West Counties Football League.", "explanation": "Your answer should be based on the given triple, and you are not allowed to add extra information."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Wikipedia"], "Instance": {"id": "task1728-ed8418b1302943dfa20d02f65d8eed3f", "input": "Turkey | leader | Ahmet_Davuto\u011flu\nAtat\u00fcrk_Monument_(\u0130zmir) | designer | Pietro_Canonica\nAtat\u00fcrk_Monument_(\u0130zmir) | material | \"Bronze\"\nAtat\u00fcrk_Monument_(\u0130zmir) | location | Turkey", "output": ["Ahmet Davutoglu is a leader of Turkey. The Atat\u00fcrk Monument (\u0130zmir) is found in Turkey, made of Bronze and designed by Pietro Canonica.", "By the way, the leader of Turkey is Ahmet Davutoglu and the Ataturk Monument designed by Pietro Canonica is made of bronze and located in Izmir, Turkey.", "Ahmet Davutoglu is the leader of Turkey, the location of the bronze Atat\u00fcrk Monument in Izmir designed by Pietro Canonica."]}, "Instance License": ["CC BY-NC-SA 4.0"], "prediction": "Turkey is a country in the Middle East and is located in the country of Turkey."}
+{"id": "task1728-e344d73b4e664a019f9a7895103f1a27", "Task": "task1728_web_nlg_data_to_text", "Contributors": "['Pegah Alipoormolabashi']", "Source": ["web_nlg"], "URL": ["https://huggingface.co/datasets/web_nlg"], "Categories": ["Data to Text"], "Reasoning": ["Relational Reasoning", "Commonsense Reasoning"], "Definition": ["You will be given one or more triples. The second part of each triple shows the relation between the first and the third element. Your task is to write a simple and short piece of text (sentence(s)) that describes the triples in natural language."], "Positive Examples": [{"input": "Amsterdam_Airport_Schiphol | runwayName | \"09/27 'Buitenveldertbaan'\"", "output": "Amsterdam Airport Schipol runway name is 09/27 Buitenvelderbaan.", "explanation": "The simplest form of input is a single triple. Here the text describes the relationship in natural language."}, {"input": "Bacon_sandwich | country | United_Kingdom\nBacon_sandwich | ingredient | Bacon", "output": "Bacon sandwich is a dish from the United Kingdom and not surprisingly includes bacon as an ingredient.", "explanation": "These triples describe the country and one of the ingredients of the bacon sandwich. The output consists of two sentences describing the triples."}, {"input": "Barny_Cakes | dishVariation | Chocolate\nBarny_Cakes | protein | 1.8 g\nBarny_Cakes | carbohydrate | 18.0 g\nBarny_Cakes | fat | 4.8 g", "output": "Barny cakes, which can be chocolate flavoured, contain 1.8g of protein, 4.8g of fat and 18g of carbohydrates.", "explanation": "The given triples show different aspects of \"Barny Cake\". The textual output correctly puts them all together."}], "Negative Examples": [{"input": "Antwerp_International_Airport | cityServed | Antwerp", "output": "Antwerp International airport city served Antwerp.", "explanation": "This is not a good output. Your answer should be grammatically correct and fluent."}, {"input": "A.F.C._Blackpool | ground | Blackpool", "output": "A.F.C. Blackpool play at their ground in Blackpool and is part of the North West Counties Football League.", "explanation": "Your answer should be based on the given triple, and you are not allowed to add extra information."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Wikipedia"], "Instance": {"id": "task1728-e344d73b4e664a019f9a7895103f1a27", "input": "Hong_Kong | leaderName | Carrie_Lam_(politician)\nBaked_Alaska | region | Hong_Kong", "output": ["Baked Alaska comes from Hong Kong where Carrie Lam is a political leader.", "Carrie Lam is the politician who leads Hong Kong, where Baked Alaska originates."]}, "Instance License": ["CC BY-NC-SA 4.0"], "prediction": "Carrie Lam (politician) Baked Alaska is a region in Hong Kong."}
+{"id": "task1728-fd7ebff2be7b466697a9b539165a2190", "Task": "task1728_web_nlg_data_to_text", "Contributors": "['Pegah Alipoormolabashi']", "Source": ["web_nlg"], "URL": ["https://huggingface.co/datasets/web_nlg"], "Categories": ["Data to Text"], "Reasoning": ["Relational Reasoning", "Commonsense Reasoning"], "Definition": ["You will be given one or more triples. The second part of each triple shows the relation between the first and the third element. Your task is to write a simple and short piece of text (sentence(s)) that describes the triples in natural language."], "Positive Examples": [{"input": "Amsterdam_Airport_Schiphol | runwayName | \"09/27 'Buitenveldertbaan'\"", "output": "Amsterdam Airport Schipol runway name is 09/27 Buitenvelderbaan.", "explanation": "The simplest form of input is a single triple. Here the text describes the relationship in natural language."}, {"input": "Bacon_sandwich | country | United_Kingdom\nBacon_sandwich | ingredient | Bacon", "output": "Bacon sandwich is a dish from the United Kingdom and not surprisingly includes bacon as an ingredient.", "explanation": "These triples describe the country and one of the ingredients of the bacon sandwich. The output consists of two sentences describing the triples."}, {"input": "Barny_Cakes | dishVariation | Chocolate\nBarny_Cakes | protein | 1.8 g\nBarny_Cakes | carbohydrate | 18.0 g\nBarny_Cakes | fat | 4.8 g", "output": "Barny cakes, which can be chocolate flavoured, contain 1.8g of protein, 4.8g of fat and 18g of carbohydrates.", "explanation": "The given triples show different aspects of \"Barny Cake\". The textual output correctly puts them all together."}], "Negative Examples": [{"input": "Antwerp_International_Airport | cityServed | Antwerp", "output": "Antwerp International airport city served Antwerp.", "explanation": "This is not a good output. Your answer should be grammatically correct and fluent."}, {"input": "A.F.C._Blackpool | ground | Blackpool", "output": "A.F.C. Blackpool play at their ground in Blackpool and is part of the North West Counties Football League.", "explanation": "Your answer should be based on the given triple, and you are not allowed to add extra information."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Wikipedia"], "Instance": {"id": "task1728-fd7ebff2be7b466697a9b539165a2190", "input": "Alan_Bean | was a crew member of | Apollo_12\nApollo_12 | operator | NASA\nAlan_Bean | occupation | Test_pilot\nApollo_12 | commander | David_Scott", "output": ["Alan Bean was a crew member of NASA's Apollo 12 with commander David Scott. He was a test pilot.", "Test Pilot Alan Bean was a crew member of NASA's Apollo 12 mission under commander David Scott."]}, "Instance License": ["CC BY-NC-SA 4.0"], "prediction": "Alan Bean was a crew member of Apollo 12 Apollo 12 and commander of Apollo 12 Apollo 12"}
+{"id": "task1640-f9a1d473686046ef926a0ead201ee880", "Task": "task1640_aqa1.0_answerable_unanswerable_question_classification", "Contributors": "['Suchit Jain']", "Source": ["adversarial_qa"], "URL": ["https://huggingface.co/datasets/adversarial_qa"], "Categories": ["Answerability Classification"], "Reasoning": [], "Definition": ["Given a paragraph from a Wikipedia article about some topic, and a question related to the topic, determine whether the question is answerable from the paragraph. If the question is answerable, answer \"True\", otherwise, answer \"False\"."], "Positive Examples": [{"input": "Another approach to brain function is to examine the consequences of damage to specific brain areas. Even though it is protected by the skull and meninges, surrounded by cerebrospinal fluid, and isolated from the bloodstream by the blood\u2013brain barrier, the delicate nature of the brain makes it vulnerable to numerous diseases and several types of damage. In humans, the effects of strokes and other types of brain damage have been a key source of information about brain function. Because there is no ability to experimentally control the nature of the damage, however, this information is often difficult to interpret. In animal studies, most commonly involving rats, it is possible to use electrodes or locally injected chemicals to produce precise patterns of damage and then examine the consequences for behavior. Question: What is surrounded by cerebrospinal fluid?", "output": "True", "explanation": "The paragraph comes from the wikipedia page on the brain. The answer to the question is the brain which can be found in the paragraph."}, {"input": "Motor systems are areas of the brain that are directly or indirectly involved in producing body movements, that is, in activating muscles. Except for the muscles that control the eye, which are driven by nuclei in the midbrain, all the voluntary muscles in the body are directly innervated by motor neurons in the spinal cord and hindbrain. Spinal motor neurons are controlled both by neural circuits intrinsic to the spinal cord, and by inputs that descend from the brain. The intrinsic spinal circuits implement many reflex responses, and contain pattern generators for rhythmic movements such as walking or swimming. The descending connections from the brain allow for more sophisticated control. Question: What is isolated from the bloodstream by the blood-brain barrier?", "output": "False", "explanation": "The paragraph comes from the wikipedia page on the brain. However, it does not contain the answer to the question."}, {"input": "Devise Minority Party Strategies. The minority leader, in consultation with other party colleagues, has a range of strategic options that he or she can employ to advance minority party objectives. The options selected depend on a wide range of circumstances, such as the visibility or significance of the issue and the degree of cohesion within the majority party. For instance, a majority party riven by internal dissension, as occurred during the early 1900s when Progressive and \"regular\" Republicans were at loggerheads, may provide the minority leader with greater opportunities to achieve his or her priorities than if the majority party exhibited high degrees of party cohesion. Among the variable strategies available to the minority party, which can vary from bill to bill and be used in combination or at different stages of the lawmaking process, are the following. Question: How might a strategy for a minority party member vary?", "output": "True", "explanation": "This paragraph comes from the wikipedia article on Party leaders of the United States House of Representatives. The answer to the question is visibility or significance of the issue and the degree of cohesion within the majority party which can be found in the paragraph."}], "Negative Examples": [{"input": "NASCAR (headquartered in Daytona Beach) begins all three of its major auto racing series in Florida at Daytona International Speedway in February, featuring the Daytona 500, and ends all three Series in November at Homestead-Miami Speedway. Daytona also has the Coke Zero 400 NASCAR race weekend around Independence Day in July. The 24 Hours of Daytona is one of the world's most prestigious endurance auto races. The Grand Prix of St. Petersburg and Grand Prix of Miami have held IndyCar races as well. Question: What is the starting time of NASCAR's big events?", "output": "False", "explanation": "This paragraph comes from the wikipedia article on Florida. The answer to the given question is February which can be found in the paragraph, however the output is given as False."}, {"input": "As of 2010, those of African ancestry accounted for 16.0% of Florida's population, which includes African Americans. Out of the 16.0%, 4.0% (741,879) were West Indian or Afro-Caribbean American. During the early 1900s, black people made up nearly half of the state's population. In response to segregation, disfranchisement and agricultural depression, many African Americans migrated from Florida to northern cities in the Great Migration, in waves from 1910 to 1940, and again starting in the later 1940s. They moved for jobs, better education for their children and the chance to vote and participate in society. By 1960 the proportion of African Americans in the state had declined to 18%. Conversely large numbers of northern whites moved to the state.[citation needed] Today, large concentrations of black residents can be found in northern and central Florida. Aside from blacks descended from African slaves brought to the US south, there are also large numbers of blacks of West Indian, recent African, and Afro-Latino immigrant origins, especially in the Miami/South Florida area. In 2010, Florida had the highest percentage of West Indians in the United States, with 2.0% (378,926) from Haitian ancestry, and 1.3% (236,950) Jamaican. All other (non-Hispanic) Caribbean nations were well below 0.1% of Florida residents. Question: Which rule managed the resources of Florida better?", "output": "True", "explanation": "This paragraph comes from the wikipedia article on Florida. The answer cannot be found in the paragraph, however the output is given as True."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Wikipedia"], "Instance": {"id": "task1640-f9a1d473686046ef926a0ead201ee880", "input": "An earlier draft of To Kill a Mockingbird, titled Go Set a Watchman, was controversially released on July 14, 2015. This draft, which was completed in 1957, is set 20 years after the time period depicted in To Kill a Mockingbird but is not a continuation of the narrative. This earlier version of the story follows an adult Scout Finch who travels from New York to visit her father, Atticus Finch, in Maycomb, Alabama, where she is confronted by the intolerance in her community. The Watchman manuscript was believed to have been lost until Lee's lawyer Tonja Carter discovered it; although this claim has been widely disputed. Watchman contains early versions of many of the characters from To Kill a Mockingbird. According to Lee's agent Andrew Nurnberg, Mockingbird was originally intended to be the first book of a trilogy: \"They discussed publishing Mockingbird first, Watchman last, and a shorter connecting novel between the two.\" This assertion has been discredited however by the rare books expert James S. Jaffe, who reviewed the pages at the request of Lee's attorney and found them to be only another draft of \"To Kill a Mockingbird\". The statement was also contrary to Jonathan Mahler's description of how \"Watchman\" was seen as just the first draft of \"Mockingbird\". Instances where many passages overlap between the two books, in some case word for word, also refutes this assertion. Question: Who does the mad dog represent?", "output": ["False"]}, "Instance License": ["MIT"], "prediction": "False"}
+{"id": "task1640-90ce20d17fcc4f119fe2428d727a3c34", "Task": "task1640_aqa1.0_answerable_unanswerable_question_classification", "Contributors": "['Suchit Jain']", "Source": ["adversarial_qa"], "URL": ["https://huggingface.co/datasets/adversarial_qa"], "Categories": ["Answerability Classification"], "Reasoning": [], "Definition": ["Given a paragraph from a Wikipedia article about some topic, and a question related to the topic, determine whether the question is answerable from the paragraph. If the question is answerable, answer \"True\", otherwise, answer \"False\"."], "Positive Examples": [{"input": "Another approach to brain function is to examine the consequences of damage to specific brain areas. Even though it is protected by the skull and meninges, surrounded by cerebrospinal fluid, and isolated from the bloodstream by the blood\u2013brain barrier, the delicate nature of the brain makes it vulnerable to numerous diseases and several types of damage. In humans, the effects of strokes and other types of brain damage have been a key source of information about brain function. Because there is no ability to experimentally control the nature of the damage, however, this information is often difficult to interpret. In animal studies, most commonly involving rats, it is possible to use electrodes or locally injected chemicals to produce precise patterns of damage and then examine the consequences for behavior. Question: What is surrounded by cerebrospinal fluid?", "output": "True", "explanation": "The paragraph comes from the wikipedia page on the brain. The answer to the question is the brain which can be found in the paragraph."}, {"input": "Motor systems are areas of the brain that are directly or indirectly involved in producing body movements, that is, in activating muscles. Except for the muscles that control the eye, which are driven by nuclei in the midbrain, all the voluntary muscles in the body are directly innervated by motor neurons in the spinal cord and hindbrain. Spinal motor neurons are controlled both by neural circuits intrinsic to the spinal cord, and by inputs that descend from the brain. The intrinsic spinal circuits implement many reflex responses, and contain pattern generators for rhythmic movements such as walking or swimming. The descending connections from the brain allow for more sophisticated control. Question: What is isolated from the bloodstream by the blood-brain barrier?", "output": "False", "explanation": "The paragraph comes from the wikipedia page on the brain. However, it does not contain the answer to the question."}, {"input": "Devise Minority Party Strategies. The minority leader, in consultation with other party colleagues, has a range of strategic options that he or she can employ to advance minority party objectives. The options selected depend on a wide range of circumstances, such as the visibility or significance of the issue and the degree of cohesion within the majority party. For instance, a majority party riven by internal dissension, as occurred during the early 1900s when Progressive and \"regular\" Republicans were at loggerheads, may provide the minority leader with greater opportunities to achieve his or her priorities than if the majority party exhibited high degrees of party cohesion. Among the variable strategies available to the minority party, which can vary from bill to bill and be used in combination or at different stages of the lawmaking process, are the following. Question: How might a strategy for a minority party member vary?", "output": "True", "explanation": "This paragraph comes from the wikipedia article on Party leaders of the United States House of Representatives. The answer to the question is visibility or significance of the issue and the degree of cohesion within the majority party which can be found in the paragraph."}], "Negative Examples": [{"input": "NASCAR (headquartered in Daytona Beach) begins all three of its major auto racing series in Florida at Daytona International Speedway in February, featuring the Daytona 500, and ends all three Series in November at Homestead-Miami Speedway. Daytona also has the Coke Zero 400 NASCAR race weekend around Independence Day in July. The 24 Hours of Daytona is one of the world's most prestigious endurance auto races. The Grand Prix of St. Petersburg and Grand Prix of Miami have held IndyCar races as well. Question: What is the starting time of NASCAR's big events?", "output": "False", "explanation": "This paragraph comes from the wikipedia article on Florida. The answer to the given question is February which can be found in the paragraph, however the output is given as False."}, {"input": "As of 2010, those of African ancestry accounted for 16.0% of Florida's population, which includes African Americans. Out of the 16.0%, 4.0% (741,879) were West Indian or Afro-Caribbean American. During the early 1900s, black people made up nearly half of the state's population. In response to segregation, disfranchisement and agricultural depression, many African Americans migrated from Florida to northern cities in the Great Migration, in waves from 1910 to 1940, and again starting in the later 1940s. They moved for jobs, better education for their children and the chance to vote and participate in society. By 1960 the proportion of African Americans in the state had declined to 18%. Conversely large numbers of northern whites moved to the state.[citation needed] Today, large concentrations of black residents can be found in northern and central Florida. Aside from blacks descended from African slaves brought to the US south, there are also large numbers of blacks of West Indian, recent African, and Afro-Latino immigrant origins, especially in the Miami/South Florida area. In 2010, Florida had the highest percentage of West Indians in the United States, with 2.0% (378,926) from Haitian ancestry, and 1.3% (236,950) Jamaican. All other (non-Hispanic) Caribbean nations were well below 0.1% of Florida residents. Question: Which rule managed the resources of Florida better?", "output": "True", "explanation": "This paragraph comes from the wikipedia article on Florida. The answer cannot be found in the paragraph, however the output is given as True."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Wikipedia"], "Instance": {"id": "task1640-90ce20d17fcc4f119fe2428d727a3c34", "input": "As Universal's main product had always been low-budget film, it was one of the last major studios to have a contract with Technicolor. The studio did not make use of the three-strip Technicolor process until Arabian Nights (1942), starring Jon Hall and Maria Montez. The following year, Technicolor was also used in Universal's remake of their 1925 horror melodrama, Phantom of the Opera with Claude Rains and Nelson Eddy. With the success of their first two pictures, a regular schedule of high-budget, Technicolor films followed. Question: Who made the movie Nelson Eddy was in?", "output": ["True"]}, "Instance License": ["MIT"], "prediction": "True"}
+{"id": "task1640-94c09eb5c66a453e8f63c4e859c13c61", "Task": "task1640_aqa1.0_answerable_unanswerable_question_classification", "Contributors": "['Suchit Jain']", "Source": ["adversarial_qa"], "URL": ["https://huggingface.co/datasets/adversarial_qa"], "Categories": ["Answerability Classification"], "Reasoning": [], "Definition": ["Given a paragraph from a Wikipedia article about some topic, and a question related to the topic, determine whether the question is answerable from the paragraph. If the question is answerable, answer \"True\", otherwise, answer \"False\"."], "Positive Examples": [{"input": "Another approach to brain function is to examine the consequences of damage to specific brain areas. Even though it is protected by the skull and meninges, surrounded by cerebrospinal fluid, and isolated from the bloodstream by the blood\u2013brain barrier, the delicate nature of the brain makes it vulnerable to numerous diseases and several types of damage. In humans, the effects of strokes and other types of brain damage have been a key source of information about brain function. Because there is no ability to experimentally control the nature of the damage, however, this information is often difficult to interpret. In animal studies, most commonly involving rats, it is possible to use electrodes or locally injected chemicals to produce precise patterns of damage and then examine the consequences for behavior. Question: What is surrounded by cerebrospinal fluid?", "output": "True", "explanation": "The paragraph comes from the wikipedia page on the brain. The answer to the question is the brain which can be found in the paragraph."}, {"input": "Motor systems are areas of the brain that are directly or indirectly involved in producing body movements, that is, in activating muscles. Except for the muscles that control the eye, which are driven by nuclei in the midbrain, all the voluntary muscles in the body are directly innervated by motor neurons in the spinal cord and hindbrain. Spinal motor neurons are controlled both by neural circuits intrinsic to the spinal cord, and by inputs that descend from the brain. The intrinsic spinal circuits implement many reflex responses, and contain pattern generators for rhythmic movements such as walking or swimming. The descending connections from the brain allow for more sophisticated control. Question: What is isolated from the bloodstream by the blood-brain barrier?", "output": "False", "explanation": "The paragraph comes from the wikipedia page on the brain. However, it does not contain the answer to the question."}, {"input": "Devise Minority Party Strategies. The minority leader, in consultation with other party colleagues, has a range of strategic options that he or she can employ to advance minority party objectives. The options selected depend on a wide range of circumstances, such as the visibility or significance of the issue and the degree of cohesion within the majority party. For instance, a majority party riven by internal dissension, as occurred during the early 1900s when Progressive and \"regular\" Republicans were at loggerheads, may provide the minority leader with greater opportunities to achieve his or her priorities than if the majority party exhibited high degrees of party cohesion. Among the variable strategies available to the minority party, which can vary from bill to bill and be used in combination or at different stages of the lawmaking process, are the following. Question: How might a strategy for a minority party member vary?", "output": "True", "explanation": "This paragraph comes from the wikipedia article on Party leaders of the United States House of Representatives. The answer to the question is visibility or significance of the issue and the degree of cohesion within the majority party which can be found in the paragraph."}], "Negative Examples": [{"input": "NASCAR (headquartered in Daytona Beach) begins all three of its major auto racing series in Florida at Daytona International Speedway in February, featuring the Daytona 500, and ends all three Series in November at Homestead-Miami Speedway. Daytona also has the Coke Zero 400 NASCAR race weekend around Independence Day in July. The 24 Hours of Daytona is one of the world's most prestigious endurance auto races. The Grand Prix of St. Petersburg and Grand Prix of Miami have held IndyCar races as well. Question: What is the starting time of NASCAR's big events?", "output": "False", "explanation": "This paragraph comes from the wikipedia article on Florida. The answer to the given question is February which can be found in the paragraph, however the output is given as False."}, {"input": "As of 2010, those of African ancestry accounted for 16.0% of Florida's population, which includes African Americans. Out of the 16.0%, 4.0% (741,879) were West Indian or Afro-Caribbean American. During the early 1900s, black people made up nearly half of the state's population. In response to segregation, disfranchisement and agricultural depression, many African Americans migrated from Florida to northern cities in the Great Migration, in waves from 1910 to 1940, and again starting in the later 1940s. They moved for jobs, better education for their children and the chance to vote and participate in society. By 1960 the proportion of African Americans in the state had declined to 18%. Conversely large numbers of northern whites moved to the state.[citation needed] Today, large concentrations of black residents can be found in northern and central Florida. Aside from blacks descended from African slaves brought to the US south, there are also large numbers of blacks of West Indian, recent African, and Afro-Latino immigrant origins, especially in the Miami/South Florida area. In 2010, Florida had the highest percentage of West Indians in the United States, with 2.0% (378,926) from Haitian ancestry, and 1.3% (236,950) Jamaican. All other (non-Hispanic) Caribbean nations were well below 0.1% of Florida residents. Question: Which rule managed the resources of Florida better?", "output": "True", "explanation": "This paragraph comes from the wikipedia article on Florida. The answer cannot be found in the paragraph, however the output is given as True."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Wikipedia"], "Instance": {"id": "task1640-94c09eb5c66a453e8f63c4e859c13c61", "input": "As of 2000[update], children and teenagers (0\u201319 years old) make up 15.1% of the population, while adults (20\u201364 years old) make up 65% and seniors (over 64 years old) make up 19.9%. Question: Suppose there are 2 more newborns, then which number will be increased, 65%, 15.1% or 19.9%?", "output": ["True"]}, "Instance License": ["MIT"], "prediction": "True"}
+{"id": "task1640-dd45c716d2b94fd291b6bbf5d4b26cd3", "Task": "task1640_aqa1.0_answerable_unanswerable_question_classification", "Contributors": "['Suchit Jain']", "Source": ["adversarial_qa"], "URL": ["https://huggingface.co/datasets/adversarial_qa"], "Categories": ["Answerability Classification"], "Reasoning": [], "Definition": ["Given a paragraph from a Wikipedia article about some topic, and a question related to the topic, determine whether the question is answerable from the paragraph. If the question is answerable, answer \"True\", otherwise, answer \"False\"."], "Positive Examples": [{"input": "Another approach to brain function is to examine the consequences of damage to specific brain areas. Even though it is protected by the skull and meninges, surrounded by cerebrospinal fluid, and isolated from the bloodstream by the blood\u2013brain barrier, the delicate nature of the brain makes it vulnerable to numerous diseases and several types of damage. In humans, the effects of strokes and other types of brain damage have been a key source of information about brain function. Because there is no ability to experimentally control the nature of the damage, however, this information is often difficult to interpret. In animal studies, most commonly involving rats, it is possible to use electrodes or locally injected chemicals to produce precise patterns of damage and then examine the consequences for behavior. Question: What is surrounded by cerebrospinal fluid?", "output": "True", "explanation": "The paragraph comes from the wikipedia page on the brain. The answer to the question is the brain which can be found in the paragraph."}, {"input": "Motor systems are areas of the brain that are directly or indirectly involved in producing body movements, that is, in activating muscles. Except for the muscles that control the eye, which are driven by nuclei in the midbrain, all the voluntary muscles in the body are directly innervated by motor neurons in the spinal cord and hindbrain. Spinal motor neurons are controlled both by neural circuits intrinsic to the spinal cord, and by inputs that descend from the brain. The intrinsic spinal circuits implement many reflex responses, and contain pattern generators for rhythmic movements such as walking or swimming. The descending connections from the brain allow for more sophisticated control. Question: What is isolated from the bloodstream by the blood-brain barrier?", "output": "False", "explanation": "The paragraph comes from the wikipedia page on the brain. However, it does not contain the answer to the question."}, {"input": "Devise Minority Party Strategies. The minority leader, in consultation with other party colleagues, has a range of strategic options that he or she can employ to advance minority party objectives. The options selected depend on a wide range of circumstances, such as the visibility or significance of the issue and the degree of cohesion within the majority party. For instance, a majority party riven by internal dissension, as occurred during the early 1900s when Progressive and \"regular\" Republicans were at loggerheads, may provide the minority leader with greater opportunities to achieve his or her priorities than if the majority party exhibited high degrees of party cohesion. Among the variable strategies available to the minority party, which can vary from bill to bill and be used in combination or at different stages of the lawmaking process, are the following. Question: How might a strategy for a minority party member vary?", "output": "True", "explanation": "This paragraph comes from the wikipedia article on Party leaders of the United States House of Representatives. The answer to the question is visibility or significance of the issue and the degree of cohesion within the majority party which can be found in the paragraph."}], "Negative Examples": [{"input": "NASCAR (headquartered in Daytona Beach) begins all three of its major auto racing series in Florida at Daytona International Speedway in February, featuring the Daytona 500, and ends all three Series in November at Homestead-Miami Speedway. Daytona also has the Coke Zero 400 NASCAR race weekend around Independence Day in July. The 24 Hours of Daytona is one of the world's most prestigious endurance auto races. The Grand Prix of St. Petersburg and Grand Prix of Miami have held IndyCar races as well. Question: What is the starting time of NASCAR's big events?", "output": "False", "explanation": "This paragraph comes from the wikipedia article on Florida. The answer to the given question is February which can be found in the paragraph, however the output is given as False."}, {"input": "As of 2010, those of African ancestry accounted for 16.0% of Florida's population, which includes African Americans. Out of the 16.0%, 4.0% (741,879) were West Indian or Afro-Caribbean American. During the early 1900s, black people made up nearly half of the state's population. In response to segregation, disfranchisement and agricultural depression, many African Americans migrated from Florida to northern cities in the Great Migration, in waves from 1910 to 1940, and again starting in the later 1940s. They moved for jobs, better education for their children and the chance to vote and participate in society. By 1960 the proportion of African Americans in the state had declined to 18%. Conversely large numbers of northern whites moved to the state.[citation needed] Today, large concentrations of black residents can be found in northern and central Florida. Aside from blacks descended from African slaves brought to the US south, there are also large numbers of blacks of West Indian, recent African, and Afro-Latino immigrant origins, especially in the Miami/South Florida area. In 2010, Florida had the highest percentage of West Indians in the United States, with 2.0% (378,926) from Haitian ancestry, and 1.3% (236,950) Jamaican. All other (non-Hispanic) Caribbean nations were well below 0.1% of Florida residents. Question: Which rule managed the resources of Florida better?", "output": "True", "explanation": "This paragraph comes from the wikipedia article on Florida. The answer cannot be found in the paragraph, however the output is given as True."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Wikipedia"], "Instance": {"id": "task1640-dd45c716d2b94fd291b6bbf5d4b26cd3", "input": "Chopin took the new salon genre of the nocturne, invented by the Irish composer John Field, to a deeper level of sophistication. He was the first to write ballades and scherzi as individual concert pieces. He essentially established a new genre with his own set of free-standing preludes (Op. 28, published 1839). He exploited the poetic potential of the concept of the concert \u00e9tude, already being developed in the 1820s and 1830s by Liszt, Clementi and Moscheles, in his two sets of studies (Op. 10 published in 1833, Op. 25 in 1837). Question: What were Chopin's complaints in 1842 when he had a recital in Paris?", "output": ["False"]}, "Instance License": ["MIT"], "prediction": "False"}
+{"id": "task1640-d4e6f5b6b1e4495eaa8ec91dab0787be", "Task": "task1640_aqa1.0_answerable_unanswerable_question_classification", "Contributors": "['Suchit Jain']", "Source": ["adversarial_qa"], "URL": ["https://huggingface.co/datasets/adversarial_qa"], "Categories": ["Answerability Classification"], "Reasoning": [], "Definition": ["Given a paragraph from a Wikipedia article about some topic, and a question related to the topic, determine whether the question is answerable from the paragraph. If the question is answerable, answer \"True\", otherwise, answer \"False\"."], "Positive Examples": [{"input": "Another approach to brain function is to examine the consequences of damage to specific brain areas. Even though it is protected by the skull and meninges, surrounded by cerebrospinal fluid, and isolated from the bloodstream by the blood\u2013brain barrier, the delicate nature of the brain makes it vulnerable to numerous diseases and several types of damage. In humans, the effects of strokes and other types of brain damage have been a key source of information about brain function. Because there is no ability to experimentally control the nature of the damage, however, this information is often difficult to interpret. In animal studies, most commonly involving rats, it is possible to use electrodes or locally injected chemicals to produce precise patterns of damage and then examine the consequences for behavior. Question: What is surrounded by cerebrospinal fluid?", "output": "True", "explanation": "The paragraph comes from the wikipedia page on the brain. The answer to the question is the brain which can be found in the paragraph."}, {"input": "Motor systems are areas of the brain that are directly or indirectly involved in producing body movements, that is, in activating muscles. Except for the muscles that control the eye, which are driven by nuclei in the midbrain, all the voluntary muscles in the body are directly innervated by motor neurons in the spinal cord and hindbrain. Spinal motor neurons are controlled both by neural circuits intrinsic to the spinal cord, and by inputs that descend from the brain. The intrinsic spinal circuits implement many reflex responses, and contain pattern generators for rhythmic movements such as walking or swimming. The descending connections from the brain allow for more sophisticated control. Question: What is isolated from the bloodstream by the blood-brain barrier?", "output": "False", "explanation": "The paragraph comes from the wikipedia page on the brain. However, it does not contain the answer to the question."}, {"input": "Devise Minority Party Strategies. The minority leader, in consultation with other party colleagues, has a range of strategic options that he or she can employ to advance minority party objectives. The options selected depend on a wide range of circumstances, such as the visibility or significance of the issue and the degree of cohesion within the majority party. For instance, a majority party riven by internal dissension, as occurred during the early 1900s when Progressive and \"regular\" Republicans were at loggerheads, may provide the minority leader with greater opportunities to achieve his or her priorities than if the majority party exhibited high degrees of party cohesion. Among the variable strategies available to the minority party, which can vary from bill to bill and be used in combination or at different stages of the lawmaking process, are the following. Question: How might a strategy for a minority party member vary?", "output": "True", "explanation": "This paragraph comes from the wikipedia article on Party leaders of the United States House of Representatives. The answer to the question is visibility or significance of the issue and the degree of cohesion within the majority party which can be found in the paragraph."}], "Negative Examples": [{"input": "NASCAR (headquartered in Daytona Beach) begins all three of its major auto racing series in Florida at Daytona International Speedway in February, featuring the Daytona 500, and ends all three Series in November at Homestead-Miami Speedway. Daytona also has the Coke Zero 400 NASCAR race weekend around Independence Day in July. The 24 Hours of Daytona is one of the world's most prestigious endurance auto races. The Grand Prix of St. Petersburg and Grand Prix of Miami have held IndyCar races as well. Question: What is the starting time of NASCAR's big events?", "output": "False", "explanation": "This paragraph comes from the wikipedia article on Florida. The answer to the given question is February which can be found in the paragraph, however the output is given as False."}, {"input": "As of 2010, those of African ancestry accounted for 16.0% of Florida's population, which includes African Americans. Out of the 16.0%, 4.0% (741,879) were West Indian or Afro-Caribbean American. During the early 1900s, black people made up nearly half of the state's population. In response to segregation, disfranchisement and agricultural depression, many African Americans migrated from Florida to northern cities in the Great Migration, in waves from 1910 to 1940, and again starting in the later 1940s. They moved for jobs, better education for their children and the chance to vote and participate in society. By 1960 the proportion of African Americans in the state had declined to 18%. Conversely large numbers of northern whites moved to the state.[citation needed] Today, large concentrations of black residents can be found in northern and central Florida. Aside from blacks descended from African slaves brought to the US south, there are also large numbers of blacks of West Indian, recent African, and Afro-Latino immigrant origins, especially in the Miami/South Florida area. In 2010, Florida had the highest percentage of West Indians in the United States, with 2.0% (378,926) from Haitian ancestry, and 1.3% (236,950) Jamaican. All other (non-Hispanic) Caribbean nations were well below 0.1% of Florida residents. Question: Which rule managed the resources of Florida better?", "output": "True", "explanation": "This paragraph comes from the wikipedia article on Florida. The answer cannot be found in the paragraph, however the output is given as True."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Wikipedia"], "Instance": {"id": "task1640-d4e6f5b6b1e4495eaa8ec91dab0787be", "input": "The first action of the Franco-Prussian War took place on 4 August 1870. This battle saw the unsupported division of General Douay of I Corps, with some attached cavalry, which was posted to watch the border, attacked in overwhelming but uncoordinated fashion by the German 3rd Army. During the day, elements of a Bavarian and two Prussian corps became engaged and were aided by Prussian artillery, which blasted holes in the defenses of the town. Douay held a very strong position initially, thanks to the accurate long-range fire of the Chassepots but his force was too thinly stretched to hold it. Douay was killed in the late morning when a caisson of the divisional mitrailleuse battery exploded near him; the encirclement of the town by the Prussians threatened the French avenue of retreat. Question: Who attacked the French division?", "output": ["True"]}, "Instance License": ["MIT"], "prediction": "True"}
+{"id": "task648-418857d1923146959efda110e97a1fb7", "Task": "task648_answer_generation", "Contributors": "['khushal chandresh modi']", "Source": ["winograd_wsc"], "URL": ["https://huggingface.co/datasets/winograd_wsc"], "Categories": ["Coreference Resolution"], "Reasoning": [], "Definition": ["You will see a sentence and a given pronoun. Answer with the word in the sentence to which the pronoun is referring."], "Positive Examples": [{"input": "text: this book introduced shakespeare to ovid; it was a fine selection of his writing.; pronoun: his", "output": "shakespeare", "explanation": "The pronoun 'his' refers to shakespeare, who was introduced to ovid."}, {"input": "text: madonna fired her trainer because she couldnt stand her boyfriend.; pronoun: her", "output": "trainer", "explanation": "It makes sense that Madonna fired ehr trainer because she couldn't stand the trainer's boyfriend."}], "Negative Examples": [{"input": "text: dan had to stop bill from toying with the injured bird. he is very compassionate.; pronoun: he", "output": "Bill", "explanation": "Bill was toying with the injured bird, so Dan is the one who is compassionate. The correct answer is Dan."}, {"input": "text: james asked robert for a favor but he refused.; pronoun: he", "output": "james", "explanation": "Usually the person who is being asked something can refuse, not the person who asks. So the correct answer here is Robert."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Narrative"], "Instance": {"id": "task648-418857d1923146959efda110e97a1fb7", "input": "text: tom threw his schoolbag down to ray after he reached the bottom of the stairs.; pronoun: he", "output": ["ray"]}, "Instance License": ["CC BY 4.0"], "prediction": "tom"}
+{"id": "task648-e8fc81ec2636400b8848e0c94cc8c8f5", "Task": "task648_answer_generation", "Contributors": "['khushal chandresh modi']", "Source": ["winograd_wsc"], "URL": ["https://huggingface.co/datasets/winograd_wsc"], "Categories": ["Coreference Resolution"], "Reasoning": [], "Definition": ["You will see a sentence and a given pronoun. Answer with the word in the sentence to which the pronoun is referring."], "Positive Examples": [{"input": "text: this book introduced shakespeare to ovid; it was a fine selection of his writing.; pronoun: his", "output": "shakespeare", "explanation": "The pronoun 'his' refers to shakespeare, who was introduced to ovid."}, {"input": "text: madonna fired her trainer because she couldnt stand her boyfriend.; pronoun: her", "output": "trainer", "explanation": "It makes sense that Madonna fired ehr trainer because she couldn't stand the trainer's boyfriend."}], "Negative Examples": [{"input": "text: dan had to stop bill from toying with the injured bird. he is very compassionate.; pronoun: he", "output": "Bill", "explanation": "Bill was toying with the injured bird, so Dan is the one who is compassionate. The correct answer is Dan."}, {"input": "text: james asked robert for a favor but he refused.; pronoun: he", "output": "james", "explanation": "Usually the person who is being asked something can refuse, not the person who asks. So the correct answer here is Robert."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Narrative"], "Instance": {"id": "task648-e8fc81ec2636400b8848e0c94cc8c8f5", "input": "text: there is a gap in the wall. you can see the garden behind it .; pronoun: it", "output": ["the wall"]}, "Instance License": ["CC BY 4.0"], "prediction": "garden"}
+{"id": "task648-1b44f48de3b84b0eb4bee0c5684d703b", "Task": "task648_answer_generation", "Contributors": "['khushal chandresh modi']", "Source": ["winograd_wsc"], "URL": ["https://huggingface.co/datasets/winograd_wsc"], "Categories": ["Coreference Resolution"], "Reasoning": [], "Definition": ["You will see a sentence and a given pronoun. Answer with the word in the sentence to which the pronoun is referring."], "Positive Examples": [{"input": "text: this book introduced shakespeare to ovid; it was a fine selection of his writing.; pronoun: his", "output": "shakespeare", "explanation": "The pronoun 'his' refers to shakespeare, who was introduced to ovid."}, {"input": "text: madonna fired her trainer because she couldnt stand her boyfriend.; pronoun: her", "output": "trainer", "explanation": "It makes sense that Madonna fired ehr trainer because she couldn't stand the trainer's boyfriend."}], "Negative Examples": [{"input": "text: dan had to stop bill from toying with the injured bird. he is very compassionate.; pronoun: he", "output": "Bill", "explanation": "Bill was toying with the injured bird, so Dan is the one who is compassionate. The correct answer is Dan."}, {"input": "text: james asked robert for a favor but he refused.; pronoun: he", "output": "james", "explanation": "Usually the person who is being asked something can refuse, not the person who asks. So the correct answer here is Robert."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Narrative"], "Instance": {"id": "task648-1b44f48de3b84b0eb4bee0c5684d703b", "input": "text: in the middle of the outdoor concert, the rain started falling, and it continued until 10.; pronoun: it", "output": ["the rain"]}, "Instance License": ["CC BY 4.0"], "prediction": "rain"}
+{"id": "task648-5db97f281b374095a5ae9a84cca90851", "Task": "task648_answer_generation", "Contributors": "['khushal chandresh modi']", "Source": ["winograd_wsc"], "URL": ["https://huggingface.co/datasets/winograd_wsc"], "Categories": ["Coreference Resolution"], "Reasoning": [], "Definition": ["You will see a sentence and a given pronoun. Answer with the word in the sentence to which the pronoun is referring."], "Positive Examples": [{"input": "text: this book introduced shakespeare to ovid; it was a fine selection of his writing.; pronoun: his", "output": "shakespeare", "explanation": "The pronoun 'his' refers to shakespeare, who was introduced to ovid."}, {"input": "text: madonna fired her trainer because she couldnt stand her boyfriend.; pronoun: her", "output": "trainer", "explanation": "It makes sense that Madonna fired ehr trainer because she couldn't stand the trainer's boyfriend."}], "Negative Examples": [{"input": "text: dan had to stop bill from toying with the injured bird. he is very compassionate.; pronoun: he", "output": "Bill", "explanation": "Bill was toying with the injured bird, so Dan is the one who is compassionate. The correct answer is Dan."}, {"input": "text: james asked robert for a favor but he refused.; pronoun: he", "output": "james", "explanation": "Usually the person who is being asked something can refuse, not the person who asks. So the correct answer here is Robert."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Narrative"], "Instance": {"id": "task648-5db97f281b374095a5ae9a84cca90851", "input": "text: sid explained his theory to mark but he couldn't convince him.; pronoun: he", "output": ["sid"]}, "Instance License": ["CC BY 4.0"], "prediction": "sid"}
+{"id": "task648-d5ae72ef6cf9417c87bea3a8a846720b", "Task": "task648_answer_generation", "Contributors": "['khushal chandresh modi']", "Source": ["winograd_wsc"], "URL": ["https://huggingface.co/datasets/winograd_wsc"], "Categories": ["Coreference Resolution"], "Reasoning": [], "Definition": ["You will see a sentence and a given pronoun. Answer with the word in the sentence to which the pronoun is referring."], "Positive Examples": [{"input": "text: this book introduced shakespeare to ovid; it was a fine selection of his writing.; pronoun: his", "output": "shakespeare", "explanation": "The pronoun 'his' refers to shakespeare, who was introduced to ovid."}, {"input": "text: madonna fired her trainer because she couldnt stand her boyfriend.; pronoun: her", "output": "trainer", "explanation": "It makes sense that Madonna fired ehr trainer because she couldn't stand the trainer's boyfriend."}], "Negative Examples": [{"input": "text: dan had to stop bill from toying with the injured bird. he is very compassionate.; pronoun: he", "output": "Bill", "explanation": "Bill was toying with the injured bird, so Dan is the one who is compassionate. The correct answer is Dan."}, {"input": "text: james asked robert for a favor but he refused.; pronoun: he", "output": "james", "explanation": "Usually the person who is being asked something can refuse, not the person who asks. So the correct answer here is Robert."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Narrative"], "Instance": {"id": "task648-d5ae72ef6cf9417c87bea3a8a846720b", "input": "text: the large ball crashed right through the table because it was made of steel.; pronoun: it", "output": ["the large ball"]}, "Instance License": ["CC BY 4.0"], "prediction": "ball"}
+{"id": "task242-ce0f91d0c00d4ddabb2c36515a8aec5d", "Task": "task242_tweetqa_classification", "Contributors": "['Mihir Parmar']", "Source": ["tweetqa"], "URL": ["https://tweetqa.github.io/"], "Categories": ["Answerability Classification"], "Reasoning": [], "Definition": ["In this task, you are given a context tweet, a question and corresponding answer of given question. Your task is to classify given passage into two categories: (1) \"yes\" if the given context is useful in answering the question, and (2) \"no\" if the given context is not useful."], "Positive Examples": [{"input": "Context: Our prayers are with the students, educators & families at Independence High School & all the first responders on the scene. #PatriotPride\u2014 Doug Ducey (@dougducey) February 12, 2016 Question: at which school were first responders on the scene for? Answer: independence high school", "output": "yes", "explanation": "Here, the generated label is 'yes' because the given context is useful in answering the question."}, {"input": "Context: Working on a new superhero film called Look At Me Man. Gonna be tight, yo. \ud83d\udc4d\ud83d\ude08\ud83d\ude0e\ud83d\udcaa\u2014 Shane West (@shanewest_1) May 13, 2014 Question: what superhero film was mentioned? Answer: look at me man", "output": "yes", "explanation": "Here, the generated label is 'yes' because we can answer the question using the tweet."}, {"input": "Context: @williebosshog huge love to you/your family huge respect for your business prosperities and the family values you still all behold. big fan\u2014 Liam Payne (@Real_Liam_Payne) January 18, 2014 Question: at which school were first responders on the scene for? Answer: independence high school", "output": "no", "explanation": "Here, the generated label is 'no' because the given context is not useful in answering the question."}], "Negative Examples": [{"input": "Context: So many bad jokes about #BrazilvsGermany right now. I can't take it an neymar.\u2014 Professor Snape (@_Snape_) July 8, 2014 Question: what can\u2019t professor snape take anymore? Answer: bad jokes", "output": "no", "explanation": "Here, the generated label should be 'yes' because the given context is helpful in answering the question, however, the label is 'no' which is not right."}, {"input": "Context: Thank you to my loved ones and those that have been there for me, who have picked me up and helped me through everything.\u2014 Oscar Pistorius (@OscarPistorius) August 8, 2014 Question: why does zendaya look gorgeous? Answer: because she speaks her mind.", "output": "yes", "explanation": "Here, the generated label should be 'no' because this context is not helpful in answering the question. Still this sample labeled as 'yes' which is wrong."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Social Media -> Twitter"], "Instance": {"id": "task242-ce0f91d0c00d4ddabb2c36515a8aec5d", "input": "Context: So thankful for my family......thankful for forgiveness and the chance to be a better man through the strength, love, and kindness of the people I love who love me through all of my imperfections.Happy Thanksgiving to you all! Tim McGraw (@TheTimMcGraw) November 23, 2017 Question: what can't jonathan gruber shake? Answer: obamacare deceptions", "output": ["no"]}, "Instance License": ["CC BY-SA 4.0"], "prediction": "no"}
+{"id": "task242-ad95fb1cd0a5440095ab28741a41d9a7", "Task": "task242_tweetqa_classification", "Contributors": "['Mihir Parmar']", "Source": ["tweetqa"], "URL": ["https://tweetqa.github.io/"], "Categories": ["Answerability Classification"], "Reasoning": [], "Definition": ["In this task, you are given a context tweet, a question and corresponding answer of given question. Your task is to classify given passage into two categories: (1) \"yes\" if the given context is useful in answering the question, and (2) \"no\" if the given context is not useful."], "Positive Examples": [{"input": "Context: Our prayers are with the students, educators & families at Independence High School & all the first responders on the scene. #PatriotPride\u2014 Doug Ducey (@dougducey) February 12, 2016 Question: at which school were first responders on the scene for? Answer: independence high school", "output": "yes", "explanation": "Here, the generated label is 'yes' because the given context is useful in answering the question."}, {"input": "Context: Working on a new superhero film called Look At Me Man. Gonna be tight, yo. \ud83d\udc4d\ud83d\ude08\ud83d\ude0e\ud83d\udcaa\u2014 Shane West (@shanewest_1) May 13, 2014 Question: what superhero film was mentioned? Answer: look at me man", "output": "yes", "explanation": "Here, the generated label is 'yes' because we can answer the question using the tweet."}, {"input": "Context: @williebosshog huge love to you/your family huge respect for your business prosperities and the family values you still all behold. big fan\u2014 Liam Payne (@Real_Liam_Payne) January 18, 2014 Question: at which school were first responders on the scene for? Answer: independence high school", "output": "no", "explanation": "Here, the generated label is 'no' because the given context is not useful in answering the question."}], "Negative Examples": [{"input": "Context: So many bad jokes about #BrazilvsGermany right now. I can't take it an neymar.\u2014 Professor Snape (@_Snape_) July 8, 2014 Question: what can\u2019t professor snape take anymore? Answer: bad jokes", "output": "no", "explanation": "Here, the generated label should be 'yes' because the given context is helpful in answering the question, however, the label is 'no' which is not right."}, {"input": "Context: Thank you to my loved ones and those that have been there for me, who have picked me up and helped me through everything.\u2014 Oscar Pistorius (@OscarPistorius) August 8, 2014 Question: why does zendaya look gorgeous? Answer: because she speaks her mind.", "output": "yes", "explanation": "Here, the generated label should be 'no' because this context is not helpful in answering the question. Still this sample labeled as 'yes' which is wrong."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Social Media -> Twitter"], "Instance": {"id": "task242-ad95fb1cd0a5440095ab28741a41d9a7", "input": "Context: Classes at Bayside High are canceled for tomorrow. Screech will still be having the prom meeting in the afternoon.\u2014 MayorMark (@MayorMark) March 4, 2015 Question: what time will screech have the prom meeting Answer: meeting in the afternoon", "output": ["yes"]}, "Instance License": ["CC BY-SA 4.0"], "prediction": "yes"}
+{"id": "task242-1fd6058a2b264989b6c6b05e4690c78d", "Task": "task242_tweetqa_classification", "Contributors": "['Mihir Parmar']", "Source": ["tweetqa"], "URL": ["https://tweetqa.github.io/"], "Categories": ["Answerability Classification"], "Reasoning": [], "Definition": ["In this task, you are given a context tweet, a question and corresponding answer of given question. Your task is to classify given passage into two categories: (1) \"yes\" if the given context is useful in answering the question, and (2) \"no\" if the given context is not useful."], "Positive Examples": [{"input": "Context: Our prayers are with the students, educators & families at Independence High School & all the first responders on the scene. #PatriotPride\u2014 Doug Ducey (@dougducey) February 12, 2016 Question: at which school were first responders on the scene for? Answer: independence high school", "output": "yes", "explanation": "Here, the generated label is 'yes' because the given context is useful in answering the question."}, {"input": "Context: Working on a new superhero film called Look At Me Man. Gonna be tight, yo. \ud83d\udc4d\ud83d\ude08\ud83d\ude0e\ud83d\udcaa\u2014 Shane West (@shanewest_1) May 13, 2014 Question: what superhero film was mentioned? Answer: look at me man", "output": "yes", "explanation": "Here, the generated label is 'yes' because we can answer the question using the tweet."}, {"input": "Context: @williebosshog huge love to you/your family huge respect for your business prosperities and the family values you still all behold. big fan\u2014 Liam Payne (@Real_Liam_Payne) January 18, 2014 Question: at which school were first responders on the scene for? Answer: independence high school", "output": "no", "explanation": "Here, the generated label is 'no' because the given context is not useful in answering the question."}], "Negative Examples": [{"input": "Context: So many bad jokes about #BrazilvsGermany right now. I can't take it an neymar.\u2014 Professor Snape (@_Snape_) July 8, 2014 Question: what can\u2019t professor snape take anymore? Answer: bad jokes", "output": "no", "explanation": "Here, the generated label should be 'yes' because the given context is helpful in answering the question, however, the label is 'no' which is not right."}, {"input": "Context: Thank you to my loved ones and those that have been there for me, who have picked me up and helped me through everything.\u2014 Oscar Pistorius (@OscarPistorius) August 8, 2014 Question: why does zendaya look gorgeous? Answer: because she speaks her mind.", "output": "yes", "explanation": "Here, the generated label should be 'no' because this context is not helpful in answering the question. Still this sample labeled as 'yes' which is wrong."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Social Media -> Twitter"], "Instance": {"id": "task242-1fd6058a2b264989b6c6b05e4690c78d", "input": "Context: What I reported on Friday was the #Titans planned to bring him back, with conditions. Munchak must've balked on conditions \u2014 Jim Wyatt (@jwyattsports) January 4, 2014 Question: who balked on conditions? Answer: munchak", "output": ["yes"]}, "Instance License": ["CC BY-SA 4.0"], "prediction": "yes"}
+{"id": "task242-4f7c970a88d14d1cae66c71d052e04db", "Task": "task242_tweetqa_classification", "Contributors": "['Mihir Parmar']", "Source": ["tweetqa"], "URL": ["https://tweetqa.github.io/"], "Categories": ["Answerability Classification"], "Reasoning": [], "Definition": ["In this task, you are given a context tweet, a question and corresponding answer of given question. Your task is to classify given passage into two categories: (1) \"yes\" if the given context is useful in answering the question, and (2) \"no\" if the given context is not useful."], "Positive Examples": [{"input": "Context: Our prayers are with the students, educators & families at Independence High School & all the first responders on the scene. #PatriotPride\u2014 Doug Ducey (@dougducey) February 12, 2016 Question: at which school were first responders on the scene for? Answer: independence high school", "output": "yes", "explanation": "Here, the generated label is 'yes' because the given context is useful in answering the question."}, {"input": "Context: Working on a new superhero film called Look At Me Man. Gonna be tight, yo. \ud83d\udc4d\ud83d\ude08\ud83d\ude0e\ud83d\udcaa\u2014 Shane West (@shanewest_1) May 13, 2014 Question: what superhero film was mentioned? Answer: look at me man", "output": "yes", "explanation": "Here, the generated label is 'yes' because we can answer the question using the tweet."}, {"input": "Context: @williebosshog huge love to you/your family huge respect for your business prosperities and the family values you still all behold. big fan\u2014 Liam Payne (@Real_Liam_Payne) January 18, 2014 Question: at which school were first responders on the scene for? Answer: independence high school", "output": "no", "explanation": "Here, the generated label is 'no' because the given context is not useful in answering the question."}], "Negative Examples": [{"input": "Context: So many bad jokes about #BrazilvsGermany right now. I can't take it an neymar.\u2014 Professor Snape (@_Snape_) July 8, 2014 Question: what can\u2019t professor snape take anymore? Answer: bad jokes", "output": "no", "explanation": "Here, the generated label should be 'yes' because the given context is helpful in answering the question, however, the label is 'no' which is not right."}, {"input": "Context: Thank you to my loved ones and those that have been there for me, who have picked me up and helped me through everything.\u2014 Oscar Pistorius (@OscarPistorius) August 8, 2014 Question: why does zendaya look gorgeous? Answer: because she speaks her mind.", "output": "yes", "explanation": "Here, the generated label should be 'no' because this context is not helpful in answering the question. Still this sample labeled as 'yes' which is wrong."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Social Media -> Twitter"], "Instance": {"id": "task242-4f7c970a88d14d1cae66c71d052e04db", "input": "Context: Danbury students be like: MayorMark (@MayorMark) March 4, 2015 Question: when will the tweeter make final impact? Answer: very soon", "output": ["no"]}, "Instance License": ["CC BY-SA 4.0"], "prediction": "yes"}
+{"id": "task242-29999f9d2dbf450b9fdea78dce465221", "Task": "task242_tweetqa_classification", "Contributors": "['Mihir Parmar']", "Source": ["tweetqa"], "URL": ["https://tweetqa.github.io/"], "Categories": ["Answerability Classification"], "Reasoning": [], "Definition": ["In this task, you are given a context tweet, a question and corresponding answer of given question. Your task is to classify given passage into two categories: (1) \"yes\" if the given context is useful in answering the question, and (2) \"no\" if the given context is not useful."], "Positive Examples": [{"input": "Context: Our prayers are with the students, educators & families at Independence High School & all the first responders on the scene. #PatriotPride\u2014 Doug Ducey (@dougducey) February 12, 2016 Question: at which school were first responders on the scene for? Answer: independence high school", "output": "yes", "explanation": "Here, the generated label is 'yes' because the given context is useful in answering the question."}, {"input": "Context: Working on a new superhero film called Look At Me Man. Gonna be tight, yo. \ud83d\udc4d\ud83d\ude08\ud83d\ude0e\ud83d\udcaa\u2014 Shane West (@shanewest_1) May 13, 2014 Question: what superhero film was mentioned? Answer: look at me man", "output": "yes", "explanation": "Here, the generated label is 'yes' because we can answer the question using the tweet."}, {"input": "Context: @williebosshog huge love to you/your family huge respect for your business prosperities and the family values you still all behold. big fan\u2014 Liam Payne (@Real_Liam_Payne) January 18, 2014 Question: at which school were first responders on the scene for? Answer: independence high school", "output": "no", "explanation": "Here, the generated label is 'no' because the given context is not useful in answering the question."}], "Negative Examples": [{"input": "Context: So many bad jokes about #BrazilvsGermany right now. I can't take it an neymar.\u2014 Professor Snape (@_Snape_) July 8, 2014 Question: what can\u2019t professor snape take anymore? Answer: bad jokes", "output": "no", "explanation": "Here, the generated label should be 'yes' because the given context is helpful in answering the question, however, the label is 'no' which is not right."}, {"input": "Context: Thank you to my loved ones and those that have been there for me, who have picked me up and helped me through everything.\u2014 Oscar Pistorius (@OscarPistorius) August 8, 2014 Question: why does zendaya look gorgeous? Answer: because she speaks her mind.", "output": "yes", "explanation": "Here, the generated label should be 'no' because this context is not helpful in answering the question. Still this sample labeled as 'yes' which is wrong."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Social Media -> Twitter"], "Instance": {"id": "task242-29999f9d2dbf450b9fdea78dce465221", "input": "Context: Jackie Evancho's album sales have skyrocketed after announcing her Inauguration performance.Some people just don't understand the \"Movement\"\u2014 Donald J. Trump (@realDonaldTrump) January 4, 2017 Question: who's album sales are increasing? Answer: jackie evancho", "output": ["yes"]}, "Instance License": ["CC BY-SA 4.0"], "prediction": "yes"}
+{"id": "task620-21dc698548af4bc5a52e7102426a9b97", "Task": "task620_ohsumed_medical_subject_headings_answer_generation", "Contributors": "['Saicharan Papani']", "Source": ["ohsumed"], "URL": ["https://huggingface.co/datasets/ohsumed"], "Categories": ["Keyword Tagging"], "Reasoning": [], "Definition": ["Given an abstract, generate a keyword (a noun phrase) that best describes the focus or contribution of the paper. Such keywords can be directly from the given abstract or outside it."], "Positive Examples": [{"input": "Abstract: Some patients converted from ventricular fibrillation to organized rhythms by defibrillation - trained ambulance technicians(EMT - Ds) will refibrillate before hospital arrival.The authors analyzed 271 cases of ventricular fibrillation managed by EMT - Ds working without paramedic back - up.Of 111 patients initially converted to organized rhythms, 19(17 % ) refibrillated, 11(58 % ) of whom were reconverted to perfusing rhythms, including nine of 11(82 % ) who had spontaneous pulses prior to refibrillation.Among patients initially converted to organized rhythms, hospital admission rates were lower for patients who refibrillated than for patients who did not(53 % versus 76 % , P = NS), although discharge rates were virtually identical(37 % and 35 % , respectively).Scene - to - hospital transport times were not predictively associated with either the frequency of refibrillation or patient outcome.Defibrillation - trained EMTs can effectively manage refibrillation with additional shocks and are not at a significant disadvantage when paramedic back - up is not available.", "output": "Ventricular Fibrillation", "explanation": "This term is directly present in the abstract and it is one of the main topic in it. So can be chosen as the medical subject heading."}, {"input": "Abstract: Our results suggest that ethylene oxide retention after sterilization is increased in cuprammonium cellulose plate dialyzers containing potting compound. In contrast, cuprammonium cellulose plate dialyzers without potting compound were characterized by a rapid disappearance of retained ethylene oxide after sterilization. Whether these findings explain the low incidence of SARD with cuprammonium cellulose plate dialyzers that do not contain potting material is a matter for continued study and experimentation.", "output": "Sterilization", "explanation": "This term is directly present in the abstract and it is one of the main topic in it. So can be chosen as the medical subject heading."}], "Negative Examples": [{"input": "Abstract: Our results suggest that ethylene oxide retention after sterilization is increased in cuprammonium cellulose plate dialyzers containing potting compound. In contrast, cuprammonium cellulose plate dialyzers without potting compound were characterized by a rapid disappearance of retained ethylene oxide after sterilization. Whether these findings explain the low incidence of SARD with cuprammonium cellulose plate dialyzers that do not contain potting material is a matter for continued study and experimentation.", "output": "Plasma Volume", "explanation": "This term is not directly present in the abstract and it is no way related to the abstract. So can not be chosen as the medical subject heading. 'Cellulose' can be become a mesh term"}, {"input": "Abstract: Calcium carbonate appears to be as effective as aluminum hydroxide in binding dietary phosphorus in hemodialysis patients. The long-term safety of this medication appears acceptable in view of today's therapeutic options.", "output": "Cellulose", "explanation": "This term is not directly present in the abstract and it is no way related to the abstract. So can not be chosen as the medical subject heading. 'Calcium' can be become a mesh term"}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Scientific Research Papers"], "Instance": {"id": "task620-21dc698548af4bc5a52e7102426a9b97", "input": "Abstract: The effect of topical application of axonal transport blockers to the transected peripheral nerve was assessed by quantitating the strychnine-enhanced transsynaptic degeneration following transection of the inferior alveolar nerve in adult rats. Systemic administration of strychnine (1 mg/kg/day) for 7 days at the postoperational interval of 23 days proved to be suitable for quantitating the transsynaptic degeneration at the light microscopic level. When the proximal stump of transected nerve was treated with 2% colchicine immediately after transection, 5.8 +/- 6.8 dark neurons in a single section of the medullary dorsal horn, ipsilateral to the nerve transection, were observed. Following similar treatment with 0.4% vinblastine and 0.2% vincristine, 24.4 +/- 10.5 and 9.4 +/- 7.0 dark neurons were seen, respectively. When compared with 43.0 +/- 9.4 dark neurons, which were seen in animals without alkaloid treatment, colchicine, vinblastine and vincristine significantly reduced the transsynaptic degeneration by 86, 43, and 78%, respectively. Possible mechanisms involved in prevention of transsynaptic degeneration by the alkaloids are discussed.", "output": ["Administration, Topical", "Alkaloids", "Animal", "Colchicine", "Male", "Medulla Oblongata", "Nerve Degeneration", "Peripheral Nerves", "Rats", "Rats, Inbred Strains", "Strychnine", "Time Factors", "Vinblastine", "Vincristine"]}, "Instance License": ["CC BY-NC 4.0"], "prediction": "Transected peripheral nerve"}
+{"id": "task620-d74098c9d2774c37bd042ebf052bad26", "Task": "task620_ohsumed_medical_subject_headings_answer_generation", "Contributors": "['Saicharan Papani']", "Source": ["ohsumed"], "URL": ["https://huggingface.co/datasets/ohsumed"], "Categories": ["Keyword Tagging"], "Reasoning": [], "Definition": ["Given an abstract, generate a keyword (a noun phrase) that best describes the focus or contribution of the paper. Such keywords can be directly from the given abstract or outside it."], "Positive Examples": [{"input": "Abstract: Some patients converted from ventricular fibrillation to organized rhythms by defibrillation - trained ambulance technicians(EMT - Ds) will refibrillate before hospital arrival.The authors analyzed 271 cases of ventricular fibrillation managed by EMT - Ds working without paramedic back - up.Of 111 patients initially converted to organized rhythms, 19(17 % ) refibrillated, 11(58 % ) of whom were reconverted to perfusing rhythms, including nine of 11(82 % ) who had spontaneous pulses prior to refibrillation.Among patients initially converted to organized rhythms, hospital admission rates were lower for patients who refibrillated than for patients who did not(53 % versus 76 % , P = NS), although discharge rates were virtually identical(37 % and 35 % , respectively).Scene - to - hospital transport times were not predictively associated with either the frequency of refibrillation or patient outcome.Defibrillation - trained EMTs can effectively manage refibrillation with additional shocks and are not at a significant disadvantage when paramedic back - up is not available.", "output": "Ventricular Fibrillation", "explanation": "This term is directly present in the abstract and it is one of the main topic in it. So can be chosen as the medical subject heading."}, {"input": "Abstract: Our results suggest that ethylene oxide retention after sterilization is increased in cuprammonium cellulose plate dialyzers containing potting compound. In contrast, cuprammonium cellulose plate dialyzers without potting compound were characterized by a rapid disappearance of retained ethylene oxide after sterilization. Whether these findings explain the low incidence of SARD with cuprammonium cellulose plate dialyzers that do not contain potting material is a matter for continued study and experimentation.", "output": "Sterilization", "explanation": "This term is directly present in the abstract and it is one of the main topic in it. So can be chosen as the medical subject heading."}], "Negative Examples": [{"input": "Abstract: Our results suggest that ethylene oxide retention after sterilization is increased in cuprammonium cellulose plate dialyzers containing potting compound. In contrast, cuprammonium cellulose plate dialyzers without potting compound were characterized by a rapid disappearance of retained ethylene oxide after sterilization. Whether these findings explain the low incidence of SARD with cuprammonium cellulose plate dialyzers that do not contain potting material is a matter for continued study and experimentation.", "output": "Plasma Volume", "explanation": "This term is not directly present in the abstract and it is no way related to the abstract. So can not be chosen as the medical subject heading. 'Cellulose' can be become a mesh term"}, {"input": "Abstract: Calcium carbonate appears to be as effective as aluminum hydroxide in binding dietary phosphorus in hemodialysis patients. The long-term safety of this medication appears acceptable in view of today's therapeutic options.", "output": "Cellulose", "explanation": "This term is not directly present in the abstract and it is no way related to the abstract. So can not be chosen as the medical subject heading. 'Calcium' can be become a mesh term"}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Scientific Research Papers"], "Instance": {"id": "task620-d74098c9d2774c37bd042ebf052bad26", "input": "Abstract: After a retreat to an Oregon farm, 19 of 31 college students developed an acute gastrointestinal illness. Campylobacter jejuni infection was recognized in all the ill students and caused asymptomatic infections in three others. In total, 22 (88%) of 25 students who consumed raw milk for the first time became infected as compared with none of two who had not consumed raw milk. Among ten persons who chronically consumed raw milk, none was ill, a striking difference from the 76% attack rate among the 25 acutely exposed students. The quantity of raw milk consumed was directly related to the occurrence and severity of illness. Acutely infected students showed significant rises in C jejuni-specific immunoglobulins, whereas the low antibody levels seen in unexposed persons did not rise. In contrast, acute-phase serum samples from persons with chronic exposure to raw milk showed elevated antibody levels to C jejuni. These findings indicate that chronic raw milk consumption is associated with elevated levels of C jejuni-specific serum antibodies and with immunity to symptomatic infection.", "output": ["Acute Disease", "Acute Phase Proteins", "Adolescence", "Adult", "Animal", "Antibodies, Bacterial", "Campylobacter fetus", "Campylobacter Infections", "Cattle", "Disease Outbreaks", "Enteritis", "Food Microbiology", "Human", "Immunity, Active", "Milk", "Support, Non-U.S. Gov't", "Support, U.S. Gov't, Non-P.H.S.."]}, "Instance License": ["CC BY-NC 4.0"], "prediction": "gastrointestinal illness"}
+{"id": "task620-741d3eddab7448bbb221687641717065", "Task": "task620_ohsumed_medical_subject_headings_answer_generation", "Contributors": "['Saicharan Papani']", "Source": ["ohsumed"], "URL": ["https://huggingface.co/datasets/ohsumed"], "Categories": ["Keyword Tagging"], "Reasoning": [], "Definition": ["Given an abstract, generate a keyword (a noun phrase) that best describes the focus or contribution of the paper. Such keywords can be directly from the given abstract or outside it."], "Positive Examples": [{"input": "Abstract: Some patients converted from ventricular fibrillation to organized rhythms by defibrillation - trained ambulance technicians(EMT - Ds) will refibrillate before hospital arrival.The authors analyzed 271 cases of ventricular fibrillation managed by EMT - Ds working without paramedic back - up.Of 111 patients initially converted to organized rhythms, 19(17 % ) refibrillated, 11(58 % ) of whom were reconverted to perfusing rhythms, including nine of 11(82 % ) who had spontaneous pulses prior to refibrillation.Among patients initially converted to organized rhythms, hospital admission rates were lower for patients who refibrillated than for patients who did not(53 % versus 76 % , P = NS), although discharge rates were virtually identical(37 % and 35 % , respectively).Scene - to - hospital transport times were not predictively associated with either the frequency of refibrillation or patient outcome.Defibrillation - trained EMTs can effectively manage refibrillation with additional shocks and are not at a significant disadvantage when paramedic back - up is not available.", "output": "Ventricular Fibrillation", "explanation": "This term is directly present in the abstract and it is one of the main topic in it. So can be chosen as the medical subject heading."}, {"input": "Abstract: Our results suggest that ethylene oxide retention after sterilization is increased in cuprammonium cellulose plate dialyzers containing potting compound. In contrast, cuprammonium cellulose plate dialyzers without potting compound were characterized by a rapid disappearance of retained ethylene oxide after sterilization. Whether these findings explain the low incidence of SARD with cuprammonium cellulose plate dialyzers that do not contain potting material is a matter for continued study and experimentation.", "output": "Sterilization", "explanation": "This term is directly present in the abstract and it is one of the main topic in it. So can be chosen as the medical subject heading."}], "Negative Examples": [{"input": "Abstract: Our results suggest that ethylene oxide retention after sterilization is increased in cuprammonium cellulose plate dialyzers containing potting compound. In contrast, cuprammonium cellulose plate dialyzers without potting compound were characterized by a rapid disappearance of retained ethylene oxide after sterilization. Whether these findings explain the low incidence of SARD with cuprammonium cellulose plate dialyzers that do not contain potting material is a matter for continued study and experimentation.", "output": "Plasma Volume", "explanation": "This term is not directly present in the abstract and it is no way related to the abstract. So can not be chosen as the medical subject heading. 'Cellulose' can be become a mesh term"}, {"input": "Abstract: Calcium carbonate appears to be as effective as aluminum hydroxide in binding dietary phosphorus in hemodialysis patients. The long-term safety of this medication appears acceptable in view of today's therapeutic options.", "output": "Cellulose", "explanation": "This term is not directly present in the abstract and it is no way related to the abstract. So can not be chosen as the medical subject heading. 'Calcium' can be become a mesh term"}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Scientific Research Papers"], "Instance": {"id": "task620-741d3eddab7448bbb221687641717065", "input": "Abstract: RV and LV failure frequently coexist. Experimental evidence suggests that RV failure results from a primary insult to the right ventricle and an increase in pulmonary vascular resistance. LV failure results in an elevation of the left atrial pressure and thereby a reduction in the transpulmonary hydrostatic gradient. Because RV function depends on the contraction of the left ventricle, this contribution is reduced during LV failure. Treatment should be aimed first at restoring LV function. If RV failure persists and is not due to a simple mechanical problem, treatment of RV failure should be commenced. If volume loading, inotropes, and pH adjustments do not result in adequate RV output, a mechanical assist device should be considered. RHBP is the most powerful device, and it is capable of restoring systemic perfusion even when there is no residual RV function. Clinical results with this device have been most encouraging--most patients demonstrate improved RV function and a decrease in pulmonary vascular resistance after several days of treatment, allowing them to be weaned from assist. However, this technique is very invasive and requires constant close attention. PABC is a simple but less powerful assist device. Experimental studies suggest that if RV function is not extremely depressed--cardiac output is greater than 50 percent of normal--PABC may be effective in restoring systemic perfusion to normal levels. Current results suggest that RHBP remains the gold standard for severe RV failure, but further clinical experience with PABC may more clearly define its role in the management of RV failure.", "output": ["Heart Failure, Congestive", "Heart Ventricle", "Human", "Intraoperative Complications", "Support, Non-U.S. Gov't", "Vascular Resistance."]}, "Instance License": ["CC BY-NC 4.0"], "prediction": "LV Failure"}
+{"id": "task620-50d954a1ecaf42f7a011ad3102ce2038", "Task": "task620_ohsumed_medical_subject_headings_answer_generation", "Contributors": "['Saicharan Papani']", "Source": ["ohsumed"], "URL": ["https://huggingface.co/datasets/ohsumed"], "Categories": ["Keyword Tagging"], "Reasoning": [], "Definition": ["Given an abstract, generate a keyword (a noun phrase) that best describes the focus or contribution of the paper. Such keywords can be directly from the given abstract or outside it."], "Positive Examples": [{"input": "Abstract: Some patients converted from ventricular fibrillation to organized rhythms by defibrillation - trained ambulance technicians(EMT - Ds) will refibrillate before hospital arrival.The authors analyzed 271 cases of ventricular fibrillation managed by EMT - Ds working without paramedic back - up.Of 111 patients initially converted to organized rhythms, 19(17 % ) refibrillated, 11(58 % ) of whom were reconverted to perfusing rhythms, including nine of 11(82 % ) who had spontaneous pulses prior to refibrillation.Among patients initially converted to organized rhythms, hospital admission rates were lower for patients who refibrillated than for patients who did not(53 % versus 76 % , P = NS), although discharge rates were virtually identical(37 % and 35 % , respectively).Scene - to - hospital transport times were not predictively associated with either the frequency of refibrillation or patient outcome.Defibrillation - trained EMTs can effectively manage refibrillation with additional shocks and are not at a significant disadvantage when paramedic back - up is not available.", "output": "Ventricular Fibrillation", "explanation": "This term is directly present in the abstract and it is one of the main topic in it. So can be chosen as the medical subject heading."}, {"input": "Abstract: Our results suggest that ethylene oxide retention after sterilization is increased in cuprammonium cellulose plate dialyzers containing potting compound. In contrast, cuprammonium cellulose plate dialyzers without potting compound were characterized by a rapid disappearance of retained ethylene oxide after sterilization. Whether these findings explain the low incidence of SARD with cuprammonium cellulose plate dialyzers that do not contain potting material is a matter for continued study and experimentation.", "output": "Sterilization", "explanation": "This term is directly present in the abstract and it is one of the main topic in it. So can be chosen as the medical subject heading."}], "Negative Examples": [{"input": "Abstract: Our results suggest that ethylene oxide retention after sterilization is increased in cuprammonium cellulose plate dialyzers containing potting compound. In contrast, cuprammonium cellulose plate dialyzers without potting compound were characterized by a rapid disappearance of retained ethylene oxide after sterilization. Whether these findings explain the low incidence of SARD with cuprammonium cellulose plate dialyzers that do not contain potting material is a matter for continued study and experimentation.", "output": "Plasma Volume", "explanation": "This term is not directly present in the abstract and it is no way related to the abstract. So can not be chosen as the medical subject heading. 'Cellulose' can be become a mesh term"}, {"input": "Abstract: Calcium carbonate appears to be as effective as aluminum hydroxide in binding dietary phosphorus in hemodialysis patients. The long-term safety of this medication appears acceptable in view of today's therapeutic options.", "output": "Cellulose", "explanation": "This term is not directly present in the abstract and it is no way related to the abstract. So can not be chosen as the medical subject heading. 'Calcium' can be become a mesh term"}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Scientific Research Papers"], "Instance": {"id": "task620-50d954a1ecaf42f7a011ad3102ce2038", "input": "Abstract: A retrospective epidemiological study of industrial burns admitted to the Royal Brisbane Hospital was conducted over a period of 7 years. A total of 182 patients were included in this survey--173 males (95 per cent) and 9 females (5 per cent). The proportion of industrial burns has decreased from 31.5 per cent to 18.5 per cent of total admissions to the burns unit over the past 10 years. Fifty per cent of the burns occurred in males less than 30 years old. The average age was 31 years. Two-thirds of the burns covered less than 10 per cent of the body and 84 per cent covered less than 20 per cent. While scalds were the commonest cause of industrial burns in our study (19.4 per cent), flame burns with clothing ignited caused the most extensive burns. Face and hands were the most common sites involved. Burns to these regions were mainly caused by flame and electrical burns. Eye burns comprised 5.5 per cent of the sample and were due to chemicals, gas explosions and electric flash. Twenty-six patients (14 per cent) suffered respiratory injury. Only one patient out of our series of 182 died. Progress has been made in industrial safety in the past few years but carelessness and human error still take their toll.", "output": ["Accidents, Occupational", "Adult", "Australia", "Burns", "Burns, Chemical", "Eye Burns", "Female", "Human", "Male."]}, "Instance License": ["CC BY-NC 4.0"], "prediction": "Industrial Burns"}
+{"id": "task620-a47d3e0376d4449ebfcccb0d7ff4384b", "Task": "task620_ohsumed_medical_subject_headings_answer_generation", "Contributors": "['Saicharan Papani']", "Source": ["ohsumed"], "URL": ["https://huggingface.co/datasets/ohsumed"], "Categories": ["Keyword Tagging"], "Reasoning": [], "Definition": ["Given an abstract, generate a keyword (a noun phrase) that best describes the focus or contribution of the paper. Such keywords can be directly from the given abstract or outside it."], "Positive Examples": [{"input": "Abstract: Some patients converted from ventricular fibrillation to organized rhythms by defibrillation - trained ambulance technicians(EMT - Ds) will refibrillate before hospital arrival.The authors analyzed 271 cases of ventricular fibrillation managed by EMT - Ds working without paramedic back - up.Of 111 patients initially converted to organized rhythms, 19(17 % ) refibrillated, 11(58 % ) of whom were reconverted to perfusing rhythms, including nine of 11(82 % ) who had spontaneous pulses prior to refibrillation.Among patients initially converted to organized rhythms, hospital admission rates were lower for patients who refibrillated than for patients who did not(53 % versus 76 % , P = NS), although discharge rates were virtually identical(37 % and 35 % , respectively).Scene - to - hospital transport times were not predictively associated with either the frequency of refibrillation or patient outcome.Defibrillation - trained EMTs can effectively manage refibrillation with additional shocks and are not at a significant disadvantage when paramedic back - up is not available.", "output": "Ventricular Fibrillation", "explanation": "This term is directly present in the abstract and it is one of the main topic in it. So can be chosen as the medical subject heading."}, {"input": "Abstract: Our results suggest that ethylene oxide retention after sterilization is increased in cuprammonium cellulose plate dialyzers containing potting compound. In contrast, cuprammonium cellulose plate dialyzers without potting compound were characterized by a rapid disappearance of retained ethylene oxide after sterilization. Whether these findings explain the low incidence of SARD with cuprammonium cellulose plate dialyzers that do not contain potting material is a matter for continued study and experimentation.", "output": "Sterilization", "explanation": "This term is directly present in the abstract and it is one of the main topic in it. So can be chosen as the medical subject heading."}], "Negative Examples": [{"input": "Abstract: Our results suggest that ethylene oxide retention after sterilization is increased in cuprammonium cellulose plate dialyzers containing potting compound. In contrast, cuprammonium cellulose plate dialyzers without potting compound were characterized by a rapid disappearance of retained ethylene oxide after sterilization. Whether these findings explain the low incidence of SARD with cuprammonium cellulose plate dialyzers that do not contain potting material is a matter for continued study and experimentation.", "output": "Plasma Volume", "explanation": "This term is not directly present in the abstract and it is no way related to the abstract. So can not be chosen as the medical subject heading. 'Cellulose' can be become a mesh term"}, {"input": "Abstract: Calcium carbonate appears to be as effective as aluminum hydroxide in binding dietary phosphorus in hemodialysis patients. The long-term safety of this medication appears acceptable in view of today's therapeutic options.", "output": "Cellulose", "explanation": "This term is not directly present in the abstract and it is no way related to the abstract. So can not be chosen as the medical subject heading. 'Calcium' can be become a mesh term"}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Scientific Research Papers"], "Instance": {"id": "task620-a47d3e0376d4449ebfcccb0d7ff4384b", "input": "Abstract: The use of atracurium during major abdominal surgery was assessed in 20 infants with hepatic dysfunction caused by biliary atresia. An initial dose of 0.6 mg kg-1 provided excellent intubating conditions in all patients. Subsequent neuromuscular blockade was monitored with a peripheral nerve stimulator and incremental doses of atracurium were given on reappearance of a single twitch. Neuromuscular conduction was allowed to return at the end of surgery and by careful timing of increments it was necessary to antagonize the neuromuscular blockade in only two patients.", "output": ["Anesthesia, Intratracheal", "Atracurium", "Biliary Atresia", "Drug Administration Schedule", "Female", "Human", "Infant", "Infant, Newborn", "Intraoperative Care", "Liver", "Male", "Neuromuscular Blocking Agents"]}, "Instance License": ["CC BY-NC 4.0"], "prediction": "Surgery"}
+{"id": "task1159-29b908c63bea43a9ba38c3284bdfa76a", "Task": "task1159_bard_analogical_reasoning_containers", "Contributors": "['Arjun Ashok']", "Source": ["bard"], "URL": ["https://github.com/NancyFulda/BYU-Analogical-Reasoning-Dataset"], "Categories": ["Word Analogy"], "Reasoning": ["Relational Reasoning", "Commonsense Reasoning", "Analogical Reasoning"], "Definition": ["Two analogies that relate items to the associated containers is given in the form \"A : B. C : ?\". \"A : B\" relates item A to its associated container B. Your task is to replace the question mark (?) with the appropriate container for the given item C, following the \"A : B\" relation."], "Positive Examples": [{"input": "soda : can. water : ?", "output": "bottle", "explanation": "The given analogy relates items to their containers. Soda can be stored in a can. Water can be stored in a bottle."}, {"input": "jam : jar. cereal : ?", "output": "box", "explanation": "The given analogy relates items to their containers. Jam can be stored in a jar. Cereal can be stored in a box."}, {"input": "diapers : bag. honey : ?", "output": "bottle", "explanation": "The given analogy relates items to their containers. Diapers can be stored in a bag. Honey can be stored in a bottle."}], "Negative Examples": [{"input": "trash : can. plates : ?", "output": "wash", "explanation": "The given analogy relates items to their containers. Trash can be stored in a can. But, wash is not the correct answer to plates, since wash is not a container. Further, the answer models an affordance"}, {"input": "detergent : bottle. cereal : ?", "output": "cupboard", "explanation": "The given analogy relates items to their containers. Detergent can be stored in a bottle. But, cupboard is not the right answer for cereal, since cereal is not stored in a cupboard."}, {"input": "picture : frame. poster : ?", "output": "sack", "explanation": "The given analogy relates items to their containers. Pictures can be stored in a frame. But, sack is not the right answer for poster, since posters are not stored in sacks."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Commonsense"], "Instance": {"id": "task1159-29b908c63bea43a9ba38c3284bdfa76a", "input": "chips : bag. money : ?", "output": ["wallet"]}, "Instance License": ["Apache 2.0"], "prediction": "box"}
+{"id": "task1159-b6c13b5642f74c0a9dbcded5910ab8f2", "Task": "task1159_bard_analogical_reasoning_containers", "Contributors": "['Arjun Ashok']", "Source": ["bard"], "URL": ["https://github.com/NancyFulda/BYU-Analogical-Reasoning-Dataset"], "Categories": ["Word Analogy"], "Reasoning": ["Relational Reasoning", "Commonsense Reasoning", "Analogical Reasoning"], "Definition": ["Two analogies that relate items to the associated containers is given in the form \"A : B. C : ?\". \"A : B\" relates item A to its associated container B. Your task is to replace the question mark (?) with the appropriate container for the given item C, following the \"A : B\" relation."], "Positive Examples": [{"input": "soda : can. water : ?", "output": "bottle", "explanation": "The given analogy relates items to their containers. Soda can be stored in a can. Water can be stored in a bottle."}, {"input": "jam : jar. cereal : ?", "output": "box", "explanation": "The given analogy relates items to their containers. Jam can be stored in a jar. Cereal can be stored in a box."}, {"input": "diapers : bag. honey : ?", "output": "bottle", "explanation": "The given analogy relates items to their containers. Diapers can be stored in a bag. Honey can be stored in a bottle."}], "Negative Examples": [{"input": "trash : can. plates : ?", "output": "wash", "explanation": "The given analogy relates items to their containers. Trash can be stored in a can. But, wash is not the correct answer to plates, since wash is not a container. Further, the answer models an affordance"}, {"input": "detergent : bottle. cereal : ?", "output": "cupboard", "explanation": "The given analogy relates items to their containers. Detergent can be stored in a bottle. But, cupboard is not the right answer for cereal, since cereal is not stored in a cupboard."}, {"input": "picture : frame. poster : ?", "output": "sack", "explanation": "The given analogy relates items to their containers. Pictures can be stored in a frame. But, sack is not the right answer for poster, since posters are not stored in sacks."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Commonsense"], "Instance": {"id": "task1159-b6c13b5642f74c0a9dbcded5910ab8f2", "input": "potatoes : sack. poster : ?", "output": ["tube"]}, "Instance License": ["Apache 2.0"], "prediction": "wall"}
+{"id": "task1159-0fef2fc3e1934a77997cadb31c6400a5", "Task": "task1159_bard_analogical_reasoning_containers", "Contributors": "['Arjun Ashok']", "Source": ["bard"], "URL": ["https://github.com/NancyFulda/BYU-Analogical-Reasoning-Dataset"], "Categories": ["Word Analogy"], "Reasoning": ["Relational Reasoning", "Commonsense Reasoning", "Analogical Reasoning"], "Definition": ["Two analogies that relate items to the associated containers is given in the form \"A : B. C : ?\". \"A : B\" relates item A to its associated container B. Your task is to replace the question mark (?) with the appropriate container for the given item C, following the \"A : B\" relation."], "Positive Examples": [{"input": "soda : can. water : ?", "output": "bottle", "explanation": "The given analogy relates items to their containers. Soda can be stored in a can. Water can be stored in a bottle."}, {"input": "jam : jar. cereal : ?", "output": "box", "explanation": "The given analogy relates items to their containers. Jam can be stored in a jar. Cereal can be stored in a box."}, {"input": "diapers : bag. honey : ?", "output": "bottle", "explanation": "The given analogy relates items to their containers. Diapers can be stored in a bag. Honey can be stored in a bottle."}], "Negative Examples": [{"input": "trash : can. plates : ?", "output": "wash", "explanation": "The given analogy relates items to their containers. Trash can be stored in a can. But, wash is not the correct answer to plates, since wash is not a container. Further, the answer models an affordance"}, {"input": "detergent : bottle. cereal : ?", "output": "cupboard", "explanation": "The given analogy relates items to their containers. Detergent can be stored in a bottle. But, cupboard is not the right answer for cereal, since cereal is not stored in a cupboard."}, {"input": "picture : frame. poster : ?", "output": "sack", "explanation": "The given analogy relates items to their containers. Pictures can be stored in a frame. But, sack is not the right answer for poster, since posters are not stored in sacks."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Commonsense"], "Instance": {"id": "task1159-0fef2fc3e1934a77997cadb31c6400a5", "input": "poster : tube. milk : ?", "output": ["jug", "bottle"]}, "Instance License": ["Apache 2.0"], "prediction": "bottle"}
+{"id": "task1159-c944b91c01aa48d7bc0345d9218b12dd", "Task": "task1159_bard_analogical_reasoning_containers", "Contributors": "['Arjun Ashok']", "Source": ["bard"], "URL": ["https://github.com/NancyFulda/BYU-Analogical-Reasoning-Dataset"], "Categories": ["Word Analogy"], "Reasoning": ["Relational Reasoning", "Commonsense Reasoning", "Analogical Reasoning"], "Definition": ["Two analogies that relate items to the associated containers is given in the form \"A : B. C : ?\". \"A : B\" relates item A to its associated container B. Your task is to replace the question mark (?) with the appropriate container for the given item C, following the \"A : B\" relation."], "Positive Examples": [{"input": "soda : can. water : ?", "output": "bottle", "explanation": "The given analogy relates items to their containers. Soda can be stored in a can. Water can be stored in a bottle."}, {"input": "jam : jar. cereal : ?", "output": "box", "explanation": "The given analogy relates items to their containers. Jam can be stored in a jar. Cereal can be stored in a box."}, {"input": "diapers : bag. honey : ?", "output": "bottle", "explanation": "The given analogy relates items to their containers. Diapers can be stored in a bag. Honey can be stored in a bottle."}], "Negative Examples": [{"input": "trash : can. plates : ?", "output": "wash", "explanation": "The given analogy relates items to their containers. Trash can be stored in a can. But, wash is not the correct answer to plates, since wash is not a container. Further, the answer models an affordance"}, {"input": "detergent : bottle. cereal : ?", "output": "cupboard", "explanation": "The given analogy relates items to their containers. Detergent can be stored in a bottle. But, cupboard is not the right answer for cereal, since cereal is not stored in a cupboard."}, {"input": "picture : frame. poster : ?", "output": "sack", "explanation": "The given analogy relates items to their containers. Pictures can be stored in a frame. But, sack is not the right answer for poster, since posters are not stored in sacks."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Commonsense"], "Instance": {"id": "task1159-c944b91c01aa48d7bc0345d9218b12dd", "input": "detergent : bottle. chips : ?", "output": ["bag"]}, "Instance License": ["Apache 2.0"], "prediction": "box"}
+{"id": "task1159-9f7408b60893452f881f7f3a7102fa02", "Task": "task1159_bard_analogical_reasoning_containers", "Contributors": "['Arjun Ashok']", "Source": ["bard"], "URL": ["https://github.com/NancyFulda/BYU-Analogical-Reasoning-Dataset"], "Categories": ["Word Analogy"], "Reasoning": ["Relational Reasoning", "Commonsense Reasoning", "Analogical Reasoning"], "Definition": ["Two analogies that relate items to the associated containers is given in the form \"A : B. C : ?\". \"A : B\" relates item A to its associated container B. Your task is to replace the question mark (?) with the appropriate container for the given item C, following the \"A : B\" relation."], "Positive Examples": [{"input": "soda : can. water : ?", "output": "bottle", "explanation": "The given analogy relates items to their containers. Soda can be stored in a can. Water can be stored in a bottle."}, {"input": "jam : jar. cereal : ?", "output": "box", "explanation": "The given analogy relates items to their containers. Jam can be stored in a jar. Cereal can be stored in a box."}, {"input": "diapers : bag. honey : ?", "output": "bottle", "explanation": "The given analogy relates items to their containers. Diapers can be stored in a bag. Honey can be stored in a bottle."}], "Negative Examples": [{"input": "trash : can. plates : ?", "output": "wash", "explanation": "The given analogy relates items to their containers. Trash can be stored in a can. But, wash is not the correct answer to plates, since wash is not a container. Further, the answer models an affordance"}, {"input": "detergent : bottle. cereal : ?", "output": "cupboard", "explanation": "The given analogy relates items to their containers. Detergent can be stored in a bottle. But, cupboard is not the right answer for cereal, since cereal is not stored in a cupboard."}, {"input": "picture : frame. poster : ?", "output": "sack", "explanation": "The given analogy relates items to their containers. Pictures can be stored in a frame. But, sack is not the right answer for poster, since posters are not stored in sacks."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Commonsense"], "Instance": {"id": "task1159-9f7408b60893452f881f7f3a7102fa02", "input": "carrots : bag. honey : ?", "output": ["jar", "bottle"]}, "Instance License": ["Apache 2.0"], "prediction": "box"}
+{"id": "task500-fda70a2e28a8468eb124c46158b1c4f4", "Task": "task500_scruples_anecdotes_title_generation", "Contributors": "['Kuntal Kumar Pal']", "Source": ["scruples"], "URL": ["https://github.com/allenai/scruples"], "Categories": ["Title Generation"], "Reasoning": [], "Definition": ["Given a real-life anecdote of a complex ethical situation, generate a suitable title that describes the main event/root cause of the situation. Imagine that the given text is a social media post, and you have to write the title of the post, so the users can decide to read the main text or not."], "Positive Examples": [{"input": "My boyfriend (well just call him M) and I are creators on Instagram (he is also on TikTok). I'm a digital and traditional artist and in one of my classes we create t shirts and things (socks, lanyards, water bottles, stickers, you name it). I'm a big fan of putting my art on t shirts so I can sell them.\n\nM wanted to make some posts for TikTok and wanted to use the shirt I made today. My one personal rule is that if the shirt isn't being given to someone else, then I wear it first (this is because I know I wont get it back. Ive made one other shirt that I've worn, and he wore it for a week and hasn't given it back.) So I told him no, because I haven't worn the shirt yet. \n\nM proceeded to complain about not having content to post, and how his IG post today didn't get any engagement, saying \"of course you dont know, because you never look.\"\n\nAm I the asshole for wanting to wear the shirt I made just once?", "output": "wanting to wear a shirt", "explanation": "The paragraph describes an argument of the author with her boyfriend regarding not wanting to give the shirt she just made before wearing herself. This desire to wear the shirt raises the ethical situation."}, {"input": "Pretty much was hanging out with two friends. I was watching the Lakers game. They won at the very last minute and I immediately hopped up and celebrated. Before I could even finish celebrating one friend started going on about how the Lakers suck. It just pissed me off so much I screamed at her to get out my room until she left. \n\n\nShe knows I'm a huge fan and she likes them too. She was only saying it to antagonize me. Am I the dick here?", "output": "going off on a friend for making a comment about my sports team", "explanation": "The root cause of the author's action is his friend commenting about his favorite sports team. Hence this is the main event that created the ethical situation"}], "Negative Examples": [{"input": "So. Bit of context here. Me and my roommate (25 y/o males) work and live together and we're both pretty lazy. For the new year I decided to start waking up earlier and walking to work and I've started cooking breakfast to make sure the day gets started in the right way. This week I've been making scrambled eggs (american style), toast and avocado with -&gt; FRESH PARSLEY &lt;- sprinkled on top of the eggs.\n\nEvery morning this week I've woken up my roommate with a really really pleasant surprise of home cooked food. He always acts really grateful, and I'm happy to do it because I enjoy making food... However. After cleaning the plates today I noticed that he had hid ALL of the parsley I had sprinkled on his eggs under his cup.\n\nParsley goes with eggs. He's making his morning experience WORSE by eating around it... and then trying to hide the evidence- WEIRD MUCH??\n\nSo tomorrow I am going to put more parsley on the eggs I make. I'm actually going to put more on than I put yesterday. So yeah. Sorry if this is the wrong format but can you just honestly tell me if I am the asshole in this situation?? I will update this post as developments happen.", "output": "preparing breakfast for my roommate", "explanation": "The event of adding more parsley is the root cause of the ethical situation. This is because, it is clear that in future, the author will attempt to put more parsley in roommate's breakfast being aware that he doesn't like parsley. So even though preparing breakfast is a relevant action, it is not the exact event which raises the situation."}, {"input": "My mom suggested instead of Christmas presents we donate it all to charities, specifically helping the fire victims here in CA. I budgeted my holiday spending anticipating clothes and cooking supplies from them, and I would rather get the tax deduction than them if/when I donate to help. My siblings are already on board and said it's something we all should do given what we have but I disagree. It doesn't help that I'm the only Democrat and me feeling like a hypocrite for not wanting this. ", "output": "I'm the only Democrat", "explanation": "The author's political affiliation is not important here. The situation is about the author's decision of telling his parents that he doesn't like his Christmas presents to be giving to charity."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Story", "Narrative"], "Instance": {"id": "task500-fda70a2e28a8468eb124c46158b1c4f4", "input": "Throwaway, mobile formatting, you know the drill.\n\nFor context, I\u2019m 17M she\u2019s 16F. I am currently being diagnosed for gender identity disorder, but I\u2019m still into girls. She has no idea about any of this and really just assumes I\u2019m normal. My current situation lies in which I feel like I\u2019m lying to her by keeping the real me hidden. She never asked, and I don\u2019t really want many people in my life knowing about this.\n\nWe\u2019ve been dating for around 6 months now, and it\u2019s really going well. We have been friends for about 3 years at this point, and I\u2019m glad we\u2019ve moved on to this stage. It\u2019s her first relationship and both of us have been much happier after we started dating.\n\nShe fell in love with the person I am not, and I\u2019m too afraid to just break her heart and just end the relationship without any reason, or at least for her it won\u2019t have any reason. Am I doing the right thing of keeping it going or am I being selfish and keeping it cause I also love her?", "output": ["keeping my relationship going despite knowing it won't last"]}, "Instance License": ["Apache 2.0"], "prediction": "lying to her"}
+{"id": "task500-e76bf4efad7c4b90b78aaa2e5ed7796d", "Task": "task500_scruples_anecdotes_title_generation", "Contributors": "['Kuntal Kumar Pal']", "Source": ["scruples"], "URL": ["https://github.com/allenai/scruples"], "Categories": ["Title Generation"], "Reasoning": [], "Definition": ["Given a real-life anecdote of a complex ethical situation, generate a suitable title that describes the main event/root cause of the situation. Imagine that the given text is a social media post, and you have to write the title of the post, so the users can decide to read the main text or not."], "Positive Examples": [{"input": "My boyfriend (well just call him M) and I are creators on Instagram (he is also on TikTok). I'm a digital and traditional artist and in one of my classes we create t shirts and things (socks, lanyards, water bottles, stickers, you name it). I'm a big fan of putting my art on t shirts so I can sell them.\n\nM wanted to make some posts for TikTok and wanted to use the shirt I made today. My one personal rule is that if the shirt isn't being given to someone else, then I wear it first (this is because I know I wont get it back. Ive made one other shirt that I've worn, and he wore it for a week and hasn't given it back.) So I told him no, because I haven't worn the shirt yet. \n\nM proceeded to complain about not having content to post, and how his IG post today didn't get any engagement, saying \"of course you dont know, because you never look.\"\n\nAm I the asshole for wanting to wear the shirt I made just once?", "output": "wanting to wear a shirt", "explanation": "The paragraph describes an argument of the author with her boyfriend regarding not wanting to give the shirt she just made before wearing herself. This desire to wear the shirt raises the ethical situation."}, {"input": "Pretty much was hanging out with two friends. I was watching the Lakers game. They won at the very last minute and I immediately hopped up and celebrated. Before I could even finish celebrating one friend started going on about how the Lakers suck. It just pissed me off so much I screamed at her to get out my room until she left. \n\n\nShe knows I'm a huge fan and she likes them too. She was only saying it to antagonize me. Am I the dick here?", "output": "going off on a friend for making a comment about my sports team", "explanation": "The root cause of the author's action is his friend commenting about his favorite sports team. Hence this is the main event that created the ethical situation"}], "Negative Examples": [{"input": "So. Bit of context here. Me and my roommate (25 y/o males) work and live together and we're both pretty lazy. For the new year I decided to start waking up earlier and walking to work and I've started cooking breakfast to make sure the day gets started in the right way. This week I've been making scrambled eggs (american style), toast and avocado with -&gt; FRESH PARSLEY &lt;- sprinkled on top of the eggs.\n\nEvery morning this week I've woken up my roommate with a really really pleasant surprise of home cooked food. He always acts really grateful, and I'm happy to do it because I enjoy making food... However. After cleaning the plates today I noticed that he had hid ALL of the parsley I had sprinkled on his eggs under his cup.\n\nParsley goes with eggs. He's making his morning experience WORSE by eating around it... and then trying to hide the evidence- WEIRD MUCH??\n\nSo tomorrow I am going to put more parsley on the eggs I make. I'm actually going to put more on than I put yesterday. So yeah. Sorry if this is the wrong format but can you just honestly tell me if I am the asshole in this situation?? I will update this post as developments happen.", "output": "preparing breakfast for my roommate", "explanation": "The event of adding more parsley is the root cause of the ethical situation. This is because, it is clear that in future, the author will attempt to put more parsley in roommate's breakfast being aware that he doesn't like parsley. So even though preparing breakfast is a relevant action, it is not the exact event which raises the situation."}, {"input": "My mom suggested instead of Christmas presents we donate it all to charities, specifically helping the fire victims here in CA. I budgeted my holiday spending anticipating clothes and cooking supplies from them, and I would rather get the tax deduction than them if/when I donate to help. My siblings are already on board and said it's something we all should do given what we have but I disagree. It doesn't help that I'm the only Democrat and me feeling like a hypocrite for not wanting this. ", "output": "I'm the only Democrat", "explanation": "The author's political affiliation is not important here. The situation is about the author's decision of telling his parents that he doesn't like his Christmas presents to be giving to charity."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Story", "Narrative"], "Instance": {"id": "task500-e76bf4efad7c4b90b78aaa2e5ed7796d", "input": "Back story is I put in for a job where I'll be traveling alot 5days in hotel weekends at home. I have a wife, 3yr old and and a 7month old. Before I ever applied I asked my wife told her everything  about it she said it sounded good (I make roughly 650 dollars more now) plus paid food and has when I'm away, so hugh savings all around. Fast forward when I get paper work saying  I got the job before I signed and told them I was committed to at least 18months I asked her yet again and she was still fine with it.  Now I've been training for last 5 weeks and only been home 3 days cause they flew me to anouther state and she's starting to say I dont love her and I'm ignoring her because I cant respond to ever text or talk to phone for 5hrs straight.  I tell her I love her everyday and facetime when I'm not doing work I watch 0 TV now or play any games all my time is on phone or work . Now the problem is she thinks I dont love her anymore because I dont talk to her enough.", "output": ["taking a new job"]}, "Instance License": ["Apache 2.0"], "prediction": "ignoring wife"}
+{"id": "task500-1248cc0472184357b51e7702bf971a2b", "Task": "task500_scruples_anecdotes_title_generation", "Contributors": "['Kuntal Kumar Pal']", "Source": ["scruples"], "URL": ["https://github.com/allenai/scruples"], "Categories": ["Title Generation"], "Reasoning": [], "Definition": ["Given a real-life anecdote of a complex ethical situation, generate a suitable title that describes the main event/root cause of the situation. Imagine that the given text is a social media post, and you have to write the title of the post, so the users can decide to read the main text or not."], "Positive Examples": [{"input": "My boyfriend (well just call him M) and I are creators on Instagram (he is also on TikTok). I'm a digital and traditional artist and in one of my classes we create t shirts and things (socks, lanyards, water bottles, stickers, you name it). I'm a big fan of putting my art on t shirts so I can sell them.\n\nM wanted to make some posts for TikTok and wanted to use the shirt I made today. My one personal rule is that if the shirt isn't being given to someone else, then I wear it first (this is because I know I wont get it back. Ive made one other shirt that I've worn, and he wore it for a week and hasn't given it back.) So I told him no, because I haven't worn the shirt yet. \n\nM proceeded to complain about not having content to post, and how his IG post today didn't get any engagement, saying \"of course you dont know, because you never look.\"\n\nAm I the asshole for wanting to wear the shirt I made just once?", "output": "wanting to wear a shirt", "explanation": "The paragraph describes an argument of the author with her boyfriend regarding not wanting to give the shirt she just made before wearing herself. This desire to wear the shirt raises the ethical situation."}, {"input": "Pretty much was hanging out with two friends. I was watching the Lakers game. They won at the very last minute and I immediately hopped up and celebrated. Before I could even finish celebrating one friend started going on about how the Lakers suck. It just pissed me off so much I screamed at her to get out my room until she left. \n\n\nShe knows I'm a huge fan and she likes them too. She was only saying it to antagonize me. Am I the dick here?", "output": "going off on a friend for making a comment about my sports team", "explanation": "The root cause of the author's action is his friend commenting about his favorite sports team. Hence this is the main event that created the ethical situation"}], "Negative Examples": [{"input": "So. Bit of context here. Me and my roommate (25 y/o males) work and live together and we're both pretty lazy. For the new year I decided to start waking up earlier and walking to work and I've started cooking breakfast to make sure the day gets started in the right way. This week I've been making scrambled eggs (american style), toast and avocado with -&gt; FRESH PARSLEY &lt;- sprinkled on top of the eggs.\n\nEvery morning this week I've woken up my roommate with a really really pleasant surprise of home cooked food. He always acts really grateful, and I'm happy to do it because I enjoy making food... However. After cleaning the plates today I noticed that he had hid ALL of the parsley I had sprinkled on his eggs under his cup.\n\nParsley goes with eggs. He's making his morning experience WORSE by eating around it... and then trying to hide the evidence- WEIRD MUCH??\n\nSo tomorrow I am going to put more parsley on the eggs I make. I'm actually going to put more on than I put yesterday. So yeah. Sorry if this is the wrong format but can you just honestly tell me if I am the asshole in this situation?? I will update this post as developments happen.", "output": "preparing breakfast for my roommate", "explanation": "The event of adding more parsley is the root cause of the ethical situation. This is because, it is clear that in future, the author will attempt to put more parsley in roommate's breakfast being aware that he doesn't like parsley. So even though preparing breakfast is a relevant action, it is not the exact event which raises the situation."}, {"input": "My mom suggested instead of Christmas presents we donate it all to charities, specifically helping the fire victims here in CA. I budgeted my holiday spending anticipating clothes and cooking supplies from them, and I would rather get the tax deduction than them if/when I donate to help. My siblings are already on board and said it's something we all should do given what we have but I disagree. It doesn't help that I'm the only Democrat and me feeling like a hypocrite for not wanting this. ", "output": "I'm the only Democrat", "explanation": "The author's political affiliation is not important here. The situation is about the author's decision of telling his parents that he doesn't like his Christmas presents to be giving to charity."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Story", "Narrative"], "Instance": {"id": "task500-1248cc0472184357b51e7702bf971a2b", "input": "The title is pretty self-explanatory. I'm currently pregnant at a really bad point in my life. Adoption isn't an option for a number of reasons. While my husband has been 100% supportive, I'm definitely seeking out a female perspective. Husband is fine with whatever I decide (in terms of telling friends/family for support reasons), but I'm reluctant because friend has a newly-acquired stepdaughter who she cares very deeply for. On top of that, friend probably can't have kids of her own due to medical stuff. I want support, but I don't want to overstep the need for support that my friend has... Would I be the asshole if I told my friend about my situation? Or should I just keep to myself and seek alternative outlets? \n\nI really don't want this to turn into a pro-life/pro-choice argument, so please stay away from those points. I've already made the decision, I just want to know if it would be selfish to tell somebody I'm close to (who probably can't have little ones).\n\nAll judgements welcome!", "output": ["telling my close friend that I'm getting an abortion"]}, "Instance License": ["Apache 2.0"], "prediction": "I'm pregnant and need to know what other people think"}
+{"id": "task500-a0acf21c87fc44afa2495938fc6cf136", "Task": "task500_scruples_anecdotes_title_generation", "Contributors": "['Kuntal Kumar Pal']", "Source": ["scruples"], "URL": ["https://github.com/allenai/scruples"], "Categories": ["Title Generation"], "Reasoning": [], "Definition": ["Given a real-life anecdote of a complex ethical situation, generate a suitable title that describes the main event/root cause of the situation. Imagine that the given text is a social media post, and you have to write the title of the post, so the users can decide to read the main text or not."], "Positive Examples": [{"input": "My boyfriend (well just call him M) and I are creators on Instagram (he is also on TikTok). I'm a digital and traditional artist and in one of my classes we create t shirts and things (socks, lanyards, water bottles, stickers, you name it). I'm a big fan of putting my art on t shirts so I can sell them.\n\nM wanted to make some posts for TikTok and wanted to use the shirt I made today. My one personal rule is that if the shirt isn't being given to someone else, then I wear it first (this is because I know I wont get it back. Ive made one other shirt that I've worn, and he wore it for a week and hasn't given it back.) So I told him no, because I haven't worn the shirt yet. \n\nM proceeded to complain about not having content to post, and how his IG post today didn't get any engagement, saying \"of course you dont know, because you never look.\"\n\nAm I the asshole for wanting to wear the shirt I made just once?", "output": "wanting to wear a shirt", "explanation": "The paragraph describes an argument of the author with her boyfriend regarding not wanting to give the shirt she just made before wearing herself. This desire to wear the shirt raises the ethical situation."}, {"input": "Pretty much was hanging out with two friends. I was watching the Lakers game. They won at the very last minute and I immediately hopped up and celebrated. Before I could even finish celebrating one friend started going on about how the Lakers suck. It just pissed me off so much I screamed at her to get out my room until she left. \n\n\nShe knows I'm a huge fan and she likes them too. She was only saying it to antagonize me. Am I the dick here?", "output": "going off on a friend for making a comment about my sports team", "explanation": "The root cause of the author's action is his friend commenting about his favorite sports team. Hence this is the main event that created the ethical situation"}], "Negative Examples": [{"input": "So. Bit of context here. Me and my roommate (25 y/o males) work and live together and we're both pretty lazy. For the new year I decided to start waking up earlier and walking to work and I've started cooking breakfast to make sure the day gets started in the right way. This week I've been making scrambled eggs (american style), toast and avocado with -&gt; FRESH PARSLEY &lt;- sprinkled on top of the eggs.\n\nEvery morning this week I've woken up my roommate with a really really pleasant surprise of home cooked food. He always acts really grateful, and I'm happy to do it because I enjoy making food... However. After cleaning the plates today I noticed that he had hid ALL of the parsley I had sprinkled on his eggs under his cup.\n\nParsley goes with eggs. He's making his morning experience WORSE by eating around it... and then trying to hide the evidence- WEIRD MUCH??\n\nSo tomorrow I am going to put more parsley on the eggs I make. I'm actually going to put more on than I put yesterday. So yeah. Sorry if this is the wrong format but can you just honestly tell me if I am the asshole in this situation?? I will update this post as developments happen.", "output": "preparing breakfast for my roommate", "explanation": "The event of adding more parsley is the root cause of the ethical situation. This is because, it is clear that in future, the author will attempt to put more parsley in roommate's breakfast being aware that he doesn't like parsley. So even though preparing breakfast is a relevant action, it is not the exact event which raises the situation."}, {"input": "My mom suggested instead of Christmas presents we donate it all to charities, specifically helping the fire victims here in CA. I budgeted my holiday spending anticipating clothes and cooking supplies from them, and I would rather get the tax deduction than them if/when I donate to help. My siblings are already on board and said it's something we all should do given what we have but I disagree. It doesn't help that I'm the only Democrat and me feeling like a hypocrite for not wanting this. ", "output": "I'm the only Democrat", "explanation": "The author's political affiliation is not important here. The situation is about the author's decision of telling his parents that he doesn't like his Christmas presents to be giving to charity."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Story", "Narrative"], "Instance": {"id": "task500-a0acf21c87fc44afa2495938fc6cf136", "input": "I usually tell my SO I am off my period a week after I actually finished bleeding because sometimes I still have some spotting episodes. To just avoid having sex while I'm accidentally bleeding, I just tell him a week later.\n\nOn Monday my SO and I had some plans for some sexy time. We were supposed to go two rounds but after our first round where I gave him oral he ended up falling asleep. No sexy times insued after. \n\nThe same day he acquires a new video game. It's not a problem until I start feeling in the mood but he just won't put the controller down. \n\nI work 6 nights And I am on my feet 100% of the time. I usually get home very exhausted and paired with all the chores I have to do on the daily, I feel like if he would help out a little i wouldn't be so frustrated. \n\nAlso I work nights so I get home fairly early (around 2) in the morning. He is sometimes on it until way after I have fallen asleep and it's morning time. \n\nI have absolutely no problem with it at all, unless we made plans to have sex then yes I would feel annoyed. \n\nLast night, he finally stopped playing his game. And we were watching a movie. In the movie they were making sexual innuendos and he turned and looked at me and said \"what about sex stuff? ;)\" (I think he was being sexually suggestive). \nBut I guess I'm dumb because I can't read cues. And he wasn't being straight up. \nAnd he had already ruined my mood since the beginning of this week. \n\nFast forward to this morning,\nHe asks me how I'm doing and I tell him I'm starting to feel my period pains coming (heavy breasts and hurting lower back). And he said \"I swear you just got off your period. I don't know what's going on with you\"\n\nSo now I feel really bad and targeted. I can't control my body from doing what it's supposed to do. I feel so frustrated and annoyed. I want to cry but somehow I feel like it's just my hormones messing with me. \n\nAITA for not being in the mood or in sync with him when he's ready to have sex?", "output": ["not being in the mood for sex"]}, "Instance License": ["Apache 2.0"], "prediction": "not being in the mood"}
+{"id": "task500-fd09bd58ef1c4ea78d3bf9cb615604ce", "Task": "task500_scruples_anecdotes_title_generation", "Contributors": "['Kuntal Kumar Pal']", "Source": ["scruples"], "URL": ["https://github.com/allenai/scruples"], "Categories": ["Title Generation"], "Reasoning": [], "Definition": ["Given a real-life anecdote of a complex ethical situation, generate a suitable title that describes the main event/root cause of the situation. Imagine that the given text is a social media post, and you have to write the title of the post, so the users can decide to read the main text or not."], "Positive Examples": [{"input": "My boyfriend (well just call him M) and I are creators on Instagram (he is also on TikTok). I'm a digital and traditional artist and in one of my classes we create t shirts and things (socks, lanyards, water bottles, stickers, you name it). I'm a big fan of putting my art on t shirts so I can sell them.\n\nM wanted to make some posts for TikTok and wanted to use the shirt I made today. My one personal rule is that if the shirt isn't being given to someone else, then I wear it first (this is because I know I wont get it back. Ive made one other shirt that I've worn, and he wore it for a week and hasn't given it back.) So I told him no, because I haven't worn the shirt yet. \n\nM proceeded to complain about not having content to post, and how his IG post today didn't get any engagement, saying \"of course you dont know, because you never look.\"\n\nAm I the asshole for wanting to wear the shirt I made just once?", "output": "wanting to wear a shirt", "explanation": "The paragraph describes an argument of the author with her boyfriend regarding not wanting to give the shirt she just made before wearing herself. This desire to wear the shirt raises the ethical situation."}, {"input": "Pretty much was hanging out with two friends. I was watching the Lakers game. They won at the very last minute and I immediately hopped up and celebrated. Before I could even finish celebrating one friend started going on about how the Lakers suck. It just pissed me off so much I screamed at her to get out my room until she left. \n\n\nShe knows I'm a huge fan and she likes them too. She was only saying it to antagonize me. Am I the dick here?", "output": "going off on a friend for making a comment about my sports team", "explanation": "The root cause of the author's action is his friend commenting about his favorite sports team. Hence this is the main event that created the ethical situation"}], "Negative Examples": [{"input": "So. Bit of context here. Me and my roommate (25 y/o males) work and live together and we're both pretty lazy. For the new year I decided to start waking up earlier and walking to work and I've started cooking breakfast to make sure the day gets started in the right way. This week I've been making scrambled eggs (american style), toast and avocado with -&gt; FRESH PARSLEY &lt;- sprinkled on top of the eggs.\n\nEvery morning this week I've woken up my roommate with a really really pleasant surprise of home cooked food. He always acts really grateful, and I'm happy to do it because I enjoy making food... However. After cleaning the plates today I noticed that he had hid ALL of the parsley I had sprinkled on his eggs under his cup.\n\nParsley goes with eggs. He's making his morning experience WORSE by eating around it... and then trying to hide the evidence- WEIRD MUCH??\n\nSo tomorrow I am going to put more parsley on the eggs I make. I'm actually going to put more on than I put yesterday. So yeah. Sorry if this is the wrong format but can you just honestly tell me if I am the asshole in this situation?? I will update this post as developments happen.", "output": "preparing breakfast for my roommate", "explanation": "The event of adding more parsley is the root cause of the ethical situation. This is because, it is clear that in future, the author will attempt to put more parsley in roommate's breakfast being aware that he doesn't like parsley. So even though preparing breakfast is a relevant action, it is not the exact event which raises the situation."}, {"input": "My mom suggested instead of Christmas presents we donate it all to charities, specifically helping the fire victims here in CA. I budgeted my holiday spending anticipating clothes and cooking supplies from them, and I would rather get the tax deduction than them if/when I donate to help. My siblings are already on board and said it's something we all should do given what we have but I disagree. It doesn't help that I'm the only Democrat and me feeling like a hypocrite for not wanting this. ", "output": "I'm the only Democrat", "explanation": "The author's political affiliation is not important here. The situation is about the author's decision of telling his parents that he doesn't like his Christmas presents to be giving to charity."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Story", "Narrative"], "Instance": {"id": "task500-fd09bd58ef1c4ea78d3bf9cb615604ce", "input": "So my husband and I had a rough year. He cheated, i caught him, we tried to work through it but it blew up so we separated and went to see counselors and have worked through everything. \n\nSo before all of that happened my husband and i had been getting really close with one of my husbands coworkers and his wife and family. We hung out a lot, at least once a week and we texted every day. We would have them over for holidays and even if my husband was working I'd go hang out with them without him. \n\nMe and his coworker really became good friends more than me and his wife because we had a lot in common and the main thing was we had the same sense of humor. A kind of raunchy humor and we would send each other funny videos or memes all the time. \n\nBut they were really like family. If we needed advice, we'd go to them. If they needed anything they could come to us. \n\nSo when I caught my husband cheating I was devastated. I went to them and confided a lot in them. As my husband and I tried to work through it they were there for us helping us both with all the things we were feeling. But when it all blew up and we separated they immediately boxed me out. It was radio silence. I reached out to them and nothing. They never answered the phone or called back or replied to my texts. They were my only friends so I was completely alone. They never once were there for me.\n\nSo after me and my husband started to figure things out and started living together again they invited my husband to a bar/restaurant. I said I wasn't ready to see them again so I stayed home. When he got there they started begging him to invite me. I said no but I was trying to put my best foot forward for my husband and I eventually caved and went. \n\nI was not very nice. I basically gave them the cold shoulder. They asked how I was doing and I said I was doing fine on my own. And then they got defensive. He(coworker) said the reason they picked my husbands side was because they work together. And then he told me to stop being mad because I was just looking for things to be mad about. I ignored this and left.\n\nAfter that he(coworker) started spamming me with funny videos and memes. Not any real conversation just memes. I'd say lol or funny but I eventually stopped replying altogether. \n\nIt went on for a bit but I got tired of all these raunchy videos. So I told him that I was sorry I was rude the day at the restaurant but if he thought of me as just his coworkers wife, then he shouldn't be sending me those things anymore. I told him he was my best friend and I had confided a lot in him and I felt abandoned when he and his wife stopped talking to me.\n\nHis reply was \"it didnt have to be like this but if that's how you want it to be fine. All you have to do is apologize and we can fix our friendship.\"\n\nI didnt text back. I dont know what else to apologize for. I've asked my husband and he doesnt know either. Am I being an asshole? Am I missing something. I miss their friendship every day but I feel like they aren't good friends. Am I crazy? \n\n", "output": ["ending a friendship"]}, "Instance License": ["Apache 2.0"], "prediction": "I was devastated when I caught my husband cheating. I went to them and confided a lot in them. They were there for me helping me work through it. They were there for me helping me both with all the things we were feeling."}
+{"id": "task890-a2ee7b6374034ab1b7efa6c8fd9ff44d", "Task": "task890_gcwd_classification", "Contributors": "['Selvaganesh Muthu']", "Source": ["gwsd"], "URL": ["https://github.com/yiweiluo/GWStance"], "Categories": ["Textual Entailment"], "Reasoning": ["Textual Entailment"], "Definition": ["Read the passage and find if the passage agrees, disagrees, or has a neutral stance on whether Global warming is caused by human activities. Answer only with keyword (a) agrees - if passage agrees with the target (b) disagrees - if passage disagrees with the target (c) neutral - if the given passage neither agrees nor disagrees with the target. You don't need to use external knowledge in this task, and you have to answer based on the given passage."], "Positive Examples": [{"input": "Most global warming is natural and even if there had been no Industrial Revolution current global temperatures would be almost exactly the same as they are now.", "output": "disagrees", "explanation": "The sentence explicitly states the global warming is natural. It also adds the temperatures would be the same even without industries. Therefore the sentence disagrees with the target."}, {"input": "All fossil fuel use needs to be regulated to reduce global warming.", "output": "agrees", "explanation": "The sentence accepts that global warming exists and states that with the reduction of fossil fuels we can reduce global warming."}, {"input": "There is no solid evidence of global warming.", "output": "disagrees", "explanation": "The sentence disagrees with the fact that global warming exists at all. So it is clear that the writer disagrees with the target."}, {"input": "The meltdown results from the complex interaction of players including emissions-driven climate change, warm air and water, and shrinking ice area.", "output": "neutral", "explanation": "The sentence puts equal weight on both human and natural causes for global warming. So this sentence has a neutral stance."}], "Negative Examples": [{"input": "We can not live on fossil fuel forever.", "output": "disagrees", "explanation": "The sentence only suggests that we cannot live on fossil fuels forever. It does not provide any information about global warming. So this sentence has a neutral stance on global warming and hence this is incorrect."}, {"input": "More warming leads to more fires, which release more carbon, which causes more warming, and so on.", "output": "I don't agree", "explanation": "The task definition clearly states that you need to reply with \"agrees\", \"disagrees\" and \"neutral\" but the output has selected a different option. So this is an incorrect answer."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Economics"], "Instance": {"id": "task890-a2ee7b6374034ab1b7efa6c8fd9ff44d", "input": "While many scientists are wary of drawing firm links between any particular storm and climate change, a rising sea level adds to the destructiveness of storm surges, and a warming atmosphere holds more moisture, leading to more rain.", "output": ["agrees"]}, "Instance License": ["Unknown"], "prediction": "agrees"}
+{"id": "task890-e585dcb97df949dbb5904e9e574c093e", "Task": "task890_gcwd_classification", "Contributors": "['Selvaganesh Muthu']", "Source": ["gwsd"], "URL": ["https://github.com/yiweiluo/GWStance"], "Categories": ["Textual Entailment"], "Reasoning": ["Textual Entailment"], "Definition": ["Read the passage and find if the passage agrees, disagrees, or has a neutral stance on whether Global warming is caused by human activities. Answer only with keyword (a) agrees - if passage agrees with the target (b) disagrees - if passage disagrees with the target (c) neutral - if the given passage neither agrees nor disagrees with the target. You don't need to use external knowledge in this task, and you have to answer based on the given passage."], "Positive Examples": [{"input": "Most global warming is natural and even if there had been no Industrial Revolution current global temperatures would be almost exactly the same as they are now.", "output": "disagrees", "explanation": "The sentence explicitly states the global warming is natural. It also adds the temperatures would be the same even without industries. Therefore the sentence disagrees with the target."}, {"input": "All fossil fuel use needs to be regulated to reduce global warming.", "output": "agrees", "explanation": "The sentence accepts that global warming exists and states that with the reduction of fossil fuels we can reduce global warming."}, {"input": "There is no solid evidence of global warming.", "output": "disagrees", "explanation": "The sentence disagrees with the fact that global warming exists at all. So it is clear that the writer disagrees with the target."}, {"input": "The meltdown results from the complex interaction of players including emissions-driven climate change, warm air and water, and shrinking ice area.", "output": "neutral", "explanation": "The sentence puts equal weight on both human and natural causes for global warming. So this sentence has a neutral stance."}], "Negative Examples": [{"input": "We can not live on fossil fuel forever.", "output": "disagrees", "explanation": "The sentence only suggests that we cannot live on fossil fuels forever. It does not provide any information about global warming. So this sentence has a neutral stance on global warming and hence this is incorrect."}, {"input": "More warming leads to more fires, which release more carbon, which causes more warming, and so on.", "output": "I don't agree", "explanation": "The task definition clearly states that you need to reply with \"agrees\", \"disagrees\" and \"neutral\" but the output has selected a different option. So this is an incorrect answer."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Economics"], "Instance": {"id": "task890-e585dcb97df949dbb5904e9e574c093e", "input": "Greenland is not only melting.", "output": ["neutral"]}, "Instance License": ["Unknown"], "prediction": "agrees"}
+{"id": "task890-aee141f6b0bb415d862212dab9c9dc32", "Task": "task890_gcwd_classification", "Contributors": "['Selvaganesh Muthu']", "Source": ["gwsd"], "URL": ["https://github.com/yiweiluo/GWStance"], "Categories": ["Textual Entailment"], "Reasoning": ["Textual Entailment"], "Definition": ["Read the passage and find if the passage agrees, disagrees, or has a neutral stance on whether Global warming is caused by human activities. Answer only with keyword (a) agrees - if passage agrees with the target (b) disagrees - if passage disagrees with the target (c) neutral - if the given passage neither agrees nor disagrees with the target. You don't need to use external knowledge in this task, and you have to answer based on the given passage."], "Positive Examples": [{"input": "Most global warming is natural and even if there had been no Industrial Revolution current global temperatures would be almost exactly the same as they are now.", "output": "disagrees", "explanation": "The sentence explicitly states the global warming is natural. It also adds the temperatures would be the same even without industries. Therefore the sentence disagrees with the target."}, {"input": "All fossil fuel use needs to be regulated to reduce global warming.", "output": "agrees", "explanation": "The sentence accepts that global warming exists and states that with the reduction of fossil fuels we can reduce global warming."}, {"input": "There is no solid evidence of global warming.", "output": "disagrees", "explanation": "The sentence disagrees with the fact that global warming exists at all. So it is clear that the writer disagrees with the target."}, {"input": "The meltdown results from the complex interaction of players including emissions-driven climate change, warm air and water, and shrinking ice area.", "output": "neutral", "explanation": "The sentence puts equal weight on both human and natural causes for global warming. So this sentence has a neutral stance."}], "Negative Examples": [{"input": "We can not live on fossil fuel forever.", "output": "disagrees", "explanation": "The sentence only suggests that we cannot live on fossil fuels forever. It does not provide any information about global warming. So this sentence has a neutral stance on global warming and hence this is incorrect."}, {"input": "More warming leads to more fires, which release more carbon, which causes more warming, and so on.", "output": "I don't agree", "explanation": "The task definition clearly states that you need to reply with \"agrees\", \"disagrees\" and \"neutral\" but the output has selected a different option. So this is an incorrect answer."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Economics"], "Instance": {"id": "task890-aee141f6b0bb415d862212dab9c9dc32", "input": "Global warming is going to cause more wars.", "output": ["agrees"]}, "Instance License": ["Unknown"], "prediction": "disagrees"}
+{"id": "task890-f899a524865e40c39bfbb7c443b0d262", "Task": "task890_gcwd_classification", "Contributors": "['Selvaganesh Muthu']", "Source": ["gwsd"], "URL": ["https://github.com/yiweiluo/GWStance"], "Categories": ["Textual Entailment"], "Reasoning": ["Textual Entailment"], "Definition": ["Read the passage and find if the passage agrees, disagrees, or has a neutral stance on whether Global warming is caused by human activities. Answer only with keyword (a) agrees - if passage agrees with the target (b) disagrees - if passage disagrees with the target (c) neutral - if the given passage neither agrees nor disagrees with the target. You don't need to use external knowledge in this task, and you have to answer based on the given passage."], "Positive Examples": [{"input": "Most global warming is natural and even if there had been no Industrial Revolution current global temperatures would be almost exactly the same as they are now.", "output": "disagrees", "explanation": "The sentence explicitly states the global warming is natural. It also adds the temperatures would be the same even without industries. Therefore the sentence disagrees with the target."}, {"input": "All fossil fuel use needs to be regulated to reduce global warming.", "output": "agrees", "explanation": "The sentence accepts that global warming exists and states that with the reduction of fossil fuels we can reduce global warming."}, {"input": "There is no solid evidence of global warming.", "output": "disagrees", "explanation": "The sentence disagrees with the fact that global warming exists at all. So it is clear that the writer disagrees with the target."}, {"input": "The meltdown results from the complex interaction of players including emissions-driven climate change, warm air and water, and shrinking ice area.", "output": "neutral", "explanation": "The sentence puts equal weight on both human and natural causes for global warming. So this sentence has a neutral stance."}], "Negative Examples": [{"input": "We can not live on fossil fuel forever.", "output": "disagrees", "explanation": "The sentence only suggests that we cannot live on fossil fuels forever. It does not provide any information about global warming. So this sentence has a neutral stance on global warming and hence this is incorrect."}, {"input": "More warming leads to more fires, which release more carbon, which causes more warming, and so on.", "output": "I don't agree", "explanation": "The task definition clearly states that you need to reply with \"agrees\", \"disagrees\" and \"neutral\" but the output has selected a different option. So this is an incorrect answer."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Economics"], "Instance": {"id": "task890-f899a524865e40c39bfbb7c443b0d262", "input": "All that our world leaders need is a little more common sense, in order to avoid the nonsense of seeking a globally-binding treaty to reduce CO2 emissions.", "output": ["disagrees"]}, "Instance License": ["Unknown"], "prediction": "agrees"}
+{"id": "task890-c2493e7bfd4c4a5fad8679fbbd40de94", "Task": "task890_gcwd_classification", "Contributors": "['Selvaganesh Muthu']", "Source": ["gwsd"], "URL": ["https://github.com/yiweiluo/GWStance"], "Categories": ["Textual Entailment"], "Reasoning": ["Textual Entailment"], "Definition": ["Read the passage and find if the passage agrees, disagrees, or has a neutral stance on whether Global warming is caused by human activities. Answer only with keyword (a) agrees - if passage agrees with the target (b) disagrees - if passage disagrees with the target (c) neutral - if the given passage neither agrees nor disagrees with the target. You don't need to use external knowledge in this task, and you have to answer based on the given passage."], "Positive Examples": [{"input": "Most global warming is natural and even if there had been no Industrial Revolution current global temperatures would be almost exactly the same as they are now.", "output": "disagrees", "explanation": "The sentence explicitly states the global warming is natural. It also adds the temperatures would be the same even without industries. Therefore the sentence disagrees with the target."}, {"input": "All fossil fuel use needs to be regulated to reduce global warming.", "output": "agrees", "explanation": "The sentence accepts that global warming exists and states that with the reduction of fossil fuels we can reduce global warming."}, {"input": "There is no solid evidence of global warming.", "output": "disagrees", "explanation": "The sentence disagrees with the fact that global warming exists at all. So it is clear that the writer disagrees with the target."}, {"input": "The meltdown results from the complex interaction of players including emissions-driven climate change, warm air and water, and shrinking ice area.", "output": "neutral", "explanation": "The sentence puts equal weight on both human and natural causes for global warming. So this sentence has a neutral stance."}], "Negative Examples": [{"input": "We can not live on fossil fuel forever.", "output": "disagrees", "explanation": "The sentence only suggests that we cannot live on fossil fuels forever. It does not provide any information about global warming. So this sentence has a neutral stance on global warming and hence this is incorrect."}, {"input": "More warming leads to more fires, which release more carbon, which causes more warming, and so on.", "output": "I don't agree", "explanation": "The task definition clearly states that you need to reply with \"agrees\", \"disagrees\" and \"neutral\" but the output has selected a different option. So this is an incorrect answer."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Economics"], "Instance": {"id": "task890-c2493e7bfd4c4a5fad8679fbbd40de94", "input": "Caring about the climate is elitist.", "output": ["disagrees"]}, "Instance License": ["Unknown"], "prediction": "disagrees"}
+{"id": "task039-2a36095feade494c88d84a6eb2cfaddc", "Task": "task039_qasc_find_overlapping_words", "Contributors": "['Swaroop Mishra', 'Daniel Khashabi']", "Source": ["qasc"], "URL": ["https://allenai.org/data/qasc"], "Categories": ["Overlap Extraction"], "Reasoning": [], "Definition": ["Generate an overlapping word between the given two sentences. When you find the overlapping words, they don't have to match exactly, e.g., \"survival\" and \"survive\" are valid overlapping words. Little words like \"the\" or \"of\" don't count! You must generate significant words which are not the stop words."], "Positive Examples": [{"input": "Sentence1: pesticides cause pollution. \nSentence2: pollution can harm animals.", "output": "pollution.", "explanation": "The word \"pollution\" is common to Sentence1 and Sentence2. So, it's a good answer."}, {"input": "Sentence1: a solar panel converts sunlight into electricity. \nSentence2: sunlight comes from the sun.", "output": "sunlight.", "explanation": "The word \"sunlight\" is common to both sentences. So, it's a good answer."}, {"input": "Sentence1: running requires a lot of energy. \nSentence2: doing a marathon requires a lot of energy.", "output": "requires.", "explanation": "The words \"requires\", \"lot\", \"energy\" are common to Sentence1 and Sentence2. Note that \"a\" and \"of\" are of little importance and better not be reported. So, it's a good answer."}, {"input": "Sentence1: soil is formed by rocks eroding. \nSentence2: rain can help form soil.", "output": "form.", "explanation": "The words \"soil\", \"form\" are common to Sentence1 and Sentence2. Note that Sentence1 contains \"formed\" and Sentence2 contains \"form\". As per the given instructions, they are treated as the same because of their same base form. So, it's a good answer."}, {"input": "Sentence1: a plant requires water for survival. \nSentence2: rain helps plants to survive.", "output": "survive.", "explanation": "The words \"plants\" and \"survive\" are the common to Sentence1 and Sentence2. Note that Sentence1 contains \"survival\" and Sentence2 contains \"survive\". As per the given instructions, they are treated as the same because of their same base form. So, it's a good answer."}, {"input": "Sentence1: vibrations in the air form sound. \nSentence2: a radio converts electrical energy into sound.", "output": "sound.", "explanation": "The word \"sound\" is common to Sentence1 and Sentence2. So, it's a good answer."}, {"input": "Sentence1: chopping down trees results in habitat destruction. \nSentence2: chopping down trees causes animals to move to another habitat.", "output": "chopping.", "explanation": "The words \"chopping\", \"trees\", \"habitat\" are common to Sentence1 and Sentence2. So, it's a good answer."}, {"input": "Sentence1: a protractor is used for measuring the angles of a triangular object. \nSentence2: a prism has a triangular shape.", "output": "triangular.", "explanation": "The word \"triangular\" is common to Sentence1 and Sentence2. Event though the word \"a\" is also common, it's not counted based on the instruction which says not to count little words or stop words. So, it's a good answer."}, {"input": "Sentence1: lightning can cause a forest fire. \nSentence2: lightning can cause harm to animals.", "output": "lightning.", "explanation": "The words \"lightning\", \"cause\" are common to Sentence1 and Sentence2. Event though the word \"can\" is also common, it's not counted based on the instruction which says not to count little words or stop words. So, it's a good answer."}], "Negative Examples": [{"input": "Sentence1: soil is formed by rocks eroding. \nSentence2: rain can help form soil.", "output": "soil, form, formed.", "explanation": "Here Sentence1 contains \"formed\" and Sentence2 contains \"form\". As per the given instructions, they should be treated as the same because of their same base form. A good answer would have been either \"soil\" or \"form\"."}, {"input": "Sentence1: a protractor is used for measuring the angles of a triangular object. \nSentence2: a prism has a triangular shape.", "output": "a, triangular.", "explanation": "Even though the word \"a\" is also common, it is better not to be reported since it adds very little to the meaning. So, it's a bad answer."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Natural Science"], "Instance": {"id": "task039-2a36095feade494c88d84a6eb2cfaddc", "input": "Sentence1: Bacteria are very small. \nSentence2: Biologists use microscopes to see bacteria.", "output": ["Bacteria"]}, "Instance License": ["CC BY 4.0"], "prediction": "microscopes"}
+{"id": "task039-328a397c748540e9995d657340e6287d", "Task": "task039_qasc_find_overlapping_words", "Contributors": "['Swaroop Mishra', 'Daniel Khashabi']", "Source": ["qasc"], "URL": ["https://allenai.org/data/qasc"], "Categories": ["Overlap Extraction"], "Reasoning": [], "Definition": ["Generate an overlapping word between the given two sentences. When you find the overlapping words, they don't have to match exactly, e.g., \"survival\" and \"survive\" are valid overlapping words. Little words like \"the\" or \"of\" don't count! You must generate significant words which are not the stop words."], "Positive Examples": [{"input": "Sentence1: pesticides cause pollution. \nSentence2: pollution can harm animals.", "output": "pollution.", "explanation": "The word \"pollution\" is common to Sentence1 and Sentence2. So, it's a good answer."}, {"input": "Sentence1: a solar panel converts sunlight into electricity. \nSentence2: sunlight comes from the sun.", "output": "sunlight.", "explanation": "The word \"sunlight\" is common to both sentences. So, it's a good answer."}, {"input": "Sentence1: running requires a lot of energy. \nSentence2: doing a marathon requires a lot of energy.", "output": "requires.", "explanation": "The words \"requires\", \"lot\", \"energy\" are common to Sentence1 and Sentence2. Note that \"a\" and \"of\" are of little importance and better not be reported. So, it's a good answer."}, {"input": "Sentence1: soil is formed by rocks eroding. \nSentence2: rain can help form soil.", "output": "form.", "explanation": "The words \"soil\", \"form\" are common to Sentence1 and Sentence2. Note that Sentence1 contains \"formed\" and Sentence2 contains \"form\". As per the given instructions, they are treated as the same because of their same base form. So, it's a good answer."}, {"input": "Sentence1: a plant requires water for survival. \nSentence2: rain helps plants to survive.", "output": "survive.", "explanation": "The words \"plants\" and \"survive\" are the common to Sentence1 and Sentence2. Note that Sentence1 contains \"survival\" and Sentence2 contains \"survive\". As per the given instructions, they are treated as the same because of their same base form. So, it's a good answer."}, {"input": "Sentence1: vibrations in the air form sound. \nSentence2: a radio converts electrical energy into sound.", "output": "sound.", "explanation": "The word \"sound\" is common to Sentence1 and Sentence2. So, it's a good answer."}, {"input": "Sentence1: chopping down trees results in habitat destruction. \nSentence2: chopping down trees causes animals to move to another habitat.", "output": "chopping.", "explanation": "The words \"chopping\", \"trees\", \"habitat\" are common to Sentence1 and Sentence2. So, it's a good answer."}, {"input": "Sentence1: a protractor is used for measuring the angles of a triangular object. \nSentence2: a prism has a triangular shape.", "output": "triangular.", "explanation": "The word \"triangular\" is common to Sentence1 and Sentence2. Event though the word \"a\" is also common, it's not counted based on the instruction which says not to count little words or stop words. So, it's a good answer."}, {"input": "Sentence1: lightning can cause a forest fire. \nSentence2: lightning can cause harm to animals.", "output": "lightning.", "explanation": "The words \"lightning\", \"cause\" are common to Sentence1 and Sentence2. Event though the word \"can\" is also common, it's not counted based on the instruction which says not to count little words or stop words. So, it's a good answer."}], "Negative Examples": [{"input": "Sentence1: soil is formed by rocks eroding. \nSentence2: rain can help form soil.", "output": "soil, form, formed.", "explanation": "Here Sentence1 contains \"formed\" and Sentence2 contains \"form\". As per the given instructions, they should be treated as the same because of their same base form. A good answer would have been either \"soil\" or \"form\"."}, {"input": "Sentence1: a protractor is used for measuring the angles of a triangular object. \nSentence2: a prism has a triangular shape.", "output": "a, triangular.", "explanation": "Even though the word \"a\" is also common, it is better not to be reported since it adds very little to the meaning. So, it's a bad answer."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Natural Science"], "Instance": {"id": "task039-328a397c748540e9995d657340e6287d", "input": "Sentence1: Well, the elbow is a hinged joint. \nSentence2: Triceps contracting causes a person 's hinged joint to straighten.", "output": ["hinged", "joint"]}, "Instance License": ["CC BY 4.0"], "prediction": "Triceps"}
+{"id": "task039-868bbb8d75d54435a698db99c3f1e1e3", "Task": "task039_qasc_find_overlapping_words", "Contributors": "['Swaroop Mishra', 'Daniel Khashabi']", "Source": ["qasc"], "URL": ["https://allenai.org/data/qasc"], "Categories": ["Overlap Extraction"], "Reasoning": [], "Definition": ["Generate an overlapping word between the given two sentences. When you find the overlapping words, they don't have to match exactly, e.g., \"survival\" and \"survive\" are valid overlapping words. Little words like \"the\" or \"of\" don't count! You must generate significant words which are not the stop words."], "Positive Examples": [{"input": "Sentence1: pesticides cause pollution. \nSentence2: pollution can harm animals.", "output": "pollution.", "explanation": "The word \"pollution\" is common to Sentence1 and Sentence2. So, it's a good answer."}, {"input": "Sentence1: a solar panel converts sunlight into electricity. \nSentence2: sunlight comes from the sun.", "output": "sunlight.", "explanation": "The word \"sunlight\" is common to both sentences. So, it's a good answer."}, {"input": "Sentence1: running requires a lot of energy. \nSentence2: doing a marathon requires a lot of energy.", "output": "requires.", "explanation": "The words \"requires\", \"lot\", \"energy\" are common to Sentence1 and Sentence2. Note that \"a\" and \"of\" are of little importance and better not be reported. So, it's a good answer."}, {"input": "Sentence1: soil is formed by rocks eroding. \nSentence2: rain can help form soil.", "output": "form.", "explanation": "The words \"soil\", \"form\" are common to Sentence1 and Sentence2. Note that Sentence1 contains \"formed\" and Sentence2 contains \"form\". As per the given instructions, they are treated as the same because of their same base form. So, it's a good answer."}, {"input": "Sentence1: a plant requires water for survival. \nSentence2: rain helps plants to survive.", "output": "survive.", "explanation": "The words \"plants\" and \"survive\" are the common to Sentence1 and Sentence2. Note that Sentence1 contains \"survival\" and Sentence2 contains \"survive\". As per the given instructions, they are treated as the same because of their same base form. So, it's a good answer."}, {"input": "Sentence1: vibrations in the air form sound. \nSentence2: a radio converts electrical energy into sound.", "output": "sound.", "explanation": "The word \"sound\" is common to Sentence1 and Sentence2. So, it's a good answer."}, {"input": "Sentence1: chopping down trees results in habitat destruction. \nSentence2: chopping down trees causes animals to move to another habitat.", "output": "chopping.", "explanation": "The words \"chopping\", \"trees\", \"habitat\" are common to Sentence1 and Sentence2. So, it's a good answer."}, {"input": "Sentence1: a protractor is used for measuring the angles of a triangular object. \nSentence2: a prism has a triangular shape.", "output": "triangular.", "explanation": "The word \"triangular\" is common to Sentence1 and Sentence2. Event though the word \"a\" is also common, it's not counted based on the instruction which says not to count little words or stop words. So, it's a good answer."}, {"input": "Sentence1: lightning can cause a forest fire. \nSentence2: lightning can cause harm to animals.", "output": "lightning.", "explanation": "The words \"lightning\", \"cause\" are common to Sentence1 and Sentence2. Event though the word \"can\" is also common, it's not counted based on the instruction which says not to count little words or stop words. So, it's a good answer."}], "Negative Examples": [{"input": "Sentence1: soil is formed by rocks eroding. \nSentence2: rain can help form soil.", "output": "soil, form, formed.", "explanation": "Here Sentence1 contains \"formed\" and Sentence2 contains \"form\". As per the given instructions, they should be treated as the same because of their same base form. A good answer would have been either \"soil\" or \"form\"."}, {"input": "Sentence1: a protractor is used for measuring the angles of a triangular object. \nSentence2: a prism has a triangular shape.", "output": "a, triangular.", "explanation": "Even though the word \"a\" is also common, it is better not to be reported since it adds very little to the meaning. So, it's a bad answer."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Natural Science"], "Instance": {"id": "task039-868bbb8d75d54435a698db99c3f1e1e3", "input": "Sentence1: Annelids are worms such as the familiar earthworm. \nSentence2: Earthworms have some of the fastest reflexes in the animal kingdom.", "output": ["earthworm"]}, "Instance License": ["CC BY 4.0"], "prediction": "Earthworms"}
+{"id": "task039-d504d908f7c244c6894215fe7bcd6444", "Task": "task039_qasc_find_overlapping_words", "Contributors": "['Swaroop Mishra', 'Daniel Khashabi']", "Source": ["qasc"], "URL": ["https://allenai.org/data/qasc"], "Categories": ["Overlap Extraction"], "Reasoning": [], "Definition": ["Generate an overlapping word between the given two sentences. When you find the overlapping words, they don't have to match exactly, e.g., \"survival\" and \"survive\" are valid overlapping words. Little words like \"the\" or \"of\" don't count! You must generate significant words which are not the stop words."], "Positive Examples": [{"input": "Sentence1: pesticides cause pollution. \nSentence2: pollution can harm animals.", "output": "pollution.", "explanation": "The word \"pollution\" is common to Sentence1 and Sentence2. So, it's a good answer."}, {"input": "Sentence1: a solar panel converts sunlight into electricity. \nSentence2: sunlight comes from the sun.", "output": "sunlight.", "explanation": "The word \"sunlight\" is common to both sentences. So, it's a good answer."}, {"input": "Sentence1: running requires a lot of energy. \nSentence2: doing a marathon requires a lot of energy.", "output": "requires.", "explanation": "The words \"requires\", \"lot\", \"energy\" are common to Sentence1 and Sentence2. Note that \"a\" and \"of\" are of little importance and better not be reported. So, it's a good answer."}, {"input": "Sentence1: soil is formed by rocks eroding. \nSentence2: rain can help form soil.", "output": "form.", "explanation": "The words \"soil\", \"form\" are common to Sentence1 and Sentence2. Note that Sentence1 contains \"formed\" and Sentence2 contains \"form\". As per the given instructions, they are treated as the same because of their same base form. So, it's a good answer."}, {"input": "Sentence1: a plant requires water for survival. \nSentence2: rain helps plants to survive.", "output": "survive.", "explanation": "The words \"plants\" and \"survive\" are the common to Sentence1 and Sentence2. Note that Sentence1 contains \"survival\" and Sentence2 contains \"survive\". As per the given instructions, they are treated as the same because of their same base form. So, it's a good answer."}, {"input": "Sentence1: vibrations in the air form sound. \nSentence2: a radio converts electrical energy into sound.", "output": "sound.", "explanation": "The word \"sound\" is common to Sentence1 and Sentence2. So, it's a good answer."}, {"input": "Sentence1: chopping down trees results in habitat destruction. \nSentence2: chopping down trees causes animals to move to another habitat.", "output": "chopping.", "explanation": "The words \"chopping\", \"trees\", \"habitat\" are common to Sentence1 and Sentence2. So, it's a good answer."}, {"input": "Sentence1: a protractor is used for measuring the angles of a triangular object. \nSentence2: a prism has a triangular shape.", "output": "triangular.", "explanation": "The word \"triangular\" is common to Sentence1 and Sentence2. Event though the word \"a\" is also common, it's not counted based on the instruction which says not to count little words or stop words. So, it's a good answer."}, {"input": "Sentence1: lightning can cause a forest fire. \nSentence2: lightning can cause harm to animals.", "output": "lightning.", "explanation": "The words \"lightning\", \"cause\" are common to Sentence1 and Sentence2. Event though the word \"can\" is also common, it's not counted based on the instruction which says not to count little words or stop words. So, it's a good answer."}], "Negative Examples": [{"input": "Sentence1: soil is formed by rocks eroding. \nSentence2: rain can help form soil.", "output": "soil, form, formed.", "explanation": "Here Sentence1 contains \"formed\" and Sentence2 contains \"form\". As per the given instructions, they should be treated as the same because of their same base form. A good answer would have been either \"soil\" or \"form\"."}, {"input": "Sentence1: a protractor is used for measuring the angles of a triangular object. \nSentence2: a prism has a triangular shape.", "output": "a, triangular.", "explanation": "Even though the word \"a\" is also common, it is better not to be reported since it adds very little to the meaning. So, it's a bad answer."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Natural Science"], "Instance": {"id": "task039-d504d908f7c244c6894215fe7bcd6444", "input": "Sentence1: Most animals that live on rocky shores eat plankton. \nSentence2: Most animals that live on rocky shores eat nonliving organic matter.", "output": ["Most", "animals", "eat", "live", "rocky", "shores", "that"]}, "Instance License": ["CC BY 4.0"], "prediction": "organic matter"}
+{"id": "task039-eaf8e0346a8d45fd8492142d21777e5a", "Task": "task039_qasc_find_overlapping_words", "Contributors": "['Swaroop Mishra', 'Daniel Khashabi']", "Source": ["qasc"], "URL": ["https://allenai.org/data/qasc"], "Categories": ["Overlap Extraction"], "Reasoning": [], "Definition": ["Generate an overlapping word between the given two sentences. When you find the overlapping words, they don't have to match exactly, e.g., \"survival\" and \"survive\" are valid overlapping words. Little words like \"the\" or \"of\" don't count! You must generate significant words which are not the stop words."], "Positive Examples": [{"input": "Sentence1: pesticides cause pollution. \nSentence2: pollution can harm animals.", "output": "pollution.", "explanation": "The word \"pollution\" is common to Sentence1 and Sentence2. So, it's a good answer."}, {"input": "Sentence1: a solar panel converts sunlight into electricity. \nSentence2: sunlight comes from the sun.", "output": "sunlight.", "explanation": "The word \"sunlight\" is common to both sentences. So, it's a good answer."}, {"input": "Sentence1: running requires a lot of energy. \nSentence2: doing a marathon requires a lot of energy.", "output": "requires.", "explanation": "The words \"requires\", \"lot\", \"energy\" are common to Sentence1 and Sentence2. Note that \"a\" and \"of\" are of little importance and better not be reported. So, it's a good answer."}, {"input": "Sentence1: soil is formed by rocks eroding. \nSentence2: rain can help form soil.", "output": "form.", "explanation": "The words \"soil\", \"form\" are common to Sentence1 and Sentence2. Note that Sentence1 contains \"formed\" and Sentence2 contains \"form\". As per the given instructions, they are treated as the same because of their same base form. So, it's a good answer."}, {"input": "Sentence1: a plant requires water for survival. \nSentence2: rain helps plants to survive.", "output": "survive.", "explanation": "The words \"plants\" and \"survive\" are the common to Sentence1 and Sentence2. Note that Sentence1 contains \"survival\" and Sentence2 contains \"survive\". As per the given instructions, they are treated as the same because of their same base form. So, it's a good answer."}, {"input": "Sentence1: vibrations in the air form sound. \nSentence2: a radio converts electrical energy into sound.", "output": "sound.", "explanation": "The word \"sound\" is common to Sentence1 and Sentence2. So, it's a good answer."}, {"input": "Sentence1: chopping down trees results in habitat destruction. \nSentence2: chopping down trees causes animals to move to another habitat.", "output": "chopping.", "explanation": "The words \"chopping\", \"trees\", \"habitat\" are common to Sentence1 and Sentence2. So, it's a good answer."}, {"input": "Sentence1: a protractor is used for measuring the angles of a triangular object. \nSentence2: a prism has a triangular shape.", "output": "triangular.", "explanation": "The word \"triangular\" is common to Sentence1 and Sentence2. Event though the word \"a\" is also common, it's not counted based on the instruction which says not to count little words or stop words. So, it's a good answer."}, {"input": "Sentence1: lightning can cause a forest fire. \nSentence2: lightning can cause harm to animals.", "output": "lightning.", "explanation": "The words \"lightning\", \"cause\" are common to Sentence1 and Sentence2. Event though the word \"can\" is also common, it's not counted based on the instruction which says not to count little words or stop words. So, it's a good answer."}], "Negative Examples": [{"input": "Sentence1: soil is formed by rocks eroding. \nSentence2: rain can help form soil.", "output": "soil, form, formed.", "explanation": "Here Sentence1 contains \"formed\" and Sentence2 contains \"form\". As per the given instructions, they should be treated as the same because of their same base form. A good answer would have been either \"soil\" or \"form\"."}, {"input": "Sentence1: a protractor is used for measuring the angles of a triangular object. \nSentence2: a prism has a triangular shape.", "output": "a, triangular.", "explanation": "Even though the word \"a\" is also common, it is better not to be reported since it adds very little to the meaning. So, it's a bad answer."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Natural Science"], "Instance": {"id": "task039-eaf8e0346a8d45fd8492142d21777e5a", "input": "Sentence1: conserving water can be used for survival in a dry environment. \nSentence2: Conserving water can help humans survive.", "output": ["conserving"]}, "Instance License": ["CC BY 4.0"], "prediction": "survival"}
+{"id": "task1154-f0764dd34c3c466c91f4785834af6783", "Task": "task1154_bard_analogical_reasoning_travel", "Contributors": "['Arjun Ashok']", "Source": ["bard"], "URL": ["https://github.com/NancyFulda/BYU-Analogical-Reasoning-Dataset"], "Categories": ["Word Analogy"], "Reasoning": ["Relational Reasoning", "Commonsense Reasoning", "Analogical Reasoning"], "Definition": ["Two analogies that relate places/locations to the associated travel mode is given in the form \"A : B. C : ?\". \"A : B\" relates place A to travel mode B. Your task is to replace the question mark (?) with the appropriate travel mode for the given place C, following the \"A : B\" relation."], "Positive Examples": [{"input": "moon : rocket. france : ?", "output": "airplane", "explanation": "Rockets are used to travel to the moon - hence the given analogy relates places/locations to the associated travel mode , and the answer also does the same"}, {"input": "mall : bus. theater : ?", "output": "car", "explanation": "A bus can be used to travel to the mall - hence the given analogy relates places/locations to the associated travel mode , and the answer also does the same"}, {"input": "australia : airplane. portland : ?", "output": "car", "explanation": "If an airplane can be used to travel to australia - the given analogy relates places/locations to the associated travel mode , and the answer also does the same"}], "Negative Examples": [{"input": "park : bicycle. school : ?", "output": "students", "explanation": "The given analogy relates places/locations to the associated travel mode , BUT the answer does not model the same"}, {"input": "restaurant : taxi. downtown : ?", "output": "rocket", "explanation": "If a taxi can be used to travel to restaurant - rocket is not the right answer for travelling to downtown"}, {"input": "airport : car. bermuda : ?", "output": "bicycle", "explanation": "If a car can be used to travel to an airport - bicycle is not the right answer for travelling to bermuda. The airplane or boat could have been the correct answer."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Commonsense", "Public Places"], "Instance": {"id": "task1154-f0764dd34c3c466c91f4785834af6783", "input": "school : bicycle. cemetery : ?", "output": ["hearse"]}, "Instance License": ["Apache 2.0"], "prediction": "cemetery"}
+{"id": "task1154-1cc276f97d2543a9ba8bf74bea782288", "Task": "task1154_bard_analogical_reasoning_travel", "Contributors": "['Arjun Ashok']", "Source": ["bard"], "URL": ["https://github.com/NancyFulda/BYU-Analogical-Reasoning-Dataset"], "Categories": ["Word Analogy"], "Reasoning": ["Relational Reasoning", "Commonsense Reasoning", "Analogical Reasoning"], "Definition": ["Two analogies that relate places/locations to the associated travel mode is given in the form \"A : B. C : ?\". \"A : B\" relates place A to travel mode B. Your task is to replace the question mark (?) with the appropriate travel mode for the given place C, following the \"A : B\" relation."], "Positive Examples": [{"input": "moon : rocket. france : ?", "output": "airplane", "explanation": "Rockets are used to travel to the moon - hence the given analogy relates places/locations to the associated travel mode , and the answer also does the same"}, {"input": "mall : bus. theater : ?", "output": "car", "explanation": "A bus can be used to travel to the mall - hence the given analogy relates places/locations to the associated travel mode , and the answer also does the same"}, {"input": "australia : airplane. portland : ?", "output": "car", "explanation": "If an airplane can be used to travel to australia - the given analogy relates places/locations to the associated travel mode , and the answer also does the same"}], "Negative Examples": [{"input": "park : bicycle. school : ?", "output": "students", "explanation": "The given analogy relates places/locations to the associated travel mode , BUT the answer does not model the same"}, {"input": "restaurant : taxi. downtown : ?", "output": "rocket", "explanation": "If a taxi can be used to travel to restaurant - rocket is not the right answer for travelling to downtown"}, {"input": "airport : car. bermuda : ?", "output": "bicycle", "explanation": "If a car can be used to travel to an airport - bicycle is not the right answer for travelling to bermuda. The airplane or boat could have been the correct answer."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Commonsense", "Public Places"], "Instance": {"id": "task1154-1cc276f97d2543a9ba8bf74bea782288", "input": "park : bicycle. bermuda : ?", "output": ["airplane"]}, "Instance License": ["Apache 2.0"], "prediction": "bike"}
+{"id": "task1154-3b7df0afc8ba49b5b9efe62b3baf1805", "Task": "task1154_bard_analogical_reasoning_travel", "Contributors": "['Arjun Ashok']", "Source": ["bard"], "URL": ["https://github.com/NancyFulda/BYU-Analogical-Reasoning-Dataset"], "Categories": ["Word Analogy"], "Reasoning": ["Relational Reasoning", "Commonsense Reasoning", "Analogical Reasoning"], "Definition": ["Two analogies that relate places/locations to the associated travel mode is given in the form \"A : B. C : ?\". \"A : B\" relates place A to travel mode B. Your task is to replace the question mark (?) with the appropriate travel mode for the given place C, following the \"A : B\" relation."], "Positive Examples": [{"input": "moon : rocket. france : ?", "output": "airplane", "explanation": "Rockets are used to travel to the moon - hence the given analogy relates places/locations to the associated travel mode , and the answer also does the same"}, {"input": "mall : bus. theater : ?", "output": "car", "explanation": "A bus can be used to travel to the mall - hence the given analogy relates places/locations to the associated travel mode , and the answer also does the same"}, {"input": "australia : airplane. portland : ?", "output": "car", "explanation": "If an airplane can be used to travel to australia - the given analogy relates places/locations to the associated travel mode , and the answer also does the same"}], "Negative Examples": [{"input": "park : bicycle. school : ?", "output": "students", "explanation": "The given analogy relates places/locations to the associated travel mode , BUT the answer does not model the same"}, {"input": "restaurant : taxi. downtown : ?", "output": "rocket", "explanation": "If a taxi can be used to travel to restaurant - rocket is not the right answer for travelling to downtown"}, {"input": "airport : car. bermuda : ?", "output": "bicycle", "explanation": "If a car can be used to travel to an airport - bicycle is not the right answer for travelling to bermuda. The airplane or boat could have been the correct answer."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Commonsense", "Public Places"], "Instance": {"id": "task1154-3b7df0afc8ba49b5b9efe62b3baf1805", "input": "restaurant : taxi. park : ?", "output": ["bicycle"]}, "Instance License": ["Apache 2.0"], "prediction": "car"}
+{"id": "task1154-416e1bf47c1c43cdaa87e1a9f48817d9", "Task": "task1154_bard_analogical_reasoning_travel", "Contributors": "['Arjun Ashok']", "Source": ["bard"], "URL": ["https://github.com/NancyFulda/BYU-Analogical-Reasoning-Dataset"], "Categories": ["Word Analogy"], "Reasoning": ["Relational Reasoning", "Commonsense Reasoning", "Analogical Reasoning"], "Definition": ["Two analogies that relate places/locations to the associated travel mode is given in the form \"A : B. C : ?\". \"A : B\" relates place A to travel mode B. Your task is to replace the question mark (?) with the appropriate travel mode for the given place C, following the \"A : B\" relation."], "Positive Examples": [{"input": "moon : rocket. france : ?", "output": "airplane", "explanation": "Rockets are used to travel to the moon - hence the given analogy relates places/locations to the associated travel mode , and the answer also does the same"}, {"input": "mall : bus. theater : ?", "output": "car", "explanation": "A bus can be used to travel to the mall - hence the given analogy relates places/locations to the associated travel mode , and the answer also does the same"}, {"input": "australia : airplane. portland : ?", "output": "car", "explanation": "If an airplane can be used to travel to australia - the given analogy relates places/locations to the associated travel mode , and the answer also does the same"}], "Negative Examples": [{"input": "park : bicycle. school : ?", "output": "students", "explanation": "The given analogy relates places/locations to the associated travel mode , BUT the answer does not model the same"}, {"input": "restaurant : taxi. downtown : ?", "output": "rocket", "explanation": "If a taxi can be used to travel to restaurant - rocket is not the right answer for travelling to downtown"}, {"input": "airport : car. bermuda : ?", "output": "bicycle", "explanation": "If a car can be used to travel to an airport - bicycle is not the right answer for travelling to bermuda. The airplane or boat could have been the correct answer."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Commonsense", "Public Places"], "Instance": {"id": "task1154-416e1bf47c1c43cdaa87e1a9f48817d9", "input": "canada : car. moon : ?", "output": ["rocket"]}, "Instance License": ["Apache 2.0"], "prediction": "rocket"}
+{"id": "task1154-d50b69cb983d414581d24c7ecf6032ff", "Task": "task1154_bard_analogical_reasoning_travel", "Contributors": "['Arjun Ashok']", "Source": ["bard"], "URL": ["https://github.com/NancyFulda/BYU-Analogical-Reasoning-Dataset"], "Categories": ["Word Analogy"], "Reasoning": ["Relational Reasoning", "Commonsense Reasoning", "Analogical Reasoning"], "Definition": ["Two analogies that relate places/locations to the associated travel mode is given in the form \"A : B. C : ?\". \"A : B\" relates place A to travel mode B. Your task is to replace the question mark (?) with the appropriate travel mode for the given place C, following the \"A : B\" relation."], "Positive Examples": [{"input": "moon : rocket. france : ?", "output": "airplane", "explanation": "Rockets are used to travel to the moon - hence the given analogy relates places/locations to the associated travel mode , and the answer also does the same"}, {"input": "mall : bus. theater : ?", "output": "car", "explanation": "A bus can be used to travel to the mall - hence the given analogy relates places/locations to the associated travel mode , and the answer also does the same"}, {"input": "australia : airplane. portland : ?", "output": "car", "explanation": "If an airplane can be used to travel to australia - the given analogy relates places/locations to the associated travel mode , and the answer also does the same"}], "Negative Examples": [{"input": "park : bicycle. school : ?", "output": "students", "explanation": "The given analogy relates places/locations to the associated travel mode , BUT the answer does not model the same"}, {"input": "restaurant : taxi. downtown : ?", "output": "rocket", "explanation": "If a taxi can be used to travel to restaurant - rocket is not the right answer for travelling to downtown"}, {"input": "airport : car. bermuda : ?", "output": "bicycle", "explanation": "If a car can be used to travel to an airport - bicycle is not the right answer for travelling to bermuda. The airplane or boat could have been the correct answer."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Commonsense", "Public Places"], "Instance": {"id": "task1154-d50b69cb983d414581d24c7ecf6032ff", "input": "office : car. portland : ?", "output": ["car"]}, "Instance License": ["Apache 2.0"], "prediction": "car"}
+{"id": "task1612-8420118afa4c48b692b3515f7c340239", "Task": "task1612_sick_label_classification", "Contributors": "['Venkata Sesha Sree Vidya Akkiraju']", "Source": ["sick"], "URL": ["https://huggingface.co/datasets/sick"], "Categories": ["Textual Entailment"], "Reasoning": ["Textual Entailment -> Deductive Reasoning"], "Definition": ["In this task, you're given a pair of sentences, sentence 1 and sentence 2. Your job is to choose whether the two sentences clearly agree (entailment)/disagree (contradiction) with each other, or if this cannot be determined (neutral). Your answer must be in the form of the numbers 0 (entailment), 1 (neutral), or 2(contradiction)."], "Positive Examples": [{"input": "sentence_A: A dancer is dancing on the stage. sentence_B: A girl is giving dance performance on the dais.", "output": "0", "explanation": "One sentence says, \"Dancing on the stage\" while the other sentence says, \"Dance performance on the dais\", which is clearly giving the same meaning and are related to each other. So the classification is entailment."}, {"input": "sentence_A: The crowd is cheering at her dance performance. sentence_B: The group is enjoying while eating food.", "output": "1", "explanation": "The first one says, \"The crowd is cheering at dance performance\" whereas the second one says, \"Enjoying eating the food.\" There is no relation at all between the two sentences as it is neither supporting nor contradicting. So it is neutral."}, {"input": "sentence_A: A man is standing and has tears of joy seeing the dance performance. sentence_B: There is no man standing with happiness seeing the dance.", "output": "2", "explanation": "Here the first sentence says, \"A man is standing\", while the second sentence contradicts saying there is no man standing so clearly this is a contradiction so label 2."}], "Negative Examples": [{"input": "sentence_A: Two dogs are fighting for bones. sentence_B: Two dogs are sharing the bones they have.", "output": "1", "explanation": "One sentence says, \"Two dogs are fighting\" and the other says, \"Two dogs are sharing\" which is a contradiction but classified as entailment. So this is a wrong example."}, {"input": "sentence_A: A dog is having fun with the toddler toys. sentence_B: The dog is enjoying with the toddler toys.", "output": "2", "explanation": "Here having fun and playing are related to each other, so we can clearly say there is entailment but classified as a contradiction."}, {"input": "sentence_A: The man is not eating breakfast because of meetings. sentence_B: The man is eating breakfast inspite of the meetings.", "output": "0", "explanation": "The first sentence says, \"Man is not eating\" while the other one says, \"Man is eating\", which is a contradiction but predicted as neutral wrongly."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Captions -> Video Captions", "Captions -> Image Captions"], "Instance": {"id": "task1612-8420118afa4c48b692b3515f7c340239", "input": "sentence_A: A person on a bike is not in the air near a body of water. sentence_B: A person on a bike is in the air near a body of water", "output": ["2"]}, "Instance License": ["CC BY-NC-SA 3.0"], "prediction": "0"}
+{"id": "task1612-7d037d0416ea45d0bbdea23cb32c7e93", "Task": "task1612_sick_label_classification", "Contributors": "['Venkata Sesha Sree Vidya Akkiraju']", "Source": ["sick"], "URL": ["https://huggingface.co/datasets/sick"], "Categories": ["Textual Entailment"], "Reasoning": ["Textual Entailment -> Deductive Reasoning"], "Definition": ["In this task, you're given a pair of sentences, sentence 1 and sentence 2. Your job is to choose whether the two sentences clearly agree (entailment)/disagree (contradiction) with each other, or if this cannot be determined (neutral). Your answer must be in the form of the numbers 0 (entailment), 1 (neutral), or 2(contradiction)."], "Positive Examples": [{"input": "sentence_A: A dancer is dancing on the stage. sentence_B: A girl is giving dance performance on the dais.", "output": "0", "explanation": "One sentence says, \"Dancing on the stage\" while the other sentence says, \"Dance performance on the dais\", which is clearly giving the same meaning and are related to each other. So the classification is entailment."}, {"input": "sentence_A: The crowd is cheering at her dance performance. sentence_B: The group is enjoying while eating food.", "output": "1", "explanation": "The first one says, \"The crowd is cheering at dance performance\" whereas the second one says, \"Enjoying eating the food.\" There is no relation at all between the two sentences as it is neither supporting nor contradicting. So it is neutral."}, {"input": "sentence_A: A man is standing and has tears of joy seeing the dance performance. sentence_B: There is no man standing with happiness seeing the dance.", "output": "2", "explanation": "Here the first sentence says, \"A man is standing\", while the second sentence contradicts saying there is no man standing so clearly this is a contradiction so label 2."}], "Negative Examples": [{"input": "sentence_A: Two dogs are fighting for bones. sentence_B: Two dogs are sharing the bones they have.", "output": "1", "explanation": "One sentence says, \"Two dogs are fighting\" and the other says, \"Two dogs are sharing\" which is a contradiction but classified as entailment. So this is a wrong example."}, {"input": "sentence_A: A dog is having fun with the toddler toys. sentence_B: The dog is enjoying with the toddler toys.", "output": "2", "explanation": "Here having fun and playing are related to each other, so we can clearly say there is entailment but classified as a contradiction."}, {"input": "sentence_A: The man is not eating breakfast because of meetings. sentence_B: The man is eating breakfast inspite of the meetings.", "output": "0", "explanation": "The first sentence says, \"Man is not eating\" while the other one says, \"Man is eating\", which is a contradiction but predicted as neutral wrongly."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Captions -> Video Captions", "Captions -> Image Captions"], "Instance": {"id": "task1612-7d037d0416ea45d0bbdea23cb32c7e93", "input": "sentence_A: Two children are rolling in dirty water. sentence_B: Two children are rolling in muddy water", "output": ["0"]}, "Instance License": ["CC BY-NC-SA 3.0"], "prediction": "1"}
+{"id": "task1612-45a02e69f51a4fae88266e75d87a45fa", "Task": "task1612_sick_label_classification", "Contributors": "['Venkata Sesha Sree Vidya Akkiraju']", "Source": ["sick"], "URL": ["https://huggingface.co/datasets/sick"], "Categories": ["Textual Entailment"], "Reasoning": ["Textual Entailment -> Deductive Reasoning"], "Definition": ["In this task, you're given a pair of sentences, sentence 1 and sentence 2. Your job is to choose whether the two sentences clearly agree (entailment)/disagree (contradiction) with each other, or if this cannot be determined (neutral). Your answer must be in the form of the numbers 0 (entailment), 1 (neutral), or 2(contradiction)."], "Positive Examples": [{"input": "sentence_A: A dancer is dancing on the stage. sentence_B: A girl is giving dance performance on the dais.", "output": "0", "explanation": "One sentence says, \"Dancing on the stage\" while the other sentence says, \"Dance performance on the dais\", which is clearly giving the same meaning and are related to each other. So the classification is entailment."}, {"input": "sentence_A: The crowd is cheering at her dance performance. sentence_B: The group is enjoying while eating food.", "output": "1", "explanation": "The first one says, \"The crowd is cheering at dance performance\" whereas the second one says, \"Enjoying eating the food.\" There is no relation at all between the two sentences as it is neither supporting nor contradicting. So it is neutral."}, {"input": "sentence_A: A man is standing and has tears of joy seeing the dance performance. sentence_B: There is no man standing with happiness seeing the dance.", "output": "2", "explanation": "Here the first sentence says, \"A man is standing\", while the second sentence contradicts saying there is no man standing so clearly this is a contradiction so label 2."}], "Negative Examples": [{"input": "sentence_A: Two dogs are fighting for bones. sentence_B: Two dogs are sharing the bones they have.", "output": "1", "explanation": "One sentence says, \"Two dogs are fighting\" and the other says, \"Two dogs are sharing\" which is a contradiction but classified as entailment. So this is a wrong example."}, {"input": "sentence_A: A dog is having fun with the toddler toys. sentence_B: The dog is enjoying with the toddler toys.", "output": "2", "explanation": "Here having fun and playing are related to each other, so we can clearly say there is entailment but classified as a contradiction."}, {"input": "sentence_A: The man is not eating breakfast because of meetings. sentence_B: The man is eating breakfast inspite of the meetings.", "output": "0", "explanation": "The first sentence says, \"Man is not eating\" while the other one says, \"Man is eating\", which is a contradiction but predicted as neutral wrongly."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Captions -> Video Captions", "Captions -> Image Captions"], "Instance": {"id": "task1612-45a02e69f51a4fae88266e75d87a45fa", "input": "sentence_A: The orange rescue boat is not rushing across the water. sentence_B: The orange rescue boat is rushing across the water", "output": ["2"]}, "Instance License": ["CC BY-NC-SA 3.0"], "prediction": "0"}
+{"id": "task1612-51836e9fbabd45db88aa29c370c3081b", "Task": "task1612_sick_label_classification", "Contributors": "['Venkata Sesha Sree Vidya Akkiraju']", "Source": ["sick"], "URL": ["https://huggingface.co/datasets/sick"], "Categories": ["Textual Entailment"], "Reasoning": ["Textual Entailment -> Deductive Reasoning"], "Definition": ["In this task, you're given a pair of sentences, sentence 1 and sentence 2. Your job is to choose whether the two sentences clearly agree (entailment)/disagree (contradiction) with each other, or if this cannot be determined (neutral). Your answer must be in the form of the numbers 0 (entailment), 1 (neutral), or 2(contradiction)."], "Positive Examples": [{"input": "sentence_A: A dancer is dancing on the stage. sentence_B: A girl is giving dance performance on the dais.", "output": "0", "explanation": "One sentence says, \"Dancing on the stage\" while the other sentence says, \"Dance performance on the dais\", which is clearly giving the same meaning and are related to each other. So the classification is entailment."}, {"input": "sentence_A: The crowd is cheering at her dance performance. sentence_B: The group is enjoying while eating food.", "output": "1", "explanation": "The first one says, \"The crowd is cheering at dance performance\" whereas the second one says, \"Enjoying eating the food.\" There is no relation at all between the two sentences as it is neither supporting nor contradicting. So it is neutral."}, {"input": "sentence_A: A man is standing and has tears of joy seeing the dance performance. sentence_B: There is no man standing with happiness seeing the dance.", "output": "2", "explanation": "Here the first sentence says, \"A man is standing\", while the second sentence contradicts saying there is no man standing so clearly this is a contradiction so label 2."}], "Negative Examples": [{"input": "sentence_A: Two dogs are fighting for bones. sentence_B: Two dogs are sharing the bones they have.", "output": "1", "explanation": "One sentence says, \"Two dogs are fighting\" and the other says, \"Two dogs are sharing\" which is a contradiction but classified as entailment. So this is a wrong example."}, {"input": "sentence_A: A dog is having fun with the toddler toys. sentence_B: The dog is enjoying with the toddler toys.", "output": "2", "explanation": "Here having fun and playing are related to each other, so we can clearly say there is entailment but classified as a contradiction."}, {"input": "sentence_A: The man is not eating breakfast because of meetings. sentence_B: The man is eating breakfast inspite of the meetings.", "output": "0", "explanation": "The first sentence says, \"Man is not eating\" while the other one says, \"Man is eating\", which is a contradiction but predicted as neutral wrongly."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Captions -> Video Captions", "Captions -> Image Captions"], "Instance": {"id": "task1612-51836e9fbabd45db88aa29c370c3081b", "input": "sentence_A: Someone is beating an egg. sentence_B: The lady is stirring eggs in a bowl", "output": ["1"]}, "Instance License": ["CC BY-NC-SA 3.0"], "prediction": "1"}
+{"id": "task1612-5bc6d01daf7d4c8b8247fd360e7ec756", "Task": "task1612_sick_label_classification", "Contributors": "['Venkata Sesha Sree Vidya Akkiraju']", "Source": ["sick"], "URL": ["https://huggingface.co/datasets/sick"], "Categories": ["Textual Entailment"], "Reasoning": ["Textual Entailment -> Deductive Reasoning"], "Definition": ["In this task, you're given a pair of sentences, sentence 1 and sentence 2. Your job is to choose whether the two sentences clearly agree (entailment)/disagree (contradiction) with each other, or if this cannot be determined (neutral). Your answer must be in the form of the numbers 0 (entailment), 1 (neutral), or 2(contradiction)."], "Positive Examples": [{"input": "sentence_A: A dancer is dancing on the stage. sentence_B: A girl is giving dance performance on the dais.", "output": "0", "explanation": "One sentence says, \"Dancing on the stage\" while the other sentence says, \"Dance performance on the dais\", which is clearly giving the same meaning and are related to each other. So the classification is entailment."}, {"input": "sentence_A: The crowd is cheering at her dance performance. sentence_B: The group is enjoying while eating food.", "output": "1", "explanation": "The first one says, \"The crowd is cheering at dance performance\" whereas the second one says, \"Enjoying eating the food.\" There is no relation at all between the two sentences as it is neither supporting nor contradicting. So it is neutral."}, {"input": "sentence_A: A man is standing and has tears of joy seeing the dance performance. sentence_B: There is no man standing with happiness seeing the dance.", "output": "2", "explanation": "Here the first sentence says, \"A man is standing\", while the second sentence contradicts saying there is no man standing so clearly this is a contradiction so label 2."}], "Negative Examples": [{"input": "sentence_A: Two dogs are fighting for bones. sentence_B: Two dogs are sharing the bones they have.", "output": "1", "explanation": "One sentence says, \"Two dogs are fighting\" and the other says, \"Two dogs are sharing\" which is a contradiction but classified as entailment. So this is a wrong example."}, {"input": "sentence_A: A dog is having fun with the toddler toys. sentence_B: The dog is enjoying with the toddler toys.", "output": "2", "explanation": "Here having fun and playing are related to each other, so we can clearly say there is entailment but classified as a contradiction."}, {"input": "sentence_A: The man is not eating breakfast because of meetings. sentence_B: The man is eating breakfast inspite of the meetings.", "output": "0", "explanation": "The first sentence says, \"Man is not eating\" while the other one says, \"Man is eating\", which is a contradiction but predicted as neutral wrongly."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Captions -> Video Captions", "Captions -> Image Captions"], "Instance": {"id": "task1612-5bc6d01daf7d4c8b8247fd360e7ec756", "input": "sentence_A: A girl is applying makeup to her face. sentence_B: A woman is putting on makeup", "output": ["1"]}, "Instance License": ["CC BY-NC-SA 3.0"], "prediction": "0"}
+{"id": "task1442-67a98662a8924ee5adc23b0be17d12da", "Task": "task1442_doqa_movies_isanswerable", "Contributors": "['Kuntal Kumar Pal']", "Source": ["doqa"], "URL": ["http://www.ixa.eus/node/12931"], "Categories": ["Answerability Classification"], "Reasoning": ["Reasoning on Social Interactions"], "Definition": ["Given a paragraph about movies and a set of conversational questions and answers about the paragraph, say whether the passage contains sufficient information to answer the follow-up question. Say Yes if it is answerable; otherwise, say No. The paragraph has the prefix 'CONTEXT:'. Each conversation question has a prefix `Q:` followed by the answer prefix `A:`, and the follow-up question has a prefix `FOLLOWUP_Q:`."], "Positive Examples": [{"input": "CONTEXT: I think it's deliberately ambiguous. If it's real, the inconsistencies are easily explained by Vidal's fascist belief system. These elements simply are not part of his world. If it's fantasy, then of course only Ofelia can see these thing because she imagined them. I think part of Del Toro's purpose in the film was to maintain the plausibility of both of these interpretations. <sep> Q: Is Ofelia just dreaming things to get herself in a fairy world? A: If it's fantasy, then of course only Ofelia can see these thing because she imagined them  Q: Are the things happening for real but visible only to Ofelia? A: If it's real, the inconsistencies are easily explained by Vidal's fascist belief system. These elements simply are not part of his world  <sep> FOLLOWUP_Q: When Vidal pulls the mandrake root out of Ofelia's mother's bed, is it just a normal root?", "output": "No", "explanation": "The answer is not mentioned in the text. Hence not answerable."}, {"input": "CONTEXT: Spider-Man: Homecoming is following the Captain America: Civil War. I've seen the same trailer - and the clip with Spidey holding Cap's shield seems to be lifted straight from the CA:CW movie during the airport fight. Later in the trailer (or in another trailer), Peter is boasting to his friend about meeting Iron Man and the Avengers, and how he stole Captain America's shield from him.  <sep> FOLLOWUP_Q: When did Spider-Man steal Captain America's shield?", "output": "Yes", "explanation": "It is mentioned that it happened during a flight scene at airport. So it is answerable."}], "Negative Examples": [{"input": "CONTEXT: Logan's plan earlier in the movie was to buy a sailboat and sail to the ocean with the Professor, where they would spend their last days. Out on the sea, the Professor wouldn't pose a threat to other humans when he lost his control over his ability. If I am not mistaken the Professor liked that idea - being out on the sea. When he died and Logan buried him, it was near a lake, so he was at least near water - Since Logan was emotional about the death of the Professor these were the only words he managed to say as a kind of eulogy. <sep> Q: What was Logan's plan? A: to buy a sailboat and sail to the ocean with the Professor <sep> FOLLOWUP_Q: Where did logan bury Professor?", "output": "No", "explanation": "It is mentioned in the paragraph it was near a lake. Hence it is incorrect."}, {"input": "CONTEXT: Yes. He's supposed to be the same character. The timeline of the story arc is all over the place now but Spectre could be regarded as a prequel to the series before Daniel Craig. Some say a reboot but apparently its all supposed to be the same story. This falls apart because of Judi Denchs M, Bond's previous encounters with Spectre and Blofeld etc though. <sep> Q: Is Franz Oberhauser related to the original Blofeld? A: He's supposed to be the same character <sep> FOLLOWUP_Q: Why was Bond running over the train?", "output": "Yes", "explanation": "The passage does not have information about why Mr. Bond was running."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Movies", "Dialogue"], "Instance": {"id": "task1442-67a98662a8924ee5adc23b0be17d12da", "input": "CONTEXT: Ada buys back the piano one key at a time by playing for him. Making love to him counts for ten times playing for him. At this point the relation between Ada and Baine is highly asymmetric: Baine desires Ada, Ada desires her piano. Only later does Ada fall in love with Baine.  <sep>  Q: Who plays the piano, Ada or Baine? A: Ada buys back the piano one key at a time by playing for him  <sep> FOLLOWUP_Q: Are Ada and Baine married?", "output": ["No"]}, "Instance License": ["CC BY-SA 4.0"], "prediction": "Yes"}
+{"id": "task1442-3fcf7413530d4eca871f997623fbb9ee", "Task": "task1442_doqa_movies_isanswerable", "Contributors": "['Kuntal Kumar Pal']", "Source": ["doqa"], "URL": ["http://www.ixa.eus/node/12931"], "Categories": ["Answerability Classification"], "Reasoning": ["Reasoning on Social Interactions"], "Definition": ["Given a paragraph about movies and a set of conversational questions and answers about the paragraph, say whether the passage contains sufficient information to answer the follow-up question. Say Yes if it is answerable; otherwise, say No. The paragraph has the prefix 'CONTEXT:'. Each conversation question has a prefix `Q:` followed by the answer prefix `A:`, and the follow-up question has a prefix `FOLLOWUP_Q:`."], "Positive Examples": [{"input": "CONTEXT: I think it's deliberately ambiguous. If it's real, the inconsistencies are easily explained by Vidal's fascist belief system. These elements simply are not part of his world. If it's fantasy, then of course only Ofelia can see these thing because she imagined them. I think part of Del Toro's purpose in the film was to maintain the plausibility of both of these interpretations. <sep> Q: Is Ofelia just dreaming things to get herself in a fairy world? A: If it's fantasy, then of course only Ofelia can see these thing because she imagined them  Q: Are the things happening for real but visible only to Ofelia? A: If it's real, the inconsistencies are easily explained by Vidal's fascist belief system. These elements simply are not part of his world  <sep> FOLLOWUP_Q: When Vidal pulls the mandrake root out of Ofelia's mother's bed, is it just a normal root?", "output": "No", "explanation": "The answer is not mentioned in the text. Hence not answerable."}, {"input": "CONTEXT: Spider-Man: Homecoming is following the Captain America: Civil War. I've seen the same trailer - and the clip with Spidey holding Cap's shield seems to be lifted straight from the CA:CW movie during the airport fight. Later in the trailer (or in another trailer), Peter is boasting to his friend about meeting Iron Man and the Avengers, and how he stole Captain America's shield from him.  <sep> FOLLOWUP_Q: When did Spider-Man steal Captain America's shield?", "output": "Yes", "explanation": "It is mentioned that it happened during a flight scene at airport. So it is answerable."}], "Negative Examples": [{"input": "CONTEXT: Logan's plan earlier in the movie was to buy a sailboat and sail to the ocean with the Professor, where they would spend their last days. Out on the sea, the Professor wouldn't pose a threat to other humans when he lost his control over his ability. If I am not mistaken the Professor liked that idea - being out on the sea. When he died and Logan buried him, it was near a lake, so he was at least near water - Since Logan was emotional about the death of the Professor these were the only words he managed to say as a kind of eulogy. <sep> Q: What was Logan's plan? A: to buy a sailboat and sail to the ocean with the Professor <sep> FOLLOWUP_Q: Where did logan bury Professor?", "output": "No", "explanation": "It is mentioned in the paragraph it was near a lake. Hence it is incorrect."}, {"input": "CONTEXT: Yes. He's supposed to be the same character. The timeline of the story arc is all over the place now but Spectre could be regarded as a prequel to the series before Daniel Craig. Some say a reboot but apparently its all supposed to be the same story. This falls apart because of Judi Denchs M, Bond's previous encounters with Spectre and Blofeld etc though. <sep> Q: Is Franz Oberhauser related to the original Blofeld? A: He's supposed to be the same character <sep> FOLLOWUP_Q: Why was Bond running over the train?", "output": "Yes", "explanation": "The passage does not have information about why Mr. Bond was running."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Movies", "Dialogue"], "Instance": {"id": "task1442-3fcf7413530d4eca871f997623fbb9ee", "input": "CONTEXT: Having seen the movie several times, I don't think anything was \"dragging\" the girl (Carina, possibly?) towards the Infinity Stone other than her own desire. She had just finished listening to Tanleer explain how powerful the stone is, and earlier in the movie we had seen how he verbally abuses her and forces her to do very menial and back-breaking work. She saw the stone as a possibility to escape. What you're interpreting as her being pulled toward the stone, I think, is actually her being very hesitant to touch it. Her own internal conflict between the need to escape her situation vs. her fear of the stone is what makes her take so long to try and grab it, but obviously, her desire to be free wins out.  <sep>  Q: What dragged the Collector's servant towards the Infinity Stone?", "output": ["Yes"]}, "Instance License": ["CC BY-SA 4.0"], "prediction": "No"}
+{"id": "task1442-508f58d65c9d4ab398fc11af9ed3488f", "Task": "task1442_doqa_movies_isanswerable", "Contributors": "['Kuntal Kumar Pal']", "Source": ["doqa"], "URL": ["http://www.ixa.eus/node/12931"], "Categories": ["Answerability Classification"], "Reasoning": ["Reasoning on Social Interactions"], "Definition": ["Given a paragraph about movies and a set of conversational questions and answers about the paragraph, say whether the passage contains sufficient information to answer the follow-up question. Say Yes if it is answerable; otherwise, say No. The paragraph has the prefix 'CONTEXT:'. Each conversation question has a prefix `Q:` followed by the answer prefix `A:`, and the follow-up question has a prefix `FOLLOWUP_Q:`."], "Positive Examples": [{"input": "CONTEXT: I think it's deliberately ambiguous. If it's real, the inconsistencies are easily explained by Vidal's fascist belief system. These elements simply are not part of his world. If it's fantasy, then of course only Ofelia can see these thing because she imagined them. I think part of Del Toro's purpose in the film was to maintain the plausibility of both of these interpretations. <sep> Q: Is Ofelia just dreaming things to get herself in a fairy world? A: If it's fantasy, then of course only Ofelia can see these thing because she imagined them  Q: Are the things happening for real but visible only to Ofelia? A: If it's real, the inconsistencies are easily explained by Vidal's fascist belief system. These elements simply are not part of his world  <sep> FOLLOWUP_Q: When Vidal pulls the mandrake root out of Ofelia's mother's bed, is it just a normal root?", "output": "No", "explanation": "The answer is not mentioned in the text. Hence not answerable."}, {"input": "CONTEXT: Spider-Man: Homecoming is following the Captain America: Civil War. I've seen the same trailer - and the clip with Spidey holding Cap's shield seems to be lifted straight from the CA:CW movie during the airport fight. Later in the trailer (or in another trailer), Peter is boasting to his friend about meeting Iron Man and the Avengers, and how he stole Captain America's shield from him.  <sep> FOLLOWUP_Q: When did Spider-Man steal Captain America's shield?", "output": "Yes", "explanation": "It is mentioned that it happened during a flight scene at airport. So it is answerable."}], "Negative Examples": [{"input": "CONTEXT: Logan's plan earlier in the movie was to buy a sailboat and sail to the ocean with the Professor, where they would spend their last days. Out on the sea, the Professor wouldn't pose a threat to other humans when he lost his control over his ability. If I am not mistaken the Professor liked that idea - being out on the sea. When he died and Logan buried him, it was near a lake, so he was at least near water - Since Logan was emotional about the death of the Professor these were the only words he managed to say as a kind of eulogy. <sep> Q: What was Logan's plan? A: to buy a sailboat and sail to the ocean with the Professor <sep> FOLLOWUP_Q: Where did logan bury Professor?", "output": "No", "explanation": "It is mentioned in the paragraph it was near a lake. Hence it is incorrect."}, {"input": "CONTEXT: Yes. He's supposed to be the same character. The timeline of the story arc is all over the place now but Spectre could be regarded as a prequel to the series before Daniel Craig. Some say a reboot but apparently its all supposed to be the same story. This falls apart because of Judi Denchs M, Bond's previous encounters with Spectre and Blofeld etc though. <sep> Q: Is Franz Oberhauser related to the original Blofeld? A: He's supposed to be the same character <sep> FOLLOWUP_Q: Why was Bond running over the train?", "output": "Yes", "explanation": "The passage does not have information about why Mr. Bond was running."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Movies", "Dialogue"], "Instance": {"id": "task1442-508f58d65c9d4ab398fc11af9ed3488f", "input": "CONTEXT: It seems as though you answered your own questions, and that's the answer I was going to give: Caleb knew (or suspected) that Nathan had heard his conversations with Ava. If Caleb hadn't tried to get Nathan drunk that morning, Nathan would have known that Caleb ALREADY completed his plan, and he would have undone the computer code that Caleb altered.  <sep>  Q: Was Nathan listening in on his conversations with Ava?", "output": ["Yes"]}, "Instance License": ["CC BY-SA 4.0"], "prediction": "Yes"}
+{"id": "task1442-0e38eaf9a2724e26aa52ed1cca1a3087", "Task": "task1442_doqa_movies_isanswerable", "Contributors": "['Kuntal Kumar Pal']", "Source": ["doqa"], "URL": ["http://www.ixa.eus/node/12931"], "Categories": ["Answerability Classification"], "Reasoning": ["Reasoning on Social Interactions"], "Definition": ["Given a paragraph about movies and a set of conversational questions and answers about the paragraph, say whether the passage contains sufficient information to answer the follow-up question. Say Yes if it is answerable; otherwise, say No. The paragraph has the prefix 'CONTEXT:'. Each conversation question has a prefix `Q:` followed by the answer prefix `A:`, and the follow-up question has a prefix `FOLLOWUP_Q:`."], "Positive Examples": [{"input": "CONTEXT: I think it's deliberately ambiguous. If it's real, the inconsistencies are easily explained by Vidal's fascist belief system. These elements simply are not part of his world. If it's fantasy, then of course only Ofelia can see these thing because she imagined them. I think part of Del Toro's purpose in the film was to maintain the plausibility of both of these interpretations. <sep> Q: Is Ofelia just dreaming things to get herself in a fairy world? A: If it's fantasy, then of course only Ofelia can see these thing because she imagined them  Q: Are the things happening for real but visible only to Ofelia? A: If it's real, the inconsistencies are easily explained by Vidal's fascist belief system. These elements simply are not part of his world  <sep> FOLLOWUP_Q: When Vidal pulls the mandrake root out of Ofelia's mother's bed, is it just a normal root?", "output": "No", "explanation": "The answer is not mentioned in the text. Hence not answerable."}, {"input": "CONTEXT: Spider-Man: Homecoming is following the Captain America: Civil War. I've seen the same trailer - and the clip with Spidey holding Cap's shield seems to be lifted straight from the CA:CW movie during the airport fight. Later in the trailer (or in another trailer), Peter is boasting to his friend about meeting Iron Man and the Avengers, and how he stole Captain America's shield from him.  <sep> FOLLOWUP_Q: When did Spider-Man steal Captain America's shield?", "output": "Yes", "explanation": "It is mentioned that it happened during a flight scene at airport. So it is answerable."}], "Negative Examples": [{"input": "CONTEXT: Logan's plan earlier in the movie was to buy a sailboat and sail to the ocean with the Professor, where they would spend their last days. Out on the sea, the Professor wouldn't pose a threat to other humans when he lost his control over his ability. If I am not mistaken the Professor liked that idea - being out on the sea. When he died and Logan buried him, it was near a lake, so he was at least near water - Since Logan was emotional about the death of the Professor these were the only words he managed to say as a kind of eulogy. <sep> Q: What was Logan's plan? A: to buy a sailboat and sail to the ocean with the Professor <sep> FOLLOWUP_Q: Where did logan bury Professor?", "output": "No", "explanation": "It is mentioned in the paragraph it was near a lake. Hence it is incorrect."}, {"input": "CONTEXT: Yes. He's supposed to be the same character. The timeline of the story arc is all over the place now but Spectre could be regarded as a prequel to the series before Daniel Craig. Some say a reboot but apparently its all supposed to be the same story. This falls apart because of Judi Denchs M, Bond's previous encounters with Spectre and Blofeld etc though. <sep> Q: Is Franz Oberhauser related to the original Blofeld? A: He's supposed to be the same character <sep> FOLLOWUP_Q: Why was Bond running over the train?", "output": "Yes", "explanation": "The passage does not have information about why Mr. Bond was running."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Movies", "Dialogue"], "Instance": {"id": "task1442-0e38eaf9a2724e26aa52ed1cca1a3087", "input": "CONTEXT: Well, what we know is that Bill was a former student of Hattori Hanzo. What actually happened between Bill and Hanzo is not clear from the movie. There is also no mention of it on Kill Bill Wikia. However we can assume that Bill learnt the art of swordsmanship from Hanzo and used it for evil. This must have infuriated Hanzo. This kind of stuff is a recurring theme in many movies where a disciple learns a skill from a master and turns again humanity to use those skills, hence infuriating the master. So to me, this seems the possible reason for Hanzo's anger.  <sep>  Q: What did Bill do to make Hanzo mad? A: Bill learnt the art of swordsmanship from Hanzo and used it for evil. This must have infuriated Hanzo  <sep> FOLLOWUP_Q: How did the black mambo meet Hanzo?", "output": ["No"]}, "Instance License": ["CC BY-SA 4.0"], "prediction": "Yes"}
+{"id": "task1442-ee99f9ebde30435eac7e23b5a12a2c81", "Task": "task1442_doqa_movies_isanswerable", "Contributors": "['Kuntal Kumar Pal']", "Source": ["doqa"], "URL": ["http://www.ixa.eus/node/12931"], "Categories": ["Answerability Classification"], "Reasoning": ["Reasoning on Social Interactions"], "Definition": ["Given a paragraph about movies and a set of conversational questions and answers about the paragraph, say whether the passage contains sufficient information to answer the follow-up question. Say Yes if it is answerable; otherwise, say No. The paragraph has the prefix 'CONTEXT:'. Each conversation question has a prefix `Q:` followed by the answer prefix `A:`, and the follow-up question has a prefix `FOLLOWUP_Q:`."], "Positive Examples": [{"input": "CONTEXT: I think it's deliberately ambiguous. If it's real, the inconsistencies are easily explained by Vidal's fascist belief system. These elements simply are not part of his world. If it's fantasy, then of course only Ofelia can see these thing because she imagined them. I think part of Del Toro's purpose in the film was to maintain the plausibility of both of these interpretations. <sep> Q: Is Ofelia just dreaming things to get herself in a fairy world? A: If it's fantasy, then of course only Ofelia can see these thing because she imagined them  Q: Are the things happening for real but visible only to Ofelia? A: If it's real, the inconsistencies are easily explained by Vidal's fascist belief system. These elements simply are not part of his world  <sep> FOLLOWUP_Q: When Vidal pulls the mandrake root out of Ofelia's mother's bed, is it just a normal root?", "output": "No", "explanation": "The answer is not mentioned in the text. Hence not answerable."}, {"input": "CONTEXT: Spider-Man: Homecoming is following the Captain America: Civil War. I've seen the same trailer - and the clip with Spidey holding Cap's shield seems to be lifted straight from the CA:CW movie during the airport fight. Later in the trailer (or in another trailer), Peter is boasting to his friend about meeting Iron Man and the Avengers, and how he stole Captain America's shield from him.  <sep> FOLLOWUP_Q: When did Spider-Man steal Captain America's shield?", "output": "Yes", "explanation": "It is mentioned that it happened during a flight scene at airport. So it is answerable."}], "Negative Examples": [{"input": "CONTEXT: Logan's plan earlier in the movie was to buy a sailboat and sail to the ocean with the Professor, where they would spend their last days. Out on the sea, the Professor wouldn't pose a threat to other humans when he lost his control over his ability. If I am not mistaken the Professor liked that idea - being out on the sea. When he died and Logan buried him, it was near a lake, so he was at least near water - Since Logan was emotional about the death of the Professor these were the only words he managed to say as a kind of eulogy. <sep> Q: What was Logan's plan? A: to buy a sailboat and sail to the ocean with the Professor <sep> FOLLOWUP_Q: Where did logan bury Professor?", "output": "No", "explanation": "It is mentioned in the paragraph it was near a lake. Hence it is incorrect."}, {"input": "CONTEXT: Yes. He's supposed to be the same character. The timeline of the story arc is all over the place now but Spectre could be regarded as a prequel to the series before Daniel Craig. Some say a reboot but apparently its all supposed to be the same story. This falls apart because of Judi Denchs M, Bond's previous encounters with Spectre and Blofeld etc though. <sep> Q: Is Franz Oberhauser related to the original Blofeld? A: He's supposed to be the same character <sep> FOLLOWUP_Q: Why was Bond running over the train?", "output": "Yes", "explanation": "The passage does not have information about why Mr. Bond was running."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Movies", "Dialogue"], "Instance": {"id": "task1442-ee99f9ebde30435eac7e23b5a12a2c81", "input": "CONTEXT: Sam loses his powers whenever he stops drinking demon blood. Bobby and Dean made him go through a detox in order to get all of the demon blood out of him. It looks like this happened some time in season 4 after Dean came back. However in at least one episode Sam intentially drank demon blood for one reason or another and ends up going through detox again. At the end of season 5 we see him drinking gallons of demon blood to prepare him to host Lucifer so that they can capture him.  <sep>  Q: When does Sam lose his psychic powers? A: Sam loses his powers whenever he stops drinking demon blood  Q: What show is this? A: season 4  Q: Who are the main characters? A: Bobby and Dean  Q: Which season does he lose his powers? A: season 4  <sep> FOLLOWUP_Q: Was it when Sam was brought back from hell?", "output": ["Yes"]}, "Instance License": ["CC BY-SA 4.0"], "prediction": "Yes"}
+{"id": "task233-56789dcda39342189dcac9ad7f79d573", "Task": "task233_iirc_link_exists_classification", "Contributors": "['Anjana Arunkumar']", "Source": ["iirc"], "URL": ["https://allenai.org/data/iirc"], "Categories": ["Answerability Classification"], "Reasoning": ["Multihop Reasoning", "Cross-document Reasoning", "Discrete Reasoning", "Numerical Reasoning", "Temporal Reasoning"], "Definition": ["In this task, you're given a question, along with a context passage. The passage will not have a direct answer to the question, but can include some information and a clue for the answer. Assuming you can only obtain information about one entity in the passage, your job is to determine whether information from the passage can be used to answer the question. Indicate your choice as `a` for Yes or `b` for No."], "Positive Examples": [{"input": "Question: When did the operation during which the 704th dropped supplies to allied troops near Nijmegen begin? Passage: The group was occasionally diverted from strategic missions to carry out air support and interdiction missions. It supported Operation Overlord, the invasion of Normandy by attacking transportation targets, including bridges, along with airfields and strong points in France. On D Day, the squadron and the rest of the 446th Group led the first heavy bomber mission of the day. The 446th aided ground forces at Caen and Saint-L\u00f4 during July by hitting bridges, gun batteries, and enemy troops. During Operation Market Garden, the attempt to seize a bridgehead across the Rhine in the Netherlands, the 704th dropped supplies to allied troops near Nijmegen. It struck lines of communications during the Battle of the Bulge. During Operation Varsity in March 1945, it supplied ground and airborne troops near Wesel. The squadron flew its last combat mission on 25 April 1945 against Salzburg, Austria. The group had flown 273 missions and had lost 58 aircraft during the war,\n.", "output": "a", "explanation": "The passage describes the 704th's actions during Operation Market Garden, so we can use the operation's name as a clue to find the answer to the question."}, {"input": "Question: What cities did the 1st tanks division's defensive line run through? Passage: In March 1945, the 1st Tank Division with its 5th Armored Regiment was reassigned to the Japanese home islands in preparation for the expected invasion by Allied forces. It gained the IJA 1st Armored Regiment from the 3rd Tank Division, and formed part of the IJA 36th Army under the Japanese Twelfth Area Army. The headquarters unit and IJA 1st Armored Regiment were based in Sano, Tochigi, with the IJA 5th Armored Regiment stationed at \u014ctawara, Tochigi (and later relocated to Kazo, Saitama, and the IJA 1st Mechanized Infantry Regiment and the Division\u2019s mechanized artillery stationed at Tochigi. Anticipating that Allied forces would land at Kuj\u016bkuri Beach, the 1st Tank Division was to hold a defensive line stretching from Mount Tsukuba to the Tama River, with forward units deployed to Choshi, Chiba. The surrender of Japan came before the landing, and the 1st Armored Division did not see any combat on Japanese soil.\n.", "output": "b", "explanation": "The 1st tanks division's defensive line is mentioned in the passage, but to find the answer, one must obtain information about both \"Mount Tsukuba\" and \"Tama River\"."}, {"input": "Question: What was the population of Los Angeles when Jarrett moved there to start screenwriting? Passage: His first feature film role was in the teen comedy \"Summer Job\", where he played an effete hairdresser. Next came minor roles in such films as The Bodyguard with Kevin Costner and Whitney Houston as well as Miami Vice and Unsolved Mysteries. His original screenplay Laws of Deception was made into a film in 1997 and starred C. Thomas Howell, James Russo and Brian Austin Green and was directed by Joey Travolta, brother of John Travolta. Jarrett had a small role in this film as Mr. Farina, a corrupt businessman.", "output": "b", "explanation": "The passage does not have any terms pertaining to Los Angeles. So there's no clue leading to an answer."}, {"input": "Question: Which song holds the record of longest weeks at number 1 on the chart where The American Breed's greatest single reached number 5 in 1968? Passage:The group was formed in Cicero, Illinois, United States, as Gary & The Knight Lites. The founding members included Gary Loizzo (vocals and guitar), Charles Colbert, Jr. (bass guitar and vocals), Al Ciner (guitar and vocals), and Jim Michalak (drums). Early releases included- \"I'm Glad She's Mine,\" \"I Don't Need Your Help,\" \"Will You Go Steady,\" \"Take Me Back,\" among others. The group's greatest success as \"The American Breed\" was the single, \"Bend Me, Shape Me\", which reached number five on the U.S. Billboard Hot 100 chart in 1968. The song, written by Scott English and Larry Weiss, had previously been recorded by an all-female band known as the Shape and had been a hit on the UK Singles Chart for the British group Amen Corner. It had also been recorded by The Outsiders after they had reached the top ten with \"Time Won't Let Me\" in 1966. Contributing to the success of the American Breed's version of \"Bend Me, Shape Me\" was the excellent arrangement of the song by the band's record producer, Bill Traut, who added horns among other changes. The group also appeared on the 16 December 1967 episode of the television show American Bandstand, along with Pink Floyd.\n", "output": "a", "explanation": "According to the passage, the chart where The American Breed's greatest single reached number 5 in 1968 is \"U.S. Billboard Hot 100 chart\". So by obtaining information about that chart, one can answer the question."}], "Negative Examples": [{"input": "Question: How many Super Bowls did the team the Cardinals beat to make their first appearance in the Super Bowl win? Passage: The 2008 Arizona Cardinals season was the 89th season for the team in the National Football League and their 21st season in Arizona. The season marked the Cardinals' first Super Bowl appearance, coming as a result of their victory against the Philadelphia Eagles in the NFC Championship. The Cardinals slogan for the season was \"Shock The World!\" Riding the back of quarterback Kurt Warner, who had gone from being a backup for the St. Louis Rams in 1999 to leading the Greatest Show on Turf to a Super Bowl XXXIV victory, and franchise wide receiver Larry Fitzgerald, the Cardinals went on a playoff run for the ages after having won just one playoff game in the last sixty years, as Warner once again recreated the magic he had captured with the Rams. (Coincidentally, both teams were based in St Louis at one point or another, only to relocate to different cities.)\n.", "output": "b", "explanation": "The team that the Cardinals beat is mentioned in the passage as the Eagles, so any further information to answer the question can be obtained with one step(by getting information on the Eagles). The correct ansewr is \"a\"."}, {"input": "Question: What margin did liberals lose to conservatives in 2010? Passage: This remained the case until the 2018 local elections when the Liberal Democrats regained one of the three seats by a single vote. The Liberal Democrats also regained control of the Council. Richmond Park, the constituency which includes Mortlake, had changed from Liberal Democrat to Conservative in the general election, was recaptured by the Liberal Democrats in the 2016 by-election, and finally reverted to Conservative MP Zac Goldsmith in the 2017 general election by a margin of only 45 votes. The London Assembly constituency South West, which includes Mortlake, is represented by former local councillor Tony Arbour (Conservative).\n", "output": "a", "explanation": "None of the terms in the passage talk about the 2010 elections."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Wikipedia"], "Instance": {"id": "task233-56789dcda39342189dcac9ad7f79d573", "input": "Question: Which of the people that  Sir Simon Fraser fought with during the Scottish Wars of Independence was the oldest? Passage:During the Scottish Wars of Independence, Sir Simon Fraser, known as \"the Patriot\", fought first with the Red Comyn, and later with Sir William Wallace and Robert the Bruce. Sir Simon is celebrated for having defeated the English at the Battle of Roslin in 1303, with just 8,000 men under his command. At the Battle of Methven in 1306, Sir Simon Fraser led troops along with Bruce, and saved the King's life in three separate instances. Simon was allegedly awarded the 3 Crowns which now appear in the Lovat Arms for these three acts of bravery. He was however captured by the English and executed with great cruelty by Edward I of England in 1306, in the same barbaric fashion as Wallace. At the Battle of Bannockburn in 1314, Sir Simon's cousin, Sir Alexander Fraser of Touchfraser and Cowie, was much more fortunate. He fought at Bannockburn, married Bruce's sister, and became Chamberlain of Scotland. The Frasers of Philorth who are chiefs of the senior Clan Fraser trace their lineage from this Alexander. Alexander's younger brother, another Sir Simon Fraser, was the ancestor of the chiefs of the Clan Fraser of Lovat. This Simon Fraser was killed at the Battle of Halidon Hill in 1333, along with his younger brothers Andrew and James.\n", "output": ["a"]}, "Instance License": ["CC BY 4.0"], "prediction": "b"}
+{"id": "task233-83bc006998bb430898b754cc02458d39", "Task": "task233_iirc_link_exists_classification", "Contributors": "['Anjana Arunkumar']", "Source": ["iirc"], "URL": ["https://allenai.org/data/iirc"], "Categories": ["Answerability Classification"], "Reasoning": ["Multihop Reasoning", "Cross-document Reasoning", "Discrete Reasoning", "Numerical Reasoning", "Temporal Reasoning"], "Definition": ["In this task, you're given a question, along with a context passage. The passage will not have a direct answer to the question, but can include some information and a clue for the answer. Assuming you can only obtain information about one entity in the passage, your job is to determine whether information from the passage can be used to answer the question. Indicate your choice as `a` for Yes or `b` for No."], "Positive Examples": [{"input": "Question: When did the operation during which the 704th dropped supplies to allied troops near Nijmegen begin? Passage: The group was occasionally diverted from strategic missions to carry out air support and interdiction missions. It supported Operation Overlord, the invasion of Normandy by attacking transportation targets, including bridges, along with airfields and strong points in France. On D Day, the squadron and the rest of the 446th Group led the first heavy bomber mission of the day. The 446th aided ground forces at Caen and Saint-L\u00f4 during July by hitting bridges, gun batteries, and enemy troops. During Operation Market Garden, the attempt to seize a bridgehead across the Rhine in the Netherlands, the 704th dropped supplies to allied troops near Nijmegen. It struck lines of communications during the Battle of the Bulge. During Operation Varsity in March 1945, it supplied ground and airborne troops near Wesel. The squadron flew its last combat mission on 25 April 1945 against Salzburg, Austria. The group had flown 273 missions and had lost 58 aircraft during the war,\n.", "output": "a", "explanation": "The passage describes the 704th's actions during Operation Market Garden, so we can use the operation's name as a clue to find the answer to the question."}, {"input": "Question: What cities did the 1st tanks division's defensive line run through? Passage: In March 1945, the 1st Tank Division with its 5th Armored Regiment was reassigned to the Japanese home islands in preparation for the expected invasion by Allied forces. It gained the IJA 1st Armored Regiment from the 3rd Tank Division, and formed part of the IJA 36th Army under the Japanese Twelfth Area Army. The headquarters unit and IJA 1st Armored Regiment were based in Sano, Tochigi, with the IJA 5th Armored Regiment stationed at \u014ctawara, Tochigi (and later relocated to Kazo, Saitama, and the IJA 1st Mechanized Infantry Regiment and the Division\u2019s mechanized artillery stationed at Tochigi. Anticipating that Allied forces would land at Kuj\u016bkuri Beach, the 1st Tank Division was to hold a defensive line stretching from Mount Tsukuba to the Tama River, with forward units deployed to Choshi, Chiba. The surrender of Japan came before the landing, and the 1st Armored Division did not see any combat on Japanese soil.\n.", "output": "b", "explanation": "The 1st tanks division's defensive line is mentioned in the passage, but to find the answer, one must obtain information about both \"Mount Tsukuba\" and \"Tama River\"."}, {"input": "Question: What was the population of Los Angeles when Jarrett moved there to start screenwriting? Passage: His first feature film role was in the teen comedy \"Summer Job\", where he played an effete hairdresser. Next came minor roles in such films as The Bodyguard with Kevin Costner and Whitney Houston as well as Miami Vice and Unsolved Mysteries. His original screenplay Laws of Deception was made into a film in 1997 and starred C. Thomas Howell, James Russo and Brian Austin Green and was directed by Joey Travolta, brother of John Travolta. Jarrett had a small role in this film as Mr. Farina, a corrupt businessman.", "output": "b", "explanation": "The passage does not have any terms pertaining to Los Angeles. So there's no clue leading to an answer."}, {"input": "Question: Which song holds the record of longest weeks at number 1 on the chart where The American Breed's greatest single reached number 5 in 1968? Passage:The group was formed in Cicero, Illinois, United States, as Gary & The Knight Lites. The founding members included Gary Loizzo (vocals and guitar), Charles Colbert, Jr. (bass guitar and vocals), Al Ciner (guitar and vocals), and Jim Michalak (drums). Early releases included- \"I'm Glad She's Mine,\" \"I Don't Need Your Help,\" \"Will You Go Steady,\" \"Take Me Back,\" among others. The group's greatest success as \"The American Breed\" was the single, \"Bend Me, Shape Me\", which reached number five on the U.S. Billboard Hot 100 chart in 1968. The song, written by Scott English and Larry Weiss, had previously been recorded by an all-female band known as the Shape and had been a hit on the UK Singles Chart for the British group Amen Corner. It had also been recorded by The Outsiders after they had reached the top ten with \"Time Won't Let Me\" in 1966. Contributing to the success of the American Breed's version of \"Bend Me, Shape Me\" was the excellent arrangement of the song by the band's record producer, Bill Traut, who added horns among other changes. The group also appeared on the 16 December 1967 episode of the television show American Bandstand, along with Pink Floyd.\n", "output": "a", "explanation": "According to the passage, the chart where The American Breed's greatest single reached number 5 in 1968 is \"U.S. Billboard Hot 100 chart\". So by obtaining information about that chart, one can answer the question."}], "Negative Examples": [{"input": "Question: How many Super Bowls did the team the Cardinals beat to make their first appearance in the Super Bowl win? Passage: The 2008 Arizona Cardinals season was the 89th season for the team in the National Football League and their 21st season in Arizona. The season marked the Cardinals' first Super Bowl appearance, coming as a result of their victory against the Philadelphia Eagles in the NFC Championship. The Cardinals slogan for the season was \"Shock The World!\" Riding the back of quarterback Kurt Warner, who had gone from being a backup for the St. Louis Rams in 1999 to leading the Greatest Show on Turf to a Super Bowl XXXIV victory, and franchise wide receiver Larry Fitzgerald, the Cardinals went on a playoff run for the ages after having won just one playoff game in the last sixty years, as Warner once again recreated the magic he had captured with the Rams. (Coincidentally, both teams were based in St Louis at one point or another, only to relocate to different cities.)\n.", "output": "b", "explanation": "The team that the Cardinals beat is mentioned in the passage as the Eagles, so any further information to answer the question can be obtained with one step(by getting information on the Eagles). The correct ansewr is \"a\"."}, {"input": "Question: What margin did liberals lose to conservatives in 2010? Passage: This remained the case until the 2018 local elections when the Liberal Democrats regained one of the three seats by a single vote. The Liberal Democrats also regained control of the Council. Richmond Park, the constituency which includes Mortlake, had changed from Liberal Democrat to Conservative in the general election, was recaptured by the Liberal Democrats in the 2016 by-election, and finally reverted to Conservative MP Zac Goldsmith in the 2017 general election by a margin of only 45 votes. The London Assembly constituency South West, which includes Mortlake, is represented by former local councillor Tony Arbour (Conservative).\n", "output": "a", "explanation": "None of the terms in the passage talk about the 2010 elections."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Wikipedia"], "Instance": {"id": "task233-83bc006998bb430898b754cc02458d39", "input": "Question: In which U.S. state is Perlmutter's childhood neighborhood located? Passage:Perlmutter spent his childhood in the Mount Airy neighborhood of Philadelphia. He went to school in nearby Germantown; first Greene Street Friends School for the elementary grades, followed by Germantown Friends School for grades 7 through 12. He graduated with an AB in physics from Harvard magna cum laude in 1981 and received his PhD in physics from the University of California, Berkeley, in 1986. Perlmutter's PhD thesis titled \"An Astrometric Search for a Stellar Companion to the Sun\" described the development and use of an automated telescope to search for Nemesis candidates under Richard A. Muller. At the same time, he was using this telescope to search for Nemesis and supernovae, which would lead him to his award-winning work in cosmology. Perlmutter attributes the idea for an automated supernova search to Luis Alvarez, a 1968 Nobel laureate, who shared his idea with Perlmutter's research adviser.\n", "output": ["b"]}, "Instance License": ["CC BY 4.0"], "prediction": "a"}
+{"id": "task233-cf7cdc427c3442ce9a41f6d26bea1177", "Task": "task233_iirc_link_exists_classification", "Contributors": "['Anjana Arunkumar']", "Source": ["iirc"], "URL": ["https://allenai.org/data/iirc"], "Categories": ["Answerability Classification"], "Reasoning": ["Multihop Reasoning", "Cross-document Reasoning", "Discrete Reasoning", "Numerical Reasoning", "Temporal Reasoning"], "Definition": ["In this task, you're given a question, along with a context passage. The passage will not have a direct answer to the question, but can include some information and a clue for the answer. Assuming you can only obtain information about one entity in the passage, your job is to determine whether information from the passage can be used to answer the question. Indicate your choice as `a` for Yes or `b` for No."], "Positive Examples": [{"input": "Question: When did the operation during which the 704th dropped supplies to allied troops near Nijmegen begin? Passage: The group was occasionally diverted from strategic missions to carry out air support and interdiction missions. It supported Operation Overlord, the invasion of Normandy by attacking transportation targets, including bridges, along with airfields and strong points in France. On D Day, the squadron and the rest of the 446th Group led the first heavy bomber mission of the day. The 446th aided ground forces at Caen and Saint-L\u00f4 during July by hitting bridges, gun batteries, and enemy troops. During Operation Market Garden, the attempt to seize a bridgehead across the Rhine in the Netherlands, the 704th dropped supplies to allied troops near Nijmegen. It struck lines of communications during the Battle of the Bulge. During Operation Varsity in March 1945, it supplied ground and airborne troops near Wesel. The squadron flew its last combat mission on 25 April 1945 against Salzburg, Austria. The group had flown 273 missions and had lost 58 aircraft during the war,\n.", "output": "a", "explanation": "The passage describes the 704th's actions during Operation Market Garden, so we can use the operation's name as a clue to find the answer to the question."}, {"input": "Question: What cities did the 1st tanks division's defensive line run through? Passage: In March 1945, the 1st Tank Division with its 5th Armored Regiment was reassigned to the Japanese home islands in preparation for the expected invasion by Allied forces. It gained the IJA 1st Armored Regiment from the 3rd Tank Division, and formed part of the IJA 36th Army under the Japanese Twelfth Area Army. The headquarters unit and IJA 1st Armored Regiment were based in Sano, Tochigi, with the IJA 5th Armored Regiment stationed at \u014ctawara, Tochigi (and later relocated to Kazo, Saitama, and the IJA 1st Mechanized Infantry Regiment and the Division\u2019s mechanized artillery stationed at Tochigi. Anticipating that Allied forces would land at Kuj\u016bkuri Beach, the 1st Tank Division was to hold a defensive line stretching from Mount Tsukuba to the Tama River, with forward units deployed to Choshi, Chiba. The surrender of Japan came before the landing, and the 1st Armored Division did not see any combat on Japanese soil.\n.", "output": "b", "explanation": "The 1st tanks division's defensive line is mentioned in the passage, but to find the answer, one must obtain information about both \"Mount Tsukuba\" and \"Tama River\"."}, {"input": "Question: What was the population of Los Angeles when Jarrett moved there to start screenwriting? Passage: His first feature film role was in the teen comedy \"Summer Job\", where he played an effete hairdresser. Next came minor roles in such films as The Bodyguard with Kevin Costner and Whitney Houston as well as Miami Vice and Unsolved Mysteries. His original screenplay Laws of Deception was made into a film in 1997 and starred C. Thomas Howell, James Russo and Brian Austin Green and was directed by Joey Travolta, brother of John Travolta. Jarrett had a small role in this film as Mr. Farina, a corrupt businessman.", "output": "b", "explanation": "The passage does not have any terms pertaining to Los Angeles. So there's no clue leading to an answer."}, {"input": "Question: Which song holds the record of longest weeks at number 1 on the chart where The American Breed's greatest single reached number 5 in 1968? Passage:The group was formed in Cicero, Illinois, United States, as Gary & The Knight Lites. The founding members included Gary Loizzo (vocals and guitar), Charles Colbert, Jr. (bass guitar and vocals), Al Ciner (guitar and vocals), and Jim Michalak (drums). Early releases included- \"I'm Glad She's Mine,\" \"I Don't Need Your Help,\" \"Will You Go Steady,\" \"Take Me Back,\" among others. The group's greatest success as \"The American Breed\" was the single, \"Bend Me, Shape Me\", which reached number five on the U.S. Billboard Hot 100 chart in 1968. The song, written by Scott English and Larry Weiss, had previously been recorded by an all-female band known as the Shape and had been a hit on the UK Singles Chart for the British group Amen Corner. It had also been recorded by The Outsiders after they had reached the top ten with \"Time Won't Let Me\" in 1966. Contributing to the success of the American Breed's version of \"Bend Me, Shape Me\" was the excellent arrangement of the song by the band's record producer, Bill Traut, who added horns among other changes. The group also appeared on the 16 December 1967 episode of the television show American Bandstand, along with Pink Floyd.\n", "output": "a", "explanation": "According to the passage, the chart where The American Breed's greatest single reached number 5 in 1968 is \"U.S. Billboard Hot 100 chart\". So by obtaining information about that chart, one can answer the question."}], "Negative Examples": [{"input": "Question: How many Super Bowls did the team the Cardinals beat to make their first appearance in the Super Bowl win? Passage: The 2008 Arizona Cardinals season was the 89th season for the team in the National Football League and their 21st season in Arizona. The season marked the Cardinals' first Super Bowl appearance, coming as a result of their victory against the Philadelphia Eagles in the NFC Championship. The Cardinals slogan for the season was \"Shock The World!\" Riding the back of quarterback Kurt Warner, who had gone from being a backup for the St. Louis Rams in 1999 to leading the Greatest Show on Turf to a Super Bowl XXXIV victory, and franchise wide receiver Larry Fitzgerald, the Cardinals went on a playoff run for the ages after having won just one playoff game in the last sixty years, as Warner once again recreated the magic he had captured with the Rams. (Coincidentally, both teams were based in St Louis at one point or another, only to relocate to different cities.)\n.", "output": "b", "explanation": "The team that the Cardinals beat is mentioned in the passage as the Eagles, so any further information to answer the question can be obtained with one step(by getting information on the Eagles). The correct ansewr is \"a\"."}, {"input": "Question: What margin did liberals lose to conservatives in 2010? Passage: This remained the case until the 2018 local elections when the Liberal Democrats regained one of the three seats by a single vote. The Liberal Democrats also regained control of the Council. Richmond Park, the constituency which includes Mortlake, had changed from Liberal Democrat to Conservative in the general election, was recaptured by the Liberal Democrats in the 2016 by-election, and finally reverted to Conservative MP Zac Goldsmith in the 2017 general election by a margin of only 45 votes. The London Assembly constituency South West, which includes Mortlake, is represented by former local councillor Tony Arbour (Conservative).\n", "output": "a", "explanation": "None of the terms in the passage talk about the 2010 elections."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Wikipedia"], "Instance": {"id": "task233-cf7cdc427c3442ce9a41f6d26bea1177", "input": "Question: When did the war that ended in 205 BC begin? Passage:In 205 BC, the First Macedonian War came to an end with the signing of the Treaty of Phoenice, under the terms of which the Macedonians were not allowed to expand westwards. Rome, meanwhile, was preoccupied with Carthage, and Philip hoped to take advantage of this to seize control of the Greek world. He knew that his ambitions would be aided by an alliance with Crete and began pressing the Cretans to attack Rhodian assets. Having crushed Pergamum, the dominant Greek state in Asia Minor, and formed an alliance with Aetolia, Philip was now opposed by no major Greek power other than Rhodes. Rhodes, an island state that dominated the south-eastern Mediterranean economically and militarily, was formally allied to Philip, but was also allied to his enemy Rome. Furthermore, Philip worked towards consolidating his position as the major power in the Balkans. Marching his forces to Macedon's northern frontier, he inflicted a crushing defeat on the Illyrians, who lost 10,000 men in battle. With his northern frontier secured, Philip was able to turn his attention towards the Aegean Sea.\n", "output": ["b"]}, "Instance License": ["CC BY 4.0"], "prediction": "b"}
+{"id": "task233-bff5ea2de23e4afbb033953670c2c160", "Task": "task233_iirc_link_exists_classification", "Contributors": "['Anjana Arunkumar']", "Source": ["iirc"], "URL": ["https://allenai.org/data/iirc"], "Categories": ["Answerability Classification"], "Reasoning": ["Multihop Reasoning", "Cross-document Reasoning", "Discrete Reasoning", "Numerical Reasoning", "Temporal Reasoning"], "Definition": ["In this task, you're given a question, along with a context passage. The passage will not have a direct answer to the question, but can include some information and a clue for the answer. Assuming you can only obtain information about one entity in the passage, your job is to determine whether information from the passage can be used to answer the question. Indicate your choice as `a` for Yes or `b` for No."], "Positive Examples": [{"input": "Question: When did the operation during which the 704th dropped supplies to allied troops near Nijmegen begin? Passage: The group was occasionally diverted from strategic missions to carry out air support and interdiction missions. It supported Operation Overlord, the invasion of Normandy by attacking transportation targets, including bridges, along with airfields and strong points in France. On D Day, the squadron and the rest of the 446th Group led the first heavy bomber mission of the day. The 446th aided ground forces at Caen and Saint-L\u00f4 during July by hitting bridges, gun batteries, and enemy troops. During Operation Market Garden, the attempt to seize a bridgehead across the Rhine in the Netherlands, the 704th dropped supplies to allied troops near Nijmegen. It struck lines of communications during the Battle of the Bulge. During Operation Varsity in March 1945, it supplied ground and airborne troops near Wesel. The squadron flew its last combat mission on 25 April 1945 against Salzburg, Austria. The group had flown 273 missions and had lost 58 aircraft during the war,\n.", "output": "a", "explanation": "The passage describes the 704th's actions during Operation Market Garden, so we can use the operation's name as a clue to find the answer to the question."}, {"input": "Question: What cities did the 1st tanks division's defensive line run through? Passage: In March 1945, the 1st Tank Division with its 5th Armored Regiment was reassigned to the Japanese home islands in preparation for the expected invasion by Allied forces. It gained the IJA 1st Armored Regiment from the 3rd Tank Division, and formed part of the IJA 36th Army under the Japanese Twelfth Area Army. The headquarters unit and IJA 1st Armored Regiment were based in Sano, Tochigi, with the IJA 5th Armored Regiment stationed at \u014ctawara, Tochigi (and later relocated to Kazo, Saitama, and the IJA 1st Mechanized Infantry Regiment and the Division\u2019s mechanized artillery stationed at Tochigi. Anticipating that Allied forces would land at Kuj\u016bkuri Beach, the 1st Tank Division was to hold a defensive line stretching from Mount Tsukuba to the Tama River, with forward units deployed to Choshi, Chiba. The surrender of Japan came before the landing, and the 1st Armored Division did not see any combat on Japanese soil.\n.", "output": "b", "explanation": "The 1st tanks division's defensive line is mentioned in the passage, but to find the answer, one must obtain information about both \"Mount Tsukuba\" and \"Tama River\"."}, {"input": "Question: What was the population of Los Angeles when Jarrett moved there to start screenwriting? Passage: His first feature film role was in the teen comedy \"Summer Job\", where he played an effete hairdresser. Next came minor roles in such films as The Bodyguard with Kevin Costner and Whitney Houston as well as Miami Vice and Unsolved Mysteries. His original screenplay Laws of Deception was made into a film in 1997 and starred C. Thomas Howell, James Russo and Brian Austin Green and was directed by Joey Travolta, brother of John Travolta. Jarrett had a small role in this film as Mr. Farina, a corrupt businessman.", "output": "b", "explanation": "The passage does not have any terms pertaining to Los Angeles. So there's no clue leading to an answer."}, {"input": "Question: Which song holds the record of longest weeks at number 1 on the chart where The American Breed's greatest single reached number 5 in 1968? Passage:The group was formed in Cicero, Illinois, United States, as Gary & The Knight Lites. The founding members included Gary Loizzo (vocals and guitar), Charles Colbert, Jr. (bass guitar and vocals), Al Ciner (guitar and vocals), and Jim Michalak (drums). Early releases included- \"I'm Glad She's Mine,\" \"I Don't Need Your Help,\" \"Will You Go Steady,\" \"Take Me Back,\" among others. The group's greatest success as \"The American Breed\" was the single, \"Bend Me, Shape Me\", which reached number five on the U.S. Billboard Hot 100 chart in 1968. The song, written by Scott English and Larry Weiss, had previously been recorded by an all-female band known as the Shape and had been a hit on the UK Singles Chart for the British group Amen Corner. It had also been recorded by The Outsiders after they had reached the top ten with \"Time Won't Let Me\" in 1966. Contributing to the success of the American Breed's version of \"Bend Me, Shape Me\" was the excellent arrangement of the song by the band's record producer, Bill Traut, who added horns among other changes. The group also appeared on the 16 December 1967 episode of the television show American Bandstand, along with Pink Floyd.\n", "output": "a", "explanation": "According to the passage, the chart where The American Breed's greatest single reached number 5 in 1968 is \"U.S. Billboard Hot 100 chart\". So by obtaining information about that chart, one can answer the question."}], "Negative Examples": [{"input": "Question: How many Super Bowls did the team the Cardinals beat to make their first appearance in the Super Bowl win? Passage: The 2008 Arizona Cardinals season was the 89th season for the team in the National Football League and their 21st season in Arizona. The season marked the Cardinals' first Super Bowl appearance, coming as a result of their victory against the Philadelphia Eagles in the NFC Championship. The Cardinals slogan for the season was \"Shock The World!\" Riding the back of quarterback Kurt Warner, who had gone from being a backup for the St. Louis Rams in 1999 to leading the Greatest Show on Turf to a Super Bowl XXXIV victory, and franchise wide receiver Larry Fitzgerald, the Cardinals went on a playoff run for the ages after having won just one playoff game in the last sixty years, as Warner once again recreated the magic he had captured with the Rams. (Coincidentally, both teams were based in St Louis at one point or another, only to relocate to different cities.)\n.", "output": "b", "explanation": "The team that the Cardinals beat is mentioned in the passage as the Eagles, so any further information to answer the question can be obtained with one step(by getting information on the Eagles). The correct ansewr is \"a\"."}, {"input": "Question: What margin did liberals lose to conservatives in 2010? Passage: This remained the case until the 2018 local elections when the Liberal Democrats regained one of the three seats by a single vote. The Liberal Democrats also regained control of the Council. Richmond Park, the constituency which includes Mortlake, had changed from Liberal Democrat to Conservative in the general election, was recaptured by the Liberal Democrats in the 2016 by-election, and finally reverted to Conservative MP Zac Goldsmith in the 2017 general election by a margin of only 45 votes. The London Assembly constituency South West, which includes Mortlake, is represented by former local councillor Tony Arbour (Conservative).\n", "output": "a", "explanation": "None of the terms in the passage talk about the 2010 elections."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Wikipedia"], "Instance": {"id": "task233-bff5ea2de23e4afbb033953670c2c160", "input": "Question: Who was the ruler of Prague the year young Alfred was sent there? Passage:Piccaver was born on 5 February 1884 in the Lincolnshire town of Long Sutton to chemist Frederick Herman Piccaver (born 1864, died 17 February 1916) and his wife Sarah Ann Sissons. The Piccavers had been farm laborers, but there were also claims of Spanish ancestry dating back to the Spanish Armada. At a young age, Alfred emigrated with his family to the United States of America. The family resettled in Albany, NY and took American citizenship. Frederick Piccaver worked as head brewer of the Beverwyck Brewery. Alfred joined the choir of Albany's St. Peter's Episcopal Church as a boy soprano. He also became a soloist at the North Reformed Church in Watervliet. The young Piccaver went on to study voice with S. Graham Nobbes, who had been chief instructor of the Emma Willard Conservatory of Music and with Allan Lindsay, conductor of the Troy Conservatory of Music. Alfred later trained to be electrical engineer but he had a talent for singing and in 1905 he enrolled at the Metropolitan School of Opera. The school's director Heinrich Conried recognised his considerable vocal ability and in 1907 sent the young Alfred to Prague, where he studied with Ludmilla Prochazka-Neumann (1872\u20131954).\n", "output": ["a"]}, "Instance License": ["CC BY 4.0"], "prediction": "b"}
+{"id": "task233-29015ee6dcf148a09a169a523311e875", "Task": "task233_iirc_link_exists_classification", "Contributors": "['Anjana Arunkumar']", "Source": ["iirc"], "URL": ["https://allenai.org/data/iirc"], "Categories": ["Answerability Classification"], "Reasoning": ["Multihop Reasoning", "Cross-document Reasoning", "Discrete Reasoning", "Numerical Reasoning", "Temporal Reasoning"], "Definition": ["In this task, you're given a question, along with a context passage. The passage will not have a direct answer to the question, but can include some information and a clue for the answer. Assuming you can only obtain information about one entity in the passage, your job is to determine whether information from the passage can be used to answer the question. Indicate your choice as `a` for Yes or `b` for No."], "Positive Examples": [{"input": "Question: When did the operation during which the 704th dropped supplies to allied troops near Nijmegen begin? Passage: The group was occasionally diverted from strategic missions to carry out air support and interdiction missions. It supported Operation Overlord, the invasion of Normandy by attacking transportation targets, including bridges, along with airfields and strong points in France. On D Day, the squadron and the rest of the 446th Group led the first heavy bomber mission of the day. The 446th aided ground forces at Caen and Saint-L\u00f4 during July by hitting bridges, gun batteries, and enemy troops. During Operation Market Garden, the attempt to seize a bridgehead across the Rhine in the Netherlands, the 704th dropped supplies to allied troops near Nijmegen. It struck lines of communications during the Battle of the Bulge. During Operation Varsity in March 1945, it supplied ground and airborne troops near Wesel. The squadron flew its last combat mission on 25 April 1945 against Salzburg, Austria. The group had flown 273 missions and had lost 58 aircraft during the war,\n.", "output": "a", "explanation": "The passage describes the 704th's actions during Operation Market Garden, so we can use the operation's name as a clue to find the answer to the question."}, {"input": "Question: What cities did the 1st tanks division's defensive line run through? Passage: In March 1945, the 1st Tank Division with its 5th Armored Regiment was reassigned to the Japanese home islands in preparation for the expected invasion by Allied forces. It gained the IJA 1st Armored Regiment from the 3rd Tank Division, and formed part of the IJA 36th Army under the Japanese Twelfth Area Army. The headquarters unit and IJA 1st Armored Regiment were based in Sano, Tochigi, with the IJA 5th Armored Regiment stationed at \u014ctawara, Tochigi (and later relocated to Kazo, Saitama, and the IJA 1st Mechanized Infantry Regiment and the Division\u2019s mechanized artillery stationed at Tochigi. Anticipating that Allied forces would land at Kuj\u016bkuri Beach, the 1st Tank Division was to hold a defensive line stretching from Mount Tsukuba to the Tama River, with forward units deployed to Choshi, Chiba. The surrender of Japan came before the landing, and the 1st Armored Division did not see any combat on Japanese soil.\n.", "output": "b", "explanation": "The 1st tanks division's defensive line is mentioned in the passage, but to find the answer, one must obtain information about both \"Mount Tsukuba\" and \"Tama River\"."}, {"input": "Question: What was the population of Los Angeles when Jarrett moved there to start screenwriting? Passage: His first feature film role was in the teen comedy \"Summer Job\", where he played an effete hairdresser. Next came minor roles in such films as The Bodyguard with Kevin Costner and Whitney Houston as well as Miami Vice and Unsolved Mysteries. His original screenplay Laws of Deception was made into a film in 1997 and starred C. Thomas Howell, James Russo and Brian Austin Green and was directed by Joey Travolta, brother of John Travolta. Jarrett had a small role in this film as Mr. Farina, a corrupt businessman.", "output": "b", "explanation": "The passage does not have any terms pertaining to Los Angeles. So there's no clue leading to an answer."}, {"input": "Question: Which song holds the record of longest weeks at number 1 on the chart where The American Breed's greatest single reached number 5 in 1968? Passage:The group was formed in Cicero, Illinois, United States, as Gary & The Knight Lites. The founding members included Gary Loizzo (vocals and guitar), Charles Colbert, Jr. (bass guitar and vocals), Al Ciner (guitar and vocals), and Jim Michalak (drums). Early releases included- \"I'm Glad She's Mine,\" \"I Don't Need Your Help,\" \"Will You Go Steady,\" \"Take Me Back,\" among others. The group's greatest success as \"The American Breed\" was the single, \"Bend Me, Shape Me\", which reached number five on the U.S. Billboard Hot 100 chart in 1968. The song, written by Scott English and Larry Weiss, had previously been recorded by an all-female band known as the Shape and had been a hit on the UK Singles Chart for the British group Amen Corner. It had also been recorded by The Outsiders after they had reached the top ten with \"Time Won't Let Me\" in 1966. Contributing to the success of the American Breed's version of \"Bend Me, Shape Me\" was the excellent arrangement of the song by the band's record producer, Bill Traut, who added horns among other changes. The group also appeared on the 16 December 1967 episode of the television show American Bandstand, along with Pink Floyd.\n", "output": "a", "explanation": "According to the passage, the chart where The American Breed's greatest single reached number 5 in 1968 is \"U.S. Billboard Hot 100 chart\". So by obtaining information about that chart, one can answer the question."}], "Negative Examples": [{"input": "Question: How many Super Bowls did the team the Cardinals beat to make their first appearance in the Super Bowl win? Passage: The 2008 Arizona Cardinals season was the 89th season for the team in the National Football League and their 21st season in Arizona. The season marked the Cardinals' first Super Bowl appearance, coming as a result of their victory against the Philadelphia Eagles in the NFC Championship. The Cardinals slogan for the season was \"Shock The World!\" Riding the back of quarterback Kurt Warner, who had gone from being a backup for the St. Louis Rams in 1999 to leading the Greatest Show on Turf to a Super Bowl XXXIV victory, and franchise wide receiver Larry Fitzgerald, the Cardinals went on a playoff run for the ages after having won just one playoff game in the last sixty years, as Warner once again recreated the magic he had captured with the Rams. (Coincidentally, both teams were based in St Louis at one point or another, only to relocate to different cities.)\n.", "output": "b", "explanation": "The team that the Cardinals beat is mentioned in the passage as the Eagles, so any further information to answer the question can be obtained with one step(by getting information on the Eagles). The correct ansewr is \"a\"."}, {"input": "Question: What margin did liberals lose to conservatives in 2010? Passage: This remained the case until the 2018 local elections when the Liberal Democrats regained one of the three seats by a single vote. The Liberal Democrats also regained control of the Council. Richmond Park, the constituency which includes Mortlake, had changed from Liberal Democrat to Conservative in the general election, was recaptured by the Liberal Democrats in the 2016 by-election, and finally reverted to Conservative MP Zac Goldsmith in the 2017 general election by a margin of only 45 votes. The London Assembly constituency South West, which includes Mortlake, is represented by former local councillor Tony Arbour (Conservative).\n", "output": "a", "explanation": "None of the terms in the passage talk about the 2010 elections."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Wikipedia"], "Instance": {"id": "task233-29015ee6dcf148a09a169a523311e875", "input": "Question: How many years had WNOK been operating when WQXL switched to country music? Passage:The station became WQXL in 1962 after the station was sold to the Belk Broadcasting Company. The WOIC call sign resurfaced that same year on 1320 AM (now WISW). WQXL originally aired a Big Band format, which eventually gave way to a Top 40 format by the end of the decade. However it was handicapped with a daytime-only signal and was unsuccessful in competing against format rivals 1230 WNOK and 1400 WCOS, which each had full-time signals. Probably its most notable personality was Mackie \"Cactus\" Quave who had worked at 560 WIS (now WVOC) and had a successful kids TV show on NBC Network affiliate Channel 10 WIS-TV. WQXL switched to country music in the summer of 1966, but again was bested by rival 620 WCAY (now WGCV). In 1973, the station switched to religious programming and eventually adopted a Contemporary Christian format.\n", "output": ["b"]}, "Instance License": ["CC BY 4.0"], "prediction": "b"}
+{"id": "task936-e947449ff52e41e68119716844d6f1b0", "Task": "task936_defeasible_nli_snli_classification", "Contributors": "['Sujan Reddy A']", "Source": ["defeasible_nli_atomic"], "URL": ["https://github.com/rudinger/defeasible-nli"], "Categories": ["Textual Entailment"], "Reasoning": ["Commonsense Reasoning -> Social Situations"], "Definition": ["In this task, you are given a premise, a hypothesis, and an update. The premise sentence describes a real-world situation and is always assumed to be true. The hypothesis sentence describes an assumption or inference that you might make about that situation having read the premise. The update provides additional information about the situation that might weaken or strengthen the hypothesis. A weakener is a statement that weakens the hypothesis, that is, it makes you much less likely to believe the hypothesis is true. A strengthener is a statement that strengthens the hypothesis, that is, it makes you much more likely to believe the hypothesis is true. Your task is to answer with 'strengthener' or 'weakener' if the update strengthens or weakens the hypothesis, respectively."], "Positive Examples": [{"input": "Premise: Old man crafting something in his workshop.\nHypothesis: An old man is working.\nUpdate: The man is serious and is surrounded by workers.", "output": "strengthener", "explanation": "If the old man is serious and surrounded by workers, it is more likely that he is working."}, {"input": "Premise: Old man crafting something in his workshop.\nHypothesis: An old man is working.\nUpdate: The man is wearing pajamas and is chuckling.", "output": "weakener", "explanation": "If the man is wearing pajamas and chuckling, it will be less likely that he is working."}], "Negative Examples": [{"input": "Premise: Old man crafting something in his workshop.\nHypothesis: An old man is working.\nUpdate: The man is serious and is surrounded by workers.", "output": "I dont know.", "explanation": "Do not generate anything else apart from one of the following : 'strengthener', 'weakener'."}, {"input": "Premise: Old man crafting something in his workshop.\nHypothesis: An old man is working.\nUpdate: The man is wearing pajamas and is chuckling.", "output": "strengthener,weakener.", "explanation": "The update could either strengthen or weaken the hypothesis, not both."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Captions -> Image Captions"], "Instance": {"id": "task936-e947449ff52e41e68119716844d6f1b0", "input": "Premise: A man standing in a white shirt is conducting a small group of violin players.\nHypothesis: Bob is conducting a small group.\nUpdate: The man's birth certificate says Robert.", "output": ["strengthener"]}, "Instance License": ["MIT"], "prediction": "weakener"}
+{"id": "task936-074c18db16f2441c922b874f6d228c9c", "Task": "task936_defeasible_nli_snli_classification", "Contributors": "['Sujan Reddy A']", "Source": ["defeasible_nli_atomic"], "URL": ["https://github.com/rudinger/defeasible-nli"], "Categories": ["Textual Entailment"], "Reasoning": ["Commonsense Reasoning -> Social Situations"], "Definition": ["In this task, you are given a premise, a hypothesis, and an update. The premise sentence describes a real-world situation and is always assumed to be true. The hypothesis sentence describes an assumption or inference that you might make about that situation having read the premise. The update provides additional information about the situation that might weaken or strengthen the hypothesis. A weakener is a statement that weakens the hypothesis, that is, it makes you much less likely to believe the hypothesis is true. A strengthener is a statement that strengthens the hypothesis, that is, it makes you much more likely to believe the hypothesis is true. Your task is to answer with 'strengthener' or 'weakener' if the update strengthens or weakens the hypothesis, respectively."], "Positive Examples": [{"input": "Premise: Old man crafting something in his workshop.\nHypothesis: An old man is working.\nUpdate: The man is serious and is surrounded by workers.", "output": "strengthener", "explanation": "If the old man is serious and surrounded by workers, it is more likely that he is working."}, {"input": "Premise: Old man crafting something in his workshop.\nHypothesis: An old man is working.\nUpdate: The man is wearing pajamas and is chuckling.", "output": "weakener", "explanation": "If the man is wearing pajamas and chuckling, it will be less likely that he is working."}], "Negative Examples": [{"input": "Premise: Old man crafting something in his workshop.\nHypothesis: An old man is working.\nUpdate: The man is serious and is surrounded by workers.", "output": "I dont know.", "explanation": "Do not generate anything else apart from one of the following : 'strengthener', 'weakener'."}, {"input": "Premise: Old man crafting something in his workshop.\nHypothesis: An old man is working.\nUpdate: The man is wearing pajamas and is chuckling.", "output": "strengthener,weakener.", "explanation": "The update could either strengthen or weaken the hypothesis, not both."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Captions -> Image Captions"], "Instance": {"id": "task936-074c18db16f2441c922b874f6d228c9c", "input": "Premise: The boy pours water on the baby.\nHypothesis: The boy is watching the baby.\nUpdate: He is helping his  mother give the baby a bath.", "output": ["weakener"]}, "Instance License": ["MIT"], "prediction": "weakener"}
+{"id": "task936-614372595e4c41a88db049fb7695a3b7", "Task": "task936_defeasible_nli_snli_classification", "Contributors": "['Sujan Reddy A']", "Source": ["defeasible_nli_atomic"], "URL": ["https://github.com/rudinger/defeasible-nli"], "Categories": ["Textual Entailment"], "Reasoning": ["Commonsense Reasoning -> Social Situations"], "Definition": ["In this task, you are given a premise, a hypothesis, and an update. The premise sentence describes a real-world situation and is always assumed to be true. The hypothesis sentence describes an assumption or inference that you might make about that situation having read the premise. The update provides additional information about the situation that might weaken or strengthen the hypothesis. A weakener is a statement that weakens the hypothesis, that is, it makes you much less likely to believe the hypothesis is true. A strengthener is a statement that strengthens the hypothesis, that is, it makes you much more likely to believe the hypothesis is true. Your task is to answer with 'strengthener' or 'weakener' if the update strengthens or weakens the hypothesis, respectively."], "Positive Examples": [{"input": "Premise: Old man crafting something in his workshop.\nHypothesis: An old man is working.\nUpdate: The man is serious and is surrounded by workers.", "output": "strengthener", "explanation": "If the old man is serious and surrounded by workers, it is more likely that he is working."}, {"input": "Premise: Old man crafting something in his workshop.\nHypothesis: An old man is working.\nUpdate: The man is wearing pajamas and is chuckling.", "output": "weakener", "explanation": "If the man is wearing pajamas and chuckling, it will be less likely that he is working."}], "Negative Examples": [{"input": "Premise: Old man crafting something in his workshop.\nHypothesis: An old man is working.\nUpdate: The man is serious and is surrounded by workers.", "output": "I dont know.", "explanation": "Do not generate anything else apart from one of the following : 'strengthener', 'weakener'."}, {"input": "Premise: Old man crafting something in his workshop.\nHypothesis: An old man is working.\nUpdate: The man is wearing pajamas and is chuckling.", "output": "strengthener,weakener.", "explanation": "The update could either strengthen or weaken the hypothesis, not both."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Captions -> Image Captions"], "Instance": {"id": "task936-614372595e4c41a88db049fb7695a3b7", "input": "Premise: A bunch of people are standing or sitting in a snow valley.\nHypothesis: They are all friends, talking with one another.\nUpdate: They are looking away from each other.", "output": ["weakener"]}, "Instance License": ["MIT"], "prediction": "weakener"}
+{"id": "task936-4e2a3caf6cf64af2888544c0eb3dadaf", "Task": "task936_defeasible_nli_snli_classification", "Contributors": "['Sujan Reddy A']", "Source": ["defeasible_nli_atomic"], "URL": ["https://github.com/rudinger/defeasible-nli"], "Categories": ["Textual Entailment"], "Reasoning": ["Commonsense Reasoning -> Social Situations"], "Definition": ["In this task, you are given a premise, a hypothesis, and an update. The premise sentence describes a real-world situation and is always assumed to be true. The hypothesis sentence describes an assumption or inference that you might make about that situation having read the premise. The update provides additional information about the situation that might weaken or strengthen the hypothesis. A weakener is a statement that weakens the hypothesis, that is, it makes you much less likely to believe the hypothesis is true. A strengthener is a statement that strengthens the hypothesis, that is, it makes you much more likely to believe the hypothesis is true. Your task is to answer with 'strengthener' or 'weakener' if the update strengthens or weakens the hypothesis, respectively."], "Positive Examples": [{"input": "Premise: Old man crafting something in his workshop.\nHypothesis: An old man is working.\nUpdate: The man is serious and is surrounded by workers.", "output": "strengthener", "explanation": "If the old man is serious and surrounded by workers, it is more likely that he is working."}, {"input": "Premise: Old man crafting something in his workshop.\nHypothesis: An old man is working.\nUpdate: The man is wearing pajamas and is chuckling.", "output": "weakener", "explanation": "If the man is wearing pajamas and chuckling, it will be less likely that he is working."}], "Negative Examples": [{"input": "Premise: Old man crafting something in his workshop.\nHypothesis: An old man is working.\nUpdate: The man is serious and is surrounded by workers.", "output": "I dont know.", "explanation": "Do not generate anything else apart from one of the following : 'strengthener', 'weakener'."}, {"input": "Premise: Old man crafting something in his workshop.\nHypothesis: An old man is working.\nUpdate: The man is wearing pajamas and is chuckling.", "output": "strengthener,weakener.", "explanation": "The update could either strengthen or weaken the hypothesis, not both."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Captions -> Image Captions"], "Instance": {"id": "task936-4e2a3caf6cf64af2888544c0eb3dadaf", "input": "Premise: An ice cream truck with an open door is driving through a residential neighborhood.\nHypothesis: An ice cream truck with an open door is driving through a big neighborhood.\nUpdate: The ice cream truck is surrounded by several dozen children.", "output": ["strengthener"]}, "Instance License": ["MIT"], "prediction": "stronger"}
+{"id": "task936-89afc2c76d5d44b6a4b64f885db97a71", "Task": "task936_defeasible_nli_snli_classification", "Contributors": "['Sujan Reddy A']", "Source": ["defeasible_nli_atomic"], "URL": ["https://github.com/rudinger/defeasible-nli"], "Categories": ["Textual Entailment"], "Reasoning": ["Commonsense Reasoning -> Social Situations"], "Definition": ["In this task, you are given a premise, a hypothesis, and an update. The premise sentence describes a real-world situation and is always assumed to be true. The hypothesis sentence describes an assumption or inference that you might make about that situation having read the premise. The update provides additional information about the situation that might weaken or strengthen the hypothesis. A weakener is a statement that weakens the hypothesis, that is, it makes you much less likely to believe the hypothesis is true. A strengthener is a statement that strengthens the hypothesis, that is, it makes you much more likely to believe the hypothesis is true. Your task is to answer with 'strengthener' or 'weakener' if the update strengthens or weakens the hypothesis, respectively."], "Positive Examples": [{"input": "Premise: Old man crafting something in his workshop.\nHypothesis: An old man is working.\nUpdate: The man is serious and is surrounded by workers.", "output": "strengthener", "explanation": "If the old man is serious and surrounded by workers, it is more likely that he is working."}, {"input": "Premise: Old man crafting something in his workshop.\nHypothesis: An old man is working.\nUpdate: The man is wearing pajamas and is chuckling.", "output": "weakener", "explanation": "If the man is wearing pajamas and chuckling, it will be less likely that he is working."}], "Negative Examples": [{"input": "Premise: Old man crafting something in his workshop.\nHypothesis: An old man is working.\nUpdate: The man is serious and is surrounded by workers.", "output": "I dont know.", "explanation": "Do not generate anything else apart from one of the following : 'strengthener', 'weakener'."}, {"input": "Premise: Old man crafting something in his workshop.\nHypothesis: An old man is working.\nUpdate: The man is wearing pajamas and is chuckling.", "output": "strengthener,weakener.", "explanation": "The update could either strengthen or weaken the hypothesis, not both."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Captions -> Image Captions"], "Instance": {"id": "task936-89afc2c76d5d44b6a4b64f885db97a71", "input": "Premise: A very skinny Santa Claus greets young children in front of a building.\nHypothesis: A man smiles at children outside while waving\nUpdate: His hands are in his pockets.", "output": ["weakener"]}, "Instance License": ["MIT"], "prediction": "weakener"}
+{"id": "task1386-e90487b5651f4239a5589bb437766591", "Task": "task1386_anli_r2_entailment", "Contributors": "['Yeganeh Kordi']", "Source": ["anli"], "URL": ["https://github.com/facebookresearch/anli"], "Categories": ["Textual Entailment"], "Reasoning": ["Textual Entailment", "Quantitative Reasoning", "Commonsense Reasoning", "Causal Reasoning"], "Definition": ["In this task, you will be presented with a premise and a hypothesis sentence. Determine whether the hypothesis sentence entails (implies), contradicts (opposes), or is neutral with respect to the given premise. Please answer with \"Contradiction\", \"Neutral\", or \"Entailment\"."], "Positive Examples": [{"input": "Premise: The Washington Nationals are a professional baseball team that has been based in Washington, D.C. since . The Nationals are a member of both the Major League Baseball's (MLB) National League Eastern Division and the National League (NL) itself. Since the 2008 season, the Nationals have played in Nationals Park; from 2005 through , the team played in Robert F. Kennedy Memorial Stadium. <sep> Hypothesis: The Washington Nationals have played in Nationals Park for more than 1000 days.", "output": "Entailment", "explanation": "This is a good example, and the hypothesis sentence entails the given premise. They've played there since the 2008 season, which is 14 years ago, which is far more than 1000 days."}, {"input": "Premise: The 1986\u201387 St. John's Redmen basketball team represented St. John's University during the 1986\u201387 NCAA Division I men's basketball season. The team was coached by Lou Carnesecca in his nineteenth year at the school. St. John's home games are played at Alumni Hall and Madison Square Garden and the team is a member of the Big East Conference. <sep> Hypothesis: Lou Carnesecca's first season as coach of the St. John's Redmen basketball team was in 1974.", "output": "Contradiction", "explanation": "His 19th season as coach was in 1986, therefore his first season as coach was in 1967, not 1974. So, hypothesis sentence contradicts the given premise."}, {"input": "Premise: Clear Hearts Grey Flowers is the second full-length and final album by Jack Off Jill. Produced by Chris Vrenna of Nine Inch Nails/Tweaker, it was released in July 2000 on the now-defunct label Risk Records. After \"Clear Hearts, Grey Flowers\" the band formally split up and moved on to establish other projects. <sep> Hypothesis: Risk Records released Jack Off Jill's initial album.", "output": "Neutral", "explanation": "The second album was released by Risk Records, but the first one is uncertain from the text. So, hypothesis sentence is neutral with respect to a given premise."}], "Negative Examples": [{"input": "Premise: The genocide of indigenous peoples is the mass destruction of entire communities or races of indigenous peoples. Indigenous peoples are understood to be people whose historical and current territory has become occupied by colonial expansion, or the formation of a state by a dominant group such as a colonial power. <sep> Hypothesis: the land of the indigenous people was stolen from a dominant group", "output": "Neutral", "explanation": "The premise states that a dominant group of the state caused mass genocide in order to take the land and territories of indigenous peoples. The hypothesis sentence entails the given premise and \"Neutral\" is incorrect."}, {"input": "Premise: KnowledgeWare was a software company headquartered in Atlanta, Georgia co-founded by James Martin and run by Fran Tarkenton. It produced a Computer Aided Software Engineering (CASE) tool called IEW (Information Engineering Workbench). KnowledgeWare was sold to Sterling Software in 1994, which was in its turn acquired by Computer Associates. <sep> Hypothesis: KnowledgeWare produced an interesting Computer Aided Software Engineering tool that enables people to fly", "output": "Entailment", "explanation": "The software can not enable people to fly. So, the answer should be \"Contradiction\"."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Miscellaneous"], "Instance": {"id": "task1386-e90487b5651f4239a5589bb437766591", "input": "Premise: Connacht Rugby (Irish: \"Rugba\u00ed Connachta\" ) is one of the four professional provincial rugby teams from the island of Ireland. Connacht competes in the Pro14 and the European Rugby Challenge Cup. The team represents the IRFU Connacht Branch, which is one of four primary branches of the IRFU, and is responsible for rugby union throughout the geographical Irish province of Connacht. <sep> Hypothesis: Connacht often competes in continental europe", "output": ["Neutral"]}, "Instance License": ["CC BY-NC 4.0"], "prediction": "Entails"}
+{"id": "task1386-be1e10e748184d1a88dc91df597a41df", "Task": "task1386_anli_r2_entailment", "Contributors": "['Yeganeh Kordi']", "Source": ["anli"], "URL": ["https://github.com/facebookresearch/anli"], "Categories": ["Textual Entailment"], "Reasoning": ["Textual Entailment", "Quantitative Reasoning", "Commonsense Reasoning", "Causal Reasoning"], "Definition": ["In this task, you will be presented with a premise and a hypothesis sentence. Determine whether the hypothesis sentence entails (implies), contradicts (opposes), or is neutral with respect to the given premise. Please answer with \"Contradiction\", \"Neutral\", or \"Entailment\"."], "Positive Examples": [{"input": "Premise: The Washington Nationals are a professional baseball team that has been based in Washington, D.C. since . The Nationals are a member of both the Major League Baseball's (MLB) National League Eastern Division and the National League (NL) itself. Since the 2008 season, the Nationals have played in Nationals Park; from 2005 through , the team played in Robert F. Kennedy Memorial Stadium. <sep> Hypothesis: The Washington Nationals have played in Nationals Park for more than 1000 days.", "output": "Entailment", "explanation": "This is a good example, and the hypothesis sentence entails the given premise. They've played there since the 2008 season, which is 14 years ago, which is far more than 1000 days."}, {"input": "Premise: The 1986\u201387 St. John's Redmen basketball team represented St. John's University during the 1986\u201387 NCAA Division I men's basketball season. The team was coached by Lou Carnesecca in his nineteenth year at the school. St. John's home games are played at Alumni Hall and Madison Square Garden and the team is a member of the Big East Conference. <sep> Hypothesis: Lou Carnesecca's first season as coach of the St. John's Redmen basketball team was in 1974.", "output": "Contradiction", "explanation": "His 19th season as coach was in 1986, therefore his first season as coach was in 1967, not 1974. So, hypothesis sentence contradicts the given premise."}, {"input": "Premise: Clear Hearts Grey Flowers is the second full-length and final album by Jack Off Jill. Produced by Chris Vrenna of Nine Inch Nails/Tweaker, it was released in July 2000 on the now-defunct label Risk Records. After \"Clear Hearts, Grey Flowers\" the band formally split up and moved on to establish other projects. <sep> Hypothesis: Risk Records released Jack Off Jill's initial album.", "output": "Neutral", "explanation": "The second album was released by Risk Records, but the first one is uncertain from the text. So, hypothesis sentence is neutral with respect to a given premise."}], "Negative Examples": [{"input": "Premise: The genocide of indigenous peoples is the mass destruction of entire communities or races of indigenous peoples. Indigenous peoples are understood to be people whose historical and current territory has become occupied by colonial expansion, or the formation of a state by a dominant group such as a colonial power. <sep> Hypothesis: the land of the indigenous people was stolen from a dominant group", "output": "Neutral", "explanation": "The premise states that a dominant group of the state caused mass genocide in order to take the land and territories of indigenous peoples. The hypothesis sentence entails the given premise and \"Neutral\" is incorrect."}, {"input": "Premise: KnowledgeWare was a software company headquartered in Atlanta, Georgia co-founded by James Martin and run by Fran Tarkenton. It produced a Computer Aided Software Engineering (CASE) tool called IEW (Information Engineering Workbench). KnowledgeWare was sold to Sterling Software in 1994, which was in its turn acquired by Computer Associates. <sep> Hypothesis: KnowledgeWare produced an interesting Computer Aided Software Engineering tool that enables people to fly", "output": "Entailment", "explanation": "The software can not enable people to fly. So, the answer should be \"Contradiction\"."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Miscellaneous"], "Instance": {"id": "task1386-be1e10e748184d1a88dc91df597a41df", "input": "Premise: RM Films International is a film distribution company based in Hollywood, California. It was started by filmmaker Russ Meyer to distribute his movies. Since Meyer\u2019s death in 2004, RM Films International has been owned and operated by the Russ Meyer Charitable Trust and is a recognized 501(c) private foundation. <sep> Hypothesis: RM Fils is a non profit film company based in California's capital.", "output": ["Contradiction"]}, "Instance License": ["CC BY-NC 4.0"], "prediction": "Entails"}
+{"id": "task1386-8fd159df87884804baf6336e4d664da6", "Task": "task1386_anli_r2_entailment", "Contributors": "['Yeganeh Kordi']", "Source": ["anli"], "URL": ["https://github.com/facebookresearch/anli"], "Categories": ["Textual Entailment"], "Reasoning": ["Textual Entailment", "Quantitative Reasoning", "Commonsense Reasoning", "Causal Reasoning"], "Definition": ["In this task, you will be presented with a premise and a hypothesis sentence. Determine whether the hypothesis sentence entails (implies), contradicts (opposes), or is neutral with respect to the given premise. Please answer with \"Contradiction\", \"Neutral\", or \"Entailment\"."], "Positive Examples": [{"input": "Premise: The Washington Nationals are a professional baseball team that has been based in Washington, D.C. since . The Nationals are a member of both the Major League Baseball's (MLB) National League Eastern Division and the National League (NL) itself. Since the 2008 season, the Nationals have played in Nationals Park; from 2005 through , the team played in Robert F. Kennedy Memorial Stadium. <sep> Hypothesis: The Washington Nationals have played in Nationals Park for more than 1000 days.", "output": "Entailment", "explanation": "This is a good example, and the hypothesis sentence entails the given premise. They've played there since the 2008 season, which is 14 years ago, which is far more than 1000 days."}, {"input": "Premise: The 1986\u201387 St. John's Redmen basketball team represented St. John's University during the 1986\u201387 NCAA Division I men's basketball season. The team was coached by Lou Carnesecca in his nineteenth year at the school. St. John's home games are played at Alumni Hall and Madison Square Garden and the team is a member of the Big East Conference. <sep> Hypothesis: Lou Carnesecca's first season as coach of the St. John's Redmen basketball team was in 1974.", "output": "Contradiction", "explanation": "His 19th season as coach was in 1986, therefore his first season as coach was in 1967, not 1974. So, hypothesis sentence contradicts the given premise."}, {"input": "Premise: Clear Hearts Grey Flowers is the second full-length and final album by Jack Off Jill. Produced by Chris Vrenna of Nine Inch Nails/Tweaker, it was released in July 2000 on the now-defunct label Risk Records. After \"Clear Hearts, Grey Flowers\" the band formally split up and moved on to establish other projects. <sep> Hypothesis: Risk Records released Jack Off Jill's initial album.", "output": "Neutral", "explanation": "The second album was released by Risk Records, but the first one is uncertain from the text. So, hypothesis sentence is neutral with respect to a given premise."}], "Negative Examples": [{"input": "Premise: The genocide of indigenous peoples is the mass destruction of entire communities or races of indigenous peoples. Indigenous peoples are understood to be people whose historical and current territory has become occupied by colonial expansion, or the formation of a state by a dominant group such as a colonial power. <sep> Hypothesis: the land of the indigenous people was stolen from a dominant group", "output": "Neutral", "explanation": "The premise states that a dominant group of the state caused mass genocide in order to take the land and territories of indigenous peoples. The hypothesis sentence entails the given premise and \"Neutral\" is incorrect."}, {"input": "Premise: KnowledgeWare was a software company headquartered in Atlanta, Georgia co-founded by James Martin and run by Fran Tarkenton. It produced a Computer Aided Software Engineering (CASE) tool called IEW (Information Engineering Workbench). KnowledgeWare was sold to Sterling Software in 1994, which was in its turn acquired by Computer Associates. <sep> Hypothesis: KnowledgeWare produced an interesting Computer Aided Software Engineering tool that enables people to fly", "output": "Entailment", "explanation": "The software can not enable people to fly. So, the answer should be \"Contradiction\"."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Miscellaneous"], "Instance": {"id": "task1386-8fd159df87884804baf6336e4d664da6", "input": "Premise: Glaiza Herradura-Agullo (born February 24, 1978) is a Filipino former child actress. She was the first-ever grand winner of the Little Miss Philippines segment of \"Eat Bulaga!\" in 1984. She starred in RPN-9's television series \"Heredero\" with Manilyn Reynes and Richard Arellano. She won the 1988 FAMAS Best Child Actress award for her role in \"Batas Sa Aking Kamay\" starring Fernando Poe, Jr.. <sep> Hypothesis: Glaiza Herradura-Agullo is a currently active actress.", "output": ["Neutral"]}, "Instance License": ["CC BY-NC 4.0"], "prediction": "Entails"}
+{"id": "task1386-7ede77b7649c44bdb1050dba4fcfb5c7", "Task": "task1386_anli_r2_entailment", "Contributors": "['Yeganeh Kordi']", "Source": ["anli"], "URL": ["https://github.com/facebookresearch/anli"], "Categories": ["Textual Entailment"], "Reasoning": ["Textual Entailment", "Quantitative Reasoning", "Commonsense Reasoning", "Causal Reasoning"], "Definition": ["In this task, you will be presented with a premise and a hypothesis sentence. Determine whether the hypothesis sentence entails (implies), contradicts (opposes), or is neutral with respect to the given premise. Please answer with \"Contradiction\", \"Neutral\", or \"Entailment\"."], "Positive Examples": [{"input": "Premise: The Washington Nationals are a professional baseball team that has been based in Washington, D.C. since . The Nationals are a member of both the Major League Baseball's (MLB) National League Eastern Division and the National League (NL) itself. Since the 2008 season, the Nationals have played in Nationals Park; from 2005 through , the team played in Robert F. Kennedy Memorial Stadium. <sep> Hypothesis: The Washington Nationals have played in Nationals Park for more than 1000 days.", "output": "Entailment", "explanation": "This is a good example, and the hypothesis sentence entails the given premise. They've played there since the 2008 season, which is 14 years ago, which is far more than 1000 days."}, {"input": "Premise: The 1986\u201387 St. John's Redmen basketball team represented St. John's University during the 1986\u201387 NCAA Division I men's basketball season. The team was coached by Lou Carnesecca in his nineteenth year at the school. St. John's home games are played at Alumni Hall and Madison Square Garden and the team is a member of the Big East Conference. <sep> Hypothesis: Lou Carnesecca's first season as coach of the St. John's Redmen basketball team was in 1974.", "output": "Contradiction", "explanation": "His 19th season as coach was in 1986, therefore his first season as coach was in 1967, not 1974. So, hypothesis sentence contradicts the given premise."}, {"input": "Premise: Clear Hearts Grey Flowers is the second full-length and final album by Jack Off Jill. Produced by Chris Vrenna of Nine Inch Nails/Tweaker, it was released in July 2000 on the now-defunct label Risk Records. After \"Clear Hearts, Grey Flowers\" the band formally split up and moved on to establish other projects. <sep> Hypothesis: Risk Records released Jack Off Jill's initial album.", "output": "Neutral", "explanation": "The second album was released by Risk Records, but the first one is uncertain from the text. So, hypothesis sentence is neutral with respect to a given premise."}], "Negative Examples": [{"input": "Premise: The genocide of indigenous peoples is the mass destruction of entire communities or races of indigenous peoples. Indigenous peoples are understood to be people whose historical and current territory has become occupied by colonial expansion, or the formation of a state by a dominant group such as a colonial power. <sep> Hypothesis: the land of the indigenous people was stolen from a dominant group", "output": "Neutral", "explanation": "The premise states that a dominant group of the state caused mass genocide in order to take the land and territories of indigenous peoples. The hypothesis sentence entails the given premise and \"Neutral\" is incorrect."}, {"input": "Premise: KnowledgeWare was a software company headquartered in Atlanta, Georgia co-founded by James Martin and run by Fran Tarkenton. It produced a Computer Aided Software Engineering (CASE) tool called IEW (Information Engineering Workbench). KnowledgeWare was sold to Sterling Software in 1994, which was in its turn acquired by Computer Associates. <sep> Hypothesis: KnowledgeWare produced an interesting Computer Aided Software Engineering tool that enables people to fly", "output": "Entailment", "explanation": "The software can not enable people to fly. So, the answer should be \"Contradiction\"."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Miscellaneous"], "Instance": {"id": "task1386-7ede77b7649c44bdb1050dba4fcfb5c7", "input": "Premise: The Vermont State Police (VSP) is the state police agency for the US state of Vermont. The force has jurisdiction throughout the entire state. The Vermont Public Safety Commission directs policy and selects the commander. The commander is Colonel Matthew Birmingham. The Vermont Public Safety Commissioner is Keith W. Flynn. There are 327 sworn state troopers. <sep> Hypothesis: The Vermont State Police has authority in the city of Montpelier.", "output": ["Entailment"]}, "Instance License": ["CC BY-NC 4.0"], "prediction": "Entails"}
+{"id": "task1386-c2d519f0e9f34e86a96a8e69cf04f7d1", "Task": "task1386_anli_r2_entailment", "Contributors": "['Yeganeh Kordi']", "Source": ["anli"], "URL": ["https://github.com/facebookresearch/anli"], "Categories": ["Textual Entailment"], "Reasoning": ["Textual Entailment", "Quantitative Reasoning", "Commonsense Reasoning", "Causal Reasoning"], "Definition": ["In this task, you will be presented with a premise and a hypothesis sentence. Determine whether the hypothesis sentence entails (implies), contradicts (opposes), or is neutral with respect to the given premise. Please answer with \"Contradiction\", \"Neutral\", or \"Entailment\"."], "Positive Examples": [{"input": "Premise: The Washington Nationals are a professional baseball team that has been based in Washington, D.C. since . The Nationals are a member of both the Major League Baseball's (MLB) National League Eastern Division and the National League (NL) itself. Since the 2008 season, the Nationals have played in Nationals Park; from 2005 through , the team played in Robert F. Kennedy Memorial Stadium. <sep> Hypothesis: The Washington Nationals have played in Nationals Park for more than 1000 days.", "output": "Entailment", "explanation": "This is a good example, and the hypothesis sentence entails the given premise. They've played there since the 2008 season, which is 14 years ago, which is far more than 1000 days."}, {"input": "Premise: The 1986\u201387 St. John's Redmen basketball team represented St. John's University during the 1986\u201387 NCAA Division I men's basketball season. The team was coached by Lou Carnesecca in his nineteenth year at the school. St. John's home games are played at Alumni Hall and Madison Square Garden and the team is a member of the Big East Conference. <sep> Hypothesis: Lou Carnesecca's first season as coach of the St. John's Redmen basketball team was in 1974.", "output": "Contradiction", "explanation": "His 19th season as coach was in 1986, therefore his first season as coach was in 1967, not 1974. So, hypothesis sentence contradicts the given premise."}, {"input": "Premise: Clear Hearts Grey Flowers is the second full-length and final album by Jack Off Jill. Produced by Chris Vrenna of Nine Inch Nails/Tweaker, it was released in July 2000 on the now-defunct label Risk Records. After \"Clear Hearts, Grey Flowers\" the band formally split up and moved on to establish other projects. <sep> Hypothesis: Risk Records released Jack Off Jill's initial album.", "output": "Neutral", "explanation": "The second album was released by Risk Records, but the first one is uncertain from the text. So, hypothesis sentence is neutral with respect to a given premise."}], "Negative Examples": [{"input": "Premise: The genocide of indigenous peoples is the mass destruction of entire communities or races of indigenous peoples. Indigenous peoples are understood to be people whose historical and current territory has become occupied by colonial expansion, or the formation of a state by a dominant group such as a colonial power. <sep> Hypothesis: the land of the indigenous people was stolen from a dominant group", "output": "Neutral", "explanation": "The premise states that a dominant group of the state caused mass genocide in order to take the land and territories of indigenous peoples. The hypothesis sentence entails the given premise and \"Neutral\" is incorrect."}, {"input": "Premise: KnowledgeWare was a software company headquartered in Atlanta, Georgia co-founded by James Martin and run by Fran Tarkenton. It produced a Computer Aided Software Engineering (CASE) tool called IEW (Information Engineering Workbench). KnowledgeWare was sold to Sterling Software in 1994, which was in its turn acquired by Computer Associates. <sep> Hypothesis: KnowledgeWare produced an interesting Computer Aided Software Engineering tool that enables people to fly", "output": "Entailment", "explanation": "The software can not enable people to fly. So, the answer should be \"Contradiction\"."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Miscellaneous"], "Instance": {"id": "task1386-c2d519f0e9f34e86a96a8e69cf04f7d1", "input": "Premise: Allen West (born October 17, 1967, Brandon, Florida) is an American death metal guitarist who has been a member of Massacre, Obituary, Six Feet Under, Lowbrow, and Southwicked. He is considered to be a pioneering figure of the death metal genre in the 1980s. <sep> Hypothesis: Allen West will be 52 years old on his next birthday.", "output": ["Entailment"]}, "Instance License": ["CC BY-NC 4.0"], "prediction": "Entails"}
+{"id": "task1152-9e8c4ba215674fc5a2ca51ee3f44b5bd", "Task": "task1152_bard_analogical_reasoning_causation", "Contributors": "['Arjun Ashok']", "Source": ["bard"], "URL": ["https://github.com/NancyFulda/BYU-Analogical-Reasoning-Dataset"], "Categories": ["Word Analogy"], "Reasoning": ["Relational Reasoning", "Commonsense Reasoning", "Analogical Reasoning"], "Definition": ["Two analogies that relate actions with their consequences are given in the form \"A : B. C : ?\". The phrase \"A : B\" relates action A to consequence B. Your task is to replace the question mark (?) with the appropriate consquence of the given action C, following the \"A : B\" relation. Your answer should be a single verb, without further explanation."], "Positive Examples": [{"input": "throw : fly. aspire : ?", "output": "attain", "explanation": "Fly is a causation of throw. Hence, the inferred analogy being causation, attain is the causation of aspire."}, {"input": "listen : hear. drop : ?", "output": "fall", "explanation": "Hear is a causation of listen. Hence, the inferred analogy being causation, the causation of drop is fall."}, {"input": "hit : shatter. nourish : ?", "output": "grow", "explanation": "Shatter is a causation of hit. Hence, the inferred analogy being causation, the causation of nourish is grow."}], "Negative Examples": [{"input": "cut : bleed. crush : ?", "output": "throw", "explanation": "Bleed in a causation of cut. Hence, the analogy given is causation. But, throw is not a causation of crush."}, {"input": "nourish : grow. listen : ?", "output": "break", "explanation": "Grow is a causation of nourish. Hence, the analogy given is causation. But, break is not a causation of listen"}, {"input": "fear : flee. ignite : ?", "output": "bleed", "explanation": "Flee is a causation of fear. Hence, the analogy given is causation. But, bleed is not a causation of ignite"}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Commonsense"], "Instance": {"id": "task1152-9e8c4ba215674fc5a2ca51ee3f44b5bd", "input": "throw : fly. trip : ?", "output": ["stumble"]}, "Instance License": ["Apache 2.0"], "prediction": "fall"}
+{"id": "task1152-f0acee8d9f4242d2adddf165f029cd04", "Task": "task1152_bard_analogical_reasoning_causation", "Contributors": "['Arjun Ashok']", "Source": ["bard"], "URL": ["https://github.com/NancyFulda/BYU-Analogical-Reasoning-Dataset"], "Categories": ["Word Analogy"], "Reasoning": ["Relational Reasoning", "Commonsense Reasoning", "Analogical Reasoning"], "Definition": ["Two analogies that relate actions with their consequences are given in the form \"A : B. C : ?\". The phrase \"A : B\" relates action A to consequence B. Your task is to replace the question mark (?) with the appropriate consquence of the given action C, following the \"A : B\" relation. Your answer should be a single verb, without further explanation."], "Positive Examples": [{"input": "throw : fly. aspire : ?", "output": "attain", "explanation": "Fly is a causation of throw. Hence, the inferred analogy being causation, attain is the causation of aspire."}, {"input": "listen : hear. drop : ?", "output": "fall", "explanation": "Hear is a causation of listen. Hence, the inferred analogy being causation, the causation of drop is fall."}, {"input": "hit : shatter. nourish : ?", "output": "grow", "explanation": "Shatter is a causation of hit. Hence, the inferred analogy being causation, the causation of nourish is grow."}], "Negative Examples": [{"input": "cut : bleed. crush : ?", "output": "throw", "explanation": "Bleed in a causation of cut. Hence, the analogy given is causation. But, throw is not a causation of crush."}, {"input": "nourish : grow. listen : ?", "output": "break", "explanation": "Grow is a causation of nourish. Hence, the analogy given is causation. But, break is not a causation of listen"}, {"input": "fear : flee. ignite : ?", "output": "bleed", "explanation": "Flee is a causation of fear. Hence, the analogy given is causation. But, bleed is not a causation of ignite"}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Commonsense"], "Instance": {"id": "task1152-f0acee8d9f4242d2adddf165f029cd04", "input": "listen : hear. hit : ?", "output": ["shatter"]}, "Instance License": ["Apache 2.0"], "prediction": "fall"}
+{"id": "task1152-96f273184c7549339e0fa021f5ecf667", "Task": "task1152_bard_analogical_reasoning_causation", "Contributors": "['Arjun Ashok']", "Source": ["bard"], "URL": ["https://github.com/NancyFulda/BYU-Analogical-Reasoning-Dataset"], "Categories": ["Word Analogy"], "Reasoning": ["Relational Reasoning", "Commonsense Reasoning", "Analogical Reasoning"], "Definition": ["Two analogies that relate actions with their consequences are given in the form \"A : B. C : ?\". The phrase \"A : B\" relates action A to consequence B. Your task is to replace the question mark (?) with the appropriate consquence of the given action C, following the \"A : B\" relation. Your answer should be a single verb, without further explanation."], "Positive Examples": [{"input": "throw : fly. aspire : ?", "output": "attain", "explanation": "Fly is a causation of throw. Hence, the inferred analogy being causation, attain is the causation of aspire."}, {"input": "listen : hear. drop : ?", "output": "fall", "explanation": "Hear is a causation of listen. Hence, the inferred analogy being causation, the causation of drop is fall."}, {"input": "hit : shatter. nourish : ?", "output": "grow", "explanation": "Shatter is a causation of hit. Hence, the inferred analogy being causation, the causation of nourish is grow."}], "Negative Examples": [{"input": "cut : bleed. crush : ?", "output": "throw", "explanation": "Bleed in a causation of cut. Hence, the analogy given is causation. But, throw is not a causation of crush."}, {"input": "nourish : grow. listen : ?", "output": "break", "explanation": "Grow is a causation of nourish. Hence, the analogy given is causation. But, break is not a causation of listen"}, {"input": "fear : flee. ignite : ?", "output": "bleed", "explanation": "Flee is a causation of fear. Hence, the analogy given is causation. But, bleed is not a causation of ignite"}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Commonsense"], "Instance": {"id": "task1152-96f273184c7549339e0fa021f5ecf667", "input": "fear : flee. cut : ?", "output": ["bleed"]}, "Instance License": ["Apache 2.0"], "prediction": "cut"}
+{"id": "task1152-4f1e92d1effe44a98d74149bcba42bfa", "Task": "task1152_bard_analogical_reasoning_causation", "Contributors": "['Arjun Ashok']", "Source": ["bard"], "URL": ["https://github.com/NancyFulda/BYU-Analogical-Reasoning-Dataset"], "Categories": ["Word Analogy"], "Reasoning": ["Relational Reasoning", "Commonsense Reasoning", "Analogical Reasoning"], "Definition": ["Two analogies that relate actions with their consequences are given in the form \"A : B. C : ?\". The phrase \"A : B\" relates action A to consequence B. Your task is to replace the question mark (?) with the appropriate consquence of the given action C, following the \"A : B\" relation. Your answer should be a single verb, without further explanation."], "Positive Examples": [{"input": "throw : fly. aspire : ?", "output": "attain", "explanation": "Fly is a causation of throw. Hence, the inferred analogy being causation, attain is the causation of aspire."}, {"input": "listen : hear. drop : ?", "output": "fall", "explanation": "Hear is a causation of listen. Hence, the inferred analogy being causation, the causation of drop is fall."}, {"input": "hit : shatter. nourish : ?", "output": "grow", "explanation": "Shatter is a causation of hit. Hence, the inferred analogy being causation, the causation of nourish is grow."}], "Negative Examples": [{"input": "cut : bleed. crush : ?", "output": "throw", "explanation": "Bleed in a causation of cut. Hence, the analogy given is causation. But, throw is not a causation of crush."}, {"input": "nourish : grow. listen : ?", "output": "break", "explanation": "Grow is a causation of nourish. Hence, the analogy given is causation. But, break is not a causation of listen"}, {"input": "fear : flee. ignite : ?", "output": "bleed", "explanation": "Flee is a causation of fear. Hence, the analogy given is causation. But, bleed is not a causation of ignite"}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Commonsense"], "Instance": {"id": "task1152-4f1e92d1effe44a98d74149bcba42bfa", "input": "drop : fall. throw : ?", "output": ["fly"]}, "Instance License": ["Apache 2.0"], "prediction": "throw"}
+{"id": "task1152-1afcbf0c5dda42daa87e8788aa789fd9", "Task": "task1152_bard_analogical_reasoning_causation", "Contributors": "['Arjun Ashok']", "Source": ["bard"], "URL": ["https://github.com/NancyFulda/BYU-Analogical-Reasoning-Dataset"], "Categories": ["Word Analogy"], "Reasoning": ["Relational Reasoning", "Commonsense Reasoning", "Analogical Reasoning"], "Definition": ["Two analogies that relate actions with their consequences are given in the form \"A : B. C : ?\". The phrase \"A : B\" relates action A to consequence B. Your task is to replace the question mark (?) with the appropriate consquence of the given action C, following the \"A : B\" relation. Your answer should be a single verb, without further explanation."], "Positive Examples": [{"input": "throw : fly. aspire : ?", "output": "attain", "explanation": "Fly is a causation of throw. Hence, the inferred analogy being causation, attain is the causation of aspire."}, {"input": "listen : hear. drop : ?", "output": "fall", "explanation": "Hear is a causation of listen. Hence, the inferred analogy being causation, the causation of drop is fall."}, {"input": "hit : shatter. nourish : ?", "output": "grow", "explanation": "Shatter is a causation of hit. Hence, the inferred analogy being causation, the causation of nourish is grow."}], "Negative Examples": [{"input": "cut : bleed. crush : ?", "output": "throw", "explanation": "Bleed in a causation of cut. Hence, the analogy given is causation. But, throw is not a causation of crush."}, {"input": "nourish : grow. listen : ?", "output": "break", "explanation": "Grow is a causation of nourish. Hence, the analogy given is causation. But, break is not a causation of listen"}, {"input": "fear : flee. ignite : ?", "output": "bleed", "explanation": "Flee is a causation of fear. Hence, the analogy given is causation. But, bleed is not a causation of ignite"}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Commonsense"], "Instance": {"id": "task1152-1afcbf0c5dda42daa87e8788aa789fd9", "input": "pursue : catch. nourish : ?", "output": ["grow"]}, "Instance License": ["Apache 2.0"], "prediction": "nourish"}
+{"id": "task290-ad483ac976c0469e95a1a50eb8dd001e", "Task": "task290_tellmewhy_question_answerability", "Contributors": "['Amirreza Mirzaei']", "Source": ["tellmewhy"], "URL": ["https://github.com/StonyBrookNLP/tellmewhy"], "Categories": ["Answerability Classification"], "Reasoning": [], "Definition": ["In this task you are given a story and a question regarding that story. You must judge whether the question is answerable based on the info given to you. Label the instances as \"Answerable\" or \"Not Answerable\" based on your judgment. the story and the question are separated by a new line character."], "Positive Examples": [{"input": "Bob was a computer scientist. He enjoyed natural language processing. He decided to revolutionize the industry! He formulated a machine learning algorithm to process words. He won the nobel prize for his work!\nWhy did He formulate a machine?", "output": "Answerable", "explanation": "He formulated a machine learning algorithm to process words."}, {"input": "Bob was a computer scientist. He enjoyed natural language processing. He decided to revolutionize the industry! He formulated a machine learning algorithm to process words. He won the nobel prize for his work!\nWhy did He enjoy natural language processing?", "output": "Not Answerable", "explanation": "no direct information about the question is given."}, {"input": "Bob was a computer scientist. He enjoyed natural language processing. He decided to revolutionize the industry! He formulated a machine learning algorithm to process words. He won the nobel prize for his work!\nWhy did He decide to revolutionize the industry?", "output": "Not Answerable", "explanation": "no direct information about the question is given."}], "Negative Examples": [{"input": "Bob was a computer scientist. He enjoyed natural language processing. He decided to revolutionize the industry! He formulated a machine learning algorithm to process words. He won the nobel prize for his work!\nWhy did He enjoy natural language processing?", "output": "I can't decide.", "explanation": "Do not generate anything else apart from one of the following characters: 'Answerable', 'Not Answerable'."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Story"], "Instance": {"id": "task290-ad483ac976c0469e95a1a50eb8dd001e", "input": "Ken needed to do laundry because all his clothes were dirty. He went to the laundromat and no one was there. Ken decided to get naked and wash the clothes he was wearing. He ran out of money by the time he needed to use the driers. Ken strutted to his car for more quarters and a man whistled at him.\nWhy did He go to the laundromat?", "output": ["Not Answerable"]}, "Instance License": ["Unknown"], "prediction": "Answerable"}
+{"id": "task290-923e08256a5c47648952d66e15c1e614", "Task": "task290_tellmewhy_question_answerability", "Contributors": "['Amirreza Mirzaei']", "Source": ["tellmewhy"], "URL": ["https://github.com/StonyBrookNLP/tellmewhy"], "Categories": ["Answerability Classification"], "Reasoning": [], "Definition": ["In this task you are given a story and a question regarding that story. You must judge whether the question is answerable based on the info given to you. Label the instances as \"Answerable\" or \"Not Answerable\" based on your judgment. the story and the question are separated by a new line character."], "Positive Examples": [{"input": "Bob was a computer scientist. He enjoyed natural language processing. He decided to revolutionize the industry! He formulated a machine learning algorithm to process words. He won the nobel prize for his work!\nWhy did He formulate a machine?", "output": "Answerable", "explanation": "He formulated a machine learning algorithm to process words."}, {"input": "Bob was a computer scientist. He enjoyed natural language processing. He decided to revolutionize the industry! He formulated a machine learning algorithm to process words. He won the nobel prize for his work!\nWhy did He enjoy natural language processing?", "output": "Not Answerable", "explanation": "no direct information about the question is given."}, {"input": "Bob was a computer scientist. He enjoyed natural language processing. He decided to revolutionize the industry! He formulated a machine learning algorithm to process words. He won the nobel prize for his work!\nWhy did He decide to revolutionize the industry?", "output": "Not Answerable", "explanation": "no direct information about the question is given."}], "Negative Examples": [{"input": "Bob was a computer scientist. He enjoyed natural language processing. He decided to revolutionize the industry! He formulated a machine learning algorithm to process words. He won the nobel prize for his work!\nWhy did He enjoy natural language processing?", "output": "I can't decide.", "explanation": "Do not generate anything else apart from one of the following characters: 'Answerable', 'Not Answerable'."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Story"], "Instance": {"id": "task290-923e08256a5c47648952d66e15c1e614", "input": "My friends came over for a fondue party last week. I spent a lot of time preparing the cheese while they arrived. My friend had some fondue and stopped because he felt bad. He asked if there was wine in the fondue because he was allergic. I said there was and he stopped eating it.\nWhy did I say there was and he stopped eating it?", "output": ["Answerable"]}, "Instance License": ["Unknown"], "prediction": "Answerable"}
+{"id": "task290-ce3f258f7c074277890148298aa9c42c", "Task": "task290_tellmewhy_question_answerability", "Contributors": "['Amirreza Mirzaei']", "Source": ["tellmewhy"], "URL": ["https://github.com/StonyBrookNLP/tellmewhy"], "Categories": ["Answerability Classification"], "Reasoning": [], "Definition": ["In this task you are given a story and a question regarding that story. You must judge whether the question is answerable based on the info given to you. Label the instances as \"Answerable\" or \"Not Answerable\" based on your judgment. the story and the question are separated by a new line character."], "Positive Examples": [{"input": "Bob was a computer scientist. He enjoyed natural language processing. He decided to revolutionize the industry! He formulated a machine learning algorithm to process words. He won the nobel prize for his work!\nWhy did He formulate a machine?", "output": "Answerable", "explanation": "He formulated a machine learning algorithm to process words."}, {"input": "Bob was a computer scientist. He enjoyed natural language processing. He decided to revolutionize the industry! He formulated a machine learning algorithm to process words. He won the nobel prize for his work!\nWhy did He enjoy natural language processing?", "output": "Not Answerable", "explanation": "no direct information about the question is given."}, {"input": "Bob was a computer scientist. He enjoyed natural language processing. He decided to revolutionize the industry! He formulated a machine learning algorithm to process words. He won the nobel prize for his work!\nWhy did He decide to revolutionize the industry?", "output": "Not Answerable", "explanation": "no direct information about the question is given."}], "Negative Examples": [{"input": "Bob was a computer scientist. He enjoyed natural language processing. He decided to revolutionize the industry! He formulated a machine learning algorithm to process words. He won the nobel prize for his work!\nWhy did He enjoy natural language processing?", "output": "I can't decide.", "explanation": "Do not generate anything else apart from one of the following characters: 'Answerable', 'Not Answerable'."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Story"], "Instance": {"id": "task290-ce3f258f7c074277890148298aa9c42c", "input": "The chair I was sitting in had a broken leg. It was our last hand of poker. I was anxious and I couldn't stop wobbling in my chair. The other players could tell I had a really good hand. I stood up as I folded.\nWhy was I anxious?", "output": ["Answerable"]}, "Instance License": ["Unknown"], "prediction": "Answerable"}
+{"id": "task290-7c133d2f433c41f8910e84e47721c3c0", "Task": "task290_tellmewhy_question_answerability", "Contributors": "['Amirreza Mirzaei']", "Source": ["tellmewhy"], "URL": ["https://github.com/StonyBrookNLP/tellmewhy"], "Categories": ["Answerability Classification"], "Reasoning": [], "Definition": ["In this task you are given a story and a question regarding that story. You must judge whether the question is answerable based on the info given to you. Label the instances as \"Answerable\" or \"Not Answerable\" based on your judgment. the story and the question are separated by a new line character."], "Positive Examples": [{"input": "Bob was a computer scientist. He enjoyed natural language processing. He decided to revolutionize the industry! He formulated a machine learning algorithm to process words. He won the nobel prize for his work!\nWhy did He formulate a machine?", "output": "Answerable", "explanation": "He formulated a machine learning algorithm to process words."}, {"input": "Bob was a computer scientist. He enjoyed natural language processing. He decided to revolutionize the industry! He formulated a machine learning algorithm to process words. He won the nobel prize for his work!\nWhy did He enjoy natural language processing?", "output": "Not Answerable", "explanation": "no direct information about the question is given."}, {"input": "Bob was a computer scientist. He enjoyed natural language processing. He decided to revolutionize the industry! He formulated a machine learning algorithm to process words. He won the nobel prize for his work!\nWhy did He decide to revolutionize the industry?", "output": "Not Answerable", "explanation": "no direct information about the question is given."}], "Negative Examples": [{"input": "Bob was a computer scientist. He enjoyed natural language processing. He decided to revolutionize the industry! He formulated a machine learning algorithm to process words. He won the nobel prize for his work!\nWhy did He enjoy natural language processing?", "output": "I can't decide.", "explanation": "Do not generate anything else apart from one of the following characters: 'Answerable', 'Not Answerable'."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Story"], "Instance": {"id": "task290-7c133d2f433c41f8910e84e47721c3c0", "input": "Jared wanted to become an actor. He auditioned for a local play. He was cast in that play and did a great job. There was a talent agent in the audience. The talent agent signed Jared and he went on to become famous.\nWhy did Jared want to become an actor?", "output": ["Not Answerable"]}, "Instance License": ["Unknown"], "prediction": "Answerable"}
+{"id": "task290-b87e972f3a2b4720af85aacbc58ce514", "Task": "task290_tellmewhy_question_answerability", "Contributors": "['Amirreza Mirzaei']", "Source": ["tellmewhy"], "URL": ["https://github.com/StonyBrookNLP/tellmewhy"], "Categories": ["Answerability Classification"], "Reasoning": [], "Definition": ["In this task you are given a story and a question regarding that story. You must judge whether the question is answerable based on the info given to you. Label the instances as \"Answerable\" or \"Not Answerable\" based on your judgment. the story and the question are separated by a new line character."], "Positive Examples": [{"input": "Bob was a computer scientist. He enjoyed natural language processing. He decided to revolutionize the industry! He formulated a machine learning algorithm to process words. He won the nobel prize for his work!\nWhy did He formulate a machine?", "output": "Answerable", "explanation": "He formulated a machine learning algorithm to process words."}, {"input": "Bob was a computer scientist. He enjoyed natural language processing. He decided to revolutionize the industry! He formulated a machine learning algorithm to process words. He won the nobel prize for his work!\nWhy did He enjoy natural language processing?", "output": "Not Answerable", "explanation": "no direct information about the question is given."}, {"input": "Bob was a computer scientist. He enjoyed natural language processing. He decided to revolutionize the industry! He formulated a machine learning algorithm to process words. He won the nobel prize for his work!\nWhy did He decide to revolutionize the industry?", "output": "Not Answerable", "explanation": "no direct information about the question is given."}], "Negative Examples": [{"input": "Bob was a computer scientist. He enjoyed natural language processing. He decided to revolutionize the industry! He formulated a machine learning algorithm to process words. He won the nobel prize for his work!\nWhy did He enjoy natural language processing?", "output": "I can't decide.", "explanation": "Do not generate anything else apart from one of the following characters: 'Answerable', 'Not Answerable'."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Story"], "Instance": {"id": "task290-b87e972f3a2b4720af85aacbc58ce514", "input": "I went to the mall to buy some gifts for a friend. As I walked past the suit store, a display caught my eye. I went into the store and demanded to try it on. The suit fit very well. I bought the suit and wore it for the rest of the day.\nWhy did I go into the store?", "output": ["Answerable"]}, "Instance License": ["Unknown"], "prediction": "Answerable"}
+{"id": "task304-d615e3dab058457394af9e96cd863ca1", "Task": "task304_numeric_fused_head_resolution", "Contributors": "['Pegah Alipoormolabashi']", "Source": ["numeric_fused_head"], "URL": ["https://github.com/yanaiela/num_fh"], "Categories": ["Coreference Resolution"], "Reasoning": ["Commonsense Reasoning -> Numerical Commonsense Reasoning"], "Definition": ["In this task, you will use your knowledge about language (and common sense) to determine what element the marked number refers to. The numbers are marked with two underlines around them, like: _ number _. There are several possible answers, you'll need to choose the proper one. Carefully read the given text, pay special attention to the marked number, think about what (unwritten) information the marked number holds inside, choose the most adequate word(s) from the optional answers. If none of them seems right to you, there's also an option for other. If your answer is \"REFERENCE\", also write the reference entity, otherwise write the implicit option name. Options to choose from are:\nREFERENCE: Some object which is being mentioned in the text before or after the target number. The reference answer has a higher priority than any other. If both Reference and another answer are possible, prioritize the Reference.\nYEAR: Describing a calendric year\nAGE: Describing someone's age\nCURRENCY: Reference to some monetary value e.g dollar, euro etc.\nPEOPLE: Describing a single/plural persons\nTIME: Describing a time of the day. Usually you can add the word o'clock after those numbers.\nOTHER: Some other option, which isn't listed here."], "Positive Examples": [{"input": "Jess Mastriani: No, I don't want another crooler, thank you very much.\n FBI Agent Nicole Scott: But it's good for you. It's got... honeyglaze. Please die for this crooler, Jess.\n Jess Mastriani: I've had _ two _ already. Who eats three croolers in a night? \nFBI Agent Nicole Scott: Take a look. [Nicole takes a huge bite] Mmmmm, Mmmmm, Mmmmm!", "output": "REFERENCE crooler", "explanation": "In this example, the number two refers to something that appears in this text. In this example, it refers to the word: crooler."}, {"input": "Adam Adamant: Do you know I haven't been to the theatre since, eh... _ '96 _.\nWilliam E. Simms: Ah, what you see... [catches on]", "output": "YEAR", "explanation": "In this example, the number 96 refers to the year 1996."}, {"input": "Jack: Have you had dinner? If memory serves, you always liked Mitchellis. \nSydney: I haven't eaten there since I was _ eight _.\nJack: I do eat, you know.", "output": "AGE", "explanation": "In this example, eight is being an indicator of an age."}], "Negative Examples": [{"input": "Joy Stark: I'm paying our credit card bill.\nEddie Stark: Well why you sending them 500 dollars? \nJoy Stark: Because we owe them _ 1200 _.", "output": "YEAR", "explanation": "From the context, it can be driven that 1200 describes an amount of money, and doesn't refer to a year."}, {"input": "Joy Stark: Okay, remember that the garbage goes out on Tuesday and if you see a man in the bushes it's probably just the gardener so please don't call _ 911 _ ... again.", "output": "REFERENCE phone number", "explanation": "The number 911 refers to a phone number, that is correct. but the answer in cases like this should be \"OTHER\". The only time you can use words other than the defined labels, is when the referenced entity is present in the text. In this case, \"phone number\" is not present in the text, so you should just use \"OTHER\"."}, {"input": "Dara:  Father , come home . This is wrong .\nDr. Timicin: Dara , if I could show you the work I have begun . There 's still so much for me to do .\nDara: There is nothing for me to look at . It is irrelevant .\nLwaxana Troi: Your father 's work may save your world , my dear . I would hardly consider that irrelevant .\nDara: All I 'm concerned with now is you , not your work . Your work is over . It is your time to rest .\nLwaxana Troi: Perhaps you will feel differently as you get a little older - say approaching _ sixty _ .\nDara: My father taught me to cherish the Resolution . I do n't know how you have poisoned him to reject it .\nLwaxana Troi: It 's an obscene ritual .\nDara: How dare you ? How dare you criticize my way of life and my beliefs ?\nDr. Timicin: Please . Please , Dara . Please .\nDara: Where will you go ?\nDr. Timicin: I do n't know .\nDara: And where will you die ? I can not bear the thought of you being laid to rest on some other world . That you will not lie beside my mother . That I will not be able to lie beside you when my Resolution comes . I 'm sorry . I do n't know how you can ... go on with your life knowing that each day is an insult to everything we believe in . Father , I love you . But I am ashamed .", "output": "REFERENCE Dara", "explanation": "The number sixty here refers to an age. Although it is about Dara's age, the correct answer it \"AGE\"."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Dialogue"], "Instance": {"id": "task304-d615e3dab058457394af9e96cd863ca1", "input": "Zach Galifianakis - Host:  I 'm sorry I had to cancel so many times , my mouse pad broke last week and I had to get my great aunt so diabetes shoes\nBarack Obama: It 's no problem I have to say when I heard that people actually watch this show I was pretty surprised .\nZach Galifianakis - Host: Welcome to Between Two Ferns , I 'm your host Zach Galifianakis and my guest today is Barack Obama , \" president \" Barack Obama\nBarack Obama: Good to be with you\nZach Galifianakis - Host: First question : in 2013 you pardoned the turkey , what do you have planned for 2014 ?\nBarack Obama: We 'll probably pardon another turkey , we do that every thanksgiving , was that the depressing to you ? Seeing the one turkey you could eat , out of circulation ?\nZach Galifianakis - Host: , So how does this work ? Did you send ambassador Rodman to North Korea on your behalf ? I send somewhere you 'd be sending Hulk Hogan to Syria , or is that more of a job for Tonya Harding ?\nBarack Obama: He 's not our ambassador\nZach Galifianakis - Host: What we do about North Ikea ?\nBarack Obama: Why do n't we move on ?\nZach Galifianakis - Host: I have to know , what is it like to be the last black president ?\nBarack Obama: Seriously ? What 's it like for this to be the last time you ever to talk to a president ?\nZach Galifianakis - Host: It must kind of stink though , that you ca n't run three times\nBarack Obama: Actually I think it 's good idea , if I ran a third time , it 'd be like doing the third Hangover movie , it did n't work out very well , did it ? I have to say I 've seen the show before and some of the episodes have been a little better than this one . For examples the _ one _ with Bradley Cooper , that was a great episode\nZach Galifianakis - Host: Bradley Cooper ...\nBarack Obama: He Kind of carried that movie , did n't he ?\nZach Galifianakis - Host: Which film were you speaking of ?\nBarack Obama: Those Hangover movies , basically he carried them .\nZach Galifianakis - Host: Yeah , everybody loves Bradley , good for him\nBarack Obama: Good looking guy\nZach Galifianakis - Host: Being in Hollywood , that 's easy , be short and fat and smell like Doritos and try and make it in Hollywood\nZach Galifianakis - Host: Is\nZach Galifianakis - Host: It going to be hard in two years when you 're no longer president and people will stop letting you win at basketball ?\nBarack Obama: How does it feel to have a three inch \" vertical \" ?\nZach Galifianakis - Host: Actually it 's a three inch \" horizontal \"", "output": ["REFERENCE episodes"]}, "Instance License": ["MIT"], "prediction": "_ number _"}
+{"id": "task304-9497003497ee46a9bb7d7d3ede91a0aa", "Task": "task304_numeric_fused_head_resolution", "Contributors": "['Pegah Alipoormolabashi']", "Source": ["numeric_fused_head"], "URL": ["https://github.com/yanaiela/num_fh"], "Categories": ["Coreference Resolution"], "Reasoning": ["Commonsense Reasoning -> Numerical Commonsense Reasoning"], "Definition": ["In this task, you will use your knowledge about language (and common sense) to determine what element the marked number refers to. The numbers are marked with two underlines around them, like: _ number _. There are several possible answers, you'll need to choose the proper one. Carefully read the given text, pay special attention to the marked number, think about what (unwritten) information the marked number holds inside, choose the most adequate word(s) from the optional answers. If none of them seems right to you, there's also an option for other. If your answer is \"REFERENCE\", also write the reference entity, otherwise write the implicit option name. Options to choose from are:\nREFERENCE: Some object which is being mentioned in the text before or after the target number. The reference answer has a higher priority than any other. If both Reference and another answer are possible, prioritize the Reference.\nYEAR: Describing a calendric year\nAGE: Describing someone's age\nCURRENCY: Reference to some monetary value e.g dollar, euro etc.\nPEOPLE: Describing a single/plural persons\nTIME: Describing a time of the day. Usually you can add the word o'clock after those numbers.\nOTHER: Some other option, which isn't listed here."], "Positive Examples": [{"input": "Jess Mastriani: No, I don't want another crooler, thank you very much.\n FBI Agent Nicole Scott: But it's good for you. It's got... honeyglaze. Please die for this crooler, Jess.\n Jess Mastriani: I've had _ two _ already. Who eats three croolers in a night? \nFBI Agent Nicole Scott: Take a look. [Nicole takes a huge bite] Mmmmm, Mmmmm, Mmmmm!", "output": "REFERENCE crooler", "explanation": "In this example, the number two refers to something that appears in this text. In this example, it refers to the word: crooler."}, {"input": "Adam Adamant: Do you know I haven't been to the theatre since, eh... _ '96 _.\nWilliam E. Simms: Ah, what you see... [catches on]", "output": "YEAR", "explanation": "In this example, the number 96 refers to the year 1996."}, {"input": "Jack: Have you had dinner? If memory serves, you always liked Mitchellis. \nSydney: I haven't eaten there since I was _ eight _.\nJack: I do eat, you know.", "output": "AGE", "explanation": "In this example, eight is being an indicator of an age."}], "Negative Examples": [{"input": "Joy Stark: I'm paying our credit card bill.\nEddie Stark: Well why you sending them 500 dollars? \nJoy Stark: Because we owe them _ 1200 _.", "output": "YEAR", "explanation": "From the context, it can be driven that 1200 describes an amount of money, and doesn't refer to a year."}, {"input": "Joy Stark: Okay, remember that the garbage goes out on Tuesday and if you see a man in the bushes it's probably just the gardener so please don't call _ 911 _ ... again.", "output": "REFERENCE phone number", "explanation": "The number 911 refers to a phone number, that is correct. but the answer in cases like this should be \"OTHER\". The only time you can use words other than the defined labels, is when the referenced entity is present in the text. In this case, \"phone number\" is not present in the text, so you should just use \"OTHER\"."}, {"input": "Dara:  Father , come home . This is wrong .\nDr. Timicin: Dara , if I could show you the work I have begun . There 's still so much for me to do .\nDara: There is nothing for me to look at . It is irrelevant .\nLwaxana Troi: Your father 's work may save your world , my dear . I would hardly consider that irrelevant .\nDara: All I 'm concerned with now is you , not your work . Your work is over . It is your time to rest .\nLwaxana Troi: Perhaps you will feel differently as you get a little older - say approaching _ sixty _ .\nDara: My father taught me to cherish the Resolution . I do n't know how you have poisoned him to reject it .\nLwaxana Troi: It 's an obscene ritual .\nDara: How dare you ? How dare you criticize my way of life and my beliefs ?\nDr. Timicin: Please . Please , Dara . Please .\nDara: Where will you go ?\nDr. Timicin: I do n't know .\nDara: And where will you die ? I can not bear the thought of you being laid to rest on some other world . That you will not lie beside my mother . That I will not be able to lie beside you when my Resolution comes . I 'm sorry . I do n't know how you can ... go on with your life knowing that each day is an insult to everything we believe in . Father , I love you . But I am ashamed .", "output": "REFERENCE Dara", "explanation": "The number sixty here refers to an age. Although it is about Dara's age, the correct answer it \"AGE\"."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Dialogue"], "Instance": {"id": "task304-9497003497ee46a9bb7d7d3ede91a0aa", "input": "Barbara Royle:  How 's your diet going , Cheryl ?\nCheryl Carroll: Oh , all right thanks , yeah , Barbara , I lost 4 pounds ... and then I put _ 2 _ back on and then another 2 . But I 've not gained any .\nBarbara Royle: Oh , well I think you 're doing ever so well to stick to it , love .", "output": ["REFERENCE pounds"]}, "Instance License": ["MIT"], "prediction": "OTHER"}
+{"id": "task304-52fd97478e9c4d5c9df41a978842949a", "Task": "task304_numeric_fused_head_resolution", "Contributors": "['Pegah Alipoormolabashi']", "Source": ["numeric_fused_head"], "URL": ["https://github.com/yanaiela/num_fh"], "Categories": ["Coreference Resolution"], "Reasoning": ["Commonsense Reasoning -> Numerical Commonsense Reasoning"], "Definition": ["In this task, you will use your knowledge about language (and common sense) to determine what element the marked number refers to. The numbers are marked with two underlines around them, like: _ number _. There are several possible answers, you'll need to choose the proper one. Carefully read the given text, pay special attention to the marked number, think about what (unwritten) information the marked number holds inside, choose the most adequate word(s) from the optional answers. If none of them seems right to you, there's also an option for other. If your answer is \"REFERENCE\", also write the reference entity, otherwise write the implicit option name. Options to choose from are:\nREFERENCE: Some object which is being mentioned in the text before or after the target number. The reference answer has a higher priority than any other. If both Reference and another answer are possible, prioritize the Reference.\nYEAR: Describing a calendric year\nAGE: Describing someone's age\nCURRENCY: Reference to some monetary value e.g dollar, euro etc.\nPEOPLE: Describing a single/plural persons\nTIME: Describing a time of the day. Usually you can add the word o'clock after those numbers.\nOTHER: Some other option, which isn't listed here."], "Positive Examples": [{"input": "Jess Mastriani: No, I don't want another crooler, thank you very much.\n FBI Agent Nicole Scott: But it's good for you. It's got... honeyglaze. Please die for this crooler, Jess.\n Jess Mastriani: I've had _ two _ already. Who eats three croolers in a night? \nFBI Agent Nicole Scott: Take a look. [Nicole takes a huge bite] Mmmmm, Mmmmm, Mmmmm!", "output": "REFERENCE crooler", "explanation": "In this example, the number two refers to something that appears in this text. In this example, it refers to the word: crooler."}, {"input": "Adam Adamant: Do you know I haven't been to the theatre since, eh... _ '96 _.\nWilliam E. Simms: Ah, what you see... [catches on]", "output": "YEAR", "explanation": "In this example, the number 96 refers to the year 1996."}, {"input": "Jack: Have you had dinner? If memory serves, you always liked Mitchellis. \nSydney: I haven't eaten there since I was _ eight _.\nJack: I do eat, you know.", "output": "AGE", "explanation": "In this example, eight is being an indicator of an age."}], "Negative Examples": [{"input": "Joy Stark: I'm paying our credit card bill.\nEddie Stark: Well why you sending them 500 dollars? \nJoy Stark: Because we owe them _ 1200 _.", "output": "YEAR", "explanation": "From the context, it can be driven that 1200 describes an amount of money, and doesn't refer to a year."}, {"input": "Joy Stark: Okay, remember that the garbage goes out on Tuesday and if you see a man in the bushes it's probably just the gardener so please don't call _ 911 _ ... again.", "output": "REFERENCE phone number", "explanation": "The number 911 refers to a phone number, that is correct. but the answer in cases like this should be \"OTHER\". The only time you can use words other than the defined labels, is when the referenced entity is present in the text. In this case, \"phone number\" is not present in the text, so you should just use \"OTHER\"."}, {"input": "Dara:  Father , come home . This is wrong .\nDr. Timicin: Dara , if I could show you the work I have begun . There 's still so much for me to do .\nDara: There is nothing for me to look at . It is irrelevant .\nLwaxana Troi: Your father 's work may save your world , my dear . I would hardly consider that irrelevant .\nDara: All I 'm concerned with now is you , not your work . Your work is over . It is your time to rest .\nLwaxana Troi: Perhaps you will feel differently as you get a little older - say approaching _ sixty _ .\nDara: My father taught me to cherish the Resolution . I do n't know how you have poisoned him to reject it .\nLwaxana Troi: It 's an obscene ritual .\nDara: How dare you ? How dare you criticize my way of life and my beliefs ?\nDr. Timicin: Please . Please , Dara . Please .\nDara: Where will you go ?\nDr. Timicin: I do n't know .\nDara: And where will you die ? I can not bear the thought of you being laid to rest on some other world . That you will not lie beside my mother . That I will not be able to lie beside you when my Resolution comes . I 'm sorry . I do n't know how you can ... go on with your life knowing that each day is an insult to everything we believe in . Father , I love you . But I am ashamed .", "output": "REFERENCE Dara", "explanation": "The number sixty here refers to an age. Although it is about Dara's age, the correct answer it \"AGE\"."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Dialogue"], "Instance": {"id": "task304-52fd97478e9c4d5c9df41a978842949a", "input": "Lieutenant Okubo:  Shall I finish him off ?\nBaron Nishi: No . Treat him .\nLieutenant Okubo: But , sir ...\nBaron Nishi: Okubo , you would expect the same , would n't you ? Endo , treat him .\nMedic Endo: We are low on morphine as it is .\nShimizu: Sir , the Americans would not treat a wounded Japanese soldier .\nBaron Nishi: Son , have you ever met _ one _ ? Treat him .", "output": ["REFERENCE soldier"]}, "Instance License": ["MIT"], "prediction": "OTHER"}
+{"id": "task304-a6d75eb8512f42d7b516b6592a56e3d2", "Task": "task304_numeric_fused_head_resolution", "Contributors": "['Pegah Alipoormolabashi']", "Source": ["numeric_fused_head"], "URL": ["https://github.com/yanaiela/num_fh"], "Categories": ["Coreference Resolution"], "Reasoning": ["Commonsense Reasoning -> Numerical Commonsense Reasoning"], "Definition": ["In this task, you will use your knowledge about language (and common sense) to determine what element the marked number refers to. The numbers are marked with two underlines around them, like: _ number _. There are several possible answers, you'll need to choose the proper one. Carefully read the given text, pay special attention to the marked number, think about what (unwritten) information the marked number holds inside, choose the most adequate word(s) from the optional answers. If none of them seems right to you, there's also an option for other. If your answer is \"REFERENCE\", also write the reference entity, otherwise write the implicit option name. Options to choose from are:\nREFERENCE: Some object which is being mentioned in the text before or after the target number. The reference answer has a higher priority than any other. If both Reference and another answer are possible, prioritize the Reference.\nYEAR: Describing a calendric year\nAGE: Describing someone's age\nCURRENCY: Reference to some monetary value e.g dollar, euro etc.\nPEOPLE: Describing a single/plural persons\nTIME: Describing a time of the day. Usually you can add the word o'clock after those numbers.\nOTHER: Some other option, which isn't listed here."], "Positive Examples": [{"input": "Jess Mastriani: No, I don't want another crooler, thank you very much.\n FBI Agent Nicole Scott: But it's good for you. It's got... honeyglaze. Please die for this crooler, Jess.\n Jess Mastriani: I've had _ two _ already. Who eats three croolers in a night? \nFBI Agent Nicole Scott: Take a look. [Nicole takes a huge bite] Mmmmm, Mmmmm, Mmmmm!", "output": "REFERENCE crooler", "explanation": "In this example, the number two refers to something that appears in this text. In this example, it refers to the word: crooler."}, {"input": "Adam Adamant: Do you know I haven't been to the theatre since, eh... _ '96 _.\nWilliam E. Simms: Ah, what you see... [catches on]", "output": "YEAR", "explanation": "In this example, the number 96 refers to the year 1996."}, {"input": "Jack: Have you had dinner? If memory serves, you always liked Mitchellis. \nSydney: I haven't eaten there since I was _ eight _.\nJack: I do eat, you know.", "output": "AGE", "explanation": "In this example, eight is being an indicator of an age."}], "Negative Examples": [{"input": "Joy Stark: I'm paying our credit card bill.\nEddie Stark: Well why you sending them 500 dollars? \nJoy Stark: Because we owe them _ 1200 _.", "output": "YEAR", "explanation": "From the context, it can be driven that 1200 describes an amount of money, and doesn't refer to a year."}, {"input": "Joy Stark: Okay, remember that the garbage goes out on Tuesday and if you see a man in the bushes it's probably just the gardener so please don't call _ 911 _ ... again.", "output": "REFERENCE phone number", "explanation": "The number 911 refers to a phone number, that is correct. but the answer in cases like this should be \"OTHER\". The only time you can use words other than the defined labels, is when the referenced entity is present in the text. In this case, \"phone number\" is not present in the text, so you should just use \"OTHER\"."}, {"input": "Dara:  Father , come home . This is wrong .\nDr. Timicin: Dara , if I could show you the work I have begun . There 's still so much for me to do .\nDara: There is nothing for me to look at . It is irrelevant .\nLwaxana Troi: Your father 's work may save your world , my dear . I would hardly consider that irrelevant .\nDara: All I 'm concerned with now is you , not your work . Your work is over . It is your time to rest .\nLwaxana Troi: Perhaps you will feel differently as you get a little older - say approaching _ sixty _ .\nDara: My father taught me to cherish the Resolution . I do n't know how you have poisoned him to reject it .\nLwaxana Troi: It 's an obscene ritual .\nDara: How dare you ? How dare you criticize my way of life and my beliefs ?\nDr. Timicin: Please . Please , Dara . Please .\nDara: Where will you go ?\nDr. Timicin: I do n't know .\nDara: And where will you die ? I can not bear the thought of you being laid to rest on some other world . That you will not lie beside my mother . That I will not be able to lie beside you when my Resolution comes . I 'm sorry . I do n't know how you can ... go on with your life knowing that each day is an insult to everything we believe in . Father , I love you . But I am ashamed .", "output": "REFERENCE Dara", "explanation": "The number sixty here refers to an age. Although it is about Dara's age, the correct answer it \"AGE\"."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Dialogue"], "Instance": {"id": "task304-a6d75eb8512f42d7b516b6592a56e3d2", "input": "Mr. E.F. Duncan, Owner Duncan's Toy Chest:  You see that tree there ? Well , to show our appreciation for your generosity , I 'm gon na let you select an object from that tree that you can take home with you .\nKevin McCallister: For free ?\nMr. E.F. Duncan, Owner Duncan's Toy Chest: Oh , yes . Oh , and may I make a suggestion ? Take the turtle doves .\nKevin McCallister: I can have _ two _ ?\nMr. E.F. Duncan, Owner Duncan's Toy Chest: Well , two turtle doves . I 'll tell you what you do : you keep one , and you give the other one to a very special person . You see , turtle doves are a symbol of friendship and love . And as long as each of you has your turtle dove , you 'll be friends forever .\nKevin McCallister: Wow , I never knew that . I thought they were just part of a song .\nMr. E.F. Duncan, Owner Duncan's Toy Chest: They are . And for that very special reason .", "output": ["REFERENCE doves"]}, "Instance License": ["MIT"], "prediction": "REFERENCE turtle doves"}
+{"id": "task304-f6d6acf8797a40f7ab867ff04cb1432a", "Task": "task304_numeric_fused_head_resolution", "Contributors": "['Pegah Alipoormolabashi']", "Source": ["numeric_fused_head"], "URL": ["https://github.com/yanaiela/num_fh"], "Categories": ["Coreference Resolution"], "Reasoning": ["Commonsense Reasoning -> Numerical Commonsense Reasoning"], "Definition": ["In this task, you will use your knowledge about language (and common sense) to determine what element the marked number refers to. The numbers are marked with two underlines around them, like: _ number _. There are several possible answers, you'll need to choose the proper one. Carefully read the given text, pay special attention to the marked number, think about what (unwritten) information the marked number holds inside, choose the most adequate word(s) from the optional answers. If none of them seems right to you, there's also an option for other. If your answer is \"REFERENCE\", also write the reference entity, otherwise write the implicit option name. Options to choose from are:\nREFERENCE: Some object which is being mentioned in the text before or after the target number. The reference answer has a higher priority than any other. If both Reference and another answer are possible, prioritize the Reference.\nYEAR: Describing a calendric year\nAGE: Describing someone's age\nCURRENCY: Reference to some monetary value e.g dollar, euro etc.\nPEOPLE: Describing a single/plural persons\nTIME: Describing a time of the day. Usually you can add the word o'clock after those numbers.\nOTHER: Some other option, which isn't listed here."], "Positive Examples": [{"input": "Jess Mastriani: No, I don't want another crooler, thank you very much.\n FBI Agent Nicole Scott: But it's good for you. It's got... honeyglaze. Please die for this crooler, Jess.\n Jess Mastriani: I've had _ two _ already. Who eats three croolers in a night? \nFBI Agent Nicole Scott: Take a look. [Nicole takes a huge bite] Mmmmm, Mmmmm, Mmmmm!", "output": "REFERENCE crooler", "explanation": "In this example, the number two refers to something that appears in this text. In this example, it refers to the word: crooler."}, {"input": "Adam Adamant: Do you know I haven't been to the theatre since, eh... _ '96 _.\nWilliam E. Simms: Ah, what you see... [catches on]", "output": "YEAR", "explanation": "In this example, the number 96 refers to the year 1996."}, {"input": "Jack: Have you had dinner? If memory serves, you always liked Mitchellis. \nSydney: I haven't eaten there since I was _ eight _.\nJack: I do eat, you know.", "output": "AGE", "explanation": "In this example, eight is being an indicator of an age."}], "Negative Examples": [{"input": "Joy Stark: I'm paying our credit card bill.\nEddie Stark: Well why you sending them 500 dollars? \nJoy Stark: Because we owe them _ 1200 _.", "output": "YEAR", "explanation": "From the context, it can be driven that 1200 describes an amount of money, and doesn't refer to a year."}, {"input": "Joy Stark: Okay, remember that the garbage goes out on Tuesday and if you see a man in the bushes it's probably just the gardener so please don't call _ 911 _ ... again.", "output": "REFERENCE phone number", "explanation": "The number 911 refers to a phone number, that is correct. but the answer in cases like this should be \"OTHER\". The only time you can use words other than the defined labels, is when the referenced entity is present in the text. In this case, \"phone number\" is not present in the text, so you should just use \"OTHER\"."}, {"input": "Dara:  Father , come home . This is wrong .\nDr. Timicin: Dara , if I could show you the work I have begun . There 's still so much for me to do .\nDara: There is nothing for me to look at . It is irrelevant .\nLwaxana Troi: Your father 's work may save your world , my dear . I would hardly consider that irrelevant .\nDara: All I 'm concerned with now is you , not your work . Your work is over . It is your time to rest .\nLwaxana Troi: Perhaps you will feel differently as you get a little older - say approaching _ sixty _ .\nDara: My father taught me to cherish the Resolution . I do n't know how you have poisoned him to reject it .\nLwaxana Troi: It 's an obscene ritual .\nDara: How dare you ? How dare you criticize my way of life and my beliefs ?\nDr. Timicin: Please . Please , Dara . Please .\nDara: Where will you go ?\nDr. Timicin: I do n't know .\nDara: And where will you die ? I can not bear the thought of you being laid to rest on some other world . That you will not lie beside my mother . That I will not be able to lie beside you when my Resolution comes . I 'm sorry . I do n't know how you can ... go on with your life knowing that each day is an insult to everything we believe in . Father , I love you . But I am ashamed .", "output": "REFERENCE Dara", "explanation": "The number sixty here refers to an age. Although it is about Dara's age, the correct answer it \"AGE\"."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Dialogue"], "Instance": {"id": "task304-f6d6acf8797a40f7ab867ff04cb1432a", "input": "Jane Rizzoli:  Yes ! Done ! Every follow - up report . What 's my price ?\nBarry Frost: 2 days off to hang with your boyfriend\nJane Rizzoli: Hm , first days I have taken in a year . BPD owes me a 116\nVince Korsak: That 's nothing , they owe me _ 243 _\nBarry Frost: Why are you two competing over who takes the fewest vacation days ?\nJane Rizzoli: Because we 're studs\nBarry Frost: So what do you and Casey have planned ?\nJane Rizzoli: Well , he only has 72 hours off , so \" nothing \"", "output": ["REFERENCE days"]}, "Instance License": ["MIT"], "prediction": "OTHER"}
+{"id": "task760-58df3a6a6727493589cd11b9ff087102", "Task": "task760_msr_sqa_long_text_generation", "Contributors": "['Shreya Sarnaik sjsarnai@asu.edu']", "Source": ["msr_sqa"], "URL": ["https://huggingface.co/datasets/msr_sqa"], "Categories": ["Data to Text"], "Reasoning": ["Multihop Reasoning"], "Definition": ["You are given data in tabular format and you need to generate a passage with content in plain text format based on the information present in the table."], "Positive Examples": [{"input": "Table: ['Pick', 'Player', 'Team', 'Position', 'School']. ['1', 'Ben McDonald', 'Baltimore Orioles', 'RHP', 'Louisiana State University']. ['2', 'Tyler Houston', 'Atlanta Braves', 'C', 'Valley HS (Las Vegas, NV)']. ['3', 'Roger Salkeld', 'Seattle Mariners', 'RHP', 'Saugus (CA) HS']. ['4', 'Jeff Jackson', 'Philadelphia Phillies', 'OF', 'Simeon HS (Chicago, IL)']. ['5', 'Donald Harris', 'Texas Rangers', 'OF', 'Texas Tech University']. ['6', 'Paul Coleman', 'Saint Louis Cardinals', 'OF', 'Frankston (TX) HS']. ['7', 'Frank Thomas', 'Chicago White Sox', '1B', 'Auburn University']. ['8', 'Earl Cunningham', 'Chicago Cubs', 'OF', 'Lancaster (SC) HS']. ['9', 'Kyle Abbott', 'California Angels', 'LHP', 'Long Beach State University']. ['10', 'Charles Johnson', 'Montreal Expos', 'C', 'Westwood HS (Fort Pierce, FL)']. ['11', 'Calvin Murray', 'Cleveland Indians', '3B', 'W.T. White High School (Dallas, TX)']. ['12', 'Jeff Juden', 'Houston Astros', 'RHP', 'Salem (MA) HS']. ['13', 'Brent Mayne', 'Kansas City Royals', 'C', 'Cal State Fullerton']. ['14', 'Steve Hosey', 'San Francisco Giants', 'OF', 'Fresno State University']. ['15', 'Kiki Jones', 'Los Angeles Dodgers', 'RHP', 'Hillsborough HS (Tampa, FL)']. ['16', 'Greg Blosser', 'Boston Red Sox', 'OF', 'Sarasota (FL) HS']. ['17', 'Cal Eldred', 'Milwaukee Brewers', 'RHP', 'University of Iowa']. ['18', 'Willie Greene', 'Pittsburgh Pirates', 'SS', 'Jones County HS (Gray, GA)']. ['19', 'Eddie Zosky', 'Toronto Blue Jays', 'SS', 'Fresno State University']. ['20', 'Scott Bryant', 'Cincinnati Reds', 'OF', 'University of Texas']. ['21', 'Greg Gohr', 'Detroit Tigers', 'RHP', 'Santa Clara University']. ['22', 'Tom Goodwin', 'Los Angeles Dodgers', 'OF', 'Fresno State University']. ['23', 'Mo Vaughn', 'Boston Red Sox', '1B', 'Seton Hall University']. ['24', 'Alan Zinter', 'New York Mets', 'C', 'University of Arizona']. ['25', 'Chuck Knoblauch', 'Minnesota Twins', '2B', 'Texas A&M University']. ['26', 'Scott Burrell', 'Seattle Mariners', 'RHP', 'Hamden (CT) HS']", "output": "Passage: The player named Ben McDonald, plays as Pick-1.Ben McDonald plays for the team Baltimore Orioles, at position RHP. Ben McDonald belongs to the school Louisiana State University. The player named Tyler Houston, plays as Pick-2.Tyler Houston plays for the team Atlanta Braves, at position C. Tyler Houston belongs to the school Valley HS (Las Vegas, NV). The player named Roger Salkeld, plays as Pick-3.Roger Salkeld plays for the team Seattle Mariners, at position RHP. Roger Salkeld belongs to the school Saugus (CA) HS. The player named Jeff Jackson, plays as Pick-4.Jeff Jackson plays for the team Philadelphia Phillies, at position OF. Jeff Jackson belongs to the school Simeon HS (Chicago, IL). The player named Donald Harris, plays as Pick-5.Donald Harris plays for the team Texas Rangers, at position OF. Donald Harris belongs to the school Texas Tech University. The player named Paul Coleman, plays as Pick-6.Paul Coleman plays for the team Saint Louis Cardinals, at position OF. Paul Coleman belongs to the school Frankston (TX) HS. The player named Frank Thomas, plays as Pick-7.Frank Thomas plays for the team Chicago White Sox, at position 1B. Frank Thomas belongs to the school Auburn University. The player named Earl Cunningham, plays as Pick-8.Earl Cunningham plays for the team Chicago Cubs, at position OF. Earl Cunningham belongs to the school Lancaster (SC) HS. The player named Kyle Abbott, plays as Pick-9.Kyle Abbott plays for the team California Angels, at position LHP. Kyle Abbott belongs to the school Long Beach State University. The player named Charles Johnson, plays as Pick-10.Charles Johnson plays for the team Montreal Expos, at position C. Charles Johnson belongs to the school Westwood HS (Fort Pierce, FL). The player named Calvin Murray, plays as Pick-11.Calvin Murray plays for the team Cleveland Indians, at position 3B. Calvin Murray belongs to the school W.T. White High School (Dallas, TX). The player named Jeff Juden, plays as Pick-12.Jeff Juden plays for the team Houston Astros, at position RHP. Jeff Juden belongs to the school Salem (MA) HS. The player named Brent Mayne, plays as Pick-13.Brent Mayne plays for the team Kansas City Royals, at position C. Brent Mayne belongs to the school Cal State Fullerton. The player named Steve Hosey, plays as Pick-14.Steve Hosey plays for the team San Francisco Giants, at position OF. Steve Hosey belongs to the school Fresno State University. The player named Kiki Jones, plays as Pick-15.Kiki Jones plays for the team Los Angeles Dodgers, at position RHP. Kiki Jones belongs to the school Hillsborough HS (Tampa, FL). The player named Greg Blosser, plays as Pick-16.Greg Blosser plays for the team Boston Red Sox, at position OF. Greg Blosser belongs to the school Sarasota (FL) HS. The player named Cal Eldred, plays as Pick-17.Cal Eldred plays for the team Milwaukee Brewers, at position RHP. Cal Eldred belongs to the school University of Iowa. The player named Willie Greene, plays as Pick-18.Willie Greene plays for the team Pittsburgh Pirates, at position SS. Willie Greene belongs to the school Jones County HS (Gray, GA). The player named Eddie Zosky, plays as Pick-19.Eddie Zosky plays for the team Toronto Blue Jays, at position SS. Eddie Zosky belongs to the school Fresno State University. The player named Scott Bryant, plays as Pick-20.Scott Bryant plays for the team Cincinnati Reds, at position OF. Scott Bryant belongs to the school University of Texas. The player named Greg Gohr, plays as Pick-21.Greg Gohr plays for the team Detroit Tigers, at position RHP. Greg Gohr belongs to the school Santa Clara University. The player named Tom Goodwin, plays as Pick-22.Tom Goodwin plays for the team Los Angeles Dodgers, at position OF. Tom Goodwin belongs to the school Fresno State University. The player named Mo Vaughn, plays as Pick-23.Mo Vaughn plays for the team Boston Red Sox, at position 1B. Mo Vaughn belongs to the school Seton Hall University. The player named Alan Zinter, plays as Pick-24.Alan Zinter plays for the team New York Mets, at position C. Alan Zinter belongs to the school University of Arizona. The player named Chuck Knoblauch, plays as Pick-25.Chuck Knoblauch plays for the team Minnesota Twins, at position 2B. Chuck Knoblauch belongs to the school Texas A&M University. The player named Scott Burrell, plays as Pick-26.Scott Burrell plays for the team Seattle Mariners, at position RHP. Scott Burrell belongs to the school Hamden (CT) HS.", "explanation": "The output correctly captures the data in table and generates a long text passage which covers all the given information."}, {"input": "Table: ['Rank','Name', 'Nationality', 'Time (hand)', 'Notes']. ['','Tommy Green', 'Great Britain', '4:50:10', 'OR']. ['', 'Janis Dalins', 'Latvia', '4:57:20', '']. ['', 'Ugo Frigerio', 'Italy', '4:59:06', '']. ['4', 'Karl Hahnel', 'Germany', '5:06:06', '']. ['5', 'Ettore Rivolta', 'Italy', '5:07:39', '']. ['6', 'Paul Sievert', 'Germany', '5:16:41', '']. ['7', 'Henri Quintric', 'France', '5:27:25', '']. ['8', 'Ernie Crosbie', 'United States', '5:28:02', '']. ['9', 'Bill Chisholm', 'United States', '5:51:00', '']. ['10', 'Alfred Maasik', 'Estonia', '6:19:00', '']. ['', 'Henry Cieman', 'Canada', '', 'DNF']. ['', 'John Moralis', 'Greece', '', 'DNF']. ['', 'Francesco Pretti', 'Italy', '', 'DNF']. ['', 'Arthur Tell Schwab', 'Switzerland', '', 'DNF']. ['', 'Harry Hinkel', 'United States', '', 'DNF']", "output": "Passage:  The Great Britain athlete named Tommy Green is ranked  globally. Tommy Green completed the marathon in 4:50:10 seconds. The Latvia athlete named Janis Dalins is ranked  globally. Janis Dalins completed the marathon in 4:57:20 seconds. The Italy athlete named Ugo Frigerio is ranked  globally. Ugo Frigerio completed the marathon in 4:59:06 seconds. The Germany athlete named Karl Hahnel is ranked 4 globally. Karl Hahnel completed the marathon in 5:06:06 seconds. The Italy athlete named Ettore Rivolta is ranked 5 globally. Ettore Rivolta completed the marathon in 5:07:39 seconds. The Germany athlete named Paul Sievert is ranked 6 globally. Paul Sievert completed the marathon in 5:16:41 seconds. The France athlete named Henri Quintric is ranked 7 globally. Henri Quintric completed the marathon in 5:27:25 seconds. The United States athlete named Ernie Crosbie is ranked 8 globally. Ernie Crosbie completed the marathon in 5:28:02 seconds. The United States athlete named Bill Chisholm is ranked 9 globally. Bill Chisholm completed the marathon in 5:51:00 seconds. The Estonia athlete named Alfred Maasik is ranked 10 globally. Alfred Maasik completed the marathon in 6:19:00 seconds. The Canada athlete named Henry Cieman is ranked  globally. Henry Cieman completed the marathon in  seconds. The Greece athlete named John Moralis is ranked  globally. John Moralis completed the marathon in  seconds. The Italy athlete named Francesco Pretti is ranked  globally. Francesco Pretti completed the marathon in  seconds. The Switzerland athlete named Arthur Tell Schwab is ranked  globally. Arthur Tell Schwab completed the marathon in  seconds. The United States athlete named Harry Hinkel is ranked  globally. Harry Hinkel completed the marathon in  seconds.", "explanation": "The output correctly captures the data in table and generates a long text passage which covers all the given information."}, {"input": "Table: ['Year', 'Miss Northern Ireland', 'Hometown', 'Placement at Miss World', 'Notes']. ['2011', 'Finola Guinnane', 'Drumbo', 'Non-Finalist', 'Top 20 of Beach Beauty and Top 77 of Beauty with a Purpose at Miss World 2011']. ['2012', 'Tiffany Brien', 'Belfast', 'Top 30', 'Top 10 of Beach Fashion and 1st runner-up of Sports & Fitness at Miss World 2012']. ['2010', 'Lori Moore', 'Belfast', 'Top 25', 'Winner of Sports at Miss World 2010']. ['2009', 'Cherie Gardiner', 'Bangor', 'Non-Finalist', '']. ['2008', 'Judith Wilson', 'Enniskillen', 'Non-Finalist', 'Top 19 of Talent at Miss World 2008']. ['2007', 'Melissa Patton', 'Belfast', 'Non-Finalist', '']. ['2006', 'Catherine Jean Milligan', 'Newtownards', 'Top 17', 'Winner of Miss Talent at Miss World 2006']. ['2005', 'Lucy Evangelista', 'Portglenone', 'Top 15', 'Later Miss United Kingdom 2005 and Miss Universe United Kingdom 2005 2nd runner-up']. ['2004', 'Kirsty Anne Gabriel Stewart', 'Enniskillen', 'Non-Finalist', '']. ['2003', 'Diana Sayers', 'Belfast', 'Non-Finalist', '']. ['2002', 'Gayle Williamson', 'Lurgan', 'Non-Finalist', 'Later Miss United Kingdom 2002']. ['2001', 'Angela McCarthy', 'Belfast', 'Non-Finalist', '']. ['2000', 'Julie Lee-Ann Martin', 'Belfast', 'Non-Finalist', '']", "output": "Passage:  Tiffany Brien from Belfast was Miss Northern Ireland in the year 2012. Tiffany Brien was placed as a Top 30 at Miss World. Tiffany Brien was Top 10 of Beach Fashion and 1st runner-up of Sports & Fitness at Miss World 2012. Finola Guinnane from Drumbo was Miss Northern Ireland in the year 2011. Finola Guinnane was placed as a Non-Finalist at Miss World. Finola Guinnane was Top 20 of Beach Beauty and Top 77 of Beauty with a Purpose at Miss World 2011. Lori Moore from Belfast was Miss Northern Ireland in the year 2010. Lori Moore was placed as a Top 25 at Miss World. Lori Moore was Winner of Sports at Miss World 2010. Cherie Gardiner from Bangor was Miss Northern Ireland in the year 2009. Cherie Gardiner was placed as a Non-Finalist at Miss World. Cherie Gardiner was . Judith Wilson from Enniskillen was Miss Northern Ireland in the year 2008. Judith Wilson was placed as a Non-Finalist at Miss World. Judith Wilson was Top 19 of Talent at Miss World 2008. Melissa Patton from Belfast was Miss Northern Ireland in the year 2007. Melissa Patton was placed as a Non-Finalist at Miss World. Melissa Patton was . Catherine Jean Milligan from Newtownards was Miss Northern Ireland in the year 2006. Catherine Jean Milligan was placed as a Top 17 at Miss World. Catherine Jean Milligan was Winner of Miss Talent at Miss World 2006. Lucy Evangelista from Portglenone was Miss Northern Ireland in the year 2005. Lucy Evangelista was placed as a Top 15 at Miss World. Lucy Evangelista was Later Miss United Kingdom 2005 and Miss Universe United Kingdom 2005 2nd runner-up. Kirsty Anne Gabriel Stewart from Enniskillen was Miss Northern Ireland in the year 2004. Kirsty Anne Gabriel Stewart was placed as a Non-Finalist at Miss World. Kirsty Anne Gabriel Stewart was . Diana Sayers from Belfast was Miss Northern Ireland in the year 2003. Diana Sayers was placed as a Non-Finalist at Miss World. Diana Sayers was . Gayle Williamson from Lurgan was Miss Northern Ireland in the year 2002. Gayle Williamson was placed as a Non-Finalist at Miss World. Gayle Williamson was Later Miss United Kingdom 2002. Angela McCarthy from Belfast was Miss Northern Ireland in the year 2001. Angela McCarthy was placed as a Non-Finalist at Miss World. Angela McCarthy was . Julie Lee-Ann Martin from Belfast was Miss Northern Ireland in the year 2000. Julie Lee-Ann Martin was placed as a Non-Finalist at Miss World. Julie Lee-Ann Martin was.", "explanation": "The output correctly captures the data in table and generates a long text passage which covers all the given information."}], "Negative Examples": [{"input": "Table: ['Year','Title','Peak chart positions US Air','Peak chart positions US Main','Peak chart positions US Mod',Album]. ['1990', 'Dig a Hole', '--', '--', '--', 'Non-album single']. ['1993', 'Mister Love', '--', '--', '--', 'Velvet']. ['1994', 'Mister Love', '--', '--', '--', 'Rubberneck']. ['1995', 'Possum Kingdom', '40', '9', '4', 'Rubberneck']. ['1995', 'Away', '--', '23', '28', 'Rubberneck']. ['1996', 'Tyler', '--', '--', '--', 'Rubberneck']. ['1996', 'Backslider', '--', '--', '--', 'Rubberneck']. ['2001', 'Push the Hand', '--', '34', '--', 'Hell Below/Stars Above']. ['2008', 'No Deliverance', '--', '38', '--', 'No Deliverance']. ['2009', 'Song I Hate', '--', '--', '--', 'No Deliverance']. ['2012', 'Summer of the Strange', '--', '--', '--', 'Play.Rock.Music']", "output": "Passage: Dig a Hole's chart positions in US Air, US Main, and US mod were --, --, and -- respectively. The title track 'Mister Love' from the album 'Velvet', was released in the year 1993. Mister Love's chart positions in US Air, US Main, and US mod were --, --, and -- respectively. The title track 'Mister Love' from the album 'Rubberneck', was released in the year 1994. Mister Love's chart positions in US Air, US Main, and US mod were --, --, and -- respectively. The title track 'Possum Kingdom' from the album 'Rubberneck', was released in the year 1995. Possum Kingdom's chart positions in US Air, US Main, and US mod were 40, 9, and 4 respectively. The title track 'Away' from the album 'Rubberneck', was released in the year 1995. Away's chart positions in US Air, US Main, and US mod were --, 23, and 28 respectively. The title track 'Tyler' from the album 'Rubberneck', was released in the year 1996. Tyler's chart positions in US Air, US Main, and US mod were --, --, and -- respectively. The title track 'Backslider' from the album 'Rubberneck', was released in the year 1996. Backslider's chart positions in US Air, US Main, and US mod were --, --, and -- respectively. The title track 'Push the Hand' from the album 'Hell Below/Stars Above', was released in the year 2001. Push the Hand's chart positions in US Air, US Main, and US mod were --, 34, and -- respectively. The title track 'No Deliverance' from the album 'No Deliverance', was released in the year 2008. No Deliverance's chart positions in US Air, US Main, and US mod were --, 38, and -- respectively. The title track 'Song I Hate' from the album 'No Deliverance', was released in the year 2009. Song I Hate's chart positions in US Air, US Main, and US mod were --, --, and -- respectively. The title track 'Summer of the Strange' from the album 'Play.Rock.Music', was released in the year 2012. Summer of the Strange's chart positions in US Air, US Main, and US mod were --, --, and -- respectively.", "explanation": "This is a bad example of 'long text passage generation task' because it fails to format/clean the missing/None/empty data values in the long text generation"}, {"input": "Table: ['Year','Title','Peak chart positions US Air','Peak chart positions US Main','Peak chart positions US Mod',Album]. ['1990', 'Dig a Hole', '--', '--', '--', 'Non-album single']. ['1993', 'Mister Love', '--', '--', '--', 'Velvet']. ['1994', 'Mister Love', '--', '--', '--', 'Rubberneck']. ['1995', 'Possum Kingdom', '40', '9', '4', 'Rubberneck']. ['1995', 'Away', '--', '23', '28', 'Rubberneck']. ['1996', 'Tyler', '--', '--', '--', 'Rubberneck']. ['1996', 'Backslider', '--', '--', '--', 'Rubberneck']. ['2001', 'Push the Hand', '--', '34', '--', 'Hell Below/Stars Above']. ['2008', 'No Deliverance', '--', '38', '--', 'No Deliverance']. ['2009', 'Song I Hate', '--', '--', '--', 'No Deliverance']. ['2012', 'Summer of the Strange', '--', '--', '--', 'Play.Rock.Music']", "output": "Passage: The title track 'Dig a Hole' from the album 'Non-album single', was released in the year 1990. Dig a Hole's chart positions in US Air, US Main,  and US mod were --, --, and -- respectively. The title track 'Mister Love' from the album 'Velvet', was released in the year 1993. Mister Love's chart positions in US Air, US Main, and US mod were --, --, and -- respectively. The title track 'Mister Love' from the album 'Rubberneck', was released in the year 1994. Mister Love's chart positions in US Air, US Main, and US mod were --, --, and -- respectively. The title track 'Possum Kingdom' from the album 'Rubberneck', was released in the year 1995. Possum Kingdom's chart positions in US Air, US Main, and US mod were 40, 9, and 4 respectively. The title track 'Away' from the album 'Rubberneck', was released in the year 1995. Away's chart positions in US Air, US Main, and US mod were --, 23, and 28 respectively. The title track 'Tyler' from the album 'Rubberneck', was released in the year 1996. Tyler's chart positions in US Air, US Main, and US mod were --, --, and -- respectively. The title track 'Backslider' from the album 'Rubberneck', was released in the year 1996. Backslider's chart positions in US Air, US Main, and US mod were --, --, and -- respectively. The title track 'Push the Hand' from the album 'Hell Below/Stars Above', was released in the year 2001. Push the Hand's chart positions in US Air, US Main, and US mod were --, 34, and -- respectively. The title track 'No Deliverance' from the album 'No Deliverance', was released in the year 2008. No Deliverance's chart positions in US Air, US Main, and US mod were --, 38, and -- respectively. The title track 'Song I Hate' from the album 'No Deliverance', was released in the year 2009. Song I Hate's chart positions in US Air, US Main, and US mod were --, --, and -- respectively. The title track 'Summer of the Strange' from the album 'Play.Rock.Music', was released in the year 2012. Summer of the Strange's chart positions in US Air, US Main, and US mod were --, --, and -- respectively.", "explanation": "This is a bad example of 'long text passage generation task' because it fails to format/clean the missing/None/empty data values in the long text generation"}, {"input": "Table: ['Year','Title','Peak chart positions US Air','Peak chart positions US Main','Peak chart positions US Mod',Album]. ['1993', 'Mister Love', '--', '--', '--', 'Velvet']. ['1990', 'Dig a Hole', '--', '--', '--', 'Non-album single']. ['1994', 'Mister Love', '--', '--', '--', 'Rubberneck']. ['1995', 'Possum Kingdom', '40', '9', '4', 'Rubberneck']. ['1995', 'Away', '--', '23', '28', 'Rubberneck']. ['1996', 'Tyler', '--', '--', '--', 'Rubberneck']. ['1996', 'Backslider', '--', '--', '--', 'Rubberneck']. ['2001', 'Push the Hand', '--', '34', '--', 'Hell Below/Stars Above']. ['2008', 'No Deliverance', '--', '38', '--', 'No Deliverance']. ['2009', 'Song I Hate', '--', '--', '--', 'No Deliverance']. ['2012', 'Summer of the Strange', '--', '--', '--', 'Play.Rock.Music']", "output": "Passage: Mister Love's chart positions in US Air, US Main, and US mod were --, --, and -- respectively. The title track 'Mister Love' from the album 'Rubberneck', was released in the year 1994. Mister Love's chart positions in US Air, US Main, and US mod were --, --, and -- respectively. The title track 'Possum Kingdom' from the album 'Rubberneck', was released in the year 1995. Possum Kingdom's chart positions in US Air, US Main, and US mod were 40, 9, and 4 respectively. The title track 'Away' from the album 'Rubberneck', was released in the year 1995. Away's chart positions in US Air, US Main, and US mod were --, 23, and 28 respectively. The title track 'Tyler' from the album 'Rubberneck', was released in the year 1996. Tyler's chart positions in US Air, US Main, and US mod were --, --, and -- respectively. The title track 'Backslider' from the album 'Rubberneck', was released in the year 1996. Backslider's chart positions in US Air, US Main, and US mod were --, --, and -- respectively. The title track 'Push the Hand' from the album 'Hell Below/Stars Above', was released in the year 2001. Push the Hand's chart positions in US Air, US Main, and US mod were --, 34, and -- respectively. The title track 'No Deliverance' from the album 'No Deliverance', was released in the year 2008. No Deliverance's chart positions in US Air, US Main, and US mod were --, 38, and -- respectively. The title track 'Song I Hate' from the album 'No Deliverance', was released in the year 2009. Song I Hate's chart positions in US Air, US Main, and US mod were --, --, and -- respectively. The title track 'Summer of the Strange' from the album 'Play.Rock.Music', was released in the year 2012. Summer of the Strange's chart positions in US Air, US Main, and US mod were --, --, and -- respectively.", "explanation": "This is a bad example of 'long text passage generation task' because it fails to format/clean the missing/None/empty data values in the long text generation"}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Sports", "Statistics", "News"], "Instance": {"id": "task760-58df3a6a6727493589cd11b9ff087102", "input": "Table: ['Pos', 'No', 'Driver', 'Constructor', 'Laps', 'Time/Retired', 'Grid', 'Points']. ['1', '5', 'Fernando Alonso', 'Renault', '56', '1:31:33.736', '1', '10']. ['2', '16', 'Jarno Trulli', 'Toyota', '56', '+24.327', '2', '8']. ['3', '8', 'Nick Heidfeld', 'Williams-BMW', '56', '+32.188', '10', '6']. ['4', '10', 'Juan Pablo Montoya', 'McLaren-Mercedes', '56', '+41.631', '11', '5']. ['5', '17', 'Ralf Schumacher', 'Toyota', '56', '+51.854', '5', '4']. ['6', '14', 'David Coulthard', 'Red Bull-Cosworth', '56', '+1:12.543', '8', '3']. ['7', '1', 'Michael Schumacher', 'Ferrari', '56', '+1:19.988', '13', '2']. ['8', '15', 'Christian Klien', 'Red Bull-Cosworth', '56', '+1:20.835', '7', '1']. ['9', '9', 'Kimi Raikkonen', 'McLaren-Mercedes', '56', '+1:21.580', '6', '']. ['10', '12', 'Felipe Massa', 'Sauber-Petronas', '55', '+1 Lap', '14', '']. ['11', '19', 'Narain Karthikeyan', 'Jordan-Toyota', '54', '+2 Laps', '17', '']. ['12', '18', 'Tiago Monteiro', 'Jordan-Toyota', '53', '+3 Laps', '18', '']. ['13', '21', 'Christijan Albers', 'Minardi-Cosworth', '52', '+4 Laps', '19', '']. ['Ret', '2', 'Rubens Barrichello', 'Ferrari', '49', 'Handling', '12', '']. ['Ret', '6', 'Giancarlo Fisichella', 'Renault', '36', 'Collision', '3', '']. ['Ret', '7', 'Mark Webber', 'Williams-BMW', '36', 'Collision', '4', '']. ['Ret', '11', 'Jacques Villeneuve', 'Sauber-Petronas', '26', 'Spun Off', '16', '']. ['Ret', '3', 'Jenson Button', 'BAR-Honda', '2', 'Engine', '9', '']. ['Ret', '4', 'Anthony Davidson', 'BAR-Honda', '2', 'Engine', '15', '']. ['Ret', '20', 'Patrick Friesacher', 'Minardi-Cosworth', '2', 'Spun Off', '20', '']", "output": ["Passage:  The driver with number 5, Fernando Alonso, from Renault constructor, finished at position 1. Fernando Alonso completed 56 laps in 1:31:33.736 time and earned 10 points. The driver with number 16, Jarno Trulli, from Toyota constructor, finished at position 2. Jarno Trulli completed 56 laps in +24.327 time and earned 8 points. The driver with number 8, Nick Heidfeld, from Williams-BMW constructor, finished at position 3. Nick Heidfeld completed 56 laps in +32.188 time and earned 6 points. The driver with number 10, Juan Pablo Montoya, from McLaren-Mercedes constructor, finished at position 4. Juan Pablo Montoya completed 56 laps in +41.631 time and earned 5 points. The driver with number 17, Ralf Schumacher, from Toyota constructor, finished at position 5. Ralf Schumacher completed 56 laps in +51.854 time and earned 4 points. The driver with number 14, David Coulthard, from Red Bull-Cosworth constructor, finished at position 6. David Coulthard completed 56 laps in +1:12.543 time and earned 3 points. The driver with number 1, Michael Schumacher, from Ferrari constructor, finished at position 7. Michael Schumacher completed 56 laps in +1:19.988 time and earned 2 points. The driver with number 15, Christian Klien, from Red Bull-Cosworth constructor, finished at position 8. Christian Klien completed 56 laps in +1:20.835 time and earned 1 points. The driver with number 9, Kimi Raikkonen, from McLaren-Mercedes constructor, finished at position 9. Kimi Raikkonen completed 56 laps in +1:21.580 time and earned  points. The driver with number 12, Felipe Massa, from Sauber-Petronas constructor, finished at position 10. Felipe Massa completed 55 laps in +1 Lap time and earned  points. The driver with number 19, Narain Karthikeyan, from Jordan-Toyota constructor, finished at position 11. Narain Karthikeyan completed 54 laps in +2 Laps time and earned  points. The driver with number 18, Tiago Monteiro, from Jordan-Toyota constructor, finished at position 12. Tiago Monteiro completed 53 laps in +3 Laps time and earned  points. The driver with number 21, Christijan Albers, from Minardi-Cosworth constructor, finished at position 13. Christijan Albers completed 52 laps in +4 Laps time and earned  points. The driver with number 2, Rubens Barrichello, from Ferrari constructor, finished at position Ret. Rubens Barrichello completed 49 laps in Handling time and earned  points. The driver with number 6, Giancarlo Fisichella, from Renault constructor, finished at position Ret. Giancarlo Fisichella completed 36 laps in Collision time and earned  points. The driver with number 7, Mark Webber, from Williams-BMW constructor, finished at position Ret. Mark Webber completed 36 laps in Collision time and earned  points. The driver with number 11, Jacques Villeneuve, from Sauber-Petronas constructor, finished at position Ret. Jacques Villeneuve completed 26 laps in Spun Off time and earned  points. The driver with number 3, Jenson Button, from BAR-Honda constructor, finished at position Ret. Jenson Button completed 2 laps in Engine time and earned  points. The driver with number 4, Anthony Davidson, from BAR-Honda constructor, finished at position Ret. Anthony Davidson completed 2 laps in Engine time and earned  points. The driver with number 20, Patrick Friesacher, from Minardi-Cosworth constructor, finished at position Ret. Patrick Friesacher completed 2 laps in Spun Off time and earned  points."]}, "Instance License": ["Microsoft Research Data License Agreement (https://msropendata-web-api.azurewebsites.net/licenses/2f933be3-284d-500b-7ea3-2aa2fd0f1bb2/view)"], "prediction": "3"}
+{"id": "task760-d655a07ec6044870b340c63bf2b51f84", "Task": "task760_msr_sqa_long_text_generation", "Contributors": "['Shreya Sarnaik sjsarnai@asu.edu']", "Source": ["msr_sqa"], "URL": ["https://huggingface.co/datasets/msr_sqa"], "Categories": ["Data to Text"], "Reasoning": ["Multihop Reasoning"], "Definition": ["You are given data in tabular format and you need to generate a passage with content in plain text format based on the information present in the table."], "Positive Examples": [{"input": "Table: ['Pick', 'Player', 'Team', 'Position', 'School']. ['1', 'Ben McDonald', 'Baltimore Orioles', 'RHP', 'Louisiana State University']. ['2', 'Tyler Houston', 'Atlanta Braves', 'C', 'Valley HS (Las Vegas, NV)']. ['3', 'Roger Salkeld', 'Seattle Mariners', 'RHP', 'Saugus (CA) HS']. ['4', 'Jeff Jackson', 'Philadelphia Phillies', 'OF', 'Simeon HS (Chicago, IL)']. ['5', 'Donald Harris', 'Texas Rangers', 'OF', 'Texas Tech University']. ['6', 'Paul Coleman', 'Saint Louis Cardinals', 'OF', 'Frankston (TX) HS']. ['7', 'Frank Thomas', 'Chicago White Sox', '1B', 'Auburn University']. ['8', 'Earl Cunningham', 'Chicago Cubs', 'OF', 'Lancaster (SC) HS']. ['9', 'Kyle Abbott', 'California Angels', 'LHP', 'Long Beach State University']. ['10', 'Charles Johnson', 'Montreal Expos', 'C', 'Westwood HS (Fort Pierce, FL)']. ['11', 'Calvin Murray', 'Cleveland Indians', '3B', 'W.T. White High School (Dallas, TX)']. ['12', 'Jeff Juden', 'Houston Astros', 'RHP', 'Salem (MA) HS']. ['13', 'Brent Mayne', 'Kansas City Royals', 'C', 'Cal State Fullerton']. ['14', 'Steve Hosey', 'San Francisco Giants', 'OF', 'Fresno State University']. ['15', 'Kiki Jones', 'Los Angeles Dodgers', 'RHP', 'Hillsborough HS (Tampa, FL)']. ['16', 'Greg Blosser', 'Boston Red Sox', 'OF', 'Sarasota (FL) HS']. ['17', 'Cal Eldred', 'Milwaukee Brewers', 'RHP', 'University of Iowa']. ['18', 'Willie Greene', 'Pittsburgh Pirates', 'SS', 'Jones County HS (Gray, GA)']. ['19', 'Eddie Zosky', 'Toronto Blue Jays', 'SS', 'Fresno State University']. ['20', 'Scott Bryant', 'Cincinnati Reds', 'OF', 'University of Texas']. ['21', 'Greg Gohr', 'Detroit Tigers', 'RHP', 'Santa Clara University']. ['22', 'Tom Goodwin', 'Los Angeles Dodgers', 'OF', 'Fresno State University']. ['23', 'Mo Vaughn', 'Boston Red Sox', '1B', 'Seton Hall University']. ['24', 'Alan Zinter', 'New York Mets', 'C', 'University of Arizona']. ['25', 'Chuck Knoblauch', 'Minnesota Twins', '2B', 'Texas A&M University']. ['26', 'Scott Burrell', 'Seattle Mariners', 'RHP', 'Hamden (CT) HS']", "output": "Passage: The player named Ben McDonald, plays as Pick-1.Ben McDonald plays for the team Baltimore Orioles, at position RHP. Ben McDonald belongs to the school Louisiana State University. The player named Tyler Houston, plays as Pick-2.Tyler Houston plays for the team Atlanta Braves, at position C. Tyler Houston belongs to the school Valley HS (Las Vegas, NV). The player named Roger Salkeld, plays as Pick-3.Roger Salkeld plays for the team Seattle Mariners, at position RHP. Roger Salkeld belongs to the school Saugus (CA) HS. The player named Jeff Jackson, plays as Pick-4.Jeff Jackson plays for the team Philadelphia Phillies, at position OF. Jeff Jackson belongs to the school Simeon HS (Chicago, IL). The player named Donald Harris, plays as Pick-5.Donald Harris plays for the team Texas Rangers, at position OF. Donald Harris belongs to the school Texas Tech University. The player named Paul Coleman, plays as Pick-6.Paul Coleman plays for the team Saint Louis Cardinals, at position OF. Paul Coleman belongs to the school Frankston (TX) HS. The player named Frank Thomas, plays as Pick-7.Frank Thomas plays for the team Chicago White Sox, at position 1B. Frank Thomas belongs to the school Auburn University. The player named Earl Cunningham, plays as Pick-8.Earl Cunningham plays for the team Chicago Cubs, at position OF. Earl Cunningham belongs to the school Lancaster (SC) HS. The player named Kyle Abbott, plays as Pick-9.Kyle Abbott plays for the team California Angels, at position LHP. Kyle Abbott belongs to the school Long Beach State University. The player named Charles Johnson, plays as Pick-10.Charles Johnson plays for the team Montreal Expos, at position C. Charles Johnson belongs to the school Westwood HS (Fort Pierce, FL). The player named Calvin Murray, plays as Pick-11.Calvin Murray plays for the team Cleveland Indians, at position 3B. Calvin Murray belongs to the school W.T. White High School (Dallas, TX). The player named Jeff Juden, plays as Pick-12.Jeff Juden plays for the team Houston Astros, at position RHP. Jeff Juden belongs to the school Salem (MA) HS. The player named Brent Mayne, plays as Pick-13.Brent Mayne plays for the team Kansas City Royals, at position C. Brent Mayne belongs to the school Cal State Fullerton. The player named Steve Hosey, plays as Pick-14.Steve Hosey plays for the team San Francisco Giants, at position OF. Steve Hosey belongs to the school Fresno State University. The player named Kiki Jones, plays as Pick-15.Kiki Jones plays for the team Los Angeles Dodgers, at position RHP. Kiki Jones belongs to the school Hillsborough HS (Tampa, FL). The player named Greg Blosser, plays as Pick-16.Greg Blosser plays for the team Boston Red Sox, at position OF. Greg Blosser belongs to the school Sarasota (FL) HS. The player named Cal Eldred, plays as Pick-17.Cal Eldred plays for the team Milwaukee Brewers, at position RHP. Cal Eldred belongs to the school University of Iowa. The player named Willie Greene, plays as Pick-18.Willie Greene plays for the team Pittsburgh Pirates, at position SS. Willie Greene belongs to the school Jones County HS (Gray, GA). The player named Eddie Zosky, plays as Pick-19.Eddie Zosky plays for the team Toronto Blue Jays, at position SS. Eddie Zosky belongs to the school Fresno State University. The player named Scott Bryant, plays as Pick-20.Scott Bryant plays for the team Cincinnati Reds, at position OF. Scott Bryant belongs to the school University of Texas. The player named Greg Gohr, plays as Pick-21.Greg Gohr plays for the team Detroit Tigers, at position RHP. Greg Gohr belongs to the school Santa Clara University. The player named Tom Goodwin, plays as Pick-22.Tom Goodwin plays for the team Los Angeles Dodgers, at position OF. Tom Goodwin belongs to the school Fresno State University. The player named Mo Vaughn, plays as Pick-23.Mo Vaughn plays for the team Boston Red Sox, at position 1B. Mo Vaughn belongs to the school Seton Hall University. The player named Alan Zinter, plays as Pick-24.Alan Zinter plays for the team New York Mets, at position C. Alan Zinter belongs to the school University of Arizona. The player named Chuck Knoblauch, plays as Pick-25.Chuck Knoblauch plays for the team Minnesota Twins, at position 2B. Chuck Knoblauch belongs to the school Texas A&M University. The player named Scott Burrell, plays as Pick-26.Scott Burrell plays for the team Seattle Mariners, at position RHP. Scott Burrell belongs to the school Hamden (CT) HS.", "explanation": "The output correctly captures the data in table and generates a long text passage which covers all the given information."}, {"input": "Table: ['Rank','Name', 'Nationality', 'Time (hand)', 'Notes']. ['','Tommy Green', 'Great Britain', '4:50:10', 'OR']. ['', 'Janis Dalins', 'Latvia', '4:57:20', '']. ['', 'Ugo Frigerio', 'Italy', '4:59:06', '']. ['4', 'Karl Hahnel', 'Germany', '5:06:06', '']. ['5', 'Ettore Rivolta', 'Italy', '5:07:39', '']. ['6', 'Paul Sievert', 'Germany', '5:16:41', '']. ['7', 'Henri Quintric', 'France', '5:27:25', '']. ['8', 'Ernie Crosbie', 'United States', '5:28:02', '']. ['9', 'Bill Chisholm', 'United States', '5:51:00', '']. ['10', 'Alfred Maasik', 'Estonia', '6:19:00', '']. ['', 'Henry Cieman', 'Canada', '', 'DNF']. ['', 'John Moralis', 'Greece', '', 'DNF']. ['', 'Francesco Pretti', 'Italy', '', 'DNF']. ['', 'Arthur Tell Schwab', 'Switzerland', '', 'DNF']. ['', 'Harry Hinkel', 'United States', '', 'DNF']", "output": "Passage:  The Great Britain athlete named Tommy Green is ranked  globally. Tommy Green completed the marathon in 4:50:10 seconds. The Latvia athlete named Janis Dalins is ranked  globally. Janis Dalins completed the marathon in 4:57:20 seconds. The Italy athlete named Ugo Frigerio is ranked  globally. Ugo Frigerio completed the marathon in 4:59:06 seconds. The Germany athlete named Karl Hahnel is ranked 4 globally. Karl Hahnel completed the marathon in 5:06:06 seconds. The Italy athlete named Ettore Rivolta is ranked 5 globally. Ettore Rivolta completed the marathon in 5:07:39 seconds. The Germany athlete named Paul Sievert is ranked 6 globally. Paul Sievert completed the marathon in 5:16:41 seconds. The France athlete named Henri Quintric is ranked 7 globally. Henri Quintric completed the marathon in 5:27:25 seconds. The United States athlete named Ernie Crosbie is ranked 8 globally. Ernie Crosbie completed the marathon in 5:28:02 seconds. The United States athlete named Bill Chisholm is ranked 9 globally. Bill Chisholm completed the marathon in 5:51:00 seconds. The Estonia athlete named Alfred Maasik is ranked 10 globally. Alfred Maasik completed the marathon in 6:19:00 seconds. The Canada athlete named Henry Cieman is ranked  globally. Henry Cieman completed the marathon in  seconds. The Greece athlete named John Moralis is ranked  globally. John Moralis completed the marathon in  seconds. The Italy athlete named Francesco Pretti is ranked  globally. Francesco Pretti completed the marathon in  seconds. The Switzerland athlete named Arthur Tell Schwab is ranked  globally. Arthur Tell Schwab completed the marathon in  seconds. The United States athlete named Harry Hinkel is ranked  globally. Harry Hinkel completed the marathon in  seconds.", "explanation": "The output correctly captures the data in table and generates a long text passage which covers all the given information."}, {"input": "Table: ['Year', 'Miss Northern Ireland', 'Hometown', 'Placement at Miss World', 'Notes']. ['2011', 'Finola Guinnane', 'Drumbo', 'Non-Finalist', 'Top 20 of Beach Beauty and Top 77 of Beauty with a Purpose at Miss World 2011']. ['2012', 'Tiffany Brien', 'Belfast', 'Top 30', 'Top 10 of Beach Fashion and 1st runner-up of Sports & Fitness at Miss World 2012']. ['2010', 'Lori Moore', 'Belfast', 'Top 25', 'Winner of Sports at Miss World 2010']. ['2009', 'Cherie Gardiner', 'Bangor', 'Non-Finalist', '']. ['2008', 'Judith Wilson', 'Enniskillen', 'Non-Finalist', 'Top 19 of Talent at Miss World 2008']. ['2007', 'Melissa Patton', 'Belfast', 'Non-Finalist', '']. ['2006', 'Catherine Jean Milligan', 'Newtownards', 'Top 17', 'Winner of Miss Talent at Miss World 2006']. ['2005', 'Lucy Evangelista', 'Portglenone', 'Top 15', 'Later Miss United Kingdom 2005 and Miss Universe United Kingdom 2005 2nd runner-up']. ['2004', 'Kirsty Anne Gabriel Stewart', 'Enniskillen', 'Non-Finalist', '']. ['2003', 'Diana Sayers', 'Belfast', 'Non-Finalist', '']. ['2002', 'Gayle Williamson', 'Lurgan', 'Non-Finalist', 'Later Miss United Kingdom 2002']. ['2001', 'Angela McCarthy', 'Belfast', 'Non-Finalist', '']. ['2000', 'Julie Lee-Ann Martin', 'Belfast', 'Non-Finalist', '']", "output": "Passage:  Tiffany Brien from Belfast was Miss Northern Ireland in the year 2012. Tiffany Brien was placed as a Top 30 at Miss World. Tiffany Brien was Top 10 of Beach Fashion and 1st runner-up of Sports & Fitness at Miss World 2012. Finola Guinnane from Drumbo was Miss Northern Ireland in the year 2011. Finola Guinnane was placed as a Non-Finalist at Miss World. Finola Guinnane was Top 20 of Beach Beauty and Top 77 of Beauty with a Purpose at Miss World 2011. Lori Moore from Belfast was Miss Northern Ireland in the year 2010. Lori Moore was placed as a Top 25 at Miss World. Lori Moore was Winner of Sports at Miss World 2010. Cherie Gardiner from Bangor was Miss Northern Ireland in the year 2009. Cherie Gardiner was placed as a Non-Finalist at Miss World. Cherie Gardiner was . Judith Wilson from Enniskillen was Miss Northern Ireland in the year 2008. Judith Wilson was placed as a Non-Finalist at Miss World. Judith Wilson was Top 19 of Talent at Miss World 2008. Melissa Patton from Belfast was Miss Northern Ireland in the year 2007. Melissa Patton was placed as a Non-Finalist at Miss World. Melissa Patton was . Catherine Jean Milligan from Newtownards was Miss Northern Ireland in the year 2006. Catherine Jean Milligan was placed as a Top 17 at Miss World. Catherine Jean Milligan was Winner of Miss Talent at Miss World 2006. Lucy Evangelista from Portglenone was Miss Northern Ireland in the year 2005. Lucy Evangelista was placed as a Top 15 at Miss World. Lucy Evangelista was Later Miss United Kingdom 2005 and Miss Universe United Kingdom 2005 2nd runner-up. Kirsty Anne Gabriel Stewart from Enniskillen was Miss Northern Ireland in the year 2004. Kirsty Anne Gabriel Stewart was placed as a Non-Finalist at Miss World. Kirsty Anne Gabriel Stewart was . Diana Sayers from Belfast was Miss Northern Ireland in the year 2003. Diana Sayers was placed as a Non-Finalist at Miss World. Diana Sayers was . Gayle Williamson from Lurgan was Miss Northern Ireland in the year 2002. Gayle Williamson was placed as a Non-Finalist at Miss World. Gayle Williamson was Later Miss United Kingdom 2002. Angela McCarthy from Belfast was Miss Northern Ireland in the year 2001. Angela McCarthy was placed as a Non-Finalist at Miss World. Angela McCarthy was . Julie Lee-Ann Martin from Belfast was Miss Northern Ireland in the year 2000. Julie Lee-Ann Martin was placed as a Non-Finalist at Miss World. Julie Lee-Ann Martin was.", "explanation": "The output correctly captures the data in table and generates a long text passage which covers all the given information."}], "Negative Examples": [{"input": "Table: ['Year','Title','Peak chart positions US Air','Peak chart positions US Main','Peak chart positions US Mod',Album]. ['1990', 'Dig a Hole', '--', '--', '--', 'Non-album single']. ['1993', 'Mister Love', '--', '--', '--', 'Velvet']. ['1994', 'Mister Love', '--', '--', '--', 'Rubberneck']. ['1995', 'Possum Kingdom', '40', '9', '4', 'Rubberneck']. ['1995', 'Away', '--', '23', '28', 'Rubberneck']. ['1996', 'Tyler', '--', '--', '--', 'Rubberneck']. ['1996', 'Backslider', '--', '--', '--', 'Rubberneck']. ['2001', 'Push the Hand', '--', '34', '--', 'Hell Below/Stars Above']. ['2008', 'No Deliverance', '--', '38', '--', 'No Deliverance']. ['2009', 'Song I Hate', '--', '--', '--', 'No Deliverance']. ['2012', 'Summer of the Strange', '--', '--', '--', 'Play.Rock.Music']", "output": "Passage: Dig a Hole's chart positions in US Air, US Main, and US mod were --, --, and -- respectively. The title track 'Mister Love' from the album 'Velvet', was released in the year 1993. Mister Love's chart positions in US Air, US Main, and US mod were --, --, and -- respectively. The title track 'Mister Love' from the album 'Rubberneck', was released in the year 1994. Mister Love's chart positions in US Air, US Main, and US mod were --, --, and -- respectively. The title track 'Possum Kingdom' from the album 'Rubberneck', was released in the year 1995. Possum Kingdom's chart positions in US Air, US Main, and US mod were 40, 9, and 4 respectively. The title track 'Away' from the album 'Rubberneck', was released in the year 1995. Away's chart positions in US Air, US Main, and US mod were --, 23, and 28 respectively. The title track 'Tyler' from the album 'Rubberneck', was released in the year 1996. Tyler's chart positions in US Air, US Main, and US mod were --, --, and -- respectively. The title track 'Backslider' from the album 'Rubberneck', was released in the year 1996. Backslider's chart positions in US Air, US Main, and US mod were --, --, and -- respectively. The title track 'Push the Hand' from the album 'Hell Below/Stars Above', was released in the year 2001. Push the Hand's chart positions in US Air, US Main, and US mod were --, 34, and -- respectively. The title track 'No Deliverance' from the album 'No Deliverance', was released in the year 2008. No Deliverance's chart positions in US Air, US Main, and US mod were --, 38, and -- respectively. The title track 'Song I Hate' from the album 'No Deliverance', was released in the year 2009. Song I Hate's chart positions in US Air, US Main, and US mod were --, --, and -- respectively. The title track 'Summer of the Strange' from the album 'Play.Rock.Music', was released in the year 2012. Summer of the Strange's chart positions in US Air, US Main, and US mod were --, --, and -- respectively.", "explanation": "This is a bad example of 'long text passage generation task' because it fails to format/clean the missing/None/empty data values in the long text generation"}, {"input": "Table: ['Year','Title','Peak chart positions US Air','Peak chart positions US Main','Peak chart positions US Mod',Album]. ['1990', 'Dig a Hole', '--', '--', '--', 'Non-album single']. ['1993', 'Mister Love', '--', '--', '--', 'Velvet']. ['1994', 'Mister Love', '--', '--', '--', 'Rubberneck']. ['1995', 'Possum Kingdom', '40', '9', '4', 'Rubberneck']. ['1995', 'Away', '--', '23', '28', 'Rubberneck']. ['1996', 'Tyler', '--', '--', '--', 'Rubberneck']. ['1996', 'Backslider', '--', '--', '--', 'Rubberneck']. ['2001', 'Push the Hand', '--', '34', '--', 'Hell Below/Stars Above']. ['2008', 'No Deliverance', '--', '38', '--', 'No Deliverance']. ['2009', 'Song I Hate', '--', '--', '--', 'No Deliverance']. ['2012', 'Summer of the Strange', '--', '--', '--', 'Play.Rock.Music']", "output": "Passage: The title track 'Dig a Hole' from the album 'Non-album single', was released in the year 1990. Dig a Hole's chart positions in US Air, US Main,  and US mod were --, --, and -- respectively. The title track 'Mister Love' from the album 'Velvet', was released in the year 1993. Mister Love's chart positions in US Air, US Main, and US mod were --, --, and -- respectively. The title track 'Mister Love' from the album 'Rubberneck', was released in the year 1994. Mister Love's chart positions in US Air, US Main, and US mod were --, --, and -- respectively. The title track 'Possum Kingdom' from the album 'Rubberneck', was released in the year 1995. Possum Kingdom's chart positions in US Air, US Main, and US mod were 40, 9, and 4 respectively. The title track 'Away' from the album 'Rubberneck', was released in the year 1995. Away's chart positions in US Air, US Main, and US mod were --, 23, and 28 respectively. The title track 'Tyler' from the album 'Rubberneck', was released in the year 1996. Tyler's chart positions in US Air, US Main, and US mod were --, --, and -- respectively. The title track 'Backslider' from the album 'Rubberneck', was released in the year 1996. Backslider's chart positions in US Air, US Main, and US mod were --, --, and -- respectively. The title track 'Push the Hand' from the album 'Hell Below/Stars Above', was released in the year 2001. Push the Hand's chart positions in US Air, US Main, and US mod were --, 34, and -- respectively. The title track 'No Deliverance' from the album 'No Deliverance', was released in the year 2008. No Deliverance's chart positions in US Air, US Main, and US mod were --, 38, and -- respectively. The title track 'Song I Hate' from the album 'No Deliverance', was released in the year 2009. Song I Hate's chart positions in US Air, US Main, and US mod were --, --, and -- respectively. The title track 'Summer of the Strange' from the album 'Play.Rock.Music', was released in the year 2012. Summer of the Strange's chart positions in US Air, US Main, and US mod were --, --, and -- respectively.", "explanation": "This is a bad example of 'long text passage generation task' because it fails to format/clean the missing/None/empty data values in the long text generation"}, {"input": "Table: ['Year','Title','Peak chart positions US Air','Peak chart positions US Main','Peak chart positions US Mod',Album]. ['1993', 'Mister Love', '--', '--', '--', 'Velvet']. ['1990', 'Dig a Hole', '--', '--', '--', 'Non-album single']. ['1994', 'Mister Love', '--', '--', '--', 'Rubberneck']. ['1995', 'Possum Kingdom', '40', '9', '4', 'Rubberneck']. ['1995', 'Away', '--', '23', '28', 'Rubberneck']. ['1996', 'Tyler', '--', '--', '--', 'Rubberneck']. ['1996', 'Backslider', '--', '--', '--', 'Rubberneck']. ['2001', 'Push the Hand', '--', '34', '--', 'Hell Below/Stars Above']. ['2008', 'No Deliverance', '--', '38', '--', 'No Deliverance']. ['2009', 'Song I Hate', '--', '--', '--', 'No Deliverance']. ['2012', 'Summer of the Strange', '--', '--', '--', 'Play.Rock.Music']", "output": "Passage: Mister Love's chart positions in US Air, US Main, and US mod were --, --, and -- respectively. The title track 'Mister Love' from the album 'Rubberneck', was released in the year 1994. Mister Love's chart positions in US Air, US Main, and US mod were --, --, and -- respectively. The title track 'Possum Kingdom' from the album 'Rubberneck', was released in the year 1995. Possum Kingdom's chart positions in US Air, US Main, and US mod were 40, 9, and 4 respectively. The title track 'Away' from the album 'Rubberneck', was released in the year 1995. Away's chart positions in US Air, US Main, and US mod were --, 23, and 28 respectively. The title track 'Tyler' from the album 'Rubberneck', was released in the year 1996. Tyler's chart positions in US Air, US Main, and US mod were --, --, and -- respectively. The title track 'Backslider' from the album 'Rubberneck', was released in the year 1996. Backslider's chart positions in US Air, US Main, and US mod were --, --, and -- respectively. The title track 'Push the Hand' from the album 'Hell Below/Stars Above', was released in the year 2001. Push the Hand's chart positions in US Air, US Main, and US mod were --, 34, and -- respectively. The title track 'No Deliverance' from the album 'No Deliverance', was released in the year 2008. No Deliverance's chart positions in US Air, US Main, and US mod were --, 38, and -- respectively. The title track 'Song I Hate' from the album 'No Deliverance', was released in the year 2009. Song I Hate's chart positions in US Air, US Main, and US mod were --, --, and -- respectively. The title track 'Summer of the Strange' from the album 'Play.Rock.Music', was released in the year 2012. Summer of the Strange's chart positions in US Air, US Main, and US mod were --, --, and -- respectively.", "explanation": "This is a bad example of 'long text passage generation task' because it fails to format/clean the missing/None/empty data values in the long text generation"}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Sports", "Statistics", "News"], "Instance": {"id": "task760-d655a07ec6044870b340c63bf2b51f84", "input": "Table: ['Draw', 'Country', 'Language', 'Artist', 'Song', 'English translation', 'National final', 'Place', 'Points']. ['01', 'Malta', 'English', 'Claudia Faniello', 'Caravaggio', '-', '2nd', '13', '53']. ['02', 'Israel', 'Hebrew', \"Bo'az Ma'uda & Oshrat Papin\", 'Parparim', 'Butterflies', '3rd', '8', '90']. ['03', 'Russia', 'English', 'Sergey Lazarev', 'Flyer', '-', '4th', '7', '119']. ['04', 'Estonia', 'English', 'Rolf Junior', 'One on One', '-', '4th', '21', '0']. ['05', 'Belgium', 'English', 'Sandrine', 'I Feel The Same Way', '-', '2nd', '10', '64']. ['06', 'Macedonia', 'Macedonian', 'Risto Samardziev', 'Dojdi do mene', 'Come to me', '3rd', '19', '7']. ['07', 'Poland', 'English', 'Man Meadow', 'Viva la Musica', 'Hail to the music', '3rd', '3', '155']. ['08', 'Finland', 'Finnish', 'Mikael Konttinen', 'Milloin', 'When', 'Unplaced', '14', '46']. ['09', 'Germany', 'German', 'Carolin Fortenbacher', 'Hinterm Ozean', 'Beyond the ocean', '2nd', '6', '129']. ['10', 'Denmark', 'English', 'Kendra Lou', \"Until We're Satisfied\", '-', '4th', '18', '21']. ['11', 'Greece', 'English', 'Kostas Martakis', 'Always and Forever', '-', '2nd', '4', '140']. ['12', 'Serbia', 'Serbian', 'Beauty Queens', 'Zavet', 'A pledge', '3rd', '9', '68']. ['13', 'Croatia', 'Croatian', 'Emilija Kokic', 'Andjeo', 'Angel', '6th', '15', '31']. ['14', 'Lithuania', 'English', 'Aiste Pilvelyte', 'Troy on Fire', '-', '2nd', '17', '26']. ['15', 'Ireland', 'English', 'Leona Daly', 'Not Crazy After All', '-', 'Unplaced', '12', '56']. ['16', 'United Kingdom', 'English', 'The Revelations', \"It's You\", '-', '3rd', '16', '29']. ['17', 'Portugal', 'Portuguese', 'Lisboa Nao Sejas Francesa', 'Porto de encontro', 'Meeting harbour', '9th', '20', '6']. ['18', 'Sweden', 'English', 'Sanna Nielsen', 'Empty Room', '-', '2nd', '1', '269']. ['19', 'Norway', 'English', 'Veronica Akselsen', 'Am I Supposed To Love Again', '-', '4th', '5', '139']. ['20', 'Slovenia', 'Slovene', 'Brigita Suler', 'Samara', '-', '3rd', '11', '57']. ['21', 'Spain', 'Spanish', 'Coral', 'Todo esta en tu mente', 'Everything is in your mind', '2nd', '2', '178']", "output": ["Passage:  The song Caravaggio by the artist Claudia Faniello finished at 2nd position in the national finals, and at 13th position in the international finals by earning total 53 points.  The song Caravaggio is in the language English from the country Malta. The English translation of the song is -. The song Parparim by the artist Bo'az Ma'uda & Oshrat Papin finished at 3rd position in the national finals, and at 8th position in the international finals by earning total 90 points.  The song Parparim is in the language Hebrew from the country Israel. The English translation of the song is Butterflies. The song Flyer by the artist Sergey Lazarev finished at 4th position in the national finals, and at 7th position in the international finals by earning total 119 points.  The song Flyer is in the language English from the country Russia. The English translation of the song is -. The song One on One by the artist Rolf Junior finished at 4th position in the national finals, and at 21th position in the international finals by earning total 0 points.  The song One on One is in the language English from the country Estonia. The English translation of the song is -. The song I Feel The Same Way by the artist Sandrine finished at 2nd position in the national finals, and at 10th position in the international finals by earning total 64 points.  The song I Feel The Same Way is in the language English from the country Belgium. The English translation of the song is -. The song Dojdi do mene by the artist Risto Samardziev finished at 3rd position in the national finals, and at 19th position in the international finals by earning total 7 points.  The song Dojdi do mene is in the language Macedonian from the country Macedonia. The English translation of the song is Come to me. The song Viva la Musica by the artist Man Meadow finished at 3rd position in the national finals, and at 3th position in the international finals by earning total 155 points.  The song Viva la Musica is in the language English from the country Poland. The English translation of the song is Hail to the music. The song Milloin by the artist Mikael Konttinen finished at Unplaced position in the national finals, and at 14th position in the international finals by earning total 46 points.  The song Milloin is in the language Finnish from the country Finland. The English translation of the song is When. The song Hinterm Ozean by the artist Carolin Fortenbacher finished at 2nd position in the national finals, and at 6th position in the international finals by earning total 129 points.  The song Hinterm Ozean is in the language German from the country Germany. The English translation of the song is Beyond the ocean. The song Until We're Satisfied by the artist Kendra Lou finished at 4th position in the national finals, and at 18th position in the international finals by earning total 21 points.  The song Until We're Satisfied is in the language English from the country Denmark. The English translation of the song is -. The song Always and Forever by the artist Kostas Martakis finished at 2nd position in the national finals, and at 4th position in the international finals by earning total 140 points.  The song Always and Forever is in the language English from the country Greece. The English translation of the song is -. The song Zavet by the artist Beauty Queens finished at 3rd position in the national finals, and at 9th position in the international finals by earning total 68 points.  The song Zavet is in the language Serbian from the country Serbia. The English translation of the song is A pledge. The song Andjeo by the artist Emilija Kokic finished at 6th position in the national finals, and at 15th position in the international finals by earning total 31 points.  The song Andjeo is in the language Croatian from the country Croatia. The English translation of the song is Angel. The song Troy on Fire by the artist Aiste Pilvelyte finished at 2nd position in the national finals, and at 17th position in the international finals by earning total 26 points.  The song Troy on Fire is in the language English from the country Lithuania. The English translation of the song is -. The song Not Crazy After All by the artist Leona Daly finished at Unplaced position in the national finals, and at 12th position in the international finals by earning total 56 points.  The song Not Crazy After All is in the language English from the country Ireland. The English translation of the song is -. The song It's You by the artist The Revelations finished at 3rd position in the national finals, and at 16th position in the international finals by earning total 29 points.  The song It's You is in the language English from the country United Kingdom. The English translation of the song is -. The song Porto de encontro by the artist Lisboa Nao Sejas Francesa finished at 9th position in the national finals, and at 20th position in the international finals by earning total 6 points.  The song Porto de encontro is in the language Portuguese from the country Portugal. The English translation of the song is Meeting harbour. The song Empty Room by the artist Sanna Nielsen finished at 2nd position in the national finals, and at 1th position in the international finals by earning total 269 points.  The song Empty Room is in the language English from the country Sweden. The English translation of the song is -. The song Am I Supposed To Love Again by the artist Veronica Akselsen finished at 4th position in the national finals, and at 5th position in the international finals by earning total 139 points.  The song Am I Supposed To Love Again is in the language English from the country Norway. The English translation of the song is -. The song Samara by the artist Brigita Suler finished at 3rd position in the national finals, and at 11th position in the international finals by earning total 57 points.  The song Samara is in the language Slovene from the country Slovenia. The English translation of the song is -. The song Todo esta en tu mente by the artist Coral finished at 2nd position in the national finals, and at 2th position in the international finals by earning total 178 points.  The song Todo esta en tu mente is in the language Spanish from the country Spain. The English translation of the song is Everything is in your mind."]}, "Instance License": ["Microsoft Research Data License Agreement (https://msropendata-web-api.azurewebsites.net/licenses/2f933be3-284d-500b-7ea3-2aa2fd0f1bb2/view)"], "prediction": "-"}
+{"id": "task760-db1f9d517b0d41f3a1369262856bb1f5", "Task": "task760_msr_sqa_long_text_generation", "Contributors": "['Shreya Sarnaik sjsarnai@asu.edu']", "Source": ["msr_sqa"], "URL": ["https://huggingface.co/datasets/msr_sqa"], "Categories": ["Data to Text"], "Reasoning": ["Multihop Reasoning"], "Definition": ["You are given data in tabular format and you need to generate a passage with content in plain text format based on the information present in the table."], "Positive Examples": [{"input": "Table: ['Pick', 'Player', 'Team', 'Position', 'School']. ['1', 'Ben McDonald', 'Baltimore Orioles', 'RHP', 'Louisiana State University']. ['2', 'Tyler Houston', 'Atlanta Braves', 'C', 'Valley HS (Las Vegas, NV)']. ['3', 'Roger Salkeld', 'Seattle Mariners', 'RHP', 'Saugus (CA) HS']. ['4', 'Jeff Jackson', 'Philadelphia Phillies', 'OF', 'Simeon HS (Chicago, IL)']. ['5', 'Donald Harris', 'Texas Rangers', 'OF', 'Texas Tech University']. ['6', 'Paul Coleman', 'Saint Louis Cardinals', 'OF', 'Frankston (TX) HS']. ['7', 'Frank Thomas', 'Chicago White Sox', '1B', 'Auburn University']. ['8', 'Earl Cunningham', 'Chicago Cubs', 'OF', 'Lancaster (SC) HS']. ['9', 'Kyle Abbott', 'California Angels', 'LHP', 'Long Beach State University']. ['10', 'Charles Johnson', 'Montreal Expos', 'C', 'Westwood HS (Fort Pierce, FL)']. ['11', 'Calvin Murray', 'Cleveland Indians', '3B', 'W.T. White High School (Dallas, TX)']. ['12', 'Jeff Juden', 'Houston Astros', 'RHP', 'Salem (MA) HS']. ['13', 'Brent Mayne', 'Kansas City Royals', 'C', 'Cal State Fullerton']. ['14', 'Steve Hosey', 'San Francisco Giants', 'OF', 'Fresno State University']. ['15', 'Kiki Jones', 'Los Angeles Dodgers', 'RHP', 'Hillsborough HS (Tampa, FL)']. ['16', 'Greg Blosser', 'Boston Red Sox', 'OF', 'Sarasota (FL) HS']. ['17', 'Cal Eldred', 'Milwaukee Brewers', 'RHP', 'University of Iowa']. ['18', 'Willie Greene', 'Pittsburgh Pirates', 'SS', 'Jones County HS (Gray, GA)']. ['19', 'Eddie Zosky', 'Toronto Blue Jays', 'SS', 'Fresno State University']. ['20', 'Scott Bryant', 'Cincinnati Reds', 'OF', 'University of Texas']. ['21', 'Greg Gohr', 'Detroit Tigers', 'RHP', 'Santa Clara University']. ['22', 'Tom Goodwin', 'Los Angeles Dodgers', 'OF', 'Fresno State University']. ['23', 'Mo Vaughn', 'Boston Red Sox', '1B', 'Seton Hall University']. ['24', 'Alan Zinter', 'New York Mets', 'C', 'University of Arizona']. ['25', 'Chuck Knoblauch', 'Minnesota Twins', '2B', 'Texas A&M University']. ['26', 'Scott Burrell', 'Seattle Mariners', 'RHP', 'Hamden (CT) HS']", "output": "Passage: The player named Ben McDonald, plays as Pick-1.Ben McDonald plays for the team Baltimore Orioles, at position RHP. Ben McDonald belongs to the school Louisiana State University. The player named Tyler Houston, plays as Pick-2.Tyler Houston plays for the team Atlanta Braves, at position C. Tyler Houston belongs to the school Valley HS (Las Vegas, NV). The player named Roger Salkeld, plays as Pick-3.Roger Salkeld plays for the team Seattle Mariners, at position RHP. Roger Salkeld belongs to the school Saugus (CA) HS. The player named Jeff Jackson, plays as Pick-4.Jeff Jackson plays for the team Philadelphia Phillies, at position OF. Jeff Jackson belongs to the school Simeon HS (Chicago, IL). The player named Donald Harris, plays as Pick-5.Donald Harris plays for the team Texas Rangers, at position OF. Donald Harris belongs to the school Texas Tech University. The player named Paul Coleman, plays as Pick-6.Paul Coleman plays for the team Saint Louis Cardinals, at position OF. Paul Coleman belongs to the school Frankston (TX) HS. The player named Frank Thomas, plays as Pick-7.Frank Thomas plays for the team Chicago White Sox, at position 1B. Frank Thomas belongs to the school Auburn University. The player named Earl Cunningham, plays as Pick-8.Earl Cunningham plays for the team Chicago Cubs, at position OF. Earl Cunningham belongs to the school Lancaster (SC) HS. The player named Kyle Abbott, plays as Pick-9.Kyle Abbott plays for the team California Angels, at position LHP. Kyle Abbott belongs to the school Long Beach State University. The player named Charles Johnson, plays as Pick-10.Charles Johnson plays for the team Montreal Expos, at position C. Charles Johnson belongs to the school Westwood HS (Fort Pierce, FL). The player named Calvin Murray, plays as Pick-11.Calvin Murray plays for the team Cleveland Indians, at position 3B. Calvin Murray belongs to the school W.T. White High School (Dallas, TX). The player named Jeff Juden, plays as Pick-12.Jeff Juden plays for the team Houston Astros, at position RHP. Jeff Juden belongs to the school Salem (MA) HS. The player named Brent Mayne, plays as Pick-13.Brent Mayne plays for the team Kansas City Royals, at position C. Brent Mayne belongs to the school Cal State Fullerton. The player named Steve Hosey, plays as Pick-14.Steve Hosey plays for the team San Francisco Giants, at position OF. Steve Hosey belongs to the school Fresno State University. The player named Kiki Jones, plays as Pick-15.Kiki Jones plays for the team Los Angeles Dodgers, at position RHP. Kiki Jones belongs to the school Hillsborough HS (Tampa, FL). The player named Greg Blosser, plays as Pick-16.Greg Blosser plays for the team Boston Red Sox, at position OF. Greg Blosser belongs to the school Sarasota (FL) HS. The player named Cal Eldred, plays as Pick-17.Cal Eldred plays for the team Milwaukee Brewers, at position RHP. Cal Eldred belongs to the school University of Iowa. The player named Willie Greene, plays as Pick-18.Willie Greene plays for the team Pittsburgh Pirates, at position SS. Willie Greene belongs to the school Jones County HS (Gray, GA). The player named Eddie Zosky, plays as Pick-19.Eddie Zosky plays for the team Toronto Blue Jays, at position SS. Eddie Zosky belongs to the school Fresno State University. The player named Scott Bryant, plays as Pick-20.Scott Bryant plays for the team Cincinnati Reds, at position OF. Scott Bryant belongs to the school University of Texas. The player named Greg Gohr, plays as Pick-21.Greg Gohr plays for the team Detroit Tigers, at position RHP. Greg Gohr belongs to the school Santa Clara University. The player named Tom Goodwin, plays as Pick-22.Tom Goodwin plays for the team Los Angeles Dodgers, at position OF. Tom Goodwin belongs to the school Fresno State University. The player named Mo Vaughn, plays as Pick-23.Mo Vaughn plays for the team Boston Red Sox, at position 1B. Mo Vaughn belongs to the school Seton Hall University. The player named Alan Zinter, plays as Pick-24.Alan Zinter plays for the team New York Mets, at position C. Alan Zinter belongs to the school University of Arizona. The player named Chuck Knoblauch, plays as Pick-25.Chuck Knoblauch plays for the team Minnesota Twins, at position 2B. Chuck Knoblauch belongs to the school Texas A&M University. The player named Scott Burrell, plays as Pick-26.Scott Burrell plays for the team Seattle Mariners, at position RHP. Scott Burrell belongs to the school Hamden (CT) HS.", "explanation": "The output correctly captures the data in table and generates a long text passage which covers all the given information."}, {"input": "Table: ['Rank','Name', 'Nationality', 'Time (hand)', 'Notes']. ['','Tommy Green', 'Great Britain', '4:50:10', 'OR']. ['', 'Janis Dalins', 'Latvia', '4:57:20', '']. ['', 'Ugo Frigerio', 'Italy', '4:59:06', '']. ['4', 'Karl Hahnel', 'Germany', '5:06:06', '']. ['5', 'Ettore Rivolta', 'Italy', '5:07:39', '']. ['6', 'Paul Sievert', 'Germany', '5:16:41', '']. ['7', 'Henri Quintric', 'France', '5:27:25', '']. ['8', 'Ernie Crosbie', 'United States', '5:28:02', '']. ['9', 'Bill Chisholm', 'United States', '5:51:00', '']. ['10', 'Alfred Maasik', 'Estonia', '6:19:00', '']. ['', 'Henry Cieman', 'Canada', '', 'DNF']. ['', 'John Moralis', 'Greece', '', 'DNF']. ['', 'Francesco Pretti', 'Italy', '', 'DNF']. ['', 'Arthur Tell Schwab', 'Switzerland', '', 'DNF']. ['', 'Harry Hinkel', 'United States', '', 'DNF']", "output": "Passage:  The Great Britain athlete named Tommy Green is ranked  globally. Tommy Green completed the marathon in 4:50:10 seconds. The Latvia athlete named Janis Dalins is ranked  globally. Janis Dalins completed the marathon in 4:57:20 seconds. The Italy athlete named Ugo Frigerio is ranked  globally. Ugo Frigerio completed the marathon in 4:59:06 seconds. The Germany athlete named Karl Hahnel is ranked 4 globally. Karl Hahnel completed the marathon in 5:06:06 seconds. The Italy athlete named Ettore Rivolta is ranked 5 globally. Ettore Rivolta completed the marathon in 5:07:39 seconds. The Germany athlete named Paul Sievert is ranked 6 globally. Paul Sievert completed the marathon in 5:16:41 seconds. The France athlete named Henri Quintric is ranked 7 globally. Henri Quintric completed the marathon in 5:27:25 seconds. The United States athlete named Ernie Crosbie is ranked 8 globally. Ernie Crosbie completed the marathon in 5:28:02 seconds. The United States athlete named Bill Chisholm is ranked 9 globally. Bill Chisholm completed the marathon in 5:51:00 seconds. The Estonia athlete named Alfred Maasik is ranked 10 globally. Alfred Maasik completed the marathon in 6:19:00 seconds. The Canada athlete named Henry Cieman is ranked  globally. Henry Cieman completed the marathon in  seconds. The Greece athlete named John Moralis is ranked  globally. John Moralis completed the marathon in  seconds. The Italy athlete named Francesco Pretti is ranked  globally. Francesco Pretti completed the marathon in  seconds. The Switzerland athlete named Arthur Tell Schwab is ranked  globally. Arthur Tell Schwab completed the marathon in  seconds. The United States athlete named Harry Hinkel is ranked  globally. Harry Hinkel completed the marathon in  seconds.", "explanation": "The output correctly captures the data in table and generates a long text passage which covers all the given information."}, {"input": "Table: ['Year', 'Miss Northern Ireland', 'Hometown', 'Placement at Miss World', 'Notes']. ['2011', 'Finola Guinnane', 'Drumbo', 'Non-Finalist', 'Top 20 of Beach Beauty and Top 77 of Beauty with a Purpose at Miss World 2011']. ['2012', 'Tiffany Brien', 'Belfast', 'Top 30', 'Top 10 of Beach Fashion and 1st runner-up of Sports & Fitness at Miss World 2012']. ['2010', 'Lori Moore', 'Belfast', 'Top 25', 'Winner of Sports at Miss World 2010']. ['2009', 'Cherie Gardiner', 'Bangor', 'Non-Finalist', '']. ['2008', 'Judith Wilson', 'Enniskillen', 'Non-Finalist', 'Top 19 of Talent at Miss World 2008']. ['2007', 'Melissa Patton', 'Belfast', 'Non-Finalist', '']. ['2006', 'Catherine Jean Milligan', 'Newtownards', 'Top 17', 'Winner of Miss Talent at Miss World 2006']. ['2005', 'Lucy Evangelista', 'Portglenone', 'Top 15', 'Later Miss United Kingdom 2005 and Miss Universe United Kingdom 2005 2nd runner-up']. ['2004', 'Kirsty Anne Gabriel Stewart', 'Enniskillen', 'Non-Finalist', '']. ['2003', 'Diana Sayers', 'Belfast', 'Non-Finalist', '']. ['2002', 'Gayle Williamson', 'Lurgan', 'Non-Finalist', 'Later Miss United Kingdom 2002']. ['2001', 'Angela McCarthy', 'Belfast', 'Non-Finalist', '']. ['2000', 'Julie Lee-Ann Martin', 'Belfast', 'Non-Finalist', '']", "output": "Passage:  Tiffany Brien from Belfast was Miss Northern Ireland in the year 2012. Tiffany Brien was placed as a Top 30 at Miss World. Tiffany Brien was Top 10 of Beach Fashion and 1st runner-up of Sports & Fitness at Miss World 2012. Finola Guinnane from Drumbo was Miss Northern Ireland in the year 2011. Finola Guinnane was placed as a Non-Finalist at Miss World. Finola Guinnane was Top 20 of Beach Beauty and Top 77 of Beauty with a Purpose at Miss World 2011. Lori Moore from Belfast was Miss Northern Ireland in the year 2010. Lori Moore was placed as a Top 25 at Miss World. Lori Moore was Winner of Sports at Miss World 2010. Cherie Gardiner from Bangor was Miss Northern Ireland in the year 2009. Cherie Gardiner was placed as a Non-Finalist at Miss World. Cherie Gardiner was . Judith Wilson from Enniskillen was Miss Northern Ireland in the year 2008. Judith Wilson was placed as a Non-Finalist at Miss World. Judith Wilson was Top 19 of Talent at Miss World 2008. Melissa Patton from Belfast was Miss Northern Ireland in the year 2007. Melissa Patton was placed as a Non-Finalist at Miss World. Melissa Patton was . Catherine Jean Milligan from Newtownards was Miss Northern Ireland in the year 2006. Catherine Jean Milligan was placed as a Top 17 at Miss World. Catherine Jean Milligan was Winner of Miss Talent at Miss World 2006. Lucy Evangelista from Portglenone was Miss Northern Ireland in the year 2005. Lucy Evangelista was placed as a Top 15 at Miss World. Lucy Evangelista was Later Miss United Kingdom 2005 and Miss Universe United Kingdom 2005 2nd runner-up. Kirsty Anne Gabriel Stewart from Enniskillen was Miss Northern Ireland in the year 2004. Kirsty Anne Gabriel Stewart was placed as a Non-Finalist at Miss World. Kirsty Anne Gabriel Stewart was . Diana Sayers from Belfast was Miss Northern Ireland in the year 2003. Diana Sayers was placed as a Non-Finalist at Miss World. Diana Sayers was . Gayle Williamson from Lurgan was Miss Northern Ireland in the year 2002. Gayle Williamson was placed as a Non-Finalist at Miss World. Gayle Williamson was Later Miss United Kingdom 2002. Angela McCarthy from Belfast was Miss Northern Ireland in the year 2001. Angela McCarthy was placed as a Non-Finalist at Miss World. Angela McCarthy was . Julie Lee-Ann Martin from Belfast was Miss Northern Ireland in the year 2000. Julie Lee-Ann Martin was placed as a Non-Finalist at Miss World. Julie Lee-Ann Martin was.", "explanation": "The output correctly captures the data in table and generates a long text passage which covers all the given information."}], "Negative Examples": [{"input": "Table: ['Year','Title','Peak chart positions US Air','Peak chart positions US Main','Peak chart positions US Mod',Album]. ['1990', 'Dig a Hole', '--', '--', '--', 'Non-album single']. ['1993', 'Mister Love', '--', '--', '--', 'Velvet']. ['1994', 'Mister Love', '--', '--', '--', 'Rubberneck']. ['1995', 'Possum Kingdom', '40', '9', '4', 'Rubberneck']. ['1995', 'Away', '--', '23', '28', 'Rubberneck']. ['1996', 'Tyler', '--', '--', '--', 'Rubberneck']. ['1996', 'Backslider', '--', '--', '--', 'Rubberneck']. ['2001', 'Push the Hand', '--', '34', '--', 'Hell Below/Stars Above']. ['2008', 'No Deliverance', '--', '38', '--', 'No Deliverance']. ['2009', 'Song I Hate', '--', '--', '--', 'No Deliverance']. ['2012', 'Summer of the Strange', '--', '--', '--', 'Play.Rock.Music']", "output": "Passage: Dig a Hole's chart positions in US Air, US Main, and US mod were --, --, and -- respectively. The title track 'Mister Love' from the album 'Velvet', was released in the year 1993. Mister Love's chart positions in US Air, US Main, and US mod were --, --, and -- respectively. The title track 'Mister Love' from the album 'Rubberneck', was released in the year 1994. Mister Love's chart positions in US Air, US Main, and US mod were --, --, and -- respectively. The title track 'Possum Kingdom' from the album 'Rubberneck', was released in the year 1995. Possum Kingdom's chart positions in US Air, US Main, and US mod were 40, 9, and 4 respectively. The title track 'Away' from the album 'Rubberneck', was released in the year 1995. Away's chart positions in US Air, US Main, and US mod were --, 23, and 28 respectively. The title track 'Tyler' from the album 'Rubberneck', was released in the year 1996. Tyler's chart positions in US Air, US Main, and US mod were --, --, and -- respectively. The title track 'Backslider' from the album 'Rubberneck', was released in the year 1996. Backslider's chart positions in US Air, US Main, and US mod were --, --, and -- respectively. The title track 'Push the Hand' from the album 'Hell Below/Stars Above', was released in the year 2001. Push the Hand's chart positions in US Air, US Main, and US mod were --, 34, and -- respectively. The title track 'No Deliverance' from the album 'No Deliverance', was released in the year 2008. No Deliverance's chart positions in US Air, US Main, and US mod were --, 38, and -- respectively. The title track 'Song I Hate' from the album 'No Deliverance', was released in the year 2009. Song I Hate's chart positions in US Air, US Main, and US mod were --, --, and -- respectively. The title track 'Summer of the Strange' from the album 'Play.Rock.Music', was released in the year 2012. Summer of the Strange's chart positions in US Air, US Main, and US mod were --, --, and -- respectively.", "explanation": "This is a bad example of 'long text passage generation task' because it fails to format/clean the missing/None/empty data values in the long text generation"}, {"input": "Table: ['Year','Title','Peak chart positions US Air','Peak chart positions US Main','Peak chart positions US Mod',Album]. ['1990', 'Dig a Hole', '--', '--', '--', 'Non-album single']. ['1993', 'Mister Love', '--', '--', '--', 'Velvet']. ['1994', 'Mister Love', '--', '--', '--', 'Rubberneck']. ['1995', 'Possum Kingdom', '40', '9', '4', 'Rubberneck']. ['1995', 'Away', '--', '23', '28', 'Rubberneck']. ['1996', 'Tyler', '--', '--', '--', 'Rubberneck']. ['1996', 'Backslider', '--', '--', '--', 'Rubberneck']. ['2001', 'Push the Hand', '--', '34', '--', 'Hell Below/Stars Above']. ['2008', 'No Deliverance', '--', '38', '--', 'No Deliverance']. ['2009', 'Song I Hate', '--', '--', '--', 'No Deliverance']. ['2012', 'Summer of the Strange', '--', '--', '--', 'Play.Rock.Music']", "output": "Passage: The title track 'Dig a Hole' from the album 'Non-album single', was released in the year 1990. Dig a Hole's chart positions in US Air, US Main,  and US mod were --, --, and -- respectively. The title track 'Mister Love' from the album 'Velvet', was released in the year 1993. Mister Love's chart positions in US Air, US Main, and US mod were --, --, and -- respectively. The title track 'Mister Love' from the album 'Rubberneck', was released in the year 1994. Mister Love's chart positions in US Air, US Main, and US mod were --, --, and -- respectively. The title track 'Possum Kingdom' from the album 'Rubberneck', was released in the year 1995. Possum Kingdom's chart positions in US Air, US Main, and US mod were 40, 9, and 4 respectively. The title track 'Away' from the album 'Rubberneck', was released in the year 1995. Away's chart positions in US Air, US Main, and US mod were --, 23, and 28 respectively. The title track 'Tyler' from the album 'Rubberneck', was released in the year 1996. Tyler's chart positions in US Air, US Main, and US mod were --, --, and -- respectively. The title track 'Backslider' from the album 'Rubberneck', was released in the year 1996. Backslider's chart positions in US Air, US Main, and US mod were --, --, and -- respectively. The title track 'Push the Hand' from the album 'Hell Below/Stars Above', was released in the year 2001. Push the Hand's chart positions in US Air, US Main, and US mod were --, 34, and -- respectively. The title track 'No Deliverance' from the album 'No Deliverance', was released in the year 2008. No Deliverance's chart positions in US Air, US Main, and US mod were --, 38, and -- respectively. The title track 'Song I Hate' from the album 'No Deliverance', was released in the year 2009. Song I Hate's chart positions in US Air, US Main, and US mod were --, --, and -- respectively. The title track 'Summer of the Strange' from the album 'Play.Rock.Music', was released in the year 2012. Summer of the Strange's chart positions in US Air, US Main, and US mod were --, --, and -- respectively.", "explanation": "This is a bad example of 'long text passage generation task' because it fails to format/clean the missing/None/empty data values in the long text generation"}, {"input": "Table: ['Year','Title','Peak chart positions US Air','Peak chart positions US Main','Peak chart positions US Mod',Album]. ['1993', 'Mister Love', '--', '--', '--', 'Velvet']. ['1990', 'Dig a Hole', '--', '--', '--', 'Non-album single']. ['1994', 'Mister Love', '--', '--', '--', 'Rubberneck']. ['1995', 'Possum Kingdom', '40', '9', '4', 'Rubberneck']. ['1995', 'Away', '--', '23', '28', 'Rubberneck']. ['1996', 'Tyler', '--', '--', '--', 'Rubberneck']. ['1996', 'Backslider', '--', '--', '--', 'Rubberneck']. ['2001', 'Push the Hand', '--', '34', '--', 'Hell Below/Stars Above']. ['2008', 'No Deliverance', '--', '38', '--', 'No Deliverance']. ['2009', 'Song I Hate', '--', '--', '--', 'No Deliverance']. ['2012', 'Summer of the Strange', '--', '--', '--', 'Play.Rock.Music']", "output": "Passage: Mister Love's chart positions in US Air, US Main, and US mod were --, --, and -- respectively. The title track 'Mister Love' from the album 'Rubberneck', was released in the year 1994. Mister Love's chart positions in US Air, US Main, and US mod were --, --, and -- respectively. The title track 'Possum Kingdom' from the album 'Rubberneck', was released in the year 1995. Possum Kingdom's chart positions in US Air, US Main, and US mod were 40, 9, and 4 respectively. The title track 'Away' from the album 'Rubberneck', was released in the year 1995. Away's chart positions in US Air, US Main, and US mod were --, 23, and 28 respectively. The title track 'Tyler' from the album 'Rubberneck', was released in the year 1996. Tyler's chart positions in US Air, US Main, and US mod were --, --, and -- respectively. The title track 'Backslider' from the album 'Rubberneck', was released in the year 1996. Backslider's chart positions in US Air, US Main, and US mod were --, --, and -- respectively. The title track 'Push the Hand' from the album 'Hell Below/Stars Above', was released in the year 2001. Push the Hand's chart positions in US Air, US Main, and US mod were --, 34, and -- respectively. The title track 'No Deliverance' from the album 'No Deliverance', was released in the year 2008. No Deliverance's chart positions in US Air, US Main, and US mod were --, 38, and -- respectively. The title track 'Song I Hate' from the album 'No Deliverance', was released in the year 2009. Song I Hate's chart positions in US Air, US Main, and US mod were --, --, and -- respectively. The title track 'Summer of the Strange' from the album 'Play.Rock.Music', was released in the year 2012. Summer of the Strange's chart positions in US Air, US Main, and US mod were --, --, and -- respectively.", "explanation": "This is a bad example of 'long text passage generation task' because it fails to format/clean the missing/None/empty data values in the long text generation"}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Sports", "Statistics", "News"], "Instance": {"id": "task760-db1f9d517b0d41f3a1369262856bb1f5", "input": "Table: ['Locomotive', 'Named', 'Serial No', 'Entered service', 'Gauge', 'Livery']. ['BL26', 'Bob Hawke', '83-1010', 'March 1983', 'Standard', 'Pacific National blue & yellow']. ['BL27', '', '83-1011', 'August 1983', 'Standard', 'Pacific National blue & yellow']. ['BL28', '', '83-1012', 'September 1983', 'Standard', 'Pacific National blue & yellow']. ['BL29', '', '83-1013', 'October 1983', 'Broad', 'Pacific National blue & yellow']. ['BL30', '', '83-1014', 'December 1983', 'Standard', 'Pacific National blue & yellow']. ['BL31', '', '83-1015', 'November 1983', 'Standard', 'Pacific National blue & yellow']. ['BL32', '', '83-1016', 'February 1984', 'Broad', 'National Rail orange & grey']. ['BL33', '', '83-1017', 'April 1984', 'Standard', 'Pacific National blue & yellow']. ['BL34', '', '83-1018', 'June 1984', 'Broad', 'Pacific National blue & yellow']. ['BL35', '', '83-1019', 'July 1984', 'Standard', 'Pacific National blue & yellow']", "output": ["Passage:  The locomotive BL26 named Bob Hawke and with serial no. 83-1010, entered the service in the month of March 1983. It has Standard gauge, and Pacific National blue & yellow livery. The locomotive BL27 named  and with serial no. 83-1011, entered the service in the month of August 1983. It has Standard gauge, and Pacific National blue & yellow livery. The locomotive BL28 named  and with serial no. 83-1012, entered the service in the month of September 1983. It has Standard gauge, and Pacific National blue & yellow livery. The locomotive BL29 named  and with serial no. 83-1013, entered the service in the month of October 1983. It has Broad gauge, and Pacific National blue & yellow livery. The locomotive BL30 named  and with serial no. 83-1014, entered the service in the month of December 1983. It has Standard gauge, and Pacific National blue & yellow livery. The locomotive BL31 named  and with serial no. 83-1015, entered the service in the month of November 1983. It has Standard gauge, and Pacific National blue & yellow livery. The locomotive BL32 named  and with serial no. 83-1016, entered the service in the month of February 1984. It has Broad gauge, and National Rail orange & grey livery. The locomotive BL33 named  and with serial no. 83-1017, entered the service in the month of April 1984. It has Standard gauge, and Pacific National blue & yellow livery. The locomotive BL34 named  and with serial no. 83-1018, entered the service in the month of June 1984. It has Broad gauge, and Pacific National blue & yellow livery. The locomotive BL35 named  and with serial no. 83-1019, entered the service in the month of July 1984. It has Standard gauge, and Pacific National blue & yellow livery."]}, "Instance License": ["Microsoft Research Data License Agreement (https://msropendata-web-api.azurewebsites.net/licenses/2f933be3-284d-500b-7ea3-2aa2fd0f1bb2/view)"], "prediction": "Highlight the parts (if any) of this table related to Locomotive that should be reviewed by a trained professional. Details: The serial number, the name of the locomotive, the type of locomotive, the type of locomotive, the locomotive's gauge, the locomotive's livery, and the locomotive's engine type."}
+{"id": "task760-175ea253a14e4d3680d2ece872a0a375", "Task": "task760_msr_sqa_long_text_generation", "Contributors": "['Shreya Sarnaik sjsarnai@asu.edu']", "Source": ["msr_sqa"], "URL": ["https://huggingface.co/datasets/msr_sqa"], "Categories": ["Data to Text"], "Reasoning": ["Multihop Reasoning"], "Definition": ["You are given data in tabular format and you need to generate a passage with content in plain text format based on the information present in the table."], "Positive Examples": [{"input": "Table: ['Pick', 'Player', 'Team', 'Position', 'School']. ['1', 'Ben McDonald', 'Baltimore Orioles', 'RHP', 'Louisiana State University']. ['2', 'Tyler Houston', 'Atlanta Braves', 'C', 'Valley HS (Las Vegas, NV)']. ['3', 'Roger Salkeld', 'Seattle Mariners', 'RHP', 'Saugus (CA) HS']. ['4', 'Jeff Jackson', 'Philadelphia Phillies', 'OF', 'Simeon HS (Chicago, IL)']. ['5', 'Donald Harris', 'Texas Rangers', 'OF', 'Texas Tech University']. ['6', 'Paul Coleman', 'Saint Louis Cardinals', 'OF', 'Frankston (TX) HS']. ['7', 'Frank Thomas', 'Chicago White Sox', '1B', 'Auburn University']. ['8', 'Earl Cunningham', 'Chicago Cubs', 'OF', 'Lancaster (SC) HS']. ['9', 'Kyle Abbott', 'California Angels', 'LHP', 'Long Beach State University']. ['10', 'Charles Johnson', 'Montreal Expos', 'C', 'Westwood HS (Fort Pierce, FL)']. ['11', 'Calvin Murray', 'Cleveland Indians', '3B', 'W.T. White High School (Dallas, TX)']. ['12', 'Jeff Juden', 'Houston Astros', 'RHP', 'Salem (MA) HS']. ['13', 'Brent Mayne', 'Kansas City Royals', 'C', 'Cal State Fullerton']. ['14', 'Steve Hosey', 'San Francisco Giants', 'OF', 'Fresno State University']. ['15', 'Kiki Jones', 'Los Angeles Dodgers', 'RHP', 'Hillsborough HS (Tampa, FL)']. ['16', 'Greg Blosser', 'Boston Red Sox', 'OF', 'Sarasota (FL) HS']. ['17', 'Cal Eldred', 'Milwaukee Brewers', 'RHP', 'University of Iowa']. ['18', 'Willie Greene', 'Pittsburgh Pirates', 'SS', 'Jones County HS (Gray, GA)']. ['19', 'Eddie Zosky', 'Toronto Blue Jays', 'SS', 'Fresno State University']. ['20', 'Scott Bryant', 'Cincinnati Reds', 'OF', 'University of Texas']. ['21', 'Greg Gohr', 'Detroit Tigers', 'RHP', 'Santa Clara University']. ['22', 'Tom Goodwin', 'Los Angeles Dodgers', 'OF', 'Fresno State University']. ['23', 'Mo Vaughn', 'Boston Red Sox', '1B', 'Seton Hall University']. ['24', 'Alan Zinter', 'New York Mets', 'C', 'University of Arizona']. ['25', 'Chuck Knoblauch', 'Minnesota Twins', '2B', 'Texas A&M University']. ['26', 'Scott Burrell', 'Seattle Mariners', 'RHP', 'Hamden (CT) HS']", "output": "Passage: The player named Ben McDonald, plays as Pick-1.Ben McDonald plays for the team Baltimore Orioles, at position RHP. Ben McDonald belongs to the school Louisiana State University. The player named Tyler Houston, plays as Pick-2.Tyler Houston plays for the team Atlanta Braves, at position C. Tyler Houston belongs to the school Valley HS (Las Vegas, NV). The player named Roger Salkeld, plays as Pick-3.Roger Salkeld plays for the team Seattle Mariners, at position RHP. Roger Salkeld belongs to the school Saugus (CA) HS. The player named Jeff Jackson, plays as Pick-4.Jeff Jackson plays for the team Philadelphia Phillies, at position OF. Jeff Jackson belongs to the school Simeon HS (Chicago, IL). The player named Donald Harris, plays as Pick-5.Donald Harris plays for the team Texas Rangers, at position OF. Donald Harris belongs to the school Texas Tech University. The player named Paul Coleman, plays as Pick-6.Paul Coleman plays for the team Saint Louis Cardinals, at position OF. Paul Coleman belongs to the school Frankston (TX) HS. The player named Frank Thomas, plays as Pick-7.Frank Thomas plays for the team Chicago White Sox, at position 1B. Frank Thomas belongs to the school Auburn University. The player named Earl Cunningham, plays as Pick-8.Earl Cunningham plays for the team Chicago Cubs, at position OF. Earl Cunningham belongs to the school Lancaster (SC) HS. The player named Kyle Abbott, plays as Pick-9.Kyle Abbott plays for the team California Angels, at position LHP. Kyle Abbott belongs to the school Long Beach State University. The player named Charles Johnson, plays as Pick-10.Charles Johnson plays for the team Montreal Expos, at position C. Charles Johnson belongs to the school Westwood HS (Fort Pierce, FL). The player named Calvin Murray, plays as Pick-11.Calvin Murray plays for the team Cleveland Indians, at position 3B. Calvin Murray belongs to the school W.T. White High School (Dallas, TX). The player named Jeff Juden, plays as Pick-12.Jeff Juden plays for the team Houston Astros, at position RHP. Jeff Juden belongs to the school Salem (MA) HS. The player named Brent Mayne, plays as Pick-13.Brent Mayne plays for the team Kansas City Royals, at position C. Brent Mayne belongs to the school Cal State Fullerton. The player named Steve Hosey, plays as Pick-14.Steve Hosey plays for the team San Francisco Giants, at position OF. Steve Hosey belongs to the school Fresno State University. The player named Kiki Jones, plays as Pick-15.Kiki Jones plays for the team Los Angeles Dodgers, at position RHP. Kiki Jones belongs to the school Hillsborough HS (Tampa, FL). The player named Greg Blosser, plays as Pick-16.Greg Blosser plays for the team Boston Red Sox, at position OF. Greg Blosser belongs to the school Sarasota (FL) HS. The player named Cal Eldred, plays as Pick-17.Cal Eldred plays for the team Milwaukee Brewers, at position RHP. Cal Eldred belongs to the school University of Iowa. The player named Willie Greene, plays as Pick-18.Willie Greene plays for the team Pittsburgh Pirates, at position SS. Willie Greene belongs to the school Jones County HS (Gray, GA). The player named Eddie Zosky, plays as Pick-19.Eddie Zosky plays for the team Toronto Blue Jays, at position SS. Eddie Zosky belongs to the school Fresno State University. The player named Scott Bryant, plays as Pick-20.Scott Bryant plays for the team Cincinnati Reds, at position OF. Scott Bryant belongs to the school University of Texas. The player named Greg Gohr, plays as Pick-21.Greg Gohr plays for the team Detroit Tigers, at position RHP. Greg Gohr belongs to the school Santa Clara University. The player named Tom Goodwin, plays as Pick-22.Tom Goodwin plays for the team Los Angeles Dodgers, at position OF. Tom Goodwin belongs to the school Fresno State University. The player named Mo Vaughn, plays as Pick-23.Mo Vaughn plays for the team Boston Red Sox, at position 1B. Mo Vaughn belongs to the school Seton Hall University. The player named Alan Zinter, plays as Pick-24.Alan Zinter plays for the team New York Mets, at position C. Alan Zinter belongs to the school University of Arizona. The player named Chuck Knoblauch, plays as Pick-25.Chuck Knoblauch plays for the team Minnesota Twins, at position 2B. Chuck Knoblauch belongs to the school Texas A&M University. The player named Scott Burrell, plays as Pick-26.Scott Burrell plays for the team Seattle Mariners, at position RHP. Scott Burrell belongs to the school Hamden (CT) HS.", "explanation": "The output correctly captures the data in table and generates a long text passage which covers all the given information."}, {"input": "Table: ['Rank','Name', 'Nationality', 'Time (hand)', 'Notes']. ['','Tommy Green', 'Great Britain', '4:50:10', 'OR']. ['', 'Janis Dalins', 'Latvia', '4:57:20', '']. ['', 'Ugo Frigerio', 'Italy', '4:59:06', '']. ['4', 'Karl Hahnel', 'Germany', '5:06:06', '']. ['5', 'Ettore Rivolta', 'Italy', '5:07:39', '']. ['6', 'Paul Sievert', 'Germany', '5:16:41', '']. ['7', 'Henri Quintric', 'France', '5:27:25', '']. ['8', 'Ernie Crosbie', 'United States', '5:28:02', '']. ['9', 'Bill Chisholm', 'United States', '5:51:00', '']. ['10', 'Alfred Maasik', 'Estonia', '6:19:00', '']. ['', 'Henry Cieman', 'Canada', '', 'DNF']. ['', 'John Moralis', 'Greece', '', 'DNF']. ['', 'Francesco Pretti', 'Italy', '', 'DNF']. ['', 'Arthur Tell Schwab', 'Switzerland', '', 'DNF']. ['', 'Harry Hinkel', 'United States', '', 'DNF']", "output": "Passage:  The Great Britain athlete named Tommy Green is ranked  globally. Tommy Green completed the marathon in 4:50:10 seconds. The Latvia athlete named Janis Dalins is ranked  globally. Janis Dalins completed the marathon in 4:57:20 seconds. The Italy athlete named Ugo Frigerio is ranked  globally. Ugo Frigerio completed the marathon in 4:59:06 seconds. The Germany athlete named Karl Hahnel is ranked 4 globally. Karl Hahnel completed the marathon in 5:06:06 seconds. The Italy athlete named Ettore Rivolta is ranked 5 globally. Ettore Rivolta completed the marathon in 5:07:39 seconds. The Germany athlete named Paul Sievert is ranked 6 globally. Paul Sievert completed the marathon in 5:16:41 seconds. The France athlete named Henri Quintric is ranked 7 globally. Henri Quintric completed the marathon in 5:27:25 seconds. The United States athlete named Ernie Crosbie is ranked 8 globally. Ernie Crosbie completed the marathon in 5:28:02 seconds. The United States athlete named Bill Chisholm is ranked 9 globally. Bill Chisholm completed the marathon in 5:51:00 seconds. The Estonia athlete named Alfred Maasik is ranked 10 globally. Alfred Maasik completed the marathon in 6:19:00 seconds. The Canada athlete named Henry Cieman is ranked  globally. Henry Cieman completed the marathon in  seconds. The Greece athlete named John Moralis is ranked  globally. John Moralis completed the marathon in  seconds. The Italy athlete named Francesco Pretti is ranked  globally. Francesco Pretti completed the marathon in  seconds. The Switzerland athlete named Arthur Tell Schwab is ranked  globally. Arthur Tell Schwab completed the marathon in  seconds. The United States athlete named Harry Hinkel is ranked  globally. Harry Hinkel completed the marathon in  seconds.", "explanation": "The output correctly captures the data in table and generates a long text passage which covers all the given information."}, {"input": "Table: ['Year', 'Miss Northern Ireland', 'Hometown', 'Placement at Miss World', 'Notes']. ['2011', 'Finola Guinnane', 'Drumbo', 'Non-Finalist', 'Top 20 of Beach Beauty and Top 77 of Beauty with a Purpose at Miss World 2011']. ['2012', 'Tiffany Brien', 'Belfast', 'Top 30', 'Top 10 of Beach Fashion and 1st runner-up of Sports & Fitness at Miss World 2012']. ['2010', 'Lori Moore', 'Belfast', 'Top 25', 'Winner of Sports at Miss World 2010']. ['2009', 'Cherie Gardiner', 'Bangor', 'Non-Finalist', '']. ['2008', 'Judith Wilson', 'Enniskillen', 'Non-Finalist', 'Top 19 of Talent at Miss World 2008']. ['2007', 'Melissa Patton', 'Belfast', 'Non-Finalist', '']. ['2006', 'Catherine Jean Milligan', 'Newtownards', 'Top 17', 'Winner of Miss Talent at Miss World 2006']. ['2005', 'Lucy Evangelista', 'Portglenone', 'Top 15', 'Later Miss United Kingdom 2005 and Miss Universe United Kingdom 2005 2nd runner-up']. ['2004', 'Kirsty Anne Gabriel Stewart', 'Enniskillen', 'Non-Finalist', '']. ['2003', 'Diana Sayers', 'Belfast', 'Non-Finalist', '']. ['2002', 'Gayle Williamson', 'Lurgan', 'Non-Finalist', 'Later Miss United Kingdom 2002']. ['2001', 'Angela McCarthy', 'Belfast', 'Non-Finalist', '']. ['2000', 'Julie Lee-Ann Martin', 'Belfast', 'Non-Finalist', '']", "output": "Passage:  Tiffany Brien from Belfast was Miss Northern Ireland in the year 2012. Tiffany Brien was placed as a Top 30 at Miss World. Tiffany Brien was Top 10 of Beach Fashion and 1st runner-up of Sports & Fitness at Miss World 2012. Finola Guinnane from Drumbo was Miss Northern Ireland in the year 2011. Finola Guinnane was placed as a Non-Finalist at Miss World. Finola Guinnane was Top 20 of Beach Beauty and Top 77 of Beauty with a Purpose at Miss World 2011. Lori Moore from Belfast was Miss Northern Ireland in the year 2010. Lori Moore was placed as a Top 25 at Miss World. Lori Moore was Winner of Sports at Miss World 2010. Cherie Gardiner from Bangor was Miss Northern Ireland in the year 2009. Cherie Gardiner was placed as a Non-Finalist at Miss World. Cherie Gardiner was . Judith Wilson from Enniskillen was Miss Northern Ireland in the year 2008. Judith Wilson was placed as a Non-Finalist at Miss World. Judith Wilson was Top 19 of Talent at Miss World 2008. Melissa Patton from Belfast was Miss Northern Ireland in the year 2007. Melissa Patton was placed as a Non-Finalist at Miss World. Melissa Patton was . Catherine Jean Milligan from Newtownards was Miss Northern Ireland in the year 2006. Catherine Jean Milligan was placed as a Top 17 at Miss World. Catherine Jean Milligan was Winner of Miss Talent at Miss World 2006. Lucy Evangelista from Portglenone was Miss Northern Ireland in the year 2005. Lucy Evangelista was placed as a Top 15 at Miss World. Lucy Evangelista was Later Miss United Kingdom 2005 and Miss Universe United Kingdom 2005 2nd runner-up. Kirsty Anne Gabriel Stewart from Enniskillen was Miss Northern Ireland in the year 2004. Kirsty Anne Gabriel Stewart was placed as a Non-Finalist at Miss World. Kirsty Anne Gabriel Stewart was . Diana Sayers from Belfast was Miss Northern Ireland in the year 2003. Diana Sayers was placed as a Non-Finalist at Miss World. Diana Sayers was . Gayle Williamson from Lurgan was Miss Northern Ireland in the year 2002. Gayle Williamson was placed as a Non-Finalist at Miss World. Gayle Williamson was Later Miss United Kingdom 2002. Angela McCarthy from Belfast was Miss Northern Ireland in the year 2001. Angela McCarthy was placed as a Non-Finalist at Miss World. Angela McCarthy was . Julie Lee-Ann Martin from Belfast was Miss Northern Ireland in the year 2000. Julie Lee-Ann Martin was placed as a Non-Finalist at Miss World. Julie Lee-Ann Martin was.", "explanation": "The output correctly captures the data in table and generates a long text passage which covers all the given information."}], "Negative Examples": [{"input": "Table: ['Year','Title','Peak chart positions US Air','Peak chart positions US Main','Peak chart positions US Mod',Album]. ['1990', 'Dig a Hole', '--', '--', '--', 'Non-album single']. ['1993', 'Mister Love', '--', '--', '--', 'Velvet']. ['1994', 'Mister Love', '--', '--', '--', 'Rubberneck']. ['1995', 'Possum Kingdom', '40', '9', '4', 'Rubberneck']. ['1995', 'Away', '--', '23', '28', 'Rubberneck']. ['1996', 'Tyler', '--', '--', '--', 'Rubberneck']. ['1996', 'Backslider', '--', '--', '--', 'Rubberneck']. ['2001', 'Push the Hand', '--', '34', '--', 'Hell Below/Stars Above']. ['2008', 'No Deliverance', '--', '38', '--', 'No Deliverance']. ['2009', 'Song I Hate', '--', '--', '--', 'No Deliverance']. ['2012', 'Summer of the Strange', '--', '--', '--', 'Play.Rock.Music']", "output": "Passage: Dig a Hole's chart positions in US Air, US Main, and US mod were --, --, and -- respectively. The title track 'Mister Love' from the album 'Velvet', was released in the year 1993. Mister Love's chart positions in US Air, US Main, and US mod were --, --, and -- respectively. The title track 'Mister Love' from the album 'Rubberneck', was released in the year 1994. Mister Love's chart positions in US Air, US Main, and US mod were --, --, and -- respectively. The title track 'Possum Kingdom' from the album 'Rubberneck', was released in the year 1995. Possum Kingdom's chart positions in US Air, US Main, and US mod were 40, 9, and 4 respectively. The title track 'Away' from the album 'Rubberneck', was released in the year 1995. Away's chart positions in US Air, US Main, and US mod were --, 23, and 28 respectively. The title track 'Tyler' from the album 'Rubberneck', was released in the year 1996. Tyler's chart positions in US Air, US Main, and US mod were --, --, and -- respectively. The title track 'Backslider' from the album 'Rubberneck', was released in the year 1996. Backslider's chart positions in US Air, US Main, and US mod were --, --, and -- respectively. The title track 'Push the Hand' from the album 'Hell Below/Stars Above', was released in the year 2001. Push the Hand's chart positions in US Air, US Main, and US mod were --, 34, and -- respectively. The title track 'No Deliverance' from the album 'No Deliverance', was released in the year 2008. No Deliverance's chart positions in US Air, US Main, and US mod were --, 38, and -- respectively. The title track 'Song I Hate' from the album 'No Deliverance', was released in the year 2009. Song I Hate's chart positions in US Air, US Main, and US mod were --, --, and -- respectively. The title track 'Summer of the Strange' from the album 'Play.Rock.Music', was released in the year 2012. Summer of the Strange's chart positions in US Air, US Main, and US mod were --, --, and -- respectively.", "explanation": "This is a bad example of 'long text passage generation task' because it fails to format/clean the missing/None/empty data values in the long text generation"}, {"input": "Table: ['Year','Title','Peak chart positions US Air','Peak chart positions US Main','Peak chart positions US Mod',Album]. ['1990', 'Dig a Hole', '--', '--', '--', 'Non-album single']. ['1993', 'Mister Love', '--', '--', '--', 'Velvet']. ['1994', 'Mister Love', '--', '--', '--', 'Rubberneck']. ['1995', 'Possum Kingdom', '40', '9', '4', 'Rubberneck']. ['1995', 'Away', '--', '23', '28', 'Rubberneck']. ['1996', 'Tyler', '--', '--', '--', 'Rubberneck']. ['1996', 'Backslider', '--', '--', '--', 'Rubberneck']. ['2001', 'Push the Hand', '--', '34', '--', 'Hell Below/Stars Above']. ['2008', 'No Deliverance', '--', '38', '--', 'No Deliverance']. ['2009', 'Song I Hate', '--', '--', '--', 'No Deliverance']. ['2012', 'Summer of the Strange', '--', '--', '--', 'Play.Rock.Music']", "output": "Passage: The title track 'Dig a Hole' from the album 'Non-album single', was released in the year 1990. Dig a Hole's chart positions in US Air, US Main,  and US mod were --, --, and -- respectively. The title track 'Mister Love' from the album 'Velvet', was released in the year 1993. Mister Love's chart positions in US Air, US Main, and US mod were --, --, and -- respectively. The title track 'Mister Love' from the album 'Rubberneck', was released in the year 1994. Mister Love's chart positions in US Air, US Main, and US mod were --, --, and -- respectively. The title track 'Possum Kingdom' from the album 'Rubberneck', was released in the year 1995. Possum Kingdom's chart positions in US Air, US Main, and US mod were 40, 9, and 4 respectively. The title track 'Away' from the album 'Rubberneck', was released in the year 1995. Away's chart positions in US Air, US Main, and US mod were --, 23, and 28 respectively. The title track 'Tyler' from the album 'Rubberneck', was released in the year 1996. Tyler's chart positions in US Air, US Main, and US mod were --, --, and -- respectively. The title track 'Backslider' from the album 'Rubberneck', was released in the year 1996. Backslider's chart positions in US Air, US Main, and US mod were --, --, and -- respectively. The title track 'Push the Hand' from the album 'Hell Below/Stars Above', was released in the year 2001. Push the Hand's chart positions in US Air, US Main, and US mod were --, 34, and -- respectively. The title track 'No Deliverance' from the album 'No Deliverance', was released in the year 2008. No Deliverance's chart positions in US Air, US Main, and US mod were --, 38, and -- respectively. The title track 'Song I Hate' from the album 'No Deliverance', was released in the year 2009. Song I Hate's chart positions in US Air, US Main, and US mod were --, --, and -- respectively. The title track 'Summer of the Strange' from the album 'Play.Rock.Music', was released in the year 2012. Summer of the Strange's chart positions in US Air, US Main, and US mod were --, --, and -- respectively.", "explanation": "This is a bad example of 'long text passage generation task' because it fails to format/clean the missing/None/empty data values in the long text generation"}, {"input": "Table: ['Year','Title','Peak chart positions US Air','Peak chart positions US Main','Peak chart positions US Mod',Album]. ['1993', 'Mister Love', '--', '--', '--', 'Velvet']. ['1990', 'Dig a Hole', '--', '--', '--', 'Non-album single']. ['1994', 'Mister Love', '--', '--', '--', 'Rubberneck']. ['1995', 'Possum Kingdom', '40', '9', '4', 'Rubberneck']. ['1995', 'Away', '--', '23', '28', 'Rubberneck']. ['1996', 'Tyler', '--', '--', '--', 'Rubberneck']. ['1996', 'Backslider', '--', '--', '--', 'Rubberneck']. ['2001', 'Push the Hand', '--', '34', '--', 'Hell Below/Stars Above']. ['2008', 'No Deliverance', '--', '38', '--', 'No Deliverance']. ['2009', 'Song I Hate', '--', '--', '--', 'No Deliverance']. ['2012', 'Summer of the Strange', '--', '--', '--', 'Play.Rock.Music']", "output": "Passage: Mister Love's chart positions in US Air, US Main, and US mod were --, --, and -- respectively. The title track 'Mister Love' from the album 'Rubberneck', was released in the year 1994. Mister Love's chart positions in US Air, US Main, and US mod were --, --, and -- respectively. The title track 'Possum Kingdom' from the album 'Rubberneck', was released in the year 1995. Possum Kingdom's chart positions in US Air, US Main, and US mod were 40, 9, and 4 respectively. The title track 'Away' from the album 'Rubberneck', was released in the year 1995. Away's chart positions in US Air, US Main, and US mod were --, 23, and 28 respectively. The title track 'Tyler' from the album 'Rubberneck', was released in the year 1996. Tyler's chart positions in US Air, US Main, and US mod were --, --, and -- respectively. The title track 'Backslider' from the album 'Rubberneck', was released in the year 1996. Backslider's chart positions in US Air, US Main, and US mod were --, --, and -- respectively. The title track 'Push the Hand' from the album 'Hell Below/Stars Above', was released in the year 2001. Push the Hand's chart positions in US Air, US Main, and US mod were --, 34, and -- respectively. The title track 'No Deliverance' from the album 'No Deliverance', was released in the year 2008. No Deliverance's chart positions in US Air, US Main, and US mod were --, 38, and -- respectively. The title track 'Song I Hate' from the album 'No Deliverance', was released in the year 2009. Song I Hate's chart positions in US Air, US Main, and US mod were --, --, and -- respectively. The title track 'Summer of the Strange' from the album 'Play.Rock.Music', was released in the year 2012. Summer of the Strange's chart positions in US Air, US Main, and US mod were --, --, and -- respectively.", "explanation": "This is a bad example of 'long text passage generation task' because it fails to format/clean the missing/None/empty data values in the long text generation"}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Sports", "Statistics", "News"], "Instance": {"id": "task760-175ea253a14e4d3680d2ece872a0a375", "input": "Table: ['Model', 'Frame', \"Years Mfg'd\", 'Caliber(s)', 'Production', 'Barrel', 'Notes']. ['Remington-Beals Army Model Revolver', 'Large', '1861-1862', '.44', '1,900 (estimated)', '8 inch octagon', '']. ['Remington-Beals Navy Model Revolver', 'Medium', '1861-1862', '.36', '14,500 (estimated)', '7 1/2 inch octagon', '']. ['1861 Army Revolver (Old Model Army)', 'Large', '1862', '.44', '6,000 (estimated)', '8 inch octagon', '']. ['1861 Navy Revolver', 'Medium', '1862', '.36', '7,000 (estimated)', '7 3/8 inch octagon', '']. ['New Model Army Revolver', 'Large', '1863-1875', '.44', '122,000 (approximately)', '8 inch octagon', 'Used for factory conversions in .46 RF & .44 Remington']. ['New Model Navy Revolver', 'Medium', '1863-1875', '.36', '28,000 (approximately)', '7 3/8 inch octagon', 'Used for factory and U.S. Navy conversions to .38 RF & CF']. ['New Model Single Action Belt Revolver', 'Large', '1863-1875', '.36 percussion and .38 CF', '2,500 - 3,000 (estimated)', '6 1/2 inch octagon', 'Factory conversion production started in 1873']. ['Remington-Rider Double Action New Model Belt Revolver', 'Large', '1863-1873', '.36 percussion and .38 CF', '3,000 - 5,000 (estimated)', '6 1/2 inch octagon', '1863-1865 available with fluted cylinder, conversions had two-piece cylinder']. ['New Model Police Revolver', 'Medium', '1865-1873', '.36 percussion and .38 RF', '25,000 (estimated)', '3 1/2, 4 1/2, 5 1/2, 6 1/2 inch octagon', 'Conversions all believed to be rimfire only']. ['New Model Pocket Revolver', 'Medium', '1865-1873', '.31 percussion and .32 CF', '25,000 (estimated)', '3, 3 1/2, 4, 4 1/2', 'Majority produced as conversions or cartridge']", "output": ["Passage:  The model named 'Remington-Beals Army Model Revolver', with Large frame, was manufactured around the period 1861-1862. 'Remington-Beals Army Model Revolver' has .44 caliber(s), and the number of production units are 1,900 (estimated) and 8 inch octagon barrels. . The model named 'Remington-Beals Navy Model Revolver', with Medium frame, was manufactured around the period 1861-1862. 'Remington-Beals Navy Model Revolver' has .36 caliber(s), and the number of production units are 14,500 (estimated) and 7 1/2 inch octagon barrels. . The model named '1861 Army Revolver (Old Model Army)', with Large frame, was manufactured around the period 1862. '1861 Army Revolver (Old Model Army)' has .44 caliber(s), and the number of production units are 6,000 (estimated) and 8 inch octagon barrels. . The model named '1861 Navy Revolver', with Medium frame, was manufactured around the period 1862. '1861 Navy Revolver' has .36 caliber(s), and the number of production units are 7,000 (estimated) and 7 3/8 inch octagon barrels. . The model named 'New Model Army Revolver', with Large frame, was manufactured around the period 1863-1875. 'New Model Army Revolver' has .44 caliber(s), and the number of production units are 122,000 (approximately) and 8 inch octagon barrels. Used for factory conversions in .46 RF & .44 Remington. The model named 'New Model Navy Revolver', with Medium frame, was manufactured around the period 1863-1875. 'New Model Navy Revolver' has .36 caliber(s), and the number of production units are 28,000 (approximately) and 7 3/8 inch octagon barrels. Used for factory and U.S. Navy conversions to .38 RF & CF. The model named 'New Model Single Action Belt Revolver', with Large frame, was manufactured around the period 1863-1875. 'New Model Single Action Belt Revolver' has .36 percussion and .38 CF caliber(s), and the number of production units are 2,500 - 3,000 (estimated) and 6 1/2 inch octagon barrels. Factory conversion production started in 1873. The model named 'Remington-Rider Double Action New Model Belt Revolver', with Large frame, was manufactured around the period 1863-1873. 'Remington-Rider Double Action New Model Belt Revolver' has .36 percussion and .38 CF caliber(s), and the number of production units are 3,000 - 5,000 (estimated) and 6 1/2 inch octagon barrels. 1863-1865 available with fluted cylinder, conversions had two-piece cylinder. The model named 'New Model Police Revolver', with Medium frame, was manufactured around the period 1865-1873. 'New Model Police Revolver' has .36 percussion and .38 RF caliber(s), and the number of production units are 25,000 (estimated) and 3 1/2, 4 1/2, 5 1/2, 6 1/2 inch octagon barrels. Conversions all believed to be rimfire only. The model named 'New Model Pocket Revolver', with Medium frame, was manufactured around the period 1865-1873. 'New Model Pocket Revolver' has .31 percussion and .32 CF caliber(s), and the number of production units are 25,000 (estimated) and 3, 3 1/2, 4, 4 1/2 barrels. Majority produced as conversions or cartridge."]}, "Instance License": ["Microsoft Research Data License Agreement (https://msropendata-web-api.azurewebsites.net/licenses/2f933be3-284d-500b-7ea3-2aa2fd0f1bb2/view)"], "prediction": "1863-1875"}
+{"id": "task760-8de9a0cdb1b342a19dd857fabc6a40db", "Task": "task760_msr_sqa_long_text_generation", "Contributors": "['Shreya Sarnaik sjsarnai@asu.edu']", "Source": ["msr_sqa"], "URL": ["https://huggingface.co/datasets/msr_sqa"], "Categories": ["Data to Text"], "Reasoning": ["Multihop Reasoning"], "Definition": ["You are given data in tabular format and you need to generate a passage with content in plain text format based on the information present in the table."], "Positive Examples": [{"input": "Table: ['Pick', 'Player', 'Team', 'Position', 'School']. ['1', 'Ben McDonald', 'Baltimore Orioles', 'RHP', 'Louisiana State University']. ['2', 'Tyler Houston', 'Atlanta Braves', 'C', 'Valley HS (Las Vegas, NV)']. ['3', 'Roger Salkeld', 'Seattle Mariners', 'RHP', 'Saugus (CA) HS']. ['4', 'Jeff Jackson', 'Philadelphia Phillies', 'OF', 'Simeon HS (Chicago, IL)']. ['5', 'Donald Harris', 'Texas Rangers', 'OF', 'Texas Tech University']. ['6', 'Paul Coleman', 'Saint Louis Cardinals', 'OF', 'Frankston (TX) HS']. ['7', 'Frank Thomas', 'Chicago White Sox', '1B', 'Auburn University']. ['8', 'Earl Cunningham', 'Chicago Cubs', 'OF', 'Lancaster (SC) HS']. ['9', 'Kyle Abbott', 'California Angels', 'LHP', 'Long Beach State University']. ['10', 'Charles Johnson', 'Montreal Expos', 'C', 'Westwood HS (Fort Pierce, FL)']. ['11', 'Calvin Murray', 'Cleveland Indians', '3B', 'W.T. White High School (Dallas, TX)']. ['12', 'Jeff Juden', 'Houston Astros', 'RHP', 'Salem (MA) HS']. ['13', 'Brent Mayne', 'Kansas City Royals', 'C', 'Cal State Fullerton']. ['14', 'Steve Hosey', 'San Francisco Giants', 'OF', 'Fresno State University']. ['15', 'Kiki Jones', 'Los Angeles Dodgers', 'RHP', 'Hillsborough HS (Tampa, FL)']. ['16', 'Greg Blosser', 'Boston Red Sox', 'OF', 'Sarasota (FL) HS']. ['17', 'Cal Eldred', 'Milwaukee Brewers', 'RHP', 'University of Iowa']. ['18', 'Willie Greene', 'Pittsburgh Pirates', 'SS', 'Jones County HS (Gray, GA)']. ['19', 'Eddie Zosky', 'Toronto Blue Jays', 'SS', 'Fresno State University']. ['20', 'Scott Bryant', 'Cincinnati Reds', 'OF', 'University of Texas']. ['21', 'Greg Gohr', 'Detroit Tigers', 'RHP', 'Santa Clara University']. ['22', 'Tom Goodwin', 'Los Angeles Dodgers', 'OF', 'Fresno State University']. ['23', 'Mo Vaughn', 'Boston Red Sox', '1B', 'Seton Hall University']. ['24', 'Alan Zinter', 'New York Mets', 'C', 'University of Arizona']. ['25', 'Chuck Knoblauch', 'Minnesota Twins', '2B', 'Texas A&M University']. ['26', 'Scott Burrell', 'Seattle Mariners', 'RHP', 'Hamden (CT) HS']", "output": "Passage: The player named Ben McDonald, plays as Pick-1.Ben McDonald plays for the team Baltimore Orioles, at position RHP. Ben McDonald belongs to the school Louisiana State University. The player named Tyler Houston, plays as Pick-2.Tyler Houston plays for the team Atlanta Braves, at position C. Tyler Houston belongs to the school Valley HS (Las Vegas, NV). The player named Roger Salkeld, plays as Pick-3.Roger Salkeld plays for the team Seattle Mariners, at position RHP. Roger Salkeld belongs to the school Saugus (CA) HS. The player named Jeff Jackson, plays as Pick-4.Jeff Jackson plays for the team Philadelphia Phillies, at position OF. Jeff Jackson belongs to the school Simeon HS (Chicago, IL). The player named Donald Harris, plays as Pick-5.Donald Harris plays for the team Texas Rangers, at position OF. Donald Harris belongs to the school Texas Tech University. The player named Paul Coleman, plays as Pick-6.Paul Coleman plays for the team Saint Louis Cardinals, at position OF. Paul Coleman belongs to the school Frankston (TX) HS. The player named Frank Thomas, plays as Pick-7.Frank Thomas plays for the team Chicago White Sox, at position 1B. Frank Thomas belongs to the school Auburn University. The player named Earl Cunningham, plays as Pick-8.Earl Cunningham plays for the team Chicago Cubs, at position OF. Earl Cunningham belongs to the school Lancaster (SC) HS. The player named Kyle Abbott, plays as Pick-9.Kyle Abbott plays for the team California Angels, at position LHP. Kyle Abbott belongs to the school Long Beach State University. The player named Charles Johnson, plays as Pick-10.Charles Johnson plays for the team Montreal Expos, at position C. Charles Johnson belongs to the school Westwood HS (Fort Pierce, FL). The player named Calvin Murray, plays as Pick-11.Calvin Murray plays for the team Cleveland Indians, at position 3B. Calvin Murray belongs to the school W.T. White High School (Dallas, TX). The player named Jeff Juden, plays as Pick-12.Jeff Juden plays for the team Houston Astros, at position RHP. Jeff Juden belongs to the school Salem (MA) HS. The player named Brent Mayne, plays as Pick-13.Brent Mayne plays for the team Kansas City Royals, at position C. Brent Mayne belongs to the school Cal State Fullerton. The player named Steve Hosey, plays as Pick-14.Steve Hosey plays for the team San Francisco Giants, at position OF. Steve Hosey belongs to the school Fresno State University. The player named Kiki Jones, plays as Pick-15.Kiki Jones plays for the team Los Angeles Dodgers, at position RHP. Kiki Jones belongs to the school Hillsborough HS (Tampa, FL). The player named Greg Blosser, plays as Pick-16.Greg Blosser plays for the team Boston Red Sox, at position OF. Greg Blosser belongs to the school Sarasota (FL) HS. The player named Cal Eldred, plays as Pick-17.Cal Eldred plays for the team Milwaukee Brewers, at position RHP. Cal Eldred belongs to the school University of Iowa. The player named Willie Greene, plays as Pick-18.Willie Greene plays for the team Pittsburgh Pirates, at position SS. Willie Greene belongs to the school Jones County HS (Gray, GA). The player named Eddie Zosky, plays as Pick-19.Eddie Zosky plays for the team Toronto Blue Jays, at position SS. Eddie Zosky belongs to the school Fresno State University. The player named Scott Bryant, plays as Pick-20.Scott Bryant plays for the team Cincinnati Reds, at position OF. Scott Bryant belongs to the school University of Texas. The player named Greg Gohr, plays as Pick-21.Greg Gohr plays for the team Detroit Tigers, at position RHP. Greg Gohr belongs to the school Santa Clara University. The player named Tom Goodwin, plays as Pick-22.Tom Goodwin plays for the team Los Angeles Dodgers, at position OF. Tom Goodwin belongs to the school Fresno State University. The player named Mo Vaughn, plays as Pick-23.Mo Vaughn plays for the team Boston Red Sox, at position 1B. Mo Vaughn belongs to the school Seton Hall University. The player named Alan Zinter, plays as Pick-24.Alan Zinter plays for the team New York Mets, at position C. Alan Zinter belongs to the school University of Arizona. The player named Chuck Knoblauch, plays as Pick-25.Chuck Knoblauch plays for the team Minnesota Twins, at position 2B. Chuck Knoblauch belongs to the school Texas A&M University. The player named Scott Burrell, plays as Pick-26.Scott Burrell plays for the team Seattle Mariners, at position RHP. Scott Burrell belongs to the school Hamden (CT) HS.", "explanation": "The output correctly captures the data in table and generates a long text passage which covers all the given information."}, {"input": "Table: ['Rank','Name', 'Nationality', 'Time (hand)', 'Notes']. ['','Tommy Green', 'Great Britain', '4:50:10', 'OR']. ['', 'Janis Dalins', 'Latvia', '4:57:20', '']. ['', 'Ugo Frigerio', 'Italy', '4:59:06', '']. ['4', 'Karl Hahnel', 'Germany', '5:06:06', '']. ['5', 'Ettore Rivolta', 'Italy', '5:07:39', '']. ['6', 'Paul Sievert', 'Germany', '5:16:41', '']. ['7', 'Henri Quintric', 'France', '5:27:25', '']. ['8', 'Ernie Crosbie', 'United States', '5:28:02', '']. ['9', 'Bill Chisholm', 'United States', '5:51:00', '']. ['10', 'Alfred Maasik', 'Estonia', '6:19:00', '']. ['', 'Henry Cieman', 'Canada', '', 'DNF']. ['', 'John Moralis', 'Greece', '', 'DNF']. ['', 'Francesco Pretti', 'Italy', '', 'DNF']. ['', 'Arthur Tell Schwab', 'Switzerland', '', 'DNF']. ['', 'Harry Hinkel', 'United States', '', 'DNF']", "output": "Passage:  The Great Britain athlete named Tommy Green is ranked  globally. Tommy Green completed the marathon in 4:50:10 seconds. The Latvia athlete named Janis Dalins is ranked  globally. Janis Dalins completed the marathon in 4:57:20 seconds. The Italy athlete named Ugo Frigerio is ranked  globally. Ugo Frigerio completed the marathon in 4:59:06 seconds. The Germany athlete named Karl Hahnel is ranked 4 globally. Karl Hahnel completed the marathon in 5:06:06 seconds. The Italy athlete named Ettore Rivolta is ranked 5 globally. Ettore Rivolta completed the marathon in 5:07:39 seconds. The Germany athlete named Paul Sievert is ranked 6 globally. Paul Sievert completed the marathon in 5:16:41 seconds. The France athlete named Henri Quintric is ranked 7 globally. Henri Quintric completed the marathon in 5:27:25 seconds. The United States athlete named Ernie Crosbie is ranked 8 globally. Ernie Crosbie completed the marathon in 5:28:02 seconds. The United States athlete named Bill Chisholm is ranked 9 globally. Bill Chisholm completed the marathon in 5:51:00 seconds. The Estonia athlete named Alfred Maasik is ranked 10 globally. Alfred Maasik completed the marathon in 6:19:00 seconds. The Canada athlete named Henry Cieman is ranked  globally. Henry Cieman completed the marathon in  seconds. The Greece athlete named John Moralis is ranked  globally. John Moralis completed the marathon in  seconds. The Italy athlete named Francesco Pretti is ranked  globally. Francesco Pretti completed the marathon in  seconds. The Switzerland athlete named Arthur Tell Schwab is ranked  globally. Arthur Tell Schwab completed the marathon in  seconds. The United States athlete named Harry Hinkel is ranked  globally. Harry Hinkel completed the marathon in  seconds.", "explanation": "The output correctly captures the data in table and generates a long text passage which covers all the given information."}, {"input": "Table: ['Year', 'Miss Northern Ireland', 'Hometown', 'Placement at Miss World', 'Notes']. ['2011', 'Finola Guinnane', 'Drumbo', 'Non-Finalist', 'Top 20 of Beach Beauty and Top 77 of Beauty with a Purpose at Miss World 2011']. ['2012', 'Tiffany Brien', 'Belfast', 'Top 30', 'Top 10 of Beach Fashion and 1st runner-up of Sports & Fitness at Miss World 2012']. ['2010', 'Lori Moore', 'Belfast', 'Top 25', 'Winner of Sports at Miss World 2010']. ['2009', 'Cherie Gardiner', 'Bangor', 'Non-Finalist', '']. ['2008', 'Judith Wilson', 'Enniskillen', 'Non-Finalist', 'Top 19 of Talent at Miss World 2008']. ['2007', 'Melissa Patton', 'Belfast', 'Non-Finalist', '']. ['2006', 'Catherine Jean Milligan', 'Newtownards', 'Top 17', 'Winner of Miss Talent at Miss World 2006']. ['2005', 'Lucy Evangelista', 'Portglenone', 'Top 15', 'Later Miss United Kingdom 2005 and Miss Universe United Kingdom 2005 2nd runner-up']. ['2004', 'Kirsty Anne Gabriel Stewart', 'Enniskillen', 'Non-Finalist', '']. ['2003', 'Diana Sayers', 'Belfast', 'Non-Finalist', '']. ['2002', 'Gayle Williamson', 'Lurgan', 'Non-Finalist', 'Later Miss United Kingdom 2002']. ['2001', 'Angela McCarthy', 'Belfast', 'Non-Finalist', '']. ['2000', 'Julie Lee-Ann Martin', 'Belfast', 'Non-Finalist', '']", "output": "Passage:  Tiffany Brien from Belfast was Miss Northern Ireland in the year 2012. Tiffany Brien was placed as a Top 30 at Miss World. Tiffany Brien was Top 10 of Beach Fashion and 1st runner-up of Sports & Fitness at Miss World 2012. Finola Guinnane from Drumbo was Miss Northern Ireland in the year 2011. Finola Guinnane was placed as a Non-Finalist at Miss World. Finola Guinnane was Top 20 of Beach Beauty and Top 77 of Beauty with a Purpose at Miss World 2011. Lori Moore from Belfast was Miss Northern Ireland in the year 2010. Lori Moore was placed as a Top 25 at Miss World. Lori Moore was Winner of Sports at Miss World 2010. Cherie Gardiner from Bangor was Miss Northern Ireland in the year 2009. Cherie Gardiner was placed as a Non-Finalist at Miss World. Cherie Gardiner was . Judith Wilson from Enniskillen was Miss Northern Ireland in the year 2008. Judith Wilson was placed as a Non-Finalist at Miss World. Judith Wilson was Top 19 of Talent at Miss World 2008. Melissa Patton from Belfast was Miss Northern Ireland in the year 2007. Melissa Patton was placed as a Non-Finalist at Miss World. Melissa Patton was . Catherine Jean Milligan from Newtownards was Miss Northern Ireland in the year 2006. Catherine Jean Milligan was placed as a Top 17 at Miss World. Catherine Jean Milligan was Winner of Miss Talent at Miss World 2006. Lucy Evangelista from Portglenone was Miss Northern Ireland in the year 2005. Lucy Evangelista was placed as a Top 15 at Miss World. Lucy Evangelista was Later Miss United Kingdom 2005 and Miss Universe United Kingdom 2005 2nd runner-up. Kirsty Anne Gabriel Stewart from Enniskillen was Miss Northern Ireland in the year 2004. Kirsty Anne Gabriel Stewart was placed as a Non-Finalist at Miss World. Kirsty Anne Gabriel Stewart was . Diana Sayers from Belfast was Miss Northern Ireland in the year 2003. Diana Sayers was placed as a Non-Finalist at Miss World. Diana Sayers was . Gayle Williamson from Lurgan was Miss Northern Ireland in the year 2002. Gayle Williamson was placed as a Non-Finalist at Miss World. Gayle Williamson was Later Miss United Kingdom 2002. Angela McCarthy from Belfast was Miss Northern Ireland in the year 2001. Angela McCarthy was placed as a Non-Finalist at Miss World. Angela McCarthy was . Julie Lee-Ann Martin from Belfast was Miss Northern Ireland in the year 2000. Julie Lee-Ann Martin was placed as a Non-Finalist at Miss World. Julie Lee-Ann Martin was.", "explanation": "The output correctly captures the data in table and generates a long text passage which covers all the given information."}], "Negative Examples": [{"input": "Table: ['Year','Title','Peak chart positions US Air','Peak chart positions US Main','Peak chart positions US Mod',Album]. ['1990', 'Dig a Hole', '--', '--', '--', 'Non-album single']. ['1993', 'Mister Love', '--', '--', '--', 'Velvet']. ['1994', 'Mister Love', '--', '--', '--', 'Rubberneck']. ['1995', 'Possum Kingdom', '40', '9', '4', 'Rubberneck']. ['1995', 'Away', '--', '23', '28', 'Rubberneck']. ['1996', 'Tyler', '--', '--', '--', 'Rubberneck']. ['1996', 'Backslider', '--', '--', '--', 'Rubberneck']. ['2001', 'Push the Hand', '--', '34', '--', 'Hell Below/Stars Above']. ['2008', 'No Deliverance', '--', '38', '--', 'No Deliverance']. ['2009', 'Song I Hate', '--', '--', '--', 'No Deliverance']. ['2012', 'Summer of the Strange', '--', '--', '--', 'Play.Rock.Music']", "output": "Passage: Dig a Hole's chart positions in US Air, US Main, and US mod were --, --, and -- respectively. The title track 'Mister Love' from the album 'Velvet', was released in the year 1993. Mister Love's chart positions in US Air, US Main, and US mod were --, --, and -- respectively. The title track 'Mister Love' from the album 'Rubberneck', was released in the year 1994. Mister Love's chart positions in US Air, US Main, and US mod were --, --, and -- respectively. The title track 'Possum Kingdom' from the album 'Rubberneck', was released in the year 1995. Possum Kingdom's chart positions in US Air, US Main, and US mod were 40, 9, and 4 respectively. The title track 'Away' from the album 'Rubberneck', was released in the year 1995. Away's chart positions in US Air, US Main, and US mod were --, 23, and 28 respectively. The title track 'Tyler' from the album 'Rubberneck', was released in the year 1996. Tyler's chart positions in US Air, US Main, and US mod were --, --, and -- respectively. The title track 'Backslider' from the album 'Rubberneck', was released in the year 1996. Backslider's chart positions in US Air, US Main, and US mod were --, --, and -- respectively. The title track 'Push the Hand' from the album 'Hell Below/Stars Above', was released in the year 2001. Push the Hand's chart positions in US Air, US Main, and US mod were --, 34, and -- respectively. The title track 'No Deliverance' from the album 'No Deliverance', was released in the year 2008. No Deliverance's chart positions in US Air, US Main, and US mod were --, 38, and -- respectively. The title track 'Song I Hate' from the album 'No Deliverance', was released in the year 2009. Song I Hate's chart positions in US Air, US Main, and US mod were --, --, and -- respectively. The title track 'Summer of the Strange' from the album 'Play.Rock.Music', was released in the year 2012. Summer of the Strange's chart positions in US Air, US Main, and US mod were --, --, and -- respectively.", "explanation": "This is a bad example of 'long text passage generation task' because it fails to format/clean the missing/None/empty data values in the long text generation"}, {"input": "Table: ['Year','Title','Peak chart positions US Air','Peak chart positions US Main','Peak chart positions US Mod',Album]. ['1990', 'Dig a Hole', '--', '--', '--', 'Non-album single']. ['1993', 'Mister Love', '--', '--', '--', 'Velvet']. ['1994', 'Mister Love', '--', '--', '--', 'Rubberneck']. ['1995', 'Possum Kingdom', '40', '9', '4', 'Rubberneck']. ['1995', 'Away', '--', '23', '28', 'Rubberneck']. ['1996', 'Tyler', '--', '--', '--', 'Rubberneck']. ['1996', 'Backslider', '--', '--', '--', 'Rubberneck']. ['2001', 'Push the Hand', '--', '34', '--', 'Hell Below/Stars Above']. ['2008', 'No Deliverance', '--', '38', '--', 'No Deliverance']. ['2009', 'Song I Hate', '--', '--', '--', 'No Deliverance']. ['2012', 'Summer of the Strange', '--', '--', '--', 'Play.Rock.Music']", "output": "Passage: The title track 'Dig a Hole' from the album 'Non-album single', was released in the year 1990. Dig a Hole's chart positions in US Air, US Main,  and US mod were --, --, and -- respectively. The title track 'Mister Love' from the album 'Velvet', was released in the year 1993. Mister Love's chart positions in US Air, US Main, and US mod were --, --, and -- respectively. The title track 'Mister Love' from the album 'Rubberneck', was released in the year 1994. Mister Love's chart positions in US Air, US Main, and US mod were --, --, and -- respectively. The title track 'Possum Kingdom' from the album 'Rubberneck', was released in the year 1995. Possum Kingdom's chart positions in US Air, US Main, and US mod were 40, 9, and 4 respectively. The title track 'Away' from the album 'Rubberneck', was released in the year 1995. Away's chart positions in US Air, US Main, and US mod were --, 23, and 28 respectively. The title track 'Tyler' from the album 'Rubberneck', was released in the year 1996. Tyler's chart positions in US Air, US Main, and US mod were --, --, and -- respectively. The title track 'Backslider' from the album 'Rubberneck', was released in the year 1996. Backslider's chart positions in US Air, US Main, and US mod were --, --, and -- respectively. The title track 'Push the Hand' from the album 'Hell Below/Stars Above', was released in the year 2001. Push the Hand's chart positions in US Air, US Main, and US mod were --, 34, and -- respectively. The title track 'No Deliverance' from the album 'No Deliverance', was released in the year 2008. No Deliverance's chart positions in US Air, US Main, and US mod were --, 38, and -- respectively. The title track 'Song I Hate' from the album 'No Deliverance', was released in the year 2009. Song I Hate's chart positions in US Air, US Main, and US mod were --, --, and -- respectively. The title track 'Summer of the Strange' from the album 'Play.Rock.Music', was released in the year 2012. Summer of the Strange's chart positions in US Air, US Main, and US mod were --, --, and -- respectively.", "explanation": "This is a bad example of 'long text passage generation task' because it fails to format/clean the missing/None/empty data values in the long text generation"}, {"input": "Table: ['Year','Title','Peak chart positions US Air','Peak chart positions US Main','Peak chart positions US Mod',Album]. ['1993', 'Mister Love', '--', '--', '--', 'Velvet']. ['1990', 'Dig a Hole', '--', '--', '--', 'Non-album single']. ['1994', 'Mister Love', '--', '--', '--', 'Rubberneck']. ['1995', 'Possum Kingdom', '40', '9', '4', 'Rubberneck']. ['1995', 'Away', '--', '23', '28', 'Rubberneck']. ['1996', 'Tyler', '--', '--', '--', 'Rubberneck']. ['1996', 'Backslider', '--', '--', '--', 'Rubberneck']. ['2001', 'Push the Hand', '--', '34', '--', 'Hell Below/Stars Above']. ['2008', 'No Deliverance', '--', '38', '--', 'No Deliverance']. ['2009', 'Song I Hate', '--', '--', '--', 'No Deliverance']. ['2012', 'Summer of the Strange', '--', '--', '--', 'Play.Rock.Music']", "output": "Passage: Mister Love's chart positions in US Air, US Main, and US mod were --, --, and -- respectively. The title track 'Mister Love' from the album 'Rubberneck', was released in the year 1994. Mister Love's chart positions in US Air, US Main, and US mod were --, --, and -- respectively. The title track 'Possum Kingdom' from the album 'Rubberneck', was released in the year 1995. Possum Kingdom's chart positions in US Air, US Main, and US mod were 40, 9, and 4 respectively. The title track 'Away' from the album 'Rubberneck', was released in the year 1995. Away's chart positions in US Air, US Main, and US mod were --, 23, and 28 respectively. The title track 'Tyler' from the album 'Rubberneck', was released in the year 1996. Tyler's chart positions in US Air, US Main, and US mod were --, --, and -- respectively. The title track 'Backslider' from the album 'Rubberneck', was released in the year 1996. Backslider's chart positions in US Air, US Main, and US mod were --, --, and -- respectively. The title track 'Push the Hand' from the album 'Hell Below/Stars Above', was released in the year 2001. Push the Hand's chart positions in US Air, US Main, and US mod were --, 34, and -- respectively. The title track 'No Deliverance' from the album 'No Deliverance', was released in the year 2008. No Deliverance's chart positions in US Air, US Main, and US mod were --, 38, and -- respectively. The title track 'Song I Hate' from the album 'No Deliverance', was released in the year 2009. Song I Hate's chart positions in US Air, US Main, and US mod were --, --, and -- respectively. The title track 'Summer of the Strange' from the album 'Play.Rock.Music', was released in the year 2012. Summer of the Strange's chart positions in US Air, US Main, and US mod were --, --, and -- respectively.", "explanation": "This is a bad example of 'long text passage generation task' because it fails to format/clean the missing/None/empty data values in the long text generation"}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Sports", "Statistics", "News"], "Instance": {"id": "task760-8de9a0cdb1b342a19dd857fabc6a40db", "input": "Table: ['Rank', 'Name', 'Nationality', 'Time (hand)', 'Notes']. ['', 'Tommy Green', 'Great Britain', '4:50:10', 'OR']. ['', 'Janis Dalins', 'Latvia', '4:57:20', '']. ['', 'Ugo Frigerio', 'Italy', '4:59:06', '']. ['4', 'Karl Hahnel', 'Germany', '5:06:06', '']. ['5', 'Ettore Rivolta', 'Italy', '5:07:39', '']. ['6', 'Paul Sievert', 'Germany', '5:16:41', '']. ['7', 'Henri Quintric', 'France', '5:27:25', '']. ['8', 'Ernie Crosbie', 'United States', '5:28:02', '']. ['9', 'Bill Chisholm', 'United States', '5:51:00', '']. ['10', 'Alfred Maasik', 'Estonia', '6:19:00', '']. ['', 'Henry Cieman', 'Canada', '', 'DNF']. ['', 'John Moralis', 'Greece', '', 'DNF']. ['', 'Francesco Pretti', 'Italy', '', 'DNF']. ['', 'Arthur Tell Schwab', 'Switzerland', '', 'DNF']. ['', 'Harry Hinkel', 'United States', '', 'DNF']", "output": ["Passage:  The Great Britain athlete named Tommy Green is ranked  globally. Tommy Green completed the marathon in 4:50:10 seconds. The Latvia athlete named Janis Dalins is ranked  globally. Janis Dalins completed the marathon in 4:57:20 seconds. The Italy athlete named Ugo Frigerio is ranked  globally. Ugo Frigerio completed the marathon in 4:59:06 seconds. The Germany athlete named Karl Hahnel is ranked 4 globally. Karl Hahnel completed the marathon in 5:06:06 seconds. The Italy athlete named Ettore Rivolta is ranked 5 globally. Ettore Rivolta completed the marathon in 5:07:39 seconds. The Germany athlete named Paul Sievert is ranked 6 globally. Paul Sievert completed the marathon in 5:16:41 seconds. The France athlete named Henri Quintric is ranked 7 globally. Henri Quintric completed the marathon in 5:27:25 seconds. The United States athlete named Ernie Crosbie is ranked 8 globally. Ernie Crosbie completed the marathon in 5:28:02 seconds. The United States athlete named Bill Chisholm is ranked 9 globally. Bill Chisholm completed the marathon in 5:51:00 seconds. The Estonia athlete named Alfred Maasik is ranked 10 globally. Alfred Maasik completed the marathon in 6:19:00 seconds. The Canada athlete named Henry Cieman is ranked  globally. Henry Cieman completed the marathon in  seconds. The Greece athlete named John Moralis is ranked  globally. John Moralis completed the marathon in  seconds. The Italy athlete named Francesco Pretti is ranked  globally. Francesco Pretti completed the marathon in  seconds. The Switzerland athlete named Arthur Tell Schwab is ranked  globally. Arthur Tell Schwab completed the marathon in  seconds. The United States athlete named Harry Hinkel is ranked  globally. Harry Hinkel completed the marathon in  seconds."]}, "Instance License": ["Microsoft Research Data License Agreement (https://msropendata-web-api.azurewebsites.net/licenses/2f933be3-284d-500b-7ea3-2aa2fd0f1bb2/view)"], "prediction": "['', '', '', '', '', '', '', '', '', '', '', '', '', '', '', '', '', '', '', '', '', '', '', '', '', '', '', '', '', '', '', ''"}
+{"id": "task035-bdf92efc1ea14b83a90afa360b98a1e4", "Task": "task035_winogrande_question_modification_person", "Contributors": "['Swaroop Mishra', 'Daniel Khashabi']", "Source": ["winogrande"], "URL": ["https://leaderboard.allenai.org/winogrande/submissions/about"], "Categories": ["Question Rewriting"], "Reasoning": ["Commonsense Reasoning"], "Definition": ["You're given a fill-in-the-blank question where the answer is PersonX. You need to minimally change the given question so that the answer flips to PersonY. This task typically involves replacing one word i.e., the 'trigger word' with its antonym (e.g., changing from \"sympathetic\" to \"stern\"). You should not change any content in the given question beyond a word or two i.e. the trigger word/phrase. PersonX and PersonY should not be equally likely to fill the blank. For your question, PersonY should be a well-agreed answer to fill in the blank. Your generations should NOT contain potentially explicit, offensive, or adult content. Do not use the names of real people or generic names (e.g., Donald Trump, John Doe, etc.) in your question. Avoid repeating the same style or phrase in generating your modified question e.g. this task can be always solved using a simple negation i.e. by adding not, never, etc. Instead, try to increase the word diversity. Your question must contain at least 15 and at most 30 words. Your question must have at least 70% overlapping words with the given question. You must utilize the given context word while writing the question. Your question must contain only one blank. Make sure that PersonX and PersonY have the same gender. In your question, PersonX and PersonY should be used only ONCE and PersonX should appear earlier than PersonY. Although there are many correct answers, you only need to write one of them."], "Positive Examples": [{"input": "Context word: upset. \nQuestion: PersonX yelled at PersonY because _ was so upset about the news. \nAnswer: PersonX.", "output": "PersonX comforted at PersonY because _ was so upset about the news.", "explanation": "On replacing the trigger word \"yelled\" with its antonym \"comforted\", the answer flips to PersonY which is as per the given instruction. So, this is a valid question."}, {"input": "Context word: library. \nQuestion: PersonX asked PersonY what time the library closes, because _ had forgotten. \nAnswer: PersonX.", "output": "PersonX asked PersonY what time the library closes, but _ had forgotten.", "explanation": "On replacing the trigger word \"because\" with \"but\", the answer flips to PersonY. This is a valid question, as it follows exactly the given instruction."}, {"input": "Context word: door. \nQuestion: PersonX knocked on PersonY's door, but there was no answer. _ was disappointed. \nAnswer: PersonX.", "output": "PersonX knocked on PersonY's door, but there was no answer. _ was out.", "explanation": "On replacing the trigger word \"disappointed\" with \"out\", the answer flips to PersonY. This is a valid question, as it follows exactly the given instruction."}, {"input": "Context word: step. \nQuestion: PersonX was always ahead of PersonY, as _ walked with a quick step. \nAnswer: PersonX.", "output": "PersonX was always behind PersonY, as _ walked with a quick step .", "explanation": "Here, replacing the trigger word \"ahead\" with its antonym \"behind\" flips answer to PersonY which is as per the given instruction. So, this is a valid question."}, {"input": "Context word: dropped. \nQuestion: When PersonX dropped his ice cream, PersonY giggled, so father gave _ a sympathetic look. \nAnswer: PersonX.", "output": "When PersonX dropped his ice cream, PersonY giggled, so father gave _ a stern look.", "explanation": "Here, replacing the trigger word \"sympathetic\" with \"stern\" flips answer to PersonY. This is a valid question, as it follows exactly the given instruction."}], "Negative Examples": [{"input": "Context word: upset. \nQuestion: PersonX yelled at PersonY because _ was so upset about the news. \nAnswer: PersonX.", "output": "PersonX yelled at PersonY when PersonX tried to kiss _.", "explanation": "The generated question contains inapprorpriate content. Note that, your generations should NOT contain potentially explicit, offensive, or adult content."}, {"input": "Context word: library. \nQuestion: PersonX asked PersonY what time the library closes, because _ had forgotten. \nAnswer: PersonX.", "output": "PersonX asked PersonY what time the library closes, because _ had reminded.", "explanation": "Even though the word \"forgotten\" is replaced by its antonym \"reminded\", the question does not makes sense."}, {"input": "Context word: door. \nQuestion: PersonX knocked on PersonY's door, but there was no answer. _ was disappointed. \nAnswer: PersonX.", "output": "PersonX knocked on PersonY's door, but there was no answer from PersonY. _ was out.", "explanation": "Here PersonY has been used more than once in the question. Note that In your question, PersonX and PersonY should be used only ONCE."}, {"input": "Context word: step. \nQuestion: PersonX was always ahead of PersonY, as _ walked with a quick step. \nAnswer: PersonX.", "output": "PersonY was always ahead of PersonX, as _ walked with a quick step .", "explanation": "Here, the issue is that the usage order of PersonX and PersonY has been changed in the generated question. Remember that, for a question to be valid, PersonX should appear earlier than PersonY."}, {"input": "Context word: dropped. \nQuestion: When PersonX dropped his ice cream, PersonY giggled, so father gave _ a sympathetic look. \nAnswer: PersonX.", "output": "When PersonX dropped his ice cream in front of Usain Bolt who is the other person. _ gave a sympathetic look.", "explanation": "The problem here is that it involves using name of a real person \"Usain Bolt\". Do not use names of real people (e.g., Donald Trump, Putin, etc.) in your question."}, {"input": "Context Word: cakes. \nQuestion: The cakes were given to PersonX but not PersonY because _ had his birthday that day. \nAnswer: PersonX", "output": "The tasks were given to PersonX but not PersonY because _ had his birthday that day.", "explanation": "The problem here is that it changes the context word. Note that you must utilize the given context word while writing the question."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Commonsense -> Concepts and Relations -> Social Commonsense", "Commonsense -> Concepts and Relations -> Physical Commonsense"], "Instance": {"id": "task035-bdf92efc1ea14b83a90afa360b98a1e4", "input": "Context Word: store. \nQuestion: PersonX went to the store for PersonY since _ is currently the healthy one at home. \nAnswer: PersonX", "output": ["PersonX went to the store for PersonY since _ is currently the sick one at home."]}, "Instance License": ["Apache 2.0"], "prediction": "PersonX went to the store for PersonY since _ is currently the healthy one at home."}
+{"id": "task035-3175e87d09724602b2479dd3cb088b41", "Task": "task035_winogrande_question_modification_person", "Contributors": "['Swaroop Mishra', 'Daniel Khashabi']", "Source": ["winogrande"], "URL": ["https://leaderboard.allenai.org/winogrande/submissions/about"], "Categories": ["Question Rewriting"], "Reasoning": ["Commonsense Reasoning"], "Definition": ["You're given a fill-in-the-blank question where the answer is PersonX. You need to minimally change the given question so that the answer flips to PersonY. This task typically involves replacing one word i.e., the 'trigger word' with its antonym (e.g., changing from \"sympathetic\" to \"stern\"). You should not change any content in the given question beyond a word or two i.e. the trigger word/phrase. PersonX and PersonY should not be equally likely to fill the blank. For your question, PersonY should be a well-agreed answer to fill in the blank. Your generations should NOT contain potentially explicit, offensive, or adult content. Do not use the names of real people or generic names (e.g., Donald Trump, John Doe, etc.) in your question. Avoid repeating the same style or phrase in generating your modified question e.g. this task can be always solved using a simple negation i.e. by adding not, never, etc. Instead, try to increase the word diversity. Your question must contain at least 15 and at most 30 words. Your question must have at least 70% overlapping words with the given question. You must utilize the given context word while writing the question. Your question must contain only one blank. Make sure that PersonX and PersonY have the same gender. In your question, PersonX and PersonY should be used only ONCE and PersonX should appear earlier than PersonY. Although there are many correct answers, you only need to write one of them."], "Positive Examples": [{"input": "Context word: upset. \nQuestion: PersonX yelled at PersonY because _ was so upset about the news. \nAnswer: PersonX.", "output": "PersonX comforted at PersonY because _ was so upset about the news.", "explanation": "On replacing the trigger word \"yelled\" with its antonym \"comforted\", the answer flips to PersonY which is as per the given instruction. So, this is a valid question."}, {"input": "Context word: library. \nQuestion: PersonX asked PersonY what time the library closes, because _ had forgotten. \nAnswer: PersonX.", "output": "PersonX asked PersonY what time the library closes, but _ had forgotten.", "explanation": "On replacing the trigger word \"because\" with \"but\", the answer flips to PersonY. This is a valid question, as it follows exactly the given instruction."}, {"input": "Context word: door. \nQuestion: PersonX knocked on PersonY's door, but there was no answer. _ was disappointed. \nAnswer: PersonX.", "output": "PersonX knocked on PersonY's door, but there was no answer. _ was out.", "explanation": "On replacing the trigger word \"disappointed\" with \"out\", the answer flips to PersonY. This is a valid question, as it follows exactly the given instruction."}, {"input": "Context word: step. \nQuestion: PersonX was always ahead of PersonY, as _ walked with a quick step. \nAnswer: PersonX.", "output": "PersonX was always behind PersonY, as _ walked with a quick step .", "explanation": "Here, replacing the trigger word \"ahead\" with its antonym \"behind\" flips answer to PersonY which is as per the given instruction. So, this is a valid question."}, {"input": "Context word: dropped. \nQuestion: When PersonX dropped his ice cream, PersonY giggled, so father gave _ a sympathetic look. \nAnswer: PersonX.", "output": "When PersonX dropped his ice cream, PersonY giggled, so father gave _ a stern look.", "explanation": "Here, replacing the trigger word \"sympathetic\" with \"stern\" flips answer to PersonY. This is a valid question, as it follows exactly the given instruction."}], "Negative Examples": [{"input": "Context word: upset. \nQuestion: PersonX yelled at PersonY because _ was so upset about the news. \nAnswer: PersonX.", "output": "PersonX yelled at PersonY when PersonX tried to kiss _.", "explanation": "The generated question contains inapprorpriate content. Note that, your generations should NOT contain potentially explicit, offensive, or adult content."}, {"input": "Context word: library. \nQuestion: PersonX asked PersonY what time the library closes, because _ had forgotten. \nAnswer: PersonX.", "output": "PersonX asked PersonY what time the library closes, because _ had reminded.", "explanation": "Even though the word \"forgotten\" is replaced by its antonym \"reminded\", the question does not makes sense."}, {"input": "Context word: door. \nQuestion: PersonX knocked on PersonY's door, but there was no answer. _ was disappointed. \nAnswer: PersonX.", "output": "PersonX knocked on PersonY's door, but there was no answer from PersonY. _ was out.", "explanation": "Here PersonY has been used more than once in the question. Note that In your question, PersonX and PersonY should be used only ONCE."}, {"input": "Context word: step. \nQuestion: PersonX was always ahead of PersonY, as _ walked with a quick step. \nAnswer: PersonX.", "output": "PersonY was always ahead of PersonX, as _ walked with a quick step .", "explanation": "Here, the issue is that the usage order of PersonX and PersonY has been changed in the generated question. Remember that, for a question to be valid, PersonX should appear earlier than PersonY."}, {"input": "Context word: dropped. \nQuestion: When PersonX dropped his ice cream, PersonY giggled, so father gave _ a sympathetic look. \nAnswer: PersonX.", "output": "When PersonX dropped his ice cream in front of Usain Bolt who is the other person. _ gave a sympathetic look.", "explanation": "The problem here is that it involves using name of a real person \"Usain Bolt\". Do not use names of real people (e.g., Donald Trump, Putin, etc.) in your question."}, {"input": "Context Word: cakes. \nQuestion: The cakes were given to PersonX but not PersonY because _ had his birthday that day. \nAnswer: PersonX", "output": "The tasks were given to PersonX but not PersonY because _ had his birthday that day.", "explanation": "The problem here is that it changes the context word. Note that you must utilize the given context word while writing the question."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Commonsense -> Concepts and Relations -> Social Commonsense", "Commonsense -> Concepts and Relations -> Physical Commonsense"], "Instance": {"id": "task035-3175e87d09724602b2479dd3cb088b41", "input": "Context Word: humility. \nQuestion: Although PersonX was overall a nicer person than PersonY, _ did not practice humility very regularlly. \nAnswer: PersonX", "output": ["Although PersonX was overall a nicer person than PersonY, _ often did practice humility very regularlly."]}, "Instance License": ["Apache 2.0"], "prediction": "PersonX was overall a nicer person than PersonY, _ did not practice humility very regularlylly."}
+{"id": "task035-d4c6176ecbcb419bbdabca6ff50cefe2", "Task": "task035_winogrande_question_modification_person", "Contributors": "['Swaroop Mishra', 'Daniel Khashabi']", "Source": ["winogrande"], "URL": ["https://leaderboard.allenai.org/winogrande/submissions/about"], "Categories": ["Question Rewriting"], "Reasoning": ["Commonsense Reasoning"], "Definition": ["You're given a fill-in-the-blank question where the answer is PersonX. You need to minimally change the given question so that the answer flips to PersonY. This task typically involves replacing one word i.e., the 'trigger word' with its antonym (e.g., changing from \"sympathetic\" to \"stern\"). You should not change any content in the given question beyond a word or two i.e. the trigger word/phrase. PersonX and PersonY should not be equally likely to fill the blank. For your question, PersonY should be a well-agreed answer to fill in the blank. Your generations should NOT contain potentially explicit, offensive, or adult content. Do not use the names of real people or generic names (e.g., Donald Trump, John Doe, etc.) in your question. Avoid repeating the same style or phrase in generating your modified question e.g. this task can be always solved using a simple negation i.e. by adding not, never, etc. Instead, try to increase the word diversity. Your question must contain at least 15 and at most 30 words. Your question must have at least 70% overlapping words with the given question. You must utilize the given context word while writing the question. Your question must contain only one blank. Make sure that PersonX and PersonY have the same gender. In your question, PersonX and PersonY should be used only ONCE and PersonX should appear earlier than PersonY. Although there are many correct answers, you only need to write one of them."], "Positive Examples": [{"input": "Context word: upset. \nQuestion: PersonX yelled at PersonY because _ was so upset about the news. \nAnswer: PersonX.", "output": "PersonX comforted at PersonY because _ was so upset about the news.", "explanation": "On replacing the trigger word \"yelled\" with its antonym \"comforted\", the answer flips to PersonY which is as per the given instruction. So, this is a valid question."}, {"input": "Context word: library. \nQuestion: PersonX asked PersonY what time the library closes, because _ had forgotten. \nAnswer: PersonX.", "output": "PersonX asked PersonY what time the library closes, but _ had forgotten.", "explanation": "On replacing the trigger word \"because\" with \"but\", the answer flips to PersonY. This is a valid question, as it follows exactly the given instruction."}, {"input": "Context word: door. \nQuestion: PersonX knocked on PersonY's door, but there was no answer. _ was disappointed. \nAnswer: PersonX.", "output": "PersonX knocked on PersonY's door, but there was no answer. _ was out.", "explanation": "On replacing the trigger word \"disappointed\" with \"out\", the answer flips to PersonY. This is a valid question, as it follows exactly the given instruction."}, {"input": "Context word: step. \nQuestion: PersonX was always ahead of PersonY, as _ walked with a quick step. \nAnswer: PersonX.", "output": "PersonX was always behind PersonY, as _ walked with a quick step .", "explanation": "Here, replacing the trigger word \"ahead\" with its antonym \"behind\" flips answer to PersonY which is as per the given instruction. So, this is a valid question."}, {"input": "Context word: dropped. \nQuestion: When PersonX dropped his ice cream, PersonY giggled, so father gave _ a sympathetic look. \nAnswer: PersonX.", "output": "When PersonX dropped his ice cream, PersonY giggled, so father gave _ a stern look.", "explanation": "Here, replacing the trigger word \"sympathetic\" with \"stern\" flips answer to PersonY. This is a valid question, as it follows exactly the given instruction."}], "Negative Examples": [{"input": "Context word: upset. \nQuestion: PersonX yelled at PersonY because _ was so upset about the news. \nAnswer: PersonX.", "output": "PersonX yelled at PersonY when PersonX tried to kiss _.", "explanation": "The generated question contains inapprorpriate content. Note that, your generations should NOT contain potentially explicit, offensive, or adult content."}, {"input": "Context word: library. \nQuestion: PersonX asked PersonY what time the library closes, because _ had forgotten. \nAnswer: PersonX.", "output": "PersonX asked PersonY what time the library closes, because _ had reminded.", "explanation": "Even though the word \"forgotten\" is replaced by its antonym \"reminded\", the question does not makes sense."}, {"input": "Context word: door. \nQuestion: PersonX knocked on PersonY's door, but there was no answer. _ was disappointed. \nAnswer: PersonX.", "output": "PersonX knocked on PersonY's door, but there was no answer from PersonY. _ was out.", "explanation": "Here PersonY has been used more than once in the question. Note that In your question, PersonX and PersonY should be used only ONCE."}, {"input": "Context word: step. \nQuestion: PersonX was always ahead of PersonY, as _ walked with a quick step. \nAnswer: PersonX.", "output": "PersonY was always ahead of PersonX, as _ walked with a quick step .", "explanation": "Here, the issue is that the usage order of PersonX and PersonY has been changed in the generated question. Remember that, for a question to be valid, PersonX should appear earlier than PersonY."}, {"input": "Context word: dropped. \nQuestion: When PersonX dropped his ice cream, PersonY giggled, so father gave _ a sympathetic look. \nAnswer: PersonX.", "output": "When PersonX dropped his ice cream in front of Usain Bolt who is the other person. _ gave a sympathetic look.", "explanation": "The problem here is that it involves using name of a real person \"Usain Bolt\". Do not use names of real people (e.g., Donald Trump, Putin, etc.) in your question."}, {"input": "Context Word: cakes. \nQuestion: The cakes were given to PersonX but not PersonY because _ had his birthday that day. \nAnswer: PersonX", "output": "The tasks were given to PersonX but not PersonY because _ had his birthday that day.", "explanation": "The problem here is that it changes the context word. Note that you must utilize the given context word while writing the question."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Commonsense -> Concepts and Relations -> Social Commonsense", "Commonsense -> Concepts and Relations -> Physical Commonsense"], "Instance": {"id": "task035-d4c6176ecbcb419bbdabca6ff50cefe2", "input": "Context Word: docent. \nQuestion: PersonX was a better museum docent than PersonY because _ always read up on the new exhibits. \nAnswer: PersonX", "output": ["PersonX was a better museum docent than PersonY because _ never read up on the new exhibits."]}, "Instance License": ["Apache 2.0"], "prediction": "PersonX was a better museum docent than PersonY because _ always read up on the new exhibits."}
+{"id": "task035-97e0d645cb5649c290fbdbe4a78b346b", "Task": "task035_winogrande_question_modification_person", "Contributors": "['Swaroop Mishra', 'Daniel Khashabi']", "Source": ["winogrande"], "URL": ["https://leaderboard.allenai.org/winogrande/submissions/about"], "Categories": ["Question Rewriting"], "Reasoning": ["Commonsense Reasoning"], "Definition": ["You're given a fill-in-the-blank question where the answer is PersonX. You need to minimally change the given question so that the answer flips to PersonY. This task typically involves replacing one word i.e., the 'trigger word' with its antonym (e.g., changing from \"sympathetic\" to \"stern\"). You should not change any content in the given question beyond a word or two i.e. the trigger word/phrase. PersonX and PersonY should not be equally likely to fill the blank. For your question, PersonY should be a well-agreed answer to fill in the blank. Your generations should NOT contain potentially explicit, offensive, or adult content. Do not use the names of real people or generic names (e.g., Donald Trump, John Doe, etc.) in your question. Avoid repeating the same style or phrase in generating your modified question e.g. this task can be always solved using a simple negation i.e. by adding not, never, etc. Instead, try to increase the word diversity. Your question must contain at least 15 and at most 30 words. Your question must have at least 70% overlapping words with the given question. You must utilize the given context word while writing the question. Your question must contain only one blank. Make sure that PersonX and PersonY have the same gender. In your question, PersonX and PersonY should be used only ONCE and PersonX should appear earlier than PersonY. Although there are many correct answers, you only need to write one of them."], "Positive Examples": [{"input": "Context word: upset. \nQuestion: PersonX yelled at PersonY because _ was so upset about the news. \nAnswer: PersonX.", "output": "PersonX comforted at PersonY because _ was so upset about the news.", "explanation": "On replacing the trigger word \"yelled\" with its antonym \"comforted\", the answer flips to PersonY which is as per the given instruction. So, this is a valid question."}, {"input": "Context word: library. \nQuestion: PersonX asked PersonY what time the library closes, because _ had forgotten. \nAnswer: PersonX.", "output": "PersonX asked PersonY what time the library closes, but _ had forgotten.", "explanation": "On replacing the trigger word \"because\" with \"but\", the answer flips to PersonY. This is a valid question, as it follows exactly the given instruction."}, {"input": "Context word: door. \nQuestion: PersonX knocked on PersonY's door, but there was no answer. _ was disappointed. \nAnswer: PersonX.", "output": "PersonX knocked on PersonY's door, but there was no answer. _ was out.", "explanation": "On replacing the trigger word \"disappointed\" with \"out\", the answer flips to PersonY. This is a valid question, as it follows exactly the given instruction."}, {"input": "Context word: step. \nQuestion: PersonX was always ahead of PersonY, as _ walked with a quick step. \nAnswer: PersonX.", "output": "PersonX was always behind PersonY, as _ walked with a quick step .", "explanation": "Here, replacing the trigger word \"ahead\" with its antonym \"behind\" flips answer to PersonY which is as per the given instruction. So, this is a valid question."}, {"input": "Context word: dropped. \nQuestion: When PersonX dropped his ice cream, PersonY giggled, so father gave _ a sympathetic look. \nAnswer: PersonX.", "output": "When PersonX dropped his ice cream, PersonY giggled, so father gave _ a stern look.", "explanation": "Here, replacing the trigger word \"sympathetic\" with \"stern\" flips answer to PersonY. This is a valid question, as it follows exactly the given instruction."}], "Negative Examples": [{"input": "Context word: upset. \nQuestion: PersonX yelled at PersonY because _ was so upset about the news. \nAnswer: PersonX.", "output": "PersonX yelled at PersonY when PersonX tried to kiss _.", "explanation": "The generated question contains inapprorpriate content. Note that, your generations should NOT contain potentially explicit, offensive, or adult content."}, {"input": "Context word: library. \nQuestion: PersonX asked PersonY what time the library closes, because _ had forgotten. \nAnswer: PersonX.", "output": "PersonX asked PersonY what time the library closes, because _ had reminded.", "explanation": "Even though the word \"forgotten\" is replaced by its antonym \"reminded\", the question does not makes sense."}, {"input": "Context word: door. \nQuestion: PersonX knocked on PersonY's door, but there was no answer. _ was disappointed. \nAnswer: PersonX.", "output": "PersonX knocked on PersonY's door, but there was no answer from PersonY. _ was out.", "explanation": "Here PersonY has been used more than once in the question. Note that In your question, PersonX and PersonY should be used only ONCE."}, {"input": "Context word: step. \nQuestion: PersonX was always ahead of PersonY, as _ walked with a quick step. \nAnswer: PersonX.", "output": "PersonY was always ahead of PersonX, as _ walked with a quick step .", "explanation": "Here, the issue is that the usage order of PersonX and PersonY has been changed in the generated question. Remember that, for a question to be valid, PersonX should appear earlier than PersonY."}, {"input": "Context word: dropped. \nQuestion: When PersonX dropped his ice cream, PersonY giggled, so father gave _ a sympathetic look. \nAnswer: PersonX.", "output": "When PersonX dropped his ice cream in front of Usain Bolt who is the other person. _ gave a sympathetic look.", "explanation": "The problem here is that it involves using name of a real person \"Usain Bolt\". Do not use names of real people (e.g., Donald Trump, Putin, etc.) in your question."}, {"input": "Context Word: cakes. \nQuestion: The cakes were given to PersonX but not PersonY because _ had his birthday that day. \nAnswer: PersonX", "output": "The tasks were given to PersonX but not PersonY because _ had his birthday that day.", "explanation": "The problem here is that it changes the context word. Note that you must utilize the given context word while writing the question."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Commonsense -> Concepts and Relations -> Social Commonsense", "Commonsense -> Concepts and Relations -> Physical Commonsense"], "Instance": {"id": "task035-97e0d645cb5649c290fbdbe4a78b346b", "input": "Context Word: fabrics. \nQuestion: PersonX did not spend a lot of time choosing fabrics unlike PersonY because _ had little time to shop. \nAnswer: PersonX", "output": ["PersonX did not spend a lot of time choosing fabrics unlike PersonY because _ had plenty time to shop."]}, "Instance License": ["Apache 2.0"], "prediction": "PersonX did not spend a lot of time choosing fabrics like PersonY because _ had little time to shop."}
+{"id": "task035-56d5e301837d4bdb8fd6729b5a20e68f", "Task": "task035_winogrande_question_modification_person", "Contributors": "['Swaroop Mishra', 'Daniel Khashabi']", "Source": ["winogrande"], "URL": ["https://leaderboard.allenai.org/winogrande/submissions/about"], "Categories": ["Question Rewriting"], "Reasoning": ["Commonsense Reasoning"], "Definition": ["You're given a fill-in-the-blank question where the answer is PersonX. You need to minimally change the given question so that the answer flips to PersonY. This task typically involves replacing one word i.e., the 'trigger word' with its antonym (e.g., changing from \"sympathetic\" to \"stern\"). You should not change any content in the given question beyond a word or two i.e. the trigger word/phrase. PersonX and PersonY should not be equally likely to fill the blank. For your question, PersonY should be a well-agreed answer to fill in the blank. Your generations should NOT contain potentially explicit, offensive, or adult content. Do not use the names of real people or generic names (e.g., Donald Trump, John Doe, etc.) in your question. Avoid repeating the same style or phrase in generating your modified question e.g. this task can be always solved using a simple negation i.e. by adding not, never, etc. Instead, try to increase the word diversity. Your question must contain at least 15 and at most 30 words. Your question must have at least 70% overlapping words with the given question. You must utilize the given context word while writing the question. Your question must contain only one blank. Make sure that PersonX and PersonY have the same gender. In your question, PersonX and PersonY should be used only ONCE and PersonX should appear earlier than PersonY. Although there are many correct answers, you only need to write one of them."], "Positive Examples": [{"input": "Context word: upset. \nQuestion: PersonX yelled at PersonY because _ was so upset about the news. \nAnswer: PersonX.", "output": "PersonX comforted at PersonY because _ was so upset about the news.", "explanation": "On replacing the trigger word \"yelled\" with its antonym \"comforted\", the answer flips to PersonY which is as per the given instruction. So, this is a valid question."}, {"input": "Context word: library. \nQuestion: PersonX asked PersonY what time the library closes, because _ had forgotten. \nAnswer: PersonX.", "output": "PersonX asked PersonY what time the library closes, but _ had forgotten.", "explanation": "On replacing the trigger word \"because\" with \"but\", the answer flips to PersonY. This is a valid question, as it follows exactly the given instruction."}, {"input": "Context word: door. \nQuestion: PersonX knocked on PersonY's door, but there was no answer. _ was disappointed. \nAnswer: PersonX.", "output": "PersonX knocked on PersonY's door, but there was no answer. _ was out.", "explanation": "On replacing the trigger word \"disappointed\" with \"out\", the answer flips to PersonY. This is a valid question, as it follows exactly the given instruction."}, {"input": "Context word: step. \nQuestion: PersonX was always ahead of PersonY, as _ walked with a quick step. \nAnswer: PersonX.", "output": "PersonX was always behind PersonY, as _ walked with a quick step .", "explanation": "Here, replacing the trigger word \"ahead\" with its antonym \"behind\" flips answer to PersonY which is as per the given instruction. So, this is a valid question."}, {"input": "Context word: dropped. \nQuestion: When PersonX dropped his ice cream, PersonY giggled, so father gave _ a sympathetic look. \nAnswer: PersonX.", "output": "When PersonX dropped his ice cream, PersonY giggled, so father gave _ a stern look.", "explanation": "Here, replacing the trigger word \"sympathetic\" with \"stern\" flips answer to PersonY. This is a valid question, as it follows exactly the given instruction."}], "Negative Examples": [{"input": "Context word: upset. \nQuestion: PersonX yelled at PersonY because _ was so upset about the news. \nAnswer: PersonX.", "output": "PersonX yelled at PersonY when PersonX tried to kiss _.", "explanation": "The generated question contains inapprorpriate content. Note that, your generations should NOT contain potentially explicit, offensive, or adult content."}, {"input": "Context word: library. \nQuestion: PersonX asked PersonY what time the library closes, because _ had forgotten. \nAnswer: PersonX.", "output": "PersonX asked PersonY what time the library closes, because _ had reminded.", "explanation": "Even though the word \"forgotten\" is replaced by its antonym \"reminded\", the question does not makes sense."}, {"input": "Context word: door. \nQuestion: PersonX knocked on PersonY's door, but there was no answer. _ was disappointed. \nAnswer: PersonX.", "output": "PersonX knocked on PersonY's door, but there was no answer from PersonY. _ was out.", "explanation": "Here PersonY has been used more than once in the question. Note that In your question, PersonX and PersonY should be used only ONCE."}, {"input": "Context word: step. \nQuestion: PersonX was always ahead of PersonY, as _ walked with a quick step. \nAnswer: PersonX.", "output": "PersonY was always ahead of PersonX, as _ walked with a quick step .", "explanation": "Here, the issue is that the usage order of PersonX and PersonY has been changed in the generated question. Remember that, for a question to be valid, PersonX should appear earlier than PersonY."}, {"input": "Context word: dropped. \nQuestion: When PersonX dropped his ice cream, PersonY giggled, so father gave _ a sympathetic look. \nAnswer: PersonX.", "output": "When PersonX dropped his ice cream in front of Usain Bolt who is the other person. _ gave a sympathetic look.", "explanation": "The problem here is that it involves using name of a real person \"Usain Bolt\". Do not use names of real people (e.g., Donald Trump, Putin, etc.) in your question."}, {"input": "Context Word: cakes. \nQuestion: The cakes were given to PersonX but not PersonY because _ had his birthday that day. \nAnswer: PersonX", "output": "The tasks were given to PersonX but not PersonY because _ had his birthday that day.", "explanation": "The problem here is that it changes the context word. Note that you must utilize the given context word while writing the question."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Commonsense -> Concepts and Relations -> Social Commonsense", "Commonsense -> Concepts and Relations -> Physical Commonsense"], "Instance": {"id": "task035-56d5e301837d4bdb8fd6729b5a20e68f", "input": "Context Word: designer. \nQuestion: PersonX had a much better style than PersonY , since _ had better taste in designer clothes. \nAnswer: PersonX", "output": ["PersonX had a much better style than PersonY , since _ had no taste in designer clothes."]}, "Instance License": ["Apache 2.0"], "prediction": "PersonX had a much better style than PersonY, since _ had better taste in designer clothes."}
+{"id": "task569-d0e3f5767b0a48f4a4846423dec0cfce", "Task": "task569_recipe_nlg_text_generation", "Contributors": "['Bhavya Sri Aravapalli']", "Source": ["recipe_nlg"], "URL": ["https://huggingface.co/datasets/recipe_nlg"], "Categories": ["Title Generation"], "Reasoning": ["Reasoning on Actions"], "Definition": ["In this task, you have to generate the title of the recipe given its required ingredients and directions."], "Positive Examples": [{"input": "ingredients: '1 cup minced onion', '1 1/2 tablespoons lemon juice', '3/4 teaspoon Hungarian paprika', '3/4 teaspoon ground cayenne pepper', '1/4 teaspoon salt', <sep> directions: 'Rinse onions in sieve under cold running water; drain.', 'Mix together ingredients in a small bowl; allow flavors to meld over 1 hour period before serving.', 'Serve as table condiment with Indian foods, samosas, pakoras, along with other chutneys.'", "output": "Indian Hot Onion Relish", "explanation": "By knowing the ingredients and its recipe, the title of the dish is predicted correctly."}, {"input": "ingredients: '2 sheets frozen puff pastry, thawed', '4 oz semi-dried tomatoes, chopped', '3 oz seeded black olives', '4 oz soft goat cheese, crumbled', '1/2  red onion, sliced', '1/4 cup fresh torn basil leaves', '1  egg, beaten lightly', <sep> directions: 'Preheat oven to 400\\u00b0F. Line a baking tray with parchment paper.', 'Cut a 6 x 9 1/2 inch rectangle from 1 sheet of puff pastry. Place on baking tray and top with tomatoes, olives, cheese, onion and basil leaves.', 'Cut a 7 x 9 1/2 inch rectangle from remaining sheet of puff pastry. Score in a diamond pattern then place on top of filling, pressing edges to seal. Brush with egg then bake for 20 mins.'", "output": "Tomato, Olive And Goat Cheese Tart", "explanation": "Given required ingredients and its recipe, the title of the recipe was generated correctly."}], "Negative Examples": [{"input": "ingredients: '4 1/2 cups seedless watermelon, cubed', '1 1/2 cups strawberry sorbet', '1 large banana, frozen', '1 1/2 cups ice (optional)', <sep> directions: 'Combine watermelon, sorbet, banana (& ice, if using) in a blender & process until smooth.', 'Pour into 4 glasses & enjoy!'", "output": "Hush Puppies", "explanation": "Given ingredients and directions, the title is generated incorrectly."}, {"input": "ingredients: '2 cup flour', '2 1/2 tsp lawrys season salt', '1 tsp onion powder', '1/2 tbsp paprika', '1/4 tsp black pepper', '2 eggs beaten', '1/4 cup water', 'pinch black pepper', 'pinch garlic powder', 'pinch dried parsley', <sep> directions: 'In a large bowl add flour season salt onion powder paprika and black pepper and set aside', 'In another bowl add eggs water pinch of pepper parsley and garlic powder and mix together', 'You can use any kind of chicken you want ..', 'I used chicken drumsticks that I had boiled in seasoned water prior to frying ...just dip your chicken in the egg mixture and then in to flour ...you can repeat the egg and flour a second time depending if you like it with a little extra batter ...', 'I do personally ...fry in hot oil until golden browned ...dry on some paper towel and enjoy'", "output": "Watermelon Strawberry Smoothie", "explanation": "Given ingredients and directions, the title is generated incorrectly."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Food"], "Instance": {"id": "task569-d0e3f5767b0a48f4a4846423dec0cfce", "input": "ingredients:  '2 eggs', '1/4 cup canola oil', '1 cup packed brown sugar', '1/2 cup applesauce', '1 1/2 cups milk (whichever kind you like)', '2 teaspoons vanilla extract', '1/2 teaspoon salt', '1 tablespoon ground cinnamon', '3 cups old fashioned oats', '2 teaspoons baking powder', '1 dash Anjou pear, favorite toppings (fruit, nuts, chocolate chips, etc)',<sep> directions: 'Preheat oven to 350. Line muffin tin with paper or paper/foil muffin liners. (Don't skip the muffin liners for this one!).', 'In large bowl, whisk eggs, oil, and brown sugar until sugar is dissolved. Add the applesauce, milk, vanilla, salt, and cinnamon. Whisk until well combined. Stir in the oats and baking powder.', 'Fill muffin tin with 1/4 cup of oat mixture in each muffin cup. Add favorite toppings. Push toppings down into the oat mixture with a spoon.', 'Bake for 30 minutes Let cool for 5 mins before eating. Store in an airtight container or freeze in a zip top storage bag.'", "output": ["To Go Baked Oatmeal"]}, "Instance License": ["Dedicated Terms and Conditions (https://recipenlg.cs.put.poznan.pl/dataset)"], "prediction": "Apricot, Pear, and Brown Sugar Oatmeal"}
+{"id": "task569-f6005366b41d4a1baaf80784c57be7ad", "Task": "task569_recipe_nlg_text_generation", "Contributors": "['Bhavya Sri Aravapalli']", "Source": ["recipe_nlg"], "URL": ["https://huggingface.co/datasets/recipe_nlg"], "Categories": ["Title Generation"], "Reasoning": ["Reasoning on Actions"], "Definition": ["In this task, you have to generate the title of the recipe given its required ingredients and directions."], "Positive Examples": [{"input": "ingredients: '1 cup minced onion', '1 1/2 tablespoons lemon juice', '3/4 teaspoon Hungarian paprika', '3/4 teaspoon ground cayenne pepper', '1/4 teaspoon salt', <sep> directions: 'Rinse onions in sieve under cold running water; drain.', 'Mix together ingredients in a small bowl; allow flavors to meld over 1 hour period before serving.', 'Serve as table condiment with Indian foods, samosas, pakoras, along with other chutneys.'", "output": "Indian Hot Onion Relish", "explanation": "By knowing the ingredients and its recipe, the title of the dish is predicted correctly."}, {"input": "ingredients: '2 sheets frozen puff pastry, thawed', '4 oz semi-dried tomatoes, chopped', '3 oz seeded black olives', '4 oz soft goat cheese, crumbled', '1/2  red onion, sliced', '1/4 cup fresh torn basil leaves', '1  egg, beaten lightly', <sep> directions: 'Preheat oven to 400\\u00b0F. Line a baking tray with parchment paper.', 'Cut a 6 x 9 1/2 inch rectangle from 1 sheet of puff pastry. Place on baking tray and top with tomatoes, olives, cheese, onion and basil leaves.', 'Cut a 7 x 9 1/2 inch rectangle from remaining sheet of puff pastry. Score in a diamond pattern then place on top of filling, pressing edges to seal. Brush with egg then bake for 20 mins.'", "output": "Tomato, Olive And Goat Cheese Tart", "explanation": "Given required ingredients and its recipe, the title of the recipe was generated correctly."}], "Negative Examples": [{"input": "ingredients: '4 1/2 cups seedless watermelon, cubed', '1 1/2 cups strawberry sorbet', '1 large banana, frozen', '1 1/2 cups ice (optional)', <sep> directions: 'Combine watermelon, sorbet, banana (& ice, if using) in a blender & process until smooth.', 'Pour into 4 glasses & enjoy!'", "output": "Hush Puppies", "explanation": "Given ingredients and directions, the title is generated incorrectly."}, {"input": "ingredients: '2 cup flour', '2 1/2 tsp lawrys season salt', '1 tsp onion powder', '1/2 tbsp paprika', '1/4 tsp black pepper', '2 eggs beaten', '1/4 cup water', 'pinch black pepper', 'pinch garlic powder', 'pinch dried parsley', <sep> directions: 'In a large bowl add flour season salt onion powder paprika and black pepper and set aside', 'In another bowl add eggs water pinch of pepper parsley and garlic powder and mix together', 'You can use any kind of chicken you want ..', 'I used chicken drumsticks that I had boiled in seasoned water prior to frying ...just dip your chicken in the egg mixture and then in to flour ...you can repeat the egg and flour a second time depending if you like it with a little extra batter ...', 'I do personally ...fry in hot oil until golden browned ...dry on some paper towel and enjoy'", "output": "Watermelon Strawberry Smoothie", "explanation": "Given ingredients and directions, the title is generated incorrectly."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Food"], "Instance": {"id": "task569-f6005366b41d4a1baaf80784c57be7ad", "input": "ingredients:  '1 (14 ounce) can sweetened condensed milk, divided', '1 ounce unsweetened chocolate square', '1/2 teaspoon almond extract, divided', '1 already baked pie crust (9inch)', '1 (10 ounce) jar maraschino cherries, drained', '8 ounces cream cheese, softened', '1 cup cold water', '1 (3 1/2 ounce) box instant vanilla pudding', '1 cup whipping cream, whipped', '1/2 cup toasted almond, chopped',<sep> directions: 'Over low heat, stir 1/2 cup milk and chocolate until smooth.', 'Stir in 1/4 t extract.', 'Pour into crust.', 'Save 8 of the cherries for garnish.', 'Chop the rest of the cherries.', 'In bowl, beat cream cheese until fluffy.', 'Slowly add water and remaining milk.', 'Add the pudding mix and the remaining extract.', 'Mix well.', 'Fold in the whipped cream.', 'Stir in the chopped cherries, and almonds.', 'Pour over the chocolate in pie crust.', 'Chill.', 'Garnish with whole cherries.'", "output": ["Cherry Almond Mousse Pie"]}, "Instance License": ["Dedicated Terms and Conditions (https://recipenlg.cs.put.poznan.pl/dataset)"], "prediction": "Chocolate and Cherry Pie"}
+{"id": "task569-9b4f328ed4d843488022db3adcd4dc4f", "Task": "task569_recipe_nlg_text_generation", "Contributors": "['Bhavya Sri Aravapalli']", "Source": ["recipe_nlg"], "URL": ["https://huggingface.co/datasets/recipe_nlg"], "Categories": ["Title Generation"], "Reasoning": ["Reasoning on Actions"], "Definition": ["In this task, you have to generate the title of the recipe given its required ingredients and directions."], "Positive Examples": [{"input": "ingredients: '1 cup minced onion', '1 1/2 tablespoons lemon juice', '3/4 teaspoon Hungarian paprika', '3/4 teaspoon ground cayenne pepper', '1/4 teaspoon salt', <sep> directions: 'Rinse onions in sieve under cold running water; drain.', 'Mix together ingredients in a small bowl; allow flavors to meld over 1 hour period before serving.', 'Serve as table condiment with Indian foods, samosas, pakoras, along with other chutneys.'", "output": "Indian Hot Onion Relish", "explanation": "By knowing the ingredients and its recipe, the title of the dish is predicted correctly."}, {"input": "ingredients: '2 sheets frozen puff pastry, thawed', '4 oz semi-dried tomatoes, chopped', '3 oz seeded black olives', '4 oz soft goat cheese, crumbled', '1/2  red onion, sliced', '1/4 cup fresh torn basil leaves', '1  egg, beaten lightly', <sep> directions: 'Preheat oven to 400\\u00b0F. Line a baking tray with parchment paper.', 'Cut a 6 x 9 1/2 inch rectangle from 1 sheet of puff pastry. Place on baking tray and top with tomatoes, olives, cheese, onion and basil leaves.', 'Cut a 7 x 9 1/2 inch rectangle from remaining sheet of puff pastry. Score in a diamond pattern then place on top of filling, pressing edges to seal. Brush with egg then bake for 20 mins.'", "output": "Tomato, Olive And Goat Cheese Tart", "explanation": "Given required ingredients and its recipe, the title of the recipe was generated correctly."}], "Negative Examples": [{"input": "ingredients: '4 1/2 cups seedless watermelon, cubed', '1 1/2 cups strawberry sorbet', '1 large banana, frozen', '1 1/2 cups ice (optional)', <sep> directions: 'Combine watermelon, sorbet, banana (& ice, if using) in a blender & process until smooth.', 'Pour into 4 glasses & enjoy!'", "output": "Hush Puppies", "explanation": "Given ingredients and directions, the title is generated incorrectly."}, {"input": "ingredients: '2 cup flour', '2 1/2 tsp lawrys season salt', '1 tsp onion powder', '1/2 tbsp paprika', '1/4 tsp black pepper', '2 eggs beaten', '1/4 cup water', 'pinch black pepper', 'pinch garlic powder', 'pinch dried parsley', <sep> directions: 'In a large bowl add flour season salt onion powder paprika and black pepper and set aside', 'In another bowl add eggs water pinch of pepper parsley and garlic powder and mix together', 'You can use any kind of chicken you want ..', 'I used chicken drumsticks that I had boiled in seasoned water prior to frying ...just dip your chicken in the egg mixture and then in to flour ...you can repeat the egg and flour a second time depending if you like it with a little extra batter ...', 'I do personally ...fry in hot oil until golden browned ...dry on some paper towel and enjoy'", "output": "Watermelon Strawberry Smoothie", "explanation": "Given ingredients and directions, the title is generated incorrectly."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Food"], "Instance": {"id": "task569-9b4f328ed4d843488022db3adcd4dc4f", "input": "ingredients:  '1 can white corn, drained and rinsed', '2 cans black beans, drained and rinsed', '1 can diced tomato, drained and rinsed', '12 red onion, chopped', '1 (4 ounce) can green chilies, chopped', '34 cup white vinegar', '2 tablespoons olive oil', '8 cloves garlic, pressed', 'Tabasco sauce or hot sauce, to taste',<sep> directions: 'Mix all ingredients together in large bowl.', 'Cover and refrigerate overnight.'", "output": ["Garlic Black Bean & White Corn Salsa"]}, "Instance License": ["Dedicated Terms and Conditions (https://recipenlg.cs.put.poznan.pl/dataset)"], "prediction": "Black Bean, Corn, Tomato, Onion, Garlic, Tabasco"}
+{"id": "task569-aa383b537c99491aa1abce7957b52e6a", "Task": "task569_recipe_nlg_text_generation", "Contributors": "['Bhavya Sri Aravapalli']", "Source": ["recipe_nlg"], "URL": ["https://huggingface.co/datasets/recipe_nlg"], "Categories": ["Title Generation"], "Reasoning": ["Reasoning on Actions"], "Definition": ["In this task, you have to generate the title of the recipe given its required ingredients and directions."], "Positive Examples": [{"input": "ingredients: '1 cup minced onion', '1 1/2 tablespoons lemon juice', '3/4 teaspoon Hungarian paprika', '3/4 teaspoon ground cayenne pepper', '1/4 teaspoon salt', <sep> directions: 'Rinse onions in sieve under cold running water; drain.', 'Mix together ingredients in a small bowl; allow flavors to meld over 1 hour period before serving.', 'Serve as table condiment with Indian foods, samosas, pakoras, along with other chutneys.'", "output": "Indian Hot Onion Relish", "explanation": "By knowing the ingredients and its recipe, the title of the dish is predicted correctly."}, {"input": "ingredients: '2 sheets frozen puff pastry, thawed', '4 oz semi-dried tomatoes, chopped', '3 oz seeded black olives', '4 oz soft goat cheese, crumbled', '1/2  red onion, sliced', '1/4 cup fresh torn basil leaves', '1  egg, beaten lightly', <sep> directions: 'Preheat oven to 400\\u00b0F. Line a baking tray with parchment paper.', 'Cut a 6 x 9 1/2 inch rectangle from 1 sheet of puff pastry. Place on baking tray and top with tomatoes, olives, cheese, onion and basil leaves.', 'Cut a 7 x 9 1/2 inch rectangle from remaining sheet of puff pastry. Score in a diamond pattern then place on top of filling, pressing edges to seal. Brush with egg then bake for 20 mins.'", "output": "Tomato, Olive And Goat Cheese Tart", "explanation": "Given required ingredients and its recipe, the title of the recipe was generated correctly."}], "Negative Examples": [{"input": "ingredients: '4 1/2 cups seedless watermelon, cubed', '1 1/2 cups strawberry sorbet', '1 large banana, frozen', '1 1/2 cups ice (optional)', <sep> directions: 'Combine watermelon, sorbet, banana (& ice, if using) in a blender & process until smooth.', 'Pour into 4 glasses & enjoy!'", "output": "Hush Puppies", "explanation": "Given ingredients and directions, the title is generated incorrectly."}, {"input": "ingredients: '2 cup flour', '2 1/2 tsp lawrys season salt', '1 tsp onion powder', '1/2 tbsp paprika', '1/4 tsp black pepper', '2 eggs beaten', '1/4 cup water', 'pinch black pepper', 'pinch garlic powder', 'pinch dried parsley', <sep> directions: 'In a large bowl add flour season salt onion powder paprika and black pepper and set aside', 'In another bowl add eggs water pinch of pepper parsley and garlic powder and mix together', 'You can use any kind of chicken you want ..', 'I used chicken drumsticks that I had boiled in seasoned water prior to frying ...just dip your chicken in the egg mixture and then in to flour ...you can repeat the egg and flour a second time depending if you like it with a little extra batter ...', 'I do personally ...fry in hot oil until golden browned ...dry on some paper towel and enjoy'", "output": "Watermelon Strawberry Smoothie", "explanation": "Given ingredients and directions, the title is generated incorrectly."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Food"], "Instance": {"id": "task569-aa383b537c99491aa1abce7957b52e6a", "input": "ingredients:  'Cake', '2 cups flour', '1/2 teaspoon baking powder', '3/4 teaspoon baking soda', '1/2 teaspoon salt', '1/2 cup butter, softened', '1 1/2 cups sugar', '2 eggs, unbeaten', '1 teaspoon vanilla extract', '1/4 cup buttermilk or 1/4 cup sour milk', '1 cup mashed banana', 'Frosting', '1 lb powdered sugar (10X)', '1/2 cup cocoa', '1/4 teaspoon salt', '1/2 cup butter, softened', '3 -4 tablespoons milk', '1 teaspoon vanilla extract',<sep> directions: 'Cream together butter, sugar, eggs and vanilla on high speed of electric mixer for 1 1/2 minutes.', 'Add buttermilk.', 'Mix together flour, baking powder, baking soda and salt.', 'Add flour mixture alternately with mashed banana.', 'Beat only enough to blend, about 2 minutes.', 'Pour battered into 2 greased and floured 9 inch round cake pans and bake in preheated 350 degree (Fahrenheit) oven for 30 to 35 minutes.', 'Cool cake then prepare frosting.', 'Mix together powdered sugar, cocoa and salt.', 'Add gradually to butter, beating with electric mixer, adding just enough milk so that mixture is not stiff (If you add too much it will get too thin when you continue beating).', 'After all ingredients are blended, mix on high speed of your mixer for 3 to 4 minutes, carefully adding small amounts of milk if too thick.', 'Fill and frost cooled layers.'", "output": ["Banana Cake With Chocolate Frosting"]}, "Instance License": ["Dedicated Terms and Conditions (https://recipenlg.cs.put.poznan.pl/dataset)"], "prediction": "Cake"}
+{"id": "task569-01eebcaa1d444fb983bde762ae5243f0", "Task": "task569_recipe_nlg_text_generation", "Contributors": "['Bhavya Sri Aravapalli']", "Source": ["recipe_nlg"], "URL": ["https://huggingface.co/datasets/recipe_nlg"], "Categories": ["Title Generation"], "Reasoning": ["Reasoning on Actions"], "Definition": ["In this task, you have to generate the title of the recipe given its required ingredients and directions."], "Positive Examples": [{"input": "ingredients: '1 cup minced onion', '1 1/2 tablespoons lemon juice', '3/4 teaspoon Hungarian paprika', '3/4 teaspoon ground cayenne pepper', '1/4 teaspoon salt', <sep> directions: 'Rinse onions in sieve under cold running water; drain.', 'Mix together ingredients in a small bowl; allow flavors to meld over 1 hour period before serving.', 'Serve as table condiment with Indian foods, samosas, pakoras, along with other chutneys.'", "output": "Indian Hot Onion Relish", "explanation": "By knowing the ingredients and its recipe, the title of the dish is predicted correctly."}, {"input": "ingredients: '2 sheets frozen puff pastry, thawed', '4 oz semi-dried tomatoes, chopped', '3 oz seeded black olives', '4 oz soft goat cheese, crumbled', '1/2  red onion, sliced', '1/4 cup fresh torn basil leaves', '1  egg, beaten lightly', <sep> directions: 'Preheat oven to 400\\u00b0F. Line a baking tray with parchment paper.', 'Cut a 6 x 9 1/2 inch rectangle from 1 sheet of puff pastry. Place on baking tray and top with tomatoes, olives, cheese, onion and basil leaves.', 'Cut a 7 x 9 1/2 inch rectangle from remaining sheet of puff pastry. Score in a diamond pattern then place on top of filling, pressing edges to seal. Brush with egg then bake for 20 mins.'", "output": "Tomato, Olive And Goat Cheese Tart", "explanation": "Given required ingredients and its recipe, the title of the recipe was generated correctly."}], "Negative Examples": [{"input": "ingredients: '4 1/2 cups seedless watermelon, cubed', '1 1/2 cups strawberry sorbet', '1 large banana, frozen', '1 1/2 cups ice (optional)', <sep> directions: 'Combine watermelon, sorbet, banana (& ice, if using) in a blender & process until smooth.', 'Pour into 4 glasses & enjoy!'", "output": "Hush Puppies", "explanation": "Given ingredients and directions, the title is generated incorrectly."}, {"input": "ingredients: '2 cup flour', '2 1/2 tsp lawrys season salt', '1 tsp onion powder', '1/2 tbsp paprika', '1/4 tsp black pepper', '2 eggs beaten', '1/4 cup water', 'pinch black pepper', 'pinch garlic powder', 'pinch dried parsley', <sep> directions: 'In a large bowl add flour season salt onion powder paprika and black pepper and set aside', 'In another bowl add eggs water pinch of pepper parsley and garlic powder and mix together', 'You can use any kind of chicken you want ..', 'I used chicken drumsticks that I had boiled in seasoned water prior to frying ...just dip your chicken in the egg mixture and then in to flour ...you can repeat the egg and flour a second time depending if you like it with a little extra batter ...', 'I do personally ...fry in hot oil until golden browned ...dry on some paper towel and enjoy'", "output": "Watermelon Strawberry Smoothie", "explanation": "Given ingredients and directions, the title is generated incorrectly."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Food"], "Instance": {"id": "task569-01eebcaa1d444fb983bde762ae5243f0", "input": "ingredients:  '2 sticks margarine', '1/2 c. sugar', '1 (3 oz.) pkg. cream cheese', '2 c. flour', '1/2 tsp. salt',<sep> directions: 'Combine all ingredients, mixing well.', 'Make into balls the size of walnuts.', 'Flatten with fork a little and bake in 350\u00b0 oven about 10 to 12 minutes.'", "output": ["Cream Cheese Cookies"]}, "Instance License": ["Dedicated Terms and Conditions (https://recipenlg.cs.put.poznan.pl/dataset)"], "prediction": "Buttermilk Cookies"}
+{"id": "task391-1bf1e0c1b76b479f870e2c2c81bc78d0", "Task": "task391_causal_relationship", "Contributors": "['Pegah Alipoormolabashi']", "Source": ["cod3s"], "URL": ["https://aclanthology.org/2020.emnlp-main.421.pdf"], "Categories": ["Cause Effect Classification"], "Reasoning": ["Causal Reasoning", "Textual Entailment"], "Definition": ["In this task, you will be given two sentences separated by \", so\". You should decide whether the first sentence can be the cause of the second sentence. If you can see a possible causation, answer with \"plausible\", otherwise answer with \"not plausible\"."], "Positive Examples": [{"input": "The woman went to the bank, so pigs can fly.", "output": "not plausible", "explanation": "Clearly, there can't be a causation relationship between someone going to the bank and pigs flying."}, {"input": "The women went to the bank, so now she has money on hand.", "output": "plausible", "explanation": "The second sentence can be a result of the first sentence, so the correct answer here is plausible."}], "Negative Examples": [{"input": "The woman went to the bank, so she waited in a line.", "output": "not plausible", "explanation": "Although waiting in a line doesn't always come as a result of going to a bank, this is a plausible sentence."}, {"input": "The physician misdiagnosed the patient, so he went to the vet", "output": "plausible", "explanation": "It is not plausible for someone to go to a vet for a diagnosis."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Commonsense"], "Instance": {"id": "task391-1bf1e0c1b76b479f870e2c2c81bc78d0", "input": "I stood on one foot, so I could see her again", "output": ["not plausible"]}, "Instance License": ["MIT"], "prediction": "plausible"}
+{"id": "task391-a7fb35e6ca744b10939e4233db113a67", "Task": "task391_causal_relationship", "Contributors": "['Pegah Alipoormolabashi']", "Source": ["cod3s"], "URL": ["https://aclanthology.org/2020.emnlp-main.421.pdf"], "Categories": ["Cause Effect Classification"], "Reasoning": ["Causal Reasoning", "Textual Entailment"], "Definition": ["In this task, you will be given two sentences separated by \", so\". You should decide whether the first sentence can be the cause of the second sentence. If you can see a possible causation, answer with \"plausible\", otherwise answer with \"not plausible\"."], "Positive Examples": [{"input": "The woman went to the bank, so pigs can fly.", "output": "not plausible", "explanation": "Clearly, there can't be a causation relationship between someone going to the bank and pigs flying."}, {"input": "The women went to the bank, so now she has money on hand.", "output": "plausible", "explanation": "The second sentence can be a result of the first sentence, so the correct answer here is plausible."}], "Negative Examples": [{"input": "The woman went to the bank, so she waited in a line.", "output": "not plausible", "explanation": "Although waiting in a line doesn't always come as a result of going to a bank, this is a plausible sentence."}, {"input": "The physician misdiagnosed the patient, so he went to the vet", "output": "plausible", "explanation": "It is not plausible for someone to go to a vet for a diagnosis."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Commonsense"], "Instance": {"id": "task391-a7fb35e6ca744b10939e4233db113a67", "input": "The photographer got the child to smile, so it was a good photo", "output": ["plausible"]}, "Instance License": ["MIT"], "prediction": "plausible"}
+{"id": "task391-58af70ef3466450a9c2abbc75c8bf67d", "Task": "task391_causal_relationship", "Contributors": "['Pegah Alipoormolabashi']", "Source": ["cod3s"], "URL": ["https://aclanthology.org/2020.emnlp-main.421.pdf"], "Categories": ["Cause Effect Classification"], "Reasoning": ["Causal Reasoning", "Textual Entailment"], "Definition": ["In this task, you will be given two sentences separated by \", so\". You should decide whether the first sentence can be the cause of the second sentence. If you can see a possible causation, answer with \"plausible\", otherwise answer with \"not plausible\"."], "Positive Examples": [{"input": "The woman went to the bank, so pigs can fly.", "output": "not plausible", "explanation": "Clearly, there can't be a causation relationship between someone going to the bank and pigs flying."}, {"input": "The women went to the bank, so now she has money on hand.", "output": "plausible", "explanation": "The second sentence can be a result of the first sentence, so the correct answer here is plausible."}], "Negative Examples": [{"input": "The woman went to the bank, so she waited in a line.", "output": "not plausible", "explanation": "Although waiting in a line doesn't always come as a result of going to a bank, this is a plausible sentence."}, {"input": "The physician misdiagnosed the patient, so he went to the vet", "output": "plausible", "explanation": "It is not plausible for someone to go to a vet for a diagnosis."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Commonsense"], "Instance": {"id": "task391-58af70ef3466450a9c2abbc75c8bf67d", "input": "My favorite song came on the radio, so this is right up my alley", "output": ["plausible"]}, "Instance License": ["MIT"], "prediction": "plausible"}
+{"id": "task391-dcce2417d0c04e7bb84f5950a5945804", "Task": "task391_causal_relationship", "Contributors": "['Pegah Alipoormolabashi']", "Source": ["cod3s"], "URL": ["https://aclanthology.org/2020.emnlp-main.421.pdf"], "Categories": ["Cause Effect Classification"], "Reasoning": ["Causal Reasoning", "Textual Entailment"], "Definition": ["In this task, you will be given two sentences separated by \", so\". You should decide whether the first sentence can be the cause of the second sentence. If you can see a possible causation, answer with \"plausible\", otherwise answer with \"not plausible\"."], "Positive Examples": [{"input": "The woman went to the bank, so pigs can fly.", "output": "not plausible", "explanation": "Clearly, there can't be a causation relationship between someone going to the bank and pigs flying."}, {"input": "The women went to the bank, so now she has money on hand.", "output": "plausible", "explanation": "The second sentence can be a result of the first sentence, so the correct answer here is plausible."}], "Negative Examples": [{"input": "The woman went to the bank, so she waited in a line.", "output": "not plausible", "explanation": "Although waiting in a line doesn't always come as a result of going to a bank, this is a plausible sentence."}, {"input": "The physician misdiagnosed the patient, so he went to the vet", "output": "plausible", "explanation": "It is not plausible for someone to go to a vet for a diagnosis."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Commonsense"], "Instance": {"id": "task391-dcce2417d0c04e7bb84f5950a5945804", "input": "The woman dangled the biscuit above the dog, so she could see the baby", "output": ["not plausible"]}, "Instance License": ["MIT"], "prediction": "plausible"}
+{"id": "task391-3233b8d93a9943b486a19864b6367679", "Task": "task391_causal_relationship", "Contributors": "['Pegah Alipoormolabashi']", "Source": ["cod3s"], "URL": ["https://aclanthology.org/2020.emnlp-main.421.pdf"], "Categories": ["Cause Effect Classification"], "Reasoning": ["Causal Reasoning", "Textual Entailment"], "Definition": ["In this task, you will be given two sentences separated by \", so\". You should decide whether the first sentence can be the cause of the second sentence. If you can see a possible causation, answer with \"plausible\", otherwise answer with \"not plausible\"."], "Positive Examples": [{"input": "The woman went to the bank, so pigs can fly.", "output": "not plausible", "explanation": "Clearly, there can't be a causation relationship between someone going to the bank and pigs flying."}, {"input": "The women went to the bank, so now she has money on hand.", "output": "plausible", "explanation": "The second sentence can be a result of the first sentence, so the correct answer here is plausible."}], "Negative Examples": [{"input": "The woman went to the bank, so she waited in a line.", "output": "not plausible", "explanation": "Although waiting in a line doesn't always come as a result of going to a bank, this is a plausible sentence."}, {"input": "The physician misdiagnosed the patient, so he went to the vet", "output": "plausible", "explanation": "It is not plausible for someone to go to a vet for a diagnosis."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Commonsense"], "Instance": {"id": "task391-3233b8d93a9943b486a19864b6367679", "input": "The physician misdiagnosed the patient, so the surgery had to be cancelled", "output": ["plausible"]}, "Instance License": ["MIT"], "prediction": "plausible"}
+{"id": "task891-7495deda872843b5b2e5d893816ede21", "Task": "task891_gap_coreference_resolution", "Contributors": "['Selvaganesh Muthu']", "Source": ["gap"], "URL": ["https://huggingface.co/datasets/gap"], "Categories": ["Coreference Resolution"], "Reasoning": [], "Definition": ["Read the passage and find the corresponding person for the given pronoun. The word between ** ** is the target pronoun."], "Positive Examples": [{"input": "The current members of Crime have also performed in San Francisco under the band name ''Remote Viewers``. Strike has published two works of fiction in recent years: Ports of Hell, which is listed in the Rock and Roll Hall of Fame Library, and A Loud Humming Sound Came from Above. Rank has produced numerous films (under **his** real name, Henry Rosenthal) including the hit The Devil and Daniel Johnston.", "output": "Henry Rosenthal", "explanation": "The person's name is referenced next to the pronoun itself. Therefore it is clear 'Henry Rosenthal' is the correct answer."}, {"input": "Killian in 1978--79, an assistant district attorney for Brunswick Judicial Circuit in 1979--80, and a practicing attorney in Glynn County in 1980--90. Williams was elected a Superior Court judge in 1990, taking the bench in 1991. In November 2010 Williams competed against Mary Helen Moses in **her** most recent bid for re-election.", "output": "Williams", "explanation": "The sentence lists the career growth of Williams and then mentions that she competed against Mary Helen Moses which makes it clear that the 'her' refers to Williams."}, {"input": "In 1987, Alison Krauss asked Brown to join her band, Union Station. Brown spent three years with Krauss. In 1990, **she** moved to Tennessee, and was named International Bluegrass Music Association Banjo Player of the Year in 1991.", "output": "Brown", "explanation": "The first sentence mentions Alison Krauss asked Brown to join her band, which defines that 'she' moved refers to Brown."}], "Negative Examples": [{"input": "Alleway played 857 minutes in 11 matches including 9 starts. The defence conceded a total of only 5 goals in the regular season and the finals. In March 2016, Alleway and Melbourne City teammate Steph Catley joined the NWSL's newest expansion club the Orlando Pride. Orlando Pride coach Tom Sermanni gave Alleway **her** first cap for Australia when he was coach of the Matildas in 2010.", "output": "Tom Sermanni", "explanation": "Tom Sermanni is referred to by the pronoun 'he' in the same sentence and so he cannot refer to the pronoun 'her' so this is incorrect."}, {"input": "The rest of the group find out what has happened to Case and decide to band together and take on Justin at the Beatdown to avenge their mentor. With each facing their own trials to reach the final match, it comes down to only one of them versus their own. Mike defeats Zack, while Justin injures Tim in the restroom - thus eliminating **him** from the tournament.", "output": "Justin", "explanation": "The pronoun 'him' refers to Tim as Tim is injured and he is the one to be eliminated. Hence this is incorrect."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Wikipedia"], "Instance": {"id": "task891-7495deda872843b5b2e5d893816ede21", "input": "Andy Spade is the co-founder of Partners & Spade, along with Anthony Sperduti. **He** started his career in advertising working on brands such as Coca-Cola, Lexus, and Paul Stuart.", "output": ["Andy Spade"]}, "Instance License": ["Apache 2.0"], "prediction": "Andy Spade"}
+{"id": "task891-e944f07613d046508ff4ecfef3666ebd", "Task": "task891_gap_coreference_resolution", "Contributors": "['Selvaganesh Muthu']", "Source": ["gap"], "URL": ["https://huggingface.co/datasets/gap"], "Categories": ["Coreference Resolution"], "Reasoning": [], "Definition": ["Read the passage and find the corresponding person for the given pronoun. The word between ** ** is the target pronoun."], "Positive Examples": [{"input": "The current members of Crime have also performed in San Francisco under the band name ''Remote Viewers``. Strike has published two works of fiction in recent years: Ports of Hell, which is listed in the Rock and Roll Hall of Fame Library, and A Loud Humming Sound Came from Above. Rank has produced numerous films (under **his** real name, Henry Rosenthal) including the hit The Devil and Daniel Johnston.", "output": "Henry Rosenthal", "explanation": "The person's name is referenced next to the pronoun itself. Therefore it is clear 'Henry Rosenthal' is the correct answer."}, {"input": "Killian in 1978--79, an assistant district attorney for Brunswick Judicial Circuit in 1979--80, and a practicing attorney in Glynn County in 1980--90. Williams was elected a Superior Court judge in 1990, taking the bench in 1991. In November 2010 Williams competed against Mary Helen Moses in **her** most recent bid for re-election.", "output": "Williams", "explanation": "The sentence lists the career growth of Williams and then mentions that she competed against Mary Helen Moses which makes it clear that the 'her' refers to Williams."}, {"input": "In 1987, Alison Krauss asked Brown to join her band, Union Station. Brown spent three years with Krauss. In 1990, **she** moved to Tennessee, and was named International Bluegrass Music Association Banjo Player of the Year in 1991.", "output": "Brown", "explanation": "The first sentence mentions Alison Krauss asked Brown to join her band, which defines that 'she' moved refers to Brown."}], "Negative Examples": [{"input": "Alleway played 857 minutes in 11 matches including 9 starts. The defence conceded a total of only 5 goals in the regular season and the finals. In March 2016, Alleway and Melbourne City teammate Steph Catley joined the NWSL's newest expansion club the Orlando Pride. Orlando Pride coach Tom Sermanni gave Alleway **her** first cap for Australia when he was coach of the Matildas in 2010.", "output": "Tom Sermanni", "explanation": "Tom Sermanni is referred to by the pronoun 'he' in the same sentence and so he cannot refer to the pronoun 'her' so this is incorrect."}, {"input": "The rest of the group find out what has happened to Case and decide to band together and take on Justin at the Beatdown to avenge their mentor. With each facing their own trials to reach the final match, it comes down to only one of them versus their own. Mike defeats Zack, while Justin injures Tim in the restroom - thus eliminating **him** from the tournament.", "output": "Justin", "explanation": "The pronoun 'him' refers to Tim as Tim is injured and he is the one to be eliminated. Hence this is incorrect."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Wikipedia"], "Instance": {"id": "task891-e944f07613d046508ff4ecfef3666ebd", "input": "Michael Moorcock, E. C. Tubb, Brian Stableford, Barrington Bayley, Michael Coney -- a new American audience. He published translations of international sf as well as anthologies of translated stories, Best From the Rest of the World. With the help of Arthur W. Saha, Wollheim also edited and published the popular ``Annual World's Best Science Fiction'' anthology from 1971 until **his** death in 1990.", "output": ["Wollheim"]}, "Instance License": ["Apache 2.0"], "prediction": "Wollheim"}
+{"id": "task891-c2979e7543794298944bf09d0e7f6f14", "Task": "task891_gap_coreference_resolution", "Contributors": "['Selvaganesh Muthu']", "Source": ["gap"], "URL": ["https://huggingface.co/datasets/gap"], "Categories": ["Coreference Resolution"], "Reasoning": [], "Definition": ["Read the passage and find the corresponding person for the given pronoun. The word between ** ** is the target pronoun."], "Positive Examples": [{"input": "The current members of Crime have also performed in San Francisco under the band name ''Remote Viewers``. Strike has published two works of fiction in recent years: Ports of Hell, which is listed in the Rock and Roll Hall of Fame Library, and A Loud Humming Sound Came from Above. Rank has produced numerous films (under **his** real name, Henry Rosenthal) including the hit The Devil and Daniel Johnston.", "output": "Henry Rosenthal", "explanation": "The person's name is referenced next to the pronoun itself. Therefore it is clear 'Henry Rosenthal' is the correct answer."}, {"input": "Killian in 1978--79, an assistant district attorney for Brunswick Judicial Circuit in 1979--80, and a practicing attorney in Glynn County in 1980--90. Williams was elected a Superior Court judge in 1990, taking the bench in 1991. In November 2010 Williams competed against Mary Helen Moses in **her** most recent bid for re-election.", "output": "Williams", "explanation": "The sentence lists the career growth of Williams and then mentions that she competed against Mary Helen Moses which makes it clear that the 'her' refers to Williams."}, {"input": "In 1987, Alison Krauss asked Brown to join her band, Union Station. Brown spent three years with Krauss. In 1990, **she** moved to Tennessee, and was named International Bluegrass Music Association Banjo Player of the Year in 1991.", "output": "Brown", "explanation": "The first sentence mentions Alison Krauss asked Brown to join her band, which defines that 'she' moved refers to Brown."}], "Negative Examples": [{"input": "Alleway played 857 minutes in 11 matches including 9 starts. The defence conceded a total of only 5 goals in the regular season and the finals. In March 2016, Alleway and Melbourne City teammate Steph Catley joined the NWSL's newest expansion club the Orlando Pride. Orlando Pride coach Tom Sermanni gave Alleway **her** first cap for Australia when he was coach of the Matildas in 2010.", "output": "Tom Sermanni", "explanation": "Tom Sermanni is referred to by the pronoun 'he' in the same sentence and so he cannot refer to the pronoun 'her' so this is incorrect."}, {"input": "The rest of the group find out what has happened to Case and decide to band together and take on Justin at the Beatdown to avenge their mentor. With each facing their own trials to reach the final match, it comes down to only one of them versus their own. Mike defeats Zack, while Justin injures Tim in the restroom - thus eliminating **him** from the tournament.", "output": "Justin", "explanation": "The pronoun 'him' refers to Tim as Tim is injured and he is the one to be eliminated. Hence this is incorrect."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Wikipedia"], "Instance": {"id": "task891-c2979e7543794298944bf09d0e7f6f14", "input": "Karl Philipp F*rst zu Schwarzenberg (or Charles Philip, Prince of Schwarzenberg (April 18, 1771 -- October 15, 1820) was an Austrian field marshal. Karl Philipp was born in Vienna as the son of Johann Nepomuk Anton of Schwarzenberg and Marie Eleonore Countess of *ttingen-Wallerstein. **He** entered the imperial cavalry in 1788, fought in 1789 under Lacy and Loudon against the Turks, distinguished himself by his bravery, and became major in 1792.", "output": ["Schwarzenberg"]}, "Instance License": ["Apache 2.0"], "prediction": "Karl Philipp"}
+{"id": "task891-8f2da83fe5ca40fc8174cb1d3a8e4c5d", "Task": "task891_gap_coreference_resolution", "Contributors": "['Selvaganesh Muthu']", "Source": ["gap"], "URL": ["https://huggingface.co/datasets/gap"], "Categories": ["Coreference Resolution"], "Reasoning": [], "Definition": ["Read the passage and find the corresponding person for the given pronoun. The word between ** ** is the target pronoun."], "Positive Examples": [{"input": "The current members of Crime have also performed in San Francisco under the band name ''Remote Viewers``. Strike has published two works of fiction in recent years: Ports of Hell, which is listed in the Rock and Roll Hall of Fame Library, and A Loud Humming Sound Came from Above. Rank has produced numerous films (under **his** real name, Henry Rosenthal) including the hit The Devil and Daniel Johnston.", "output": "Henry Rosenthal", "explanation": "The person's name is referenced next to the pronoun itself. Therefore it is clear 'Henry Rosenthal' is the correct answer."}, {"input": "Killian in 1978--79, an assistant district attorney for Brunswick Judicial Circuit in 1979--80, and a practicing attorney in Glynn County in 1980--90. Williams was elected a Superior Court judge in 1990, taking the bench in 1991. In November 2010 Williams competed against Mary Helen Moses in **her** most recent bid for re-election.", "output": "Williams", "explanation": "The sentence lists the career growth of Williams and then mentions that she competed against Mary Helen Moses which makes it clear that the 'her' refers to Williams."}, {"input": "In 1987, Alison Krauss asked Brown to join her band, Union Station. Brown spent three years with Krauss. In 1990, **she** moved to Tennessee, and was named International Bluegrass Music Association Banjo Player of the Year in 1991.", "output": "Brown", "explanation": "The first sentence mentions Alison Krauss asked Brown to join her band, which defines that 'she' moved refers to Brown."}], "Negative Examples": [{"input": "Alleway played 857 minutes in 11 matches including 9 starts. The defence conceded a total of only 5 goals in the regular season and the finals. In March 2016, Alleway and Melbourne City teammate Steph Catley joined the NWSL's newest expansion club the Orlando Pride. Orlando Pride coach Tom Sermanni gave Alleway **her** first cap for Australia when he was coach of the Matildas in 2010.", "output": "Tom Sermanni", "explanation": "Tom Sermanni is referred to by the pronoun 'he' in the same sentence and so he cannot refer to the pronoun 'her' so this is incorrect."}, {"input": "The rest of the group find out what has happened to Case and decide to band together and take on Justin at the Beatdown to avenge their mentor. With each facing their own trials to reach the final match, it comes down to only one of them versus their own. Mike defeats Zack, while Justin injures Tim in the restroom - thus eliminating **him** from the tournament.", "output": "Justin", "explanation": "The pronoun 'him' refers to Tim as Tim is injured and he is the one to be eliminated. Hence this is incorrect."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Wikipedia"], "Instance": {"id": "task891-8f2da83fe5ca40fc8174cb1d3a8e4c5d", "input": "Father Joseph savors the power which he possesses on the fate of Cinq-Mars (``Tu t'en vas''). He confronts Marie with the announcement of the execution of Cinq-Mars, for betraying the country by dealing independently with a foreign power. Further, **he** tells her, the Polish ambassador will return soon from a hunt with the King, and Father Joseph advises Marie to answer him favorably; in exchange, Cinq-Mars will be spared.", "output": ["Father Joseph"]}, "Instance License": ["Apache 2.0"], "prediction": "Father Joseph"}
+{"id": "task891-e23f14d28a3545f091127df6fc56a548", "Task": "task891_gap_coreference_resolution", "Contributors": "['Selvaganesh Muthu']", "Source": ["gap"], "URL": ["https://huggingface.co/datasets/gap"], "Categories": ["Coreference Resolution"], "Reasoning": [], "Definition": ["Read the passage and find the corresponding person for the given pronoun. The word between ** ** is the target pronoun."], "Positive Examples": [{"input": "The current members of Crime have also performed in San Francisco under the band name ''Remote Viewers``. Strike has published two works of fiction in recent years: Ports of Hell, which is listed in the Rock and Roll Hall of Fame Library, and A Loud Humming Sound Came from Above. Rank has produced numerous films (under **his** real name, Henry Rosenthal) including the hit The Devil and Daniel Johnston.", "output": "Henry Rosenthal", "explanation": "The person's name is referenced next to the pronoun itself. Therefore it is clear 'Henry Rosenthal' is the correct answer."}, {"input": "Killian in 1978--79, an assistant district attorney for Brunswick Judicial Circuit in 1979--80, and a practicing attorney in Glynn County in 1980--90. Williams was elected a Superior Court judge in 1990, taking the bench in 1991. In November 2010 Williams competed against Mary Helen Moses in **her** most recent bid for re-election.", "output": "Williams", "explanation": "The sentence lists the career growth of Williams and then mentions that she competed against Mary Helen Moses which makes it clear that the 'her' refers to Williams."}, {"input": "In 1987, Alison Krauss asked Brown to join her band, Union Station. Brown spent three years with Krauss. In 1990, **she** moved to Tennessee, and was named International Bluegrass Music Association Banjo Player of the Year in 1991.", "output": "Brown", "explanation": "The first sentence mentions Alison Krauss asked Brown to join her band, which defines that 'she' moved refers to Brown."}], "Negative Examples": [{"input": "Alleway played 857 minutes in 11 matches including 9 starts. The defence conceded a total of only 5 goals in the regular season and the finals. In March 2016, Alleway and Melbourne City teammate Steph Catley joined the NWSL's newest expansion club the Orlando Pride. Orlando Pride coach Tom Sermanni gave Alleway **her** first cap for Australia when he was coach of the Matildas in 2010.", "output": "Tom Sermanni", "explanation": "Tom Sermanni is referred to by the pronoun 'he' in the same sentence and so he cannot refer to the pronoun 'her' so this is incorrect."}, {"input": "The rest of the group find out what has happened to Case and decide to band together and take on Justin at the Beatdown to avenge their mentor. With each facing their own trials to reach the final match, it comes down to only one of them versus their own. Mike defeats Zack, while Justin injures Tim in the restroom - thus eliminating **him** from the tournament.", "output": "Justin", "explanation": "The pronoun 'him' refers to Tim as Tim is injured and he is the one to be eliminated. Hence this is incorrect."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Wikipedia"], "Instance": {"id": "task891-e23f14d28a3545f091127df6fc56a548", "input": "The writers and dandies Charles Baudelaire and Jules Barbey d'Aurevilly also had some influence, but the most important model was the notorious aristocratic aesthete Robert de Montesquiou, who was also the basis for Baron de Charlus in Marcel Proust's * la recherche du temps perdu. Montesquiou's furnishings bear a strong resemblance to those in Des Esseintes's house: In 1883, to **his** eternal regret, Montesquiou admitted St*phane Mallarm* (to his home).", "output": ["Montesquiou"]}, "Instance License": ["Apache 2.0"], "prediction": "Robert de Montesquiou"}
+{"id": "task1586-43bb07b6cb074c3aa5b92272b48299e5", "Task": "task1586_scifact_title_generation", "Contributors": "['Nakul Vaidya']", "Source": ["scifact"], "URL": ["https://huggingface.co/datasets/scifact"], "Categories": ["Title Generation"], "Reasoning": [], "Definition": ["In this task, you are given an abstract of article. Your task is to generate title for this article. Preferred titles are under thirty words."], "Positive Examples": [{"input": "Alterations of the architecture of cerebral white matter in the developing human brain can affect cortical development and result in functional disabilities. A line scan diffusion-weighted magnetic resonance imaging (MRI) sequence with diffusion tensor analysis was applied to measure the apparent diffusion coefficient, to calculate relative anisotropy, and to delineate three-dimensional fiber architecture in cerebral white matter in preterm (n = 17) and full-term infants (n = 7). To assess effects of prematurity on cerebral white matter development, early gestation preterm infants (n = 10) were studied a second time at term. In the central white matter the mean apparent diffusion coefficient at 28 wk was high, 1.8 microm2/ms, and decreased toward term to 1.2 microm2/ms. In the posterior limb of the internal capsule, the mean apparent diffusion coefficients at both times were similar (1.2 versus 1.1 microm2/ms). Relative anisotropy was higher the closer birth was to term with greater absolute values in the internal capsule than in the central white matter. Preterm infants at term showed higher mean diffusion coefficients in the central white matter (1.4 +/- 0.24 versus 1.15 +/- 0.09 microm2/ms, p = 0.016) and lower relative anisotropy in both areas compared with full-term infants (white matter, 10.9 +/- 0.6 versus 22.9 +/- 3.0%, p = 0.001; internal capsule, 24.0 +/- 4.44 versus 33.1 +/- 0.6% p = 0.006). Nonmyelinated fibers in the corpus callosum were visible by diffusion tensor MRI as early as 28 wk; full-term and preterm infants at term showed marked differences in white matter fiber organization. The data indicate that quantitative assessment of water diffusion by diffusion tensor MRI provides insight into microstructural development in cerebral white matter in living infants.", "output": "Microstructural development of human newborn cerebral white matter assessed in vivo by diffusion tensor magnetic resonance imaging.", "explanation": "This title is appropriate for the given abstract because the focus of this abstract is cerebral white matter assesment."}, {"input": "Myelodysplastic syndromes (MDS) are age-dependent stem cell malignancies that share biological features of activated adaptive immune response and ineffective hematopoiesis. Here we report that myeloid-derived suppressor cells (MDSC), which are classically linked to immunosuppression, inflammation, and cancer, were markedly expanded in the bone marrow of MDS patients and played a pathogenetic role in the development of ineffective hematopoiesis. These clonally distinct MDSC overproduce hematopoietic suppressive cytokines and function as potent apoptotic effectors targeting autologous hematopoietic progenitors. Using multiple transfected cell models, we found that MDSC expansion is driven by the interaction of the proinflammatory molecule S100A9 with CD33. These 2 proteins formed a functional ligand/receptor pair that recruited components to CD33\u2019s immunoreceptor tyrosine-based inhibition motif (ITIM), inducing secretion of the suppressive cytokines IL-10 and TGF-\u03b2 by immature myeloid cells. S100A9 transgenic mice displayed bone marrow accumulation of MDSC accompanied by development of progressive multilineage cytopenias and cytological dysplasia. Importantly, early forced maturation of MDSC by either all-trans-retinoic acid treatment or active immunoreceptor tyrosine-based activation motif\u2013bearing (ITAM-bearing) adapter protein (DAP12) interruption of CD33 signaling rescued the hematologic phenotype. These findings indicate that primary bone marrow expansion of MDSC driven by the S100A9/CD33 pathway perturbs hematopoiesis and contributes to the development of MDS.", "output": "Induction of myelodysplasia by myeloid-derived suppressor cells.", "explanation": "This title is appropriate for the given abstract because the focus of this abstract is myelodysplastic syndromes."}], "Negative Examples": [{"input": "Alterations of the architecture of cerebral white matter in the developing human brain can affect cortical development and result in functional disabilities. A line scan diffusion-weighted magnetic resonance imaging (MRI) sequence with diffusion tensor analysis was applied to measure the apparent diffusion coefficient, to calculate relative anisotropy, and to delineate three-dimensional fiber architecture in cerebral white matter in preterm (n = 17) and full-term infants (n = 7). To assess effects of prematurity on cerebral white matter development, early gestation preterm infants (n = 10) were studied a second time at term. In the central white matter the mean apparent diffusion coefficient at 28 wk was high, 1.8 microm2/ms, and decreased toward term to 1.2 microm2/ms. In the posterior limb of the internal capsule, the mean apparent diffusion coefficients at both times were similar (1.2 versus 1.1 microm2/ms). Relative anisotropy was higher the closer birth was to term with greater absolute values in the internal capsule than in the central white matter. Preterm infants at term showed higher mean diffusion coefficients in the central white matter (1.4 +/- 0.24 versus 1.15 +/- 0.09 microm2/ms, p = 0.016) and lower relative anisotropy in both areas compared with full-term infants (white matter, 10.9 +/- 0.6 versus 22.9 +/- 3.0%, p = 0.001; internal capsule, 24.0 +/- 4.44 versus 33.1 +/- 0.6% p = 0.006). Nonmyelinated fibers in the corpus callosum were visible by diffusion tensor MRI as early as 28 wk; full-term and preterm infants at term showed marked differences in white matter fiber organization. The data indicate that quantitative assessment of water diffusion by diffusion tensor MRI provides insight into microstructural development in cerebral white matter in living infants.", "output": "Induction of myelodysplasia by myeloid-derived suppressor cells.", "explanation": "This abstract talks about cerebral white matter assesment, but there is no indication about white matter assesment in the given title."}, {"input": "Myelodysplastic syndromes (MDS) are age-dependent stem cell malignancies that share biological features of activated adaptive immune response and ineffective hematopoiesis. Here we report that myeloid-derived suppressor cells (MDSC), which are classically linked to immunosuppression, inflammation, and cancer, were markedly expanded in the bone marrow of MDS patients and played a pathogenetic role in the development of ineffective hematopoiesis. These clonally distinct MDSC overproduce hematopoietic suppressive cytokines and function as potent apoptotic effectors targeting autologous hematopoietic progenitors. Using multiple transfected cell models, we found that MDSC expansion is driven by the interaction of the proinflammatory molecule S100A9 with CD33. These 2 proteins formed a functional ligand/receptor pair that recruited components to CD33\u2019s immunoreceptor tyrosine-based inhibition motif (ITIM), inducing secretion of the suppressive cytokines IL-10 and TGF-\u03b2 by immature myeloid cells. S100A9 transgenic mice displayed bone marrow accumulation of MDSC accompanied by development of progressive multilineage cytopenias and cytological dysplasia. Importantly, early forced maturation of MDSC by either all-trans-retinoic acid treatment or active immunoreceptor tyrosine-based activation motif\u2013bearing (ITAM-bearing) adapter protein (DAP12) interruption of CD33 signaling rescued the hematologic phenotype. These findings indicate that primary bone marrow expansion of MDSC driven by the S100A9/CD33 pathway perturbs hematopoiesis and contributes to the development of MDS.", "output": "Microstructural development of human newborn cerebral white matter assessed in vivo by diffusion tensor magnetic resonance imaging.", "explanation": "Generated title and abstract text is totally different. Hence, this is not a right title."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Scientific Research Papers"], "Instance": {"id": "task1586-43bb07b6cb074c3aa5b92272b48299e5", "input": "Podocytes are critical in the maintenance of a healthy glomerular filter; however, they have been difficult to study in the intact kidney because of technical limitations. Here we report the development of serial multiphoton microscopy (MPM) of the same glomeruli over several days to visualize the motility of podocytes and parietal epithelial cells (PECs) in vivo. In podocin-GFP mice, podocytes formed sporadic multicellular clusters after unilateral ureteral ligation and migrated into the parietal Bowman's capsule. The tracking of single cells in podocin-confetti mice featuring cell-specific expression of CFP, GFP, YFP or RFP revealed the simultaneous migration of multiple podocytes. In phosphoenolpyruvate carboxykinase (PEPCK)-GFP mice, serial MPM found PEC-to-podocyte migration and nanotubule connections. Our data support a highly dynamic rather than a static nature of the glomerular environment and cellular composition. Future application of this new approach should advance our understanding of the mechanisms of glomerular injury and regeneration.", "output": ["Tracking the fate of glomerular epithelial cells in vivo using serial multiphoton imaging in novel mouse models with fluorescent lineage tags"]}, "Instance License": ["CC BY-NC 2.0"], "prediction": "Podocytes are critical in the maintenance of a healthy glomerular filter in vivo."}
+{"id": "task1586-3c1d94a543424bf3ae71209d3bb52ba8", "Task": "task1586_scifact_title_generation", "Contributors": "['Nakul Vaidya']", "Source": ["scifact"], "URL": ["https://huggingface.co/datasets/scifact"], "Categories": ["Title Generation"], "Reasoning": [], "Definition": ["In this task, you are given an abstract of article. Your task is to generate title for this article. Preferred titles are under thirty words."], "Positive Examples": [{"input": "Alterations of the architecture of cerebral white matter in the developing human brain can affect cortical development and result in functional disabilities. A line scan diffusion-weighted magnetic resonance imaging (MRI) sequence with diffusion tensor analysis was applied to measure the apparent diffusion coefficient, to calculate relative anisotropy, and to delineate three-dimensional fiber architecture in cerebral white matter in preterm (n = 17) and full-term infants (n = 7). To assess effects of prematurity on cerebral white matter development, early gestation preterm infants (n = 10) were studied a second time at term. In the central white matter the mean apparent diffusion coefficient at 28 wk was high, 1.8 microm2/ms, and decreased toward term to 1.2 microm2/ms. In the posterior limb of the internal capsule, the mean apparent diffusion coefficients at both times were similar (1.2 versus 1.1 microm2/ms). Relative anisotropy was higher the closer birth was to term with greater absolute values in the internal capsule than in the central white matter. Preterm infants at term showed higher mean diffusion coefficients in the central white matter (1.4 +/- 0.24 versus 1.15 +/- 0.09 microm2/ms, p = 0.016) and lower relative anisotropy in both areas compared with full-term infants (white matter, 10.9 +/- 0.6 versus 22.9 +/- 3.0%, p = 0.001; internal capsule, 24.0 +/- 4.44 versus 33.1 +/- 0.6% p = 0.006). Nonmyelinated fibers in the corpus callosum were visible by diffusion tensor MRI as early as 28 wk; full-term and preterm infants at term showed marked differences in white matter fiber organization. The data indicate that quantitative assessment of water diffusion by diffusion tensor MRI provides insight into microstructural development in cerebral white matter in living infants.", "output": "Microstructural development of human newborn cerebral white matter assessed in vivo by diffusion tensor magnetic resonance imaging.", "explanation": "This title is appropriate for the given abstract because the focus of this abstract is cerebral white matter assesment."}, {"input": "Myelodysplastic syndromes (MDS) are age-dependent stem cell malignancies that share biological features of activated adaptive immune response and ineffective hematopoiesis. Here we report that myeloid-derived suppressor cells (MDSC), which are classically linked to immunosuppression, inflammation, and cancer, were markedly expanded in the bone marrow of MDS patients and played a pathogenetic role in the development of ineffective hematopoiesis. These clonally distinct MDSC overproduce hematopoietic suppressive cytokines and function as potent apoptotic effectors targeting autologous hematopoietic progenitors. Using multiple transfected cell models, we found that MDSC expansion is driven by the interaction of the proinflammatory molecule S100A9 with CD33. These 2 proteins formed a functional ligand/receptor pair that recruited components to CD33\u2019s immunoreceptor tyrosine-based inhibition motif (ITIM), inducing secretion of the suppressive cytokines IL-10 and TGF-\u03b2 by immature myeloid cells. S100A9 transgenic mice displayed bone marrow accumulation of MDSC accompanied by development of progressive multilineage cytopenias and cytological dysplasia. Importantly, early forced maturation of MDSC by either all-trans-retinoic acid treatment or active immunoreceptor tyrosine-based activation motif\u2013bearing (ITAM-bearing) adapter protein (DAP12) interruption of CD33 signaling rescued the hematologic phenotype. These findings indicate that primary bone marrow expansion of MDSC driven by the S100A9/CD33 pathway perturbs hematopoiesis and contributes to the development of MDS.", "output": "Induction of myelodysplasia by myeloid-derived suppressor cells.", "explanation": "This title is appropriate for the given abstract because the focus of this abstract is myelodysplastic syndromes."}], "Negative Examples": [{"input": "Alterations of the architecture of cerebral white matter in the developing human brain can affect cortical development and result in functional disabilities. A line scan diffusion-weighted magnetic resonance imaging (MRI) sequence with diffusion tensor analysis was applied to measure the apparent diffusion coefficient, to calculate relative anisotropy, and to delineate three-dimensional fiber architecture in cerebral white matter in preterm (n = 17) and full-term infants (n = 7). To assess effects of prematurity on cerebral white matter development, early gestation preterm infants (n = 10) were studied a second time at term. In the central white matter the mean apparent diffusion coefficient at 28 wk was high, 1.8 microm2/ms, and decreased toward term to 1.2 microm2/ms. In the posterior limb of the internal capsule, the mean apparent diffusion coefficients at both times were similar (1.2 versus 1.1 microm2/ms). Relative anisotropy was higher the closer birth was to term with greater absolute values in the internal capsule than in the central white matter. Preterm infants at term showed higher mean diffusion coefficients in the central white matter (1.4 +/- 0.24 versus 1.15 +/- 0.09 microm2/ms, p = 0.016) and lower relative anisotropy in both areas compared with full-term infants (white matter, 10.9 +/- 0.6 versus 22.9 +/- 3.0%, p = 0.001; internal capsule, 24.0 +/- 4.44 versus 33.1 +/- 0.6% p = 0.006). Nonmyelinated fibers in the corpus callosum were visible by diffusion tensor MRI as early as 28 wk; full-term and preterm infants at term showed marked differences in white matter fiber organization. The data indicate that quantitative assessment of water diffusion by diffusion tensor MRI provides insight into microstructural development in cerebral white matter in living infants.", "output": "Induction of myelodysplasia by myeloid-derived suppressor cells.", "explanation": "This abstract talks about cerebral white matter assesment, but there is no indication about white matter assesment in the given title."}, {"input": "Myelodysplastic syndromes (MDS) are age-dependent stem cell malignancies that share biological features of activated adaptive immune response and ineffective hematopoiesis. Here we report that myeloid-derived suppressor cells (MDSC), which are classically linked to immunosuppression, inflammation, and cancer, were markedly expanded in the bone marrow of MDS patients and played a pathogenetic role in the development of ineffective hematopoiesis. These clonally distinct MDSC overproduce hematopoietic suppressive cytokines and function as potent apoptotic effectors targeting autologous hematopoietic progenitors. Using multiple transfected cell models, we found that MDSC expansion is driven by the interaction of the proinflammatory molecule S100A9 with CD33. These 2 proteins formed a functional ligand/receptor pair that recruited components to CD33\u2019s immunoreceptor tyrosine-based inhibition motif (ITIM), inducing secretion of the suppressive cytokines IL-10 and TGF-\u03b2 by immature myeloid cells. S100A9 transgenic mice displayed bone marrow accumulation of MDSC accompanied by development of progressive multilineage cytopenias and cytological dysplasia. Importantly, early forced maturation of MDSC by either all-trans-retinoic acid treatment or active immunoreceptor tyrosine-based activation motif\u2013bearing (ITAM-bearing) adapter protein (DAP12) interruption of CD33 signaling rescued the hematologic phenotype. These findings indicate that primary bone marrow expansion of MDSC driven by the S100A9/CD33 pathway perturbs hematopoiesis and contributes to the development of MDS.", "output": "Microstructural development of human newborn cerebral white matter assessed in vivo by diffusion tensor magnetic resonance imaging.", "explanation": "Generated title and abstract text is totally different. Hence, this is not a right title."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Scientific Research Papers"], "Instance": {"id": "task1586-3c1d94a543424bf3ae71209d3bb52ba8", "input": "T cell activation is predicated on the interaction between the T cell receptor and peptide-major histocompatibility (pMHC) ligands. The factors that determine the stimulatory potency of a pMHC molecule remain unclear. We describe results showing that a peptide exhibiting many hallmarks of a weak agonist stimulates T cells to proliferate more than the wild-type agonist ligand. An in silico approach suggested that the inability to form the central supramolecular activation cluster (cSMAC) could underlie the increased proliferation. This conclusion was supported by experiments that showed that enhancing cSMAC formation reduced stimulatory capacity of the weak peptide. Our studies highlight the fact that a complex interplay of factors determines the quality of a T cell antigen.", "output": ["The stimulatory potency of T cell antigens is influenced by the formation of the immunological synapse."]}, "Instance License": ["CC BY-NC 2.0"], "prediction": "T cell activation is predicated on the interaction between the T cell receptor and peptide-major histocompatibility ligands."}
+{"id": "task1586-725280cc7de74989a630cb88c5a15973", "Task": "task1586_scifact_title_generation", "Contributors": "['Nakul Vaidya']", "Source": ["scifact"], "URL": ["https://huggingface.co/datasets/scifact"], "Categories": ["Title Generation"], "Reasoning": [], "Definition": ["In this task, you are given an abstract of article. Your task is to generate title for this article. Preferred titles are under thirty words."], "Positive Examples": [{"input": "Alterations of the architecture of cerebral white matter in the developing human brain can affect cortical development and result in functional disabilities. A line scan diffusion-weighted magnetic resonance imaging (MRI) sequence with diffusion tensor analysis was applied to measure the apparent diffusion coefficient, to calculate relative anisotropy, and to delineate three-dimensional fiber architecture in cerebral white matter in preterm (n = 17) and full-term infants (n = 7). To assess effects of prematurity on cerebral white matter development, early gestation preterm infants (n = 10) were studied a second time at term. In the central white matter the mean apparent diffusion coefficient at 28 wk was high, 1.8 microm2/ms, and decreased toward term to 1.2 microm2/ms. In the posterior limb of the internal capsule, the mean apparent diffusion coefficients at both times were similar (1.2 versus 1.1 microm2/ms). Relative anisotropy was higher the closer birth was to term with greater absolute values in the internal capsule than in the central white matter. Preterm infants at term showed higher mean diffusion coefficients in the central white matter (1.4 +/- 0.24 versus 1.15 +/- 0.09 microm2/ms, p = 0.016) and lower relative anisotropy in both areas compared with full-term infants (white matter, 10.9 +/- 0.6 versus 22.9 +/- 3.0%, p = 0.001; internal capsule, 24.0 +/- 4.44 versus 33.1 +/- 0.6% p = 0.006). Nonmyelinated fibers in the corpus callosum were visible by diffusion tensor MRI as early as 28 wk; full-term and preterm infants at term showed marked differences in white matter fiber organization. The data indicate that quantitative assessment of water diffusion by diffusion tensor MRI provides insight into microstructural development in cerebral white matter in living infants.", "output": "Microstructural development of human newborn cerebral white matter assessed in vivo by diffusion tensor magnetic resonance imaging.", "explanation": "This title is appropriate for the given abstract because the focus of this abstract is cerebral white matter assesment."}, {"input": "Myelodysplastic syndromes (MDS) are age-dependent stem cell malignancies that share biological features of activated adaptive immune response and ineffective hematopoiesis. Here we report that myeloid-derived suppressor cells (MDSC), which are classically linked to immunosuppression, inflammation, and cancer, were markedly expanded in the bone marrow of MDS patients and played a pathogenetic role in the development of ineffective hematopoiesis. These clonally distinct MDSC overproduce hematopoietic suppressive cytokines and function as potent apoptotic effectors targeting autologous hematopoietic progenitors. Using multiple transfected cell models, we found that MDSC expansion is driven by the interaction of the proinflammatory molecule S100A9 with CD33. These 2 proteins formed a functional ligand/receptor pair that recruited components to CD33\u2019s immunoreceptor tyrosine-based inhibition motif (ITIM), inducing secretion of the suppressive cytokines IL-10 and TGF-\u03b2 by immature myeloid cells. S100A9 transgenic mice displayed bone marrow accumulation of MDSC accompanied by development of progressive multilineage cytopenias and cytological dysplasia. Importantly, early forced maturation of MDSC by either all-trans-retinoic acid treatment or active immunoreceptor tyrosine-based activation motif\u2013bearing (ITAM-bearing) adapter protein (DAP12) interruption of CD33 signaling rescued the hematologic phenotype. These findings indicate that primary bone marrow expansion of MDSC driven by the S100A9/CD33 pathway perturbs hematopoiesis and contributes to the development of MDS.", "output": "Induction of myelodysplasia by myeloid-derived suppressor cells.", "explanation": "This title is appropriate for the given abstract because the focus of this abstract is myelodysplastic syndromes."}], "Negative Examples": [{"input": "Alterations of the architecture of cerebral white matter in the developing human brain can affect cortical development and result in functional disabilities. A line scan diffusion-weighted magnetic resonance imaging (MRI) sequence with diffusion tensor analysis was applied to measure the apparent diffusion coefficient, to calculate relative anisotropy, and to delineate three-dimensional fiber architecture in cerebral white matter in preterm (n = 17) and full-term infants (n = 7). To assess effects of prematurity on cerebral white matter development, early gestation preterm infants (n = 10) were studied a second time at term. In the central white matter the mean apparent diffusion coefficient at 28 wk was high, 1.8 microm2/ms, and decreased toward term to 1.2 microm2/ms. In the posterior limb of the internal capsule, the mean apparent diffusion coefficients at both times were similar (1.2 versus 1.1 microm2/ms). Relative anisotropy was higher the closer birth was to term with greater absolute values in the internal capsule than in the central white matter. Preterm infants at term showed higher mean diffusion coefficients in the central white matter (1.4 +/- 0.24 versus 1.15 +/- 0.09 microm2/ms, p = 0.016) and lower relative anisotropy in both areas compared with full-term infants (white matter, 10.9 +/- 0.6 versus 22.9 +/- 3.0%, p = 0.001; internal capsule, 24.0 +/- 4.44 versus 33.1 +/- 0.6% p = 0.006). Nonmyelinated fibers in the corpus callosum were visible by diffusion tensor MRI as early as 28 wk; full-term and preterm infants at term showed marked differences in white matter fiber organization. The data indicate that quantitative assessment of water diffusion by diffusion tensor MRI provides insight into microstructural development in cerebral white matter in living infants.", "output": "Induction of myelodysplasia by myeloid-derived suppressor cells.", "explanation": "This abstract talks about cerebral white matter assesment, but there is no indication about white matter assesment in the given title."}, {"input": "Myelodysplastic syndromes (MDS) are age-dependent stem cell malignancies that share biological features of activated adaptive immune response and ineffective hematopoiesis. Here we report that myeloid-derived suppressor cells (MDSC), which are classically linked to immunosuppression, inflammation, and cancer, were markedly expanded in the bone marrow of MDS patients and played a pathogenetic role in the development of ineffective hematopoiesis. These clonally distinct MDSC overproduce hematopoietic suppressive cytokines and function as potent apoptotic effectors targeting autologous hematopoietic progenitors. Using multiple transfected cell models, we found that MDSC expansion is driven by the interaction of the proinflammatory molecule S100A9 with CD33. These 2 proteins formed a functional ligand/receptor pair that recruited components to CD33\u2019s immunoreceptor tyrosine-based inhibition motif (ITIM), inducing secretion of the suppressive cytokines IL-10 and TGF-\u03b2 by immature myeloid cells. S100A9 transgenic mice displayed bone marrow accumulation of MDSC accompanied by development of progressive multilineage cytopenias and cytological dysplasia. Importantly, early forced maturation of MDSC by either all-trans-retinoic acid treatment or active immunoreceptor tyrosine-based activation motif\u2013bearing (ITAM-bearing) adapter protein (DAP12) interruption of CD33 signaling rescued the hematologic phenotype. These findings indicate that primary bone marrow expansion of MDSC driven by the S100A9/CD33 pathway perturbs hematopoiesis and contributes to the development of MDS.", "output": "Microstructural development of human newborn cerebral white matter assessed in vivo by diffusion tensor magnetic resonance imaging.", "explanation": "Generated title and abstract text is totally different. Hence, this is not a right title."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Scientific Research Papers"], "Instance": {"id": "task1586-725280cc7de74989a630cb88c5a15973", "input": "BACKGROUND Under the Revised National Tuberculosis Control Programme of India, patients with new smear-positive pulmonary tuberculosis are treated with a thrice-weekly regimen of antitubercular drugs (2H(3)R(3)Z(3)E(3)/4H(3)R(3) [H isoniazid, R rifampicin, Z pyrazinamide and E ethambutol]) for 6 months. We conducted a retrospective analysis of the efficacy andtolerability of this regimen under clinical trial conditions in HIV-negative patients with newly diagnosed smear-positive pulmonary tuberculosis.   \n METHODS We retrospectively analysed the data on patients assigned to the control regimen (2H (3)R(3)Z(3)E(3)/4H(3)R(3)) in two clinical trials during 2001-06 at the National Institute for Research in Tuberculosis, Chennai, India.   \n RESULTS Of the 268 patients treated with this regimen, data for efficacy analysis were available for 249. At the end of treatment, of 249 patients, 238 (96%) had a favourable status. Treatment failure occurred in the remaining 11: 7 in whom the organisms were initially drug-susceptible and 4 with initial drug resistance. Of the 238 patients who had a favourable status at the end of treatment, 14 (6%) had recurrence of tuberculosis during the following 24 months. In the intention-to-treat analysis, 245 (94%) of 262 patients had a favourable status at the end of treatment. Of the 28 patients with initial drug resistance, 24 (86%) had a favourable outcome. Only 4 of these 24 patients were found to have recurrence of tuberculosis in 2 years of follow-up. Among the 221 patients initially infected with drug-susceptible organisms, drug resistance did not develop in any of the 7 patients in whom the treatment failed or the 10 who had recurrence of tuberculosis. Further, 5 of the 7 patients in whom the treatment failed continued to excrete drug-susceptible bacilli at 6 months. Adverse drug reactions were observed in 38 (14%) of the 262 patients. Only 3 (1.1%) needed a modification in the treatment.   \n CONCLUSION This thrice-weekly 6-month regimen of antitubercular drugs, when administered under full supervision, is associated with a high rate of favourable treatment outcomes in HIV-negative patients with newly diagnosed sputum smearpositive pulmonary tuberculosis. There are few adverse drug reactions in these patients.", "output": ["Efficacy of the 6-month thrice-weekly regimen in the treatment of new sputum smear-positive pulmonary tuberculosis under clinical trial conditions."]}, "Instance License": ["CC BY-NC 2.0"], "prediction": "This thrice-weekly antitubercular drug regimen is associated with a high rate of favourable treatment outcomes in HIV-negative patients with newly diagnosed sputum smearpositive pulmonary tuberculosis."}
+{"id": "task1586-609d473000e241219f7b85e9937e5a11", "Task": "task1586_scifact_title_generation", "Contributors": "['Nakul Vaidya']", "Source": ["scifact"], "URL": ["https://huggingface.co/datasets/scifact"], "Categories": ["Title Generation"], "Reasoning": [], "Definition": ["In this task, you are given an abstract of article. Your task is to generate title for this article. Preferred titles are under thirty words."], "Positive Examples": [{"input": "Alterations of the architecture of cerebral white matter in the developing human brain can affect cortical development and result in functional disabilities. A line scan diffusion-weighted magnetic resonance imaging (MRI) sequence with diffusion tensor analysis was applied to measure the apparent diffusion coefficient, to calculate relative anisotropy, and to delineate three-dimensional fiber architecture in cerebral white matter in preterm (n = 17) and full-term infants (n = 7). To assess effects of prematurity on cerebral white matter development, early gestation preterm infants (n = 10) were studied a second time at term. In the central white matter the mean apparent diffusion coefficient at 28 wk was high, 1.8 microm2/ms, and decreased toward term to 1.2 microm2/ms. In the posterior limb of the internal capsule, the mean apparent diffusion coefficients at both times were similar (1.2 versus 1.1 microm2/ms). Relative anisotropy was higher the closer birth was to term with greater absolute values in the internal capsule than in the central white matter. Preterm infants at term showed higher mean diffusion coefficients in the central white matter (1.4 +/- 0.24 versus 1.15 +/- 0.09 microm2/ms, p = 0.016) and lower relative anisotropy in both areas compared with full-term infants (white matter, 10.9 +/- 0.6 versus 22.9 +/- 3.0%, p = 0.001; internal capsule, 24.0 +/- 4.44 versus 33.1 +/- 0.6% p = 0.006). Nonmyelinated fibers in the corpus callosum were visible by diffusion tensor MRI as early as 28 wk; full-term and preterm infants at term showed marked differences in white matter fiber organization. The data indicate that quantitative assessment of water diffusion by diffusion tensor MRI provides insight into microstructural development in cerebral white matter in living infants.", "output": "Microstructural development of human newborn cerebral white matter assessed in vivo by diffusion tensor magnetic resonance imaging.", "explanation": "This title is appropriate for the given abstract because the focus of this abstract is cerebral white matter assesment."}, {"input": "Myelodysplastic syndromes (MDS) are age-dependent stem cell malignancies that share biological features of activated adaptive immune response and ineffective hematopoiesis. Here we report that myeloid-derived suppressor cells (MDSC), which are classically linked to immunosuppression, inflammation, and cancer, were markedly expanded in the bone marrow of MDS patients and played a pathogenetic role in the development of ineffective hematopoiesis. These clonally distinct MDSC overproduce hematopoietic suppressive cytokines and function as potent apoptotic effectors targeting autologous hematopoietic progenitors. Using multiple transfected cell models, we found that MDSC expansion is driven by the interaction of the proinflammatory molecule S100A9 with CD33. These 2 proteins formed a functional ligand/receptor pair that recruited components to CD33\u2019s immunoreceptor tyrosine-based inhibition motif (ITIM), inducing secretion of the suppressive cytokines IL-10 and TGF-\u03b2 by immature myeloid cells. S100A9 transgenic mice displayed bone marrow accumulation of MDSC accompanied by development of progressive multilineage cytopenias and cytological dysplasia. Importantly, early forced maturation of MDSC by either all-trans-retinoic acid treatment or active immunoreceptor tyrosine-based activation motif\u2013bearing (ITAM-bearing) adapter protein (DAP12) interruption of CD33 signaling rescued the hematologic phenotype. These findings indicate that primary bone marrow expansion of MDSC driven by the S100A9/CD33 pathway perturbs hematopoiesis and contributes to the development of MDS.", "output": "Induction of myelodysplasia by myeloid-derived suppressor cells.", "explanation": "This title is appropriate for the given abstract because the focus of this abstract is myelodysplastic syndromes."}], "Negative Examples": [{"input": "Alterations of the architecture of cerebral white matter in the developing human brain can affect cortical development and result in functional disabilities. A line scan diffusion-weighted magnetic resonance imaging (MRI) sequence with diffusion tensor analysis was applied to measure the apparent diffusion coefficient, to calculate relative anisotropy, and to delineate three-dimensional fiber architecture in cerebral white matter in preterm (n = 17) and full-term infants (n = 7). To assess effects of prematurity on cerebral white matter development, early gestation preterm infants (n = 10) were studied a second time at term. In the central white matter the mean apparent diffusion coefficient at 28 wk was high, 1.8 microm2/ms, and decreased toward term to 1.2 microm2/ms. In the posterior limb of the internal capsule, the mean apparent diffusion coefficients at both times were similar (1.2 versus 1.1 microm2/ms). Relative anisotropy was higher the closer birth was to term with greater absolute values in the internal capsule than in the central white matter. Preterm infants at term showed higher mean diffusion coefficients in the central white matter (1.4 +/- 0.24 versus 1.15 +/- 0.09 microm2/ms, p = 0.016) and lower relative anisotropy in both areas compared with full-term infants (white matter, 10.9 +/- 0.6 versus 22.9 +/- 3.0%, p = 0.001; internal capsule, 24.0 +/- 4.44 versus 33.1 +/- 0.6% p = 0.006). Nonmyelinated fibers in the corpus callosum were visible by diffusion tensor MRI as early as 28 wk; full-term and preterm infants at term showed marked differences in white matter fiber organization. The data indicate that quantitative assessment of water diffusion by diffusion tensor MRI provides insight into microstructural development in cerebral white matter in living infants.", "output": "Induction of myelodysplasia by myeloid-derived suppressor cells.", "explanation": "This abstract talks about cerebral white matter assesment, but there is no indication about white matter assesment in the given title."}, {"input": "Myelodysplastic syndromes (MDS) are age-dependent stem cell malignancies that share biological features of activated adaptive immune response and ineffective hematopoiesis. Here we report that myeloid-derived suppressor cells (MDSC), which are classically linked to immunosuppression, inflammation, and cancer, were markedly expanded in the bone marrow of MDS patients and played a pathogenetic role in the development of ineffective hematopoiesis. These clonally distinct MDSC overproduce hematopoietic suppressive cytokines and function as potent apoptotic effectors targeting autologous hematopoietic progenitors. Using multiple transfected cell models, we found that MDSC expansion is driven by the interaction of the proinflammatory molecule S100A9 with CD33. These 2 proteins formed a functional ligand/receptor pair that recruited components to CD33\u2019s immunoreceptor tyrosine-based inhibition motif (ITIM), inducing secretion of the suppressive cytokines IL-10 and TGF-\u03b2 by immature myeloid cells. S100A9 transgenic mice displayed bone marrow accumulation of MDSC accompanied by development of progressive multilineage cytopenias and cytological dysplasia. Importantly, early forced maturation of MDSC by either all-trans-retinoic acid treatment or active immunoreceptor tyrosine-based activation motif\u2013bearing (ITAM-bearing) adapter protein (DAP12) interruption of CD33 signaling rescued the hematologic phenotype. These findings indicate that primary bone marrow expansion of MDSC driven by the S100A9/CD33 pathway perturbs hematopoiesis and contributes to the development of MDS.", "output": "Microstructural development of human newborn cerebral white matter assessed in vivo by diffusion tensor magnetic resonance imaging.", "explanation": "Generated title and abstract text is totally different. Hence, this is not a right title."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Scientific Research Papers"], "Instance": {"id": "task1586-609d473000e241219f7b85e9937e5a11", "input": "Regulatory T (T reg) cells are critical regulators of immune tolerance. Most T reg cells are defined based on expression of CD4, CD25, and the transcription factor, FoxP3. However, these markers have proven problematic for uniquely defining this specialized T cell subset in humans. We found that the IL-7 receptor (CD127) is down-regulated on a subset of CD4+ T cells in peripheral blood. We demonstrate that the majority of these cells are FoxP3+, including those that express low levels or no CD25. A combination of CD4, CD25, and CD127 resulted in a highly purified population of T reg cells accounting for significantly more cells that previously identified based on other cell surface markers. These cells were highly suppressive in functional suppressor assays. In fact, cells separated based solely on CD4 and CD127 expression were anergic and, although representing at least three times the number of cells (including both CD25+CD4+ and CD25\u2212CD4+ T cell subsets), were as suppressive as the \u201cclassic\u201d CD4+CD25hi T reg cell subset. Finally, we show that CD127 can be used to quantitate T reg cell subsets in individuals with type 1 diabetes supporting the use of CD127 as a biomarker for human T reg cells.", "output": ["CD127 expression inversely correlates with FoxP3 and suppressive function of human CD4+ T reg cells"]}, "Instance License": ["CC BY-NC 2.0"], "prediction": "IL-7 receptor down-regulated T reg cells in peripheral blood: a novel biomarker for T cell tolerance"}
+{"id": "task1586-ebfa69505c04448eaad7c793fb917a06", "Task": "task1586_scifact_title_generation", "Contributors": "['Nakul Vaidya']", "Source": ["scifact"], "URL": ["https://huggingface.co/datasets/scifact"], "Categories": ["Title Generation"], "Reasoning": [], "Definition": ["In this task, you are given an abstract of article. Your task is to generate title for this article. Preferred titles are under thirty words."], "Positive Examples": [{"input": "Alterations of the architecture of cerebral white matter in the developing human brain can affect cortical development and result in functional disabilities. A line scan diffusion-weighted magnetic resonance imaging (MRI) sequence with diffusion tensor analysis was applied to measure the apparent diffusion coefficient, to calculate relative anisotropy, and to delineate three-dimensional fiber architecture in cerebral white matter in preterm (n = 17) and full-term infants (n = 7). To assess effects of prematurity on cerebral white matter development, early gestation preterm infants (n = 10) were studied a second time at term. In the central white matter the mean apparent diffusion coefficient at 28 wk was high, 1.8 microm2/ms, and decreased toward term to 1.2 microm2/ms. In the posterior limb of the internal capsule, the mean apparent diffusion coefficients at both times were similar (1.2 versus 1.1 microm2/ms). Relative anisotropy was higher the closer birth was to term with greater absolute values in the internal capsule than in the central white matter. Preterm infants at term showed higher mean diffusion coefficients in the central white matter (1.4 +/- 0.24 versus 1.15 +/- 0.09 microm2/ms, p = 0.016) and lower relative anisotropy in both areas compared with full-term infants (white matter, 10.9 +/- 0.6 versus 22.9 +/- 3.0%, p = 0.001; internal capsule, 24.0 +/- 4.44 versus 33.1 +/- 0.6% p = 0.006). Nonmyelinated fibers in the corpus callosum were visible by diffusion tensor MRI as early as 28 wk; full-term and preterm infants at term showed marked differences in white matter fiber organization. The data indicate that quantitative assessment of water diffusion by diffusion tensor MRI provides insight into microstructural development in cerebral white matter in living infants.", "output": "Microstructural development of human newborn cerebral white matter assessed in vivo by diffusion tensor magnetic resonance imaging.", "explanation": "This title is appropriate for the given abstract because the focus of this abstract is cerebral white matter assesment."}, {"input": "Myelodysplastic syndromes (MDS) are age-dependent stem cell malignancies that share biological features of activated adaptive immune response and ineffective hematopoiesis. Here we report that myeloid-derived suppressor cells (MDSC), which are classically linked to immunosuppression, inflammation, and cancer, were markedly expanded in the bone marrow of MDS patients and played a pathogenetic role in the development of ineffective hematopoiesis. These clonally distinct MDSC overproduce hematopoietic suppressive cytokines and function as potent apoptotic effectors targeting autologous hematopoietic progenitors. Using multiple transfected cell models, we found that MDSC expansion is driven by the interaction of the proinflammatory molecule S100A9 with CD33. These 2 proteins formed a functional ligand/receptor pair that recruited components to CD33\u2019s immunoreceptor tyrosine-based inhibition motif (ITIM), inducing secretion of the suppressive cytokines IL-10 and TGF-\u03b2 by immature myeloid cells. S100A9 transgenic mice displayed bone marrow accumulation of MDSC accompanied by development of progressive multilineage cytopenias and cytological dysplasia. Importantly, early forced maturation of MDSC by either all-trans-retinoic acid treatment or active immunoreceptor tyrosine-based activation motif\u2013bearing (ITAM-bearing) adapter protein (DAP12) interruption of CD33 signaling rescued the hematologic phenotype. These findings indicate that primary bone marrow expansion of MDSC driven by the S100A9/CD33 pathway perturbs hematopoiesis and contributes to the development of MDS.", "output": "Induction of myelodysplasia by myeloid-derived suppressor cells.", "explanation": "This title is appropriate for the given abstract because the focus of this abstract is myelodysplastic syndromes."}], "Negative Examples": [{"input": "Alterations of the architecture of cerebral white matter in the developing human brain can affect cortical development and result in functional disabilities. A line scan diffusion-weighted magnetic resonance imaging (MRI) sequence with diffusion tensor analysis was applied to measure the apparent diffusion coefficient, to calculate relative anisotropy, and to delineate three-dimensional fiber architecture in cerebral white matter in preterm (n = 17) and full-term infants (n = 7). To assess effects of prematurity on cerebral white matter development, early gestation preterm infants (n = 10) were studied a second time at term. In the central white matter the mean apparent diffusion coefficient at 28 wk was high, 1.8 microm2/ms, and decreased toward term to 1.2 microm2/ms. In the posterior limb of the internal capsule, the mean apparent diffusion coefficients at both times were similar (1.2 versus 1.1 microm2/ms). Relative anisotropy was higher the closer birth was to term with greater absolute values in the internal capsule than in the central white matter. Preterm infants at term showed higher mean diffusion coefficients in the central white matter (1.4 +/- 0.24 versus 1.15 +/- 0.09 microm2/ms, p = 0.016) and lower relative anisotropy in both areas compared with full-term infants (white matter, 10.9 +/- 0.6 versus 22.9 +/- 3.0%, p = 0.001; internal capsule, 24.0 +/- 4.44 versus 33.1 +/- 0.6% p = 0.006). Nonmyelinated fibers in the corpus callosum were visible by diffusion tensor MRI as early as 28 wk; full-term and preterm infants at term showed marked differences in white matter fiber organization. The data indicate that quantitative assessment of water diffusion by diffusion tensor MRI provides insight into microstructural development in cerebral white matter in living infants.", "output": "Induction of myelodysplasia by myeloid-derived suppressor cells.", "explanation": "This abstract talks about cerebral white matter assesment, but there is no indication about white matter assesment in the given title."}, {"input": "Myelodysplastic syndromes (MDS) are age-dependent stem cell malignancies that share biological features of activated adaptive immune response and ineffective hematopoiesis. Here we report that myeloid-derived suppressor cells (MDSC), which are classically linked to immunosuppression, inflammation, and cancer, were markedly expanded in the bone marrow of MDS patients and played a pathogenetic role in the development of ineffective hematopoiesis. These clonally distinct MDSC overproduce hematopoietic suppressive cytokines and function as potent apoptotic effectors targeting autologous hematopoietic progenitors. Using multiple transfected cell models, we found that MDSC expansion is driven by the interaction of the proinflammatory molecule S100A9 with CD33. These 2 proteins formed a functional ligand/receptor pair that recruited components to CD33\u2019s immunoreceptor tyrosine-based inhibition motif (ITIM), inducing secretion of the suppressive cytokines IL-10 and TGF-\u03b2 by immature myeloid cells. S100A9 transgenic mice displayed bone marrow accumulation of MDSC accompanied by development of progressive multilineage cytopenias and cytological dysplasia. Importantly, early forced maturation of MDSC by either all-trans-retinoic acid treatment or active immunoreceptor tyrosine-based activation motif\u2013bearing (ITAM-bearing) adapter protein (DAP12) interruption of CD33 signaling rescued the hematologic phenotype. These findings indicate that primary bone marrow expansion of MDSC driven by the S100A9/CD33 pathway perturbs hematopoiesis and contributes to the development of MDS.", "output": "Microstructural development of human newborn cerebral white matter assessed in vivo by diffusion tensor magnetic resonance imaging.", "explanation": "Generated title and abstract text is totally different. Hence, this is not a right title."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Scientific Research Papers"], "Instance": {"id": "task1586-ebfa69505c04448eaad7c793fb917a06", "input": "Bone tissue undergoes constant turnover supported by stem cells. Recent studies showed that perivascular mesenchymal stem cells (MSCs) contribute to the turnover of long bones. Craniofacial bones are flat bones derived from a different embryonic origin than the long bones. The identity and regulating niche for craniofacial-bone MSCs remain unknown. Here, we identify Gli1+ cells within the suture mesenchyme as the main MSC population for craniofacial bones. They are not associated with vasculature, give rise to all craniofacial bones in the adult and are activated during injury repair. Gli1+ cells are typical MSCs in vitro. Ablation of Gli1+ cells leads to craniosynostosis and arrest of skull growth, indicating that these cells are an indispensable stem cell population. Twist1(+/-) mice with craniosynostosis show reduced Gli1+ MSCs in sutures, suggesting that craniosynostosis may result from diminished suture stem cells. Our study indicates that craniofacial sutures provide a unique niche for MSCs for craniofacial bone homeostasis and repair.", "output": ["The suture provides a niche for mesenchymal stem cells of craniofacial bones"]}, "Instance License": ["CC BY-NC 2.0"], "prediction": "Identification of Gli1+ cells in suture mesenchyme as the main MSC population for craniofacial bones."}
+{"id": "task602-3696e1d018994616833f653ccb649131", "Task": "task602_wikitext-103_answer_generation", "Contributors": "['Nikitha Munugala']", "Source": ["wikitext"], "URL": ["https://blog.salesforceairesearch.com/the-wikitext-long-term-dependency-language-modeling-dataset/"], "Categories": ["Title Generation"], "Reasoning": [], "Definition": ["Given a text passage, you need to generate a suitable title as the output. The output title should be one of the words/phrases used in the passage and must be no longer than five words. "], "Positive Examples": [{"input": "Paragraph:  Concept work for Valkyria Chronicles III began after development finished on Valkyria Chronicles II in early 2010 , with full development beginning shortly after this . The director of Valkyria Chronicles II , Takeshi Ozawa , returned to that role for Valkyria Chronicles III . Development work took approximately one year . After the release of Valkyria Chronicles II , the staff took a look at both the popular response for the game and what they wanted to do next for the series . Like its predecessor , Valkyria Chronicles III was developed for PlayStation Portable : this was due to the team wanting to refine the mechanics created for Valkyria Chronicles II , and they had not come up with the \" revolutionary \" idea that would warrant a new entry for the PlayStation 3 . Speaking in an interview , it was stated that the development team considered Valkyria Chronicles III to be the series ' first true sequel : while Valkyria Chronicles II had required a large amount of trial and error during development due to the platform move , the third game gave them a chance to improve upon the best parts of Valkyria Chronicles II due to being on the same platform . In addition to Sega staff from the previous games , development work was also handled by Media.Vision. The original scenario was written Kazuki Yamanobe , while the script was written by Hiroyuki Fujii , Koichi Majima , Kishiko Miyagi , Seiki Nagakawa and Takayuki Shouji . Its story was darker and more somber than that of its predecessor . \n The majority of material created for previous games , such as the BLiTZ system and the design of maps , was carried over . Alongside this , improvements were made to the game 's graphics and some elements were expanded , such as map layouts , mission structure , and the number of playable units per mission . A part of this upgrade involved creating unique polygon models for each character 's body . In order to achieve this , the cooperative elements incorporated into the second game were removed , as they took up a large portion of memory space needed for the improvements . They also adjusted the difficulty settings and ease of play so they could appeal to new players while retaining the essential components of the series ' gameplay . The newer systems were decided upon early in development . The character designs were done by Raita Honjou , who had worked on the previous Valkyria Chronicles games . When creating the Nameless Squad , Honjou was faced with the same problem he had had during the first game : the military uniforms essentially destroyed character individuality , despite him needing to create unique characters the player could identify while maintaining a sense of reality within the Valkyria Chronicles world . The main color of the Nameless was black . As with the previous Valkyria games , Valkyria Chronicles III used the CANVAS graphics engine . The anime opening was produced by Production I.G.   Question: what is the suitable title of the passage ?", "output": " Valkyria Chronicles", "explanation": " It is clear from the passage that the answer is Valkyaria Chronicles, as it appears most frequently in the passage."}, {"input": "Paragraph:    The music was composed by Hitoshi Sakimoto , who had also worked on the previous Valkyria Chronicles games . When he originally heard about the project , he thought it would be a light tone similar to other Valkyria Chronicles games , but found the themes much darker than expected . An early theme he designed around his original vision of the project was rejected . He redid the main theme about seven times through the music production due to this need to reassess the game . The main theme was initially recorded using orchestra , then Sakimoto removed elements such as the guitar and bass , then adjusted the theme using a synthesizer before redoing segments such as the guitar piece on their own before incorporating them into the theme . The rejected main theme was used as a hopeful tune that played during the game 's ending . The battle themes were designed around the concept of a \" modern battle \" divorced from a fantasy scenario by using modern musical instruments , constructed to create a sense of atonality . While Sakimoto was most used to working with synthesized music , he felt that he needed to incorporate live instruments such as orchestra and guitar . The guitar was played by Mitsuhiro Ohta , who also arranged several of the later tracks . The game 's opening theme song , \" If You Wish for ... \" ( \u3082\u3057\u3082\u541b\u304c\u9858\u3046\u306e\u306a\u3089 , Moshimo Kimi ga Negauno Nara ) , was sung by Japanese singer May 'n . Its theme was the reason soldiers fought , in particular their wish to protect what was precious to them rather than a sense of responsibility or duty . Its lyrics were written by Seiko Fujibayashi , who had worked on May 'n on previous singles .   Question: what is the suitable title of the passage ?", "output": " Music", "explanation": " It is clear from the passage that the answer is Music, as it appears most frequently in the passage."}], "Negative Examples": [{"input": "Paragraph:    Concept work for Valkyria Chronicles III began after development finished on Valkyria Chronicles II in early 2010 , with full development beginning shortly after this . The director of Valkyria Chronicles II , Takeshi Ozawa , returned to that role for Valkyria Chronicles III . Development work took approximately one year . After the release of Valkyria Chronicles II , the staff took a look at both the popular response for the game and what they wanted to do next for the series . Like its predecessor , Valkyria Chronicles III was developed for PlayStation Portable : this was due to the team wanting to refine the mechanics created for Valkyria Chronicles II , and they had not come up with the \" revolutionary \" idea that would warrant a new entry for the PlayStation 3 . Speaking in an interview , it was stated that the development team considered Valkyria Chronicles III to be the series ' first true sequel : while Valkyria Chronicles II had required a large amount of trial and error during development due to the platform move , the third game gave them a chance to improve upon the best parts of Valkyria Chronicles II due to being on the same platform . In addition to Sega staff from the previous games , development work was also handled by Media.Vision. The original scenario was written Kazuki Yamanobe , while the script was written by Hiroyuki Fujii , Koichi Majima , Kishiko Miyagi , Seiki Nagakawa and Takayuki Shouji . Its story was darker and more somber than that of its predecessor . \n The majority of material created for previous games , such as the BLiTZ system and the design of maps , was carried over . Alongside this , improvements were made to the game 's graphics and some elements were expanded , such as map layouts , mission structure , and the number of playable units per mission . A part of this upgrade involved creating unique polygon models for each character 's body . In order to achieve this , the cooperative elements incorporated into the second game were removed , as they took up a large portion of memory space needed for the improvements . They also adjusted the difficulty settings and ease of play so they could appeal to new players while retaining the essential components of the series ' gameplay . The newer systems were decided upon early in development . The character designs were done by Raita Honjou , who had worked on the previous Valkyria Chronicles games . When creating the Nameless Squad , Honjou was faced with the same problem he had had during the first game : the military uniforms essentially destroyed character individuality , despite him needing to create unique characters the player could identify while maintaining a sense of reality within the Valkyria Chronicles world . The main color of the Nameless was black . As with the previous Valkyria games , Valkyria Chronicles III used the CANVAS graphics engine . The anime opening was produced by Production I.G.   Question: what is the suitable title of the passage ?", "output": "Education", "explanation": " This is a bad example as the answer is not even present in the given context."}, {"input": "Paragraph:    The music was composed by Hitoshi Sakimoto , who had also worked on the previous Valkyria Chronicles games . When he originally heard about the project , he thought it would be a light tone similar to other Valkyria Chronicles games , but found the themes much darker than expected . An early theme he designed around his original vision of the project was rejected . He redid the main theme about seven times through the music production due to this need to reassess the game . The main theme was initially recorded using orchestra , then Sakimoto removed elements such as the guitar and bass , then adjusted the theme using a synthesizer before redoing segments such as the guitar piece on their own before incorporating them into the theme . The rejected main theme was used as a hopeful tune that played during the game 's ending . The battle themes were designed around the concept of a \" modern battle \" divorced from a fantasy scenario by using modern musical instruments , constructed to create a sense of atonality . While Sakimoto was most used to working with synthesized music , he felt that he needed to incorporate live instruments such as orchestra and guitar . The guitar was played by Mitsuhiro Ohta , who also arranged several of the later tracks . The game 's opening theme song , \" If You Wish for ... \" ( \u3082\u3057\u3082\u541b\u304c\u9858\u3046\u306e\u306a\u3089 , Moshimo Kimi ga Negauno Nara ) , was sung by Japanese singer May 'n . Its theme was the reason soldiers fought , in particular their wish to protect what was precious to them rather than a sense of responsibility or duty . Its lyrics were written by Seiko Fujibayashi , who had worked on May 'n on previous singles .   Question: what is the suitable title of the passage ?", "output": " Sports", "explanation": " This is a bad example as the answer is not even present in the given context."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Wikipedia"], "Instance": {"id": "task602-3696e1d018994616833f653ccb649131", "input": "Paragraph:    St. Cecily 's Garden ; 1920 \n Cradle roll design ; St. Edmund 's , Pitlake , 1922 \n Banner design ; St. Mary 's , Sanderstead , 1923 \n The Feeding of the Five Thousand ; reredos triptych , chapel at Penarth , Wales ; 1929 \n The Parable of the Great Supper ; triptych , St. George 's chapel , Waddon \n The Seven Sacraments ; baptismal font panels , St. Andrew 's , Croydon \n St. John the Baptist ; central banner panel , Abesford church , 1943 \n Lettering , sword , and shield ; mount for a list of men and woman serving in the Forces , St. Andrews , Croydon , 1943 \n Baptismal rolls ; St. Andrews , Croydon , 1948 , 1962 \n The font in St Andrew 's Church , South Croydon \n Out of Great Tribulation ; memorial chapel , Norbury Medthodist church , 1948 \n I Am Among You As He That Serveth ; stained glass window design , St. Edmund 's , Pitlake , 1962   \n Question: what is the suitable title of the passage ?", "output": [" Religious works"]}, "Instance License": ["CC BY-SA 4.0"], "prediction": "St. Andrew's Church, South Croydon"}
+{"id": "task602-618c7b60e3014cbc907dc3d3e082fa71", "Task": "task602_wikitext-103_answer_generation", "Contributors": "['Nikitha Munugala']", "Source": ["wikitext"], "URL": ["https://blog.salesforceairesearch.com/the-wikitext-long-term-dependency-language-modeling-dataset/"], "Categories": ["Title Generation"], "Reasoning": [], "Definition": ["Given a text passage, you need to generate a suitable title as the output. The output title should be one of the words/phrases used in the passage and must be no longer than five words. "], "Positive Examples": [{"input": "Paragraph:  Concept work for Valkyria Chronicles III began after development finished on Valkyria Chronicles II in early 2010 , with full development beginning shortly after this . The director of Valkyria Chronicles II , Takeshi Ozawa , returned to that role for Valkyria Chronicles III . Development work took approximately one year . After the release of Valkyria Chronicles II , the staff took a look at both the popular response for the game and what they wanted to do next for the series . Like its predecessor , Valkyria Chronicles III was developed for PlayStation Portable : this was due to the team wanting to refine the mechanics created for Valkyria Chronicles II , and they had not come up with the \" revolutionary \" idea that would warrant a new entry for the PlayStation 3 . Speaking in an interview , it was stated that the development team considered Valkyria Chronicles III to be the series ' first true sequel : while Valkyria Chronicles II had required a large amount of trial and error during development due to the platform move , the third game gave them a chance to improve upon the best parts of Valkyria Chronicles II due to being on the same platform . In addition to Sega staff from the previous games , development work was also handled by Media.Vision. The original scenario was written Kazuki Yamanobe , while the script was written by Hiroyuki Fujii , Koichi Majima , Kishiko Miyagi , Seiki Nagakawa and Takayuki Shouji . Its story was darker and more somber than that of its predecessor . \n The majority of material created for previous games , such as the BLiTZ system and the design of maps , was carried over . Alongside this , improvements were made to the game 's graphics and some elements were expanded , such as map layouts , mission structure , and the number of playable units per mission . A part of this upgrade involved creating unique polygon models for each character 's body . In order to achieve this , the cooperative elements incorporated into the second game were removed , as they took up a large portion of memory space needed for the improvements . They also adjusted the difficulty settings and ease of play so they could appeal to new players while retaining the essential components of the series ' gameplay . The newer systems were decided upon early in development . The character designs were done by Raita Honjou , who had worked on the previous Valkyria Chronicles games . When creating the Nameless Squad , Honjou was faced with the same problem he had had during the first game : the military uniforms essentially destroyed character individuality , despite him needing to create unique characters the player could identify while maintaining a sense of reality within the Valkyria Chronicles world . The main color of the Nameless was black . As with the previous Valkyria games , Valkyria Chronicles III used the CANVAS graphics engine . The anime opening was produced by Production I.G.   Question: what is the suitable title of the passage ?", "output": " Valkyria Chronicles", "explanation": " It is clear from the passage that the answer is Valkyaria Chronicles, as it appears most frequently in the passage."}, {"input": "Paragraph:    The music was composed by Hitoshi Sakimoto , who had also worked on the previous Valkyria Chronicles games . When he originally heard about the project , he thought it would be a light tone similar to other Valkyria Chronicles games , but found the themes much darker than expected . An early theme he designed around his original vision of the project was rejected . He redid the main theme about seven times through the music production due to this need to reassess the game . The main theme was initially recorded using orchestra , then Sakimoto removed elements such as the guitar and bass , then adjusted the theme using a synthesizer before redoing segments such as the guitar piece on their own before incorporating them into the theme . The rejected main theme was used as a hopeful tune that played during the game 's ending . The battle themes were designed around the concept of a \" modern battle \" divorced from a fantasy scenario by using modern musical instruments , constructed to create a sense of atonality . While Sakimoto was most used to working with synthesized music , he felt that he needed to incorporate live instruments such as orchestra and guitar . The guitar was played by Mitsuhiro Ohta , who also arranged several of the later tracks . The game 's opening theme song , \" If You Wish for ... \" ( \u3082\u3057\u3082\u541b\u304c\u9858\u3046\u306e\u306a\u3089 , Moshimo Kimi ga Negauno Nara ) , was sung by Japanese singer May 'n . Its theme was the reason soldiers fought , in particular their wish to protect what was precious to them rather than a sense of responsibility or duty . Its lyrics were written by Seiko Fujibayashi , who had worked on May 'n on previous singles .   Question: what is the suitable title of the passage ?", "output": " Music", "explanation": " It is clear from the passage that the answer is Music, as it appears most frequently in the passage."}], "Negative Examples": [{"input": "Paragraph:    Concept work for Valkyria Chronicles III began after development finished on Valkyria Chronicles II in early 2010 , with full development beginning shortly after this . The director of Valkyria Chronicles II , Takeshi Ozawa , returned to that role for Valkyria Chronicles III . Development work took approximately one year . After the release of Valkyria Chronicles II , the staff took a look at both the popular response for the game and what they wanted to do next for the series . Like its predecessor , Valkyria Chronicles III was developed for PlayStation Portable : this was due to the team wanting to refine the mechanics created for Valkyria Chronicles II , and they had not come up with the \" revolutionary \" idea that would warrant a new entry for the PlayStation 3 . Speaking in an interview , it was stated that the development team considered Valkyria Chronicles III to be the series ' first true sequel : while Valkyria Chronicles II had required a large amount of trial and error during development due to the platform move , the third game gave them a chance to improve upon the best parts of Valkyria Chronicles II due to being on the same platform . In addition to Sega staff from the previous games , development work was also handled by Media.Vision. The original scenario was written Kazuki Yamanobe , while the script was written by Hiroyuki Fujii , Koichi Majima , Kishiko Miyagi , Seiki Nagakawa and Takayuki Shouji . Its story was darker and more somber than that of its predecessor . \n The majority of material created for previous games , such as the BLiTZ system and the design of maps , was carried over . Alongside this , improvements were made to the game 's graphics and some elements were expanded , such as map layouts , mission structure , and the number of playable units per mission . A part of this upgrade involved creating unique polygon models for each character 's body . In order to achieve this , the cooperative elements incorporated into the second game were removed , as they took up a large portion of memory space needed for the improvements . They also adjusted the difficulty settings and ease of play so they could appeal to new players while retaining the essential components of the series ' gameplay . The newer systems were decided upon early in development . The character designs were done by Raita Honjou , who had worked on the previous Valkyria Chronicles games . When creating the Nameless Squad , Honjou was faced with the same problem he had had during the first game : the military uniforms essentially destroyed character individuality , despite him needing to create unique characters the player could identify while maintaining a sense of reality within the Valkyria Chronicles world . The main color of the Nameless was black . As with the previous Valkyria games , Valkyria Chronicles III used the CANVAS graphics engine . The anime opening was produced by Production I.G.   Question: what is the suitable title of the passage ?", "output": "Education", "explanation": " This is a bad example as the answer is not even present in the given context."}, {"input": "Paragraph:    The music was composed by Hitoshi Sakimoto , who had also worked on the previous Valkyria Chronicles games . When he originally heard about the project , he thought it would be a light tone similar to other Valkyria Chronicles games , but found the themes much darker than expected . An early theme he designed around his original vision of the project was rejected . He redid the main theme about seven times through the music production due to this need to reassess the game . The main theme was initially recorded using orchestra , then Sakimoto removed elements such as the guitar and bass , then adjusted the theme using a synthesizer before redoing segments such as the guitar piece on their own before incorporating them into the theme . The rejected main theme was used as a hopeful tune that played during the game 's ending . The battle themes were designed around the concept of a \" modern battle \" divorced from a fantasy scenario by using modern musical instruments , constructed to create a sense of atonality . While Sakimoto was most used to working with synthesized music , he felt that he needed to incorporate live instruments such as orchestra and guitar . The guitar was played by Mitsuhiro Ohta , who also arranged several of the later tracks . The game 's opening theme song , \" If You Wish for ... \" ( \u3082\u3057\u3082\u541b\u304c\u9858\u3046\u306e\u306a\u3089 , Moshimo Kimi ga Negauno Nara ) , was sung by Japanese singer May 'n . Its theme was the reason soldiers fought , in particular their wish to protect what was precious to them rather than a sense of responsibility or duty . Its lyrics were written by Seiko Fujibayashi , who had worked on May 'n on previous singles .   Question: what is the suitable title of the passage ?", "output": " Sports", "explanation": " This is a bad example as the answer is not even present in the given context."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Wikipedia"], "Instance": {"id": "task602-618c7b60e3014cbc907dc3d3e082fa71", "input": "Paragraph:    N @-@ 88 starts at the Nebraska \u2013 Wyoming state line in Banner County , where WYO 151 ends , and travels northeast . The road quickly bends east after less than one mile ( 1 @.@ 6 km ) , and continues in a straight line . For the next twenty miles ( 32 km ) , N @-@ 88 intersects minor streets , through rural farmland . The route turns south at N @-@ 71 , and becomes concurrent . Four miles ( 6 @.@ 4 km ) later , N @-@ 88 turns east , ending the concurrency with N @-@ 71 . The route continues to travel through farmland for sixteen miles ( 26 km ) , where it enters Morrill County . The road crosses over Pumpkin Creek four times , and enters the unincorporated community of Redington . Two rock formations , Courthouse and Jail Rocks , become visible from the road . N @-@ 88 turns north toward Bridgeport soon after . The road crosses over Pumpkin Creek for the fifth time , and enters into Bridgeport five miles ( 8 @.@ 0 km ) later . The road intersects a railroad owned by BNSF Railway . N @-@ 88 turns northeast soon after , and ends at the intersection of US 385 and N @-@ 92 . In 2012 , Nebraska Department of Roads ( NDOR ) calculated as many as 2 @,@ 410 vehicles traveling on the N @-@ 71 / N @-@ 88 concurrency , and as few as 315 vehicles traveling east of the Banner \u2013 Morrill county line . This is expressed in terms of annual average daily traffic ( AADT ) , a measure of traffic volume for any average day of the year . Only the N @-@ 71 / N @-@ 88 concurrency is part of the National Highway System ( NHS ) , a network of highways identified as being most important for the economy , mobility and defense of the nation .   Question: what is the suitable title of the passage ?", "output": [" Route description"]}, "Instance License": ["CC BY-SA 4.0"], "prediction": "N @-@ 88 starts at the Nebraska \u2013 Wyoming state line in Banner County, where WYO 151 ends, and travels northeast."}
+{"id": "task602-41e937c617eb41e18c96f5906b6dc39b", "Task": "task602_wikitext-103_answer_generation", "Contributors": "['Nikitha Munugala']", "Source": ["wikitext"], "URL": ["https://blog.salesforceairesearch.com/the-wikitext-long-term-dependency-language-modeling-dataset/"], "Categories": ["Title Generation"], "Reasoning": [], "Definition": ["Given a text passage, you need to generate a suitable title as the output. The output title should be one of the words/phrases used in the passage and must be no longer than five words. "], "Positive Examples": [{"input": "Paragraph:  Concept work for Valkyria Chronicles III began after development finished on Valkyria Chronicles II in early 2010 , with full development beginning shortly after this . The director of Valkyria Chronicles II , Takeshi Ozawa , returned to that role for Valkyria Chronicles III . Development work took approximately one year . After the release of Valkyria Chronicles II , the staff took a look at both the popular response for the game and what they wanted to do next for the series . Like its predecessor , Valkyria Chronicles III was developed for PlayStation Portable : this was due to the team wanting to refine the mechanics created for Valkyria Chronicles II , and they had not come up with the \" revolutionary \" idea that would warrant a new entry for the PlayStation 3 . Speaking in an interview , it was stated that the development team considered Valkyria Chronicles III to be the series ' first true sequel : while Valkyria Chronicles II had required a large amount of trial and error during development due to the platform move , the third game gave them a chance to improve upon the best parts of Valkyria Chronicles II due to being on the same platform . In addition to Sega staff from the previous games , development work was also handled by Media.Vision. The original scenario was written Kazuki Yamanobe , while the script was written by Hiroyuki Fujii , Koichi Majima , Kishiko Miyagi , Seiki Nagakawa and Takayuki Shouji . Its story was darker and more somber than that of its predecessor . \n The majority of material created for previous games , such as the BLiTZ system and the design of maps , was carried over . Alongside this , improvements were made to the game 's graphics and some elements were expanded , such as map layouts , mission structure , and the number of playable units per mission . A part of this upgrade involved creating unique polygon models for each character 's body . In order to achieve this , the cooperative elements incorporated into the second game were removed , as they took up a large portion of memory space needed for the improvements . They also adjusted the difficulty settings and ease of play so they could appeal to new players while retaining the essential components of the series ' gameplay . The newer systems were decided upon early in development . The character designs were done by Raita Honjou , who had worked on the previous Valkyria Chronicles games . When creating the Nameless Squad , Honjou was faced with the same problem he had had during the first game : the military uniforms essentially destroyed character individuality , despite him needing to create unique characters the player could identify while maintaining a sense of reality within the Valkyria Chronicles world . The main color of the Nameless was black . As with the previous Valkyria games , Valkyria Chronicles III used the CANVAS graphics engine . The anime opening was produced by Production I.G.   Question: what is the suitable title of the passage ?", "output": " Valkyria Chronicles", "explanation": " It is clear from the passage that the answer is Valkyaria Chronicles, as it appears most frequently in the passage."}, {"input": "Paragraph:    The music was composed by Hitoshi Sakimoto , who had also worked on the previous Valkyria Chronicles games . When he originally heard about the project , he thought it would be a light tone similar to other Valkyria Chronicles games , but found the themes much darker than expected . An early theme he designed around his original vision of the project was rejected . He redid the main theme about seven times through the music production due to this need to reassess the game . The main theme was initially recorded using orchestra , then Sakimoto removed elements such as the guitar and bass , then adjusted the theme using a synthesizer before redoing segments such as the guitar piece on their own before incorporating them into the theme . The rejected main theme was used as a hopeful tune that played during the game 's ending . The battle themes were designed around the concept of a \" modern battle \" divorced from a fantasy scenario by using modern musical instruments , constructed to create a sense of atonality . While Sakimoto was most used to working with synthesized music , he felt that he needed to incorporate live instruments such as orchestra and guitar . The guitar was played by Mitsuhiro Ohta , who also arranged several of the later tracks . The game 's opening theme song , \" If You Wish for ... \" ( \u3082\u3057\u3082\u541b\u304c\u9858\u3046\u306e\u306a\u3089 , Moshimo Kimi ga Negauno Nara ) , was sung by Japanese singer May 'n . Its theme was the reason soldiers fought , in particular their wish to protect what was precious to them rather than a sense of responsibility or duty . Its lyrics were written by Seiko Fujibayashi , who had worked on May 'n on previous singles .   Question: what is the suitable title of the passage ?", "output": " Music", "explanation": " It is clear from the passage that the answer is Music, as it appears most frequently in the passage."}], "Negative Examples": [{"input": "Paragraph:    Concept work for Valkyria Chronicles III began after development finished on Valkyria Chronicles II in early 2010 , with full development beginning shortly after this . The director of Valkyria Chronicles II , Takeshi Ozawa , returned to that role for Valkyria Chronicles III . Development work took approximately one year . After the release of Valkyria Chronicles II , the staff took a look at both the popular response for the game and what they wanted to do next for the series . Like its predecessor , Valkyria Chronicles III was developed for PlayStation Portable : this was due to the team wanting to refine the mechanics created for Valkyria Chronicles II , and they had not come up with the \" revolutionary \" idea that would warrant a new entry for the PlayStation 3 . Speaking in an interview , it was stated that the development team considered Valkyria Chronicles III to be the series ' first true sequel : while Valkyria Chronicles II had required a large amount of trial and error during development due to the platform move , the third game gave them a chance to improve upon the best parts of Valkyria Chronicles II due to being on the same platform . In addition to Sega staff from the previous games , development work was also handled by Media.Vision. The original scenario was written Kazuki Yamanobe , while the script was written by Hiroyuki Fujii , Koichi Majima , Kishiko Miyagi , Seiki Nagakawa and Takayuki Shouji . Its story was darker and more somber than that of its predecessor . \n The majority of material created for previous games , such as the BLiTZ system and the design of maps , was carried over . Alongside this , improvements were made to the game 's graphics and some elements were expanded , such as map layouts , mission structure , and the number of playable units per mission . A part of this upgrade involved creating unique polygon models for each character 's body . In order to achieve this , the cooperative elements incorporated into the second game were removed , as they took up a large portion of memory space needed for the improvements . They also adjusted the difficulty settings and ease of play so they could appeal to new players while retaining the essential components of the series ' gameplay . The newer systems were decided upon early in development . The character designs were done by Raita Honjou , who had worked on the previous Valkyria Chronicles games . When creating the Nameless Squad , Honjou was faced with the same problem he had had during the first game : the military uniforms essentially destroyed character individuality , despite him needing to create unique characters the player could identify while maintaining a sense of reality within the Valkyria Chronicles world . The main color of the Nameless was black . As with the previous Valkyria games , Valkyria Chronicles III used the CANVAS graphics engine . The anime opening was produced by Production I.G.   Question: what is the suitable title of the passage ?", "output": "Education", "explanation": " This is a bad example as the answer is not even present in the given context."}, {"input": "Paragraph:    The music was composed by Hitoshi Sakimoto , who had also worked on the previous Valkyria Chronicles games . When he originally heard about the project , he thought it would be a light tone similar to other Valkyria Chronicles games , but found the themes much darker than expected . An early theme he designed around his original vision of the project was rejected . He redid the main theme about seven times through the music production due to this need to reassess the game . The main theme was initially recorded using orchestra , then Sakimoto removed elements such as the guitar and bass , then adjusted the theme using a synthesizer before redoing segments such as the guitar piece on their own before incorporating them into the theme . The rejected main theme was used as a hopeful tune that played during the game 's ending . The battle themes were designed around the concept of a \" modern battle \" divorced from a fantasy scenario by using modern musical instruments , constructed to create a sense of atonality . While Sakimoto was most used to working with synthesized music , he felt that he needed to incorporate live instruments such as orchestra and guitar . The guitar was played by Mitsuhiro Ohta , who also arranged several of the later tracks . The game 's opening theme song , \" If You Wish for ... \" ( \u3082\u3057\u3082\u541b\u304c\u9858\u3046\u306e\u306a\u3089 , Moshimo Kimi ga Negauno Nara ) , was sung by Japanese singer May 'n . Its theme was the reason soldiers fought , in particular their wish to protect what was precious to them rather than a sense of responsibility or duty . Its lyrics were written by Seiko Fujibayashi , who had worked on May 'n on previous singles .   Question: what is the suitable title of the passage ?", "output": " Sports", "explanation": " This is a bad example as the answer is not even present in the given context."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Wikipedia"], "Instance": {"id": "task602-41e937c617eb41e18c96f5906b6dc39b", "input": "Paragraph:    Barker took correspondence courses in art , probably until about 1919 . In 1908 at 13 years , she entered an evening class at the Croydon School of Art , and attended the school into the 1940s . In time , she received a teaching position . \n In 1911 , Raphael Tuck & Sons bought four of Barker 's \" little drawings \" for half a sovereign , and published them as postcards . In October 1911 , she won second prize in the Croydon Art Society 's poster competition , and shortly afterward was elected the youngest member of the Society . The art critic for the Croydon Advertiser remarked , \" Her drawings show a remarkable freedom of spirit . She has distinct promise . \" \n Following her father \u2019 s death in June 1912 , the seventeen @-@ year @-@ old Barker submitted art and poetry to My Magazine , Child \u2019 s Own , Leading Strings , and Raphael Tuck annuals in an effort to support both her mother and sister . Her sister Dorothy taught kindergarten in two private schools before opening a kindergarten at home . She brought in some money for the family 's support while supervising the household .   Question: what is the suitable title of the passage ?", "output": [" Art education and first professional work"]}, "Instance License": ["CC BY-SA 4.0"], "prediction": "\" The Little Drawings \""}
+{"id": "task602-b99bb73c0eda46d38d9e93fc8f430928", "Task": "task602_wikitext-103_answer_generation", "Contributors": "['Nikitha Munugala']", "Source": ["wikitext"], "URL": ["https://blog.salesforceairesearch.com/the-wikitext-long-term-dependency-language-modeling-dataset/"], "Categories": ["Title Generation"], "Reasoning": [], "Definition": ["Given a text passage, you need to generate a suitable title as the output. The output title should be one of the words/phrases used in the passage and must be no longer than five words. "], "Positive Examples": [{"input": "Paragraph:  Concept work for Valkyria Chronicles III began after development finished on Valkyria Chronicles II in early 2010 , with full development beginning shortly after this . The director of Valkyria Chronicles II , Takeshi Ozawa , returned to that role for Valkyria Chronicles III . Development work took approximately one year . After the release of Valkyria Chronicles II , the staff took a look at both the popular response for the game and what they wanted to do next for the series . Like its predecessor , Valkyria Chronicles III was developed for PlayStation Portable : this was due to the team wanting to refine the mechanics created for Valkyria Chronicles II , and they had not come up with the \" revolutionary \" idea that would warrant a new entry for the PlayStation 3 . Speaking in an interview , it was stated that the development team considered Valkyria Chronicles III to be the series ' first true sequel : while Valkyria Chronicles II had required a large amount of trial and error during development due to the platform move , the third game gave them a chance to improve upon the best parts of Valkyria Chronicles II due to being on the same platform . In addition to Sega staff from the previous games , development work was also handled by Media.Vision. The original scenario was written Kazuki Yamanobe , while the script was written by Hiroyuki Fujii , Koichi Majima , Kishiko Miyagi , Seiki Nagakawa and Takayuki Shouji . Its story was darker and more somber than that of its predecessor . \n The majority of material created for previous games , such as the BLiTZ system and the design of maps , was carried over . Alongside this , improvements were made to the game 's graphics and some elements were expanded , such as map layouts , mission structure , and the number of playable units per mission . A part of this upgrade involved creating unique polygon models for each character 's body . In order to achieve this , the cooperative elements incorporated into the second game were removed , as they took up a large portion of memory space needed for the improvements . They also adjusted the difficulty settings and ease of play so they could appeal to new players while retaining the essential components of the series ' gameplay . The newer systems were decided upon early in development . The character designs were done by Raita Honjou , who had worked on the previous Valkyria Chronicles games . When creating the Nameless Squad , Honjou was faced with the same problem he had had during the first game : the military uniforms essentially destroyed character individuality , despite him needing to create unique characters the player could identify while maintaining a sense of reality within the Valkyria Chronicles world . The main color of the Nameless was black . As with the previous Valkyria games , Valkyria Chronicles III used the CANVAS graphics engine . The anime opening was produced by Production I.G.   Question: what is the suitable title of the passage ?", "output": " Valkyria Chronicles", "explanation": " It is clear from the passage that the answer is Valkyaria Chronicles, as it appears most frequently in the passage."}, {"input": "Paragraph:    The music was composed by Hitoshi Sakimoto , who had also worked on the previous Valkyria Chronicles games . When he originally heard about the project , he thought it would be a light tone similar to other Valkyria Chronicles games , but found the themes much darker than expected . An early theme he designed around his original vision of the project was rejected . He redid the main theme about seven times through the music production due to this need to reassess the game . The main theme was initially recorded using orchestra , then Sakimoto removed elements such as the guitar and bass , then adjusted the theme using a synthesizer before redoing segments such as the guitar piece on their own before incorporating them into the theme . The rejected main theme was used as a hopeful tune that played during the game 's ending . The battle themes were designed around the concept of a \" modern battle \" divorced from a fantasy scenario by using modern musical instruments , constructed to create a sense of atonality . While Sakimoto was most used to working with synthesized music , he felt that he needed to incorporate live instruments such as orchestra and guitar . The guitar was played by Mitsuhiro Ohta , who also arranged several of the later tracks . The game 's opening theme song , \" If You Wish for ... \" ( \u3082\u3057\u3082\u541b\u304c\u9858\u3046\u306e\u306a\u3089 , Moshimo Kimi ga Negauno Nara ) , was sung by Japanese singer May 'n . Its theme was the reason soldiers fought , in particular their wish to protect what was precious to them rather than a sense of responsibility or duty . Its lyrics were written by Seiko Fujibayashi , who had worked on May 'n on previous singles .   Question: what is the suitable title of the passage ?", "output": " Music", "explanation": " It is clear from the passage that the answer is Music, as it appears most frequently in the passage."}], "Negative Examples": [{"input": "Paragraph:    Concept work for Valkyria Chronicles III began after development finished on Valkyria Chronicles II in early 2010 , with full development beginning shortly after this . The director of Valkyria Chronicles II , Takeshi Ozawa , returned to that role for Valkyria Chronicles III . Development work took approximately one year . After the release of Valkyria Chronicles II , the staff took a look at both the popular response for the game and what they wanted to do next for the series . Like its predecessor , Valkyria Chronicles III was developed for PlayStation Portable : this was due to the team wanting to refine the mechanics created for Valkyria Chronicles II , and they had not come up with the \" revolutionary \" idea that would warrant a new entry for the PlayStation 3 . Speaking in an interview , it was stated that the development team considered Valkyria Chronicles III to be the series ' first true sequel : while Valkyria Chronicles II had required a large amount of trial and error during development due to the platform move , the third game gave them a chance to improve upon the best parts of Valkyria Chronicles II due to being on the same platform . In addition to Sega staff from the previous games , development work was also handled by Media.Vision. The original scenario was written Kazuki Yamanobe , while the script was written by Hiroyuki Fujii , Koichi Majima , Kishiko Miyagi , Seiki Nagakawa and Takayuki Shouji . Its story was darker and more somber than that of its predecessor . \n The majority of material created for previous games , such as the BLiTZ system and the design of maps , was carried over . Alongside this , improvements were made to the game 's graphics and some elements were expanded , such as map layouts , mission structure , and the number of playable units per mission . A part of this upgrade involved creating unique polygon models for each character 's body . In order to achieve this , the cooperative elements incorporated into the second game were removed , as they took up a large portion of memory space needed for the improvements . They also adjusted the difficulty settings and ease of play so they could appeal to new players while retaining the essential components of the series ' gameplay . The newer systems were decided upon early in development . The character designs were done by Raita Honjou , who had worked on the previous Valkyria Chronicles games . When creating the Nameless Squad , Honjou was faced with the same problem he had had during the first game : the military uniforms essentially destroyed character individuality , despite him needing to create unique characters the player could identify while maintaining a sense of reality within the Valkyria Chronicles world . The main color of the Nameless was black . As with the previous Valkyria games , Valkyria Chronicles III used the CANVAS graphics engine . The anime opening was produced by Production I.G.   Question: what is the suitable title of the passage ?", "output": "Education", "explanation": " This is a bad example as the answer is not even present in the given context."}, {"input": "Paragraph:    The music was composed by Hitoshi Sakimoto , who had also worked on the previous Valkyria Chronicles games . When he originally heard about the project , he thought it would be a light tone similar to other Valkyria Chronicles games , but found the themes much darker than expected . An early theme he designed around his original vision of the project was rejected . He redid the main theme about seven times through the music production due to this need to reassess the game . The main theme was initially recorded using orchestra , then Sakimoto removed elements such as the guitar and bass , then adjusted the theme using a synthesizer before redoing segments such as the guitar piece on their own before incorporating them into the theme . The rejected main theme was used as a hopeful tune that played during the game 's ending . The battle themes were designed around the concept of a \" modern battle \" divorced from a fantasy scenario by using modern musical instruments , constructed to create a sense of atonality . While Sakimoto was most used to working with synthesized music , he felt that he needed to incorporate live instruments such as orchestra and guitar . The guitar was played by Mitsuhiro Ohta , who also arranged several of the later tracks . The game 's opening theme song , \" If You Wish for ... \" ( \u3082\u3057\u3082\u541b\u304c\u9858\u3046\u306e\u306a\u3089 , Moshimo Kimi ga Negauno Nara ) , was sung by Japanese singer May 'n . Its theme was the reason soldiers fought , in particular their wish to protect what was precious to them rather than a sense of responsibility or duty . Its lyrics were written by Seiko Fujibayashi , who had worked on May 'n on previous singles .   Question: what is the suitable title of the passage ?", "output": " Sports", "explanation": " This is a bad example as the answer is not even present in the given context."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Wikipedia"], "Instance": {"id": "task602-b99bb73c0eda46d38d9e93fc8f430928", "input": "Paragraph:    The accompanying music video begins with a shot of an empty street , followed by clips of disadvantaged and poorer members of society going about their daily activities . Two men play dominoes on a wooden crate outside a building , a gang make fun of an elderly man hanging newspapers outside his store and an obese woman walks down the street . Clips of Carey leaning against a wall and sitting on some steps looking on at what is happening are shown . As the first chorus begins , everyone starts to dance joyfully in the street and help those in need . A gospel choir comes out of one of the buildings as the street becomes more crowded with people of all ages and backgrounds rejoicing and getting along with each other . One of the shops in the background has a neon light outside the entrance which says \" Jesus Saves \" .   Question: what is the suitable title of the passage ?", "output": [" Music video"]}, "Instance License": ["CC BY-SA 4.0"], "prediction": "Jesus Saves"}
+{"id": "task602-98ba4414cd744513ba81498b2271836a", "Task": "task602_wikitext-103_answer_generation", "Contributors": "['Nikitha Munugala']", "Source": ["wikitext"], "URL": ["https://blog.salesforceairesearch.com/the-wikitext-long-term-dependency-language-modeling-dataset/"], "Categories": ["Title Generation"], "Reasoning": [], "Definition": ["Given a text passage, you need to generate a suitable title as the output. The output title should be one of the words/phrases used in the passage and must be no longer than five words. "], "Positive Examples": [{"input": "Paragraph:  Concept work for Valkyria Chronicles III began after development finished on Valkyria Chronicles II in early 2010 , with full development beginning shortly after this . The director of Valkyria Chronicles II , Takeshi Ozawa , returned to that role for Valkyria Chronicles III . Development work took approximately one year . After the release of Valkyria Chronicles II , the staff took a look at both the popular response for the game and what they wanted to do next for the series . Like its predecessor , Valkyria Chronicles III was developed for PlayStation Portable : this was due to the team wanting to refine the mechanics created for Valkyria Chronicles II , and they had not come up with the \" revolutionary \" idea that would warrant a new entry for the PlayStation 3 . Speaking in an interview , it was stated that the development team considered Valkyria Chronicles III to be the series ' first true sequel : while Valkyria Chronicles II had required a large amount of trial and error during development due to the platform move , the third game gave them a chance to improve upon the best parts of Valkyria Chronicles II due to being on the same platform . In addition to Sega staff from the previous games , development work was also handled by Media.Vision. The original scenario was written Kazuki Yamanobe , while the script was written by Hiroyuki Fujii , Koichi Majima , Kishiko Miyagi , Seiki Nagakawa and Takayuki Shouji . Its story was darker and more somber than that of its predecessor . \n The majority of material created for previous games , such as the BLiTZ system and the design of maps , was carried over . Alongside this , improvements were made to the game 's graphics and some elements were expanded , such as map layouts , mission structure , and the number of playable units per mission . A part of this upgrade involved creating unique polygon models for each character 's body . In order to achieve this , the cooperative elements incorporated into the second game were removed , as they took up a large portion of memory space needed for the improvements . They also adjusted the difficulty settings and ease of play so they could appeal to new players while retaining the essential components of the series ' gameplay . The newer systems were decided upon early in development . The character designs were done by Raita Honjou , who had worked on the previous Valkyria Chronicles games . When creating the Nameless Squad , Honjou was faced with the same problem he had had during the first game : the military uniforms essentially destroyed character individuality , despite him needing to create unique characters the player could identify while maintaining a sense of reality within the Valkyria Chronicles world . The main color of the Nameless was black . As with the previous Valkyria games , Valkyria Chronicles III used the CANVAS graphics engine . The anime opening was produced by Production I.G.   Question: what is the suitable title of the passage ?", "output": " Valkyria Chronicles", "explanation": " It is clear from the passage that the answer is Valkyaria Chronicles, as it appears most frequently in the passage."}, {"input": "Paragraph:    The music was composed by Hitoshi Sakimoto , who had also worked on the previous Valkyria Chronicles games . When he originally heard about the project , he thought it would be a light tone similar to other Valkyria Chronicles games , but found the themes much darker than expected . An early theme he designed around his original vision of the project was rejected . He redid the main theme about seven times through the music production due to this need to reassess the game . The main theme was initially recorded using orchestra , then Sakimoto removed elements such as the guitar and bass , then adjusted the theme using a synthesizer before redoing segments such as the guitar piece on their own before incorporating them into the theme . The rejected main theme was used as a hopeful tune that played during the game 's ending . The battle themes were designed around the concept of a \" modern battle \" divorced from a fantasy scenario by using modern musical instruments , constructed to create a sense of atonality . While Sakimoto was most used to working with synthesized music , he felt that he needed to incorporate live instruments such as orchestra and guitar . The guitar was played by Mitsuhiro Ohta , who also arranged several of the later tracks . The game 's opening theme song , \" If You Wish for ... \" ( \u3082\u3057\u3082\u541b\u304c\u9858\u3046\u306e\u306a\u3089 , Moshimo Kimi ga Negauno Nara ) , was sung by Japanese singer May 'n . Its theme was the reason soldiers fought , in particular their wish to protect what was precious to them rather than a sense of responsibility or duty . Its lyrics were written by Seiko Fujibayashi , who had worked on May 'n on previous singles .   Question: what is the suitable title of the passage ?", "output": " Music", "explanation": " It is clear from the passage that the answer is Music, as it appears most frequently in the passage."}], "Negative Examples": [{"input": "Paragraph:    Concept work for Valkyria Chronicles III began after development finished on Valkyria Chronicles II in early 2010 , with full development beginning shortly after this . The director of Valkyria Chronicles II , Takeshi Ozawa , returned to that role for Valkyria Chronicles III . Development work took approximately one year . After the release of Valkyria Chronicles II , the staff took a look at both the popular response for the game and what they wanted to do next for the series . Like its predecessor , Valkyria Chronicles III was developed for PlayStation Portable : this was due to the team wanting to refine the mechanics created for Valkyria Chronicles II , and they had not come up with the \" revolutionary \" idea that would warrant a new entry for the PlayStation 3 . Speaking in an interview , it was stated that the development team considered Valkyria Chronicles III to be the series ' first true sequel : while Valkyria Chronicles II had required a large amount of trial and error during development due to the platform move , the third game gave them a chance to improve upon the best parts of Valkyria Chronicles II due to being on the same platform . In addition to Sega staff from the previous games , development work was also handled by Media.Vision. The original scenario was written Kazuki Yamanobe , while the script was written by Hiroyuki Fujii , Koichi Majima , Kishiko Miyagi , Seiki Nagakawa and Takayuki Shouji . Its story was darker and more somber than that of its predecessor . \n The majority of material created for previous games , such as the BLiTZ system and the design of maps , was carried over . Alongside this , improvements were made to the game 's graphics and some elements were expanded , such as map layouts , mission structure , and the number of playable units per mission . A part of this upgrade involved creating unique polygon models for each character 's body . In order to achieve this , the cooperative elements incorporated into the second game were removed , as they took up a large portion of memory space needed for the improvements . They also adjusted the difficulty settings and ease of play so they could appeal to new players while retaining the essential components of the series ' gameplay . The newer systems were decided upon early in development . The character designs were done by Raita Honjou , who had worked on the previous Valkyria Chronicles games . When creating the Nameless Squad , Honjou was faced with the same problem he had had during the first game : the military uniforms essentially destroyed character individuality , despite him needing to create unique characters the player could identify while maintaining a sense of reality within the Valkyria Chronicles world . The main color of the Nameless was black . As with the previous Valkyria games , Valkyria Chronicles III used the CANVAS graphics engine . The anime opening was produced by Production I.G.   Question: what is the suitable title of the passage ?", "output": "Education", "explanation": " This is a bad example as the answer is not even present in the given context."}, {"input": "Paragraph:    The music was composed by Hitoshi Sakimoto , who had also worked on the previous Valkyria Chronicles games . When he originally heard about the project , he thought it would be a light tone similar to other Valkyria Chronicles games , but found the themes much darker than expected . An early theme he designed around his original vision of the project was rejected . He redid the main theme about seven times through the music production due to this need to reassess the game . The main theme was initially recorded using orchestra , then Sakimoto removed elements such as the guitar and bass , then adjusted the theme using a synthesizer before redoing segments such as the guitar piece on their own before incorporating them into the theme . The rejected main theme was used as a hopeful tune that played during the game 's ending . The battle themes were designed around the concept of a \" modern battle \" divorced from a fantasy scenario by using modern musical instruments , constructed to create a sense of atonality . While Sakimoto was most used to working with synthesized music , he felt that he needed to incorporate live instruments such as orchestra and guitar . The guitar was played by Mitsuhiro Ohta , who also arranged several of the later tracks . The game 's opening theme song , \" If You Wish for ... \" ( \u3082\u3057\u3082\u541b\u304c\u9858\u3046\u306e\u306a\u3089 , Moshimo Kimi ga Negauno Nara ) , was sung by Japanese singer May 'n . Its theme was the reason soldiers fought , in particular their wish to protect what was precious to them rather than a sense of responsibility or duty . Its lyrics were written by Seiko Fujibayashi , who had worked on May 'n on previous singles .   Question: what is the suitable title of the passage ?", "output": " Sports", "explanation": " This is a bad example as the answer is not even present in the given context."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Wikipedia"], "Instance": {"id": "task602-98ba4414cd744513ba81498b2271836a", "input": "Paragraph:    On its day of release in Japan , Valkyria Chronicles III topped both platform @-@ exclusive and multi @-@ platform sales charts . By early February , the game sold 102 @,@ 779 units , coming in second overall to The Last Story for the Wii . By the end of the year , the game had sold just over 152 @,@ 500 units . \n Famitsu enjoyed the story , and were particularly pleased with the improvements to gameplay . Japanese gaming site Game Watch Impress , despite negatively noting its pacing and elements recycled from previous games , was generally positive about its story and characters , and found its gameplay entertaining despite off @-@ putting difficulty spikes . 4Gamer.net writer Naohiko Misuosame , in a \" Play Test \" article based on the game 's PSN demo , felt that Valkyria Chronicles III provided a \" profound feeling of closure \" for the Valkyria Chronicles series . He praised its gameplay despite annoying limitations to aspects such as special abilities , and positively noted its shift in story to a tone similar to the first game . \n PlayStation Official Magazine - UK praised the story 's blurring of Gallia 's moral standing , art style , and most points about its gameplay , positively noting the latter for both its continued quality and the tweaks to balance and content . Its one major criticism were multiple difficulty spikes , something that had affected the previous games . Heath Hindman of gaming website PlayStation Lifestyle praised the addition of non @-@ linear elements and improvements or removal of mechanics from Valkyria Chronicles II in addition to praising the returning gameplay style of previous games . He also positively noted the story 's serious tone . Points criticized in the review were recycled elements , awkward cutscenes that seemed to include all characters in a scene for no good reason , pacing issues , and occasional problems with the game 's AI . \n In a preview of the TGS demo , Ryan Geddes of IGN was left excited as to where the game would go after completing the demo , along with enjoying the improved visuals over Valkyria Chronicles II . Kotaku 's Richard Eisenbeis was highly positive about the game , citing is story as a return to form after Valkyria Chronicles II and its gameplay being the best in the series . His main criticisms were its length and gameplay repetition , along with expressing regret that it would not be localized .   Question: what is the suitable title of the passage ?", "output": [" Reception"]}, "Instance License": ["CC BY-SA 4.0"], "prediction": "Valkyria Chronicles III"}
+{"id": "task1195-b4afdf0e695c436fa403fe2a09c1fa03", "Task": "task1195_disflqa_disfluent_to_fluent_conversion", "Contributors": "['Arjun Ashok']", "Source": ["disfl_qa"], "URL": ["https://github.com/google-research-datasets/Disfl-QA"], "Categories": ["Question Rewriting"], "Reasoning": [], "Definition": ["Given a disfluent sentence, modify the sentence to it to its equivalent fluent form, preserving the meaning of the sentence."], "Positive Examples": [{"input": "Who did the Han Chinese want to help the Khitan no I mean the Mongols fight?", "output": "Who did the Han Chinese want to help the Mongols fight?", "explanation": "The input initially means Khitan and then changes to Mongols, hence this is correct."}, {"input": "What part did no I meant how many chapters have coordinating lead authors?", "output": "How many chapters have coordinating lead authors?", "explanation": "The input initially means which part, and then changes to how many chapters. Hence this is correct."}, {"input": "How did no Who masterminded many terror attacks?", "output": "Who masterminded many terror attacks?", "explanation": "The input initially means how and then changes to who, hence this is correct."}], "Negative Examples": [{"input": "Where is the oldest known sedimentary sequence or rather rock in the world located?", "output": "How is the oldest known rock in the world located?", "explanation": "The output changes the interrogative word from the input."}, {"input": "For how many years had sea levels been studied in the 2001 report no temperatures?", "output": "For how many years had sea levels been studied in the 2001 report?", "explanation": "The input initially means sea levels and then changes to temperature, but the output does not reflect that."}, {"input": "The contrast of what no the second item of business on Wednesdays is usually what?", "output": "The contrast of business on Wednesdays is usually what?", "explanation": "The input initially means the constrast of and then changes to the second item, but the output does not reflect that."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Wikipedia"], "Instance": {"id": "task1195-b4afdf0e695c436fa403fe2a09c1fa03", "input": "In what other way can disobedience be applied to international unions no rather organizations and governments?", "output": ["In what other way can disobedience be applied to international organizations and governments?"]}, "Instance License": ["CC BY 4.0"], "prediction": "In what other way can disobedience be applied to international unions no rather organizations and governments?"}
+{"id": "task1195-6c125a6fca1e4c718bc98a41e30724f2", "Task": "task1195_disflqa_disfluent_to_fluent_conversion", "Contributors": "['Arjun Ashok']", "Source": ["disfl_qa"], "URL": ["https://github.com/google-research-datasets/Disfl-QA"], "Categories": ["Question Rewriting"], "Reasoning": [], "Definition": ["Given a disfluent sentence, modify the sentence to it to its equivalent fluent form, preserving the meaning of the sentence."], "Positive Examples": [{"input": "Who did the Han Chinese want to help the Khitan no I mean the Mongols fight?", "output": "Who did the Han Chinese want to help the Mongols fight?", "explanation": "The input initially means Khitan and then changes to Mongols, hence this is correct."}, {"input": "What part did no I meant how many chapters have coordinating lead authors?", "output": "How many chapters have coordinating lead authors?", "explanation": "The input initially means which part, and then changes to how many chapters. Hence this is correct."}, {"input": "How did no Who masterminded many terror attacks?", "output": "Who masterminded many terror attacks?", "explanation": "The input initially means how and then changes to who, hence this is correct."}], "Negative Examples": [{"input": "Where is the oldest known sedimentary sequence or rather rock in the world located?", "output": "How is the oldest known rock in the world located?", "explanation": "The output changes the interrogative word from the input."}, {"input": "For how many years had sea levels been studied in the 2001 report no temperatures?", "output": "For how many years had sea levels been studied in the 2001 report?", "explanation": "The input initially means sea levels and then changes to temperature, but the output does not reflect that."}, {"input": "The contrast of what no the second item of business on Wednesdays is usually what?", "output": "The contrast of business on Wednesdays is usually what?", "explanation": "The input initially means the constrast of and then changes to the second item, but the output does not reflect that."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Wikipedia"], "Instance": {"id": "task1195-6c125a6fca1e4c718bc98a41e30724f2", "input": "What year no how many branches does the Zuider Zee brackish lagoon have?", "output": ["How many branches does the Zuider Zee brackish lagoon have?"]}, "Instance License": ["CC BY 4.0"], "prediction": "What year no how many branches does the Zuider Zee brackish lagoon have?"}
+{"id": "task1195-2bddda2556dc42b0a915b200d70737dc", "Task": "task1195_disflqa_disfluent_to_fluent_conversion", "Contributors": "['Arjun Ashok']", "Source": ["disfl_qa"], "URL": ["https://github.com/google-research-datasets/Disfl-QA"], "Categories": ["Question Rewriting"], "Reasoning": [], "Definition": ["Given a disfluent sentence, modify the sentence to it to its equivalent fluent form, preserving the meaning of the sentence."], "Positive Examples": [{"input": "Who did the Han Chinese want to help the Khitan no I mean the Mongols fight?", "output": "Who did the Han Chinese want to help the Mongols fight?", "explanation": "The input initially means Khitan and then changes to Mongols, hence this is correct."}, {"input": "What part did no I meant how many chapters have coordinating lead authors?", "output": "How many chapters have coordinating lead authors?", "explanation": "The input initially means which part, and then changes to how many chapters. Hence this is correct."}, {"input": "How did no Who masterminded many terror attacks?", "output": "Who masterminded many terror attacks?", "explanation": "The input initially means how and then changes to who, hence this is correct."}], "Negative Examples": [{"input": "Where is the oldest known sedimentary sequence or rather rock in the world located?", "output": "How is the oldest known rock in the world located?", "explanation": "The output changes the interrogative word from the input."}, {"input": "For how many years had sea levels been studied in the 2001 report no temperatures?", "output": "For how many years had sea levels been studied in the 2001 report?", "explanation": "The input initially means sea levels and then changes to temperature, but the output does not reflect that."}, {"input": "The contrast of what no the second item of business on Wednesdays is usually what?", "output": "The contrast of business on Wednesdays is usually what?", "explanation": "The input initially means the constrast of and then changes to the second item, but the output does not reflect that."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Wikipedia"], "Instance": {"id": "task1195-2bddda2556dc42b0a915b200d70737dc", "input": "When was the first class taught at the University of Texas no sorry Chicago?", "output": ["What year was the first class taught at the University of Chicago?"]}, "Instance License": ["CC BY 4.0"], "prediction": "When was the first class taught at the University of Texas?"}
+{"id": "task1195-28245f4d682a4693b85e0b4c39ccd99c", "Task": "task1195_disflqa_disfluent_to_fluent_conversion", "Contributors": "['Arjun Ashok']", "Source": ["disfl_qa"], "URL": ["https://github.com/google-research-datasets/Disfl-QA"], "Categories": ["Question Rewriting"], "Reasoning": [], "Definition": ["Given a disfluent sentence, modify the sentence to it to its equivalent fluent form, preserving the meaning of the sentence."], "Positive Examples": [{"input": "Who did the Han Chinese want to help the Khitan no I mean the Mongols fight?", "output": "Who did the Han Chinese want to help the Mongols fight?", "explanation": "The input initially means Khitan and then changes to Mongols, hence this is correct."}, {"input": "What part did no I meant how many chapters have coordinating lead authors?", "output": "How many chapters have coordinating lead authors?", "explanation": "The input initially means which part, and then changes to how many chapters. Hence this is correct."}, {"input": "How did no Who masterminded many terror attacks?", "output": "Who masterminded many terror attacks?", "explanation": "The input initially means how and then changes to who, hence this is correct."}], "Negative Examples": [{"input": "Where is the oldest known sedimentary sequence or rather rock in the world located?", "output": "How is the oldest known rock in the world located?", "explanation": "The output changes the interrogative word from the input."}, {"input": "For how many years had sea levels been studied in the 2001 report no temperatures?", "output": "For how many years had sea levels been studied in the 2001 report?", "explanation": "The input initially means sea levels and then changes to temperature, but the output does not reflect that."}, {"input": "The contrast of what no the second item of business on Wednesdays is usually what?", "output": "The contrast of business on Wednesdays is usually what?", "explanation": "The input initially means the constrast of and then changes to the second item, but the output does not reflect that."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Wikipedia"], "Instance": {"id": "task1195-28245f4d682a4693b85e0b4c39ccd99c", "input": "What do x.25 and Frame Relay both provide no sorry what do they require?", "output": ["WHat do x.25 and Frame Relay both require"]}, "Instance License": ["CC BY 4.0"], "prediction": "What do x.25 and Frame Relay both provide?"}
+{"id": "task1195-8c8c5b45bb664cc1b7e29a42fec072f2", "Task": "task1195_disflqa_disfluent_to_fluent_conversion", "Contributors": "['Arjun Ashok']", "Source": ["disfl_qa"], "URL": ["https://github.com/google-research-datasets/Disfl-QA"], "Categories": ["Question Rewriting"], "Reasoning": [], "Definition": ["Given a disfluent sentence, modify the sentence to it to its equivalent fluent form, preserving the meaning of the sentence."], "Positive Examples": [{"input": "Who did the Han Chinese want to help the Khitan no I mean the Mongols fight?", "output": "Who did the Han Chinese want to help the Mongols fight?", "explanation": "The input initially means Khitan and then changes to Mongols, hence this is correct."}, {"input": "What part did no I meant how many chapters have coordinating lead authors?", "output": "How many chapters have coordinating lead authors?", "explanation": "The input initially means which part, and then changes to how many chapters. Hence this is correct."}, {"input": "How did no Who masterminded many terror attacks?", "output": "Who masterminded many terror attacks?", "explanation": "The input initially means how and then changes to who, hence this is correct."}], "Negative Examples": [{"input": "Where is the oldest known sedimentary sequence or rather rock in the world located?", "output": "How is the oldest known rock in the world located?", "explanation": "The output changes the interrogative word from the input."}, {"input": "For how many years had sea levels been studied in the 2001 report no temperatures?", "output": "For how many years had sea levels been studied in the 2001 report?", "explanation": "The input initially means sea levels and then changes to temperature, but the output does not reflect that."}, {"input": "The contrast of what no the second item of business on Wednesdays is usually what?", "output": "The contrast of business on Wednesdays is usually what?", "explanation": "The input initially means the constrast of and then changes to the second item, but the output does not reflect that."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Wikipedia"], "Instance": {"id": "task1195-8c8c5b45bb664cc1b7e29a42fec072f2", "input": "Who had Toghun Temur oops Toghtogha tried to defeat?", "output": ["Who had Toghtogha tried to defeat?"]}, "Instance License": ["CC BY 4.0"], "prediction": "Who had Toghun Temur oops Toghtogha tried to defeat?"}
+{"id": "task1409-1da5f3967a9748138e77d13a925615b7", "Task": "task1409_dart_text_generation", "Contributors": "['Rushang Karia']", "Source": ["dart"], "URL": ["https://huggingface.co/datasets/dart"], "Categories": ["Data to Text"], "Reasoning": [], "Definition": ["In this task, you are given triplets. Each triplet is in the form of [subject, predicate, object]. Your task is to generate proper sentence that utilizes these triples. The objective is to construct a sentence that (a) captures the facts specified in the triples and (b) is a well-formed sentence easily understandable by a human. All triple values need not be used directly in the sentence as long as the facts are adequately captured."], "Positive Examples": [{"input": "[['Northwestern College', 'NICKNAME', 'Red Raiders'], ['Northwestern College', 'LOCATION', 'Orange City, Iowa']]", "output": "The team whose nickname is red raiders is located in the orange city, iowa", "explanation": "This sentence uses the triplets by correctly using the (subject, predicate, object) semantics for both the triplets provided. Since college teams are popularly associated with nicknames, some information in the generated sentence can be inferred. In this case, Northwestern College was replaced with the team automatically."}, {"input": "[['University of Mississippi', 'NEW_CONFERENCE', 'SELC']]", "output": "University of mississippi was in the selc new conference.", "explanation": "This sentence logically follows from the triplet provided. The subject (University of Mississippi) interacts with the object (SELC) using the predicate (NEW_CONFERENCE). The statement is grammatically correct and logically follows from the triplet."}, {"input": "[['hear the birds', 'SEASON_3_EP_#', '12']]", "output": "The title of season 3 episode 12 is \"Hear the Birds.\"", "explanation": "This sentence is based on the subject (hear the birds) associated with being a part of the object (12) via the predicate (season_3_ep_#). This sentence is a good example since it is easily interpretable by a human and it is likely that this sentence would be generated by a human given access to just the triplet."}], "Negative Examples": [{"input": "[['Graham Edwards', 'PROVINCE', 'North Metropolitan']]", "output": "Province North Metropolitan Province is represented by the Graham.", "explanation": "This sentence is a bad example since even though it utilizes the triplets, it does not form a coherent statement correctly. The subject (Graham Edwards) appears as the object in this statement. The correct output could be Graham Edwards is in the North Metropolitan Province."}, {"input": "[['Li Qiaoxian (CHN)', 'PRELIMINARY_RANK', '6']]", "output": "Li Qiaoxian has 6 ranks in China.", "explanation": "This sentence is not a good example because the intention conveyed by the triplets is not accurately represented by the generated sentence."}, {"input": "[['2006', 'COMPETITION', 'Commonwealth Games'], ['[TABLECONTEXT]', 'YEAR', '2006'], ['[TABLECONTEXT]', '[TITLE]', 'Olivia McKoy']]", "output": "Mrs. Olivia McKoy born 2006 participated in the Olympics", "explanation": "This sentence is a negative example since the generated sentence misappropriates the facts that are represented by the triplet. For example, addressing Olivia as 'Mrs' is factually incorrect assuming that she is born is 2006, which makes her a minor. Also, intuitively, 2006 was likely associated with the competition and not w.r.t. Olivia."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Wikipedia"], "Instance": {"id": "task1409-1da5f3967a9748138e77d13a925615b7", "input": "[['Chicago Road Informational Designation', 'LOCATION', 'US-12 and Prairie River Road (Park 1.5 miles west of Bronson)'], ['US-12 and Prairie River Road (Park 1.5 miles west of Bronson)', 'CITY', 'Bronson Township']]", "output": ["The Chicago Road Informational Designation is located in the Bronson Township."]}, "Instance License": ["MIT"], "prediction": "Chicago road informational designation is located on the us-12 and prairie river road inbronson twp."}
+{"id": "task1409-024f908c946243b4a7a1a25a457e3885", "Task": "task1409_dart_text_generation", "Contributors": "['Rushang Karia']", "Source": ["dart"], "URL": ["https://huggingface.co/datasets/dart"], "Categories": ["Data to Text"], "Reasoning": [], "Definition": ["In this task, you are given triplets. Each triplet is in the form of [subject, predicate, object]. Your task is to generate proper sentence that utilizes these triples. The objective is to construct a sentence that (a) captures the facts specified in the triples and (b) is a well-formed sentence easily understandable by a human. All triple values need not be used directly in the sentence as long as the facts are adequately captured."], "Positive Examples": [{"input": "[['Northwestern College', 'NICKNAME', 'Red Raiders'], ['Northwestern College', 'LOCATION', 'Orange City, Iowa']]", "output": "The team whose nickname is red raiders is located in the orange city, iowa", "explanation": "This sentence uses the triplets by correctly using the (subject, predicate, object) semantics for both the triplets provided. Since college teams are popularly associated with nicknames, some information in the generated sentence can be inferred. In this case, Northwestern College was replaced with the team automatically."}, {"input": "[['University of Mississippi', 'NEW_CONFERENCE', 'SELC']]", "output": "University of mississippi was in the selc new conference.", "explanation": "This sentence logically follows from the triplet provided. The subject (University of Mississippi) interacts with the object (SELC) using the predicate (NEW_CONFERENCE). The statement is grammatically correct and logically follows from the triplet."}, {"input": "[['hear the birds', 'SEASON_3_EP_#', '12']]", "output": "The title of season 3 episode 12 is \"Hear the Birds.\"", "explanation": "This sentence is based on the subject (hear the birds) associated with being a part of the object (12) via the predicate (season_3_ep_#). This sentence is a good example since it is easily interpretable by a human and it is likely that this sentence would be generated by a human given access to just the triplet."}], "Negative Examples": [{"input": "[['Graham Edwards', 'PROVINCE', 'North Metropolitan']]", "output": "Province North Metropolitan Province is represented by the Graham.", "explanation": "This sentence is a bad example since even though it utilizes the triplets, it does not form a coherent statement correctly. The subject (Graham Edwards) appears as the object in this statement. The correct output could be Graham Edwards is in the North Metropolitan Province."}, {"input": "[['Li Qiaoxian (CHN)', 'PRELIMINARY_RANK', '6']]", "output": "Li Qiaoxian has 6 ranks in China.", "explanation": "This sentence is not a good example because the intention conveyed by the triplets is not accurately represented by the generated sentence."}, {"input": "[['2006', 'COMPETITION', 'Commonwealth Games'], ['[TABLECONTEXT]', 'YEAR', '2006'], ['[TABLECONTEXT]', '[TITLE]', 'Olivia McKoy']]", "output": "Mrs. Olivia McKoy born 2006 participated in the Olympics", "explanation": "This sentence is a negative example since the generated sentence misappropriates the facts that are represented by the triplet. For example, addressing Olivia as 'Mrs' is factually incorrect assuming that she is born is 2006, which makes her a minor. Also, intuitively, 2006 was likely associated with the competition and not w.r.t. Olivia."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Wikipedia"], "Instance": {"id": "task1409-024f908c946243b4a7a1a25a457e3885", "input": "[['nbsp', 'STANDARD', 'HTML 3.2'], ['[TABLECONTEXT]', '[TITLE]', 'List of XML and HTML character entity references'], ['[TABLECONTEXT]', 'NAME', 'nbsp']]", "output": ["The Standard reference for nbsp is HTML 3.2"]}, "Instance License": ["MIT"], "prediction": "nbsp is a standard of xml and html character entity reference."}
+{"id": "task1409-00139a31bb004b2cae11cce11d704ad6", "Task": "task1409_dart_text_generation", "Contributors": "['Rushang Karia']", "Source": ["dart"], "URL": ["https://huggingface.co/datasets/dart"], "Categories": ["Data to Text"], "Reasoning": [], "Definition": ["In this task, you are given triplets. Each triplet is in the form of [subject, predicate, object]. Your task is to generate proper sentence that utilizes these triples. The objective is to construct a sentence that (a) captures the facts specified in the triples and (b) is a well-formed sentence easily understandable by a human. All triple values need not be used directly in the sentence as long as the facts are adequately captured."], "Positive Examples": [{"input": "[['Northwestern College', 'NICKNAME', 'Red Raiders'], ['Northwestern College', 'LOCATION', 'Orange City, Iowa']]", "output": "The team whose nickname is red raiders is located in the orange city, iowa", "explanation": "This sentence uses the triplets by correctly using the (subject, predicate, object) semantics for both the triplets provided. Since college teams are popularly associated with nicknames, some information in the generated sentence can be inferred. In this case, Northwestern College was replaced with the team automatically."}, {"input": "[['University of Mississippi', 'NEW_CONFERENCE', 'SELC']]", "output": "University of mississippi was in the selc new conference.", "explanation": "This sentence logically follows from the triplet provided. The subject (University of Mississippi) interacts with the object (SELC) using the predicate (NEW_CONFERENCE). The statement is grammatically correct and logically follows from the triplet."}, {"input": "[['hear the birds', 'SEASON_3_EP_#', '12']]", "output": "The title of season 3 episode 12 is \"Hear the Birds.\"", "explanation": "This sentence is based on the subject (hear the birds) associated with being a part of the object (12) via the predicate (season_3_ep_#). This sentence is a good example since it is easily interpretable by a human and it is likely that this sentence would be generated by a human given access to just the triplet."}], "Negative Examples": [{"input": "[['Graham Edwards', 'PROVINCE', 'North Metropolitan']]", "output": "Province North Metropolitan Province is represented by the Graham.", "explanation": "This sentence is a bad example since even though it utilizes the triplets, it does not form a coherent statement correctly. The subject (Graham Edwards) appears as the object in this statement. The correct output could be Graham Edwards is in the North Metropolitan Province."}, {"input": "[['Li Qiaoxian (CHN)', 'PRELIMINARY_RANK', '6']]", "output": "Li Qiaoxian has 6 ranks in China.", "explanation": "This sentence is not a good example because the intention conveyed by the triplets is not accurately represented by the generated sentence."}, {"input": "[['2006', 'COMPETITION', 'Commonwealth Games'], ['[TABLECONTEXT]', 'YEAR', '2006'], ['[TABLECONTEXT]', '[TITLE]', 'Olivia McKoy']]", "output": "Mrs. Olivia McKoy born 2006 participated in the Olympics", "explanation": "This sentence is a negative example since the generated sentence misappropriates the facts that are represented by the triplet. For example, addressing Olivia as 'Mrs' is factually incorrect assuming that she is born is 2006, which makes her a minor. Also, intuitively, 2006 was likely associated with the competition and not w.r.t. Olivia."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Wikipedia"], "Instance": {"id": "task1409-00139a31bb004b2cae11cce11d704ad6", "input": "[['The Cambridge Blue', 'eatType', 'restaurant'], ['The Cambridge Blue', 'customer rating', 'average']]", "output": ["The Cambridge Blue is a three star restaurant located in the middle of nowhere", "The Cambridge Blue is a three star rated restaurant that sells sushi.", "There is a three star rated restaurant called The Cambridge Blue that sells sushi.", "The Cambridge Blue is a three star restaurant located in the middle of nowhere", "The average customer rated restaurant is The Cambridge Blue.", "The Cambridge Blue restaurant has been rated 3 out of 5 stars. It offers wine, spirits, and appetizers.", "The Cambridge Blue is a 3 star restaurant that offers a selection of wine, spirits and appetizers.", "The Cambridge Blue restaurant, food and drink. Rated three stars."]}, "Instance License": ["MIT"], "prediction": "The Cambridge blue has an average customer rating."}
+{"id": "task1409-aa6602e6c34d44988e6a7158edc7701a", "Task": "task1409_dart_text_generation", "Contributors": "['Rushang Karia']", "Source": ["dart"], "URL": ["https://huggingface.co/datasets/dart"], "Categories": ["Data to Text"], "Reasoning": [], "Definition": ["In this task, you are given triplets. Each triplet is in the form of [subject, predicate, object]. Your task is to generate proper sentence that utilizes these triples. The objective is to construct a sentence that (a) captures the facts specified in the triples and (b) is a well-formed sentence easily understandable by a human. All triple values need not be used directly in the sentence as long as the facts are adequately captured."], "Positive Examples": [{"input": "[['Northwestern College', 'NICKNAME', 'Red Raiders'], ['Northwestern College', 'LOCATION', 'Orange City, Iowa']]", "output": "The team whose nickname is red raiders is located in the orange city, iowa", "explanation": "This sentence uses the triplets by correctly using the (subject, predicate, object) semantics for both the triplets provided. Since college teams are popularly associated with nicknames, some information in the generated sentence can be inferred. In this case, Northwestern College was replaced with the team automatically."}, {"input": "[['University of Mississippi', 'NEW_CONFERENCE', 'SELC']]", "output": "University of mississippi was in the selc new conference.", "explanation": "This sentence logically follows from the triplet provided. The subject (University of Mississippi) interacts with the object (SELC) using the predicate (NEW_CONFERENCE). The statement is grammatically correct and logically follows from the triplet."}, {"input": "[['hear the birds', 'SEASON_3_EP_#', '12']]", "output": "The title of season 3 episode 12 is \"Hear the Birds.\"", "explanation": "This sentence is based on the subject (hear the birds) associated with being a part of the object (12) via the predicate (season_3_ep_#). This sentence is a good example since it is easily interpretable by a human and it is likely that this sentence would be generated by a human given access to just the triplet."}], "Negative Examples": [{"input": "[['Graham Edwards', 'PROVINCE', 'North Metropolitan']]", "output": "Province North Metropolitan Province is represented by the Graham.", "explanation": "This sentence is a bad example since even though it utilizes the triplets, it does not form a coherent statement correctly. The subject (Graham Edwards) appears as the object in this statement. The correct output could be Graham Edwards is in the North Metropolitan Province."}, {"input": "[['Li Qiaoxian (CHN)', 'PRELIMINARY_RANK', '6']]", "output": "Li Qiaoxian has 6 ranks in China.", "explanation": "This sentence is not a good example because the intention conveyed by the triplets is not accurately represented by the generated sentence."}, {"input": "[['2006', 'COMPETITION', 'Commonwealth Games'], ['[TABLECONTEXT]', 'YEAR', '2006'], ['[TABLECONTEXT]', '[TITLE]', 'Olivia McKoy']]", "output": "Mrs. Olivia McKoy born 2006 participated in the Olympics", "explanation": "This sentence is a negative example since the generated sentence misappropriates the facts that are represented by the triplet. For example, addressing Olivia as 'Mrs' is factually incorrect assuming that she is born is 2006, which makes her a minor. Also, intuitively, 2006 was likely associated with the competition and not w.r.t. Olivia."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Wikipedia"], "Instance": {"id": "task1409-aa6602e6c34d44988e6a7158edc7701a", "input": "[['The Wrestlers', 'food', 'English'], ['The Wrestlers', 'customer rating', 'high'], ['The Wrestlers', 'familyFriendly', 'yes']]", "output": ["The Wrestlers provides English food for \u00a320-\u00a325. It is child friendly and has high customer rating."]}, "Instance License": ["MIT"], "prediction": "The wrestlers is a family friendly restaurant."}
+{"id": "task1409-caf71d305d58409fb733eb474cf77a92", "Task": "task1409_dart_text_generation", "Contributors": "['Rushang Karia']", "Source": ["dart"], "URL": ["https://huggingface.co/datasets/dart"], "Categories": ["Data to Text"], "Reasoning": [], "Definition": ["In this task, you are given triplets. Each triplet is in the form of [subject, predicate, object]. Your task is to generate proper sentence that utilizes these triples. The objective is to construct a sentence that (a) captures the facts specified in the triples and (b) is a well-formed sentence easily understandable by a human. All triple values need not be used directly in the sentence as long as the facts are adequately captured."], "Positive Examples": [{"input": "[['Northwestern College', 'NICKNAME', 'Red Raiders'], ['Northwestern College', 'LOCATION', 'Orange City, Iowa']]", "output": "The team whose nickname is red raiders is located in the orange city, iowa", "explanation": "This sentence uses the triplets by correctly using the (subject, predicate, object) semantics for both the triplets provided. Since college teams are popularly associated with nicknames, some information in the generated sentence can be inferred. In this case, Northwestern College was replaced with the team automatically."}, {"input": "[['University of Mississippi', 'NEW_CONFERENCE', 'SELC']]", "output": "University of mississippi was in the selc new conference.", "explanation": "This sentence logically follows from the triplet provided. The subject (University of Mississippi) interacts with the object (SELC) using the predicate (NEW_CONFERENCE). The statement is grammatically correct and logically follows from the triplet."}, {"input": "[['hear the birds', 'SEASON_3_EP_#', '12']]", "output": "The title of season 3 episode 12 is \"Hear the Birds.\"", "explanation": "This sentence is based on the subject (hear the birds) associated with being a part of the object (12) via the predicate (season_3_ep_#). This sentence is a good example since it is easily interpretable by a human and it is likely that this sentence would be generated by a human given access to just the triplet."}], "Negative Examples": [{"input": "[['Graham Edwards', 'PROVINCE', 'North Metropolitan']]", "output": "Province North Metropolitan Province is represented by the Graham.", "explanation": "This sentence is a bad example since even though it utilizes the triplets, it does not form a coherent statement correctly. The subject (Graham Edwards) appears as the object in this statement. The correct output could be Graham Edwards is in the North Metropolitan Province."}, {"input": "[['Li Qiaoxian (CHN)', 'PRELIMINARY_RANK', '6']]", "output": "Li Qiaoxian has 6 ranks in China.", "explanation": "This sentence is not a good example because the intention conveyed by the triplets is not accurately represented by the generated sentence."}, {"input": "[['2006', 'COMPETITION', 'Commonwealth Games'], ['[TABLECONTEXT]', 'YEAR', '2006'], ['[TABLECONTEXT]', '[TITLE]', 'Olivia McKoy']]", "output": "Mrs. Olivia McKoy born 2006 participated in the Olympics", "explanation": "This sentence is a negative example since the generated sentence misappropriates the facts that are represented by the triplet. For example, addressing Olivia as 'Mrs' is factually incorrect assuming that she is born is 2006, which makes her a minor. Also, intuitively, 2006 was likely associated with the competition and not w.r.t. Olivia."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Wikipedia"], "Instance": {"id": "task1409-caf71d305d58409fb733eb474cf77a92", "input": "[['[TABLECONTEXT]', '[TITLE]', '1996-97 FA Cup'], ['[TABLECONTEXT]', 'TIE_NO', '1'], ['1', 'AWAY_TEAM', 'Nottingham Forest'], ['1', 'SCORE', '1-0'], ['1', 'HOME_TEAM', 'Chesterfield']]", "output": ["In 1996-97 FA Cup, Chesterfield at home played against Nottingham Forest with score 1-0"]}, "Instance License": ["MIT"], "prediction": "The table contains the title of the 1996-97 FA cup, the away team, the score and the home team."}
+{"id": "task033-15333cb838e7455e826f518cef1c373a", "Task": "task033_winogrande_answer_generation", "Contributors": "['Swaroop Mishra', 'Daniel Khashabi']", "Source": ["winogrande"], "URL": ["https://leaderboard.allenai.org/winogrande/submissions/about"], "Categories": ["Coreference Resolution"], "Reasoning": ["Commonsense Reasoning"], "Definition": ["You need to answer a given question containing a blank (_). Your answer must be one of the two objects mentioned in the question, for example \"trophy\" and \"suitcase\". Your answer must not contain a word that is not present in the question. Please don't use articles (e.g., the, a) before the answer."], "Positive Examples": [{"input": "The trophy doesn't fit into the brown suitcase because _ is too large.", "output": "trophy", "explanation": "Answer is one of the objects (\"trophy\" and \"suitcase\") in the question. Since the blank is a \"large\" object that didn't fit the \"suitcase\", the answer must be \"trophy\"."}, {"input": "Grace was happy to trade me her sweater for my jacket. She thinks _ looks dowdy on her.", "output": "sweater", "explanation": "The word \"dowdy\" decides the answer among the objects (\"sweater\" and \"jacket\") present in the question."}, {"input": "While redecorating her home, Sam took out the carpet and replaced it with wood floors. The _ was old.", "output": "carpet", "explanation": "The blank is \"old\", it must be what gets \"replaced\", which has to be \"carpet\"."}, {"input": "The table won't fit through the doorway because the _ is too wide.", "output": "table", "explanation": "Answer is one of the objects (\"table\" and \"doorway\") in the question. Since the blank co-appears with \"too wide\". it must be the object that didn't \"fit through the doorway\" (i.e., \"the table\")."}, {"input": "I poured water from the bottle into the cup until the _ was empty.", "output": "bottle", "explanation": "Answer is one of the objects (\"bottle\" and \"cup\") in the question. Therefore, this is a valid answer. Since _ become \"empty\", it must be the container from which the water was poured from (\"bottle\")."}, {"input": "My meeting started at 4:00 and I needed to catch the train at 4:30, so there wasn't much time. Luckily, the _ was short, so it worked out.", "output": "meeting", "explanation": "Here \"meeting\" and \"train\" are the objects. Since the blank was \"short\", which worked out (was able to \"catch the train\"), the answer must be \"meeting\"."}, {"input": "James wanted to light the candle in the wind when on a date but the _ is too weak.", "output": "light", "explanation": "Here \"light\" and \"wind\" are the objects. The connective \"but\" indicates that \"James\" was not able to \"light the candle\"; so the blank that appears with \"weak\" must be \"light\"."}], "Negative Examples": [{"input": "The trophy doesn't fit into the brown suitcase because _ is too large.", "output": "bottle.", "explanation": "The issue is that the answer is not one of the objects present in the question which are \"trophy\" and \"suitcase\". Note that, a valid answer must be one of the objects present in the question."}, {"input": "Grace was happy to trade me her sweater for my jacket. She thinks _ looks dowdy on her.", "output": "yellow sweater.", "explanation": "Here, an additonal word \"yellow\" has been added to the answer. Note that, a valid answer must not contain a word that is not present in the question."}, {"input": "While redecorating her home, Sam took out the carpet and replaced it with wood floors. The _ was old.", "output": "carpets.", "explanation": "Here, the answer is not valid because it represents plural version of one of the objects present in the question (\"carpet\" and \"wood floors\"). Note that, a valid answer must be one of the objects present in the question."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Commonsense -> Concepts and Relations -> Social Commonsense", "Commonsense -> Concepts and Relations -> Physical Commonsense"], "Instance": {"id": "task033-15333cb838e7455e826f518cef1c373a", "input": "Jen tried using medication and then be pollen to help her allergies, and she found that the _ was more natural.", "output": ["pollen"]}, "Instance License": ["Apache 2.0"], "prediction": "be pollen"}
+{"id": "task033-9c70e4c9b96e4bb4b7069cb16ba173a8", "Task": "task033_winogrande_answer_generation", "Contributors": "['Swaroop Mishra', 'Daniel Khashabi']", "Source": ["winogrande"], "URL": ["https://leaderboard.allenai.org/winogrande/submissions/about"], "Categories": ["Coreference Resolution"], "Reasoning": ["Commonsense Reasoning"], "Definition": ["You need to answer a given question containing a blank (_). Your answer must be one of the two objects mentioned in the question, for example \"trophy\" and \"suitcase\". Your answer must not contain a word that is not present in the question. Please don't use articles (e.g., the, a) before the answer."], "Positive Examples": [{"input": "The trophy doesn't fit into the brown suitcase because _ is too large.", "output": "trophy", "explanation": "Answer is one of the objects (\"trophy\" and \"suitcase\") in the question. Since the blank is a \"large\" object that didn't fit the \"suitcase\", the answer must be \"trophy\"."}, {"input": "Grace was happy to trade me her sweater for my jacket. She thinks _ looks dowdy on her.", "output": "sweater", "explanation": "The word \"dowdy\" decides the answer among the objects (\"sweater\" and \"jacket\") present in the question."}, {"input": "While redecorating her home, Sam took out the carpet and replaced it with wood floors. The _ was old.", "output": "carpet", "explanation": "The blank is \"old\", it must be what gets \"replaced\", which has to be \"carpet\"."}, {"input": "The table won't fit through the doorway because the _ is too wide.", "output": "table", "explanation": "Answer is one of the objects (\"table\" and \"doorway\") in the question. Since the blank co-appears with \"too wide\". it must be the object that didn't \"fit through the doorway\" (i.e., \"the table\")."}, {"input": "I poured water from the bottle into the cup until the _ was empty.", "output": "bottle", "explanation": "Answer is one of the objects (\"bottle\" and \"cup\") in the question. Therefore, this is a valid answer. Since _ become \"empty\", it must be the container from which the water was poured from (\"bottle\")."}, {"input": "My meeting started at 4:00 and I needed to catch the train at 4:30, so there wasn't much time. Luckily, the _ was short, so it worked out.", "output": "meeting", "explanation": "Here \"meeting\" and \"train\" are the objects. Since the blank was \"short\", which worked out (was able to \"catch the train\"), the answer must be \"meeting\"."}, {"input": "James wanted to light the candle in the wind when on a date but the _ is too weak.", "output": "light", "explanation": "Here \"light\" and \"wind\" are the objects. The connective \"but\" indicates that \"James\" was not able to \"light the candle\"; so the blank that appears with \"weak\" must be \"light\"."}], "Negative Examples": [{"input": "The trophy doesn't fit into the brown suitcase because _ is too large.", "output": "bottle.", "explanation": "The issue is that the answer is not one of the objects present in the question which are \"trophy\" and \"suitcase\". Note that, a valid answer must be one of the objects present in the question."}, {"input": "Grace was happy to trade me her sweater for my jacket. She thinks _ looks dowdy on her.", "output": "yellow sweater.", "explanation": "Here, an additonal word \"yellow\" has been added to the answer. Note that, a valid answer must not contain a word that is not present in the question."}, {"input": "While redecorating her home, Sam took out the carpet and replaced it with wood floors. The _ was old.", "output": "carpets.", "explanation": "Here, the answer is not valid because it represents plural version of one of the objects present in the question (\"carpet\" and \"wood floors\"). Note that, a valid answer must be one of the objects present in the question."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Commonsense -> Concepts and Relations -> Social Commonsense", "Commonsense -> Concepts and Relations -> Physical Commonsense"], "Instance": {"id": "task033-9c70e4c9b96e4bb4b7069cb16ba173a8", "input": "The local cafe was a much better place for making new friendships than the library was, as the _ was accommodating to social activity.", "output": ["cafe"]}, "Instance License": ["Apache 2.0"], "prediction": "cafe"}
+{"id": "task033-85f06bb7d71c42e2ab92bc42cd4958ac", "Task": "task033_winogrande_answer_generation", "Contributors": "['Swaroop Mishra', 'Daniel Khashabi']", "Source": ["winogrande"], "URL": ["https://leaderboard.allenai.org/winogrande/submissions/about"], "Categories": ["Coreference Resolution"], "Reasoning": ["Commonsense Reasoning"], "Definition": ["You need to answer a given question containing a blank (_). Your answer must be one of the two objects mentioned in the question, for example \"trophy\" and \"suitcase\". Your answer must not contain a word that is not present in the question. Please don't use articles (e.g., the, a) before the answer."], "Positive Examples": [{"input": "The trophy doesn't fit into the brown suitcase because _ is too large.", "output": "trophy", "explanation": "Answer is one of the objects (\"trophy\" and \"suitcase\") in the question. Since the blank is a \"large\" object that didn't fit the \"suitcase\", the answer must be \"trophy\"."}, {"input": "Grace was happy to trade me her sweater for my jacket. She thinks _ looks dowdy on her.", "output": "sweater", "explanation": "The word \"dowdy\" decides the answer among the objects (\"sweater\" and \"jacket\") present in the question."}, {"input": "While redecorating her home, Sam took out the carpet and replaced it with wood floors. The _ was old.", "output": "carpet", "explanation": "The blank is \"old\", it must be what gets \"replaced\", which has to be \"carpet\"."}, {"input": "The table won't fit through the doorway because the _ is too wide.", "output": "table", "explanation": "Answer is one of the objects (\"table\" and \"doorway\") in the question. Since the blank co-appears with \"too wide\". it must be the object that didn't \"fit through the doorway\" (i.e., \"the table\")."}, {"input": "I poured water from the bottle into the cup until the _ was empty.", "output": "bottle", "explanation": "Answer is one of the objects (\"bottle\" and \"cup\") in the question. Therefore, this is a valid answer. Since _ become \"empty\", it must be the container from which the water was poured from (\"bottle\")."}, {"input": "My meeting started at 4:00 and I needed to catch the train at 4:30, so there wasn't much time. Luckily, the _ was short, so it worked out.", "output": "meeting", "explanation": "Here \"meeting\" and \"train\" are the objects. Since the blank was \"short\", which worked out (was able to \"catch the train\"), the answer must be \"meeting\"."}, {"input": "James wanted to light the candle in the wind when on a date but the _ is too weak.", "output": "light", "explanation": "Here \"light\" and \"wind\" are the objects. The connective \"but\" indicates that \"James\" was not able to \"light the candle\"; so the blank that appears with \"weak\" must be \"light\"."}], "Negative Examples": [{"input": "The trophy doesn't fit into the brown suitcase because _ is too large.", "output": "bottle.", "explanation": "The issue is that the answer is not one of the objects present in the question which are \"trophy\" and \"suitcase\". Note that, a valid answer must be one of the objects present in the question."}, {"input": "Grace was happy to trade me her sweater for my jacket. She thinks _ looks dowdy on her.", "output": "yellow sweater.", "explanation": "Here, an additonal word \"yellow\" has been added to the answer. Note that, a valid answer must not contain a word that is not present in the question."}, {"input": "While redecorating her home, Sam took out the carpet and replaced it with wood floors. The _ was old.", "output": "carpets.", "explanation": "Here, the answer is not valid because it represents plural version of one of the objects present in the question (\"carpet\" and \"wood floors\"). Note that, a valid answer must be one of the objects present in the question."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Commonsense -> Concepts and Relations -> Social Commonsense", "Commonsense -> Concepts and Relations -> Physical Commonsense"], "Instance": {"id": "task033-85f06bb7d71c42e2ab92bc42cd4958ac", "input": "Jen started lifting weights and drinking protein shakes to gain muscle, but she noticed the _ made her feel tired.", "output": ["weights"]}, "Instance License": ["Apache 2.0"], "prediction": "shakes"}
+{"id": "task033-24860e02b0e847b2b5d09c4deb7bedad", "Task": "task033_winogrande_answer_generation", "Contributors": "['Swaroop Mishra', 'Daniel Khashabi']", "Source": ["winogrande"], "URL": ["https://leaderboard.allenai.org/winogrande/submissions/about"], "Categories": ["Coreference Resolution"], "Reasoning": ["Commonsense Reasoning"], "Definition": ["You need to answer a given question containing a blank (_). Your answer must be one of the two objects mentioned in the question, for example \"trophy\" and \"suitcase\". Your answer must not contain a word that is not present in the question. Please don't use articles (e.g., the, a) before the answer."], "Positive Examples": [{"input": "The trophy doesn't fit into the brown suitcase because _ is too large.", "output": "trophy", "explanation": "Answer is one of the objects (\"trophy\" and \"suitcase\") in the question. Since the blank is a \"large\" object that didn't fit the \"suitcase\", the answer must be \"trophy\"."}, {"input": "Grace was happy to trade me her sweater for my jacket. She thinks _ looks dowdy on her.", "output": "sweater", "explanation": "The word \"dowdy\" decides the answer among the objects (\"sweater\" and \"jacket\") present in the question."}, {"input": "While redecorating her home, Sam took out the carpet and replaced it with wood floors. The _ was old.", "output": "carpet", "explanation": "The blank is \"old\", it must be what gets \"replaced\", which has to be \"carpet\"."}, {"input": "The table won't fit through the doorway because the _ is too wide.", "output": "table", "explanation": "Answer is one of the objects (\"table\" and \"doorway\") in the question. Since the blank co-appears with \"too wide\". it must be the object that didn't \"fit through the doorway\" (i.e., \"the table\")."}, {"input": "I poured water from the bottle into the cup until the _ was empty.", "output": "bottle", "explanation": "Answer is one of the objects (\"bottle\" and \"cup\") in the question. Therefore, this is a valid answer. Since _ become \"empty\", it must be the container from which the water was poured from (\"bottle\")."}, {"input": "My meeting started at 4:00 and I needed to catch the train at 4:30, so there wasn't much time. Luckily, the _ was short, so it worked out.", "output": "meeting", "explanation": "Here \"meeting\" and \"train\" are the objects. Since the blank was \"short\", which worked out (was able to \"catch the train\"), the answer must be \"meeting\"."}, {"input": "James wanted to light the candle in the wind when on a date but the _ is too weak.", "output": "light", "explanation": "Here \"light\" and \"wind\" are the objects. The connective \"but\" indicates that \"James\" was not able to \"light the candle\"; so the blank that appears with \"weak\" must be \"light\"."}], "Negative Examples": [{"input": "The trophy doesn't fit into the brown suitcase because _ is too large.", "output": "bottle.", "explanation": "The issue is that the answer is not one of the objects present in the question which are \"trophy\" and \"suitcase\". Note that, a valid answer must be one of the objects present in the question."}, {"input": "Grace was happy to trade me her sweater for my jacket. She thinks _ looks dowdy on her.", "output": "yellow sweater.", "explanation": "Here, an additonal word \"yellow\" has been added to the answer. Note that, a valid answer must not contain a word that is not present in the question."}, {"input": "While redecorating her home, Sam took out the carpet and replaced it with wood floors. The _ was old.", "output": "carpets.", "explanation": "Here, the answer is not valid because it represents plural version of one of the objects present in the question (\"carpet\" and \"wood floors\"). Note that, a valid answer must be one of the objects present in the question."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Commonsense -> Concepts and Relations -> Social Commonsense", "Commonsense -> Concepts and Relations -> Physical Commonsense"], "Instance": {"id": "task033-24860e02b0e847b2b5d09c4deb7bedad", "input": "Chris wanted the nurse to give him an injection with a syringe and not an IV needle, because the _ was dull.", "output": ["needle"]}, "Instance License": ["Apache 2.0"], "prediction": "needle"}
+{"id": "task033-e09782c9c0554244969779628a056cbc", "Task": "task033_winogrande_answer_generation", "Contributors": "['Swaroop Mishra', 'Daniel Khashabi']", "Source": ["winogrande"], "URL": ["https://leaderboard.allenai.org/winogrande/submissions/about"], "Categories": ["Coreference Resolution"], "Reasoning": ["Commonsense Reasoning"], "Definition": ["You need to answer a given question containing a blank (_). Your answer must be one of the two objects mentioned in the question, for example \"trophy\" and \"suitcase\". Your answer must not contain a word that is not present in the question. Please don't use articles (e.g., the, a) before the answer."], "Positive Examples": [{"input": "The trophy doesn't fit into the brown suitcase because _ is too large.", "output": "trophy", "explanation": "Answer is one of the objects (\"trophy\" and \"suitcase\") in the question. Since the blank is a \"large\" object that didn't fit the \"suitcase\", the answer must be \"trophy\"."}, {"input": "Grace was happy to trade me her sweater for my jacket. She thinks _ looks dowdy on her.", "output": "sweater", "explanation": "The word \"dowdy\" decides the answer among the objects (\"sweater\" and \"jacket\") present in the question."}, {"input": "While redecorating her home, Sam took out the carpet and replaced it with wood floors. The _ was old.", "output": "carpet", "explanation": "The blank is \"old\", it must be what gets \"replaced\", which has to be \"carpet\"."}, {"input": "The table won't fit through the doorway because the _ is too wide.", "output": "table", "explanation": "Answer is one of the objects (\"table\" and \"doorway\") in the question. Since the blank co-appears with \"too wide\". it must be the object that didn't \"fit through the doorway\" (i.e., \"the table\")."}, {"input": "I poured water from the bottle into the cup until the _ was empty.", "output": "bottle", "explanation": "Answer is one of the objects (\"bottle\" and \"cup\") in the question. Therefore, this is a valid answer. Since _ become \"empty\", it must be the container from which the water was poured from (\"bottle\")."}, {"input": "My meeting started at 4:00 and I needed to catch the train at 4:30, so there wasn't much time. Luckily, the _ was short, so it worked out.", "output": "meeting", "explanation": "Here \"meeting\" and \"train\" are the objects. Since the blank was \"short\", which worked out (was able to \"catch the train\"), the answer must be \"meeting\"."}, {"input": "James wanted to light the candle in the wind when on a date but the _ is too weak.", "output": "light", "explanation": "Here \"light\" and \"wind\" are the objects. The connective \"but\" indicates that \"James\" was not able to \"light the candle\"; so the blank that appears with \"weak\" must be \"light\"."}], "Negative Examples": [{"input": "The trophy doesn't fit into the brown suitcase because _ is too large.", "output": "bottle.", "explanation": "The issue is that the answer is not one of the objects present in the question which are \"trophy\" and \"suitcase\". Note that, a valid answer must be one of the objects present in the question."}, {"input": "Grace was happy to trade me her sweater for my jacket. She thinks _ looks dowdy on her.", "output": "yellow sweater.", "explanation": "Here, an additonal word \"yellow\" has been added to the answer. Note that, a valid answer must not contain a word that is not present in the question."}, {"input": "While redecorating her home, Sam took out the carpet and replaced it with wood floors. The _ was old.", "output": "carpets.", "explanation": "Here, the answer is not valid because it represents plural version of one of the objects present in the question (\"carpet\" and \"wood floors\"). Note that, a valid answer must be one of the objects present in the question."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Commonsense -> Concepts and Relations -> Social Commonsense", "Commonsense -> Concepts and Relations -> Physical Commonsense"], "Instance": {"id": "task033-e09782c9c0554244969779628a056cbc", "input": "I tried to place the grocery bag in the basket on the bike, but the _ was too small.", "output": ["basket"]}, "Instance License": ["Apache 2.0"], "prediction": "basket"}
+{"id": "task1407-ba41effea81844ff8ba393fbdd317fef", "Task": "task1407_dart_question_generation", "Contributors": "['Rushang Karia']", "Source": ["dart"], "URL": ["https://huggingface.co/datasets/dart"], "Categories": ["Data to Text"], "Reasoning": [], "Definition": ["In this task you are given a list of triplets of the form [subject, predicate, object] and the output should be a question based on the triplets but with the subject and/or object replaced with blanks (represented using two or more consecutive underscores). Triplet values encompassed in [*] are special tokens that can be replaced with synonyms. The objective is to construct a question in a manner that (a) captures the facts specified in at least one of the triplets, and (b) ideally contains a limited number of blanks such that it is a well-formed question that is easy to answer. A blank can represent a single word or a phrase."], "Positive Examples": [{"input": "[['Northwestern College', 'NICKNAME', 'Red Raiders'], ['Northwestern College', 'LOCATION', 'Orange City, Iowa']]", "output": "The team whose nickname is red raiders is located in the _______", "explanation": "This sentence uses the triplets by correctly using the (subject, predicate, object) semantics for both the triplets provided, and is a good question since red raiders can be associated by a human to Northwestern college which is located in Iowa."}, {"input": "[['University of Mississippi', 'NEW_CONFERENCE', 'SELC']]", "output": "_____ was in the selc new conference.", "explanation": "This is a good example since the question clearly indicates that the subject is missing and its relationship is to be involved with the SELC conference."}, {"input": "[['hear the birds', 'SEASON_3_EP_#', '12']]", "output": "The title of _____ _____ is \"Hear the Birds.\"", "explanation": "This is a good question since it provides the exact subject (hear the birds) and asks a question pertaining to the predicate as well as the object."}], "Negative Examples": [{"input": "[['Graham Edwards', 'PROVINCE', 'North Metropolitan']]", "output": "Edwards _____ the North Metropolitan Province.", "explanation": "This sentence is a bad example since it does not utilize the RDF triplet in the question making it open to interpretation. For example, this blank can be filled in several ways like: represented, belongs to etc. making it a poorly generated question."}, {"input": "[['Li Qiaoxian (CHN)', 'PRELIMINARY_RANK', '6']]", "output": "_____ had a _____ of _____.", "explanation": "This sentence is not a good example because there is too little information present. In fact, the RDF relationships is not captured in any sense over here leaving this question very open-ended."}, {"input": "[['27', 'POINTS_FOR', '393'], ['Garndiffaith RFC', 'PLAYED', '22'], ['Garndiffaith RFC', 'POINTS', '27']]", "output": "22 games _____ played and 393 points _____.", "explanation": "This sentence is a poor example since even though the RDF triplet is captured correctly, the question generated does not involve the RDF triplets in the answer."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Wikipedia"], "Instance": {"id": "task1407-ba41effea81844ff8ba393fbdd317fef", "input": "[['13.1', 'YARDS', '197'], ['Sam Simmons', 'AVG.', '13.1']]", "output": ["_____ had _____ total receiving yards, with an average of 13.1 yards/reception."]}, "Instance License": ["MIT"], "prediction": "197 is a ___"}
+{"id": "task1407-8b3cfd5c9c02440bab92fd5d8e5c77fd", "Task": "task1407_dart_question_generation", "Contributors": "['Rushang Karia']", "Source": ["dart"], "URL": ["https://huggingface.co/datasets/dart"], "Categories": ["Data to Text"], "Reasoning": [], "Definition": ["In this task you are given a list of triplets of the form [subject, predicate, object] and the output should be a question based on the triplets but with the subject and/or object replaced with blanks (represented using two or more consecutive underscores). Triplet values encompassed in [*] are special tokens that can be replaced with synonyms. The objective is to construct a question in a manner that (a) captures the facts specified in at least one of the triplets, and (b) ideally contains a limited number of blanks such that it is a well-formed question that is easy to answer. A blank can represent a single word or a phrase."], "Positive Examples": [{"input": "[['Northwestern College', 'NICKNAME', 'Red Raiders'], ['Northwestern College', 'LOCATION', 'Orange City, Iowa']]", "output": "The team whose nickname is red raiders is located in the _______", "explanation": "This sentence uses the triplets by correctly using the (subject, predicate, object) semantics for both the triplets provided, and is a good question since red raiders can be associated by a human to Northwestern college which is located in Iowa."}, {"input": "[['University of Mississippi', 'NEW_CONFERENCE', 'SELC']]", "output": "_____ was in the selc new conference.", "explanation": "This is a good example since the question clearly indicates that the subject is missing and its relationship is to be involved with the SELC conference."}, {"input": "[['hear the birds', 'SEASON_3_EP_#', '12']]", "output": "The title of _____ _____ is \"Hear the Birds.\"", "explanation": "This is a good question since it provides the exact subject (hear the birds) and asks a question pertaining to the predicate as well as the object."}], "Negative Examples": [{"input": "[['Graham Edwards', 'PROVINCE', 'North Metropolitan']]", "output": "Edwards _____ the North Metropolitan Province.", "explanation": "This sentence is a bad example since it does not utilize the RDF triplet in the question making it open to interpretation. For example, this blank can be filled in several ways like: represented, belongs to etc. making it a poorly generated question."}, {"input": "[['Li Qiaoxian (CHN)', 'PRELIMINARY_RANK', '6']]", "output": "_____ had a _____ of _____.", "explanation": "This sentence is not a good example because there is too little information present. In fact, the RDF relationships is not captured in any sense over here leaving this question very open-ended."}, {"input": "[['27', 'POINTS_FOR', '393'], ['Garndiffaith RFC', 'PLAYED', '22'], ['Garndiffaith RFC', 'POINTS', '27']]", "output": "22 games _____ played and 393 points _____.", "explanation": "This sentence is a poor example since even though the RDF triplet is captured correctly, the question generated does not involve the RDF triplets in the answer."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Wikipedia"], "Instance": {"id": "task1407-8b3cfd5c9c02440bab92fd5d8e5c77fd", "input": "[['Cocum', 'eatType', 'coffee shop'], ['Cocum', 'food', 'Japanese'], ['Cocum', 'priceRange', 'high'], ['Cocum', 'customer rating', '3 out of 5'], ['Cocum', 'familyFriendly', 'no']]", "output": ["_____ is a _____ coffee shop that is non child friendly with a high price range and a customer rating of 3 out of 5.", "_____ is a _____ coffee shop which is not child friendly. It has a customer rating of 3 out of 5. The price range is high.", "There is a _____ coffee shop named _____ that is non child friendly with a high price range and a customer rating of 3 out of 5.", "There is a _____ coffee shop named _____. It is not child friendly. It has a customer rating of 3 out of 5. The price range is high."]}, "Instance License": ["MIT"], "prediction": "___ is a coffee shop located in ___"}
+{"id": "task1407-84c627e08ac64986a9f973f891768e7a", "Task": "task1407_dart_question_generation", "Contributors": "['Rushang Karia']", "Source": ["dart"], "URL": ["https://huggingface.co/datasets/dart"], "Categories": ["Data to Text"], "Reasoning": [], "Definition": ["In this task you are given a list of triplets of the form [subject, predicate, object] and the output should be a question based on the triplets but with the subject and/or object replaced with blanks (represented using two or more consecutive underscores). Triplet values encompassed in [*] are special tokens that can be replaced with synonyms. The objective is to construct a question in a manner that (a) captures the facts specified in at least one of the triplets, and (b) ideally contains a limited number of blanks such that it is a well-formed question that is easy to answer. A blank can represent a single word or a phrase."], "Positive Examples": [{"input": "[['Northwestern College', 'NICKNAME', 'Red Raiders'], ['Northwestern College', 'LOCATION', 'Orange City, Iowa']]", "output": "The team whose nickname is red raiders is located in the _______", "explanation": "This sentence uses the triplets by correctly using the (subject, predicate, object) semantics for both the triplets provided, and is a good question since red raiders can be associated by a human to Northwestern college which is located in Iowa."}, {"input": "[['University of Mississippi', 'NEW_CONFERENCE', 'SELC']]", "output": "_____ was in the selc new conference.", "explanation": "This is a good example since the question clearly indicates that the subject is missing and its relationship is to be involved with the SELC conference."}, {"input": "[['hear the birds', 'SEASON_3_EP_#', '12']]", "output": "The title of _____ _____ is \"Hear the Birds.\"", "explanation": "This is a good question since it provides the exact subject (hear the birds) and asks a question pertaining to the predicate as well as the object."}], "Negative Examples": [{"input": "[['Graham Edwards', 'PROVINCE', 'North Metropolitan']]", "output": "Edwards _____ the North Metropolitan Province.", "explanation": "This sentence is a bad example since it does not utilize the RDF triplet in the question making it open to interpretation. For example, this blank can be filled in several ways like: represented, belongs to etc. making it a poorly generated question."}, {"input": "[['Li Qiaoxian (CHN)', 'PRELIMINARY_RANK', '6']]", "output": "_____ had a _____ of _____.", "explanation": "This sentence is not a good example because there is too little information present. In fact, the RDF relationships is not captured in any sense over here leaving this question very open-ended."}, {"input": "[['27', 'POINTS_FOR', '393'], ['Garndiffaith RFC', 'PLAYED', '22'], ['Garndiffaith RFC', 'POINTS', '27']]", "output": "22 games _____ played and 393 points _____.", "explanation": "This sentence is a poor example since even though the RDF triplet is captured correctly, the question generated does not involve the RDF triplets in the answer."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Wikipedia"], "Instance": {"id": "task1407-84c627e08ac64986a9f973f891768e7a", "input": "[['Fitzbillies', 'eatType', 'coffee shop'], ['Fitzbillies', 'food', 'French'], ['Fitzbillies', 'priceRange', 'moderate'], ['Fitzbillies', 'area', 'city centre']]", "output": ["_____ is a coffee shop offering French food at a moderate price. It is located in the _____.", "_____ is a coffee shop located within the _____ offering French food at a moderate price."]}, "Instance License": ["MIT"], "prediction": "_ is a coffee shop located in the _ area"}
+{"id": "task1407-20f0787c59c441b4baa6a43cd8b8beff", "Task": "task1407_dart_question_generation", "Contributors": "['Rushang Karia']", "Source": ["dart"], "URL": ["https://huggingface.co/datasets/dart"], "Categories": ["Data to Text"], "Reasoning": [], "Definition": ["In this task you are given a list of triplets of the form [subject, predicate, object] and the output should be a question based on the triplets but with the subject and/or object replaced with blanks (represented using two or more consecutive underscores). Triplet values encompassed in [*] are special tokens that can be replaced with synonyms. The objective is to construct a question in a manner that (a) captures the facts specified in at least one of the triplets, and (b) ideally contains a limited number of blanks such that it is a well-formed question that is easy to answer. A blank can represent a single word or a phrase."], "Positive Examples": [{"input": "[['Northwestern College', 'NICKNAME', 'Red Raiders'], ['Northwestern College', 'LOCATION', 'Orange City, Iowa']]", "output": "The team whose nickname is red raiders is located in the _______", "explanation": "This sentence uses the triplets by correctly using the (subject, predicate, object) semantics for both the triplets provided, and is a good question since red raiders can be associated by a human to Northwestern college which is located in Iowa."}, {"input": "[['University of Mississippi', 'NEW_CONFERENCE', 'SELC']]", "output": "_____ was in the selc new conference.", "explanation": "This is a good example since the question clearly indicates that the subject is missing and its relationship is to be involved with the SELC conference."}, {"input": "[['hear the birds', 'SEASON_3_EP_#', '12']]", "output": "The title of _____ _____ is \"Hear the Birds.\"", "explanation": "This is a good question since it provides the exact subject (hear the birds) and asks a question pertaining to the predicate as well as the object."}], "Negative Examples": [{"input": "[['Graham Edwards', 'PROVINCE', 'North Metropolitan']]", "output": "Edwards _____ the North Metropolitan Province.", "explanation": "This sentence is a bad example since it does not utilize the RDF triplet in the question making it open to interpretation. For example, this blank can be filled in several ways like: represented, belongs to etc. making it a poorly generated question."}, {"input": "[['Li Qiaoxian (CHN)', 'PRELIMINARY_RANK', '6']]", "output": "_____ had a _____ of _____.", "explanation": "This sentence is not a good example because there is too little information present. In fact, the RDF relationships is not captured in any sense over here leaving this question very open-ended."}, {"input": "[['27', 'POINTS_FOR', '393'], ['Garndiffaith RFC', 'PLAYED', '22'], ['Garndiffaith RFC', 'POINTS', '27']]", "output": "22 games _____ played and 393 points _____.", "explanation": "This sentence is a poor example since even though the RDF triplet is captured correctly, the question generated does not involve the RDF triplets in the answer."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Wikipedia"], "Instance": {"id": "task1407-20f0787c59c441b4baa6a43cd8b8beff", "input": "[['The Ref', 'ROLE', 'Old Baybrook Policeman']]", "output": ["John Benjamin Hickey role is \t_____ title name _____"]}, "Instance License": ["MIT"], "prediction": "_ is a policeman in the old baybrook policeman role"}
+{"id": "task1407-73dd269eb0884675914453c3250f92ef", "Task": "task1407_dart_question_generation", "Contributors": "['Rushang Karia']", "Source": ["dart"], "URL": ["https://huggingface.co/datasets/dart"], "Categories": ["Data to Text"], "Reasoning": [], "Definition": ["In this task you are given a list of triplets of the form [subject, predicate, object] and the output should be a question based on the triplets but with the subject and/or object replaced with blanks (represented using two or more consecutive underscores). Triplet values encompassed in [*] are special tokens that can be replaced with synonyms. The objective is to construct a question in a manner that (a) captures the facts specified in at least one of the triplets, and (b) ideally contains a limited number of blanks such that it is a well-formed question that is easy to answer. A blank can represent a single word or a phrase."], "Positive Examples": [{"input": "[['Northwestern College', 'NICKNAME', 'Red Raiders'], ['Northwestern College', 'LOCATION', 'Orange City, Iowa']]", "output": "The team whose nickname is red raiders is located in the _______", "explanation": "This sentence uses the triplets by correctly using the (subject, predicate, object) semantics for both the triplets provided, and is a good question since red raiders can be associated by a human to Northwestern college which is located in Iowa."}, {"input": "[['University of Mississippi', 'NEW_CONFERENCE', 'SELC']]", "output": "_____ was in the selc new conference.", "explanation": "This is a good example since the question clearly indicates that the subject is missing and its relationship is to be involved with the SELC conference."}, {"input": "[['hear the birds', 'SEASON_3_EP_#', '12']]", "output": "The title of _____ _____ is \"Hear the Birds.\"", "explanation": "This is a good question since it provides the exact subject (hear the birds) and asks a question pertaining to the predicate as well as the object."}], "Negative Examples": [{"input": "[['Graham Edwards', 'PROVINCE', 'North Metropolitan']]", "output": "Edwards _____ the North Metropolitan Province.", "explanation": "This sentence is a bad example since it does not utilize the RDF triplet in the question making it open to interpretation. For example, this blank can be filled in several ways like: represented, belongs to etc. making it a poorly generated question."}, {"input": "[['Li Qiaoxian (CHN)', 'PRELIMINARY_RANK', '6']]", "output": "_____ had a _____ of _____.", "explanation": "This sentence is not a good example because there is too little information present. In fact, the RDF relationships is not captured in any sense over here leaving this question very open-ended."}, {"input": "[['27', 'POINTS_FOR', '393'], ['Garndiffaith RFC', 'PLAYED', '22'], ['Garndiffaith RFC', 'POINTS', '27']]", "output": "22 games _____ played and 393 points _____.", "explanation": "This sentence is a poor example since even though the RDF triplet is captured correctly, the question generated does not involve the RDF triplets in the answer."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Wikipedia"], "Instance": {"id": "task1407-73dd269eb0884675914453c3250f92ef", "input": "[['AIP Advances', 'EDITOR', 'A.T. Charlie Johnson'], ['A.T. Charlie Johnson', 'ALMA_MATER', 'Harvard University'], ['A.T. Charlie Johnson', 'DOCTORAL_ADVISOR', 'Michael Tinkham'], ['AIP Advances', 'PUBLISHER', 'American Institute of Physics']]", "output": ["Published by American Institute of Physics, _____ was edited by A.T. Charlie Johnson who's almaMater is Harvard University and who is the doctoral advisor for Michael Tinkham.", "_____ is published by the American Institute of Physics. It is edited by A.T. Charlie Johnson, whose alma mater is Harvard University, and whose doctoral advisor was Michael Tinkham.", "The editor of _____ published by American Institute of Physics is A.T Charlie Johnson who graduated from Harvard University and is the doctoral advisor for Michael Tinkham."]}, "Instance License": ["MIT"], "prediction": "_ is the editor of AIP Advances."}
+{"id": "task402-cb25ec53f48e45e7945202c0e171332d", "Task": "task402_grailqa_paraphrase_generation", "Contributors": "['Pegah Alipoormolabashi']", "Source": ["grailqa"], "URL": ["https://dki-lab.github.io/GrailQA/"], "Categories": ["Question Rewriting"], "Reasoning": [], "Definition": ["Compose a new way to ask the same question. The new question must be asking the exact same thing as the original question does. Without any other information, you should be able to tell that the original question and the new question are the same. Preserve bracketed phrases in your new question. You can change the rest of the question provided the above requirements are satisfied. The new question must have a natural, fluent formulation, as if it were composed by a native English speaker. You will be given three pieces of information to help you create better questions. Those are: \"Answer\": the answer to the question, e.g., \"Honolulu\". \"Answer Type\": the type of the answer, e.g., \"Location\". \"Auxiliary Information\" is a detailed description of some concepts mentioned in the question, if any."], "Positive Examples": [{"input": "original question: Who is the museum director of [Science Museum, London]?\nanswer: Ian Blatchford\nanswer type: Museum director. \nauxiliary information: The Science Museum is a major museum on Exhibition Road in South Kensington, London. It was founded in 1857 and today is one of the city's major tourist attractions, attracting 3.3 million visitors annually. Like other publicly funded national museums in the United Kingdom, the Science Museum does not charge visitors for admission. Temporary exhibitions, however, may incur an admission fee. It is part of the Science Museum Group, having merged with the Museum of Science and Industry in Manchester in 2012.", "output": "The museum director of the [Science Museum, London] is?", "explanation": "The question is correctly paraphrased in this example."}, {"input": "original question: Which zoo is in the category of [Public aquarium]?\nanswer: Istanbul Aquarium, Minnesota Zoo, Monterey Bay Aquarium...\nanswer type: Zoo.\nauxiliary information: A public aquarium is the aquatic counterpart of a zoo, which houses living aquatic animal and plant specimens for public viewing. Most public aquariums feature tanks larger than those kept by home aquarists, as well as smaller tanks. Since the first public aquariums were built in the mid-19th century, they have become popular and their numbers have increased. Most modern accredited aquariums stress conservation issues and educating the public.", "output": "What zoos are also considered to be [Public aquarium]s?", "explanation": "This answer correctly paraphrases the question."}, {"input": "original question: Which apis have the protocol of [JSON]?\nanswer: Hi5 API\nanswer type: API.\nauxiliary information: JSON canonically pronounced /\u00c0\u00e0d\u00a0\u00ede\u2026\u2122s\u2026\u00f4n/ JAY-s\u2026\u00f4n; sometimes JavaScript Object Notation, is an open standard format that uses human-readable text to transmit data objects consisting of attribute\u201a\u00c4\u00ecvalue pairs. It is used primarily to transmit data between a server and web application, as an alternative to XML. Although originally derived from the JavaScript scripting language, JSON is a language-independent data format. Code for parsing and generating JSON data is readily available in many programming languages. The JSON format was originally specified by Douglas Crockford. It is currently described by two competing standards, RFC 7159 and ECMA-404. The ECMA standard is minimal, describing only the allowed grammar syntax, whereas the RFC also provides some semantic and security considerations. The official Internet media type for JSON is application/json. The JSON filename extension is .json.", "output": "Which apis include the protocol of [JSON]?", "explanation": "This is a good paraphrase of the question."}], "Negative Examples": [{"input": "original question: Which opera is in [Sanskrit Language]?\nanswer: Satyagraha\nanswer type: Opera.\nauxiliary information: Sanskrit is the primary liturgical language of Hinduism, a philosophical language in Buddhism, Hinduism and Jainism, and a literary language that was in use as a lingua franca in the Indian cultural zone. It is a standardised dialect of the Old Indo-Aryan language, originating as Vedic Sanskrit and tracing its linguistic ancestry back to Proto-Indo-Iranian and Proto-Indo-European. Today it is listed as one of the 22 scheduled languages of India and is an official language of the state of Uttarakhand. Sanskrit holds a prominent position in Indo-European studies. The corpus of Sanskrit literature encompasses a rich tradition of poetry and drama as well as scientific, technical, philosophical and religious texts. Sanskrit continues to be widely used as a ceremonial language in Hindu religious rituals and Buddhist practice in the form of hymns and chants. Spoken Sanskrit has been revived in some villages with traditional institutions, and there are attempts to enhance its popularisation.", "output": "What is the opera performed in [Sanskrit]?", "explanation": "This is a good paraphrase, but the words in the bracket are changed, so the answer is invalid."}, {"input": "original question: Which opera is in [Sanskrit Language]?\nanswer: Satyagraha\nanswer type: Opera.\nauxiliary information: Sanskrit is the primary liturgical language of Hinduism, a philosophical language in Buddhism, Hinduism and Jainism, and a literary language that was in use as a lingua franca in the Indian cultural zone. It is a standardised dialect of the Old Indo-Aryan language, originating as Vedic Sanskrit and tracing its linguistic ancestry back to Proto-Indo-Iranian and Proto-Indo-European. Today it is listed as one of the 22 scheduled languages of India and is an official language of the state of Uttarakhand. Sanskrit holds a prominent position in Indo-European studies. The corpus of Sanskrit literature encompasses a rich tradition of poetry and drama as well as scientific, technical, philosophical and religious texts. Sanskrit continues to be widely used as a ceremonial language in Hindu religious rituals and Buddhist practice in the form of hymns and chants. Spoken Sanskrit has been revived in some villages with traditional institutions, and there are attempts to enhance its popularisation.", "output": "Sanskrit Language is the literary language of which opera?", "explanation": "You should remember to put the brakets around the preserved phrases."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Knowledge Base -> Freebase"], "Instance": {"id": "task402-cb25ec53f48e45e7945202c0e171332d", "input": "original question: Which opera is in [Sanskrit Language]?\nanswer: satyagraha\nanswer type: Opera.\nauxiliary information: Sanskrit is the primary liturgical language of Hinduism, a philosophical language in Buddhism, Hinduism and Jainism, and a literary language that was in use as a lingua franca in the Indian cultural zone. It is a standardised dialect of the Old Indo-Aryan language, originating as Vedic Sanskrit and tracing its linguistic ancestry back to Proto-Indo-Iranian and Proto-Indo-European. Today it is listed as one of the 22 scheduled languages of India and is an official language of the state of Uttarakhand. Sanskrit holds a prominent position in Indo-European studies. The corpus of Sanskrit literature encompasses a rich tradition of poetry and drama as well as scientific, technical, philosophical and religious texts. Sanskrit continues to be widely used as a ceremonial language in Hindu religious rituals and Buddhist practice in the form of hymns and chants. Spoken Sanskrit has been revived in some villages with traditional institutions, and there are attempts to enhance its popularisation.", "output": ["What is the opera performed in the [Sanskrit Language]?", "[Sanskrit Language] is the literary language of which opera?", "[Sanskrit Language] is the language of which opera?", "What opera has [Sanskrit Language] in it?", "[Sanskrit Language] is used in which opera?"]}, "Instance License": ["CC BY-SA 4.0"], "prediction": "What language is the language of opera?"}
+{"id": "task402-bf281b924df14bd398a0f6ca65a662c9", "Task": "task402_grailqa_paraphrase_generation", "Contributors": "['Pegah Alipoormolabashi']", "Source": ["grailqa"], "URL": ["https://dki-lab.github.io/GrailQA/"], "Categories": ["Question Rewriting"], "Reasoning": [], "Definition": ["Compose a new way to ask the same question. The new question must be asking the exact same thing as the original question does. Without any other information, you should be able to tell that the original question and the new question are the same. Preserve bracketed phrases in your new question. You can change the rest of the question provided the above requirements are satisfied. The new question must have a natural, fluent formulation, as if it were composed by a native English speaker. You will be given three pieces of information to help you create better questions. Those are: \"Answer\": the answer to the question, e.g., \"Honolulu\". \"Answer Type\": the type of the answer, e.g., \"Location\". \"Auxiliary Information\" is a detailed description of some concepts mentioned in the question, if any."], "Positive Examples": [{"input": "original question: Who is the museum director of [Science Museum, London]?\nanswer: Ian Blatchford\nanswer type: Museum director. \nauxiliary information: The Science Museum is a major museum on Exhibition Road in South Kensington, London. It was founded in 1857 and today is one of the city's major tourist attractions, attracting 3.3 million visitors annually. Like other publicly funded national museums in the United Kingdom, the Science Museum does not charge visitors for admission. Temporary exhibitions, however, may incur an admission fee. It is part of the Science Museum Group, having merged with the Museum of Science and Industry in Manchester in 2012.", "output": "The museum director of the [Science Museum, London] is?", "explanation": "The question is correctly paraphrased in this example."}, {"input": "original question: Which zoo is in the category of [Public aquarium]?\nanswer: Istanbul Aquarium, Minnesota Zoo, Monterey Bay Aquarium...\nanswer type: Zoo.\nauxiliary information: A public aquarium is the aquatic counterpart of a zoo, which houses living aquatic animal and plant specimens for public viewing. Most public aquariums feature tanks larger than those kept by home aquarists, as well as smaller tanks. Since the first public aquariums were built in the mid-19th century, they have become popular and their numbers have increased. Most modern accredited aquariums stress conservation issues and educating the public.", "output": "What zoos are also considered to be [Public aquarium]s?", "explanation": "This answer correctly paraphrases the question."}, {"input": "original question: Which apis have the protocol of [JSON]?\nanswer: Hi5 API\nanswer type: API.\nauxiliary information: JSON canonically pronounced /\u00c0\u00e0d\u00a0\u00ede\u2026\u2122s\u2026\u00f4n/ JAY-s\u2026\u00f4n; sometimes JavaScript Object Notation, is an open standard format that uses human-readable text to transmit data objects consisting of attribute\u201a\u00c4\u00ecvalue pairs. It is used primarily to transmit data between a server and web application, as an alternative to XML. Although originally derived from the JavaScript scripting language, JSON is a language-independent data format. Code for parsing and generating JSON data is readily available in many programming languages. The JSON format was originally specified by Douglas Crockford. It is currently described by two competing standards, RFC 7159 and ECMA-404. The ECMA standard is minimal, describing only the allowed grammar syntax, whereas the RFC also provides some semantic and security considerations. The official Internet media type for JSON is application/json. The JSON filename extension is .json.", "output": "Which apis include the protocol of [JSON]?", "explanation": "This is a good paraphrase of the question."}], "Negative Examples": [{"input": "original question: Which opera is in [Sanskrit Language]?\nanswer: Satyagraha\nanswer type: Opera.\nauxiliary information: Sanskrit is the primary liturgical language of Hinduism, a philosophical language in Buddhism, Hinduism and Jainism, and a literary language that was in use as a lingua franca in the Indian cultural zone. It is a standardised dialect of the Old Indo-Aryan language, originating as Vedic Sanskrit and tracing its linguistic ancestry back to Proto-Indo-Iranian and Proto-Indo-European. Today it is listed as one of the 22 scheduled languages of India and is an official language of the state of Uttarakhand. Sanskrit holds a prominent position in Indo-European studies. The corpus of Sanskrit literature encompasses a rich tradition of poetry and drama as well as scientific, technical, philosophical and religious texts. Sanskrit continues to be widely used as a ceremonial language in Hindu religious rituals and Buddhist practice in the form of hymns and chants. Spoken Sanskrit has been revived in some villages with traditional institutions, and there are attempts to enhance its popularisation.", "output": "What is the opera performed in [Sanskrit]?", "explanation": "This is a good paraphrase, but the words in the bracket are changed, so the answer is invalid."}, {"input": "original question: Which opera is in [Sanskrit Language]?\nanswer: Satyagraha\nanswer type: Opera.\nauxiliary information: Sanskrit is the primary liturgical language of Hinduism, a philosophical language in Buddhism, Hinduism and Jainism, and a literary language that was in use as a lingua franca in the Indian cultural zone. It is a standardised dialect of the Old Indo-Aryan language, originating as Vedic Sanskrit and tracing its linguistic ancestry back to Proto-Indo-Iranian and Proto-Indo-European. Today it is listed as one of the 22 scheduled languages of India and is an official language of the state of Uttarakhand. Sanskrit holds a prominent position in Indo-European studies. The corpus of Sanskrit literature encompasses a rich tradition of poetry and drama as well as scientific, technical, philosophical and religious texts. Sanskrit continues to be widely used as a ceremonial language in Hindu religious rituals and Buddhist practice in the form of hymns and chants. Spoken Sanskrit has been revived in some villages with traditional institutions, and there are attempts to enhance its popularisation.", "output": "Sanskrit Language is the literary language of which opera?", "explanation": "You should remember to put the brakets around the preserved phrases."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Knowledge Base -> Freebase"], "Instance": {"id": "task402-bf281b924df14bd398a0f6ca65a662c9", "input": "original question: Which sports league championship did league of [European Volleyball Confederation] participate in?\nanswer: european volleyball championship\nanswer type: Sports League Championship.\nauxiliary information: The European Volleyball Confederation is the continental governing body for the sport of volleyball in Europe. Its headquarters are located in Luxembourg, Luxembourg.", "output": ["The league of [European Volleyball Confederation] played in what sports league championship?", "What sports league championship did the [European Volleyball Confederation] compete in?", "The league of [European Volleyball Confederation] participated in what sports league championship?", "[European Volleyball Confederation]  took part in what sport's league championship?", "[European Volleyball Confederation] league participated in what sports league championship?"]}, "Instance License": ["CC BY-SA 4.0"], "prediction": "What is the name of the European Volleyball Confederation?"}
+{"id": "task402-dc5e96b1b6784852ac679a137240b70b", "Task": "task402_grailqa_paraphrase_generation", "Contributors": "['Pegah Alipoormolabashi']", "Source": ["grailqa"], "URL": ["https://dki-lab.github.io/GrailQA/"], "Categories": ["Question Rewriting"], "Reasoning": [], "Definition": ["Compose a new way to ask the same question. The new question must be asking the exact same thing as the original question does. Without any other information, you should be able to tell that the original question and the new question are the same. Preserve bracketed phrases in your new question. You can change the rest of the question provided the above requirements are satisfied. The new question must have a natural, fluent formulation, as if it were composed by a native English speaker. You will be given three pieces of information to help you create better questions. Those are: \"Answer\": the answer to the question, e.g., \"Honolulu\". \"Answer Type\": the type of the answer, e.g., \"Location\". \"Auxiliary Information\" is a detailed description of some concepts mentioned in the question, if any."], "Positive Examples": [{"input": "original question: Who is the museum director of [Science Museum, London]?\nanswer: Ian Blatchford\nanswer type: Museum director. \nauxiliary information: The Science Museum is a major museum on Exhibition Road in South Kensington, London. It was founded in 1857 and today is one of the city's major tourist attractions, attracting 3.3 million visitors annually. Like other publicly funded national museums in the United Kingdom, the Science Museum does not charge visitors for admission. Temporary exhibitions, however, may incur an admission fee. It is part of the Science Museum Group, having merged with the Museum of Science and Industry in Manchester in 2012.", "output": "The museum director of the [Science Museum, London] is?", "explanation": "The question is correctly paraphrased in this example."}, {"input": "original question: Which zoo is in the category of [Public aquarium]?\nanswer: Istanbul Aquarium, Minnesota Zoo, Monterey Bay Aquarium...\nanswer type: Zoo.\nauxiliary information: A public aquarium is the aquatic counterpart of a zoo, which houses living aquatic animal and plant specimens for public viewing. Most public aquariums feature tanks larger than those kept by home aquarists, as well as smaller tanks. Since the first public aquariums were built in the mid-19th century, they have become popular and their numbers have increased. Most modern accredited aquariums stress conservation issues and educating the public.", "output": "What zoos are also considered to be [Public aquarium]s?", "explanation": "This answer correctly paraphrases the question."}, {"input": "original question: Which apis have the protocol of [JSON]?\nanswer: Hi5 API\nanswer type: API.\nauxiliary information: JSON canonically pronounced /\u00c0\u00e0d\u00a0\u00ede\u2026\u2122s\u2026\u00f4n/ JAY-s\u2026\u00f4n; sometimes JavaScript Object Notation, is an open standard format that uses human-readable text to transmit data objects consisting of attribute\u201a\u00c4\u00ecvalue pairs. It is used primarily to transmit data between a server and web application, as an alternative to XML. Although originally derived from the JavaScript scripting language, JSON is a language-independent data format. Code for parsing and generating JSON data is readily available in many programming languages. The JSON format was originally specified by Douglas Crockford. It is currently described by two competing standards, RFC 7159 and ECMA-404. The ECMA standard is minimal, describing only the allowed grammar syntax, whereas the RFC also provides some semantic and security considerations. The official Internet media type for JSON is application/json. The JSON filename extension is .json.", "output": "Which apis include the protocol of [JSON]?", "explanation": "This is a good paraphrase of the question."}], "Negative Examples": [{"input": "original question: Which opera is in [Sanskrit Language]?\nanswer: Satyagraha\nanswer type: Opera.\nauxiliary information: Sanskrit is the primary liturgical language of Hinduism, a philosophical language in Buddhism, Hinduism and Jainism, and a literary language that was in use as a lingua franca in the Indian cultural zone. It is a standardised dialect of the Old Indo-Aryan language, originating as Vedic Sanskrit and tracing its linguistic ancestry back to Proto-Indo-Iranian and Proto-Indo-European. Today it is listed as one of the 22 scheduled languages of India and is an official language of the state of Uttarakhand. Sanskrit holds a prominent position in Indo-European studies. The corpus of Sanskrit literature encompasses a rich tradition of poetry and drama as well as scientific, technical, philosophical and religious texts. Sanskrit continues to be widely used as a ceremonial language in Hindu religious rituals and Buddhist practice in the form of hymns and chants. Spoken Sanskrit has been revived in some villages with traditional institutions, and there are attempts to enhance its popularisation.", "output": "What is the opera performed in [Sanskrit]?", "explanation": "This is a good paraphrase, but the words in the bracket are changed, so the answer is invalid."}, {"input": "original question: Which opera is in [Sanskrit Language]?\nanswer: Satyagraha\nanswer type: Opera.\nauxiliary information: Sanskrit is the primary liturgical language of Hinduism, a philosophical language in Buddhism, Hinduism and Jainism, and a literary language that was in use as a lingua franca in the Indian cultural zone. It is a standardised dialect of the Old Indo-Aryan language, originating as Vedic Sanskrit and tracing its linguistic ancestry back to Proto-Indo-Iranian and Proto-Indo-European. Today it is listed as one of the 22 scheduled languages of India and is an official language of the state of Uttarakhand. Sanskrit holds a prominent position in Indo-European studies. The corpus of Sanskrit literature encompasses a rich tradition of poetry and drama as well as scientific, technical, philosophical and religious texts. Sanskrit continues to be widely used as a ceremonial language in Hindu religious rituals and Buddhist practice in the form of hymns and chants. Spoken Sanskrit has been revived in some villages with traditional institutions, and there are attempts to enhance its popularisation.", "output": "Sanskrit Language is the literary language of which opera?", "explanation": "You should remember to put the brakets around the preserved phrases."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Knowledge Base -> Freebase"], "Instance": {"id": "task402-dc5e96b1b6784852ac679a137240b70b", "input": "original question: Which animal breed is the breed of [Guinea pig]?\nanswer: himalayan guinea pig, teddy guinea pig, skinny pig...\nanswer type: Animal breed.\nauxiliary information: The guinea pig, also called the cavy, is a species of rodent belonging to the family Caviidae and the genus Cavia. Despite their common name, these animals are not in the pig family, nor are they from Guinea. They originated in the Andes, and earlier studies based on biochemistry and hybridization suggested they are domesticated descendants of a closely related species of cavy such as Cavia aperea, C. fulgida, or C. tschudii and, therefore, do not exist naturally in the wild. Recent studies applying molecular markers, in addition to studying the skull and skeletal morphology of current and mummified animals, revealed that the ancestor is most likely Cavia tschudii. The guinea pig plays an important role in the folk culture of many Indigenous South American groups, especially as a food source, but also in folk medicine and in community religious ceremonies. Since the 1960s, efforts have been made to increase consumption of the animal outside South America. In Western societies, the guinea pig has enjoyed widespread popularity as a household pet since its introduction by European traders in the 16th century.", "output": ["A [Guinea pig] is included in what type of animal breed?", "The [Guinea pig] is of what animal breed?", "What is the animal breed of a [Guinea pig]?", "[Guinea pig] is what animal breed?", "The [Guinea pig] species has which breeds?"]}, "Instance License": ["CC BY-SA 4.0"], "prediction": "What is the name of the genus Cavia?"}
+{"id": "task402-f88fdca02bf84e79ab052bbcd1a1873a", "Task": "task402_grailqa_paraphrase_generation", "Contributors": "['Pegah Alipoormolabashi']", "Source": ["grailqa"], "URL": ["https://dki-lab.github.io/GrailQA/"], "Categories": ["Question Rewriting"], "Reasoning": [], "Definition": ["Compose a new way to ask the same question. The new question must be asking the exact same thing as the original question does. Without any other information, you should be able to tell that the original question and the new question are the same. Preserve bracketed phrases in your new question. You can change the rest of the question provided the above requirements are satisfied. The new question must have a natural, fluent formulation, as if it were composed by a native English speaker. You will be given three pieces of information to help you create better questions. Those are: \"Answer\": the answer to the question, e.g., \"Honolulu\". \"Answer Type\": the type of the answer, e.g., \"Location\". \"Auxiliary Information\" is a detailed description of some concepts mentioned in the question, if any."], "Positive Examples": [{"input": "original question: Who is the museum director of [Science Museum, London]?\nanswer: Ian Blatchford\nanswer type: Museum director. \nauxiliary information: The Science Museum is a major museum on Exhibition Road in South Kensington, London. It was founded in 1857 and today is one of the city's major tourist attractions, attracting 3.3 million visitors annually. Like other publicly funded national museums in the United Kingdom, the Science Museum does not charge visitors for admission. Temporary exhibitions, however, may incur an admission fee. It is part of the Science Museum Group, having merged with the Museum of Science and Industry in Manchester in 2012.", "output": "The museum director of the [Science Museum, London] is?", "explanation": "The question is correctly paraphrased in this example."}, {"input": "original question: Which zoo is in the category of [Public aquarium]?\nanswer: Istanbul Aquarium, Minnesota Zoo, Monterey Bay Aquarium...\nanswer type: Zoo.\nauxiliary information: A public aquarium is the aquatic counterpart of a zoo, which houses living aquatic animal and plant specimens for public viewing. Most public aquariums feature tanks larger than those kept by home aquarists, as well as smaller tanks. Since the first public aquariums were built in the mid-19th century, they have become popular and their numbers have increased. Most modern accredited aquariums stress conservation issues and educating the public.", "output": "What zoos are also considered to be [Public aquarium]s?", "explanation": "This answer correctly paraphrases the question."}, {"input": "original question: Which apis have the protocol of [JSON]?\nanswer: Hi5 API\nanswer type: API.\nauxiliary information: JSON canonically pronounced /\u00c0\u00e0d\u00a0\u00ede\u2026\u2122s\u2026\u00f4n/ JAY-s\u2026\u00f4n; sometimes JavaScript Object Notation, is an open standard format that uses human-readable text to transmit data objects consisting of attribute\u201a\u00c4\u00ecvalue pairs. It is used primarily to transmit data between a server and web application, as an alternative to XML. Although originally derived from the JavaScript scripting language, JSON is a language-independent data format. Code for parsing and generating JSON data is readily available in many programming languages. The JSON format was originally specified by Douglas Crockford. It is currently described by two competing standards, RFC 7159 and ECMA-404. The ECMA standard is minimal, describing only the allowed grammar syntax, whereas the RFC also provides some semantic and security considerations. The official Internet media type for JSON is application/json. The JSON filename extension is .json.", "output": "Which apis include the protocol of [JSON]?", "explanation": "This is a good paraphrase of the question."}], "Negative Examples": [{"input": "original question: Which opera is in [Sanskrit Language]?\nanswer: Satyagraha\nanswer type: Opera.\nauxiliary information: Sanskrit is the primary liturgical language of Hinduism, a philosophical language in Buddhism, Hinduism and Jainism, and a literary language that was in use as a lingua franca in the Indian cultural zone. It is a standardised dialect of the Old Indo-Aryan language, originating as Vedic Sanskrit and tracing its linguistic ancestry back to Proto-Indo-Iranian and Proto-Indo-European. Today it is listed as one of the 22 scheduled languages of India and is an official language of the state of Uttarakhand. Sanskrit holds a prominent position in Indo-European studies. The corpus of Sanskrit literature encompasses a rich tradition of poetry and drama as well as scientific, technical, philosophical and religious texts. Sanskrit continues to be widely used as a ceremonial language in Hindu religious rituals and Buddhist practice in the form of hymns and chants. Spoken Sanskrit has been revived in some villages with traditional institutions, and there are attempts to enhance its popularisation.", "output": "What is the opera performed in [Sanskrit]?", "explanation": "This is a good paraphrase, but the words in the bracket are changed, so the answer is invalid."}, {"input": "original question: Which opera is in [Sanskrit Language]?\nanswer: Satyagraha\nanswer type: Opera.\nauxiliary information: Sanskrit is the primary liturgical language of Hinduism, a philosophical language in Buddhism, Hinduism and Jainism, and a literary language that was in use as a lingua franca in the Indian cultural zone. It is a standardised dialect of the Old Indo-Aryan language, originating as Vedic Sanskrit and tracing its linguistic ancestry back to Proto-Indo-Iranian and Proto-Indo-European. Today it is listed as one of the 22 scheduled languages of India and is an official language of the state of Uttarakhand. Sanskrit holds a prominent position in Indo-European studies. The corpus of Sanskrit literature encompasses a rich tradition of poetry and drama as well as scientific, technical, philosophical and religious texts. Sanskrit continues to be widely used as a ceremonial language in Hindu religious rituals and Buddhist practice in the form of hymns and chants. Spoken Sanskrit has been revived in some villages with traditional institutions, and there are attempts to enhance its popularisation.", "output": "Sanskrit Language is the literary language of which opera?", "explanation": "You should remember to put the brakets around the preserved phrases."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Knowledge Base -> Freebase"], "Instance": {"id": "task402-f88fdca02bf84e79ab052bbcd1a1873a", "input": "original question: What is the professional field of [Website content writer]\nanswer: online marketing, independent content provider, internet marketing\nanswer type: Professional field.\nauxiliary information: A website content writer or web content writer is a person who specializes in providing relevant content for websites. Every website has a specific target audience and requires a different type and level of content. Content should contain words that attract and retain users on a website. Content written specifically for a website should concentrate on a specific topic. It should also be easy to read, offering the information in easy to understand clusters or laid out in bullet points. Most story pieces are centered on marketing products or services that the website is selling or endorsing, though this is not always the case. Some websites are informational only and do not sell a product or service. In those instances, the content should be geared toward helping to educate the reader while providing them with complex information in a way that is easy to understand and retain.", "output": ["What professional field does [Website content writer] belong to?", "[Website content writer] is what professional field?", "[Website content writer] is part of which professional field?", "A [Website content writer] is a member of what professional field?", "Which professional field does [Website content writer] pertain to?"]}, "Instance License": ["CC BY-SA 4.0"], "prediction": "What is the field of [Website content writer]?"}
+{"id": "task402-09402559bcd04e3985e0a94871716e75", "Task": "task402_grailqa_paraphrase_generation", "Contributors": "['Pegah Alipoormolabashi']", "Source": ["grailqa"], "URL": ["https://dki-lab.github.io/GrailQA/"], "Categories": ["Question Rewriting"], "Reasoning": [], "Definition": ["Compose a new way to ask the same question. The new question must be asking the exact same thing as the original question does. Without any other information, you should be able to tell that the original question and the new question are the same. Preserve bracketed phrases in your new question. You can change the rest of the question provided the above requirements are satisfied. The new question must have a natural, fluent formulation, as if it were composed by a native English speaker. You will be given three pieces of information to help you create better questions. Those are: \"Answer\": the answer to the question, e.g., \"Honolulu\". \"Answer Type\": the type of the answer, e.g., \"Location\". \"Auxiliary Information\" is a detailed description of some concepts mentioned in the question, if any."], "Positive Examples": [{"input": "original question: Who is the museum director of [Science Museum, London]?\nanswer: Ian Blatchford\nanswer type: Museum director. \nauxiliary information: The Science Museum is a major museum on Exhibition Road in South Kensington, London. It was founded in 1857 and today is one of the city's major tourist attractions, attracting 3.3 million visitors annually. Like other publicly funded national museums in the United Kingdom, the Science Museum does not charge visitors for admission. Temporary exhibitions, however, may incur an admission fee. It is part of the Science Museum Group, having merged with the Museum of Science and Industry in Manchester in 2012.", "output": "The museum director of the [Science Museum, London] is?", "explanation": "The question is correctly paraphrased in this example."}, {"input": "original question: Which zoo is in the category of [Public aquarium]?\nanswer: Istanbul Aquarium, Minnesota Zoo, Monterey Bay Aquarium...\nanswer type: Zoo.\nauxiliary information: A public aquarium is the aquatic counterpart of a zoo, which houses living aquatic animal and plant specimens for public viewing. Most public aquariums feature tanks larger than those kept by home aquarists, as well as smaller tanks. Since the first public aquariums were built in the mid-19th century, they have become popular and their numbers have increased. Most modern accredited aquariums stress conservation issues and educating the public.", "output": "What zoos are also considered to be [Public aquarium]s?", "explanation": "This answer correctly paraphrases the question."}, {"input": "original question: Which apis have the protocol of [JSON]?\nanswer: Hi5 API\nanswer type: API.\nauxiliary information: JSON canonically pronounced /\u00c0\u00e0d\u00a0\u00ede\u2026\u2122s\u2026\u00f4n/ JAY-s\u2026\u00f4n; sometimes JavaScript Object Notation, is an open standard format that uses human-readable text to transmit data objects consisting of attribute\u201a\u00c4\u00ecvalue pairs. It is used primarily to transmit data between a server and web application, as an alternative to XML. Although originally derived from the JavaScript scripting language, JSON is a language-independent data format. Code for parsing and generating JSON data is readily available in many programming languages. The JSON format was originally specified by Douglas Crockford. It is currently described by two competing standards, RFC 7159 and ECMA-404. The ECMA standard is minimal, describing only the allowed grammar syntax, whereas the RFC also provides some semantic and security considerations. The official Internet media type for JSON is application/json. The JSON filename extension is .json.", "output": "Which apis include the protocol of [JSON]?", "explanation": "This is a good paraphrase of the question."}], "Negative Examples": [{"input": "original question: Which opera is in [Sanskrit Language]?\nanswer: Satyagraha\nanswer type: Opera.\nauxiliary information: Sanskrit is the primary liturgical language of Hinduism, a philosophical language in Buddhism, Hinduism and Jainism, and a literary language that was in use as a lingua franca in the Indian cultural zone. It is a standardised dialect of the Old Indo-Aryan language, originating as Vedic Sanskrit and tracing its linguistic ancestry back to Proto-Indo-Iranian and Proto-Indo-European. Today it is listed as one of the 22 scheduled languages of India and is an official language of the state of Uttarakhand. Sanskrit holds a prominent position in Indo-European studies. The corpus of Sanskrit literature encompasses a rich tradition of poetry and drama as well as scientific, technical, philosophical and religious texts. Sanskrit continues to be widely used as a ceremonial language in Hindu religious rituals and Buddhist practice in the form of hymns and chants. Spoken Sanskrit has been revived in some villages with traditional institutions, and there are attempts to enhance its popularisation.", "output": "What is the opera performed in [Sanskrit]?", "explanation": "This is a good paraphrase, but the words in the bracket are changed, so the answer is invalid."}, {"input": "original question: Which opera is in [Sanskrit Language]?\nanswer: Satyagraha\nanswer type: Opera.\nauxiliary information: Sanskrit is the primary liturgical language of Hinduism, a philosophical language in Buddhism, Hinduism and Jainism, and a literary language that was in use as a lingua franca in the Indian cultural zone. It is a standardised dialect of the Old Indo-Aryan language, originating as Vedic Sanskrit and tracing its linguistic ancestry back to Proto-Indo-Iranian and Proto-Indo-European. Today it is listed as one of the 22 scheduled languages of India and is an official language of the state of Uttarakhand. Sanskrit holds a prominent position in Indo-European studies. The corpus of Sanskrit literature encompasses a rich tradition of poetry and drama as well as scientific, technical, philosophical and religious texts. Sanskrit continues to be widely used as a ceremonial language in Hindu religious rituals and Buddhist practice in the form of hymns and chants. Spoken Sanskrit has been revived in some villages with traditional institutions, and there are attempts to enhance its popularisation.", "output": "Sanskrit Language is the literary language of which opera?", "explanation": "You should remember to put the brakets around the preserved phrases."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Knowledge Base -> Freebase"], "Instance": {"id": "task402-09402559bcd04e3985e0a94871716e75", "input": "original question: Find products made of [Sugar]\nanswer: bon v\u2248\u00ecux 750ml\nanswer type: Product with ingredients.\nauxiliary information: Sugar is the generalized name for sweet, short-chain, soluble carbohydrates, many of which are used in food. They are carbohydrates, composed of carbon, hydrogen, and oxygen. There are various types of sugar derived from different sources. Simple sugars are called monosaccharides and include glucose, fructose and galactose. The table or granulated sugar most customarily used as food is sucrose, a disaccharide. Other disaccharides include maltose and lactose. Longer chains of sugars are called oligosaccharides. Chemically-different substances may also have a sweet taste, but are not classified as sugars. Some are used as lower-calorie food substitutes for sugar described as artificial sweeteners. Sugars are found in the tissues of most plants, but are present in sufficient concentrations for efficient extraction only in sugarcane and sugar beet. Sugarcane refers to any of several species of giant grass in the genus Saccharum that have been cultivated in tropical climates in South Asia and Southeast Asia since ancient times. A great expansion in its production took place in the 18th century with the establishment of sugar plantations in the West Indies and Americas.", "output": ["[Sugar] is found in what products?", "[Sugar] composes what products?", "Give me some products that are made with [Sugar] in it.", "What products are made with  [Sugar].", "[Sugar] is used to make what products?"]}, "Instance License": ["CC BY-SA 4.0"], "prediction": "What is the name of the main source of sugar in the world?"}
+{"id": "task201-e047a21f70ab4f44a036069c9f9669c0", "Task": "task201_mnli_neutral_classification", "Contributors": "['Anjana Arunkumar']", "Source": ["multinli"], "URL": ["https://cims.nyu.edu/~sbowman/multinli/paper.pdf"], "Categories": ["Textual Entailment"], "Reasoning": ["Textual Entailment -> Deductive Reasoning", "Commonsense Reasoning"], "Definition": ["In this task, you're given a statement and three sentences as choices. Your job is to determine the neutral choice based on your inference from the statement and your commonsense knowledge. The neutral choice is a sentence that neither agrees nor disagrees with the statement. Indicate your answer as '1', '2', or '3', corresponding to the choice number of the selected sentence. If sentence X agrees with sentence Y, one's correctness follows from the other one. If sentence X disagrees with sentence Y, they can not be correct at the same time."], "Positive Examples": [{"input": "Statement: Next to the MGM Grand you will find M and M World, four stories of merchandise and memorabilia dedicated to the candy that doesn't melt in your hand. Choices: 1. The candy has many fans who love its attractions. 2. There's four stories of memorabilia dedicated to a candy. 3. That particular candy melts and becomes difficult to eat.", "output": "1", "explanation": "The candy may or may not be popular and the first choice is correct. Based on the statement, candy doesn't melt and there's four stories of memorabilia dedicated to a candy. So the second choice agrees with the statement and the third choice disagrees with the statement."}, {"input": "Statment: I've forgotten his name now, confessed Tuppence. Choices: 1. Tuppence forgot his name. 2.Tuppence remembered his name later. 3. Tuppence never could forget his name.", "output": "2", "explanation": "Tuppence may or may not have later remembered the name, and has definitely forgotten it. So the first choice agrees with the statement, the third choice disagrees with the statement and the second choice is correct."}, {"input": "Statement: One of the first organizational realignments taking place is in the Office of the Taxpayer Advocate. Choices: 1. The office of the taxpayer advocate is the last to be realigned. 2. The realignment is taking place over a few weeks. 3. The office of the taxpayer advocate is having an organizational realignment.", "output": "2", "explanation": "The office realignment duration is not known. So the second choice doesn't agree with the statement and doesn't disagree with it either."}, {"input": "Statement: yeah i tell you what though if you go price some of those tennis shoes i can see why now you know they're getting up in the hundred dollar range. Choices: 1. The tennis shoes have a range of prices. 2. The tennis shoes can be in the hundred dollar range. 3. The tennis shoes are not over hundred dollars.", "output": "1", "explanation": "The range of shoes' prices is not known. And, the first choice is correct."}], "Negative Examples": [{"input": "Statement: In 1994, fraction of households owning a personal computer is 0.25. Choices: 1. In 1994, 0.25 of households owned a PC, which was a high sum at the time. 2. In 1984, 0.8 of households owned a PC. In 1994, 0.25 of households owned a PC.", "output": "3", "explanation": "The choice and statement both clearly fully agree that 0.25 of all households had PCs in 1994, hence choice 3 is incorrect."}, {"input": "Statement: You could say you were in an auto accident, and the ambulance driver took you straight to Dr. Famous' office. Choices: 1. Ambulance drivers knew Dr Famous was great for treating famous people. 2. Ambulance drivers just took you to the hospital. 3. Ambulance drivers knew Dr Famous.", "output": "2", "explanation": "The ambulance took the person to Dr. Famous, and not a hospital, so the second choice clearly disagress with the statement and is incorrect."}, {"input": "Statement: The cattle and sugar barrels exported from the plantation in fact had these initials branded onto them. Choices: 1. There is no branding on barrels and cattle from the plantation. 2. The plantation produces tobacco in addition to cattle and sugar. 3. These initials were branded onto the barrels of sugar that were exported.", "output": "1", "explanation": "Based on the statement there are branding on barrels and cattle from the plantation. So, the first sentence disagrees with the statement and it's incorrect. The correct answer is choice 2. "}, {"input": "Statement:  There were results at once. Choices: 1. The results came too slowly.  2. The results were abundant.  3. There were results asap. ", "output": "1", "explanation": "Based on the statement, There were results asap. So the first choice disagrees with the statement and it is incorrect. We don't know if the results were abundant or not and the second choice is correct."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["History", "Fiction", "Dialogue", "Law", "Government and Politics"], "Instance": {"id": "task201-e047a21f70ab4f44a036069c9f9669c0", "input": "Statement: You've never had a job. Choices: 1. You've never worked. 2. You've never been employed.  3. You had a job in the past. ", "output": ["1"]}, "Instance License": ["OANC"], "prediction": "2"}
+{"id": "task201-e751866455854760886db81e08a47a00", "Task": "task201_mnli_neutral_classification", "Contributors": "['Anjana Arunkumar']", "Source": ["multinli"], "URL": ["https://cims.nyu.edu/~sbowman/multinli/paper.pdf"], "Categories": ["Textual Entailment"], "Reasoning": ["Textual Entailment -> Deductive Reasoning", "Commonsense Reasoning"], "Definition": ["In this task, you're given a statement and three sentences as choices. Your job is to determine the neutral choice based on your inference from the statement and your commonsense knowledge. The neutral choice is a sentence that neither agrees nor disagrees with the statement. Indicate your answer as '1', '2', or '3', corresponding to the choice number of the selected sentence. If sentence X agrees with sentence Y, one's correctness follows from the other one. If sentence X disagrees with sentence Y, they can not be correct at the same time."], "Positive Examples": [{"input": "Statement: Next to the MGM Grand you will find M and M World, four stories of merchandise and memorabilia dedicated to the candy that doesn't melt in your hand. Choices: 1. The candy has many fans who love its attractions. 2. There's four stories of memorabilia dedicated to a candy. 3. That particular candy melts and becomes difficult to eat.", "output": "1", "explanation": "The candy may or may not be popular and the first choice is correct. Based on the statement, candy doesn't melt and there's four stories of memorabilia dedicated to a candy. So the second choice agrees with the statement and the third choice disagrees with the statement."}, {"input": "Statment: I've forgotten his name now, confessed Tuppence. Choices: 1. Tuppence forgot his name. 2.Tuppence remembered his name later. 3. Tuppence never could forget his name.", "output": "2", "explanation": "Tuppence may or may not have later remembered the name, and has definitely forgotten it. So the first choice agrees with the statement, the third choice disagrees with the statement and the second choice is correct."}, {"input": "Statement: One of the first organizational realignments taking place is in the Office of the Taxpayer Advocate. Choices: 1. The office of the taxpayer advocate is the last to be realigned. 2. The realignment is taking place over a few weeks. 3. The office of the taxpayer advocate is having an organizational realignment.", "output": "2", "explanation": "The office realignment duration is not known. So the second choice doesn't agree with the statement and doesn't disagree with it either."}, {"input": "Statement: yeah i tell you what though if you go price some of those tennis shoes i can see why now you know they're getting up in the hundred dollar range. Choices: 1. The tennis shoes have a range of prices. 2. The tennis shoes can be in the hundred dollar range. 3. The tennis shoes are not over hundred dollars.", "output": "1", "explanation": "The range of shoes' prices is not known. And, the first choice is correct."}], "Negative Examples": [{"input": "Statement: In 1994, fraction of households owning a personal computer is 0.25. Choices: 1. In 1994, 0.25 of households owned a PC, which was a high sum at the time. 2. In 1984, 0.8 of households owned a PC. In 1994, 0.25 of households owned a PC.", "output": "3", "explanation": "The choice and statement both clearly fully agree that 0.25 of all households had PCs in 1994, hence choice 3 is incorrect."}, {"input": "Statement: You could say you were in an auto accident, and the ambulance driver took you straight to Dr. Famous' office. Choices: 1. Ambulance drivers knew Dr Famous was great for treating famous people. 2. Ambulance drivers just took you to the hospital. 3. Ambulance drivers knew Dr Famous.", "output": "2", "explanation": "The ambulance took the person to Dr. Famous, and not a hospital, so the second choice clearly disagress with the statement and is incorrect."}, {"input": "Statement: The cattle and sugar barrels exported from the plantation in fact had these initials branded onto them. Choices: 1. There is no branding on barrels and cattle from the plantation. 2. The plantation produces tobacco in addition to cattle and sugar. 3. These initials were branded onto the barrels of sugar that were exported.", "output": "1", "explanation": "Based on the statement there are branding on barrels and cattle from the plantation. So, the first sentence disagrees with the statement and it's incorrect. The correct answer is choice 2. "}, {"input": "Statement:  There were results at once. Choices: 1. The results came too slowly.  2. The results were abundant.  3. There were results asap. ", "output": "1", "explanation": "Based on the statement, There were results asap. So the first choice disagrees with the statement and it is incorrect. We don't know if the results were abundant or not and the second choice is correct."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["History", "Fiction", "Dialogue", "Law", "Government and Politics"], "Instance": {"id": "task201-e751866455854760886db81e08a47a00", "input": "Statement: For example, mail could be sorted one day and delivered the next, resulting in a less demanding schedule. Choices: 1. The schedule is more hectic when mail is sorted in one day and delivered in another. 2. If mail can be sorted in one day, delivered the next the schedule will be less demanding.  3. A two day system of mail delivery works best. ", "output": ["3"]}, "Instance License": ["OANC"], "prediction": "2"}
+{"id": "task201-5ba4eb1c9f154fdf8bb5d966d2869165", "Task": "task201_mnli_neutral_classification", "Contributors": "['Anjana Arunkumar']", "Source": ["multinli"], "URL": ["https://cims.nyu.edu/~sbowman/multinli/paper.pdf"], "Categories": ["Textual Entailment"], "Reasoning": ["Textual Entailment -> Deductive Reasoning", "Commonsense Reasoning"], "Definition": ["In this task, you're given a statement and three sentences as choices. Your job is to determine the neutral choice based on your inference from the statement and your commonsense knowledge. The neutral choice is a sentence that neither agrees nor disagrees with the statement. Indicate your answer as '1', '2', or '3', corresponding to the choice number of the selected sentence. If sentence X agrees with sentence Y, one's correctness follows from the other one. If sentence X disagrees with sentence Y, they can not be correct at the same time."], "Positive Examples": [{"input": "Statement: Next to the MGM Grand you will find M and M World, four stories of merchandise and memorabilia dedicated to the candy that doesn't melt in your hand. Choices: 1. The candy has many fans who love its attractions. 2. There's four stories of memorabilia dedicated to a candy. 3. That particular candy melts and becomes difficult to eat.", "output": "1", "explanation": "The candy may or may not be popular and the first choice is correct. Based on the statement, candy doesn't melt and there's four stories of memorabilia dedicated to a candy. So the second choice agrees with the statement and the third choice disagrees with the statement."}, {"input": "Statment: I've forgotten his name now, confessed Tuppence. Choices: 1. Tuppence forgot his name. 2.Tuppence remembered his name later. 3. Tuppence never could forget his name.", "output": "2", "explanation": "Tuppence may or may not have later remembered the name, and has definitely forgotten it. So the first choice agrees with the statement, the third choice disagrees with the statement and the second choice is correct."}, {"input": "Statement: One of the first organizational realignments taking place is in the Office of the Taxpayer Advocate. Choices: 1. The office of the taxpayer advocate is the last to be realigned. 2. The realignment is taking place over a few weeks. 3. The office of the taxpayer advocate is having an organizational realignment.", "output": "2", "explanation": "The office realignment duration is not known. So the second choice doesn't agree with the statement and doesn't disagree with it either."}, {"input": "Statement: yeah i tell you what though if you go price some of those tennis shoes i can see why now you know they're getting up in the hundred dollar range. Choices: 1. The tennis shoes have a range of prices. 2. The tennis shoes can be in the hundred dollar range. 3. The tennis shoes are not over hundred dollars.", "output": "1", "explanation": "The range of shoes' prices is not known. And, the first choice is correct."}], "Negative Examples": [{"input": "Statement: In 1994, fraction of households owning a personal computer is 0.25. Choices: 1. In 1994, 0.25 of households owned a PC, which was a high sum at the time. 2. In 1984, 0.8 of households owned a PC. In 1994, 0.25 of households owned a PC.", "output": "3", "explanation": "The choice and statement both clearly fully agree that 0.25 of all households had PCs in 1994, hence choice 3 is incorrect."}, {"input": "Statement: You could say you were in an auto accident, and the ambulance driver took you straight to Dr. Famous' office. Choices: 1. Ambulance drivers knew Dr Famous was great for treating famous people. 2. Ambulance drivers just took you to the hospital. 3. Ambulance drivers knew Dr Famous.", "output": "2", "explanation": "The ambulance took the person to Dr. Famous, and not a hospital, so the second choice clearly disagress with the statement and is incorrect."}, {"input": "Statement: The cattle and sugar barrels exported from the plantation in fact had these initials branded onto them. Choices: 1. There is no branding on barrels and cattle from the plantation. 2. The plantation produces tobacco in addition to cattle and sugar. 3. These initials were branded onto the barrels of sugar that were exported.", "output": "1", "explanation": "Based on the statement there are branding on barrels and cattle from the plantation. So, the first sentence disagrees with the statement and it's incorrect. The correct answer is choice 2. "}, {"input": "Statement:  There were results at once. Choices: 1. The results came too slowly.  2. The results were abundant.  3. There were results asap. ", "output": "1", "explanation": "Based on the statement, There were results asap. So the first choice disagrees with the statement and it is incorrect. We don't know if the results were abundant or not and the second choice is correct."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["History", "Fiction", "Dialogue", "Law", "Government and Politics"], "Instance": {"id": "task201-5ba4eb1c9f154fdf8bb5d966d2869165", "input": "Statement: Spun and spun and spun the president's denial for months without bothering to check if it was true. Choices: 1. The President's advisors knew that it wasn't true. 2. The President was completely open from the start and made no denials. 3. The President kept denying, but did not check to see if it was true.", "output": ["1"]}, "Instance License": ["OANC"], "prediction": "3"}
+{"id": "task201-052923547b384b7eb229246fa7418eeb", "Task": "task201_mnli_neutral_classification", "Contributors": "['Anjana Arunkumar']", "Source": ["multinli"], "URL": ["https://cims.nyu.edu/~sbowman/multinli/paper.pdf"], "Categories": ["Textual Entailment"], "Reasoning": ["Textual Entailment -> Deductive Reasoning", "Commonsense Reasoning"], "Definition": ["In this task, you're given a statement and three sentences as choices. Your job is to determine the neutral choice based on your inference from the statement and your commonsense knowledge. The neutral choice is a sentence that neither agrees nor disagrees with the statement. Indicate your answer as '1', '2', or '3', corresponding to the choice number of the selected sentence. If sentence X agrees with sentence Y, one's correctness follows from the other one. If sentence X disagrees with sentence Y, they can not be correct at the same time."], "Positive Examples": [{"input": "Statement: Next to the MGM Grand you will find M and M World, four stories of merchandise and memorabilia dedicated to the candy that doesn't melt in your hand. Choices: 1. The candy has many fans who love its attractions. 2. There's four stories of memorabilia dedicated to a candy. 3. That particular candy melts and becomes difficult to eat.", "output": "1", "explanation": "The candy may or may not be popular and the first choice is correct. Based on the statement, candy doesn't melt and there's four stories of memorabilia dedicated to a candy. So the second choice agrees with the statement and the third choice disagrees with the statement."}, {"input": "Statment: I've forgotten his name now, confessed Tuppence. Choices: 1. Tuppence forgot his name. 2.Tuppence remembered his name later. 3. Tuppence never could forget his name.", "output": "2", "explanation": "Tuppence may or may not have later remembered the name, and has definitely forgotten it. So the first choice agrees with the statement, the third choice disagrees with the statement and the second choice is correct."}, {"input": "Statement: One of the first organizational realignments taking place is in the Office of the Taxpayer Advocate. Choices: 1. The office of the taxpayer advocate is the last to be realigned. 2. The realignment is taking place over a few weeks. 3. The office of the taxpayer advocate is having an organizational realignment.", "output": "2", "explanation": "The office realignment duration is not known. So the second choice doesn't agree with the statement and doesn't disagree with it either."}, {"input": "Statement: yeah i tell you what though if you go price some of those tennis shoes i can see why now you know they're getting up in the hundred dollar range. Choices: 1. The tennis shoes have a range of prices. 2. The tennis shoes can be in the hundred dollar range. 3. The tennis shoes are not over hundred dollars.", "output": "1", "explanation": "The range of shoes' prices is not known. And, the first choice is correct."}], "Negative Examples": [{"input": "Statement: In 1994, fraction of households owning a personal computer is 0.25. Choices: 1. In 1994, 0.25 of households owned a PC, which was a high sum at the time. 2. In 1984, 0.8 of households owned a PC. In 1994, 0.25 of households owned a PC.", "output": "3", "explanation": "The choice and statement both clearly fully agree that 0.25 of all households had PCs in 1994, hence choice 3 is incorrect."}, {"input": "Statement: You could say you were in an auto accident, and the ambulance driver took you straight to Dr. Famous' office. Choices: 1. Ambulance drivers knew Dr Famous was great for treating famous people. 2. Ambulance drivers just took you to the hospital. 3. Ambulance drivers knew Dr Famous.", "output": "2", "explanation": "The ambulance took the person to Dr. Famous, and not a hospital, so the second choice clearly disagress with the statement and is incorrect."}, {"input": "Statement: The cattle and sugar barrels exported from the plantation in fact had these initials branded onto them. Choices: 1. There is no branding on barrels and cattle from the plantation. 2. The plantation produces tobacco in addition to cattle and sugar. 3. These initials were branded onto the barrels of sugar that were exported.", "output": "1", "explanation": "Based on the statement there are branding on barrels and cattle from the plantation. So, the first sentence disagrees with the statement and it's incorrect. The correct answer is choice 2. "}, {"input": "Statement:  There were results at once. Choices: 1. The results came too slowly.  2. The results were abundant.  3. There were results asap. ", "output": "1", "explanation": "Based on the statement, There were results asap. So the first choice disagrees with the statement and it is incorrect. We don't know if the results were abundant or not and the second choice is correct."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["History", "Fiction", "Dialogue", "Law", "Government and Politics"], "Instance": {"id": "task201-052923547b384b7eb229246fa7418eeb", "input": "Statement: and it's all over him the poor thing you know so there's definitely hazards to going camping if you don't know what you're looking at Choices: 1. You should know what you're doing if you want to go camping. 2. He got covered in poison ivy because he didn't recognize it. 3. Camping is very safe and you don't know what you're looking at.", "output": ["2"]}, "Instance License": ["OANC"], "prediction": "1"}
+{"id": "task201-e9c022b8c6704905bb03f758879604b2", "Task": "task201_mnli_neutral_classification", "Contributors": "['Anjana Arunkumar']", "Source": ["multinli"], "URL": ["https://cims.nyu.edu/~sbowman/multinli/paper.pdf"], "Categories": ["Textual Entailment"], "Reasoning": ["Textual Entailment -> Deductive Reasoning", "Commonsense Reasoning"], "Definition": ["In this task, you're given a statement and three sentences as choices. Your job is to determine the neutral choice based on your inference from the statement and your commonsense knowledge. The neutral choice is a sentence that neither agrees nor disagrees with the statement. Indicate your answer as '1', '2', or '3', corresponding to the choice number of the selected sentence. If sentence X agrees with sentence Y, one's correctness follows from the other one. If sentence X disagrees with sentence Y, they can not be correct at the same time."], "Positive Examples": [{"input": "Statement: Next to the MGM Grand you will find M and M World, four stories of merchandise and memorabilia dedicated to the candy that doesn't melt in your hand. Choices: 1. The candy has many fans who love its attractions. 2. There's four stories of memorabilia dedicated to a candy. 3. That particular candy melts and becomes difficult to eat.", "output": "1", "explanation": "The candy may or may not be popular and the first choice is correct. Based on the statement, candy doesn't melt and there's four stories of memorabilia dedicated to a candy. So the second choice agrees with the statement and the third choice disagrees with the statement."}, {"input": "Statment: I've forgotten his name now, confessed Tuppence. Choices: 1. Tuppence forgot his name. 2.Tuppence remembered his name later. 3. Tuppence never could forget his name.", "output": "2", "explanation": "Tuppence may or may not have later remembered the name, and has definitely forgotten it. So the first choice agrees with the statement, the third choice disagrees with the statement and the second choice is correct."}, {"input": "Statement: One of the first organizational realignments taking place is in the Office of the Taxpayer Advocate. Choices: 1. The office of the taxpayer advocate is the last to be realigned. 2. The realignment is taking place over a few weeks. 3. The office of the taxpayer advocate is having an organizational realignment.", "output": "2", "explanation": "The office realignment duration is not known. So the second choice doesn't agree with the statement and doesn't disagree with it either."}, {"input": "Statement: yeah i tell you what though if you go price some of those tennis shoes i can see why now you know they're getting up in the hundred dollar range. Choices: 1. The tennis shoes have a range of prices. 2. The tennis shoes can be in the hundred dollar range. 3. The tennis shoes are not over hundred dollars.", "output": "1", "explanation": "The range of shoes' prices is not known. And, the first choice is correct."}], "Negative Examples": [{"input": "Statement: In 1994, fraction of households owning a personal computer is 0.25. Choices: 1. In 1994, 0.25 of households owned a PC, which was a high sum at the time. 2. In 1984, 0.8 of households owned a PC. In 1994, 0.25 of households owned a PC.", "output": "3", "explanation": "The choice and statement both clearly fully agree that 0.25 of all households had PCs in 1994, hence choice 3 is incorrect."}, {"input": "Statement: You could say you were in an auto accident, and the ambulance driver took you straight to Dr. Famous' office. Choices: 1. Ambulance drivers knew Dr Famous was great for treating famous people. 2. Ambulance drivers just took you to the hospital. 3. Ambulance drivers knew Dr Famous.", "output": "2", "explanation": "The ambulance took the person to Dr. Famous, and not a hospital, so the second choice clearly disagress with the statement and is incorrect."}, {"input": "Statement: The cattle and sugar barrels exported from the plantation in fact had these initials branded onto them. Choices: 1. There is no branding on barrels and cattle from the plantation. 2. The plantation produces tobacco in addition to cattle and sugar. 3. These initials were branded onto the barrels of sugar that were exported.", "output": "1", "explanation": "Based on the statement there are branding on barrels and cattle from the plantation. So, the first sentence disagrees with the statement and it's incorrect. The correct answer is choice 2. "}, {"input": "Statement:  There were results at once. Choices: 1. The results came too slowly.  2. The results were abundant.  3. There were results asap. ", "output": "1", "explanation": "Based on the statement, There were results asap. So the first choice disagrees with the statement and it is incorrect. We don't know if the results were abundant or not and the second choice is correct."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["History", "Fiction", "Dialogue", "Law", "Government and Politics"], "Instance": {"id": "task201-e9c022b8c6704905bb03f758879604b2", "input": "Statement: no no no you went to Galveston uh i have a favorite hotel that extends out over the water Choices: 1. You went to Dallas. 2. You went to Galveston while I was in Arizona. 3. You went to Galveston.", "output": ["2"]}, "Instance License": ["OANC"], "prediction": "3"}
+{"id": "task520-948963bd86e2454b966af103d2956f9a", "Task": "task520_aquamuse_answer_given_in_passage", "Contributors": "['Kirby Kuznia']", "Source": ["aquamuse"], "URL": ["https://huggingface.co/datasets/aquamuse"], "Categories": ["Answerability Classification"], "Reasoning": [], "Definition": ["In this task you will be given a question and a passage. You need to determine if the answer to the question is contained in the passage. If the answer can be found in the passage you should output 'True'. If the answer cannot be found in the passage you should output 'False'."], "Positive Examples": [{"input": "Passage: 'The size of a matrix is defined by the number of rows and columns that it contains. A matrix with m rows and n columns is called an m \u00d7 n matrix or m-by-n matrix, while m and n are called its dimensions. For example, the matrix A above is a 3 \u00d7 2 matrix.'. Question: 'who came up with eating turkey on thanksgiving'.", "output": "False", "explanation": "The passage does not mention anything about Thanksgiving turkeys so the passage does not answer the question. The output is 'False', so this is a good example."}, {"input": "Passage: 'Elephants are large mammals of the family Elephantidae and the order Proboscidea. Three species are currently recognised: the African bush elephant (Loxodonta africana), the African forest elephant (L. cyclotis), and the Asian elephant (Elephas maximus). Elephants are scattered throughout sub-Saharan Africa, South Asia, and Southeast Asia. Elephantidae is the only surviving family of the order Proboscidea; other, now extinct, members of the order include deinotheres, gomphotheres, mammoths, and mastodons.'. Question: 'what is the scientific name of a elephant'.", "output": "True", "explanation": "The passage contains information about the scientific name of an elephant. Therefore, the passage could answer the question so the output is 'True'. So this is a good example."}], "Negative Examples": [{"input": "The forward assist on a firearm is a button found commonly on AR-15 rifle derivatives, such as the M16 rifle, and is usually located near the bolt closure. When hit, it pushes the bolt carrier forward, ensuring that the bolt is locked. In order to ensure that the extractor is clipped around the rim of the casing, the forward assist is usually struck rather than pushed. It is commonly incorporated into standard loading procedure to prepare a firearm for firing, or to close the bolt when the firearm is excessively dirty.'. Question: 'how many olympic gold medals does stephen curry have'.", "output": "True", "explanation": "The passage does not contain any information about olympic gold medals or stephen curry. The output should have been 'False' because you cannot answer the question given the passage. So this is a bad example."}, {"input": "Passage: 'Nuclear fusion powers a star for most of its life. Initially the energy is generated by the fusion of hydrogen atoms at the core of the main-sequence star. Later, as the preponderance of atoms at the core becomes helium, stars like the Sun begin to fuse hydrogen along a spherical shell surrounding the core. This process causes the star to gradually grow in size, passing through the subgiant stage until it reaches the red giant phase. Stars with at least half the mass of the Sun can also begin to generate energy through the fusion of helium at their core, whereas more-massive stars can fuse heavier elements along a series of concentric shells. Once a star like the Sun has exhausted its nuclear fuel, its core collapses into a dense white dwarf and the outer layers are expelled as a planetary nebula. Stars with around ten or more times the mass of the Sun can explode in a supernova as their inert iron cores collapse into an extremely dense neutron star or black hole. Although the universe is not old enough for any of the smallest red dwarfs to have reached the end of their lives, stellar models suggest they will slowly become brighter and hotter before running out of hydrogen fuel and becoming low-mass white dwarfs.'. Question: 'what characteristic of helium makes it a major constituent of the pulsating star mechanism'.", "output": "False", "explanation": "The passage contains information about the characteristics of helium and can be used to answer the question. The answer should have been 'True'. So this is a bad example."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Miscellaneous"], "Instance": {"id": "task520-948963bd86e2454b966af103d2956f9a", "input": "Passage: 'PlayStation Network's services are dedicated to an online marketplace (PlayStation Store), a premium subscription service for enhanced gaming and social features (PlayStation Plus), movie streaming, rentals and purchases (PlayStation Video), a cloud-based television programming service (PlayStation Vue), music streaming (PlayStation Music) and a cloud gaming service (PlayStation Now).'. Question: 'what is the difference between playstation store and playstation network'.", "output": ["True"]}, "Instance License": ["Unknown"], "prediction": "True"}
+{"id": "task520-472d0ab563124f569f160065cfc58aa1", "Task": "task520_aquamuse_answer_given_in_passage", "Contributors": "['Kirby Kuznia']", "Source": ["aquamuse"], "URL": ["https://huggingface.co/datasets/aquamuse"], "Categories": ["Answerability Classification"], "Reasoning": [], "Definition": ["In this task you will be given a question and a passage. You need to determine if the answer to the question is contained in the passage. If the answer can be found in the passage you should output 'True'. If the answer cannot be found in the passage you should output 'False'."], "Positive Examples": [{"input": "Passage: 'The size of a matrix is defined by the number of rows and columns that it contains. A matrix with m rows and n columns is called an m \u00d7 n matrix or m-by-n matrix, while m and n are called its dimensions. For example, the matrix A above is a 3 \u00d7 2 matrix.'. Question: 'who came up with eating turkey on thanksgiving'.", "output": "False", "explanation": "The passage does not mention anything about Thanksgiving turkeys so the passage does not answer the question. The output is 'False', so this is a good example."}, {"input": "Passage: 'Elephants are large mammals of the family Elephantidae and the order Proboscidea. Three species are currently recognised: the African bush elephant (Loxodonta africana), the African forest elephant (L. cyclotis), and the Asian elephant (Elephas maximus). Elephants are scattered throughout sub-Saharan Africa, South Asia, and Southeast Asia. Elephantidae is the only surviving family of the order Proboscidea; other, now extinct, members of the order include deinotheres, gomphotheres, mammoths, and mastodons.'. Question: 'what is the scientific name of a elephant'.", "output": "True", "explanation": "The passage contains information about the scientific name of an elephant. Therefore, the passage could answer the question so the output is 'True'. So this is a good example."}], "Negative Examples": [{"input": "The forward assist on a firearm is a button found commonly on AR-15 rifle derivatives, such as the M16 rifle, and is usually located near the bolt closure. When hit, it pushes the bolt carrier forward, ensuring that the bolt is locked. In order to ensure that the extractor is clipped around the rim of the casing, the forward assist is usually struck rather than pushed. It is commonly incorporated into standard loading procedure to prepare a firearm for firing, or to close the bolt when the firearm is excessively dirty.'. Question: 'how many olympic gold medals does stephen curry have'.", "output": "True", "explanation": "The passage does not contain any information about olympic gold medals or stephen curry. The output should have been 'False' because you cannot answer the question given the passage. So this is a bad example."}, {"input": "Passage: 'Nuclear fusion powers a star for most of its life. Initially the energy is generated by the fusion of hydrogen atoms at the core of the main-sequence star. Later, as the preponderance of atoms at the core becomes helium, stars like the Sun begin to fuse hydrogen along a spherical shell surrounding the core. This process causes the star to gradually grow in size, passing through the subgiant stage until it reaches the red giant phase. Stars with at least half the mass of the Sun can also begin to generate energy through the fusion of helium at their core, whereas more-massive stars can fuse heavier elements along a series of concentric shells. Once a star like the Sun has exhausted its nuclear fuel, its core collapses into a dense white dwarf and the outer layers are expelled as a planetary nebula. Stars with around ten or more times the mass of the Sun can explode in a supernova as their inert iron cores collapse into an extremely dense neutron star or black hole. Although the universe is not old enough for any of the smallest red dwarfs to have reached the end of their lives, stellar models suggest they will slowly become brighter and hotter before running out of hydrogen fuel and becoming low-mass white dwarfs.'. Question: 'what characteristic of helium makes it a major constituent of the pulsating star mechanism'.", "output": "False", "explanation": "The passage contains information about the characteristics of helium and can be used to answer the question. The answer should have been 'True'. So this is a bad example."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Miscellaneous"], "Instance": {"id": "task520-472d0ab563124f569f160065cfc58aa1", "input": "Passage: 'The Yellow River or Huang He (listen) is the third longest river in Asia, after the Yangtze River and Yenisei River, and the sixth-longest river system in the world at the estimated length of 5,464 km (3,395 mi). Originating in the Bayan Har Mountains in Qinghai province of western China, it flows through nine provinces, and it empties into the Bohai Sea near the city of Dongying in Shandong province. The Yellow River basin has an east -- west extent of about 1,900 kilometers (1,180 mi) and a north -- south extent of about 1,100 km (680 mi). Its total drainage area is about 752,546 square kilometers (290,560 sq mi).'. Question: 'when did woodblock printing become widely used throughout east asia'.", "output": ["False"]}, "Instance License": ["Unknown"], "prediction": "False"}
+{"id": "task520-38791d9f547e402a89a1e76c4f0b17e1", "Task": "task520_aquamuse_answer_given_in_passage", "Contributors": "['Kirby Kuznia']", "Source": ["aquamuse"], "URL": ["https://huggingface.co/datasets/aquamuse"], "Categories": ["Answerability Classification"], "Reasoning": [], "Definition": ["In this task you will be given a question and a passage. You need to determine if the answer to the question is contained in the passage. If the answer can be found in the passage you should output 'True'. If the answer cannot be found in the passage you should output 'False'."], "Positive Examples": [{"input": "Passage: 'The size of a matrix is defined by the number of rows and columns that it contains. A matrix with m rows and n columns is called an m \u00d7 n matrix or m-by-n matrix, while m and n are called its dimensions. For example, the matrix A above is a 3 \u00d7 2 matrix.'. Question: 'who came up with eating turkey on thanksgiving'.", "output": "False", "explanation": "The passage does not mention anything about Thanksgiving turkeys so the passage does not answer the question. The output is 'False', so this is a good example."}, {"input": "Passage: 'Elephants are large mammals of the family Elephantidae and the order Proboscidea. Three species are currently recognised: the African bush elephant (Loxodonta africana), the African forest elephant (L. cyclotis), and the Asian elephant (Elephas maximus). Elephants are scattered throughout sub-Saharan Africa, South Asia, and Southeast Asia. Elephantidae is the only surviving family of the order Proboscidea; other, now extinct, members of the order include deinotheres, gomphotheres, mammoths, and mastodons.'. Question: 'what is the scientific name of a elephant'.", "output": "True", "explanation": "The passage contains information about the scientific name of an elephant. Therefore, the passage could answer the question so the output is 'True'. So this is a good example."}], "Negative Examples": [{"input": "The forward assist on a firearm is a button found commonly on AR-15 rifle derivatives, such as the M16 rifle, and is usually located near the bolt closure. When hit, it pushes the bolt carrier forward, ensuring that the bolt is locked. In order to ensure that the extractor is clipped around the rim of the casing, the forward assist is usually struck rather than pushed. It is commonly incorporated into standard loading procedure to prepare a firearm for firing, or to close the bolt when the firearm is excessively dirty.'. Question: 'how many olympic gold medals does stephen curry have'.", "output": "True", "explanation": "The passage does not contain any information about olympic gold medals or stephen curry. The output should have been 'False' because you cannot answer the question given the passage. So this is a bad example."}, {"input": "Passage: 'Nuclear fusion powers a star for most of its life. Initially the energy is generated by the fusion of hydrogen atoms at the core of the main-sequence star. Later, as the preponderance of atoms at the core becomes helium, stars like the Sun begin to fuse hydrogen along a spherical shell surrounding the core. This process causes the star to gradually grow in size, passing through the subgiant stage until it reaches the red giant phase. Stars with at least half the mass of the Sun can also begin to generate energy through the fusion of helium at their core, whereas more-massive stars can fuse heavier elements along a series of concentric shells. Once a star like the Sun has exhausted its nuclear fuel, its core collapses into a dense white dwarf and the outer layers are expelled as a planetary nebula. Stars with around ten or more times the mass of the Sun can explode in a supernova as their inert iron cores collapse into an extremely dense neutron star or black hole. Although the universe is not old enough for any of the smallest red dwarfs to have reached the end of their lives, stellar models suggest they will slowly become brighter and hotter before running out of hydrogen fuel and becoming low-mass white dwarfs.'. Question: 'what characteristic of helium makes it a major constituent of the pulsating star mechanism'.", "output": "False", "explanation": "The passage contains information about the characteristics of helium and can be used to answer the question. The answer should have been 'True'. So this is a bad example."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Miscellaneous"], "Instance": {"id": "task520-38791d9f547e402a89a1e76c4f0b17e1", "input": "Passage: 'The operating system can be located on any storage, but is typically installed on a hard disk or solid-state drive. A Live CD represents the concept of running an operating system directly from a CD. While this is slow compared to storing the operating system on a hard disk drive, it is typically used for installation of operating systems, demonstrations, system recovery, or other special purposes. Large flash memory is currently more expensive than hard disk drives of similar size (as of mid-2014) but are starting to appear in laptop computers because of their low weight, small size and low power requirements. Computer communications involve internal modem cards, modems, network adapter cards, and routers. Common peripherals and adapter cards include headsets, joysticks, microphones, printers, scanners, sound adapter cards (as a separate card rather than located on the motherboard), speakers and webcams.'. Question: 'what is common between foehn and chinook winds'.", "output": ["False"]}, "Instance License": ["Unknown"], "prediction": "False"}
+{"id": "task520-078a03bd9f9442a58f180ce523863209", "Task": "task520_aquamuse_answer_given_in_passage", "Contributors": "['Kirby Kuznia']", "Source": ["aquamuse"], "URL": ["https://huggingface.co/datasets/aquamuse"], "Categories": ["Answerability Classification"], "Reasoning": [], "Definition": ["In this task you will be given a question and a passage. You need to determine if the answer to the question is contained in the passage. If the answer can be found in the passage you should output 'True'. If the answer cannot be found in the passage you should output 'False'."], "Positive Examples": [{"input": "Passage: 'The size of a matrix is defined by the number of rows and columns that it contains. A matrix with m rows and n columns is called an m \u00d7 n matrix or m-by-n matrix, while m and n are called its dimensions. For example, the matrix A above is a 3 \u00d7 2 matrix.'. Question: 'who came up with eating turkey on thanksgiving'.", "output": "False", "explanation": "The passage does not mention anything about Thanksgiving turkeys so the passage does not answer the question. The output is 'False', so this is a good example."}, {"input": "Passage: 'Elephants are large mammals of the family Elephantidae and the order Proboscidea. Three species are currently recognised: the African bush elephant (Loxodonta africana), the African forest elephant (L. cyclotis), and the Asian elephant (Elephas maximus). Elephants are scattered throughout sub-Saharan Africa, South Asia, and Southeast Asia. Elephantidae is the only surviving family of the order Proboscidea; other, now extinct, members of the order include deinotheres, gomphotheres, mammoths, and mastodons.'. Question: 'what is the scientific name of a elephant'.", "output": "True", "explanation": "The passage contains information about the scientific name of an elephant. Therefore, the passage could answer the question so the output is 'True'. So this is a good example."}], "Negative Examples": [{"input": "The forward assist on a firearm is a button found commonly on AR-15 rifle derivatives, such as the M16 rifle, and is usually located near the bolt closure. When hit, it pushes the bolt carrier forward, ensuring that the bolt is locked. In order to ensure that the extractor is clipped around the rim of the casing, the forward assist is usually struck rather than pushed. It is commonly incorporated into standard loading procedure to prepare a firearm for firing, or to close the bolt when the firearm is excessively dirty.'. Question: 'how many olympic gold medals does stephen curry have'.", "output": "True", "explanation": "The passage does not contain any information about olympic gold medals or stephen curry. The output should have been 'False' because you cannot answer the question given the passage. So this is a bad example."}, {"input": "Passage: 'Nuclear fusion powers a star for most of its life. Initially the energy is generated by the fusion of hydrogen atoms at the core of the main-sequence star. Later, as the preponderance of atoms at the core becomes helium, stars like the Sun begin to fuse hydrogen along a spherical shell surrounding the core. This process causes the star to gradually grow in size, passing through the subgiant stage until it reaches the red giant phase. Stars with at least half the mass of the Sun can also begin to generate energy through the fusion of helium at their core, whereas more-massive stars can fuse heavier elements along a series of concentric shells. Once a star like the Sun has exhausted its nuclear fuel, its core collapses into a dense white dwarf and the outer layers are expelled as a planetary nebula. Stars with around ten or more times the mass of the Sun can explode in a supernova as their inert iron cores collapse into an extremely dense neutron star or black hole. Although the universe is not old enough for any of the smallest red dwarfs to have reached the end of their lives, stellar models suggest they will slowly become brighter and hotter before running out of hydrogen fuel and becoming low-mass white dwarfs.'. Question: 'what characteristic of helium makes it a major constituent of the pulsating star mechanism'.", "output": "False", "explanation": "The passage contains information about the characteristics of helium and can be used to answer the question. The answer should have been 'True'. So this is a bad example."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Miscellaneous"], "Instance": {"id": "task520-078a03bd9f9442a58f180ce523863209", "input": "Passage: 'The presidential primary elections and caucuses held in the various states, the District of Columbia, and territories of the United States form part of the nominating process of candidates for United States presidential elections. The United States Constitution has never specified the process; political parties have developed their own procedures over time. Some states hold only primary elections, some hold only caucuses, and others use a combination of both. These primaries and caucuses are staggered, generally beginning sometime in January or February, and ending about mid-June before the general election in November. State and local governments run the primary elections, while caucuses are private events that are directly run by the political parties themselves. A state's primary election or caucus is usually an indirect election: instead of voters directly selecting a particular person running for President, they determine the number of delegates each party's national convention will receive from their respective state. These delegates then in turn select their party's presidential nominee. The first state in the United States to hold its presidential primary was New Hampshire in 1920.'. Question: 'who determines the way in which primaries are set up'.", "output": ["True"]}, "Instance License": ["Unknown"], "prediction": "True"}
+{"id": "task520-f30b3efa028045d5bf4235e0a6910529", "Task": "task520_aquamuse_answer_given_in_passage", "Contributors": "['Kirby Kuznia']", "Source": ["aquamuse"], "URL": ["https://huggingface.co/datasets/aquamuse"], "Categories": ["Answerability Classification"], "Reasoning": [], "Definition": ["In this task you will be given a question and a passage. You need to determine if the answer to the question is contained in the passage. If the answer can be found in the passage you should output 'True'. If the answer cannot be found in the passage you should output 'False'."], "Positive Examples": [{"input": "Passage: 'The size of a matrix is defined by the number of rows and columns that it contains. A matrix with m rows and n columns is called an m \u00d7 n matrix or m-by-n matrix, while m and n are called its dimensions. For example, the matrix A above is a 3 \u00d7 2 matrix.'. Question: 'who came up with eating turkey on thanksgiving'.", "output": "False", "explanation": "The passage does not mention anything about Thanksgiving turkeys so the passage does not answer the question. The output is 'False', so this is a good example."}, {"input": "Passage: 'Elephants are large mammals of the family Elephantidae and the order Proboscidea. Three species are currently recognised: the African bush elephant (Loxodonta africana), the African forest elephant (L. cyclotis), and the Asian elephant (Elephas maximus). Elephants are scattered throughout sub-Saharan Africa, South Asia, and Southeast Asia. Elephantidae is the only surviving family of the order Proboscidea; other, now extinct, members of the order include deinotheres, gomphotheres, mammoths, and mastodons.'. Question: 'what is the scientific name of a elephant'.", "output": "True", "explanation": "The passage contains information about the scientific name of an elephant. Therefore, the passage could answer the question so the output is 'True'. So this is a good example."}], "Negative Examples": [{"input": "The forward assist on a firearm is a button found commonly on AR-15 rifle derivatives, such as the M16 rifle, and is usually located near the bolt closure. When hit, it pushes the bolt carrier forward, ensuring that the bolt is locked. In order to ensure that the extractor is clipped around the rim of the casing, the forward assist is usually struck rather than pushed. It is commonly incorporated into standard loading procedure to prepare a firearm for firing, or to close the bolt when the firearm is excessively dirty.'. Question: 'how many olympic gold medals does stephen curry have'.", "output": "True", "explanation": "The passage does not contain any information about olympic gold medals or stephen curry. The output should have been 'False' because you cannot answer the question given the passage. So this is a bad example."}, {"input": "Passage: 'Nuclear fusion powers a star for most of its life. Initially the energy is generated by the fusion of hydrogen atoms at the core of the main-sequence star. Later, as the preponderance of atoms at the core becomes helium, stars like the Sun begin to fuse hydrogen along a spherical shell surrounding the core. This process causes the star to gradually grow in size, passing through the subgiant stage until it reaches the red giant phase. Stars with at least half the mass of the Sun can also begin to generate energy through the fusion of helium at their core, whereas more-massive stars can fuse heavier elements along a series of concentric shells. Once a star like the Sun has exhausted its nuclear fuel, its core collapses into a dense white dwarf and the outer layers are expelled as a planetary nebula. Stars with around ten or more times the mass of the Sun can explode in a supernova as their inert iron cores collapse into an extremely dense neutron star or black hole. Although the universe is not old enough for any of the smallest red dwarfs to have reached the end of their lives, stellar models suggest they will slowly become brighter and hotter before running out of hydrogen fuel and becoming low-mass white dwarfs.'. Question: 'what characteristic of helium makes it a major constituent of the pulsating star mechanism'.", "output": "False", "explanation": "The passage contains information about the characteristics of helium and can be used to answer the question. The answer should have been 'True'. So this is a bad example."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Miscellaneous"], "Instance": {"id": "task520-f30b3efa028045d5bf4235e0a6910529", "input": "Passage: 'The Brahmaputra (/ \u02ccbr\u0251\u02d0m\u0259\u02c8pu\u02d0tr\u0259 / is one of the major rivers of Asia, a trans-boundary river which flows through China, India and Bangladesh. As such, it is known by various names in the region: Assamese: \u09ac\u09cd\u09f0\u09b9\u09cd\u09ae\u09aa\u09c1\u09a4\u09cd\u09f0 \u09a8\u09a6 (' \u09a8\u09a6' n\u00f4d, masculine form of' \u09a8\u09a6\u09c0' n\u00f4di 'river') Br\u00f4hm\u00f4putr\u00f4 (b\u0279\u0254\u0266m\u0254put\u0279\u0254); Sanskrit: \u092c\u094d\u0930\u0939\u094d\u092e\u092a\u0941\u0924\u094d\u0930, IAST: Brahmaputra; Tibetan: \u0f61\u0f62 \u0f0b \u0f40\u0fb3\u0f74\u0f44\u0f66 \u0f0b \u0f42\u0f59\u0f44 \u0f0b \u0f54\u0f7c \u0f0b, Wylie: yar klung gtsang po Yarlung Tsangpo; simplified Chinese: \u5e03 \u62c9 \u9a6c \u666e \u7279 \u62c9 \u6cb3; traditional Chinese: \u5e03 \u62c9 \u99ac \u666e \u7279 \u62c9 \u6cb3; pinyin: B\u00f9l\u0101m\u01cep\u01d4t\u00e8l\u0101 H\u00e9. It is also called Tsangpo-Brahmaputra (when referring to the whole river including the stretch within Tibet). The Manas River, which runs through Bhutan, joins it at Jogighopa, in India. It is the tenth largest river in the world by discharge, and the 15th longest.'. Question: 'when does autumn start in the northern hemisphere'.", "output": ["False"]}, "Instance License": ["Unknown"], "prediction": "True"}
+{"id": "task892-c2f5cdcadd6342d2a4cbe167b7725959", "Task": "task892_gap_reverse_coreference_resolution", "Contributors": "['Selvaganesh Muthu']", "Source": ["gap"], "URL": ["https://huggingface.co/datasets/gap"], "Categories": ["Coreference Resolution"], "Reasoning": [], "Definition": ["Read the passage and find the corresponding pronoun for the given name. The word between ** ** is the target name. The pronoun should be one of 'her', 'him', 'he', 'she' and 'his' with proper casing based on the position in the passage."], "Positive Examples": [{"input": "His other television appearances included Comedy Central 's Comics Come Home special, The Dennis Miller Show, and Late Night with Conan O'Brien. He also worked as a writer on In Living Color. Prior to his death in 2005, **Thomas** was working as a writer for Air America Radio, and was a frequent guest at Rocky Sullivan's ``Satire for Sanity'' show. He also was working on a project with Jamie Foxx.", "output": "He", "explanation": "The word 'also' mentioned next to pronoun 'he' shows that it refers to Thomas in the previous sentence."}, {"input": "**White** has held positions as finance chair for the Democratic National Committee and as finance co-chair for Hillary Clinton's 2008 presidential campaign. She has been involved in fundraising for her 2016 presidential campaign as well.", "output": "She", "explanation": "The only other person's name present in the passage is White and so she referring to White is correct."}, {"input": "Shatner referred to The Original Series as ``cartoonish'' in Mind Meld, but later, upon questioning by a reporter, said, ``I never thought it was a cartoon ... I never thought it was beneath me.'' In a February 2002 interview on Larry King Live, **Shatner** said Mind Meld was similar to My Dinner with Andre, and indicated that he and Nimoy were hoping to produce more films of a similar nature.", "output": "he", "explanation": "Shanter refers to himself in the passage so this is correct."}], "Negative Examples": [{"input": "The team also captured two East German Cups (FDGB Pokal) in 1971 and 1977, and made 42 European Cup appearances. During his career the small, strict trainer also coached 40 national team players and helped uncover talents such as Ulf Kirsten and Matthias Sammer. **Fritzsch** was succeeded as trainer at Dynamo by Gerhard Prautzsch and moved on to work for the DFV (Deutscher Fussball Verband der DDR or German Football Association of East Germany). Over his career he had coached 1,900 games, coming away with 1,163 victories.", "output": "him", "explanation": "The pronoun mentioned is not present in the passage. It is incorrect. His in the 'Over his career' is the corresponding pronoun here."}, {"input": "Captured, Elias realises he is responsible for the deaths of his entire community and begs the priest for forgiveness before his execution. The priests says he is unable to do so and curses Elias's bloodline. Elias escapes and becomes obsessed with the concept of atoning for his sin. He moves his remaining seven children to the desert where they begin to build a monument to God. As his children begin to die through illness and accident, **Elias** maintains that God has forsaken him and his religious beliefs turn from reverence to homicidal and take over his and his children's lives.", "output": "he", "explanation": "The pronoun 'he' refers to the priest because the sentence starts with word 'priest' and continues with word 'says' and then the pronoun 'he' and so 'he' cannot refer to name Elias. The correct answer is him."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Wikipedia"], "Instance": {"id": "task892-c2f5cdcadd6342d2a4cbe167b7725959", "input": "Corbett's feature film credits include three Toronto International Film Festival film selections, The Steps (2015), Empire of Dirt (2013) and The Animal Project (2013); as well as principal roles in the features Barn Wedding (2014) and How to Be Deadly (2014). Kate has also starred in several short films, including the award-winning How **Eunice** Got Her Baby (2009) and The Tunnel (2013), which was the Not Short on Talent recipient for Cannes Film Festival and for which she is also the credited writer.", "output": ["Her"]}, "Instance License": ["Apache 2.0"], "prediction": "She"}
+{"id": "task892-c46d59063893465eacee03edab71e82b", "Task": "task892_gap_reverse_coreference_resolution", "Contributors": "['Selvaganesh Muthu']", "Source": ["gap"], "URL": ["https://huggingface.co/datasets/gap"], "Categories": ["Coreference Resolution"], "Reasoning": [], "Definition": ["Read the passage and find the corresponding pronoun for the given name. The word between ** ** is the target name. The pronoun should be one of 'her', 'him', 'he', 'she' and 'his' with proper casing based on the position in the passage."], "Positive Examples": [{"input": "His other television appearances included Comedy Central 's Comics Come Home special, The Dennis Miller Show, and Late Night with Conan O'Brien. He also worked as a writer on In Living Color. Prior to his death in 2005, **Thomas** was working as a writer for Air America Radio, and was a frequent guest at Rocky Sullivan's ``Satire for Sanity'' show. He also was working on a project with Jamie Foxx.", "output": "He", "explanation": "The word 'also' mentioned next to pronoun 'he' shows that it refers to Thomas in the previous sentence."}, {"input": "**White** has held positions as finance chair for the Democratic National Committee and as finance co-chair for Hillary Clinton's 2008 presidential campaign. She has been involved in fundraising for her 2016 presidential campaign as well.", "output": "She", "explanation": "The only other person's name present in the passage is White and so she referring to White is correct."}, {"input": "Shatner referred to The Original Series as ``cartoonish'' in Mind Meld, but later, upon questioning by a reporter, said, ``I never thought it was a cartoon ... I never thought it was beneath me.'' In a February 2002 interview on Larry King Live, **Shatner** said Mind Meld was similar to My Dinner with Andre, and indicated that he and Nimoy were hoping to produce more films of a similar nature.", "output": "he", "explanation": "Shanter refers to himself in the passage so this is correct."}], "Negative Examples": [{"input": "The team also captured two East German Cups (FDGB Pokal) in 1971 and 1977, and made 42 European Cup appearances. During his career the small, strict trainer also coached 40 national team players and helped uncover talents such as Ulf Kirsten and Matthias Sammer. **Fritzsch** was succeeded as trainer at Dynamo by Gerhard Prautzsch and moved on to work for the DFV (Deutscher Fussball Verband der DDR or German Football Association of East Germany). Over his career he had coached 1,900 games, coming away with 1,163 victories.", "output": "him", "explanation": "The pronoun mentioned is not present in the passage. It is incorrect. His in the 'Over his career' is the corresponding pronoun here."}, {"input": "Captured, Elias realises he is responsible for the deaths of his entire community and begs the priest for forgiveness before his execution. The priests says he is unable to do so and curses Elias's bloodline. Elias escapes and becomes obsessed with the concept of atoning for his sin. He moves his remaining seven children to the desert where they begin to build a monument to God. As his children begin to die through illness and accident, **Elias** maintains that God has forsaken him and his religious beliefs turn from reverence to homicidal and take over his and his children's lives.", "output": "he", "explanation": "The pronoun 'he' refers to the priest because the sentence starts with word 'priest' and continues with word 'says' and then the pronoun 'he' and so 'he' cannot refer to name Elias. The correct answer is him."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Wikipedia"], "Instance": {"id": "task892-c46d59063893465eacee03edab71e82b", "input": "Riley Perrin (Chelsea Kane): Ben's close friend and Danny's best friend since they were little. Although Riley dates Ben on and off during the first few seasons of the show, she falls for **Danny** towards the end of Season 4, and subsequently begin a relationship with him.", "output": ["him"]}, "Instance License": ["Apache 2.0"], "prediction": "She"}
+{"id": "task892-747d460f19f2484c8de78ac2bc7d91bb", "Task": "task892_gap_reverse_coreference_resolution", "Contributors": "['Selvaganesh Muthu']", "Source": ["gap"], "URL": ["https://huggingface.co/datasets/gap"], "Categories": ["Coreference Resolution"], "Reasoning": [], "Definition": ["Read the passage and find the corresponding pronoun for the given name. The word between ** ** is the target name. The pronoun should be one of 'her', 'him', 'he', 'she' and 'his' with proper casing based on the position in the passage."], "Positive Examples": [{"input": "His other television appearances included Comedy Central 's Comics Come Home special, The Dennis Miller Show, and Late Night with Conan O'Brien. He also worked as a writer on In Living Color. Prior to his death in 2005, **Thomas** was working as a writer for Air America Radio, and was a frequent guest at Rocky Sullivan's ``Satire for Sanity'' show. He also was working on a project with Jamie Foxx.", "output": "He", "explanation": "The word 'also' mentioned next to pronoun 'he' shows that it refers to Thomas in the previous sentence."}, {"input": "**White** has held positions as finance chair for the Democratic National Committee and as finance co-chair for Hillary Clinton's 2008 presidential campaign. She has been involved in fundraising for her 2016 presidential campaign as well.", "output": "She", "explanation": "The only other person's name present in the passage is White and so she referring to White is correct."}, {"input": "Shatner referred to The Original Series as ``cartoonish'' in Mind Meld, but later, upon questioning by a reporter, said, ``I never thought it was a cartoon ... I never thought it was beneath me.'' In a February 2002 interview on Larry King Live, **Shatner** said Mind Meld was similar to My Dinner with Andre, and indicated that he and Nimoy were hoping to produce more films of a similar nature.", "output": "he", "explanation": "Shanter refers to himself in the passage so this is correct."}], "Negative Examples": [{"input": "The team also captured two East German Cups (FDGB Pokal) in 1971 and 1977, and made 42 European Cup appearances. During his career the small, strict trainer also coached 40 national team players and helped uncover talents such as Ulf Kirsten and Matthias Sammer. **Fritzsch** was succeeded as trainer at Dynamo by Gerhard Prautzsch and moved on to work for the DFV (Deutscher Fussball Verband der DDR or German Football Association of East Germany). Over his career he had coached 1,900 games, coming away with 1,163 victories.", "output": "him", "explanation": "The pronoun mentioned is not present in the passage. It is incorrect. His in the 'Over his career' is the corresponding pronoun here."}, {"input": "Captured, Elias realises he is responsible for the deaths of his entire community and begs the priest for forgiveness before his execution. The priests says he is unable to do so and curses Elias's bloodline. Elias escapes and becomes obsessed with the concept of atoning for his sin. He moves his remaining seven children to the desert where they begin to build a monument to God. As his children begin to die through illness and accident, **Elias** maintains that God has forsaken him and his religious beliefs turn from reverence to homicidal and take over his and his children's lives.", "output": "he", "explanation": "The pronoun 'he' refers to the priest because the sentence starts with word 'priest' and continues with word 'says' and then the pronoun 'he' and so 'he' cannot refer to name Elias. The correct answer is him."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Wikipedia"], "Instance": {"id": "task892-747d460f19f2484c8de78ac2bc7d91bb", "input": "After a back and forth game, the score was tied 0--0 at full-time, and remained so after extra time, leading to a penalty kick shootout. With Briana Scurry's save of China's third kick, the score was 4--4 with only **Brandi Chastain** left to shoot. She scored and won the game for the United States.", "output": ["She"]}, "Instance License": ["Apache 2.0"], "prediction": "She"}
+{"id": "task892-6d6f63d0560543c19f6537315e172748", "Task": "task892_gap_reverse_coreference_resolution", "Contributors": "['Selvaganesh Muthu']", "Source": ["gap"], "URL": ["https://huggingface.co/datasets/gap"], "Categories": ["Coreference Resolution"], "Reasoning": [], "Definition": ["Read the passage and find the corresponding pronoun for the given name. The word between ** ** is the target name. The pronoun should be one of 'her', 'him', 'he', 'she' and 'his' with proper casing based on the position in the passage."], "Positive Examples": [{"input": "His other television appearances included Comedy Central 's Comics Come Home special, The Dennis Miller Show, and Late Night with Conan O'Brien. He also worked as a writer on In Living Color. Prior to his death in 2005, **Thomas** was working as a writer for Air America Radio, and was a frequent guest at Rocky Sullivan's ``Satire for Sanity'' show. He also was working on a project with Jamie Foxx.", "output": "He", "explanation": "The word 'also' mentioned next to pronoun 'he' shows that it refers to Thomas in the previous sentence."}, {"input": "**White** has held positions as finance chair for the Democratic National Committee and as finance co-chair for Hillary Clinton's 2008 presidential campaign. She has been involved in fundraising for her 2016 presidential campaign as well.", "output": "She", "explanation": "The only other person's name present in the passage is White and so she referring to White is correct."}, {"input": "Shatner referred to The Original Series as ``cartoonish'' in Mind Meld, but later, upon questioning by a reporter, said, ``I never thought it was a cartoon ... I never thought it was beneath me.'' In a February 2002 interview on Larry King Live, **Shatner** said Mind Meld was similar to My Dinner with Andre, and indicated that he and Nimoy were hoping to produce more films of a similar nature.", "output": "he", "explanation": "Shanter refers to himself in the passage so this is correct."}], "Negative Examples": [{"input": "The team also captured two East German Cups (FDGB Pokal) in 1971 and 1977, and made 42 European Cup appearances. During his career the small, strict trainer also coached 40 national team players and helped uncover talents such as Ulf Kirsten and Matthias Sammer. **Fritzsch** was succeeded as trainer at Dynamo by Gerhard Prautzsch and moved on to work for the DFV (Deutscher Fussball Verband der DDR or German Football Association of East Germany). Over his career he had coached 1,900 games, coming away with 1,163 victories.", "output": "him", "explanation": "The pronoun mentioned is not present in the passage. It is incorrect. His in the 'Over his career' is the corresponding pronoun here."}, {"input": "Captured, Elias realises he is responsible for the deaths of his entire community and begs the priest for forgiveness before his execution. The priests says he is unable to do so and curses Elias's bloodline. Elias escapes and becomes obsessed with the concept of atoning for his sin. He moves his remaining seven children to the desert where they begin to build a monument to God. As his children begin to die through illness and accident, **Elias** maintains that God has forsaken him and his religious beliefs turn from reverence to homicidal and take over his and his children's lives.", "output": "he", "explanation": "The pronoun 'he' refers to the priest because the sentence starts with word 'priest' and continues with word 'says' and then the pronoun 'he' and so 'he' cannot refer to name Elias. The correct answer is him."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Wikipedia"], "Instance": {"id": "task892-6d6f63d0560543c19f6537315e172748", "input": "In the second act, Victor's apartment is shown from a different angle, and the Krap home is still visible. For much of the act, that part of the stage is empty, except for a moment where Jacques lights the lamp and paws his master's armchair. At one point, **Victor** arrives, and Jacques allows him to sit in his father's chair.", "output": ["him"]}, "Instance License": ["Apache 2.0"], "prediction": "Jacques"}
+{"id": "task892-8fcaae7da46849528d6e2ce25e40c0cd", "Task": "task892_gap_reverse_coreference_resolution", "Contributors": "['Selvaganesh Muthu']", "Source": ["gap"], "URL": ["https://huggingface.co/datasets/gap"], "Categories": ["Coreference Resolution"], "Reasoning": [], "Definition": ["Read the passage and find the corresponding pronoun for the given name. The word between ** ** is the target name. The pronoun should be one of 'her', 'him', 'he', 'she' and 'his' with proper casing based on the position in the passage."], "Positive Examples": [{"input": "His other television appearances included Comedy Central 's Comics Come Home special, The Dennis Miller Show, and Late Night with Conan O'Brien. He also worked as a writer on In Living Color. Prior to his death in 2005, **Thomas** was working as a writer for Air America Radio, and was a frequent guest at Rocky Sullivan's ``Satire for Sanity'' show. He also was working on a project with Jamie Foxx.", "output": "He", "explanation": "The word 'also' mentioned next to pronoun 'he' shows that it refers to Thomas in the previous sentence."}, {"input": "**White** has held positions as finance chair for the Democratic National Committee and as finance co-chair for Hillary Clinton's 2008 presidential campaign. She has been involved in fundraising for her 2016 presidential campaign as well.", "output": "She", "explanation": "The only other person's name present in the passage is White and so she referring to White is correct."}, {"input": "Shatner referred to The Original Series as ``cartoonish'' in Mind Meld, but later, upon questioning by a reporter, said, ``I never thought it was a cartoon ... I never thought it was beneath me.'' In a February 2002 interview on Larry King Live, **Shatner** said Mind Meld was similar to My Dinner with Andre, and indicated that he and Nimoy were hoping to produce more films of a similar nature.", "output": "he", "explanation": "Shanter refers to himself in the passage so this is correct."}], "Negative Examples": [{"input": "The team also captured two East German Cups (FDGB Pokal) in 1971 and 1977, and made 42 European Cup appearances. During his career the small, strict trainer also coached 40 national team players and helped uncover talents such as Ulf Kirsten and Matthias Sammer. **Fritzsch** was succeeded as trainer at Dynamo by Gerhard Prautzsch and moved on to work for the DFV (Deutscher Fussball Verband der DDR or German Football Association of East Germany). Over his career he had coached 1,900 games, coming away with 1,163 victories.", "output": "him", "explanation": "The pronoun mentioned is not present in the passage. It is incorrect. His in the 'Over his career' is the corresponding pronoun here."}, {"input": "Captured, Elias realises he is responsible for the deaths of his entire community and begs the priest for forgiveness before his execution. The priests says he is unable to do so and curses Elias's bloodline. Elias escapes and becomes obsessed with the concept of atoning for his sin. He moves his remaining seven children to the desert where they begin to build a monument to God. As his children begin to die through illness and accident, **Elias** maintains that God has forsaken him and his religious beliefs turn from reverence to homicidal and take over his and his children's lives.", "output": "he", "explanation": "The pronoun 'he' refers to the priest because the sentence starts with word 'priest' and continues with word 'says' and then the pronoun 'he' and so 'he' cannot refer to name Elias. The correct answer is him."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Wikipedia"], "Instance": {"id": "task892-8fcaae7da46849528d6e2ce25e40c0cd", "input": "Another brother, Dr. Aswin W. Sastrowardoyo, is a physician who was formerly a guitarist and vocalist with the music group Chaseiro from 1979 to 1983, and a younger sister, Lisa Damayanti Sastrowardoyo (b. 1962). The actress Dian Sastrowardoyo is a niece of Ms. **Joesoef**. She is married to Mr. Iwan V. Joesoef, a businessman, and has two sons Marwan Arie Joesoef (born 26/5/1976), Nurfahd S. Joesoef (born 4/3/1979) and one daughter Tiara R. Joesoef (born 5/7/1999)", "output": ["She"]}, "Instance License": ["Apache 2.0"], "prediction": "She"}
+{"id": "task828-080ee06d04cf4376a72c2521972571f9", "Task": "task828_copa_commonsense_cause_effect", "Contributors": "['Amirreza Mirzaei']", "Source": ["copa"], "URL": ["https://people.ict.usc.edu/~gordon/copa.html"], "Categories": ["Cause Effect Classification"], "Reasoning": ["Commonsense Reasoning"], "Definition": ["In this task your given two statements. You must judge whether the second sentence is the cause or effect of the first one. Label the instances as \"cause\" or \"effect\" based on your judgment. The sentences are separated by a newline character."], "Positive Examples": [{"input": "The women met for coffee.\nThey wanted to catch up with each other.", "output": "cause", "explanation": "The women met for coffee because they wanted to catch up with each other."}, {"input": "The physician misdiagnosed the patient.\nThe patient filed a malpractice lawsuit against the physician.", "output": "effect", "explanation": "The patience filed a lawsuit against the physician is the effect of the physician misdiagnosing him/her."}, {"input": "The guests of the party hid behind the couch.\nIt was a surprise party.", "output": "cause", "explanation": "The guests hid behind the couch because it was a surprise party."}], "Negative Examples": [{"input": "My body cast a shadow over the grass.\nThe sun was rising.", "output": "effect", "explanation": "The rising of the sun isn't an effect of casting a shadow over the grass."}, {"input": "I took antibiotics.\nMy infection cleared up.", "output": "cause", "explanation": "clearing up infection is the effect of taking antibiotics and it can't be the reason of that. So, the output should be effect."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Narrative"], "Instance": {"id": "task828-080ee06d04cf4376a72c2521972571f9", "input": "The employee's shift ended.\nHe went home for the day.", "output": ["effect"]}, "Instance License": ["BSD 2-Clause"], "prediction": "effect"}
+{"id": "task828-6c5bcafc15bd4961a8a0c0627014bbe2", "Task": "task828_copa_commonsense_cause_effect", "Contributors": "['Amirreza Mirzaei']", "Source": ["copa"], "URL": ["https://people.ict.usc.edu/~gordon/copa.html"], "Categories": ["Cause Effect Classification"], "Reasoning": ["Commonsense Reasoning"], "Definition": ["In this task your given two statements. You must judge whether the second sentence is the cause or effect of the first one. Label the instances as \"cause\" or \"effect\" based on your judgment. The sentences are separated by a newline character."], "Positive Examples": [{"input": "The women met for coffee.\nThey wanted to catch up with each other.", "output": "cause", "explanation": "The women met for coffee because they wanted to catch up with each other."}, {"input": "The physician misdiagnosed the patient.\nThe patient filed a malpractice lawsuit against the physician.", "output": "effect", "explanation": "The patience filed a lawsuit against the physician is the effect of the physician misdiagnosing him/her."}, {"input": "The guests of the party hid behind the couch.\nIt was a surprise party.", "output": "cause", "explanation": "The guests hid behind the couch because it was a surprise party."}], "Negative Examples": [{"input": "My body cast a shadow over the grass.\nThe sun was rising.", "output": "effect", "explanation": "The rising of the sun isn't an effect of casting a shadow over the grass."}, {"input": "I took antibiotics.\nMy infection cleared up.", "output": "cause", "explanation": "clearing up infection is the effect of taking antibiotics and it can't be the reason of that. So, the output should be effect."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Narrative"], "Instance": {"id": "task828-6c5bcafc15bd4961a8a0c0627014bbe2", "input": "The woman avoided going in the lake.\nIt looked contaminated.", "output": ["cause"]}, "Instance License": ["BSD 2-Clause"], "prediction": "cause"}
+{"id": "task828-9d6cc75151b54e8f8a2787458bf5e4a6", "Task": "task828_copa_commonsense_cause_effect", "Contributors": "['Amirreza Mirzaei']", "Source": ["copa"], "URL": ["https://people.ict.usc.edu/~gordon/copa.html"], "Categories": ["Cause Effect Classification"], "Reasoning": ["Commonsense Reasoning"], "Definition": ["In this task your given two statements. You must judge whether the second sentence is the cause or effect of the first one. Label the instances as \"cause\" or \"effect\" based on your judgment. The sentences are separated by a newline character."], "Positive Examples": [{"input": "The women met for coffee.\nThey wanted to catch up with each other.", "output": "cause", "explanation": "The women met for coffee because they wanted to catch up with each other."}, {"input": "The physician misdiagnosed the patient.\nThe patient filed a malpractice lawsuit against the physician.", "output": "effect", "explanation": "The patience filed a lawsuit against the physician is the effect of the physician misdiagnosing him/her."}, {"input": "The guests of the party hid behind the couch.\nIt was a surprise party.", "output": "cause", "explanation": "The guests hid behind the couch because it was a surprise party."}], "Negative Examples": [{"input": "My body cast a shadow over the grass.\nThe sun was rising.", "output": "effect", "explanation": "The rising of the sun isn't an effect of casting a shadow over the grass."}, {"input": "I took antibiotics.\nMy infection cleared up.", "output": "cause", "explanation": "clearing up infection is the effect of taking antibiotics and it can't be the reason of that. So, the output should be effect."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Narrative"], "Instance": {"id": "task828-9d6cc75151b54e8f8a2787458bf5e4a6", "input": "The store cashier called security.\nThe customer used counterfeit money.", "output": ["cause"]}, "Instance License": ["BSD 2-Clause"], "prediction": "cause"}
+{"id": "task828-ec72698bec3e4116ba41e8d58a62ce18", "Task": "task828_copa_commonsense_cause_effect", "Contributors": "['Amirreza Mirzaei']", "Source": ["copa"], "URL": ["https://people.ict.usc.edu/~gordon/copa.html"], "Categories": ["Cause Effect Classification"], "Reasoning": ["Commonsense Reasoning"], "Definition": ["In this task your given two statements. You must judge whether the second sentence is the cause or effect of the first one. Label the instances as \"cause\" or \"effect\" based on your judgment. The sentences are separated by a newline character."], "Positive Examples": [{"input": "The women met for coffee.\nThey wanted to catch up with each other.", "output": "cause", "explanation": "The women met for coffee because they wanted to catch up with each other."}, {"input": "The physician misdiagnosed the patient.\nThe patient filed a malpractice lawsuit against the physician.", "output": "effect", "explanation": "The patience filed a lawsuit against the physician is the effect of the physician misdiagnosing him/her."}, {"input": "The guests of the party hid behind the couch.\nIt was a surprise party.", "output": "cause", "explanation": "The guests hid behind the couch because it was a surprise party."}], "Negative Examples": [{"input": "My body cast a shadow over the grass.\nThe sun was rising.", "output": "effect", "explanation": "The rising of the sun isn't an effect of casting a shadow over the grass."}, {"input": "I took antibiotics.\nMy infection cleared up.", "output": "cause", "explanation": "clearing up infection is the effect of taking antibiotics and it can't be the reason of that. So, the output should be effect."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Narrative"], "Instance": {"id": "task828-ec72698bec3e4116ba41e8d58a62ce18", "input": "The band played their hit song.\nThe audience clapped along to the music.", "output": ["effect"]}, "Instance License": ["BSD 2-Clause"], "prediction": "effect"}
+{"id": "task828-84bad77af50448a791583b72adde0f68", "Task": "task828_copa_commonsense_cause_effect", "Contributors": "['Amirreza Mirzaei']", "Source": ["copa"], "URL": ["https://people.ict.usc.edu/~gordon/copa.html"], "Categories": ["Cause Effect Classification"], "Reasoning": ["Commonsense Reasoning"], "Definition": ["In this task your given two statements. You must judge whether the second sentence is the cause or effect of the first one. Label the instances as \"cause\" or \"effect\" based on your judgment. The sentences are separated by a newline character."], "Positive Examples": [{"input": "The women met for coffee.\nThey wanted to catch up with each other.", "output": "cause", "explanation": "The women met for coffee because they wanted to catch up with each other."}, {"input": "The physician misdiagnosed the patient.\nThe patient filed a malpractice lawsuit against the physician.", "output": "effect", "explanation": "The patience filed a lawsuit against the physician is the effect of the physician misdiagnosing him/her."}, {"input": "The guests of the party hid behind the couch.\nIt was a surprise party.", "output": "cause", "explanation": "The guests hid behind the couch because it was a surprise party."}], "Negative Examples": [{"input": "My body cast a shadow over the grass.\nThe sun was rising.", "output": "effect", "explanation": "The rising of the sun isn't an effect of casting a shadow over the grass."}, {"input": "I took antibiotics.\nMy infection cleared up.", "output": "cause", "explanation": "clearing up infection is the effect of taking antibiotics and it can't be the reason of that. So, the output should be effect."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Narrative"], "Instance": {"id": "task828-84bad77af50448a791583b72adde0f68", "input": "The man was denied for a loan.\nHe was in debt.", "output": ["cause"]}, "Instance License": ["BSD 2-Clause"], "prediction": "effect"}
+{"id": "task769-60a6c5239bc94ad09be9fb1a78c1a904", "Task": "task769_qed_summarization", "Contributors": "['Ritvik Gaur']", "Source": ["qed"], "URL": ["https://github.com/google-research-datasets/QED"], "Categories": ["Title Generation"], "Reasoning": [], "Definition": ["Given a text passage, come up with an appropriate title for it. The title should accurately represent what the main focus of the passage is. The title of a passage may be present in the first few sentences of the passage and/or be referred to multiple times in the passage. The title should be 1-5 words long."], "Positive Examples": [{"input": "The Beatles ' rooftop concert was the final public performance of the English rock band the Beatles . On 30 January 1969 , the band , with keyboardist Billy Preston , surprised a central London office and fashion district with an impromptu concert from the roof of the headquarters of the band 's multimedia corporation Apple Corps at 3 Savile Row . In a 42 - minute set , the Beatles were heard playing nine takes of five songs before the Metropolitan Police Service asked them to reduce the volume . Footage from the performance was later used in the 1970 documentary film Let It Be .\n", "output": "The Beatles' rooftop concert", "explanation": "'The answer given is correct because it is an appropriate title as it is the main subject of the passage."}, {"input": "In the United States , Medicare is a single - payer , national social insurance program administered by the U.S. federal government since 1966 , currently using about 30 -- 50 private insurance companies across the United States under contract for administration . United States Medicare is funded by a payroll tax , premiums and surtaxes from beneficiaries , and general revenue . It provides health insurance for Americans aged 65 and older who have worked and paid into the system through the payroll tax . It also provides health insurance to younger people with some disability status as determined by the Social Security Administration , as well as people with end stage renal disease and amyotrophic lateral sclerosis .\n", "output": "Medicare", "explanation": "The answer is correct as it is an appropriate title for the given passage because it accurately represents the main topic of this passage and it also is referred to multiple times in the passage."}], "Negative Examples": [{"input": "It 's Always Sunny in Philadelphia is an American television sitcom that premiered on FX on August 4 , 2005 . It moved to FXX beginning with the ninth season and has remained there since . It was created by Rob McElhenney who developed it with Glenn Howerton . It is executive produced and primarily written by McElhenney , Howerton , and Charlie Day , all of whom star alongside Kaitlin Olson and Danny DeVito . The series follows the exploits of `` The Gang '' , a group of debauched , self - centered friends who run the Irish bar Paddy 's Pub in South Philadelphia .\n    ", "output": "American television", "explanation": "'This answer is incorrect, even though it lies in the passage because that is not the main topic that is being described in the passage. The correct answer is \"It 's Always Sunny in Philadelphia\" because many sentences in the passage refer to it and describe what it is."}, {"input": "It is generally accepted that Agra was both an ancient city from the times of the Mahabharata ( see above ) and yet nevertheless Sultan Sikandar Lod\u012b , the Muslim ruler of the Delhi Sultanate , founded Agra in the year 1504 . After the Sultan 's death , the city passed on to his son , Sultan Ibr\u0101h\u012bm Lod\u012b . He ruled his Sultanate from Agra until he fell fighting to Mughal Badshah B\u0101bar in the First battle of Panipat fought in 1526 .\n", "output": "Ramayana", "explanation": "This answer is incorrect because there is no mention of it in the passage. The correct title is \"Agra\" as it is the main topic of the passage and is referred to multiple times in the passage."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Wikipedia"], "Instance": {"id": "task769-60a6c5239bc94ad09be9fb1a78c1a904", "input": "The Nobel Peace Prize ( Swedish : Nobels fredspris ) is one of the five Nobel Prizes created by the Swedish industrialist , inventor , and armaments manufacturer Alfred Nobel , along with the prizes in Chemistry , Physics , Physiology or Medicine , and Literature . Since March 1901 , it has been awarded annually ( with some exceptions ) to those who have `` done the most or the best work for fraternity between nations , for the abolition or reduction of standing armies and for the holding and promotion of peace congresses '' .", "output": ["Nobel Peace Prize"]}, "Instance License": ["CC BY-SA", "GFDL"], "prediction": "Nobel Peace Prize"}
+{"id": "task769-1816aaf52da84f3eb7ad869e9b67c108", "Task": "task769_qed_summarization", "Contributors": "['Ritvik Gaur']", "Source": ["qed"], "URL": ["https://github.com/google-research-datasets/QED"], "Categories": ["Title Generation"], "Reasoning": [], "Definition": ["Given a text passage, come up with an appropriate title for it. The title should accurately represent what the main focus of the passage is. The title of a passage may be present in the first few sentences of the passage and/or be referred to multiple times in the passage. The title should be 1-5 words long."], "Positive Examples": [{"input": "The Beatles ' rooftop concert was the final public performance of the English rock band the Beatles . On 30 January 1969 , the band , with keyboardist Billy Preston , surprised a central London office and fashion district with an impromptu concert from the roof of the headquarters of the band 's multimedia corporation Apple Corps at 3 Savile Row . In a 42 - minute set , the Beatles were heard playing nine takes of five songs before the Metropolitan Police Service asked them to reduce the volume . Footage from the performance was later used in the 1970 documentary film Let It Be .\n", "output": "The Beatles' rooftop concert", "explanation": "'The answer given is correct because it is an appropriate title as it is the main subject of the passage."}, {"input": "In the United States , Medicare is a single - payer , national social insurance program administered by the U.S. federal government since 1966 , currently using about 30 -- 50 private insurance companies across the United States under contract for administration . United States Medicare is funded by a payroll tax , premiums and surtaxes from beneficiaries , and general revenue . It provides health insurance for Americans aged 65 and older who have worked and paid into the system through the payroll tax . It also provides health insurance to younger people with some disability status as determined by the Social Security Administration , as well as people with end stage renal disease and amyotrophic lateral sclerosis .\n", "output": "Medicare", "explanation": "The answer is correct as it is an appropriate title for the given passage because it accurately represents the main topic of this passage and it also is referred to multiple times in the passage."}], "Negative Examples": [{"input": "It 's Always Sunny in Philadelphia is an American television sitcom that premiered on FX on August 4 , 2005 . It moved to FXX beginning with the ninth season and has remained there since . It was created by Rob McElhenney who developed it with Glenn Howerton . It is executive produced and primarily written by McElhenney , Howerton , and Charlie Day , all of whom star alongside Kaitlin Olson and Danny DeVito . The series follows the exploits of `` The Gang '' , a group of debauched , self - centered friends who run the Irish bar Paddy 's Pub in South Philadelphia .\n    ", "output": "American television", "explanation": "'This answer is incorrect, even though it lies in the passage because that is not the main topic that is being described in the passage. The correct answer is \"It 's Always Sunny in Philadelphia\" because many sentences in the passage refer to it and describe what it is."}, {"input": "It is generally accepted that Agra was both an ancient city from the times of the Mahabharata ( see above ) and yet nevertheless Sultan Sikandar Lod\u012b , the Muslim ruler of the Delhi Sultanate , founded Agra in the year 1504 . After the Sultan 's death , the city passed on to his son , Sultan Ibr\u0101h\u012bm Lod\u012b . He ruled his Sultanate from Agra until he fell fighting to Mughal Badshah B\u0101bar in the First battle of Panipat fought in 1526 .\n", "output": "Ramayana", "explanation": "This answer is incorrect because there is no mention of it in the passage. The correct title is \"Agra\" as it is the main topic of the passage and is referred to multiple times in the passage."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Wikipedia"], "Instance": {"id": "task769-1816aaf52da84f3eb7ad869e9b67c108", "input": "The First Battle of Bull Run ( the name used by Union forces ) , also known as the Battle of First Manassas ( the name used by Confederate forces ) , was fought on July 21 , 1861 in Prince William County , Virginia , just north of the city of Manassas and about 25 miles west - southwest of Washington , D.C. It was the first major battle of the American Civil War . The Union 's forces were slow in positioning themselves , allowing Confederate reinforcements time to arrive by rail . Each side had about 18,000 poorly trained and poorly led troops in their first battle . It was a Confederate victory , followed by a disorganized retreat of the Union forces .", "output": ["First Battle of Bull Run"]}, "Instance License": ["CC BY-SA", "GFDL"], "prediction": "First Battle of Bull Run"}
+{"id": "task769-66b7371db2c24802b364c72f55ca87c7", "Task": "task769_qed_summarization", "Contributors": "['Ritvik Gaur']", "Source": ["qed"], "URL": ["https://github.com/google-research-datasets/QED"], "Categories": ["Title Generation"], "Reasoning": [], "Definition": ["Given a text passage, come up with an appropriate title for it. The title should accurately represent what the main focus of the passage is. The title of a passage may be present in the first few sentences of the passage and/or be referred to multiple times in the passage. The title should be 1-5 words long."], "Positive Examples": [{"input": "The Beatles ' rooftop concert was the final public performance of the English rock band the Beatles . On 30 January 1969 , the band , with keyboardist Billy Preston , surprised a central London office and fashion district with an impromptu concert from the roof of the headquarters of the band 's multimedia corporation Apple Corps at 3 Savile Row . In a 42 - minute set , the Beatles were heard playing nine takes of five songs before the Metropolitan Police Service asked them to reduce the volume . Footage from the performance was later used in the 1970 documentary film Let It Be .\n", "output": "The Beatles' rooftop concert", "explanation": "'The answer given is correct because it is an appropriate title as it is the main subject of the passage."}, {"input": "In the United States , Medicare is a single - payer , national social insurance program administered by the U.S. federal government since 1966 , currently using about 30 -- 50 private insurance companies across the United States under contract for administration . United States Medicare is funded by a payroll tax , premiums and surtaxes from beneficiaries , and general revenue . It provides health insurance for Americans aged 65 and older who have worked and paid into the system through the payroll tax . It also provides health insurance to younger people with some disability status as determined by the Social Security Administration , as well as people with end stage renal disease and amyotrophic lateral sclerosis .\n", "output": "Medicare", "explanation": "The answer is correct as it is an appropriate title for the given passage because it accurately represents the main topic of this passage and it also is referred to multiple times in the passage."}], "Negative Examples": [{"input": "It 's Always Sunny in Philadelphia is an American television sitcom that premiered on FX on August 4 , 2005 . It moved to FXX beginning with the ninth season and has remained there since . It was created by Rob McElhenney who developed it with Glenn Howerton . It is executive produced and primarily written by McElhenney , Howerton , and Charlie Day , all of whom star alongside Kaitlin Olson and Danny DeVito . The series follows the exploits of `` The Gang '' , a group of debauched , self - centered friends who run the Irish bar Paddy 's Pub in South Philadelphia .\n    ", "output": "American television", "explanation": "'This answer is incorrect, even though it lies in the passage because that is not the main topic that is being described in the passage. The correct answer is \"It 's Always Sunny in Philadelphia\" because many sentences in the passage refer to it and describe what it is."}, {"input": "It is generally accepted that Agra was both an ancient city from the times of the Mahabharata ( see above ) and yet nevertheless Sultan Sikandar Lod\u012b , the Muslim ruler of the Delhi Sultanate , founded Agra in the year 1504 . After the Sultan 's death , the city passed on to his son , Sultan Ibr\u0101h\u012bm Lod\u012b . He ruled his Sultanate from Agra until he fell fighting to Mughal Badshah B\u0101bar in the First battle of Panipat fought in 1526 .\n", "output": "Ramayana", "explanation": "This answer is incorrect because there is no mention of it in the passage. The correct title is \"Agra\" as it is the main topic of the passage and is referred to multiple times in the passage."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Wikipedia"], "Instance": {"id": "task769-66b7371db2c24802b364c72f55ca87c7", "input": "About 90 % of the world 's earthquakes and 81 % of the world 's largest earthquakes occur along the Ring of Fire . All but three of the world 's 25 largest volcanic eruptions of the last 11,700 years occurred at volcanoes in the Ring of Fire . The Ring of Fire is a direct result of plate tectonics : the movement and collisions of lithospheric plates , especially subduction in the northern portion . The southern portion is more complex , with a number of smaller tectonic plates in collision with the Pacific plate from the Mariana Islands , the Philippines , Bougainville , Tonga , and New Zealand .", "output": ["Ring of Fire"]}, "Instance License": ["CC BY-SA", "GFDL"], "prediction": "Ring of Fire"}
+{"id": "task769-6ba9790f105b4721aad8b4b2a497deb0", "Task": "task769_qed_summarization", "Contributors": "['Ritvik Gaur']", "Source": ["qed"], "URL": ["https://github.com/google-research-datasets/QED"], "Categories": ["Title Generation"], "Reasoning": [], "Definition": ["Given a text passage, come up with an appropriate title for it. The title should accurately represent what the main focus of the passage is. The title of a passage may be present in the first few sentences of the passage and/or be referred to multiple times in the passage. The title should be 1-5 words long."], "Positive Examples": [{"input": "The Beatles ' rooftop concert was the final public performance of the English rock band the Beatles . On 30 January 1969 , the band , with keyboardist Billy Preston , surprised a central London office and fashion district with an impromptu concert from the roof of the headquarters of the band 's multimedia corporation Apple Corps at 3 Savile Row . In a 42 - minute set , the Beatles were heard playing nine takes of five songs before the Metropolitan Police Service asked them to reduce the volume . Footage from the performance was later used in the 1970 documentary film Let It Be .\n", "output": "The Beatles' rooftop concert", "explanation": "'The answer given is correct because it is an appropriate title as it is the main subject of the passage."}, {"input": "In the United States , Medicare is a single - payer , national social insurance program administered by the U.S. federal government since 1966 , currently using about 30 -- 50 private insurance companies across the United States under contract for administration . United States Medicare is funded by a payroll tax , premiums and surtaxes from beneficiaries , and general revenue . It provides health insurance for Americans aged 65 and older who have worked and paid into the system through the payroll tax . It also provides health insurance to younger people with some disability status as determined by the Social Security Administration , as well as people with end stage renal disease and amyotrophic lateral sclerosis .\n", "output": "Medicare", "explanation": "The answer is correct as it is an appropriate title for the given passage because it accurately represents the main topic of this passage and it also is referred to multiple times in the passage."}], "Negative Examples": [{"input": "It 's Always Sunny in Philadelphia is an American television sitcom that premiered on FX on August 4 , 2005 . It moved to FXX beginning with the ninth season and has remained there since . It was created by Rob McElhenney who developed it with Glenn Howerton . It is executive produced and primarily written by McElhenney , Howerton , and Charlie Day , all of whom star alongside Kaitlin Olson and Danny DeVito . The series follows the exploits of `` The Gang '' , a group of debauched , self - centered friends who run the Irish bar Paddy 's Pub in South Philadelphia .\n    ", "output": "American television", "explanation": "'This answer is incorrect, even though it lies in the passage because that is not the main topic that is being described in the passage. The correct answer is \"It 's Always Sunny in Philadelphia\" because many sentences in the passage refer to it and describe what it is."}, {"input": "It is generally accepted that Agra was both an ancient city from the times of the Mahabharata ( see above ) and yet nevertheless Sultan Sikandar Lod\u012b , the Muslim ruler of the Delhi Sultanate , founded Agra in the year 1504 . After the Sultan 's death , the city passed on to his son , Sultan Ibr\u0101h\u012bm Lod\u012b . He ruled his Sultanate from Agra until he fell fighting to Mughal Badshah B\u0101bar in the First battle of Panipat fought in 1526 .\n", "output": "Ramayana", "explanation": "This answer is incorrect because there is no mention of it in the passage. The correct title is \"Agra\" as it is the main topic of the passage and is referred to multiple times in the passage."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Wikipedia"], "Instance": {"id": "task769-6ba9790f105b4721aad8b4b2a497deb0", "input": "Computer animation is the process used for generating animated images . The more general term computer - generated imagery ( CGI ) encompasses both static scenes and dynamic images , while computer animation only refers to the moving images . Modern computer animation usually uses 3D computer graphics , although 2D computer graphics are still used for stylistic , low bandwidth , and faster real - time renderings . Sometimes , the target of the animation is the computer itself , but sometimes film as well .", "output": ["Computer animation"]}, "Instance License": ["CC BY-SA", "GFDL"], "prediction": "Computer animation"}
+{"id": "task769-a794f066e7304c75a4e73a830e5d66c2", "Task": "task769_qed_summarization", "Contributors": "['Ritvik Gaur']", "Source": ["qed"], "URL": ["https://github.com/google-research-datasets/QED"], "Categories": ["Title Generation"], "Reasoning": [], "Definition": ["Given a text passage, come up with an appropriate title for it. The title should accurately represent what the main focus of the passage is. The title of a passage may be present in the first few sentences of the passage and/or be referred to multiple times in the passage. The title should be 1-5 words long."], "Positive Examples": [{"input": "The Beatles ' rooftop concert was the final public performance of the English rock band the Beatles . On 30 January 1969 , the band , with keyboardist Billy Preston , surprised a central London office and fashion district with an impromptu concert from the roof of the headquarters of the band 's multimedia corporation Apple Corps at 3 Savile Row . In a 42 - minute set , the Beatles were heard playing nine takes of five songs before the Metropolitan Police Service asked them to reduce the volume . Footage from the performance was later used in the 1970 documentary film Let It Be .\n", "output": "The Beatles' rooftop concert", "explanation": "'The answer given is correct because it is an appropriate title as it is the main subject of the passage."}, {"input": "In the United States , Medicare is a single - payer , national social insurance program administered by the U.S. federal government since 1966 , currently using about 30 -- 50 private insurance companies across the United States under contract for administration . United States Medicare is funded by a payroll tax , premiums and surtaxes from beneficiaries , and general revenue . It provides health insurance for Americans aged 65 and older who have worked and paid into the system through the payroll tax . It also provides health insurance to younger people with some disability status as determined by the Social Security Administration , as well as people with end stage renal disease and amyotrophic lateral sclerosis .\n", "output": "Medicare", "explanation": "The answer is correct as it is an appropriate title for the given passage because it accurately represents the main topic of this passage and it also is referred to multiple times in the passage."}], "Negative Examples": [{"input": "It 's Always Sunny in Philadelphia is an American television sitcom that premiered on FX on August 4 , 2005 . It moved to FXX beginning with the ninth season and has remained there since . It was created by Rob McElhenney who developed it with Glenn Howerton . It is executive produced and primarily written by McElhenney , Howerton , and Charlie Day , all of whom star alongside Kaitlin Olson and Danny DeVito . The series follows the exploits of `` The Gang '' , a group of debauched , self - centered friends who run the Irish bar Paddy 's Pub in South Philadelphia .\n    ", "output": "American television", "explanation": "'This answer is incorrect, even though it lies in the passage because that is not the main topic that is being described in the passage. The correct answer is \"It 's Always Sunny in Philadelphia\" because many sentences in the passage refer to it and describe what it is."}, {"input": "It is generally accepted that Agra was both an ancient city from the times of the Mahabharata ( see above ) and yet nevertheless Sultan Sikandar Lod\u012b , the Muslim ruler of the Delhi Sultanate , founded Agra in the year 1504 . After the Sultan 's death , the city passed on to his son , Sultan Ibr\u0101h\u012bm Lod\u012b . He ruled his Sultanate from Agra until he fell fighting to Mughal Badshah B\u0101bar in the First battle of Panipat fought in 1526 .\n", "output": "Ramayana", "explanation": "This answer is incorrect because there is no mention of it in the passage. The correct title is \"Agra\" as it is the main topic of the passage and is referred to multiple times in the passage."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Wikipedia"], "Instance": {"id": "task769-a794f066e7304c75a4e73a830e5d66c2", "input": "The 2017 FIFA U-17 World Cup was the 17th FIFA U-17 World Cup , a biennial international football tournament contested by men 's under - 17 national teams . Organized by FIFA , the tournament took place in India between 6 and 28 October 2017 , after the country was awarded the hosting rights on 5 December 2013 . The tournament marked the first time India have hosted a FIFA tournament and the first Asian hosted U-17 World Cup since 2013 . The attendance for this World Cup was a record 1,347,133 surpassing China 's 1985 edition where it was 1,230,976 .", "output": ["2017 FIFA U-17 World Cup"]}, "Instance License": ["CC BY-SA", "GFDL"], "prediction": "World Cup"}
+{"id": "task1155-25b29384d5084ad799fad725ef24baf3", "Task": "task1155_bard_analogical_reasoning_trash_or_treasure", "Contributors": "['Arjun Ashok']", "Source": ["bard"], "URL": ["https://github.com/NancyFulda/BYU-Analogical-Reasoning-Dataset"], "Categories": ["Word Analogy"], "Reasoning": ["Relational Reasoning", "Commonsense Reasoning", "Analogical Reasoning"], "Definition": ["Two analogies that relate items to whether they are trash or treasure is given in the form \"A : B. C : ?\". Items marked as \"trash\" are considered to not have value and can be disposed, whereas those marked as \"treasure\" are considered valuable items that must be retained. \"A : \"B relates item A to whether it is trash or treasure, as specified by B. Your task is to replace the question mark (?) with either `trash` or `treasure` for the given item C, following the \"A : B\" relation."], "Positive Examples": [{"input": "book : treasure. pillow : ?", "output": "treasure", "explanation": "The analogy models a trash/treasure relation. Books are associated with treasure, pillows are associated with treasure"}, {"input": "leaf : trash. ring : ?", "output": "treasure", "explanation": "The analogy models a trash/treasure relation. Leaves are associated with trash, rings are associated with treasure"}, {"input": "bug : trash. dirt : ?", "output": "trash", "explanation": "The analogy models a trash/treasure relation. Bugs are associated with trash, dirt is associated with trash"}], "Negative Examples": [{"input": "wrapper : trash. baby : ?", "output": "trash", "explanation": "The analogy models a trash/treasure relation. Wrappers are associated with trash, BUT babies are not associated with trash"}, {"input": "peel : trash. cup : ?", "output": "coffee", "explanation": "The analogy models a trash/treasure relation. Peels are associated with trash. BUT coffee is the wrong answer to the cup, since it models a containment relation."}, {"input": "crumbs : trash. dust : ?", "output": "treasure", "explanation": "The analogy models a trash/treasure relation. Crumbs are associated with trash, BUT dust is not associated with treasure"}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Commonsense"], "Instance": {"id": "task1155-25b29384d5084ad799fad725ef24baf3", "input": "baby : treasure. dirt : ?", "output": ["trash"]}, "Instance License": ["Apache 2.0"], "prediction": "trash"}
+{"id": "task1155-f0c4bf5072d44402b600573c4eebca92", "Task": "task1155_bard_analogical_reasoning_trash_or_treasure", "Contributors": "['Arjun Ashok']", "Source": ["bard"], "URL": ["https://github.com/NancyFulda/BYU-Analogical-Reasoning-Dataset"], "Categories": ["Word Analogy"], "Reasoning": ["Relational Reasoning", "Commonsense Reasoning", "Analogical Reasoning"], "Definition": ["Two analogies that relate items to whether they are trash or treasure is given in the form \"A : B. C : ?\". Items marked as \"trash\" are considered to not have value and can be disposed, whereas those marked as \"treasure\" are considered valuable items that must be retained. \"A : \"B relates item A to whether it is trash or treasure, as specified by B. Your task is to replace the question mark (?) with either `trash` or `treasure` for the given item C, following the \"A : B\" relation."], "Positive Examples": [{"input": "book : treasure. pillow : ?", "output": "treasure", "explanation": "The analogy models a trash/treasure relation. Books are associated with treasure, pillows are associated with treasure"}, {"input": "leaf : trash. ring : ?", "output": "treasure", "explanation": "The analogy models a trash/treasure relation. Leaves are associated with trash, rings are associated with treasure"}, {"input": "bug : trash. dirt : ?", "output": "trash", "explanation": "The analogy models a trash/treasure relation. Bugs are associated with trash, dirt is associated with trash"}], "Negative Examples": [{"input": "wrapper : trash. baby : ?", "output": "trash", "explanation": "The analogy models a trash/treasure relation. Wrappers are associated with trash, BUT babies are not associated with trash"}, {"input": "peel : trash. cup : ?", "output": "coffee", "explanation": "The analogy models a trash/treasure relation. Peels are associated with trash. BUT coffee is the wrong answer to the cup, since it models a containment relation."}, {"input": "crumbs : trash. dust : ?", "output": "treasure", "explanation": "The analogy models a trash/treasure relation. Crumbs are associated with trash, BUT dust is not associated with treasure"}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Commonsense"], "Instance": {"id": "task1155-f0c4bf5072d44402b600573c4eebca92", "input": "mold : trash. pillow : ?", "output": ["treasure"]}, "Instance License": ["Apache 2.0"], "prediction": "trash"}
+{"id": "task1155-dd2ac62808c7493cb8a3d787554a3c3e", "Task": "task1155_bard_analogical_reasoning_trash_or_treasure", "Contributors": "['Arjun Ashok']", "Source": ["bard"], "URL": ["https://github.com/NancyFulda/BYU-Analogical-Reasoning-Dataset"], "Categories": ["Word Analogy"], "Reasoning": ["Relational Reasoning", "Commonsense Reasoning", "Analogical Reasoning"], "Definition": ["Two analogies that relate items to whether they are trash or treasure is given in the form \"A : B. C : ?\". Items marked as \"trash\" are considered to not have value and can be disposed, whereas those marked as \"treasure\" are considered valuable items that must be retained. \"A : \"B relates item A to whether it is trash or treasure, as specified by B. Your task is to replace the question mark (?) with either `trash` or `treasure` for the given item C, following the \"A : B\" relation."], "Positive Examples": [{"input": "book : treasure. pillow : ?", "output": "treasure", "explanation": "The analogy models a trash/treasure relation. Books are associated with treasure, pillows are associated with treasure"}, {"input": "leaf : trash. ring : ?", "output": "treasure", "explanation": "The analogy models a trash/treasure relation. Leaves are associated with trash, rings are associated with treasure"}, {"input": "bug : trash. dirt : ?", "output": "trash", "explanation": "The analogy models a trash/treasure relation. Bugs are associated with trash, dirt is associated with trash"}], "Negative Examples": [{"input": "wrapper : trash. baby : ?", "output": "trash", "explanation": "The analogy models a trash/treasure relation. Wrappers are associated with trash, BUT babies are not associated with trash"}, {"input": "peel : trash. cup : ?", "output": "coffee", "explanation": "The analogy models a trash/treasure relation. Peels are associated with trash. BUT coffee is the wrong answer to the cup, since it models a containment relation."}, {"input": "crumbs : trash. dust : ?", "output": "treasure", "explanation": "The analogy models a trash/treasure relation. Crumbs are associated with trash, BUT dust is not associated with treasure"}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Commonsense"], "Instance": {"id": "task1155-dd2ac62808c7493cb8a3d787554a3c3e", "input": "computer : treasure. book : ?", "output": ["treasure"]}, "Instance License": ["Apache 2.0"], "prediction": "treasure"}
+{"id": "task1155-2b49a6a24eef4ea08a01da18962ce093", "Task": "task1155_bard_analogical_reasoning_trash_or_treasure", "Contributors": "['Arjun Ashok']", "Source": ["bard"], "URL": ["https://github.com/NancyFulda/BYU-Analogical-Reasoning-Dataset"], "Categories": ["Word Analogy"], "Reasoning": ["Relational Reasoning", "Commonsense Reasoning", "Analogical Reasoning"], "Definition": ["Two analogies that relate items to whether they are trash or treasure is given in the form \"A : B. C : ?\". Items marked as \"trash\" are considered to not have value and can be disposed, whereas those marked as \"treasure\" are considered valuable items that must be retained. \"A : \"B relates item A to whether it is trash or treasure, as specified by B. Your task is to replace the question mark (?) with either `trash` or `treasure` for the given item C, following the \"A : B\" relation."], "Positive Examples": [{"input": "book : treasure. pillow : ?", "output": "treasure", "explanation": "The analogy models a trash/treasure relation. Books are associated with treasure, pillows are associated with treasure"}, {"input": "leaf : trash. ring : ?", "output": "treasure", "explanation": "The analogy models a trash/treasure relation. Leaves are associated with trash, rings are associated with treasure"}, {"input": "bug : trash. dirt : ?", "output": "trash", "explanation": "The analogy models a trash/treasure relation. Bugs are associated with trash, dirt is associated with trash"}], "Negative Examples": [{"input": "wrapper : trash. baby : ?", "output": "trash", "explanation": "The analogy models a trash/treasure relation. Wrappers are associated with trash, BUT babies are not associated with trash"}, {"input": "peel : trash. cup : ?", "output": "coffee", "explanation": "The analogy models a trash/treasure relation. Peels are associated with trash. BUT coffee is the wrong answer to the cup, since it models a containment relation."}, {"input": "crumbs : trash. dust : ?", "output": "treasure", "explanation": "The analogy models a trash/treasure relation. Crumbs are associated with trash, BUT dust is not associated with treasure"}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Commonsense"], "Instance": {"id": "task1155-2b49a6a24eef4ea08a01da18962ce093", "input": "crumbs : trash. slime : ?", "output": ["trash"]}, "Instance License": ["Apache 2.0"], "prediction": "trash"}
+{"id": "task1155-23c45053d2f94799bde7e975111fac67", "Task": "task1155_bard_analogical_reasoning_trash_or_treasure", "Contributors": "['Arjun Ashok']", "Source": ["bard"], "URL": ["https://github.com/NancyFulda/BYU-Analogical-Reasoning-Dataset"], "Categories": ["Word Analogy"], "Reasoning": ["Relational Reasoning", "Commonsense Reasoning", "Analogical Reasoning"], "Definition": ["Two analogies that relate items to whether they are trash or treasure is given in the form \"A : B. C : ?\". Items marked as \"trash\" are considered to not have value and can be disposed, whereas those marked as \"treasure\" are considered valuable items that must be retained. \"A : \"B relates item A to whether it is trash or treasure, as specified by B. Your task is to replace the question mark (?) with either `trash` or `treasure` for the given item C, following the \"A : B\" relation."], "Positive Examples": [{"input": "book : treasure. pillow : ?", "output": "treasure", "explanation": "The analogy models a trash/treasure relation. Books are associated with treasure, pillows are associated with treasure"}, {"input": "leaf : trash. ring : ?", "output": "treasure", "explanation": "The analogy models a trash/treasure relation. Leaves are associated with trash, rings are associated with treasure"}, {"input": "bug : trash. dirt : ?", "output": "trash", "explanation": "The analogy models a trash/treasure relation. Bugs are associated with trash, dirt is associated with trash"}], "Negative Examples": [{"input": "wrapper : trash. baby : ?", "output": "trash", "explanation": "The analogy models a trash/treasure relation. Wrappers are associated with trash, BUT babies are not associated with trash"}, {"input": "peel : trash. cup : ?", "output": "coffee", "explanation": "The analogy models a trash/treasure relation. Peels are associated with trash. BUT coffee is the wrong answer to the cup, since it models a containment relation."}, {"input": "crumbs : trash. dust : ?", "output": "treasure", "explanation": "The analogy models a trash/treasure relation. Crumbs are associated with trash, BUT dust is not associated with treasure"}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Commonsense"], "Instance": {"id": "task1155-23c45053d2f94799bde7e975111fac67", "input": "apple : treasure. baby : ?", "output": ["treasure"]}, "Instance License": ["Apache 2.0"], "prediction": "treasure"}
+{"id": "task1385-df4ed18f581c4687b407a500e8d756a0", "Task": "task1385_anli_r1_entailment", "Contributors": "['Yeganeh Kordi']", "Source": ["anli"], "URL": ["https://github.com/facebookresearch/anli"], "Categories": ["Textual Entailment"], "Reasoning": ["Textual Entailment", "Quantitative Reasoning", "Commonsense Reasoning", "Causal Reasoning"], "Definition": ["In this task, you will be presented with a premise and a hypothesis sentence. Determine whether the hypothesis sentence entails (implies), contradicts (opposes), or is neutral with respect to the given premise sentence. Please answer with \"Contradiction\", \"Neutral\", or \"Entailment\"."], "Positive Examples": [{"input": "Premise: Lost Moon: The Perilous Voyage of Apollo 13 (published in paperback as Apollo 13), is a non-fiction book first published in 1994 by astronaut James Lovell and journalist Jeffrey Kluger, about the failed April 1970 Apollo 13 lunar landing mission which Lovell commanded. The book is the basis of the 1995 film adaptation \"Apollo 13\", directed by Ron Howard. <sep> Hypothesis: the book wouldnt have happened if we didnt try to go into space", "output": "Entailment", "explanation": "This is a good example, the book wouldnt have happened if we didnt try to go into space. The hypothesis sentence entails the given premise, so the correct answer is \"Entailment\"."}, {"input": "Premise: Linguistics is the scientific study of language, and involves an analysis of language form, language meaning, and language in context. The earliest activities in the documentation and description of language have been attributed to the 4th century BCE Indian grammarian P\u0101\u1e47ini, who wrote a formal description of the Sanskrit language in his \"A\u1e63\u1e6d\u0101dhy\u0101y\u012b \". <sep> Hypothesis: Form and meaning are the only aspects of language linguistics is concerned with.", "output": "Contradiction", "explanation": "Linguistics involves an analysis of language form, language meaning, and language in context, so context is also a crucial aspect. In this example hypothesis sentence contradicts the given premise, so the correct answer is \"Contradiction\"."}, {"input": "Premise: Stephen Williams (born 5 June 1961) is a former Australian rules footballer in the South Australian National Football League, playing for the Port Adelaide Magpies and is currently an assistant development coach at Port Adelaide Power and head coach of the Immanuel College first XVIII. <sep> Hypothesis: Stephen Williams quit playing football due to an injury.", "output": "Neutral", "explanation": "In this example we don't know why he quit playing. So, hypothesis sentence is neutral with respect to a given premise, so the correct answer is \"Neutral\"."}], "Negative Examples": [{"input": "Premise: Will Wheaton, born Willie Mack Wheaton Jr. (born October 26, 1972) is an American singer, songwriter and musician. He grew up in Los Angeles and is the son of Gospel singer Juanita Wheaton. He studied music in his teens and was eventually tutored by Furman Fordham, whose former students include Lena Horne. <sep> Hypothesis: Willie Mack Wheaton Jr. was born 5 days away from the end of the 10th month of 1972", "output": "Neutral", "explanation": "The hypothesis sentence entails the given premise sentence and \"Neutral\" is incorrect."}, {"input": "Premise: Eme 15 is the self-titled debut studio album by Mexican-Argentine pop band, Eme 15. The album was released in Mexico and Latin America on June 26, 2012 through Warner Music M\u00e9xico, and features songs from the Nickelodeon Latin America and Televisa musical television series, Miss XV. <sep> Hypothesis: Eme 15 was released in Mexico and Latin America on June 27, 2012 through Warner Music M\u00e9xico, and features songs from the Nickelodeon Latin America and Televisa musical television series, Miss XV.", "output": "Entailment", "explanation": "The album was released in June 26, 2012 not June 27, 2012. So, the answer should be \"Contradiction\"."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Miscellaneous"], "Instance": {"id": "task1385-df4ed18f581c4687b407a500e8d756a0", "input": "Premise: Murder in Amsterdam: The Death of Theo Van Gogh and the Limits of Tolerance is a 2006 book by Ian Buruma. \"The Guardian\" describes it as, \"part reportage, part essay.\" It explores the impact of mass immigration from Muslim countries on Dutch culture through the lens of the murder of film director and anti-immigration activist, Theo van Gogh. <sep> Hypothesis: Theo van Gogh made documentary films.", "output": ["Neutral"]}, "Instance License": ["CC BY-NC 4.0"], "prediction": "Entails"}
+{"id": "task1385-512a33e562e9417f9b08fd1b5910d1f8", "Task": "task1385_anli_r1_entailment", "Contributors": "['Yeganeh Kordi']", "Source": ["anli"], "URL": ["https://github.com/facebookresearch/anli"], "Categories": ["Textual Entailment"], "Reasoning": ["Textual Entailment", "Quantitative Reasoning", "Commonsense Reasoning", "Causal Reasoning"], "Definition": ["In this task, you will be presented with a premise and a hypothesis sentence. Determine whether the hypothesis sentence entails (implies), contradicts (opposes), or is neutral with respect to the given premise sentence. Please answer with \"Contradiction\", \"Neutral\", or \"Entailment\"."], "Positive Examples": [{"input": "Premise: Lost Moon: The Perilous Voyage of Apollo 13 (published in paperback as Apollo 13), is a non-fiction book first published in 1994 by astronaut James Lovell and journalist Jeffrey Kluger, about the failed April 1970 Apollo 13 lunar landing mission which Lovell commanded. The book is the basis of the 1995 film adaptation \"Apollo 13\", directed by Ron Howard. <sep> Hypothesis: the book wouldnt have happened if we didnt try to go into space", "output": "Entailment", "explanation": "This is a good example, the book wouldnt have happened if we didnt try to go into space. The hypothesis sentence entails the given premise, so the correct answer is \"Entailment\"."}, {"input": "Premise: Linguistics is the scientific study of language, and involves an analysis of language form, language meaning, and language in context. The earliest activities in the documentation and description of language have been attributed to the 4th century BCE Indian grammarian P\u0101\u1e47ini, who wrote a formal description of the Sanskrit language in his \"A\u1e63\u1e6d\u0101dhy\u0101y\u012b \". <sep> Hypothesis: Form and meaning are the only aspects of language linguistics is concerned with.", "output": "Contradiction", "explanation": "Linguistics involves an analysis of language form, language meaning, and language in context, so context is also a crucial aspect. In this example hypothesis sentence contradicts the given premise, so the correct answer is \"Contradiction\"."}, {"input": "Premise: Stephen Williams (born 5 June 1961) is a former Australian rules footballer in the South Australian National Football League, playing for the Port Adelaide Magpies and is currently an assistant development coach at Port Adelaide Power and head coach of the Immanuel College first XVIII. <sep> Hypothesis: Stephen Williams quit playing football due to an injury.", "output": "Neutral", "explanation": "In this example we don't know why he quit playing. So, hypothesis sentence is neutral with respect to a given premise, so the correct answer is \"Neutral\"."}], "Negative Examples": [{"input": "Premise: Will Wheaton, born Willie Mack Wheaton Jr. (born October 26, 1972) is an American singer, songwriter and musician. He grew up in Los Angeles and is the son of Gospel singer Juanita Wheaton. He studied music in his teens and was eventually tutored by Furman Fordham, whose former students include Lena Horne. <sep> Hypothesis: Willie Mack Wheaton Jr. was born 5 days away from the end of the 10th month of 1972", "output": "Neutral", "explanation": "The hypothesis sentence entails the given premise sentence and \"Neutral\" is incorrect."}, {"input": "Premise: Eme 15 is the self-titled debut studio album by Mexican-Argentine pop band, Eme 15. The album was released in Mexico and Latin America on June 26, 2012 through Warner Music M\u00e9xico, and features songs from the Nickelodeon Latin America and Televisa musical television series, Miss XV. <sep> Hypothesis: Eme 15 was released in Mexico and Latin America on June 27, 2012 through Warner Music M\u00e9xico, and features songs from the Nickelodeon Latin America and Televisa musical television series, Miss XV.", "output": "Entailment", "explanation": "The album was released in June 26, 2012 not June 27, 2012. So, the answer should be \"Contradiction\"."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Miscellaneous"], "Instance": {"id": "task1385-512a33e562e9417f9b08fd1b5910d1f8", "input": "Premise: KAUJ (100.9 FM, \"Oldies 101\") is a radio station licensed to serve Grafton, North Dakota. The station is owned by Simmons Broadcasting Inc. It airs an Oldies music format featuring satellite-fed programming from Scott Shannon's The True Oldies Channel from ABC Radio. <sep> Hypothesis: KAUJ specializes in playing music that was not recently released.", "output": ["Entailment"]}, "Instance License": ["CC BY-NC 4.0"], "prediction": "Neutral"}
+{"id": "task1385-6ae6ee1367ea441fa8b19fb82b5ab9fb", "Task": "task1385_anli_r1_entailment", "Contributors": "['Yeganeh Kordi']", "Source": ["anli"], "URL": ["https://github.com/facebookresearch/anli"], "Categories": ["Textual Entailment"], "Reasoning": ["Textual Entailment", "Quantitative Reasoning", "Commonsense Reasoning", "Causal Reasoning"], "Definition": ["In this task, you will be presented with a premise and a hypothesis sentence. Determine whether the hypothesis sentence entails (implies), contradicts (opposes), or is neutral with respect to the given premise sentence. Please answer with \"Contradiction\", \"Neutral\", or \"Entailment\"."], "Positive Examples": [{"input": "Premise: Lost Moon: The Perilous Voyage of Apollo 13 (published in paperback as Apollo 13), is a non-fiction book first published in 1994 by astronaut James Lovell and journalist Jeffrey Kluger, about the failed April 1970 Apollo 13 lunar landing mission which Lovell commanded. The book is the basis of the 1995 film adaptation \"Apollo 13\", directed by Ron Howard. <sep> Hypothesis: the book wouldnt have happened if we didnt try to go into space", "output": "Entailment", "explanation": "This is a good example, the book wouldnt have happened if we didnt try to go into space. The hypothesis sentence entails the given premise, so the correct answer is \"Entailment\"."}, {"input": "Premise: Linguistics is the scientific study of language, and involves an analysis of language form, language meaning, and language in context. The earliest activities in the documentation and description of language have been attributed to the 4th century BCE Indian grammarian P\u0101\u1e47ini, who wrote a formal description of the Sanskrit language in his \"A\u1e63\u1e6d\u0101dhy\u0101y\u012b \". <sep> Hypothesis: Form and meaning are the only aspects of language linguistics is concerned with.", "output": "Contradiction", "explanation": "Linguistics involves an analysis of language form, language meaning, and language in context, so context is also a crucial aspect. In this example hypothesis sentence contradicts the given premise, so the correct answer is \"Contradiction\"."}, {"input": "Premise: Stephen Williams (born 5 June 1961) is a former Australian rules footballer in the South Australian National Football League, playing for the Port Adelaide Magpies and is currently an assistant development coach at Port Adelaide Power and head coach of the Immanuel College first XVIII. <sep> Hypothesis: Stephen Williams quit playing football due to an injury.", "output": "Neutral", "explanation": "In this example we don't know why he quit playing. So, hypothesis sentence is neutral with respect to a given premise, so the correct answer is \"Neutral\"."}], "Negative Examples": [{"input": "Premise: Will Wheaton, born Willie Mack Wheaton Jr. (born October 26, 1972) is an American singer, songwriter and musician. He grew up in Los Angeles and is the son of Gospel singer Juanita Wheaton. He studied music in his teens and was eventually tutored by Furman Fordham, whose former students include Lena Horne. <sep> Hypothesis: Willie Mack Wheaton Jr. was born 5 days away from the end of the 10th month of 1972", "output": "Neutral", "explanation": "The hypothesis sentence entails the given premise sentence and \"Neutral\" is incorrect."}, {"input": "Premise: Eme 15 is the self-titled debut studio album by Mexican-Argentine pop band, Eme 15. The album was released in Mexico and Latin America on June 26, 2012 through Warner Music M\u00e9xico, and features songs from the Nickelodeon Latin America and Televisa musical television series, Miss XV. <sep> Hypothesis: Eme 15 was released in Mexico and Latin America on June 27, 2012 through Warner Music M\u00e9xico, and features songs from the Nickelodeon Latin America and Televisa musical television series, Miss XV.", "output": "Entailment", "explanation": "The album was released in June 26, 2012 not June 27, 2012. So, the answer should be \"Contradiction\"."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Miscellaneous"], "Instance": {"id": "task1385-6ae6ee1367ea441fa8b19fb82b5ab9fb", "input": "Premise: The Wrath of the Gods is a 1914 American silent drama film directed by Reginald Barker, and starring Sessue Hayakawa, Tsuru Aoki, Frank Borzage, Thomas Kurihara and Henry Kotani in the lead roles. This was the first feature film appearance of Hayakawa and the directorial debut of Barker. <sep> Hypothesis: The Wrath of the Gods is a 1914 American silent drama film which was the first feature film appearance of Tsuru Aoki.", "output": ["Neutral"]}, "Instance License": ["CC BY-NC 4.0"], "prediction": "Entails"}
+{"id": "task1385-d19ab294a2bc47e08378d83be526ffdf", "Task": "task1385_anli_r1_entailment", "Contributors": "['Yeganeh Kordi']", "Source": ["anli"], "URL": ["https://github.com/facebookresearch/anli"], "Categories": ["Textual Entailment"], "Reasoning": ["Textual Entailment", "Quantitative Reasoning", "Commonsense Reasoning", "Causal Reasoning"], "Definition": ["In this task, you will be presented with a premise and a hypothesis sentence. Determine whether the hypothesis sentence entails (implies), contradicts (opposes), or is neutral with respect to the given premise sentence. Please answer with \"Contradiction\", \"Neutral\", or \"Entailment\"."], "Positive Examples": [{"input": "Premise: Lost Moon: The Perilous Voyage of Apollo 13 (published in paperback as Apollo 13), is a non-fiction book first published in 1994 by astronaut James Lovell and journalist Jeffrey Kluger, about the failed April 1970 Apollo 13 lunar landing mission which Lovell commanded. The book is the basis of the 1995 film adaptation \"Apollo 13\", directed by Ron Howard. <sep> Hypothesis: the book wouldnt have happened if we didnt try to go into space", "output": "Entailment", "explanation": "This is a good example, the book wouldnt have happened if we didnt try to go into space. The hypothesis sentence entails the given premise, so the correct answer is \"Entailment\"."}, {"input": "Premise: Linguistics is the scientific study of language, and involves an analysis of language form, language meaning, and language in context. The earliest activities in the documentation and description of language have been attributed to the 4th century BCE Indian grammarian P\u0101\u1e47ini, who wrote a formal description of the Sanskrit language in his \"A\u1e63\u1e6d\u0101dhy\u0101y\u012b \". <sep> Hypothesis: Form and meaning are the only aspects of language linguistics is concerned with.", "output": "Contradiction", "explanation": "Linguistics involves an analysis of language form, language meaning, and language in context, so context is also a crucial aspect. In this example hypothesis sentence contradicts the given premise, so the correct answer is \"Contradiction\"."}, {"input": "Premise: Stephen Williams (born 5 June 1961) is a former Australian rules footballer in the South Australian National Football League, playing for the Port Adelaide Magpies and is currently an assistant development coach at Port Adelaide Power and head coach of the Immanuel College first XVIII. <sep> Hypothesis: Stephen Williams quit playing football due to an injury.", "output": "Neutral", "explanation": "In this example we don't know why he quit playing. So, hypothesis sentence is neutral with respect to a given premise, so the correct answer is \"Neutral\"."}], "Negative Examples": [{"input": "Premise: Will Wheaton, born Willie Mack Wheaton Jr. (born October 26, 1972) is an American singer, songwriter and musician. He grew up in Los Angeles and is the son of Gospel singer Juanita Wheaton. He studied music in his teens and was eventually tutored by Furman Fordham, whose former students include Lena Horne. <sep> Hypothesis: Willie Mack Wheaton Jr. was born 5 days away from the end of the 10th month of 1972", "output": "Neutral", "explanation": "The hypothesis sentence entails the given premise sentence and \"Neutral\" is incorrect."}, {"input": "Premise: Eme 15 is the self-titled debut studio album by Mexican-Argentine pop band, Eme 15. The album was released in Mexico and Latin America on June 26, 2012 through Warner Music M\u00e9xico, and features songs from the Nickelodeon Latin America and Televisa musical television series, Miss XV. <sep> Hypothesis: Eme 15 was released in Mexico and Latin America on June 27, 2012 through Warner Music M\u00e9xico, and features songs from the Nickelodeon Latin America and Televisa musical television series, Miss XV.", "output": "Entailment", "explanation": "The album was released in June 26, 2012 not June 27, 2012. So, the answer should be \"Contradiction\"."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Miscellaneous"], "Instance": {"id": "task1385-d19ab294a2bc47e08378d83be526ffdf", "input": "Premise: Earl Mountbatten of Burma is a title in the Peerage of the United Kingdom. It was created in 1947 for Rear Admiral Louis Mountbatten, 1st Viscount Mountbatten of Burma, the last Viceroy of India. The letters patent creating the title specified the following special remainder: <sep> Hypothesis: The last Viceroy of India was not alive in 1947", "output": ["Contradiction"]}, "Instance License": ["CC BY-NC 4.0"], "prediction": "Falsehood"}
+{"id": "task1385-3b1f947626a64a82a061d1f6b9b8f04f", "Task": "task1385_anli_r1_entailment", "Contributors": "['Yeganeh Kordi']", "Source": ["anli"], "URL": ["https://github.com/facebookresearch/anli"], "Categories": ["Textual Entailment"], "Reasoning": ["Textual Entailment", "Quantitative Reasoning", "Commonsense Reasoning", "Causal Reasoning"], "Definition": ["In this task, you will be presented with a premise and a hypothesis sentence. Determine whether the hypothesis sentence entails (implies), contradicts (opposes), or is neutral with respect to the given premise sentence. Please answer with \"Contradiction\", \"Neutral\", or \"Entailment\"."], "Positive Examples": [{"input": "Premise: Lost Moon: The Perilous Voyage of Apollo 13 (published in paperback as Apollo 13), is a non-fiction book first published in 1994 by astronaut James Lovell and journalist Jeffrey Kluger, about the failed April 1970 Apollo 13 lunar landing mission which Lovell commanded. The book is the basis of the 1995 film adaptation \"Apollo 13\", directed by Ron Howard. <sep> Hypothesis: the book wouldnt have happened if we didnt try to go into space", "output": "Entailment", "explanation": "This is a good example, the book wouldnt have happened if we didnt try to go into space. The hypothesis sentence entails the given premise, so the correct answer is \"Entailment\"."}, {"input": "Premise: Linguistics is the scientific study of language, and involves an analysis of language form, language meaning, and language in context. The earliest activities in the documentation and description of language have been attributed to the 4th century BCE Indian grammarian P\u0101\u1e47ini, who wrote a formal description of the Sanskrit language in his \"A\u1e63\u1e6d\u0101dhy\u0101y\u012b \". <sep> Hypothesis: Form and meaning are the only aspects of language linguistics is concerned with.", "output": "Contradiction", "explanation": "Linguistics involves an analysis of language form, language meaning, and language in context, so context is also a crucial aspect. In this example hypothesis sentence contradicts the given premise, so the correct answer is \"Contradiction\"."}, {"input": "Premise: Stephen Williams (born 5 June 1961) is a former Australian rules footballer in the South Australian National Football League, playing for the Port Adelaide Magpies and is currently an assistant development coach at Port Adelaide Power and head coach of the Immanuel College first XVIII. <sep> Hypothesis: Stephen Williams quit playing football due to an injury.", "output": "Neutral", "explanation": "In this example we don't know why he quit playing. So, hypothesis sentence is neutral with respect to a given premise, so the correct answer is \"Neutral\"."}], "Negative Examples": [{"input": "Premise: Will Wheaton, born Willie Mack Wheaton Jr. (born October 26, 1972) is an American singer, songwriter and musician. He grew up in Los Angeles and is the son of Gospel singer Juanita Wheaton. He studied music in his teens and was eventually tutored by Furman Fordham, whose former students include Lena Horne. <sep> Hypothesis: Willie Mack Wheaton Jr. was born 5 days away from the end of the 10th month of 1972", "output": "Neutral", "explanation": "The hypothesis sentence entails the given premise sentence and \"Neutral\" is incorrect."}, {"input": "Premise: Eme 15 is the self-titled debut studio album by Mexican-Argentine pop band, Eme 15. The album was released in Mexico and Latin America on June 26, 2012 through Warner Music M\u00e9xico, and features songs from the Nickelodeon Latin America and Televisa musical television series, Miss XV. <sep> Hypothesis: Eme 15 was released in Mexico and Latin America on June 27, 2012 through Warner Music M\u00e9xico, and features songs from the Nickelodeon Latin America and Televisa musical television series, Miss XV.", "output": "Entailment", "explanation": "The album was released in June 26, 2012 not June 27, 2012. So, the answer should be \"Contradiction\"."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Miscellaneous"], "Instance": {"id": "task1385-3b1f947626a64a82a061d1f6b9b8f04f", "input": "Premise: Edna Krabappel-Flanders is a fictional character from the animated television series \"The Simpsons\", who was voiced by Marcia Wallace until her death in 2013. She is the teacher of Bart Simpson's 4th grade class at Springfield Elementary School, and Ned Flanders's wife in later seasons. <sep> Hypothesis: Edna Krabappel-Flanders was married to Ned Flanders since the beginning of the Simpsons.", "output": ["Contradiction"]}, "Instance License": ["CC BY-NC 4.0"], "prediction": "Entails"}
+{"id": "task1531-0560cababd9b471696723e972c8427c2", "Task": "task1531_daily_dialog_type_classification", "Contributors": "['Krishna Sriharsha Gundu']", "Source": ["dailydialog"], "URL": ["https://huggingface.co/datasets/daily_dialog"], "Categories": ["Dialogue Act Recognition"], "Reasoning": [], "Definition": ["You have to predict the type of conversation sentence given as input. Your predictions can be one among: 'information' if the input statement states a piece of information, 'question' if the input statement asks for some information, 'directive' if the input sentence involves the management or guidance of operations, and 'commissive' when it constitutes a statement that commits the speaker to some future action."], "Positive Examples": [{"input": "What for ?", "output": "question", "explanation": "The input sentence is a question asking the reason. Therefore this is a sentence classified as the question."}, {"input": "They want the government to reduce the price of the gasoline .", "output": "information", "explanation": "The input sentence states the information about the increase in gasoline prices."}, {"input": "Why don't we go for one now ?", "output": "directive", "explanation": "The input sentence is a directive statement suggesting an action. Therefore this a directive sentence"}, {"input": "Great . We can chat while enjoying a cup there .", "output": "commissive", "explanation": "The input statement commits an act of having a cup of beverage, therefore this is a commissive statement"}], "Negative Examples": [{"input": "ok . You haven \u2019 t seen my company car , have you ? ", "output": "question", "explanation": "The input sentence is not a question as the speaker did not ask this with the intention of getting answered. This is asked as a confirmation message to an already known fact. Therefore this should be classified as 3 and not as 2."}, {"input": "no . let me take a look ... it \u2019 s longer than my car .", "output": "information", "explanation": "This statement is incorrectly classified as an informative statement. The speaker wants to commit to action of looking at the car therefore it should be classified as a commissive statement."}, {"input": "how long will it take us to drive to London ? ", "output": "information", "explanation": "This statement is a question asked to know the length of time taken to drive to London. It should be correctly classified as question instead of information."}, {"input": "You can take it in a couple weeks .", "output": "directive", "explanation": "The speaker commits to an action of lending the object for a couple of weeks therefore it should be classified as a commissive instead of directive."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Dialogue"], "Instance": {"id": "task1531-0560cababd9b471696723e972c8427c2", "input": " I know it does , and that's because it is . ", "output": ["information"]}, "Instance License": ["CC BY-NC-SA 4.0"], "prediction": "information"}
+{"id": "task1531-364fd985fb5d406bbdbff2a62cb12314", "Task": "task1531_daily_dialog_type_classification", "Contributors": "['Krishna Sriharsha Gundu']", "Source": ["dailydialog"], "URL": ["https://huggingface.co/datasets/daily_dialog"], "Categories": ["Dialogue Act Recognition"], "Reasoning": [], "Definition": ["You have to predict the type of conversation sentence given as input. Your predictions can be one among: 'information' if the input statement states a piece of information, 'question' if the input statement asks for some information, 'directive' if the input sentence involves the management or guidance of operations, and 'commissive' when it constitutes a statement that commits the speaker to some future action."], "Positive Examples": [{"input": "What for ?", "output": "question", "explanation": "The input sentence is a question asking the reason. Therefore this is a sentence classified as the question."}, {"input": "They want the government to reduce the price of the gasoline .", "output": "information", "explanation": "The input sentence states the information about the increase in gasoline prices."}, {"input": "Why don't we go for one now ?", "output": "directive", "explanation": "The input sentence is a directive statement suggesting an action. Therefore this a directive sentence"}, {"input": "Great . We can chat while enjoying a cup there .", "output": "commissive", "explanation": "The input statement commits an act of having a cup of beverage, therefore this is a commissive statement"}], "Negative Examples": [{"input": "ok . You haven \u2019 t seen my company car , have you ? ", "output": "question", "explanation": "The input sentence is not a question as the speaker did not ask this with the intention of getting answered. This is asked as a confirmation message to an already known fact. Therefore this should be classified as 3 and not as 2."}, {"input": "no . let me take a look ... it \u2019 s longer than my car .", "output": "information", "explanation": "This statement is incorrectly classified as an informative statement. The speaker wants to commit to action of looking at the car therefore it should be classified as a commissive statement."}, {"input": "how long will it take us to drive to London ? ", "output": "information", "explanation": "This statement is a question asked to know the length of time taken to drive to London. It should be correctly classified as question instead of information."}, {"input": "You can take it in a couple weeks .", "output": "directive", "explanation": "The speaker commits to an action of lending the object for a couple of weeks therefore it should be classified as a commissive instead of directive."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Dialogue"], "Instance": {"id": "task1531-364fd985fb5d406bbdbff2a62cb12314", "input": " How long will you be out of class ? ", "output": ["question"]}, "Instance License": ["CC BY-NC-SA 4.0"], "prediction": "question"}
+{"id": "task1531-048fae4fcdd94299a3aa3e98b06a9547", "Task": "task1531_daily_dialog_type_classification", "Contributors": "['Krishna Sriharsha Gundu']", "Source": ["dailydialog"], "URL": ["https://huggingface.co/datasets/daily_dialog"], "Categories": ["Dialogue Act Recognition"], "Reasoning": [], "Definition": ["You have to predict the type of conversation sentence given as input. Your predictions can be one among: 'information' if the input statement states a piece of information, 'question' if the input statement asks for some information, 'directive' if the input sentence involves the management or guidance of operations, and 'commissive' when it constitutes a statement that commits the speaker to some future action."], "Positive Examples": [{"input": "What for ?", "output": "question", "explanation": "The input sentence is a question asking the reason. Therefore this is a sentence classified as the question."}, {"input": "They want the government to reduce the price of the gasoline .", "output": "information", "explanation": "The input sentence states the information about the increase in gasoline prices."}, {"input": "Why don't we go for one now ?", "output": "directive", "explanation": "The input sentence is a directive statement suggesting an action. Therefore this a directive sentence"}, {"input": "Great . We can chat while enjoying a cup there .", "output": "commissive", "explanation": "The input statement commits an act of having a cup of beverage, therefore this is a commissive statement"}], "Negative Examples": [{"input": "ok . You haven \u2019 t seen my company car , have you ? ", "output": "question", "explanation": "The input sentence is not a question as the speaker did not ask this with the intention of getting answered. This is asked as a confirmation message to an already known fact. Therefore this should be classified as 3 and not as 2."}, {"input": "no . let me take a look ... it \u2019 s longer than my car .", "output": "information", "explanation": "This statement is incorrectly classified as an informative statement. The speaker wants to commit to action of looking at the car therefore it should be classified as a commissive statement."}, {"input": "how long will it take us to drive to London ? ", "output": "information", "explanation": "This statement is a question asked to know the length of time taken to drive to London. It should be correctly classified as question instead of information."}, {"input": "You can take it in a couple weeks .", "output": "directive", "explanation": "The speaker commits to an action of lending the object for a couple of weeks therefore it should be classified as a commissive instead of directive."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Dialogue"], "Instance": {"id": "task1531-048fae4fcdd94299a3aa3e98b06a9547", "input": " Besides I want two copies of all the photos . ", "output": ["directive"]}, "Instance License": ["CC BY-NC-SA 4.0"], "prediction": "question"}
+{"id": "task1531-7c683f22948b4b54a822394541f9a1f5", "Task": "task1531_daily_dialog_type_classification", "Contributors": "['Krishna Sriharsha Gundu']", "Source": ["dailydialog"], "URL": ["https://huggingface.co/datasets/daily_dialog"], "Categories": ["Dialogue Act Recognition"], "Reasoning": [], "Definition": ["You have to predict the type of conversation sentence given as input. Your predictions can be one among: 'information' if the input statement states a piece of information, 'question' if the input statement asks for some information, 'directive' if the input sentence involves the management or guidance of operations, and 'commissive' when it constitutes a statement that commits the speaker to some future action."], "Positive Examples": [{"input": "What for ?", "output": "question", "explanation": "The input sentence is a question asking the reason. Therefore this is a sentence classified as the question."}, {"input": "They want the government to reduce the price of the gasoline .", "output": "information", "explanation": "The input sentence states the information about the increase in gasoline prices."}, {"input": "Why don't we go for one now ?", "output": "directive", "explanation": "The input sentence is a directive statement suggesting an action. Therefore this a directive sentence"}, {"input": "Great . We can chat while enjoying a cup there .", "output": "commissive", "explanation": "The input statement commits an act of having a cup of beverage, therefore this is a commissive statement"}], "Negative Examples": [{"input": "ok . You haven \u2019 t seen my company car , have you ? ", "output": "question", "explanation": "The input sentence is not a question as the speaker did not ask this with the intention of getting answered. This is asked as a confirmation message to an already known fact. Therefore this should be classified as 3 and not as 2."}, {"input": "no . let me take a look ... it \u2019 s longer than my car .", "output": "information", "explanation": "This statement is incorrectly classified as an informative statement. The speaker wants to commit to action of looking at the car therefore it should be classified as a commissive statement."}, {"input": "how long will it take us to drive to London ? ", "output": "information", "explanation": "This statement is a question asked to know the length of time taken to drive to London. It should be correctly classified as question instead of information."}, {"input": "You can take it in a couple weeks .", "output": "directive", "explanation": "The speaker commits to an action of lending the object for a couple of weeks therefore it should be classified as a commissive instead of directive."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Dialogue"], "Instance": {"id": "task1531-7c683f22948b4b54a822394541f9a1f5", "input": " OK . ", "output": ["commissive"]}, "Instance License": ["CC BY-NC-SA 4.0"], "prediction": "yes"}
+{"id": "task1531-99a9bed5f5f9446eb99484282a520324", "Task": "task1531_daily_dialog_type_classification", "Contributors": "['Krishna Sriharsha Gundu']", "Source": ["dailydialog"], "URL": ["https://huggingface.co/datasets/daily_dialog"], "Categories": ["Dialogue Act Recognition"], "Reasoning": [], "Definition": ["You have to predict the type of conversation sentence given as input. Your predictions can be one among: 'information' if the input statement states a piece of information, 'question' if the input statement asks for some information, 'directive' if the input sentence involves the management or guidance of operations, and 'commissive' when it constitutes a statement that commits the speaker to some future action."], "Positive Examples": [{"input": "What for ?", "output": "question", "explanation": "The input sentence is a question asking the reason. Therefore this is a sentence classified as the question."}, {"input": "They want the government to reduce the price of the gasoline .", "output": "information", "explanation": "The input sentence states the information about the increase in gasoline prices."}, {"input": "Why don't we go for one now ?", "output": "directive", "explanation": "The input sentence is a directive statement suggesting an action. Therefore this a directive sentence"}, {"input": "Great . We can chat while enjoying a cup there .", "output": "commissive", "explanation": "The input statement commits an act of having a cup of beverage, therefore this is a commissive statement"}], "Negative Examples": [{"input": "ok . You haven \u2019 t seen my company car , have you ? ", "output": "question", "explanation": "The input sentence is not a question as the speaker did not ask this with the intention of getting answered. This is asked as a confirmation message to an already known fact. Therefore this should be classified as 3 and not as 2."}, {"input": "no . let me take a look ... it \u2019 s longer than my car .", "output": "information", "explanation": "This statement is incorrectly classified as an informative statement. The speaker wants to commit to action of looking at the car therefore it should be classified as a commissive statement."}, {"input": "how long will it take us to drive to London ? ", "output": "information", "explanation": "This statement is a question asked to know the length of time taken to drive to London. It should be correctly classified as question instead of information."}, {"input": "You can take it in a couple weeks .", "output": "directive", "explanation": "The speaker commits to an action of lending the object for a couple of weeks therefore it should be classified as a commissive instead of directive."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Dialogue"], "Instance": {"id": "task1531-99a9bed5f5f9446eb99484282a520324", "input": " I also want to pack up my package . This is the notes . ", "output": ["directive"]}, "Instance License": ["CC BY-NC-SA 4.0"], "prediction": "information"}
+{"id": "task1516-30b6ee5668fb4e9c863f8365627fcbc2", "Task": "task1516_imppres_naturallanguageinference", "Contributors": "['Vivek Bellalacharvu Srinivasa Rao']", "Source": ["imppres"], "URL": ["https://huggingface.co/datasets/imppres"], "Categories": ["Textual Entailment"], "Reasoning": ["Textual Entailment"], "Definition": ["In this task, you are given a premise and hypothesis. The task is to classify them into three categories: 'positive' if the hypothesis supports the premise, 'negated' if it opposes the premise, and 'neutral' if it neither supports nor opposes it."], "Positive Examples": [{"input": "'Premise : All ten guys that proved to boast were divorcing.','Hypothesis : There are exactly ten guys that proved to boast.'", "output": "positive", "explanation": "The output of the given hypothesis and hremise is 'Positive' as the hypothesis supports the premise in a 'Positive' way. In the premise it is mentioned ten guys and even in the hypothesis, ten guys are mentioned"}, {"input": "'Premise : All ten reports that can bore some waiter aren't disagreeing with Naomi.','Hypothesis : There are exactly eleven reports that can bore some waiter.'", "output": "negated", "explanation": "The output of the given hypothesis and premise is 'Negated' as the hypothesis is related to the premise but in a negative way. In the premise there is mention of ten reports but in hypothesis it is mentioned eleven reports"}, {"input": "Premise : All ten guys that proved to boast weren't divorcing.','Hypothesis : There are exactly ten senators that proved to boast.'", "output": "neutral", "explanation": "The output is 'neutral' because the hypothesis neither supports or negates the Premise"}], "Negative Examples": [{"input": "'Premise : If all ten guys that proved to boast were divorcing, it's okay.','Hypothesis : There are exactly ten guys that proved to boast.'", "output": "negated", "explanation": "The output is 'positive' not 'negated' as the hypothesis supports the premise in a 'positive' way. In the premise it is mentioned ten guys boasted and even in the hypothesis, ten guys are mentioned to be boasting"}, {"input": "'Premise : All ten reports that can bore some waiter aren't disagreeing with Naomi.','Hypothesis : There are exactly ten reports that can bore some waiter.'", "output": "negated", "explanation": "The output is 'positive' not 'negated' as the hypothesis supports the premise in a 'positive' way. In the premise it is mentioned ten reports and even in the hypothesis, ten reports are mentioned that bore some waiter"}, {"input": "'Premise : There are exactly ten waiters that can bore some waiter.','Hypothesis : There are exactly ten waitresses that can bore some waiter.'", "output": "positive", "explanation": "The output is 'neutral' not 'positive' as the hypothesis and premise talk about different things and they have no relation with each other. In the premise, it mentions ten waiters and in the hypothesis it mentions ten waitresses."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Commonsense"], "Instance": {"id": "task1516-30b6ee5668fb4e9c863f8365627fcbc2", "input": "Premise : 'Had all six guys who haven't won boasted about Steve?','Hypothesis : There are exactly six guests who haven't won.'", "output": ["neutral"]}, "Instance License": ["CC BY-NC 4.0"], "prediction": "positive"}
+{"id": "task1516-24211f5b3d814634a47370ca16569af3", "Task": "task1516_imppres_naturallanguageinference", "Contributors": "['Vivek Bellalacharvu Srinivasa Rao']", "Source": ["imppres"], "URL": ["https://huggingface.co/datasets/imppres"], "Categories": ["Textual Entailment"], "Reasoning": ["Textual Entailment"], "Definition": ["In this task, you are given a premise and hypothesis. The task is to classify them into three categories: 'positive' if the hypothesis supports the premise, 'negated' if it opposes the premise, and 'neutral' if it neither supports nor opposes it."], "Positive Examples": [{"input": "'Premise : All ten guys that proved to boast were divorcing.','Hypothesis : There are exactly ten guys that proved to boast.'", "output": "positive", "explanation": "The output of the given hypothesis and hremise is 'Positive' as the hypothesis supports the premise in a 'Positive' way. In the premise it is mentioned ten guys and even in the hypothesis, ten guys are mentioned"}, {"input": "'Premise : All ten reports that can bore some waiter aren't disagreeing with Naomi.','Hypothesis : There are exactly eleven reports that can bore some waiter.'", "output": "negated", "explanation": "The output of the given hypothesis and premise is 'Negated' as the hypothesis is related to the premise but in a negative way. In the premise there is mention of ten reports but in hypothesis it is mentioned eleven reports"}, {"input": "Premise : All ten guys that proved to boast weren't divorcing.','Hypothesis : There are exactly ten senators that proved to boast.'", "output": "neutral", "explanation": "The output is 'neutral' because the hypothesis neither supports or negates the Premise"}], "Negative Examples": [{"input": "'Premise : If all ten guys that proved to boast were divorcing, it's okay.','Hypothesis : There are exactly ten guys that proved to boast.'", "output": "negated", "explanation": "The output is 'positive' not 'negated' as the hypothesis supports the premise in a 'positive' way. In the premise it is mentioned ten guys boasted and even in the hypothesis, ten guys are mentioned to be boasting"}, {"input": "'Premise : All ten reports that can bore some waiter aren't disagreeing with Naomi.','Hypothesis : There are exactly ten reports that can bore some waiter.'", "output": "negated", "explanation": "The output is 'positive' not 'negated' as the hypothesis supports the premise in a 'positive' way. In the premise it is mentioned ten reports and even in the hypothesis, ten reports are mentioned that bore some waiter"}, {"input": "'Premise : There are exactly ten waiters that can bore some waiter.','Hypothesis : There are exactly ten waitresses that can bore some waiter.'", "output": "positive", "explanation": "The output is 'neutral' not 'positive' as the hypothesis and premise talk about different things and they have no relation with each other. In the premise, it mentions ten waiters and in the hypothesis it mentions ten waitresses."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Commonsense"], "Instance": {"id": "task1516-24211f5b3d814634a47370ca16569af3", "input": "Premise : 'All seven dresses that haven't resembled those sketches aren't warping.','Hypothesis : There are exactly eight dresses that haven't resembled those sketches.'", "output": ["negated"]}, "Instance License": ["CC BY-NC 4.0"], "prediction": "positive"}
+{"id": "task1516-2c55fa35bfbd4b73971a657edf4db46e", "Task": "task1516_imppres_naturallanguageinference", "Contributors": "['Vivek Bellalacharvu Srinivasa Rao']", "Source": ["imppres"], "URL": ["https://huggingface.co/datasets/imppres"], "Categories": ["Textual Entailment"], "Reasoning": ["Textual Entailment"], "Definition": ["In this task, you are given a premise and hypothesis. The task is to classify them into three categories: 'positive' if the hypothesis supports the premise, 'negated' if it opposes the premise, and 'neutral' if it neither supports nor opposes it."], "Positive Examples": [{"input": "'Premise : All ten guys that proved to boast were divorcing.','Hypothesis : There are exactly ten guys that proved to boast.'", "output": "positive", "explanation": "The output of the given hypothesis and hremise is 'Positive' as the hypothesis supports the premise in a 'Positive' way. In the premise it is mentioned ten guys and even in the hypothesis, ten guys are mentioned"}, {"input": "'Premise : All ten reports that can bore some waiter aren't disagreeing with Naomi.','Hypothesis : There are exactly eleven reports that can bore some waiter.'", "output": "negated", "explanation": "The output of the given hypothesis and premise is 'Negated' as the hypothesis is related to the premise but in a negative way. In the premise there is mention of ten reports but in hypothesis it is mentioned eleven reports"}, {"input": "Premise : All ten guys that proved to boast weren't divorcing.','Hypothesis : There are exactly ten senators that proved to boast.'", "output": "neutral", "explanation": "The output is 'neutral' because the hypothesis neither supports or negates the Premise"}], "Negative Examples": [{"input": "'Premise : If all ten guys that proved to boast were divorcing, it's okay.','Hypothesis : There are exactly ten guys that proved to boast.'", "output": "negated", "explanation": "The output is 'positive' not 'negated' as the hypothesis supports the premise in a 'positive' way. In the premise it is mentioned ten guys boasted and even in the hypothesis, ten guys are mentioned to be boasting"}, {"input": "'Premise : All ten reports that can bore some waiter aren't disagreeing with Naomi.','Hypothesis : There are exactly ten reports that can bore some waiter.'", "output": "negated", "explanation": "The output is 'positive' not 'negated' as the hypothesis supports the premise in a 'positive' way. In the premise it is mentioned ten reports and even in the hypothesis, ten reports are mentioned that bore some waiter"}, {"input": "'Premise : There are exactly ten waiters that can bore some waiter.','Hypothesis : There are exactly ten waitresses that can bore some waiter.'", "output": "positive", "explanation": "The output is 'neutral' not 'positive' as the hypothesis and premise talk about different things and they have no relation with each other. In the premise, it mentions ten waiters and in the hypothesis it mentions ten waitresses."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Commonsense"], "Instance": {"id": "task1516-2c55fa35bfbd4b73971a657edf4db46e", "input": "Premise : 'The two boys that divorced aren't needing to bike to a mountain.','Hypothesis : There are exactly two museums that divorced.'", "output": ["neutral"]}, "Instance License": ["CC BY-NC 4.0"], "prediction": "neutral"}
+{"id": "task1516-c5dac34bf8c14af8a520825ca09230f4", "Task": "task1516_imppres_naturallanguageinference", "Contributors": "['Vivek Bellalacharvu Srinivasa Rao']", "Source": ["imppres"], "URL": ["https://huggingface.co/datasets/imppres"], "Categories": ["Textual Entailment"], "Reasoning": ["Textual Entailment"], "Definition": ["In this task, you are given a premise and hypothesis. The task is to classify them into three categories: 'positive' if the hypothesis supports the premise, 'negated' if it opposes the premise, and 'neutral' if it neither supports nor opposes it."], "Positive Examples": [{"input": "'Premise : All ten guys that proved to boast were divorcing.','Hypothesis : There are exactly ten guys that proved to boast.'", "output": "positive", "explanation": "The output of the given hypothesis and hremise is 'Positive' as the hypothesis supports the premise in a 'Positive' way. In the premise it is mentioned ten guys and even in the hypothesis, ten guys are mentioned"}, {"input": "'Premise : All ten reports that can bore some waiter aren't disagreeing with Naomi.','Hypothesis : There are exactly eleven reports that can bore some waiter.'", "output": "negated", "explanation": "The output of the given hypothesis and premise is 'Negated' as the hypothesis is related to the premise but in a negative way. In the premise there is mention of ten reports but in hypothesis it is mentioned eleven reports"}, {"input": "Premise : All ten guys that proved to boast weren't divorcing.','Hypothesis : There are exactly ten senators that proved to boast.'", "output": "neutral", "explanation": "The output is 'neutral' because the hypothesis neither supports or negates the Premise"}], "Negative Examples": [{"input": "'Premise : If all ten guys that proved to boast were divorcing, it's okay.','Hypothesis : There are exactly ten guys that proved to boast.'", "output": "negated", "explanation": "The output is 'positive' not 'negated' as the hypothesis supports the premise in a 'positive' way. In the premise it is mentioned ten guys boasted and even in the hypothesis, ten guys are mentioned to be boasting"}, {"input": "'Premise : All ten reports that can bore some waiter aren't disagreeing with Naomi.','Hypothesis : There are exactly ten reports that can bore some waiter.'", "output": "negated", "explanation": "The output is 'positive' not 'negated' as the hypothesis supports the premise in a 'positive' way. In the premise it is mentioned ten reports and even in the hypothesis, ten reports are mentioned that bore some waiter"}, {"input": "'Premise : There are exactly ten waiters that can bore some waiter.','Hypothesis : There are exactly ten waitresses that can bore some waiter.'", "output": "positive", "explanation": "The output is 'neutral' not 'positive' as the hypothesis and premise talk about different things and they have no relation with each other. In the premise, it mentions ten waiters and in the hypothesis it mentions ten waitresses."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Commonsense"], "Instance": {"id": "task1516-c5dac34bf8c14af8a520825ca09230f4", "input": "Premise : 'The nine adults who ascertained Carmen to dislike a lot of high schools hunt.','Hypothesis : There are exactly nine adults who ascertained Carmen to dislike a lot of high schools.'", "output": ["positive"]}, "Instance License": ["CC BY-NC 4.0"], "prediction": "positive"}
+{"id": "task1516-41c273774e3e412a8100c8f8bae52220", "Task": "task1516_imppres_naturallanguageinference", "Contributors": "['Vivek Bellalacharvu Srinivasa Rao']", "Source": ["imppres"], "URL": ["https://huggingface.co/datasets/imppres"], "Categories": ["Textual Entailment"], "Reasoning": ["Textual Entailment"], "Definition": ["In this task, you are given a premise and hypothesis. The task is to classify them into three categories: 'positive' if the hypothesis supports the premise, 'negated' if it opposes the premise, and 'neutral' if it neither supports nor opposes it."], "Positive Examples": [{"input": "'Premise : All ten guys that proved to boast were divorcing.','Hypothesis : There are exactly ten guys that proved to boast.'", "output": "positive", "explanation": "The output of the given hypothesis and hremise is 'Positive' as the hypothesis supports the premise in a 'Positive' way. In the premise it is mentioned ten guys and even in the hypothesis, ten guys are mentioned"}, {"input": "'Premise : All ten reports that can bore some waiter aren't disagreeing with Naomi.','Hypothesis : There are exactly eleven reports that can bore some waiter.'", "output": "negated", "explanation": "The output of the given hypothesis and premise is 'Negated' as the hypothesis is related to the premise but in a negative way. In the premise there is mention of ten reports but in hypothesis it is mentioned eleven reports"}, {"input": "Premise : All ten guys that proved to boast weren't divorcing.','Hypothesis : There are exactly ten senators that proved to boast.'", "output": "neutral", "explanation": "The output is 'neutral' because the hypothesis neither supports or negates the Premise"}], "Negative Examples": [{"input": "'Premise : If all ten guys that proved to boast were divorcing, it's okay.','Hypothesis : There are exactly ten guys that proved to boast.'", "output": "negated", "explanation": "The output is 'positive' not 'negated' as the hypothesis supports the premise in a 'positive' way. In the premise it is mentioned ten guys boasted and even in the hypothesis, ten guys are mentioned to be boasting"}, {"input": "'Premise : All ten reports that can bore some waiter aren't disagreeing with Naomi.','Hypothesis : There are exactly ten reports that can bore some waiter.'", "output": "negated", "explanation": "The output is 'positive' not 'negated' as the hypothesis supports the premise in a 'positive' way. In the premise it is mentioned ten reports and even in the hypothesis, ten reports are mentioned that bore some waiter"}, {"input": "'Premise : There are exactly ten waiters that can bore some waiter.','Hypothesis : There are exactly ten waitresses that can bore some waiter.'", "output": "positive", "explanation": "The output is 'neutral' not 'positive' as the hypothesis and premise talk about different things and they have no relation with each other. In the premise, it mentions ten waiters and in the hypothesis it mentions ten waitresses."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Commonsense"], "Instance": {"id": "task1516-41c273774e3e412a8100c8f8bae52220", "input": "Premise : 'The four organizations that appreciate Sherry haven't dared Derek to talk about Lori.','Hypothesis : There are exactly four organizations that appreciate Sherry.'", "output": ["positive"]}, "Instance License": ["CC BY-NC 4.0"], "prediction": "positive"}
+{"id": "task1394-e447ff346c484666816ed33f250702f7", "Task": "task1394_meta_woz_task_classification", "Contributors": "['Wen-Jui Mao']", "Source": ["meta_woz"], "URL": ["https://huggingface.co/datasets/meta_woz"], "Categories": ["Dialogue Act Recognition"], "Reasoning": ["Reasoning on Social Interactions"], "Definition": ["In this task, you are given four sentences: a bot task sentence, a bot role sentence, a user task sentence and a user role sentence. Your job is to classify given sentences into one of the 47 different domains. The domains are: 'UPDATE_CALENDAR', 'PRESENT_IDEAS', 'MOVIE_LISTINGS', 'AUTO_SORT', 'GAME_RULES', 'CONTACT_MANAGER', 'BANK_BOT', 'MUSIC_SUGGESTER', 'CHECK_STATUS', 'PET_ADVICE', 'HOW_TO_BASIC', 'NAME_SUGGESTER', 'QUOTE_OF_THE_DAY_BOT', 'GUINESS_CHECK', 'INSURANCE', 'RESTAURANT_PICKER', 'MAKE_RESTAURANT_RESERVATIONS', 'WEDDING_PLANNER', 'SKI_BOT', 'HOME_BOT', 'PLAY_TIMES', 'BUS_SCHEDULE_BOT', 'WHAT_IS_IT', 'PHONE_PLAN_BOT', 'DECIDER_BOT', 'PHONE_SETTINGS', 'TIME_ZONE', 'LIBRARY_REQUEST', 'UPDATE_CONTACT', 'CATALOGUE_BOT', 'PROMPT_GENERATOR', 'SCAM_LOOKUP', 'SPORTS_INFO', 'POLICY_BOT', 'CITY_INFO', 'APARTMENT_FINDER', 'EVENT_RESERVE', 'SHOPPING', 'EDIT_PLAYLIST', 'LOOK_UP_INFO', 'ORDER_PIZZA', 'WEATHER_CHECK', 'APPOINTMENT_REMINDER', 'GEOGRAPHY', 'STORE_DETAILS', 'AGREEMENT_BOT', 'ALARM_SET'."], "Positive Examples": [{"input": "Bot's task: Inform the user that the topping they are asking for is unavailable \nBot's role: You are a bot designed to help customers order pizza \nUser's task: Ask if a certain pizza topping is available \nUser's role: You are interacting with a pizza restaurant bot", "output": "ORDER_PIZZA", "explanation": "According to the descriptions of the four sentences, we know that the type of task is ORDER_PIZZA"}, {"input": "Bot's task: Clarify which playlist the user wants to retitle and what they want to change the title to \nBot's role: You are a bot that manages music playlists \nUser's task: Ask the bot to retitle your playlist \nUser's role: You are interacting with a bot that can manage your music playlists", "output": "EDIT_PLAYLIST", "explanation": "The word about playlist appears in all four sentences, so the categories of the task and role sentences are EDIT_PLAYLIST"}, {"input": "Bot's task: Offer the user three two bedroom apartments in the downtown area \nBot's role: You are a bot designed to find and compare available apartments in a city \nUser's task: Ask the bot to find you a 2 bedroom apartment in the downtown area \nUser's role: You are interacting with a bot designed to find and compare available apartments in a city", "output": "APARTMENT_FINDER", "explanation": "These four sentences are about finding an apartment, so the answer is APARTMENT_FINDER"}], "Negative Examples": [{"input": "Bot's task: Help the user with their pizza order \nBot's role: You are a bot designed to help customers order pizza \nUser's task: Ask the bot for three different pizzas \nUser's role: You are interacting with a pizza restaurant bot", "output": "UPDATE_CALENDAR", "explanation": "According to the descriptions of the tasks and roles, we know that the type of task is ORDER_PIZZA, but the output is UPDATE_CALENDAR, so it is incorrect."}, {"input": "Bot's task: Tell the user that there isn't any room at their first choice of restaurant. If the user then provides an alternate choice, make the reservation for them \nBot's role: You are a bot designed to make restaurant reservations \nUser's task: You and fifteen business partners need to book a few tables for tonight at a fancy restaurant \nUser's role: You are interacting with a bot designed to help you make restaurant reservations", "output": "APARTMENT_FINDER", "explanation": "These four sentences of the task is about ordering restaurants, the answer is wrong."}, {"input": "Bot's task: Tell the user that you are a bot designed to clarify rules, not controls, and suggest they look for some kind of GAME_CONTROLS bot \nBot's role: You are a bot that clarifies the rules for games \nUser's task: Ask the bot what button you have to press to Jump in Super Mario 64 \nUser's role: You are interacting with a bot that clarifies the rules of games", "output": "PLAY_TIMES", "explanation": "These four quests are about the rules of the game and not the game time, so this is a negative example"}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Dialogue", "Commonsense -> Concepts and Relations -> Social Commonsense"], "Instance": {"id": "task1394-e447ff346c484666816ed33f250702f7", "input": "Bot's task: Give the user some music suggestions without first asking them what they like \nBot's role: You are a bot designed to give music suggestions \nUser's task: Ask the bot for music suggestions without telling it what you like \nUser's role: You are interacting with a bot designed to give music suggestions", "output": ["MUSIC_SUGGESTER"]}, "Instance License": ["Microsoft Research Data License Agreement (https://msropendata-web-api.azurewebsites.net/licenses/2f933be3-284d-500b-7ea3-2aa2fd0f1bb2/view)"], "prediction": "MUSIC_SUGGESTER"}
+{"id": "task1394-61de97a571e043c7bfe5ad79df055f08", "Task": "task1394_meta_woz_task_classification", "Contributors": "['Wen-Jui Mao']", "Source": ["meta_woz"], "URL": ["https://huggingface.co/datasets/meta_woz"], "Categories": ["Dialogue Act Recognition"], "Reasoning": ["Reasoning on Social Interactions"], "Definition": ["In this task, you are given four sentences: a bot task sentence, a bot role sentence, a user task sentence and a user role sentence. Your job is to classify given sentences into one of the 47 different domains. The domains are: 'UPDATE_CALENDAR', 'PRESENT_IDEAS', 'MOVIE_LISTINGS', 'AUTO_SORT', 'GAME_RULES', 'CONTACT_MANAGER', 'BANK_BOT', 'MUSIC_SUGGESTER', 'CHECK_STATUS', 'PET_ADVICE', 'HOW_TO_BASIC', 'NAME_SUGGESTER', 'QUOTE_OF_THE_DAY_BOT', 'GUINESS_CHECK', 'INSURANCE', 'RESTAURANT_PICKER', 'MAKE_RESTAURANT_RESERVATIONS', 'WEDDING_PLANNER', 'SKI_BOT', 'HOME_BOT', 'PLAY_TIMES', 'BUS_SCHEDULE_BOT', 'WHAT_IS_IT', 'PHONE_PLAN_BOT', 'DECIDER_BOT', 'PHONE_SETTINGS', 'TIME_ZONE', 'LIBRARY_REQUEST', 'UPDATE_CONTACT', 'CATALOGUE_BOT', 'PROMPT_GENERATOR', 'SCAM_LOOKUP', 'SPORTS_INFO', 'POLICY_BOT', 'CITY_INFO', 'APARTMENT_FINDER', 'EVENT_RESERVE', 'SHOPPING', 'EDIT_PLAYLIST', 'LOOK_UP_INFO', 'ORDER_PIZZA', 'WEATHER_CHECK', 'APPOINTMENT_REMINDER', 'GEOGRAPHY', 'STORE_DETAILS', 'AGREEMENT_BOT', 'ALARM_SET'."], "Positive Examples": [{"input": "Bot's task: Inform the user that the topping they are asking for is unavailable \nBot's role: You are a bot designed to help customers order pizza \nUser's task: Ask if a certain pizza topping is available \nUser's role: You are interacting with a pizza restaurant bot", "output": "ORDER_PIZZA", "explanation": "According to the descriptions of the four sentences, we know that the type of task is ORDER_PIZZA"}, {"input": "Bot's task: Clarify which playlist the user wants to retitle and what they want to change the title to \nBot's role: You are a bot that manages music playlists \nUser's task: Ask the bot to retitle your playlist \nUser's role: You are interacting with a bot that can manage your music playlists", "output": "EDIT_PLAYLIST", "explanation": "The word about playlist appears in all four sentences, so the categories of the task and role sentences are EDIT_PLAYLIST"}, {"input": "Bot's task: Offer the user three two bedroom apartments in the downtown area \nBot's role: You are a bot designed to find and compare available apartments in a city \nUser's task: Ask the bot to find you a 2 bedroom apartment in the downtown area \nUser's role: You are interacting with a bot designed to find and compare available apartments in a city", "output": "APARTMENT_FINDER", "explanation": "These four sentences are about finding an apartment, so the answer is APARTMENT_FINDER"}], "Negative Examples": [{"input": "Bot's task: Help the user with their pizza order \nBot's role: You are a bot designed to help customers order pizza \nUser's task: Ask the bot for three different pizzas \nUser's role: You are interacting with a pizza restaurant bot", "output": "UPDATE_CALENDAR", "explanation": "According to the descriptions of the tasks and roles, we know that the type of task is ORDER_PIZZA, but the output is UPDATE_CALENDAR, so it is incorrect."}, {"input": "Bot's task: Tell the user that there isn't any room at their first choice of restaurant. If the user then provides an alternate choice, make the reservation for them \nBot's role: You are a bot designed to make restaurant reservations \nUser's task: You and fifteen business partners need to book a few tables for tonight at a fancy restaurant \nUser's role: You are interacting with a bot designed to help you make restaurant reservations", "output": "APARTMENT_FINDER", "explanation": "These four sentences of the task is about ordering restaurants, the answer is wrong."}, {"input": "Bot's task: Tell the user that you are a bot designed to clarify rules, not controls, and suggest they look for some kind of GAME_CONTROLS bot \nBot's role: You are a bot that clarifies the rules for games \nUser's task: Ask the bot what button you have to press to Jump in Super Mario 64 \nUser's role: You are interacting with a bot that clarifies the rules of games", "output": "PLAY_TIMES", "explanation": "These four quests are about the rules of the game and not the game time, so this is a negative example"}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Dialogue", "Commonsense -> Concepts and Relations -> Social Commonsense"], "Instance": {"id": "task1394-61de97a571e043c7bfe5ad79df055f08", "input": "Bot's task: Inform the user that there aren't any seats available to reserve \nBot's role: You are a bot designed to make reservations for events \nUser's task: You want to reserve seats at a theatre \nUser's role: You are interacting with a bot designed to make reservations for events", "output": ["EVENT_RESERVE"]}, "Instance License": ["Microsoft Research Data License Agreement (https://msropendata-web-api.azurewebsites.net/licenses/2f933be3-284d-500b-7ea3-2aa2fd0f1bb2/view)"], "prediction": "EVENT_RESERVE"}
+{"id": "task1394-344962cac5d343e48b7fa9217c4c28ed", "Task": "task1394_meta_woz_task_classification", "Contributors": "['Wen-Jui Mao']", "Source": ["meta_woz"], "URL": ["https://huggingface.co/datasets/meta_woz"], "Categories": ["Dialogue Act Recognition"], "Reasoning": ["Reasoning on Social Interactions"], "Definition": ["In this task, you are given four sentences: a bot task sentence, a bot role sentence, a user task sentence and a user role sentence. Your job is to classify given sentences into one of the 47 different domains. The domains are: 'UPDATE_CALENDAR', 'PRESENT_IDEAS', 'MOVIE_LISTINGS', 'AUTO_SORT', 'GAME_RULES', 'CONTACT_MANAGER', 'BANK_BOT', 'MUSIC_SUGGESTER', 'CHECK_STATUS', 'PET_ADVICE', 'HOW_TO_BASIC', 'NAME_SUGGESTER', 'QUOTE_OF_THE_DAY_BOT', 'GUINESS_CHECK', 'INSURANCE', 'RESTAURANT_PICKER', 'MAKE_RESTAURANT_RESERVATIONS', 'WEDDING_PLANNER', 'SKI_BOT', 'HOME_BOT', 'PLAY_TIMES', 'BUS_SCHEDULE_BOT', 'WHAT_IS_IT', 'PHONE_PLAN_BOT', 'DECIDER_BOT', 'PHONE_SETTINGS', 'TIME_ZONE', 'LIBRARY_REQUEST', 'UPDATE_CONTACT', 'CATALOGUE_BOT', 'PROMPT_GENERATOR', 'SCAM_LOOKUP', 'SPORTS_INFO', 'POLICY_BOT', 'CITY_INFO', 'APARTMENT_FINDER', 'EVENT_RESERVE', 'SHOPPING', 'EDIT_PLAYLIST', 'LOOK_UP_INFO', 'ORDER_PIZZA', 'WEATHER_CHECK', 'APPOINTMENT_REMINDER', 'GEOGRAPHY', 'STORE_DETAILS', 'AGREEMENT_BOT', 'ALARM_SET'."], "Positive Examples": [{"input": "Bot's task: Inform the user that the topping they are asking for is unavailable \nBot's role: You are a bot designed to help customers order pizza \nUser's task: Ask if a certain pizza topping is available \nUser's role: You are interacting with a pizza restaurant bot", "output": "ORDER_PIZZA", "explanation": "According to the descriptions of the four sentences, we know that the type of task is ORDER_PIZZA"}, {"input": "Bot's task: Clarify which playlist the user wants to retitle and what they want to change the title to \nBot's role: You are a bot that manages music playlists \nUser's task: Ask the bot to retitle your playlist \nUser's role: You are interacting with a bot that can manage your music playlists", "output": "EDIT_PLAYLIST", "explanation": "The word about playlist appears in all four sentences, so the categories of the task and role sentences are EDIT_PLAYLIST"}, {"input": "Bot's task: Offer the user three two bedroom apartments in the downtown area \nBot's role: You are a bot designed to find and compare available apartments in a city \nUser's task: Ask the bot to find you a 2 bedroom apartment in the downtown area \nUser's role: You are interacting with a bot designed to find and compare available apartments in a city", "output": "APARTMENT_FINDER", "explanation": "These four sentences are about finding an apartment, so the answer is APARTMENT_FINDER"}], "Negative Examples": [{"input": "Bot's task: Help the user with their pizza order \nBot's role: You are a bot designed to help customers order pizza \nUser's task: Ask the bot for three different pizzas \nUser's role: You are interacting with a pizza restaurant bot", "output": "UPDATE_CALENDAR", "explanation": "According to the descriptions of the tasks and roles, we know that the type of task is ORDER_PIZZA, but the output is UPDATE_CALENDAR, so it is incorrect."}, {"input": "Bot's task: Tell the user that there isn't any room at their first choice of restaurant. If the user then provides an alternate choice, make the reservation for them \nBot's role: You are a bot designed to make restaurant reservations \nUser's task: You and fifteen business partners need to book a few tables for tonight at a fancy restaurant \nUser's role: You are interacting with a bot designed to help you make restaurant reservations", "output": "APARTMENT_FINDER", "explanation": "These four sentences of the task is about ordering restaurants, the answer is wrong."}, {"input": "Bot's task: Tell the user that you are a bot designed to clarify rules, not controls, and suggest they look for some kind of GAME_CONTROLS bot \nBot's role: You are a bot that clarifies the rules for games \nUser's task: Ask the bot what button you have to press to Jump in Super Mario 64 \nUser's role: You are interacting with a bot that clarifies the rules of games", "output": "PLAY_TIMES", "explanation": "These four quests are about the rules of the game and not the game time, so this is a negative example"}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Dialogue", "Commonsense -> Concepts and Relations -> Social Commonsense"], "Instance": {"id": "task1394-344962cac5d343e48b7fa9217c4c28ed", "input": "Bot's task: Help the user with their request \nBot's role: You are a bot designed to provide instructions for basic tasks \nUser's task: Ask how to set up an account on a social media site \nUser's role: You are interacting with a bot that gives instructions on how to complete basic tasks", "output": ["HOW_TO_BASIC"]}, "Instance License": ["Microsoft Research Data License Agreement (https://msropendata-web-api.azurewebsites.net/licenses/2f933be3-284d-500b-7ea3-2aa2fd0f1bb2/view)"], "prediction": "How_to_Banic"}
+{"id": "task1394-02e3077f9dd248069f4e68681a7581c8", "Task": "task1394_meta_woz_task_classification", "Contributors": "['Wen-Jui Mao']", "Source": ["meta_woz"], "URL": ["https://huggingface.co/datasets/meta_woz"], "Categories": ["Dialogue Act Recognition"], "Reasoning": ["Reasoning on Social Interactions"], "Definition": ["In this task, you are given four sentences: a bot task sentence, a bot role sentence, a user task sentence and a user role sentence. Your job is to classify given sentences into one of the 47 different domains. The domains are: 'UPDATE_CALENDAR', 'PRESENT_IDEAS', 'MOVIE_LISTINGS', 'AUTO_SORT', 'GAME_RULES', 'CONTACT_MANAGER', 'BANK_BOT', 'MUSIC_SUGGESTER', 'CHECK_STATUS', 'PET_ADVICE', 'HOW_TO_BASIC', 'NAME_SUGGESTER', 'QUOTE_OF_THE_DAY_BOT', 'GUINESS_CHECK', 'INSURANCE', 'RESTAURANT_PICKER', 'MAKE_RESTAURANT_RESERVATIONS', 'WEDDING_PLANNER', 'SKI_BOT', 'HOME_BOT', 'PLAY_TIMES', 'BUS_SCHEDULE_BOT', 'WHAT_IS_IT', 'PHONE_PLAN_BOT', 'DECIDER_BOT', 'PHONE_SETTINGS', 'TIME_ZONE', 'LIBRARY_REQUEST', 'UPDATE_CONTACT', 'CATALOGUE_BOT', 'PROMPT_GENERATOR', 'SCAM_LOOKUP', 'SPORTS_INFO', 'POLICY_BOT', 'CITY_INFO', 'APARTMENT_FINDER', 'EVENT_RESERVE', 'SHOPPING', 'EDIT_PLAYLIST', 'LOOK_UP_INFO', 'ORDER_PIZZA', 'WEATHER_CHECK', 'APPOINTMENT_REMINDER', 'GEOGRAPHY', 'STORE_DETAILS', 'AGREEMENT_BOT', 'ALARM_SET'."], "Positive Examples": [{"input": "Bot's task: Inform the user that the topping they are asking for is unavailable \nBot's role: You are a bot designed to help customers order pizza \nUser's task: Ask if a certain pizza topping is available \nUser's role: You are interacting with a pizza restaurant bot", "output": "ORDER_PIZZA", "explanation": "According to the descriptions of the four sentences, we know that the type of task is ORDER_PIZZA"}, {"input": "Bot's task: Clarify which playlist the user wants to retitle and what they want to change the title to \nBot's role: You are a bot that manages music playlists \nUser's task: Ask the bot to retitle your playlist \nUser's role: You are interacting with a bot that can manage your music playlists", "output": "EDIT_PLAYLIST", "explanation": "The word about playlist appears in all four sentences, so the categories of the task and role sentences are EDIT_PLAYLIST"}, {"input": "Bot's task: Offer the user three two bedroom apartments in the downtown area \nBot's role: You are a bot designed to find and compare available apartments in a city \nUser's task: Ask the bot to find you a 2 bedroom apartment in the downtown area \nUser's role: You are interacting with a bot designed to find and compare available apartments in a city", "output": "APARTMENT_FINDER", "explanation": "These four sentences are about finding an apartment, so the answer is APARTMENT_FINDER"}], "Negative Examples": [{"input": "Bot's task: Help the user with their pizza order \nBot's role: You are a bot designed to help customers order pizza \nUser's task: Ask the bot for three different pizzas \nUser's role: You are interacting with a pizza restaurant bot", "output": "UPDATE_CALENDAR", "explanation": "According to the descriptions of the tasks and roles, we know that the type of task is ORDER_PIZZA, but the output is UPDATE_CALENDAR, so it is incorrect."}, {"input": "Bot's task: Tell the user that there isn't any room at their first choice of restaurant. If the user then provides an alternate choice, make the reservation for them \nBot's role: You are a bot designed to make restaurant reservations \nUser's task: You and fifteen business partners need to book a few tables for tonight at a fancy restaurant \nUser's role: You are interacting with a bot designed to help you make restaurant reservations", "output": "APARTMENT_FINDER", "explanation": "These four sentences of the task is about ordering restaurants, the answer is wrong."}, {"input": "Bot's task: Tell the user that you are a bot designed to clarify rules, not controls, and suggest they look for some kind of GAME_CONTROLS bot \nBot's role: You are a bot that clarifies the rules for games \nUser's task: Ask the bot what button you have to press to Jump in Super Mario 64 \nUser's role: You are interacting with a bot that clarifies the rules of games", "output": "PLAY_TIMES", "explanation": "These four quests are about the rules of the game and not the game time, so this is a negative example"}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Dialogue", "Commonsense -> Concepts and Relations -> Social Commonsense"], "Instance": {"id": "task1394-02e3077f9dd248069f4e68681a7581c8", "input": "Bot's task: Tell the user that there are a lot of conditions that decide the cost of a wedding, so it's impossible to say which destination will cost more. \nBot's role: You are a bot that helps plan weddings \nUser's task: Ask the bot whether a beach wedding or a private island wedding would be more expensive. \nUser's role: You are interacting with a bot that helps plan weddings", "output": ["WEDDING_PLANNER"]}, "Instance License": ["Microsoft Research Data License Agreement (https://msropendata-web-api.azurewebsites.net/licenses/2f933be3-284d-500b-7ea3-2aa2fd0f1bb2/view)"], "prediction": "PART_PLAN_BOT"}
+{"id": "task1394-0d265fb36cae4043b844f4d9595b1dce", "Task": "task1394_meta_woz_task_classification", "Contributors": "['Wen-Jui Mao']", "Source": ["meta_woz"], "URL": ["https://huggingface.co/datasets/meta_woz"], "Categories": ["Dialogue Act Recognition"], "Reasoning": ["Reasoning on Social Interactions"], "Definition": ["In this task, you are given four sentences: a bot task sentence, a bot role sentence, a user task sentence and a user role sentence. Your job is to classify given sentences into one of the 47 different domains. The domains are: 'UPDATE_CALENDAR', 'PRESENT_IDEAS', 'MOVIE_LISTINGS', 'AUTO_SORT', 'GAME_RULES', 'CONTACT_MANAGER', 'BANK_BOT', 'MUSIC_SUGGESTER', 'CHECK_STATUS', 'PET_ADVICE', 'HOW_TO_BASIC', 'NAME_SUGGESTER', 'QUOTE_OF_THE_DAY_BOT', 'GUINESS_CHECK', 'INSURANCE', 'RESTAURANT_PICKER', 'MAKE_RESTAURANT_RESERVATIONS', 'WEDDING_PLANNER', 'SKI_BOT', 'HOME_BOT', 'PLAY_TIMES', 'BUS_SCHEDULE_BOT', 'WHAT_IS_IT', 'PHONE_PLAN_BOT', 'DECIDER_BOT', 'PHONE_SETTINGS', 'TIME_ZONE', 'LIBRARY_REQUEST', 'UPDATE_CONTACT', 'CATALOGUE_BOT', 'PROMPT_GENERATOR', 'SCAM_LOOKUP', 'SPORTS_INFO', 'POLICY_BOT', 'CITY_INFO', 'APARTMENT_FINDER', 'EVENT_RESERVE', 'SHOPPING', 'EDIT_PLAYLIST', 'LOOK_UP_INFO', 'ORDER_PIZZA', 'WEATHER_CHECK', 'APPOINTMENT_REMINDER', 'GEOGRAPHY', 'STORE_DETAILS', 'AGREEMENT_BOT', 'ALARM_SET'."], "Positive Examples": [{"input": "Bot's task: Inform the user that the topping they are asking for is unavailable \nBot's role: You are a bot designed to help customers order pizza \nUser's task: Ask if a certain pizza topping is available \nUser's role: You are interacting with a pizza restaurant bot", "output": "ORDER_PIZZA", "explanation": "According to the descriptions of the four sentences, we know that the type of task is ORDER_PIZZA"}, {"input": "Bot's task: Clarify which playlist the user wants to retitle and what they want to change the title to \nBot's role: You are a bot that manages music playlists \nUser's task: Ask the bot to retitle your playlist \nUser's role: You are interacting with a bot that can manage your music playlists", "output": "EDIT_PLAYLIST", "explanation": "The word about playlist appears in all four sentences, so the categories of the task and role sentences are EDIT_PLAYLIST"}, {"input": "Bot's task: Offer the user three two bedroom apartments in the downtown area \nBot's role: You are a bot designed to find and compare available apartments in a city \nUser's task: Ask the bot to find you a 2 bedroom apartment in the downtown area \nUser's role: You are interacting with a bot designed to find and compare available apartments in a city", "output": "APARTMENT_FINDER", "explanation": "These four sentences are about finding an apartment, so the answer is APARTMENT_FINDER"}], "Negative Examples": [{"input": "Bot's task: Help the user with their pizza order \nBot's role: You are a bot designed to help customers order pizza \nUser's task: Ask the bot for three different pizzas \nUser's role: You are interacting with a pizza restaurant bot", "output": "UPDATE_CALENDAR", "explanation": "According to the descriptions of the tasks and roles, we know that the type of task is ORDER_PIZZA, but the output is UPDATE_CALENDAR, so it is incorrect."}, {"input": "Bot's task: Tell the user that there isn't any room at their first choice of restaurant. If the user then provides an alternate choice, make the reservation for them \nBot's role: You are a bot designed to make restaurant reservations \nUser's task: You and fifteen business partners need to book a few tables for tonight at a fancy restaurant \nUser's role: You are interacting with a bot designed to help you make restaurant reservations", "output": "APARTMENT_FINDER", "explanation": "These four sentences of the task is about ordering restaurants, the answer is wrong."}, {"input": "Bot's task: Tell the user that you are a bot designed to clarify rules, not controls, and suggest they look for some kind of GAME_CONTROLS bot \nBot's role: You are a bot that clarifies the rules for games \nUser's task: Ask the bot what button you have to press to Jump in Super Mario 64 \nUser's role: You are interacting with a bot that clarifies the rules of games", "output": "PLAY_TIMES", "explanation": "These four quests are about the rules of the game and not the game time, so this is a negative example"}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Dialogue", "Commonsense -> Concepts and Relations -> Social Commonsense"], "Instance": {"id": "task1394-0d265fb36cae4043b844f4d9595b1dce", "input": "Bot's task: Fulfil the user's request \nBot's role: You are a bot representing a bank \nUser's task: Try to put money from your chequing account into your savings account \nUser's role: You are interacting with a bot representing your bank", "output": ["BANK_BOT"]}, "Instance License": ["Microsoft Research Data License Agreement (https://msropendata-web-api.azurewebsites.net/licenses/2f933be3-284d-500b-7ea3-2aa2fd0f1bb2/view)"], "prediction": "BK_BOT"}
+{"id": "task401-cffc6883bd934038b0bfea6359887aae", "Task": "task401_numeric_fused_head_reference", "Contributors": "['Pegah Alipoormolabashi']", "Source": ["numeric_fused_head"], "URL": ["https://github.com/yanaiela/num_fh"], "Categories": ["Coreference Resolution"], "Reasoning": ["Commonsense Reasoning -> Numerical Commonsense Reasoning"], "Definition": ["In this task, you will use your knowledge about language (and common sense) to determine what element the marked number refers to. The numbers are marked with two underlines around them, like: _ number _. Your answer should be chosen from the given text, and should not contain other words."], "Positive Examples": [{"input": "Jess Mastriani: No, I don't want another crooler, thank you very much.\n FBI Agent Nicole Scott: But it's good for you. It's got... honeyglaze. Please die for this crooler, Jess.\n Jess Mastriani: I've had _ two _ already. Who eats three croolers in a night? \nFBI Agent Nicole Scott: Take a look. [Nicole takes a huge bite] Mmmmm, Mmmmm, Mmmmm!", "output": "crooler", "explanation": "In this example, the number two refers to the word: crooler."}, {"input": "Susan Ivanova:  Another lesson ?\nCaptain John Sheridan: Uh - huh .\nSusan Ivanova: What was this _ one _ about ?\nCaptain John Sheridan: Uh ... Beauty ... In the dark ...\nSusan Ivanova: Well ... They must be working . You 're beginning to sound just like a Vorlon .", "output": "lesson", "explanation": "From the first dialogue in this example, you can conclude that the number \"one\" refers to a lesson."}, {"input": "Catherine Willows:  Mouthing off to teachers , slipping grades , and now hitchhiking . I mean what 's next , Lindsey ?\nLindsey Willows: Stripping .\nCatherine Willows: What did you just say ? Okay , no phone , no friends , no nothing .\nLindsey Willows: For how long ?\nCatherine Willows: A month .\nLindsey Willows: Whatever .\nCatherine Willows: Hey , you want to make it _ two _ ?\nLindsey Willows: Dad always said you were a drama queen .\nCatherine Willows: Well , what do you expect , Lindsey , since he was always high .\nLindsey Willows: I 'd take Dad high over you any day ! Nana 's coming to pick me up . I 'll be out front .", "output": "month", "explanation": "The person is asking if their kid wants to make the punishment two months long, instead of one. So the word \"two\" is counting months"}], "Negative Examples": [{"input": "Josie:  So how many people have you killed ?\nMitchell: Dunno . It 's hard to say . More than a _ hundred _ , less than a thousand .", "output": "person", "explanation": "Although this answer is semantically correct, it can't be accepted, because the word \"person\" doesn't appear in the text. The correct answer would be \"people\"."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Dialogue"], "Instance": {"id": "task401-cffc6883bd934038b0bfea6359887aae", "input": "Danger Mouse:  I ca n't think what they 'll do with 99 bicycle clips . Eh , by the way , have we got 99 bicycle clips ?\nPenfold: Eh , we 've got eh , we 've got _ 3 _ , chief . Do you think that will do ?\nDanger Mouse: Hardly .\nPenfold: Ere , perhaps when they said ' bicycle clip ' , they met toothbrushes ?\nDanger Mouse: Yes , may ... Penfold , you 're pottier than they are !", "output": ["clips"]}, "Instance License": ["MIT"], "prediction": "toothbrush"}
+{"id": "task401-f39376392fa7428b8586860f55c39b4a", "Task": "task401_numeric_fused_head_reference", "Contributors": "['Pegah Alipoormolabashi']", "Source": ["numeric_fused_head"], "URL": ["https://github.com/yanaiela/num_fh"], "Categories": ["Coreference Resolution"], "Reasoning": ["Commonsense Reasoning -> Numerical Commonsense Reasoning"], "Definition": ["In this task, you will use your knowledge about language (and common sense) to determine what element the marked number refers to. The numbers are marked with two underlines around them, like: _ number _. Your answer should be chosen from the given text, and should not contain other words."], "Positive Examples": [{"input": "Jess Mastriani: No, I don't want another crooler, thank you very much.\n FBI Agent Nicole Scott: But it's good for you. It's got... honeyglaze. Please die for this crooler, Jess.\n Jess Mastriani: I've had _ two _ already. Who eats three croolers in a night? \nFBI Agent Nicole Scott: Take a look. [Nicole takes a huge bite] Mmmmm, Mmmmm, Mmmmm!", "output": "crooler", "explanation": "In this example, the number two refers to the word: crooler."}, {"input": "Susan Ivanova:  Another lesson ?\nCaptain John Sheridan: Uh - huh .\nSusan Ivanova: What was this _ one _ about ?\nCaptain John Sheridan: Uh ... Beauty ... In the dark ...\nSusan Ivanova: Well ... They must be working . You 're beginning to sound just like a Vorlon .", "output": "lesson", "explanation": "From the first dialogue in this example, you can conclude that the number \"one\" refers to a lesson."}, {"input": "Catherine Willows:  Mouthing off to teachers , slipping grades , and now hitchhiking . I mean what 's next , Lindsey ?\nLindsey Willows: Stripping .\nCatherine Willows: What did you just say ? Okay , no phone , no friends , no nothing .\nLindsey Willows: For how long ?\nCatherine Willows: A month .\nLindsey Willows: Whatever .\nCatherine Willows: Hey , you want to make it _ two _ ?\nLindsey Willows: Dad always said you were a drama queen .\nCatherine Willows: Well , what do you expect , Lindsey , since he was always high .\nLindsey Willows: I 'd take Dad high over you any day ! Nana 's coming to pick me up . I 'll be out front .", "output": "month", "explanation": "The person is asking if their kid wants to make the punishment two months long, instead of one. So the word \"two\" is counting months"}], "Negative Examples": [{"input": "Josie:  So how many people have you killed ?\nMitchell: Dunno . It 's hard to say . More than a _ hundred _ , less than a thousand .", "output": "person", "explanation": "Although this answer is semantically correct, it can't be accepted, because the word \"person\" doesn't appear in the text. The correct answer would be \"people\"."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Dialogue"], "Instance": {"id": "task401-f39376392fa7428b8586860f55c39b4a", "input": "Lily:  So that 's what happened to the bouquet . Well , good for Victoria , that 's an evil tradition .\nTed: So wait , you 're not gon na have _ one _ at your wedding ?\nLily: Hell , yeah , I 'm gon na throw that flower grenade and yell \" Crawl for it , Bitches ! \" It 's just what girls do .", "output": ["bouquet"]}, "Instance License": ["MIT"], "prediction": "bouquet"}
+{"id": "task401-8755a4205e1a4014beac2370d33d4bdb", "Task": "task401_numeric_fused_head_reference", "Contributors": "['Pegah Alipoormolabashi']", "Source": ["numeric_fused_head"], "URL": ["https://github.com/yanaiela/num_fh"], "Categories": ["Coreference Resolution"], "Reasoning": ["Commonsense Reasoning -> Numerical Commonsense Reasoning"], "Definition": ["In this task, you will use your knowledge about language (and common sense) to determine what element the marked number refers to. The numbers are marked with two underlines around them, like: _ number _. Your answer should be chosen from the given text, and should not contain other words."], "Positive Examples": [{"input": "Jess Mastriani: No, I don't want another crooler, thank you very much.\n FBI Agent Nicole Scott: But it's good for you. It's got... honeyglaze. Please die for this crooler, Jess.\n Jess Mastriani: I've had _ two _ already. Who eats three croolers in a night? \nFBI Agent Nicole Scott: Take a look. [Nicole takes a huge bite] Mmmmm, Mmmmm, Mmmmm!", "output": "crooler", "explanation": "In this example, the number two refers to the word: crooler."}, {"input": "Susan Ivanova:  Another lesson ?\nCaptain John Sheridan: Uh - huh .\nSusan Ivanova: What was this _ one _ about ?\nCaptain John Sheridan: Uh ... Beauty ... In the dark ...\nSusan Ivanova: Well ... They must be working . You 're beginning to sound just like a Vorlon .", "output": "lesson", "explanation": "From the first dialogue in this example, you can conclude that the number \"one\" refers to a lesson."}, {"input": "Catherine Willows:  Mouthing off to teachers , slipping grades , and now hitchhiking . I mean what 's next , Lindsey ?\nLindsey Willows: Stripping .\nCatherine Willows: What did you just say ? Okay , no phone , no friends , no nothing .\nLindsey Willows: For how long ?\nCatherine Willows: A month .\nLindsey Willows: Whatever .\nCatherine Willows: Hey , you want to make it _ two _ ?\nLindsey Willows: Dad always said you were a drama queen .\nCatherine Willows: Well , what do you expect , Lindsey , since he was always high .\nLindsey Willows: I 'd take Dad high over you any day ! Nana 's coming to pick me up . I 'll be out front .", "output": "month", "explanation": "The person is asking if their kid wants to make the punishment two months long, instead of one. So the word \"two\" is counting months"}], "Negative Examples": [{"input": "Josie:  So how many people have you killed ?\nMitchell: Dunno . It 's hard to say . More than a _ hundred _ , less than a thousand .", "output": "person", "explanation": "Although this answer is semantically correct, it can't be accepted, because the word \"person\" doesn't appear in the text. The correct answer would be \"people\"."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Dialogue"], "Instance": {"id": "task401-8755a4205e1a4014beac2370d33d4bdb", "input": "Hank Griffin:  How many rats ?\nNick Burkhardt: What ?\nHank Griffin: For the report , how many rats do you think were down there ?\nNick Burkhardt: Sorry , I did n't stop to count them .\nHank Griffin: I 'd like to put a _ million _ , 'cause that 's what it seemed like .\nNick Burkhardt: Put a thousand . Nobody 's gon na believe a million .\nHank Griffin: No one 's gon na believe a thousand .", "output": ["rats"]}, "Instance License": ["MIT"], "prediction": "report"}
+{"id": "task401-3663d16bc9fd422cbfb8f255e436878c", "Task": "task401_numeric_fused_head_reference", "Contributors": "['Pegah Alipoormolabashi']", "Source": ["numeric_fused_head"], "URL": ["https://github.com/yanaiela/num_fh"], "Categories": ["Coreference Resolution"], "Reasoning": ["Commonsense Reasoning -> Numerical Commonsense Reasoning"], "Definition": ["In this task, you will use your knowledge about language (and common sense) to determine what element the marked number refers to. The numbers are marked with two underlines around them, like: _ number _. Your answer should be chosen from the given text, and should not contain other words."], "Positive Examples": [{"input": "Jess Mastriani: No, I don't want another crooler, thank you very much.\n FBI Agent Nicole Scott: But it's good for you. It's got... honeyglaze. Please die for this crooler, Jess.\n Jess Mastriani: I've had _ two _ already. Who eats three croolers in a night? \nFBI Agent Nicole Scott: Take a look. [Nicole takes a huge bite] Mmmmm, Mmmmm, Mmmmm!", "output": "crooler", "explanation": "In this example, the number two refers to the word: crooler."}, {"input": "Susan Ivanova:  Another lesson ?\nCaptain John Sheridan: Uh - huh .\nSusan Ivanova: What was this _ one _ about ?\nCaptain John Sheridan: Uh ... Beauty ... In the dark ...\nSusan Ivanova: Well ... They must be working . You 're beginning to sound just like a Vorlon .", "output": "lesson", "explanation": "From the first dialogue in this example, you can conclude that the number \"one\" refers to a lesson."}, {"input": "Catherine Willows:  Mouthing off to teachers , slipping grades , and now hitchhiking . I mean what 's next , Lindsey ?\nLindsey Willows: Stripping .\nCatherine Willows: What did you just say ? Okay , no phone , no friends , no nothing .\nLindsey Willows: For how long ?\nCatherine Willows: A month .\nLindsey Willows: Whatever .\nCatherine Willows: Hey , you want to make it _ two _ ?\nLindsey Willows: Dad always said you were a drama queen .\nCatherine Willows: Well , what do you expect , Lindsey , since he was always high .\nLindsey Willows: I 'd take Dad high over you any day ! Nana 's coming to pick me up . I 'll be out front .", "output": "month", "explanation": "The person is asking if their kid wants to make the punishment two months long, instead of one. So the word \"two\" is counting months"}], "Negative Examples": [{"input": "Josie:  So how many people have you killed ?\nMitchell: Dunno . It 's hard to say . More than a _ hundred _ , less than a thousand .", "output": "person", "explanation": "Although this answer is semantically correct, it can't be accepted, because the word \"person\" doesn't appear in the text. The correct answer would be \"people\"."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Dialogue"], "Instance": {"id": "task401-3663d16bc9fd422cbfb8f255e436878c", "input": "Dr. Dustin Crenshaw:  Mrs. Draper is back for her 27th hospital admission status , post - pancreatic pseudocyst .\nDr. Neela Rasgotra: _ 27 _ ?\nDr. Dustin Crenshaw: Yes , somebody needs to tell her the hospital stopped giving out frequent - flier miles . Oh , and she 's a chronic rectal discomfort , and you two get to work her up and review her old charts .\nDr. Neela Rasgotra: All 27 ?\nDr. Dustin Crenshaw: No , why do n't you just forget all about visits 6 , 13 , and uh , what do you think , 21 ? Yeah , that should keep it interesting . It 'll be like playing patient roulette .", "output": ["status"]}, "Instance License": ["MIT"], "prediction": "27"}
+{"id": "task401-17ac244c2dd5447fa32d4ccf1b8a4936", "Task": "task401_numeric_fused_head_reference", "Contributors": "['Pegah Alipoormolabashi']", "Source": ["numeric_fused_head"], "URL": ["https://github.com/yanaiela/num_fh"], "Categories": ["Coreference Resolution"], "Reasoning": ["Commonsense Reasoning -> Numerical Commonsense Reasoning"], "Definition": ["In this task, you will use your knowledge about language (and common sense) to determine what element the marked number refers to. The numbers are marked with two underlines around them, like: _ number _. Your answer should be chosen from the given text, and should not contain other words."], "Positive Examples": [{"input": "Jess Mastriani: No, I don't want another crooler, thank you very much.\n FBI Agent Nicole Scott: But it's good for you. It's got... honeyglaze. Please die for this crooler, Jess.\n Jess Mastriani: I've had _ two _ already. Who eats three croolers in a night? \nFBI Agent Nicole Scott: Take a look. [Nicole takes a huge bite] Mmmmm, Mmmmm, Mmmmm!", "output": "crooler", "explanation": "In this example, the number two refers to the word: crooler."}, {"input": "Susan Ivanova:  Another lesson ?\nCaptain John Sheridan: Uh - huh .\nSusan Ivanova: What was this _ one _ about ?\nCaptain John Sheridan: Uh ... Beauty ... In the dark ...\nSusan Ivanova: Well ... They must be working . You 're beginning to sound just like a Vorlon .", "output": "lesson", "explanation": "From the first dialogue in this example, you can conclude that the number \"one\" refers to a lesson."}, {"input": "Catherine Willows:  Mouthing off to teachers , slipping grades , and now hitchhiking . I mean what 's next , Lindsey ?\nLindsey Willows: Stripping .\nCatherine Willows: What did you just say ? Okay , no phone , no friends , no nothing .\nLindsey Willows: For how long ?\nCatherine Willows: A month .\nLindsey Willows: Whatever .\nCatherine Willows: Hey , you want to make it _ two _ ?\nLindsey Willows: Dad always said you were a drama queen .\nCatherine Willows: Well , what do you expect , Lindsey , since he was always high .\nLindsey Willows: I 'd take Dad high over you any day ! Nana 's coming to pick me up . I 'll be out front .", "output": "month", "explanation": "The person is asking if their kid wants to make the punishment two months long, instead of one. So the word \"two\" is counting months"}], "Negative Examples": [{"input": "Josie:  So how many people have you killed ?\nMitchell: Dunno . It 's hard to say . More than a _ hundred _ , less than a thousand .", "output": "person", "explanation": "Although this answer is semantically correct, it can't be accepted, because the word \"person\" doesn't appear in the text. The correct answer would be \"people\"."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Dialogue"], "Instance": {"id": "task401-17ac244c2dd5447fa32d4ccf1b8a4936", "input": "Cory Matthews:  Topanga , I warned you not to ... ... Oh , boy , why 'd you have to wear that ?\nTopanga Lawrence: Because I 'm a damsel . But not the distressed kind . _ One _ who is very together and in complete control of her own destiny .", "output": ["damsel"]}, "Instance License": ["MIT"], "prediction": "One"}
+{"id": "task1598-206fec3617fa4e7a93655b6fc2e5ba5f", "Task": "task1598_nyc_long_text_generation", "Contributors": "['Abdullah Masud']", "Source": ["nyc"], "URL": ["https://nlds.soe.ucsc.edu/source-blending-NLG"], "Categories": ["Data to Text"], "Reasoning": [], "Definition": ["The task is to write a full sentence or two using all of the information given. The sentence(s) will be a brief review of a restaurant. Use all of the information provided."], "Positive Examples": [{"input": "name[xname], cuisine[Fast Food], rating[average], familyFriendly[yes], near[xnear]", "output": "Located near xnear, xname serves Fast food and is child friendly. its customer rating is: average.", "explanation": "This is a good example of the task because the written sentence uses all of the given information."}, {"input": "name[xname], cuisine[Chinese], price[less than \u00a320]", "output": "xname, Chinese restaurant,  prices from \u00a319.99", "explanation": "This is a good example. The output uses all of the given information."}, {"input": "name[xname], recommend[yes], cuisine[Vietnamese], qual[good], price[affordable]", "output": "I would suggest xname because it's affordable and a Vietnamese restaurant with nice food!", "explanation": "This is another good example because the sentence is a normal sentence that describes the restaurant and contains all of the given information."}], "Negative Examples": [{"input": "name[xname], recommend[yes], decor[good], qual[acceptable], service[good]", "output": "xname is a restaurant with poor service but acceptable food and good decor.", "explanation": "This is a bad example because the sentence does not match the given information (service is poor instead of good.) Also it is missing information about whether the restaurant is recommended or not."}, {"input": "name[xname], eattype[coffee shop], cuisine[Chinese], price[moderate], location[riverside], near[xnear]", "output": "xname is a Chinese coffee shop located in riverside near xnear.", "explanation": "This is a bad example because it does not include the price, thereby missing some information."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Public Places -> Restaurants", "Reviews -> Restaurants"], "Instance": {"id": "task1598-206fec3617fa4e7a93655b6fc2e5ba5f", "input": "name[xname], recommend[yes], qual[acceptable], location[Murray Hill]", "output": ["xname is the best place because it is in Murray Hill with adequate food."]}, "Instance License": ["Unknown"], "prediction": "xname is a recommended restaurant in Murray Hill."}
+{"id": "task1598-7c5b2fe7332f4e6b88e330e74994f0c1", "Task": "task1598_nyc_long_text_generation", "Contributors": "['Abdullah Masud']", "Source": ["nyc"], "URL": ["https://nlds.soe.ucsc.edu/source-blending-NLG"], "Categories": ["Data to Text"], "Reasoning": [], "Definition": ["The task is to write a full sentence or two using all of the information given. The sentence(s) will be a brief review of a restaurant. Use all of the information provided."], "Positive Examples": [{"input": "name[xname], cuisine[Fast Food], rating[average], familyFriendly[yes], near[xnear]", "output": "Located near xnear, xname serves Fast food and is child friendly. its customer rating is: average.", "explanation": "This is a good example of the task because the written sentence uses all of the given information."}, {"input": "name[xname], cuisine[Chinese], price[less than \u00a320]", "output": "xname, Chinese restaurant,  prices from \u00a319.99", "explanation": "This is a good example. The output uses all of the given information."}, {"input": "name[xname], recommend[yes], cuisine[Vietnamese], qual[good], price[affordable]", "output": "I would suggest xname because it's affordable and a Vietnamese restaurant with nice food!", "explanation": "This is another good example because the sentence is a normal sentence that describes the restaurant and contains all of the given information."}], "Negative Examples": [{"input": "name[xname], recommend[yes], decor[good], qual[acceptable], service[good]", "output": "xname is a restaurant with poor service but acceptable food and good decor.", "explanation": "This is a bad example because the sentence does not match the given information (service is poor instead of good.) Also it is missing information about whether the restaurant is recommended or not."}, {"input": "name[xname], eattype[coffee shop], cuisine[Chinese], price[moderate], location[riverside], near[xnear]", "output": "xname is a Chinese coffee shop located in riverside near xnear.", "explanation": "This is a bad example because it does not include the price, thereby missing some information."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Public Places -> Restaurants", "Reviews -> Restaurants"], "Instance": {"id": "task1598-7c5b2fe7332f4e6b88e330e74994f0c1", "input": "name[xname], recommend[yes], cuisine[Italian], decor[bad], qual[acceptable], location[Chinatown], price[affordable], service[bad]", "output": ["xname is the only restaurant I would suggest since it provides rude staff and bad ambiance. It is an Italian place with satisfying food. it's in Chinatown. xname is affordable."]}, "Instance License": ["Unknown"], "prediction": "xname is a Italian restaurant serving Italian food. its decor is unacceptable and service is unacceptable."}
+{"id": "task1598-482e8d1c80be4613a5eb2897abb9dcea", "Task": "task1598_nyc_long_text_generation", "Contributors": "['Abdullah Masud']", "Source": ["nyc"], "URL": ["https://nlds.soe.ucsc.edu/source-blending-NLG"], "Categories": ["Data to Text"], "Reasoning": [], "Definition": ["The task is to write a full sentence or two using all of the information given. The sentence(s) will be a brief review of a restaurant. Use all of the information provided."], "Positive Examples": [{"input": "name[xname], cuisine[Fast Food], rating[average], familyFriendly[yes], near[xnear]", "output": "Located near xnear, xname serves Fast food and is child friendly. its customer rating is: average.", "explanation": "This is a good example of the task because the written sentence uses all of the given information."}, {"input": "name[xname], cuisine[Chinese], price[less than \u00a320]", "output": "xname, Chinese restaurant,  prices from \u00a319.99", "explanation": "This is a good example. The output uses all of the given information."}, {"input": "name[xname], recommend[yes], cuisine[Vietnamese], qual[good], price[affordable]", "output": "I would suggest xname because it's affordable and a Vietnamese restaurant with nice food!", "explanation": "This is another good example because the sentence is a normal sentence that describes the restaurant and contains all of the given information."}], "Negative Examples": [{"input": "name[xname], recommend[yes], decor[good], qual[acceptable], service[good]", "output": "xname is a restaurant with poor service but acceptable food and good decor.", "explanation": "This is a bad example because the sentence does not match the given information (service is poor instead of good.) Also it is missing information about whether the restaurant is recommended or not."}, {"input": "name[xname], eattype[coffee shop], cuisine[Chinese], price[moderate], location[riverside], near[xnear]", "output": "xname is a Chinese coffee shop located in riverside near xnear.", "explanation": "This is a bad example because it does not include the price, thereby missing some information."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Public Places -> Restaurants", "Reviews -> Restaurants"], "Instance": {"id": "task1598-482e8d1c80be4613a5eb2897abb9dcea", "input": "name[xname], eattype[coffee shop], cuisine[Indian], price[\u00a320-25], rating[high], familyFriendly[yes]", "output": ["xname is a coffee shop that provides Indian food. The price range is \u00a320-25. It has a high customer rating and is kids friendly."]}, "Instance License": ["Unknown"], "prediction": "xname is a coffee shop and Indian restaurant. its customer rating is high."}
+{"id": "task1598-c2b840950256402d9f8955c009fa1ba4", "Task": "task1598_nyc_long_text_generation", "Contributors": "['Abdullah Masud']", "Source": ["nyc"], "URL": ["https://nlds.soe.ucsc.edu/source-blending-NLG"], "Categories": ["Data to Text"], "Reasoning": [], "Definition": ["The task is to write a full sentence or two using all of the information given. The sentence(s) will be a brief review of a restaurant. Use all of the information provided."], "Positive Examples": [{"input": "name[xname], cuisine[Fast Food], rating[average], familyFriendly[yes], near[xnear]", "output": "Located near xnear, xname serves Fast food and is child friendly. its customer rating is: average.", "explanation": "This is a good example of the task because the written sentence uses all of the given information."}, {"input": "name[xname], cuisine[Chinese], price[less than \u00a320]", "output": "xname, Chinese restaurant,  prices from \u00a319.99", "explanation": "This is a good example. The output uses all of the given information."}, {"input": "name[xname], recommend[yes], cuisine[Vietnamese], qual[good], price[affordable]", "output": "I would suggest xname because it's affordable and a Vietnamese restaurant with nice food!", "explanation": "This is another good example because the sentence is a normal sentence that describes the restaurant and contains all of the given information."}], "Negative Examples": [{"input": "name[xname], recommend[yes], decor[good], qual[acceptable], service[good]", "output": "xname is a restaurant with poor service but acceptable food and good decor.", "explanation": "This is a bad example because the sentence does not match the given information (service is poor instead of good.) Also it is missing information about whether the restaurant is recommended or not."}, {"input": "name[xname], eattype[coffee shop], cuisine[Chinese], price[moderate], location[riverside], near[xnear]", "output": "xname is a Chinese coffee shop located in riverside near xnear.", "explanation": "This is a bad example because it does not include the price, thereby missing some information."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Public Places -> Restaurants", "Reviews -> Restaurants"], "Instance": {"id": "task1598-c2b840950256402d9f8955c009fa1ba4", "input": "name[xname], cuisine[Chinese], price[more than \u00a330], familyFriendly[yes], near[xnear]", "output": ["Located near xnear, xname Chinese restaurant is child friendly but be prepared to pay more than 30 British pounds."]}, "Instance License": ["Unknown"], "prediction": "xname Chinese restaurant is located near xnear. its customer rating is: family friendly."}
+{"id": "task1598-5996ee193ab749d5b4b1a738c0f36889", "Task": "task1598_nyc_long_text_generation", "Contributors": "['Abdullah Masud']", "Source": ["nyc"], "URL": ["https://nlds.soe.ucsc.edu/source-blending-NLG"], "Categories": ["Data to Text"], "Reasoning": [], "Definition": ["The task is to write a full sentence or two using all of the information given. The sentence(s) will be a brief review of a restaurant. Use all of the information provided."], "Positive Examples": [{"input": "name[xname], cuisine[Fast Food], rating[average], familyFriendly[yes], near[xnear]", "output": "Located near xnear, xname serves Fast food and is child friendly. its customer rating is: average.", "explanation": "This is a good example of the task because the written sentence uses all of the given information."}, {"input": "name[xname], cuisine[Chinese], price[less than \u00a320]", "output": "xname, Chinese restaurant,  prices from \u00a319.99", "explanation": "This is a good example. The output uses all of the given information."}, {"input": "name[xname], recommend[yes], cuisine[Vietnamese], qual[good], price[affordable]", "output": "I would suggest xname because it's affordable and a Vietnamese restaurant with nice food!", "explanation": "This is another good example because the sentence is a normal sentence that describes the restaurant and contains all of the given information."}], "Negative Examples": [{"input": "name[xname], recommend[yes], decor[good], qual[acceptable], service[good]", "output": "xname is a restaurant with poor service but acceptable food and good decor.", "explanation": "This is a bad example because the sentence does not match the given information (service is poor instead of good.) Also it is missing information about whether the restaurant is recommended or not."}, {"input": "name[xname], eattype[coffee shop], cuisine[Chinese], price[moderate], location[riverside], near[xnear]", "output": "xname is a Chinese coffee shop located in riverside near xnear.", "explanation": "This is a bad example because it does not include the price, thereby missing some information."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Public Places -> Restaurants", "Reviews -> Restaurants"], "Instance": {"id": "task1598-5996ee193ab749d5b4b1a738c0f36889", "input": "name[xname], cuisine[Indian], location[city centre], familyFriendly[yes]", "output": ["xname provides Indian food It is located in the city centre."]}, "Instance License": ["Unknown"], "prediction": "xname is a Indian restaurant in the city centre. its customer rating is: family friendly."}
+{"id": "task1615-11e57fb93c4a4a6d83ff1124cd1297a7", "Task": "task1615_sick_tclassify_b_relation_a", "Contributors": "['Venkata Sesha Sree Vidya Akkiraju']", "Source": ["sick"], "URL": ["https://huggingface.co/datasets/sick"], "Categories": ["Textual Entailment"], "Reasoning": ["Textual Entailment -> Deductive Reasoning"], "Definition": ["In this task, given 2 input sentences, you must classify the relation between them. If the second sentence has a similar meaning to that of the first sentence then the output is ' B_entails_A', if the second sentence has the opposite meaning to the first sentence then it is classified as ' B_contradicts_A'. If you cannot clearly ascertain agreement/disagreement between the two sentences, the label is ' B_neutral_A'."], "Positive Examples": [{"input": "sentence_A: man is wearing a hard hat and dancing. sentence_B: There is no man with a hard hat dancing.", "output": "B_contradicts_A", "explanation": "The sentence B has opposite meaning as sentence_B says, \"No man with a hat\", but sentence_A says, \"A man is wearing a hat\", so B is contradicting A."}, {"input": "sentence_A: A baby is crying. sentence_B: A man is exercising.", "output": "B_neutral_A", "explanation": "Sentence B says exercising but sentence A says crying, which are two different tasks and is not contradicting as they don't have the opposite meaning, so B_neutral_A."}, {"input": "sentence_A: A tiger is pacing around a cage. sentence_B: A tiger is walking around a cage", "output": "B_entails_A", "explanation": "Walking and pacing are synonyms, so B_entails_A is correct."}], "Negative Examples": [{"input": "sentence_A: There is no man playing an instrument. sentence_B: A man is playing an instrument.", "output": "B_neutral_A", "explanation": "B says man is playing an instrument, while A says no man is playing, so this is a contradiction not neutral."}, {"input": "sentence_A: A man is walking slowly across a rope bridge sentence_B: A boy is fearfully walking across a bridge", "output": "B_entails_A", "explanation": "Fearfully and walking slowly are different meanings and not same, they are not even opposite words, so this is B_Neutral_A, not B_entails_A."}, {"input": "sentence_A: A lady is mixing a meat mixture in a bowl sentence_B: The woman is stirring meat in a bowl", "output": "B_contradicts_A", "explanation": "Stirring meat and mixing meat are synonyms, so this is B_entails_A, not B_Contradicts_A."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Captions -> Video Captions", "Captions -> Image Captions"], "Instance": {"id": "task1615-11e57fb93c4a4a6d83ff1124cd1297a7", "input": "sentence_A: A woman is coating a pork chop. sentence_B: A cook is coating a pork chop", "output": ["B_neutral_A"]}, "Instance License": ["CC BY-NC-SA 3.0"], "prediction": "B_entails_A"}
+{"id": "task1615-90f51520d8594027bbf9d84ed66e9a87", "Task": "task1615_sick_tclassify_b_relation_a", "Contributors": "['Venkata Sesha Sree Vidya Akkiraju']", "Source": ["sick"], "URL": ["https://huggingface.co/datasets/sick"], "Categories": ["Textual Entailment"], "Reasoning": ["Textual Entailment -> Deductive Reasoning"], "Definition": ["In this task, given 2 input sentences, you must classify the relation between them. If the second sentence has a similar meaning to that of the first sentence then the output is ' B_entails_A', if the second sentence has the opposite meaning to the first sentence then it is classified as ' B_contradicts_A'. If you cannot clearly ascertain agreement/disagreement between the two sentences, the label is ' B_neutral_A'."], "Positive Examples": [{"input": "sentence_A: man is wearing a hard hat and dancing. sentence_B: There is no man with a hard hat dancing.", "output": "B_contradicts_A", "explanation": "The sentence B has opposite meaning as sentence_B says, \"No man with a hat\", but sentence_A says, \"A man is wearing a hat\", so B is contradicting A."}, {"input": "sentence_A: A baby is crying. sentence_B: A man is exercising.", "output": "B_neutral_A", "explanation": "Sentence B says exercising but sentence A says crying, which are two different tasks and is not contradicting as they don't have the opposite meaning, so B_neutral_A."}, {"input": "sentence_A: A tiger is pacing around a cage. sentence_B: A tiger is walking around a cage", "output": "B_entails_A", "explanation": "Walking and pacing are synonyms, so B_entails_A is correct."}], "Negative Examples": [{"input": "sentence_A: There is no man playing an instrument. sentence_B: A man is playing an instrument.", "output": "B_neutral_A", "explanation": "B says man is playing an instrument, while A says no man is playing, so this is a contradiction not neutral."}, {"input": "sentence_A: A man is walking slowly across a rope bridge sentence_B: A boy is fearfully walking across a bridge", "output": "B_entails_A", "explanation": "Fearfully and walking slowly are different meanings and not same, they are not even opposite words, so this is B_Neutral_A, not B_entails_A."}, {"input": "sentence_A: A lady is mixing a meat mixture in a bowl sentence_B: The woman is stirring meat in a bowl", "output": "B_contradicts_A", "explanation": "Stirring meat and mixing meat are synonyms, so this is B_entails_A, not B_Contradicts_A."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Captions -> Video Captions", "Captions -> Image Captions"], "Instance": {"id": "task1615-90f51520d8594027bbf9d84ed66e9a87", "input": "sentence_A: A woman is cutting a tomato. sentence_B: A woman is slicing a tomato", "output": ["B_entails_A"]}, "Instance License": ["CC BY-NC-SA 3.0"], "prediction": "B_entails_A"}
+{"id": "task1615-4584884377cb43e5945194d051ddf2ea", "Task": "task1615_sick_tclassify_b_relation_a", "Contributors": "['Venkata Sesha Sree Vidya Akkiraju']", "Source": ["sick"], "URL": ["https://huggingface.co/datasets/sick"], "Categories": ["Textual Entailment"], "Reasoning": ["Textual Entailment -> Deductive Reasoning"], "Definition": ["In this task, given 2 input sentences, you must classify the relation between them. If the second sentence has a similar meaning to that of the first sentence then the output is ' B_entails_A', if the second sentence has the opposite meaning to the first sentence then it is classified as ' B_contradicts_A'. If you cannot clearly ascertain agreement/disagreement between the two sentences, the label is ' B_neutral_A'."], "Positive Examples": [{"input": "sentence_A: man is wearing a hard hat and dancing. sentence_B: There is no man with a hard hat dancing.", "output": "B_contradicts_A", "explanation": "The sentence B has opposite meaning as sentence_B says, \"No man with a hat\", but sentence_A says, \"A man is wearing a hat\", so B is contradicting A."}, {"input": "sentence_A: A baby is crying. sentence_B: A man is exercising.", "output": "B_neutral_A", "explanation": "Sentence B says exercising but sentence A says crying, which are two different tasks and is not contradicting as they don't have the opposite meaning, so B_neutral_A."}, {"input": "sentence_A: A tiger is pacing around a cage. sentence_B: A tiger is walking around a cage", "output": "B_entails_A", "explanation": "Walking and pacing are synonyms, so B_entails_A is correct."}], "Negative Examples": [{"input": "sentence_A: There is no man playing an instrument. sentence_B: A man is playing an instrument.", "output": "B_neutral_A", "explanation": "B says man is playing an instrument, while A says no man is playing, so this is a contradiction not neutral."}, {"input": "sentence_A: A man is walking slowly across a rope bridge sentence_B: A boy is fearfully walking across a bridge", "output": "B_entails_A", "explanation": "Fearfully and walking slowly are different meanings and not same, they are not even opposite words, so this is B_Neutral_A, not B_entails_A."}, {"input": "sentence_A: A lady is mixing a meat mixture in a bowl sentence_B: The woman is stirring meat in a bowl", "output": "B_contradicts_A", "explanation": "Stirring meat and mixing meat are synonyms, so this is B_entails_A, not B_Contradicts_A."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Captions -> Video Captions", "Captions -> Image Captions"], "Instance": {"id": "task1615-4584884377cb43e5945194d051ddf2ea", "input": "sentence_A: A boy is knocking a dog with a bottle of water. sentence_B: The dog is knocking a boy into the water", "output": ["B_neutral_A"]}, "Instance License": ["CC BY-NC-SA 3.0"], "prediction": "B_entails_A"}
+{"id": "task1615-17f070024c4440aeaec56bda5ab1ba38", "Task": "task1615_sick_tclassify_b_relation_a", "Contributors": "['Venkata Sesha Sree Vidya Akkiraju']", "Source": ["sick"], "URL": ["https://huggingface.co/datasets/sick"], "Categories": ["Textual Entailment"], "Reasoning": ["Textual Entailment -> Deductive Reasoning"], "Definition": ["In this task, given 2 input sentences, you must classify the relation between them. If the second sentence has a similar meaning to that of the first sentence then the output is ' B_entails_A', if the second sentence has the opposite meaning to the first sentence then it is classified as ' B_contradicts_A'. If you cannot clearly ascertain agreement/disagreement between the two sentences, the label is ' B_neutral_A'."], "Positive Examples": [{"input": "sentence_A: man is wearing a hard hat and dancing. sentence_B: There is no man with a hard hat dancing.", "output": "B_contradicts_A", "explanation": "The sentence B has opposite meaning as sentence_B says, \"No man with a hat\", but sentence_A says, \"A man is wearing a hat\", so B is contradicting A."}, {"input": "sentence_A: A baby is crying. sentence_B: A man is exercising.", "output": "B_neutral_A", "explanation": "Sentence B says exercising but sentence A says crying, which are two different tasks and is not contradicting as they don't have the opposite meaning, so B_neutral_A."}, {"input": "sentence_A: A tiger is pacing around a cage. sentence_B: A tiger is walking around a cage", "output": "B_entails_A", "explanation": "Walking and pacing are synonyms, so B_entails_A is correct."}], "Negative Examples": [{"input": "sentence_A: There is no man playing an instrument. sentence_B: A man is playing an instrument.", "output": "B_neutral_A", "explanation": "B says man is playing an instrument, while A says no man is playing, so this is a contradiction not neutral."}, {"input": "sentence_A: A man is walking slowly across a rope bridge sentence_B: A boy is fearfully walking across a bridge", "output": "B_entails_A", "explanation": "Fearfully and walking slowly are different meanings and not same, they are not even opposite words, so this is B_Neutral_A, not B_entails_A."}, {"input": "sentence_A: A lady is mixing a meat mixture in a bowl sentence_B: The woman is stirring meat in a bowl", "output": "B_contradicts_A", "explanation": "Stirring meat and mixing meat are synonyms, so this is B_entails_A, not B_Contradicts_A."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Captions -> Video Captions", "Captions -> Image Captions"], "Instance": {"id": "task1615-17f070024c4440aeaec56bda5ab1ba38", "input": "sentence_A: A woman is standing near three children. sentence_B: There is no woman standing near three children", "output": ["B_contradicts_A"]}, "Instance License": ["CC BY-NC-SA 3.0"], "prediction": "B_contradicts_A"}
+{"id": "task1615-cb82f8ea5d194d01b65a5500a8c8e70b", "Task": "task1615_sick_tclassify_b_relation_a", "Contributors": "['Venkata Sesha Sree Vidya Akkiraju']", "Source": ["sick"], "URL": ["https://huggingface.co/datasets/sick"], "Categories": ["Textual Entailment"], "Reasoning": ["Textual Entailment -> Deductive Reasoning"], "Definition": ["In this task, given 2 input sentences, you must classify the relation between them. If the second sentence has a similar meaning to that of the first sentence then the output is ' B_entails_A', if the second sentence has the opposite meaning to the first sentence then it is classified as ' B_contradicts_A'. If you cannot clearly ascertain agreement/disagreement between the two sentences, the label is ' B_neutral_A'."], "Positive Examples": [{"input": "sentence_A: man is wearing a hard hat and dancing. sentence_B: There is no man with a hard hat dancing.", "output": "B_contradicts_A", "explanation": "The sentence B has opposite meaning as sentence_B says, \"No man with a hat\", but sentence_A says, \"A man is wearing a hat\", so B is contradicting A."}, {"input": "sentence_A: A baby is crying. sentence_B: A man is exercising.", "output": "B_neutral_A", "explanation": "Sentence B says exercising but sentence A says crying, which are two different tasks and is not contradicting as they don't have the opposite meaning, so B_neutral_A."}, {"input": "sentence_A: A tiger is pacing around a cage. sentence_B: A tiger is walking around a cage", "output": "B_entails_A", "explanation": "Walking and pacing are synonyms, so B_entails_A is correct."}], "Negative Examples": [{"input": "sentence_A: There is no man playing an instrument. sentence_B: A man is playing an instrument.", "output": "B_neutral_A", "explanation": "B says man is playing an instrument, while A says no man is playing, so this is a contradiction not neutral."}, {"input": "sentence_A: A man is walking slowly across a rope bridge sentence_B: A boy is fearfully walking across a bridge", "output": "B_entails_A", "explanation": "Fearfully and walking slowly are different meanings and not same, they are not even opposite words, so this is B_Neutral_A, not B_entails_A."}, {"input": "sentence_A: A lady is mixing a meat mixture in a bowl sentence_B: The woman is stirring meat in a bowl", "output": "B_contradicts_A", "explanation": "Stirring meat and mixing meat are synonyms, so this is B_entails_A, not B_Contradicts_A."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Captions -> Video Captions", "Captions -> Image Captions"], "Instance": {"id": "task1615-cb82f8ea5d194d01b65a5500a8c8e70b", "input": "sentence_A: A man is jumping a wall. sentence_B: A man is standing in front of a wall", "output": ["B_contradicts_A"]}, "Instance License": ["CC BY-NC-SA 3.0"], "prediction": "B_entails_A"}
+{"id": "task970-52ff5e21e27742aa9bdcdf07f6445da1", "Task": "task970_sherliic_causal_relationship", "Contributors": "['Krima Doshi', 'Swaroop']", "Source": ["sherliic"], "URL": ["http://cistern.cis.lmu.de/SherLIiC/"], "Categories": ["Textual Entailment"], "Reasoning": ["Textual Entailment -> Deductive Reasoning"], "Definition": ["In this task, you will be given two sentences sentence1 and sentence2. You should decide whether the second sentence is entailed(agreed) by the first sentence. If it does entail, answer \"yes\", else answer \"no\"."], "Positive Examples": [{"input": "sentence1:region is nation in location\nsentence2:region is country in location", "output": "yes", "explanation": "A nation is a community of people of similar characteristics/descent with a common government. A country is a region sharing a common government. Hence, a nation can be defined as a country."}, {"input": "sentence1:location is going to war with region sentence1:location is facing  region ", "output": "yes", "explanation": "Both sentences have the same meaning. So the second sentence entails the first sentence."}, {"input": "sentence1:person is calling  location\nsentence2:person is urging  location", "output": "no", "explanation": "Calling a location does not mean urging it."}], "Negative Examples": [{"input": "sentence1:award_winner is edging  employer\nsentence2:award_winner is winning over employer", "output": "Incorrect", "explanation": "Answer expected is either \"yes\" or \"no\""}, {"input": "sentence1:award_nominee is finishing in sports.sports_league\nsentence2:award_nominee is teaming in sports.sports_league", "output": "yes", "explanation": "Finishing in a sport means a person or team is competing in it, while teaming means participating in a team. A sportsperson may finishing in a solo event (with no teams) as well, hence correct answer here is no."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Formal logic"], "Instance": {"id": "task970-52ff5e21e27742aa9bdcdf07f6445da1", "input": "sentence1:employer is eliminating  sports_team*professional_sports_team sentence1:employer is hosting  sports_team*professional_sports_team ", "output": ["no"]}, "Instance License": ["CC BY 4.0"], "prediction": "no"}
+{"id": "task970-6afa615e848f4d4fb3877427fc8464e6", "Task": "task970_sherliic_causal_relationship", "Contributors": "['Krima Doshi', 'Swaroop']", "Source": ["sherliic"], "URL": ["http://cistern.cis.lmu.de/SherLIiC/"], "Categories": ["Textual Entailment"], "Reasoning": ["Textual Entailment -> Deductive Reasoning"], "Definition": ["In this task, you will be given two sentences sentence1 and sentence2. You should decide whether the second sentence is entailed(agreed) by the first sentence. If it does entail, answer \"yes\", else answer \"no\"."], "Positive Examples": [{"input": "sentence1:region is nation in location\nsentence2:region is country in location", "output": "yes", "explanation": "A nation is a community of people of similar characteristics/descent with a common government. A country is a region sharing a common government. Hence, a nation can be defined as a country."}, {"input": "sentence1:location is going to war with region sentence1:location is facing  region ", "output": "yes", "explanation": "Both sentences have the same meaning. So the second sentence entails the first sentence."}, {"input": "sentence1:person is calling  location\nsentence2:person is urging  location", "output": "no", "explanation": "Calling a location does not mean urging it."}], "Negative Examples": [{"input": "sentence1:award_winner is edging  employer\nsentence2:award_winner is winning over employer", "output": "Incorrect", "explanation": "Answer expected is either \"yes\" or \"no\""}, {"input": "sentence1:award_nominee is finishing in sports.sports_league\nsentence2:award_nominee is teaming in sports.sports_league", "output": "yes", "explanation": "Finishing in a sport means a person or team is competing in it, while teaming means participating in a team. A sportsperson may finishing in a solo event (with no teams) as well, hence correct answer here is no."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Formal logic"], "Instance": {"id": "task970-6afa615e848f4d4fb3877427fc8464e6", "input": "sentence1:person is elected President of location sentence1:person is leading  location ", "output": ["yes"]}, "Instance License": ["CC BY 4.0"], "prediction": "yes"}
+{"id": "task970-7ff464ed44fc43c6a8056eb55e80a3de", "Task": "task970_sherliic_causal_relationship", "Contributors": "['Krima Doshi', 'Swaroop']", "Source": ["sherliic"], "URL": ["http://cistern.cis.lmu.de/SherLIiC/"], "Categories": ["Textual Entailment"], "Reasoning": ["Textual Entailment -> Deductive Reasoning"], "Definition": ["In this task, you will be given two sentences sentence1 and sentence2. You should decide whether the second sentence is entailed(agreed) by the first sentence. If it does entail, answer \"yes\", else answer \"no\"."], "Positive Examples": [{"input": "sentence1:region is nation in location\nsentence2:region is country in location", "output": "yes", "explanation": "A nation is a community of people of similar characteristics/descent with a common government. A country is a region sharing a common government. Hence, a nation can be defined as a country."}, {"input": "sentence1:location is going to war with region sentence1:location is facing  region ", "output": "yes", "explanation": "Both sentences have the same meaning. So the second sentence entails the first sentence."}, {"input": "sentence1:person is calling  location\nsentence2:person is urging  location", "output": "no", "explanation": "Calling a location does not mean urging it."}], "Negative Examples": [{"input": "sentence1:award_winner is edging  employer\nsentence2:award_winner is winning over employer", "output": "Incorrect", "explanation": "Answer expected is either \"yes\" or \"no\""}, {"input": "sentence1:award_nominee is finishing in sports.sports_league\nsentence2:award_nominee is teaming in sports.sports_league", "output": "yes", "explanation": "Finishing in a sport means a person or team is competing in it, while teaming means participating in a team. A sportsperson may finishing in a solo event (with no teams) as well, hence correct answer here is no."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Formal logic"], "Instance": {"id": "task970-7ff464ed44fc43c6a8056eb55e80a3de", "input": "sentence1:award_winner is unveiling at time.recurring_event sentence1:award_winner announces At time.recurring_event ", "output": ["yes"]}, "Instance License": ["CC BY 4.0"], "prediction": "yes"}
+{"id": "task970-cb348d79023a4b88984b91378873b22d", "Task": "task970_sherliic_causal_relationship", "Contributors": "['Krima Doshi', 'Swaroop']", "Source": ["sherliic"], "URL": ["http://cistern.cis.lmu.de/SherLIiC/"], "Categories": ["Textual Entailment"], "Reasoning": ["Textual Entailment -> Deductive Reasoning"], "Definition": ["In this task, you will be given two sentences sentence1 and sentence2. You should decide whether the second sentence is entailed(agreed) by the first sentence. If it does entail, answer \"yes\", else answer \"no\"."], "Positive Examples": [{"input": "sentence1:region is nation in location\nsentence2:region is country in location", "output": "yes", "explanation": "A nation is a community of people of similar characteristics/descent with a common government. A country is a region sharing a common government. Hence, a nation can be defined as a country."}, {"input": "sentence1:location is going to war with region sentence1:location is facing  region ", "output": "yes", "explanation": "Both sentences have the same meaning. So the second sentence entails the first sentence."}, {"input": "sentence1:person is calling  location\nsentence2:person is urging  location", "output": "no", "explanation": "Calling a location does not mean urging it."}], "Negative Examples": [{"input": "sentence1:award_winner is edging  employer\nsentence2:award_winner is winning over employer", "output": "Incorrect", "explanation": "Answer expected is either \"yes\" or \"no\""}, {"input": "sentence1:award_nominee is finishing in sports.sports_league\nsentence2:award_nominee is teaming in sports.sports_league", "output": "yes", "explanation": "Finishing in a sport means a person or team is competing in it, while teaming means participating in a team. A sportsperson may finishing in a solo event (with no teams) as well, hence correct answer here is no."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Formal logic"], "Instance": {"id": "task970-cb348d79023a4b88984b91378873b22d", "input": "sentence1:organization is cancelling  award.award_winning_work sentence1:award.award_winning_work is airing on organization ", "output": ["no"]}, "Instance License": ["CC BY 4.0"], "prediction": "no"}
+{"id": "task970-e4efd9bfa47d45139e459cf12dd962e2", "Task": "task970_sherliic_causal_relationship", "Contributors": "['Krima Doshi', 'Swaroop']", "Source": ["sherliic"], "URL": ["http://cistern.cis.lmu.de/SherLIiC/"], "Categories": ["Textual Entailment"], "Reasoning": ["Textual Entailment -> Deductive Reasoning"], "Definition": ["In this task, you will be given two sentences sentence1 and sentence2. You should decide whether the second sentence is entailed(agreed) by the first sentence. If it does entail, answer \"yes\", else answer \"no\"."], "Positive Examples": [{"input": "sentence1:region is nation in location\nsentence2:region is country in location", "output": "yes", "explanation": "A nation is a community of people of similar characteristics/descent with a common government. A country is a region sharing a common government. Hence, a nation can be defined as a country."}, {"input": "sentence1:location is going to war with region sentence1:location is facing  region ", "output": "yes", "explanation": "Both sentences have the same meaning. So the second sentence entails the first sentence."}, {"input": "sentence1:person is calling  location\nsentence2:person is urging  location", "output": "no", "explanation": "Calling a location does not mean urging it."}], "Negative Examples": [{"input": "sentence1:award_winner is edging  employer\nsentence2:award_winner is winning over employer", "output": "Incorrect", "explanation": "Answer expected is either \"yes\" or \"no\""}, {"input": "sentence1:award_nominee is finishing in sports.sports_league\nsentence2:award_nominee is teaming in sports.sports_league", "output": "yes", "explanation": "Finishing in a sport means a person or team is competing in it, while teaming means participating in a team. A sportsperson may finishing in a solo event (with no teams) as well, hence correct answer here is no."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Formal logic"], "Instance": {"id": "task970-e4efd9bfa47d45139e459cf12dd962e2", "input": "sentence1:employer is dominating  location sentence1:employer is taking  location ", "output": ["yes"]}, "Instance License": ["CC BY 4.0"], "prediction": "yes"}
+{"id": "task1390-015832aca1b54342ae5a87f709ea7e2c", "Task": "task1390_wscfixed_coreference", "Contributors": "['Yeganeh Kordi']", "Source": ["wsc_fiexed"], "URL": ["https://huggingface.co/datasets/super_glue"], "Categories": ["Coreference Resolution"], "Reasoning": ["Commonsense Reasoning"], "Definition": ["You are given a context, a pronoun, and a noun in this task. The given pronoun is shown in the context within parentheses. You should determine if the pronoun refers to the given noun or not. Please answer with \"True\" and \"False\"."], "Positive Examples": [{"input": "Sam pulled up a chair to the piano , but (it) was broken, so he had to sing instead. <sep> Pronoun:it <sep> Noun: the piano", "output": "True", "explanation": "This is a good example. In this context, he had to sing after recognizing it was broken. So, it refers to the piano."}, {"input": "Fred covered his eyes with his hands , because the wind was blowing sand around. He lowered (them) when the wind stopped. <sep> Pronoun:them <sep> Noun: his eyes", "output": "False", "explanation": "In this example, he lowered his hands when the wind stopped. So, them refer to his hands, and the output should be \"False\"."}, {"input": "Our mistress hired a room for my crippled sister Nelly , and she gave (her) knitting and needlework when she was able to do it, and when she was ill she sent her dinners and many nice comfortable things and was like a mother to her. <sep> Pronoun:her <sep> Noun: Nelly", "output": "True", "explanation": "In this example, her refers to Nelly. So, the given noun is correct, and the output should be \"True\"."}], "Negative Examples": [{"input": "Jim yelled at Kevin because (he) was so upset. <sep> Pronoun:he <sep> Noun: Kevin", "output": "True", "explanation": "In this example, he refers to Jim. So, kevin is incorrect, and the output should be \"False\"."}, {"input": "Meanwhile, in the forest, the elephants are calling and hunting high and low for Arthur and Celeste , and their mothers are very worried. Fortunately, in flying over the town, an old marabou bird has seen (them) and come back quickly to tell the news. <sep> Pronoun:them <sep> Noun: Arthur and Celeste", "output": "False", "explanation": "In this example, them refer to Arthur and Celeste. So, the output should be \"True\"."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Fiction", "Books"], "Instance": {"id": "task1390-015832aca1b54342ae5a87f709ea7e2c", "input": "The woman held the girl against (her) will. <sep> Pronoun:her <sep> Noun: The woman", "output": ["False"]}, "Instance License": ["CC BY 4.0"], "prediction": "True"}
+{"id": "task1390-8779c02c28c04d9c80fccbd1ed3b012b", "Task": "task1390_wscfixed_coreference", "Contributors": "['Yeganeh Kordi']", "Source": ["wsc_fiexed"], "URL": ["https://huggingface.co/datasets/super_glue"], "Categories": ["Coreference Resolution"], "Reasoning": ["Commonsense Reasoning"], "Definition": ["You are given a context, a pronoun, and a noun in this task. The given pronoun is shown in the context within parentheses. You should determine if the pronoun refers to the given noun or not. Please answer with \"True\" and \"False\"."], "Positive Examples": [{"input": "Sam pulled up a chair to the piano , but (it) was broken, so he had to sing instead. <sep> Pronoun:it <sep> Noun: the piano", "output": "True", "explanation": "This is a good example. In this context, he had to sing after recognizing it was broken. So, it refers to the piano."}, {"input": "Fred covered his eyes with his hands , because the wind was blowing sand around. He lowered (them) when the wind stopped. <sep> Pronoun:them <sep> Noun: his eyes", "output": "False", "explanation": "In this example, he lowered his hands when the wind stopped. So, them refer to his hands, and the output should be \"False\"."}, {"input": "Our mistress hired a room for my crippled sister Nelly , and she gave (her) knitting and needlework when she was able to do it, and when she was ill she sent her dinners and many nice comfortable things and was like a mother to her. <sep> Pronoun:her <sep> Noun: Nelly", "output": "True", "explanation": "In this example, her refers to Nelly. So, the given noun is correct, and the output should be \"True\"."}], "Negative Examples": [{"input": "Jim yelled at Kevin because (he) was so upset. <sep> Pronoun:he <sep> Noun: Kevin", "output": "True", "explanation": "In this example, he refers to Jim. So, kevin is incorrect, and the output should be \"False\"."}, {"input": "Meanwhile, in the forest, the elephants are calling and hunting high and low for Arthur and Celeste , and their mothers are very worried. Fortunately, in flying over the town, an old marabou bird has seen (them) and come back quickly to tell the news. <sep> Pronoun:them <sep> Noun: Arthur and Celeste", "output": "False", "explanation": "In this example, them refer to Arthur and Celeste. So, the output should be \"True\"."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Fiction", "Books"], "Instance": {"id": "task1390-8779c02c28c04d9c80fccbd1ed3b012b", "input": "Anne gave birth to a daughter last month. (She) is a very charming woman. <sep> Pronoun:She <sep> Noun: Anne", "output": ["True"]}, "Instance License": ["CC BY 4.0"], "prediction": "True"}
+{"id": "task1390-4c1b834a738c432f9ffe4e3751fb124a", "Task": "task1390_wscfixed_coreference", "Contributors": "['Yeganeh Kordi']", "Source": ["wsc_fiexed"], "URL": ["https://huggingface.co/datasets/super_glue"], "Categories": ["Coreference Resolution"], "Reasoning": ["Commonsense Reasoning"], "Definition": ["You are given a context, a pronoun, and a noun in this task. The given pronoun is shown in the context within parentheses. You should determine if the pronoun refers to the given noun or not. Please answer with \"True\" and \"False\"."], "Positive Examples": [{"input": "Sam pulled up a chair to the piano , but (it) was broken, so he had to sing instead. <sep> Pronoun:it <sep> Noun: the piano", "output": "True", "explanation": "This is a good example. In this context, he had to sing after recognizing it was broken. So, it refers to the piano."}, {"input": "Fred covered his eyes with his hands , because the wind was blowing sand around. He lowered (them) when the wind stopped. <sep> Pronoun:them <sep> Noun: his eyes", "output": "False", "explanation": "In this example, he lowered his hands when the wind stopped. So, them refer to his hands, and the output should be \"False\"."}, {"input": "Our mistress hired a room for my crippled sister Nelly , and she gave (her) knitting and needlework when she was able to do it, and when she was ill she sent her dinners and many nice comfortable things and was like a mother to her. <sep> Pronoun:her <sep> Noun: Nelly", "output": "True", "explanation": "In this example, her refers to Nelly. So, the given noun is correct, and the output should be \"True\"."}], "Negative Examples": [{"input": "Jim yelled at Kevin because (he) was so upset. <sep> Pronoun:he <sep> Noun: Kevin", "output": "True", "explanation": "In this example, he refers to Jim. So, kevin is incorrect, and the output should be \"False\"."}, {"input": "Meanwhile, in the forest, the elephants are calling and hunting high and low for Arthur and Celeste , and their mothers are very worried. Fortunately, in flying over the town, an old marabou bird has seen (them) and come back quickly to tell the news. <sep> Pronoun:them <sep> Noun: Arthur and Celeste", "output": "False", "explanation": "In this example, them refer to Arthur and Celeste. So, the output should be \"True\"."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Fiction", "Books"], "Instance": {"id": "task1390-4c1b834a738c432f9ffe4e3751fb124a", "input": "Papa looked down at the children 's faces , so puzzled and sad now. It was bad enough that (they) had to be denied so many things because he couldn't afford them. <sep> Pronoun:they <sep> Noun: children", "output": ["True"]}, "Instance License": ["CC BY 4.0"], "prediction": "True"}
+{"id": "task1390-1039783c3d424b1a89e21b2fc2a448df", "Task": "task1390_wscfixed_coreference", "Contributors": "['Yeganeh Kordi']", "Source": ["wsc_fiexed"], "URL": ["https://huggingface.co/datasets/super_glue"], "Categories": ["Coreference Resolution"], "Reasoning": ["Commonsense Reasoning"], "Definition": ["You are given a context, a pronoun, and a noun in this task. The given pronoun is shown in the context within parentheses. You should determine if the pronoun refers to the given noun or not. Please answer with \"True\" and \"False\"."], "Positive Examples": [{"input": "Sam pulled up a chair to the piano , but (it) was broken, so he had to sing instead. <sep> Pronoun:it <sep> Noun: the piano", "output": "True", "explanation": "This is a good example. In this context, he had to sing after recognizing it was broken. So, it refers to the piano."}, {"input": "Fred covered his eyes with his hands , because the wind was blowing sand around. He lowered (them) when the wind stopped. <sep> Pronoun:them <sep> Noun: his eyes", "output": "False", "explanation": "In this example, he lowered his hands when the wind stopped. So, them refer to his hands, and the output should be \"False\"."}, {"input": "Our mistress hired a room for my crippled sister Nelly , and she gave (her) knitting and needlework when she was able to do it, and when she was ill she sent her dinners and many nice comfortable things and was like a mother to her. <sep> Pronoun:her <sep> Noun: Nelly", "output": "True", "explanation": "In this example, her refers to Nelly. So, the given noun is correct, and the output should be \"True\"."}], "Negative Examples": [{"input": "Jim yelled at Kevin because (he) was so upset. <sep> Pronoun:he <sep> Noun: Kevin", "output": "True", "explanation": "In this example, he refers to Jim. So, kevin is incorrect, and the output should be \"False\"."}, {"input": "Meanwhile, in the forest, the elephants are calling and hunting high and low for Arthur and Celeste , and their mothers are very worried. Fortunately, in flying over the town, an old marabou bird has seen (them) and come back quickly to tell the news. <sep> Pronoun:them <sep> Noun: Arthur and Celeste", "output": "False", "explanation": "In this example, them refer to Arthur and Celeste. So, the output should be \"True\"."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Fiction", "Books"], "Instance": {"id": "task1390-1039783c3d424b1a89e21b2fc2a448df", "input": "Paul tried to call George on the phone, but (he) wasn't available. <sep> Pronoun:he <sep> Noun: Paul", "output": ["False"]}, "Instance License": ["CC BY 4.0"], "prediction": "True"}
+{"id": "task1390-478874dd80594af286e6b197cd07f9cd", "Task": "task1390_wscfixed_coreference", "Contributors": "['Yeganeh Kordi']", "Source": ["wsc_fiexed"], "URL": ["https://huggingface.co/datasets/super_glue"], "Categories": ["Coreference Resolution"], "Reasoning": ["Commonsense Reasoning"], "Definition": ["You are given a context, a pronoun, and a noun in this task. The given pronoun is shown in the context within parentheses. You should determine if the pronoun refers to the given noun or not. Please answer with \"True\" and \"False\"."], "Positive Examples": [{"input": "Sam pulled up a chair to the piano , but (it) was broken, so he had to sing instead. <sep> Pronoun:it <sep> Noun: the piano", "output": "True", "explanation": "This is a good example. In this context, he had to sing after recognizing it was broken. So, it refers to the piano."}, {"input": "Fred covered his eyes with his hands , because the wind was blowing sand around. He lowered (them) when the wind stopped. <sep> Pronoun:them <sep> Noun: his eyes", "output": "False", "explanation": "In this example, he lowered his hands when the wind stopped. So, them refer to his hands, and the output should be \"False\"."}, {"input": "Our mistress hired a room for my crippled sister Nelly , and she gave (her) knitting and needlework when she was able to do it, and when she was ill she sent her dinners and many nice comfortable things and was like a mother to her. <sep> Pronoun:her <sep> Noun: Nelly", "output": "True", "explanation": "In this example, her refers to Nelly. So, the given noun is correct, and the output should be \"True\"."}], "Negative Examples": [{"input": "Jim yelled at Kevin because (he) was so upset. <sep> Pronoun:he <sep> Noun: Kevin", "output": "True", "explanation": "In this example, he refers to Jim. So, kevin is incorrect, and the output should be \"False\"."}, {"input": "Meanwhile, in the forest, the elephants are calling and hunting high and low for Arthur and Celeste , and their mothers are very worried. Fortunately, in flying over the town, an old marabou bird has seen (them) and come back quickly to tell the news. <sep> Pronoun:them <sep> Noun: Arthur and Celeste", "output": "False", "explanation": "In this example, them refer to Arthur and Celeste. So, the output should be \"True\"."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Fiction", "Books"], "Instance": {"id": "task1390-478874dd80594af286e6b197cd07f9cd", "input": "Thomson visited Cooper 's grave in 1765. At that date (he) had been travelling for five years. <sep> Pronoun:he <sep> Noun: Thomson", "output": ["True"]}, "Instance License": ["CC BY 4.0"], "prediction": "True"}
+{"id": "task199-5ab4602faad44c5d9c8d81aed80d90e9", "Task": "task199_mnli_classification", "Contributors": "['Anjana Arunkumar']", "Source": ["multinli"], "URL": ["https://cims.nyu.edu/~sbowman/multinli/paper.pdf"], "Categories": ["Textual Entailment"], "Reasoning": ["Textual Entailment"], "Definition": ["In this task, you're given a pair of sentences, sentence 1 and sentence 2. Your job is to determine if the two sentences clearly agree/disagree with each other, or if this can't be determined. Indicate your answer as yes or no respectively."], "Positive Examples": [{"input": "Sentence 1: Next to the MGM Grand you will find M and M World. Sentence 2: The candy has many fans who love its attractions.", "output": "no", "explanation": "It is not clear that M and M world is popular."}, {"input": "Sentence 1: I've forgotten his name now, confessed Tuppence. Sentence 2: Tuppence remembered his name later.", "output": "no", "explanation": "Tuppence may or may not have later remembered the name."}, {"input": "Sentence 1: One of the first organizational realignments taking place is in the Office of the Taxpayer Advocate. Sentence 2: The office of the taxpayer advocate is having an organizational realignment.", "output": "yes", "explanation": "Both sentences refer to the reorganization of an official department and agree with each other."}, {"input": "Sentence 1: yeah i tell you what though if you go price some of those tennis shoes i can see why now you know they're getting up in the hundred dollar range. Sentence 2: The tennis shoes have only one price.", "output": "yes", "explanation": "The prices of the shoes vary in the hundred dollar range in the first sentence, so the second sentence disagrees with it as the tennis shoes can't have only one price."}], "Negative Examples": [{"input": "Sentence 1: There was an earthquake in San Fransisco. Sentence 2: The earthquake caused a lot of road damage.", "output": "yes", "explanation": "The magnitude of the earthquake may or may not have been large enough to cause damage."}, {"input": "Sentence 1: Representing yourself in court can be a tricky endeavor. Sentence 2: Lawyers are much better than self-representation.", "output": "yes", "explanation": "Even though self-representation in court is tricky, that doesn't indicate or deny that lawyers are better than self-representation. So, the output should be no."}, {"input": "Sentence 1: Anna went to the school picnic and had a busy afternoon. Sentence 2: Anna had lunch at the picnic with her classmates.", "output": "no", "explanation": "The sentences both refer to a picnic Anna attended, organized by her school and clearly agree with each other. So, the output should be yes."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["History", "Fiction", "Dialogue", "Law", "Government and Politics"], "Instance": {"id": "task199-5ab4602faad44c5d9c8d81aed80d90e9", "input": "Sentence 1: For three decades, Krakew existed as an independent city-state, though it was again incorporated into the Austrian partition in 1846. Sentence 2: Krakew fought not to be a part of the Austrian 1846 partition.", "output": ["no"]}, "Instance License": ["OANC"], "prediction": "no"}
+{"id": "task199-a3975e54f4894f99858ba26b1033358c", "Task": "task199_mnli_classification", "Contributors": "['Anjana Arunkumar']", "Source": ["multinli"], "URL": ["https://cims.nyu.edu/~sbowman/multinli/paper.pdf"], "Categories": ["Textual Entailment"], "Reasoning": ["Textual Entailment"], "Definition": ["In this task, you're given a pair of sentences, sentence 1 and sentence 2. Your job is to determine if the two sentences clearly agree/disagree with each other, or if this can't be determined. Indicate your answer as yes or no respectively."], "Positive Examples": [{"input": "Sentence 1: Next to the MGM Grand you will find M and M World. Sentence 2: The candy has many fans who love its attractions.", "output": "no", "explanation": "It is not clear that M and M world is popular."}, {"input": "Sentence 1: I've forgotten his name now, confessed Tuppence. Sentence 2: Tuppence remembered his name later.", "output": "no", "explanation": "Tuppence may or may not have later remembered the name."}, {"input": "Sentence 1: One of the first organizational realignments taking place is in the Office of the Taxpayer Advocate. Sentence 2: The office of the taxpayer advocate is having an organizational realignment.", "output": "yes", "explanation": "Both sentences refer to the reorganization of an official department and agree with each other."}, {"input": "Sentence 1: yeah i tell you what though if you go price some of those tennis shoes i can see why now you know they're getting up in the hundred dollar range. Sentence 2: The tennis shoes have only one price.", "output": "yes", "explanation": "The prices of the shoes vary in the hundred dollar range in the first sentence, so the second sentence disagrees with it as the tennis shoes can't have only one price."}], "Negative Examples": [{"input": "Sentence 1: There was an earthquake in San Fransisco. Sentence 2: The earthquake caused a lot of road damage.", "output": "yes", "explanation": "The magnitude of the earthquake may or may not have been large enough to cause damage."}, {"input": "Sentence 1: Representing yourself in court can be a tricky endeavor. Sentence 2: Lawyers are much better than self-representation.", "output": "yes", "explanation": "Even though self-representation in court is tricky, that doesn't indicate or deny that lawyers are better than self-representation. So, the output should be no."}, {"input": "Sentence 1: Anna went to the school picnic and had a busy afternoon. Sentence 2: Anna had lunch at the picnic with her classmates.", "output": "no", "explanation": "The sentences both refer to a picnic Anna attended, organized by her school and clearly agree with each other. So, the output should be yes."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["History", "Fiction", "Dialogue", "Law", "Government and Politics"], "Instance": {"id": "task199-a3975e54f4894f99858ba26b1033358c", "input": "Sentence 1: The club itself was a bastion of Ascendancy establishment. Sentence 2: The club was a fortification of Ascendancy establishment.", "output": ["yes"]}, "Instance License": ["OANC"], "prediction": "no"}
+{"id": "task199-b34fc897119042379c6229db90dbe59a", "Task": "task199_mnli_classification", "Contributors": "['Anjana Arunkumar']", "Source": ["multinli"], "URL": ["https://cims.nyu.edu/~sbowman/multinli/paper.pdf"], "Categories": ["Textual Entailment"], "Reasoning": ["Textual Entailment"], "Definition": ["In this task, you're given a pair of sentences, sentence 1 and sentence 2. Your job is to determine if the two sentences clearly agree/disagree with each other, or if this can't be determined. Indicate your answer as yes or no respectively."], "Positive Examples": [{"input": "Sentence 1: Next to the MGM Grand you will find M and M World. Sentence 2: The candy has many fans who love its attractions.", "output": "no", "explanation": "It is not clear that M and M world is popular."}, {"input": "Sentence 1: I've forgotten his name now, confessed Tuppence. Sentence 2: Tuppence remembered his name later.", "output": "no", "explanation": "Tuppence may or may not have later remembered the name."}, {"input": "Sentence 1: One of the first organizational realignments taking place is in the Office of the Taxpayer Advocate. Sentence 2: The office of the taxpayer advocate is having an organizational realignment.", "output": "yes", "explanation": "Both sentences refer to the reorganization of an official department and agree with each other."}, {"input": "Sentence 1: yeah i tell you what though if you go price some of those tennis shoes i can see why now you know they're getting up in the hundred dollar range. Sentence 2: The tennis shoes have only one price.", "output": "yes", "explanation": "The prices of the shoes vary in the hundred dollar range in the first sentence, so the second sentence disagrees with it as the tennis shoes can't have only one price."}], "Negative Examples": [{"input": "Sentence 1: There was an earthquake in San Fransisco. Sentence 2: The earthquake caused a lot of road damage.", "output": "yes", "explanation": "The magnitude of the earthquake may or may not have been large enough to cause damage."}, {"input": "Sentence 1: Representing yourself in court can be a tricky endeavor. Sentence 2: Lawyers are much better than self-representation.", "output": "yes", "explanation": "Even though self-representation in court is tricky, that doesn't indicate or deny that lawyers are better than self-representation. So, the output should be no."}, {"input": "Sentence 1: Anna went to the school picnic and had a busy afternoon. Sentence 2: Anna had lunch at the picnic with her classmates.", "output": "no", "explanation": "The sentences both refer to a picnic Anna attended, organized by her school and clearly agree with each other. So, the output should be yes."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["History", "Fiction", "Dialogue", "Law", "Government and Politics"], "Instance": {"id": "task199-b34fc897119042379c6229db90dbe59a", "input": "Sentence 1: Impaling all the old men took a long time and when the armored men stood the pikes upright, the sharp tips gleaming from the elders' gaping mouths. Sentence 2: It took a long time but old men were impailed. ", "output": ["yes"]}, "Instance License": ["OANC"], "prediction": "yes"}
+{"id": "task199-9f3e5f6241ce41c7ba83bf9a2b6be11d", "Task": "task199_mnli_classification", "Contributors": "['Anjana Arunkumar']", "Source": ["multinli"], "URL": ["https://cims.nyu.edu/~sbowman/multinli/paper.pdf"], "Categories": ["Textual Entailment"], "Reasoning": ["Textual Entailment"], "Definition": ["In this task, you're given a pair of sentences, sentence 1 and sentence 2. Your job is to determine if the two sentences clearly agree/disagree with each other, or if this can't be determined. Indicate your answer as yes or no respectively."], "Positive Examples": [{"input": "Sentence 1: Next to the MGM Grand you will find M and M World. Sentence 2: The candy has many fans who love its attractions.", "output": "no", "explanation": "It is not clear that M and M world is popular."}, {"input": "Sentence 1: I've forgotten his name now, confessed Tuppence. Sentence 2: Tuppence remembered his name later.", "output": "no", "explanation": "Tuppence may or may not have later remembered the name."}, {"input": "Sentence 1: One of the first organizational realignments taking place is in the Office of the Taxpayer Advocate. Sentence 2: The office of the taxpayer advocate is having an organizational realignment.", "output": "yes", "explanation": "Both sentences refer to the reorganization of an official department and agree with each other."}, {"input": "Sentence 1: yeah i tell you what though if you go price some of those tennis shoes i can see why now you know they're getting up in the hundred dollar range. Sentence 2: The tennis shoes have only one price.", "output": "yes", "explanation": "The prices of the shoes vary in the hundred dollar range in the first sentence, so the second sentence disagrees with it as the tennis shoes can't have only one price."}], "Negative Examples": [{"input": "Sentence 1: There was an earthquake in San Fransisco. Sentence 2: The earthquake caused a lot of road damage.", "output": "yes", "explanation": "The magnitude of the earthquake may or may not have been large enough to cause damage."}, {"input": "Sentence 1: Representing yourself in court can be a tricky endeavor. Sentence 2: Lawyers are much better than self-representation.", "output": "yes", "explanation": "Even though self-representation in court is tricky, that doesn't indicate or deny that lawyers are better than self-representation. So, the output should be no."}, {"input": "Sentence 1: Anna went to the school picnic and had a busy afternoon. Sentence 2: Anna had lunch at the picnic with her classmates.", "output": "no", "explanation": "The sentences both refer to a picnic Anna attended, organized by her school and clearly agree with each other. So, the output should be yes."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["History", "Fiction", "Dialogue", "Law", "Government and Politics"], "Instance": {"id": "task199-9f3e5f6241ce41c7ba83bf9a2b6be11d", "input": "Sentence 1: Ninety-five percent of the total amount of sulfur dioxide allowances allocated each year under Section 423 will be allocated based on the amount of sulfur dioxide allowances allocated under the Acid Rain Program for 2010 and thereafter and that are held in allowance accounts in the Allowance Tracking System on the date 180 days after enactment. Sentence 2: Most of the sulfur dioxide that is allowed are controlled by the Acid Rain Program.", "output": ["no", "yes"]}, "Instance License": ["OANC"], "prediction": "no"}
+{"id": "task199-050707010b334464b9fa3ef7c7e14de2", "Task": "task199_mnli_classification", "Contributors": "['Anjana Arunkumar']", "Source": ["multinli"], "URL": ["https://cims.nyu.edu/~sbowman/multinli/paper.pdf"], "Categories": ["Textual Entailment"], "Reasoning": ["Textual Entailment"], "Definition": ["In this task, you're given a pair of sentences, sentence 1 and sentence 2. Your job is to determine if the two sentences clearly agree/disagree with each other, or if this can't be determined. Indicate your answer as yes or no respectively."], "Positive Examples": [{"input": "Sentence 1: Next to the MGM Grand you will find M and M World. Sentence 2: The candy has many fans who love its attractions.", "output": "no", "explanation": "It is not clear that M and M world is popular."}, {"input": "Sentence 1: I've forgotten his name now, confessed Tuppence. Sentence 2: Tuppence remembered his name later.", "output": "no", "explanation": "Tuppence may or may not have later remembered the name."}, {"input": "Sentence 1: One of the first organizational realignments taking place is in the Office of the Taxpayer Advocate. Sentence 2: The office of the taxpayer advocate is having an organizational realignment.", "output": "yes", "explanation": "Both sentences refer to the reorganization of an official department and agree with each other."}, {"input": "Sentence 1: yeah i tell you what though if you go price some of those tennis shoes i can see why now you know they're getting up in the hundred dollar range. Sentence 2: The tennis shoes have only one price.", "output": "yes", "explanation": "The prices of the shoes vary in the hundred dollar range in the first sentence, so the second sentence disagrees with it as the tennis shoes can't have only one price."}], "Negative Examples": [{"input": "Sentence 1: There was an earthquake in San Fransisco. Sentence 2: The earthquake caused a lot of road damage.", "output": "yes", "explanation": "The magnitude of the earthquake may or may not have been large enough to cause damage."}, {"input": "Sentence 1: Representing yourself in court can be a tricky endeavor. Sentence 2: Lawyers are much better than self-representation.", "output": "yes", "explanation": "Even though self-representation in court is tricky, that doesn't indicate or deny that lawyers are better than self-representation. So, the output should be no."}, {"input": "Sentence 1: Anna went to the school picnic and had a busy afternoon. Sentence 2: Anna had lunch at the picnic with her classmates.", "output": "no", "explanation": "The sentences both refer to a picnic Anna attended, organized by her school and clearly agree with each other. So, the output should be yes."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["History", "Fiction", "Dialogue", "Law", "Government and Politics"], "Instance": {"id": "task199-050707010b334464b9fa3ef7c7e14de2", "input": "Sentence 1: well let's see if you're in Plano and i'm in Plano are you in east Plano or west Plano Sentence 2: We are both in Plano, which side are you in?", "output": ["yes"]}, "Instance License": ["OANC"], "prediction": "no"}
+{"id": "task034-80c557ac3bf84a3b80ad124ab3e05c67", "Task": "task034_winogrande_question_modification_object", "Contributors": "['Swaroop Mishra', 'Daniel Khashabi']", "Source": ["winogrande"], "URL": ["https://leaderboard.allenai.org/winogrande/submissions/about"], "Categories": ["Question Rewriting"], "Reasoning": ["Commonsense Reasoning"], "Definition": ["In this task, you're given a fill-in-the-blank question that contains two object names. Additionally, you're given one answer which is one of the objects present in the question. In this task, you need to minimally change the given question so that the answer flips to another object in the question. Remember the question has to be about both objects which are related but different; for example, \"trophy\" and \"suitcase\". This task typically involves replacing one word i.e., the 'trigger word' with its antonym (e.g., changing from \"small\" to \"big\"). You should not change any content in the given question beyond a word or two, i.e., the trigger word/phrase. The expected answer to your question must not be associated with just the trigger word; instead, it should depend on the context present in the question. The expected answer should not be ambiguous. For your question, there should be an agreed upon answer to fill in the blank. Your generations should NOT contain potentially explicit, offensive, or adult content. In your generated question, retain the object names from the input question. Avoid repeating the same style or phrase in generating your modified question e.g. this task can be always solved using a simple negation i.e. by adding not, never, etc. Instead, try to increase the word diversity. Your question must contain at least 15 and at most 30 words. Your question must have at least 70% overlapping words with the given question. You must utilize the given context word while writing the question. Your question must contain only one blank. The two objects should be used ONCE in your question. Here is a list of attributes and associated contrastive words that may help write contrastive trigger words. Note that contrastive trigger words help in flipping the label.\n| Attribute | triggerword | contrastive triggerword | \n| age | old | new | \n| altitude | low | high |\n| area | small | vast | \n| brightness | dark | light | \n| clarity | obscure | clear | \n| cleanness | dirty | clean | \n| complexity | simple | complex | \n| cost | cheap | expensive |\n| density | sparse | dense |\n| depth | shallow | deep |\n| distance | near | far |  \n| electric conductivity | low | high |\n| flexibility | rigid | flexible |\n| granularity | fine | coarse | \n| hardness | soft | hard | \n| length | short | long | \n| magnitude | small | large | \n| mass | small | large | \n| odor | weak | strong | \n| pressure | low | high | \n| resistance | low | high | \n| shape | round | sharp |\n| shape | flat | spiky |\n| size | small | large | \n| sound | quiet | loud | \n| sound pitch | low | high | \n| speed | slow | fast | \n| stability | unstable | stable | \n| strength | weak | strong | \n| temperature | low | high | \n| texture | smooth | rough | \n| thermal conductivity | low | high |\n| thickness | thin | thick | \n| volume | small | large |\n| weight | light | heavy | \n| width | narrow | wide | \n| location | in | out |\n| location | up | down |\n| location | above | below |\n| location | on | off |\n| location | to | from |\n"], "Positive Examples": [{"input": "Context word: fit. \nQuestion: The trophy doesn't fit into the brown suitcase because _ is too large. \nAnswer: trophy.", "output": "The trophy doesn't fit into the brown suitcase because _ is too small.", "explanation": "Here, replacing the trigger word \"large\" by its antonym \"small\" flips answer to the second object (\"suitcase\") in the question. So, this is a valid question."}, {"input": "Context word: trade. \nQuestion: Grace was happy to trade me her sweater for my jacket. She thinks _ looks dowdy on her. \nAnswer: sweater.", "output": "Grace was happy to trade me her sweater for my jacket. She thinks _ looks great on her.", "explanation": "Here, replacing the trigger word \"dowdy\" by its antonym \"great\" flips answer to the second object (\"jacket\") in the question. Therefore, this is a valid question."}, {"input": "Context word: carpet. \nQuestion: While redecorating her home, Sam took out the carpet and replaced it with wood floors. The _ was old. \nAnswer: carpet.", "output": "While redecorating her home, Sam took out the carpet and replaced it with wood floors. The _ was trendy.", "explanation": "This is a valid question because: on replacing the trigger word \"old\" by its antonym \"trendy\", the answer flips to the second object (\"wood floors\") in the question."}, {"input": "Context word: fit. \nQuestion: The table won't fit through the doorway because the _ is too wide. \nAnswer: table.", "output": "The table won't fit through the doorway because the _ is too narrow.", "explanation": "Here, replacing the trigger word \"wide\" by its antonym \"narrow\" flips answer to the second object (\"doorway\") in the question. That's why this is a good question."}, {"input": "Context word: water. \nQuestion: I poured water from the bottle into the cup until the _ was empty. \nAnswer: bottle.", "output": "I poured water from the bottle into the cup until the _ was full.", "explanation": "Here, replacing the trigger word \"empty\" by its antonym \"full\" flips answer to the second object (\"cup\") in the question. That's why this is a good question."}, {"input": "Context word: catch. \nQuestion: My meeting started at 4:00 and I needed to catch the train at 4:30, so there wasn't much time. Luckily, the _ was short, so it worked out. \nAnswer: meeting.", "output": "My meeting started at 4:00 and I needed to catch the train at 4:30, so there wasn't much time. Luckily, the _ was delayed, so it worked out.", "explanation": "Here, replacing the trigger word \"short\" by its antonym \"delayed\" flips answer to the second object (\"train\") in the question. So, this is a valid question."}, {"input": "Context word: candle. \nQuestion: James wanted to light the candle in the wind when on a date but the _ is too weak. \nAnswer: light.", "output": "James wanted to light the candle in the wind when on a date but the _ is too strong.", "explanation": "On replacing the trigger word \"weak\" by its antonym \"strong\", the answer flips to the second object (\"wind\") in the question. So, this is a valid question."}], "Negative Examples": [{"input": "Context word: fit. \nQuestion: The trophy doesn't fit into the brown suitcase because _ is too large. \nAnswer: trophy.", "output": "The trophy doesn't fit into the brown suitcase because there were a lot of other eseential items and jewlleries to pack and  _ is too large.", "explanation": "The problem here is that, the new question is very different from the given question. Note that, the new question must have at least 70% word overlap with the given question."}, {"input": "Context word: trade. \nQuestion: Grace was happy to trade me her sweater for my jacket. She thinks _ looks dowdy on her. \nAnswer: sweater.", "output": "Grace was happy to trade me her sweater for my jacket. She thinks _ is colored purple.", "explanation": "Here, there is an issue as both objects (\"sweater\" and \"jacket\") are equally likely to fill the blank. This makes the question ambiguous."}, {"input": "Context word: carpet. \nQuestion: While redecorating her home, Sam took out the carpet and replaced it with wood floors. The _ was old. \nAnswer: carpet.", "output": "While redecorating her home, Sam took out the carpet and replaced it with wood floors. The wood floor's feature is that _  was trendy.", "explanation": "Here the object \"wood floor\" has been used more than once in the question. Note that the two objects should be used ONCE in your question."}, {"input": "Context word: fit. \nQuestion: The table won't fit through the doorway because the _ is too wide. \nAnswer: table.", "output": "The table is brown in color which is different from the color of the _.", "explanation": "The question is based on color of objects which is different from the context word \"fit\". Note that, you must utilize the given context word while writing the question."}, {"input": "Context word: water. \nQuestion: I poured water from the bottle into the cup until the _ was empty. \nAnswer: bottle.", "output": "I poured water from the bottle into the _ until the _ was empty.", "explanation": "This question contains more than one blank. Note that, your question must contain only one blank."}, {"input": "Context word: catch. \nQuestion: My meeting started at 4:00 and I needed to catch the train at 4:30, so there wasn't much time. Luckily, the _ was short, so it worked out. \nAnswer: meeting.", "output": "My meeting started at 4:00 and I needed to catch the train at 4:30, so there wasn't much time. Luckily, the meeting was _.", "explanation": "The expected answer to this question is \"short\" which is not one of the two objects present in the question (\"train\" and \"meeting\"). Note that, the answer in your generated question must flip to another object in the question."}, {"input": "Context word: candle. \nQuestion: James wanted to light the candle in the wind when on a date but the _ is too weak. \nAnswer: light.", "output": "James wanted to light the candle in the _.", "explanation": "The issue is that the generated question has lesser than 15 words. Remember, your question must contain at least 15 and at most 30 words."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Commonsense -> Concepts and Relations -> Social Commonsense", "Commonsense -> Concepts and Relations -> Physical Commonsense"], "Instance": {"id": "task034-80c557ac3bf84a3b80ad124ab3e05c67", "input": "Context Word: cardboard. \nQuestion: The shirt was in the cardboard box and the book was sitting on top of it when it rained, so the _ got wet. \nAnswer: book.", "output": ["The shirt was in the cardboard box and the book was sitting on top of it when it rained, so the _ stayed dry."]}, "Instance License": ["Apache 2.0"], "prediction": "The shirt was in the cardboard box and the book was sitting on top of it when it rained, so the _ got wet."}
+{"id": "task034-7e673c6cad2642d4b41f7d1b4535fac7", "Task": "task034_winogrande_question_modification_object", "Contributors": "['Swaroop Mishra', 'Daniel Khashabi']", "Source": ["winogrande"], "URL": ["https://leaderboard.allenai.org/winogrande/submissions/about"], "Categories": ["Question Rewriting"], "Reasoning": ["Commonsense Reasoning"], "Definition": ["In this task, you're given a fill-in-the-blank question that contains two object names. Additionally, you're given one answer which is one of the objects present in the question. In this task, you need to minimally change the given question so that the answer flips to another object in the question. Remember the question has to be about both objects which are related but different; for example, \"trophy\" and \"suitcase\". This task typically involves replacing one word i.e., the 'trigger word' with its antonym (e.g., changing from \"small\" to \"big\"). You should not change any content in the given question beyond a word or two, i.e., the trigger word/phrase. The expected answer to your question must not be associated with just the trigger word; instead, it should depend on the context present in the question. The expected answer should not be ambiguous. For your question, there should be an agreed upon answer to fill in the blank. Your generations should NOT contain potentially explicit, offensive, or adult content. In your generated question, retain the object names from the input question. Avoid repeating the same style or phrase in generating your modified question e.g. this task can be always solved using a simple negation i.e. by adding not, never, etc. Instead, try to increase the word diversity. Your question must contain at least 15 and at most 30 words. Your question must have at least 70% overlapping words with the given question. You must utilize the given context word while writing the question. Your question must contain only one blank. The two objects should be used ONCE in your question. Here is a list of attributes and associated contrastive words that may help write contrastive trigger words. Note that contrastive trigger words help in flipping the label.\n| Attribute | triggerword | contrastive triggerword | \n| age | old | new | \n| altitude | low | high |\n| area | small | vast | \n| brightness | dark | light | \n| clarity | obscure | clear | \n| cleanness | dirty | clean | \n| complexity | simple | complex | \n| cost | cheap | expensive |\n| density | sparse | dense |\n| depth | shallow | deep |\n| distance | near | far |  \n| electric conductivity | low | high |\n| flexibility | rigid | flexible |\n| granularity | fine | coarse | \n| hardness | soft | hard | \n| length | short | long | \n| magnitude | small | large | \n| mass | small | large | \n| odor | weak | strong | \n| pressure | low | high | \n| resistance | low | high | \n| shape | round | sharp |\n| shape | flat | spiky |\n| size | small | large | \n| sound | quiet | loud | \n| sound pitch | low | high | \n| speed | slow | fast | \n| stability | unstable | stable | \n| strength | weak | strong | \n| temperature | low | high | \n| texture | smooth | rough | \n| thermal conductivity | low | high |\n| thickness | thin | thick | \n| volume | small | large |\n| weight | light | heavy | \n| width | narrow | wide | \n| location | in | out |\n| location | up | down |\n| location | above | below |\n| location | on | off |\n| location | to | from |\n"], "Positive Examples": [{"input": "Context word: fit. \nQuestion: The trophy doesn't fit into the brown suitcase because _ is too large. \nAnswer: trophy.", "output": "The trophy doesn't fit into the brown suitcase because _ is too small.", "explanation": "Here, replacing the trigger word \"large\" by its antonym \"small\" flips answer to the second object (\"suitcase\") in the question. So, this is a valid question."}, {"input": "Context word: trade. \nQuestion: Grace was happy to trade me her sweater for my jacket. She thinks _ looks dowdy on her. \nAnswer: sweater.", "output": "Grace was happy to trade me her sweater for my jacket. She thinks _ looks great on her.", "explanation": "Here, replacing the trigger word \"dowdy\" by its antonym \"great\" flips answer to the second object (\"jacket\") in the question. Therefore, this is a valid question."}, {"input": "Context word: carpet. \nQuestion: While redecorating her home, Sam took out the carpet and replaced it with wood floors. The _ was old. \nAnswer: carpet.", "output": "While redecorating her home, Sam took out the carpet and replaced it with wood floors. The _ was trendy.", "explanation": "This is a valid question because: on replacing the trigger word \"old\" by its antonym \"trendy\", the answer flips to the second object (\"wood floors\") in the question."}, {"input": "Context word: fit. \nQuestion: The table won't fit through the doorway because the _ is too wide. \nAnswer: table.", "output": "The table won't fit through the doorway because the _ is too narrow.", "explanation": "Here, replacing the trigger word \"wide\" by its antonym \"narrow\" flips answer to the second object (\"doorway\") in the question. That's why this is a good question."}, {"input": "Context word: water. \nQuestion: I poured water from the bottle into the cup until the _ was empty. \nAnswer: bottle.", "output": "I poured water from the bottle into the cup until the _ was full.", "explanation": "Here, replacing the trigger word \"empty\" by its antonym \"full\" flips answer to the second object (\"cup\") in the question. That's why this is a good question."}, {"input": "Context word: catch. \nQuestion: My meeting started at 4:00 and I needed to catch the train at 4:30, so there wasn't much time. Luckily, the _ was short, so it worked out. \nAnswer: meeting.", "output": "My meeting started at 4:00 and I needed to catch the train at 4:30, so there wasn't much time. Luckily, the _ was delayed, so it worked out.", "explanation": "Here, replacing the trigger word \"short\" by its antonym \"delayed\" flips answer to the second object (\"train\") in the question. So, this is a valid question."}, {"input": "Context word: candle. \nQuestion: James wanted to light the candle in the wind when on a date but the _ is too weak. \nAnswer: light.", "output": "James wanted to light the candle in the wind when on a date but the _ is too strong.", "explanation": "On replacing the trigger word \"weak\" by its antonym \"strong\", the answer flips to the second object (\"wind\") in the question. So, this is a valid question."}], "Negative Examples": [{"input": "Context word: fit. \nQuestion: The trophy doesn't fit into the brown suitcase because _ is too large. \nAnswer: trophy.", "output": "The trophy doesn't fit into the brown suitcase because there were a lot of other eseential items and jewlleries to pack and  _ is too large.", "explanation": "The problem here is that, the new question is very different from the given question. Note that, the new question must have at least 70% word overlap with the given question."}, {"input": "Context word: trade. \nQuestion: Grace was happy to trade me her sweater for my jacket. She thinks _ looks dowdy on her. \nAnswer: sweater.", "output": "Grace was happy to trade me her sweater for my jacket. She thinks _ is colored purple.", "explanation": "Here, there is an issue as both objects (\"sweater\" and \"jacket\") are equally likely to fill the blank. This makes the question ambiguous."}, {"input": "Context word: carpet. \nQuestion: While redecorating her home, Sam took out the carpet and replaced it with wood floors. The _ was old. \nAnswer: carpet.", "output": "While redecorating her home, Sam took out the carpet and replaced it with wood floors. The wood floor's feature is that _  was trendy.", "explanation": "Here the object \"wood floor\" has been used more than once in the question. Note that the two objects should be used ONCE in your question."}, {"input": "Context word: fit. \nQuestion: The table won't fit through the doorway because the _ is too wide. \nAnswer: table.", "output": "The table is brown in color which is different from the color of the _.", "explanation": "The question is based on color of objects which is different from the context word \"fit\". Note that, you must utilize the given context word while writing the question."}, {"input": "Context word: water. \nQuestion: I poured water from the bottle into the cup until the _ was empty. \nAnswer: bottle.", "output": "I poured water from the bottle into the _ until the _ was empty.", "explanation": "This question contains more than one blank. Note that, your question must contain only one blank."}, {"input": "Context word: catch. \nQuestion: My meeting started at 4:00 and I needed to catch the train at 4:30, so there wasn't much time. Luckily, the _ was short, so it worked out. \nAnswer: meeting.", "output": "My meeting started at 4:00 and I needed to catch the train at 4:30, so there wasn't much time. Luckily, the meeting was _.", "explanation": "The expected answer to this question is \"short\" which is not one of the two objects present in the question (\"train\" and \"meeting\"). Note that, the answer in your generated question must flip to another object in the question."}, {"input": "Context word: candle. \nQuestion: James wanted to light the candle in the wind when on a date but the _ is too weak. \nAnswer: light.", "output": "James wanted to light the candle in the _.", "explanation": "The issue is that the generated question has lesser than 15 words. Remember, your question must contain at least 15 and at most 30 words."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Commonsense -> Concepts and Relations -> Social Commonsense", "Commonsense -> Concepts and Relations -> Physical Commonsense"], "Instance": {"id": "task034-7e673c6cad2642d4b41f7d1b4535fac7", "input": "Context Word: electricity. \nQuestion: Al got solar panels and a small generator installed at his house for electricity as the _ would be his main power supply. \nAnswer: panels.", "output": ["Al got solar panels and a small generator installed at his house for electricity as the _ would be his backup power supply."]}, "Instance License": ["Apache 2.0"], "prediction": "Al got solar panels and a small generator installed at his house for electricity as the _ would be his main power supply."}
+{"id": "task034-9c82906e872a4c31996131615d07d811", "Task": "task034_winogrande_question_modification_object", "Contributors": "['Swaroop Mishra', 'Daniel Khashabi']", "Source": ["winogrande"], "URL": ["https://leaderboard.allenai.org/winogrande/submissions/about"], "Categories": ["Question Rewriting"], "Reasoning": ["Commonsense Reasoning"], "Definition": ["In this task, you're given a fill-in-the-blank question that contains two object names. Additionally, you're given one answer which is one of the objects present in the question. In this task, you need to minimally change the given question so that the answer flips to another object in the question. Remember the question has to be about both objects which are related but different; for example, \"trophy\" and \"suitcase\". This task typically involves replacing one word i.e., the 'trigger word' with its antonym (e.g., changing from \"small\" to \"big\"). You should not change any content in the given question beyond a word or two, i.e., the trigger word/phrase. The expected answer to your question must not be associated with just the trigger word; instead, it should depend on the context present in the question. The expected answer should not be ambiguous. For your question, there should be an agreed upon answer to fill in the blank. Your generations should NOT contain potentially explicit, offensive, or adult content. In your generated question, retain the object names from the input question. Avoid repeating the same style or phrase in generating your modified question e.g. this task can be always solved using a simple negation i.e. by adding not, never, etc. Instead, try to increase the word diversity. Your question must contain at least 15 and at most 30 words. Your question must have at least 70% overlapping words with the given question. You must utilize the given context word while writing the question. Your question must contain only one blank. The two objects should be used ONCE in your question. Here is a list of attributes and associated contrastive words that may help write contrastive trigger words. Note that contrastive trigger words help in flipping the label.\n| Attribute | triggerword | contrastive triggerword | \n| age | old | new | \n| altitude | low | high |\n| area | small | vast | \n| brightness | dark | light | \n| clarity | obscure | clear | \n| cleanness | dirty | clean | \n| complexity | simple | complex | \n| cost | cheap | expensive |\n| density | sparse | dense |\n| depth | shallow | deep |\n| distance | near | far |  \n| electric conductivity | low | high |\n| flexibility | rigid | flexible |\n| granularity | fine | coarse | \n| hardness | soft | hard | \n| length | short | long | \n| magnitude | small | large | \n| mass | small | large | \n| odor | weak | strong | \n| pressure | low | high | \n| resistance | low | high | \n| shape | round | sharp |\n| shape | flat | spiky |\n| size | small | large | \n| sound | quiet | loud | \n| sound pitch | low | high | \n| speed | slow | fast | \n| stability | unstable | stable | \n| strength | weak | strong | \n| temperature | low | high | \n| texture | smooth | rough | \n| thermal conductivity | low | high |\n| thickness | thin | thick | \n| volume | small | large |\n| weight | light | heavy | \n| width | narrow | wide | \n| location | in | out |\n| location | up | down |\n| location | above | below |\n| location | on | off |\n| location | to | from |\n"], "Positive Examples": [{"input": "Context word: fit. \nQuestion: The trophy doesn't fit into the brown suitcase because _ is too large. \nAnswer: trophy.", "output": "The trophy doesn't fit into the brown suitcase because _ is too small.", "explanation": "Here, replacing the trigger word \"large\" by its antonym \"small\" flips answer to the second object (\"suitcase\") in the question. So, this is a valid question."}, {"input": "Context word: trade. \nQuestion: Grace was happy to trade me her sweater for my jacket. She thinks _ looks dowdy on her. \nAnswer: sweater.", "output": "Grace was happy to trade me her sweater for my jacket. She thinks _ looks great on her.", "explanation": "Here, replacing the trigger word \"dowdy\" by its antonym \"great\" flips answer to the second object (\"jacket\") in the question. Therefore, this is a valid question."}, {"input": "Context word: carpet. \nQuestion: While redecorating her home, Sam took out the carpet and replaced it with wood floors. The _ was old. \nAnswer: carpet.", "output": "While redecorating her home, Sam took out the carpet and replaced it with wood floors. The _ was trendy.", "explanation": "This is a valid question because: on replacing the trigger word \"old\" by its antonym \"trendy\", the answer flips to the second object (\"wood floors\") in the question."}, {"input": "Context word: fit. \nQuestion: The table won't fit through the doorway because the _ is too wide. \nAnswer: table.", "output": "The table won't fit through the doorway because the _ is too narrow.", "explanation": "Here, replacing the trigger word \"wide\" by its antonym \"narrow\" flips answer to the second object (\"doorway\") in the question. That's why this is a good question."}, {"input": "Context word: water. \nQuestion: I poured water from the bottle into the cup until the _ was empty. \nAnswer: bottle.", "output": "I poured water from the bottle into the cup until the _ was full.", "explanation": "Here, replacing the trigger word \"empty\" by its antonym \"full\" flips answer to the second object (\"cup\") in the question. That's why this is a good question."}, {"input": "Context word: catch. \nQuestion: My meeting started at 4:00 and I needed to catch the train at 4:30, so there wasn't much time. Luckily, the _ was short, so it worked out. \nAnswer: meeting.", "output": "My meeting started at 4:00 and I needed to catch the train at 4:30, so there wasn't much time. Luckily, the _ was delayed, so it worked out.", "explanation": "Here, replacing the trigger word \"short\" by its antonym \"delayed\" flips answer to the second object (\"train\") in the question. So, this is a valid question."}, {"input": "Context word: candle. \nQuestion: James wanted to light the candle in the wind when on a date but the _ is too weak. \nAnswer: light.", "output": "James wanted to light the candle in the wind when on a date but the _ is too strong.", "explanation": "On replacing the trigger word \"weak\" by its antonym \"strong\", the answer flips to the second object (\"wind\") in the question. So, this is a valid question."}], "Negative Examples": [{"input": "Context word: fit. \nQuestion: The trophy doesn't fit into the brown suitcase because _ is too large. \nAnswer: trophy.", "output": "The trophy doesn't fit into the brown suitcase because there were a lot of other eseential items and jewlleries to pack and  _ is too large.", "explanation": "The problem here is that, the new question is very different from the given question. Note that, the new question must have at least 70% word overlap with the given question."}, {"input": "Context word: trade. \nQuestion: Grace was happy to trade me her sweater for my jacket. She thinks _ looks dowdy on her. \nAnswer: sweater.", "output": "Grace was happy to trade me her sweater for my jacket. She thinks _ is colored purple.", "explanation": "Here, there is an issue as both objects (\"sweater\" and \"jacket\") are equally likely to fill the blank. This makes the question ambiguous."}, {"input": "Context word: carpet. \nQuestion: While redecorating her home, Sam took out the carpet and replaced it with wood floors. The _ was old. \nAnswer: carpet.", "output": "While redecorating her home, Sam took out the carpet and replaced it with wood floors. The wood floor's feature is that _  was trendy.", "explanation": "Here the object \"wood floor\" has been used more than once in the question. Note that the two objects should be used ONCE in your question."}, {"input": "Context word: fit. \nQuestion: The table won't fit through the doorway because the _ is too wide. \nAnswer: table.", "output": "The table is brown in color which is different from the color of the _.", "explanation": "The question is based on color of objects which is different from the context word \"fit\". Note that, you must utilize the given context word while writing the question."}, {"input": "Context word: water. \nQuestion: I poured water from the bottle into the cup until the _ was empty. \nAnswer: bottle.", "output": "I poured water from the bottle into the _ until the _ was empty.", "explanation": "This question contains more than one blank. Note that, your question must contain only one blank."}, {"input": "Context word: catch. \nQuestion: My meeting started at 4:00 and I needed to catch the train at 4:30, so there wasn't much time. Luckily, the _ was short, so it worked out. \nAnswer: meeting.", "output": "My meeting started at 4:00 and I needed to catch the train at 4:30, so there wasn't much time. Luckily, the meeting was _.", "explanation": "The expected answer to this question is \"short\" which is not one of the two objects present in the question (\"train\" and \"meeting\"). Note that, the answer in your generated question must flip to another object in the question."}, {"input": "Context word: candle. \nQuestion: James wanted to light the candle in the wind when on a date but the _ is too weak. \nAnswer: light.", "output": "James wanted to light the candle in the _.", "explanation": "The issue is that the generated question has lesser than 15 words. Remember, your question must contain at least 15 and at most 30 words."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Commonsense -> Concepts and Relations -> Social Commonsense", "Commonsense -> Concepts and Relations -> Physical Commonsense"], "Instance": {"id": "task034-9c82906e872a4c31996131615d07d811", "input": "Context Word: Slider. \nQuestion: The chef recommended sliders to the VIP guests, but they ordered ribeyes instead. They were told the _ were tastier. \nAnswer: ribeyes.", "output": ["The chef recommended sliders to the VIP guests, but they ordered ribeyes instead. They were told the _ were not fresh."]}, "Instance License": ["Apache 2.0"], "prediction": "The chef recommended sliders to the VIP guests, but they ordered ribeyes instead. They were told the _ were tastier."}
+{"id": "task034-ccf5f05c287643f8a6d19de82a705ffa", "Task": "task034_winogrande_question_modification_object", "Contributors": "['Swaroop Mishra', 'Daniel Khashabi']", "Source": ["winogrande"], "URL": ["https://leaderboard.allenai.org/winogrande/submissions/about"], "Categories": ["Question Rewriting"], "Reasoning": ["Commonsense Reasoning"], "Definition": ["In this task, you're given a fill-in-the-blank question that contains two object names. Additionally, you're given one answer which is one of the objects present in the question. In this task, you need to minimally change the given question so that the answer flips to another object in the question. Remember the question has to be about both objects which are related but different; for example, \"trophy\" and \"suitcase\". This task typically involves replacing one word i.e., the 'trigger word' with its antonym (e.g., changing from \"small\" to \"big\"). You should not change any content in the given question beyond a word or two, i.e., the trigger word/phrase. The expected answer to your question must not be associated with just the trigger word; instead, it should depend on the context present in the question. The expected answer should not be ambiguous. For your question, there should be an agreed upon answer to fill in the blank. Your generations should NOT contain potentially explicit, offensive, or adult content. In your generated question, retain the object names from the input question. Avoid repeating the same style or phrase in generating your modified question e.g. this task can be always solved using a simple negation i.e. by adding not, never, etc. Instead, try to increase the word diversity. Your question must contain at least 15 and at most 30 words. Your question must have at least 70% overlapping words with the given question. You must utilize the given context word while writing the question. Your question must contain only one blank. The two objects should be used ONCE in your question. Here is a list of attributes and associated contrastive words that may help write contrastive trigger words. Note that contrastive trigger words help in flipping the label.\n| Attribute | triggerword | contrastive triggerword | \n| age | old | new | \n| altitude | low | high |\n| area | small | vast | \n| brightness | dark | light | \n| clarity | obscure | clear | \n| cleanness | dirty | clean | \n| complexity | simple | complex | \n| cost | cheap | expensive |\n| density | sparse | dense |\n| depth | shallow | deep |\n| distance | near | far |  \n| electric conductivity | low | high |\n| flexibility | rigid | flexible |\n| granularity | fine | coarse | \n| hardness | soft | hard | \n| length | short | long | \n| magnitude | small | large | \n| mass | small | large | \n| odor | weak | strong | \n| pressure | low | high | \n| resistance | low | high | \n| shape | round | sharp |\n| shape | flat | spiky |\n| size | small | large | \n| sound | quiet | loud | \n| sound pitch | low | high | \n| speed | slow | fast | \n| stability | unstable | stable | \n| strength | weak | strong | \n| temperature | low | high | \n| texture | smooth | rough | \n| thermal conductivity | low | high |\n| thickness | thin | thick | \n| volume | small | large |\n| weight | light | heavy | \n| width | narrow | wide | \n| location | in | out |\n| location | up | down |\n| location | above | below |\n| location | on | off |\n| location | to | from |\n"], "Positive Examples": [{"input": "Context word: fit. \nQuestion: The trophy doesn't fit into the brown suitcase because _ is too large. \nAnswer: trophy.", "output": "The trophy doesn't fit into the brown suitcase because _ is too small.", "explanation": "Here, replacing the trigger word \"large\" by its antonym \"small\" flips answer to the second object (\"suitcase\") in the question. So, this is a valid question."}, {"input": "Context word: trade. \nQuestion: Grace was happy to trade me her sweater for my jacket. She thinks _ looks dowdy on her. \nAnswer: sweater.", "output": "Grace was happy to trade me her sweater for my jacket. She thinks _ looks great on her.", "explanation": "Here, replacing the trigger word \"dowdy\" by its antonym \"great\" flips answer to the second object (\"jacket\") in the question. Therefore, this is a valid question."}, {"input": "Context word: carpet. \nQuestion: While redecorating her home, Sam took out the carpet and replaced it with wood floors. The _ was old. \nAnswer: carpet.", "output": "While redecorating her home, Sam took out the carpet and replaced it with wood floors. The _ was trendy.", "explanation": "This is a valid question because: on replacing the trigger word \"old\" by its antonym \"trendy\", the answer flips to the second object (\"wood floors\") in the question."}, {"input": "Context word: fit. \nQuestion: The table won't fit through the doorway because the _ is too wide. \nAnswer: table.", "output": "The table won't fit through the doorway because the _ is too narrow.", "explanation": "Here, replacing the trigger word \"wide\" by its antonym \"narrow\" flips answer to the second object (\"doorway\") in the question. That's why this is a good question."}, {"input": "Context word: water. \nQuestion: I poured water from the bottle into the cup until the _ was empty. \nAnswer: bottle.", "output": "I poured water from the bottle into the cup until the _ was full.", "explanation": "Here, replacing the trigger word \"empty\" by its antonym \"full\" flips answer to the second object (\"cup\") in the question. That's why this is a good question."}, {"input": "Context word: catch. \nQuestion: My meeting started at 4:00 and I needed to catch the train at 4:30, so there wasn't much time. Luckily, the _ was short, so it worked out. \nAnswer: meeting.", "output": "My meeting started at 4:00 and I needed to catch the train at 4:30, so there wasn't much time. Luckily, the _ was delayed, so it worked out.", "explanation": "Here, replacing the trigger word \"short\" by its antonym \"delayed\" flips answer to the second object (\"train\") in the question. So, this is a valid question."}, {"input": "Context word: candle. \nQuestion: James wanted to light the candle in the wind when on a date but the _ is too weak. \nAnswer: light.", "output": "James wanted to light the candle in the wind when on a date but the _ is too strong.", "explanation": "On replacing the trigger word \"weak\" by its antonym \"strong\", the answer flips to the second object (\"wind\") in the question. So, this is a valid question."}], "Negative Examples": [{"input": "Context word: fit. \nQuestion: The trophy doesn't fit into the brown suitcase because _ is too large. \nAnswer: trophy.", "output": "The trophy doesn't fit into the brown suitcase because there were a lot of other eseential items and jewlleries to pack and  _ is too large.", "explanation": "The problem here is that, the new question is very different from the given question. Note that, the new question must have at least 70% word overlap with the given question."}, {"input": "Context word: trade. \nQuestion: Grace was happy to trade me her sweater for my jacket. She thinks _ looks dowdy on her. \nAnswer: sweater.", "output": "Grace was happy to trade me her sweater for my jacket. She thinks _ is colored purple.", "explanation": "Here, there is an issue as both objects (\"sweater\" and \"jacket\") are equally likely to fill the blank. This makes the question ambiguous."}, {"input": "Context word: carpet. \nQuestion: While redecorating her home, Sam took out the carpet and replaced it with wood floors. The _ was old. \nAnswer: carpet.", "output": "While redecorating her home, Sam took out the carpet and replaced it with wood floors. The wood floor's feature is that _  was trendy.", "explanation": "Here the object \"wood floor\" has been used more than once in the question. Note that the two objects should be used ONCE in your question."}, {"input": "Context word: fit. \nQuestion: The table won't fit through the doorway because the _ is too wide. \nAnswer: table.", "output": "The table is brown in color which is different from the color of the _.", "explanation": "The question is based on color of objects which is different from the context word \"fit\". Note that, you must utilize the given context word while writing the question."}, {"input": "Context word: water. \nQuestion: I poured water from the bottle into the cup until the _ was empty. \nAnswer: bottle.", "output": "I poured water from the bottle into the _ until the _ was empty.", "explanation": "This question contains more than one blank. Note that, your question must contain only one blank."}, {"input": "Context word: catch. \nQuestion: My meeting started at 4:00 and I needed to catch the train at 4:30, so there wasn't much time. Luckily, the _ was short, so it worked out. \nAnswer: meeting.", "output": "My meeting started at 4:00 and I needed to catch the train at 4:30, so there wasn't much time. Luckily, the meeting was _.", "explanation": "The expected answer to this question is \"short\" which is not one of the two objects present in the question (\"train\" and \"meeting\"). Note that, the answer in your generated question must flip to another object in the question."}, {"input": "Context word: candle. \nQuestion: James wanted to light the candle in the wind when on a date but the _ is too weak. \nAnswer: light.", "output": "James wanted to light the candle in the _.", "explanation": "The issue is that the generated question has lesser than 15 words. Remember, your question must contain at least 15 and at most 30 words."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Commonsense -> Concepts and Relations -> Social Commonsense", "Commonsense -> Concepts and Relations -> Physical Commonsense"], "Instance": {"id": "task034-ccf5f05c287643f8a6d19de82a705ffa", "input": "Context Word: boyfriend. \nQuestion: The girl chose to get a game for her boyfriend instead of flowers because her boyfriend didn't like _ . \nAnswer: flowers.", "output": ["The girl chose to get a game for her boyfriend instead of flowers because her boyfriend liked _ ."]}, "Instance License": ["Apache 2.0"], "prediction": "The girl chose to get a game for her boyfriend instead of flowers because _ didn't like _."}
+{"id": "task034-8663a23ba7624510963d15b406c982b8", "Task": "task034_winogrande_question_modification_object", "Contributors": "['Swaroop Mishra', 'Daniel Khashabi']", "Source": ["winogrande"], "URL": ["https://leaderboard.allenai.org/winogrande/submissions/about"], "Categories": ["Question Rewriting"], "Reasoning": ["Commonsense Reasoning"], "Definition": ["In this task, you're given a fill-in-the-blank question that contains two object names. Additionally, you're given one answer which is one of the objects present in the question. In this task, you need to minimally change the given question so that the answer flips to another object in the question. Remember the question has to be about both objects which are related but different; for example, \"trophy\" and \"suitcase\". This task typically involves replacing one word i.e., the 'trigger word' with its antonym (e.g., changing from \"small\" to \"big\"). You should not change any content in the given question beyond a word or two, i.e., the trigger word/phrase. The expected answer to your question must not be associated with just the trigger word; instead, it should depend on the context present in the question. The expected answer should not be ambiguous. For your question, there should be an agreed upon answer to fill in the blank. Your generations should NOT contain potentially explicit, offensive, or adult content. In your generated question, retain the object names from the input question. Avoid repeating the same style or phrase in generating your modified question e.g. this task can be always solved using a simple negation i.e. by adding not, never, etc. Instead, try to increase the word diversity. Your question must contain at least 15 and at most 30 words. Your question must have at least 70% overlapping words with the given question. You must utilize the given context word while writing the question. Your question must contain only one blank. The two objects should be used ONCE in your question. Here is a list of attributes and associated contrastive words that may help write contrastive trigger words. Note that contrastive trigger words help in flipping the label.\n| Attribute | triggerword | contrastive triggerword | \n| age | old | new | \n| altitude | low | high |\n| area | small | vast | \n| brightness | dark | light | \n| clarity | obscure | clear | \n| cleanness | dirty | clean | \n| complexity | simple | complex | \n| cost | cheap | expensive |\n| density | sparse | dense |\n| depth | shallow | deep |\n| distance | near | far |  \n| electric conductivity | low | high |\n| flexibility | rigid | flexible |\n| granularity | fine | coarse | \n| hardness | soft | hard | \n| length | short | long | \n| magnitude | small | large | \n| mass | small | large | \n| odor | weak | strong | \n| pressure | low | high | \n| resistance | low | high | \n| shape | round | sharp |\n| shape | flat | spiky |\n| size | small | large | \n| sound | quiet | loud | \n| sound pitch | low | high | \n| speed | slow | fast | \n| stability | unstable | stable | \n| strength | weak | strong | \n| temperature | low | high | \n| texture | smooth | rough | \n| thermal conductivity | low | high |\n| thickness | thin | thick | \n| volume | small | large |\n| weight | light | heavy | \n| width | narrow | wide | \n| location | in | out |\n| location | up | down |\n| location | above | below |\n| location | on | off |\n| location | to | from |\n"], "Positive Examples": [{"input": "Context word: fit. \nQuestion: The trophy doesn't fit into the brown suitcase because _ is too large. \nAnswer: trophy.", "output": "The trophy doesn't fit into the brown suitcase because _ is too small.", "explanation": "Here, replacing the trigger word \"large\" by its antonym \"small\" flips answer to the second object (\"suitcase\") in the question. So, this is a valid question."}, {"input": "Context word: trade. \nQuestion: Grace was happy to trade me her sweater for my jacket. She thinks _ looks dowdy on her. \nAnswer: sweater.", "output": "Grace was happy to trade me her sweater for my jacket. She thinks _ looks great on her.", "explanation": "Here, replacing the trigger word \"dowdy\" by its antonym \"great\" flips answer to the second object (\"jacket\") in the question. Therefore, this is a valid question."}, {"input": "Context word: carpet. \nQuestion: While redecorating her home, Sam took out the carpet and replaced it with wood floors. The _ was old. \nAnswer: carpet.", "output": "While redecorating her home, Sam took out the carpet and replaced it with wood floors. The _ was trendy.", "explanation": "This is a valid question because: on replacing the trigger word \"old\" by its antonym \"trendy\", the answer flips to the second object (\"wood floors\") in the question."}, {"input": "Context word: fit. \nQuestion: The table won't fit through the doorway because the _ is too wide. \nAnswer: table.", "output": "The table won't fit through the doorway because the _ is too narrow.", "explanation": "Here, replacing the trigger word \"wide\" by its antonym \"narrow\" flips answer to the second object (\"doorway\") in the question. That's why this is a good question."}, {"input": "Context word: water. \nQuestion: I poured water from the bottle into the cup until the _ was empty. \nAnswer: bottle.", "output": "I poured water from the bottle into the cup until the _ was full.", "explanation": "Here, replacing the trigger word \"empty\" by its antonym \"full\" flips answer to the second object (\"cup\") in the question. That's why this is a good question."}, {"input": "Context word: catch. \nQuestion: My meeting started at 4:00 and I needed to catch the train at 4:30, so there wasn't much time. Luckily, the _ was short, so it worked out. \nAnswer: meeting.", "output": "My meeting started at 4:00 and I needed to catch the train at 4:30, so there wasn't much time. Luckily, the _ was delayed, so it worked out.", "explanation": "Here, replacing the trigger word \"short\" by its antonym \"delayed\" flips answer to the second object (\"train\") in the question. So, this is a valid question."}, {"input": "Context word: candle. \nQuestion: James wanted to light the candle in the wind when on a date but the _ is too weak. \nAnswer: light.", "output": "James wanted to light the candle in the wind when on a date but the _ is too strong.", "explanation": "On replacing the trigger word \"weak\" by its antonym \"strong\", the answer flips to the second object (\"wind\") in the question. So, this is a valid question."}], "Negative Examples": [{"input": "Context word: fit. \nQuestion: The trophy doesn't fit into the brown suitcase because _ is too large. \nAnswer: trophy.", "output": "The trophy doesn't fit into the brown suitcase because there were a lot of other eseential items and jewlleries to pack and  _ is too large.", "explanation": "The problem here is that, the new question is very different from the given question. Note that, the new question must have at least 70% word overlap with the given question."}, {"input": "Context word: trade. \nQuestion: Grace was happy to trade me her sweater for my jacket. She thinks _ looks dowdy on her. \nAnswer: sweater.", "output": "Grace was happy to trade me her sweater for my jacket. She thinks _ is colored purple.", "explanation": "Here, there is an issue as both objects (\"sweater\" and \"jacket\") are equally likely to fill the blank. This makes the question ambiguous."}, {"input": "Context word: carpet. \nQuestion: While redecorating her home, Sam took out the carpet and replaced it with wood floors. The _ was old. \nAnswer: carpet.", "output": "While redecorating her home, Sam took out the carpet and replaced it with wood floors. The wood floor's feature is that _  was trendy.", "explanation": "Here the object \"wood floor\" has been used more than once in the question. Note that the two objects should be used ONCE in your question."}, {"input": "Context word: fit. \nQuestion: The table won't fit through the doorway because the _ is too wide. \nAnswer: table.", "output": "The table is brown in color which is different from the color of the _.", "explanation": "The question is based on color of objects which is different from the context word \"fit\". Note that, you must utilize the given context word while writing the question."}, {"input": "Context word: water. \nQuestion: I poured water from the bottle into the cup until the _ was empty. \nAnswer: bottle.", "output": "I poured water from the bottle into the _ until the _ was empty.", "explanation": "This question contains more than one blank. Note that, your question must contain only one blank."}, {"input": "Context word: catch. \nQuestion: My meeting started at 4:00 and I needed to catch the train at 4:30, so there wasn't much time. Luckily, the _ was short, so it worked out. \nAnswer: meeting.", "output": "My meeting started at 4:00 and I needed to catch the train at 4:30, so there wasn't much time. Luckily, the meeting was _.", "explanation": "The expected answer to this question is \"short\" which is not one of the two objects present in the question (\"train\" and \"meeting\"). Note that, the answer in your generated question must flip to another object in the question."}, {"input": "Context word: candle. \nQuestion: James wanted to light the candle in the wind when on a date but the _ is too weak. \nAnswer: light.", "output": "James wanted to light the candle in the _.", "explanation": "The issue is that the generated question has lesser than 15 words. Remember, your question must contain at least 15 and at most 30 words."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Commonsense -> Concepts and Relations -> Social Commonsense", "Commonsense -> Concepts and Relations -> Physical Commonsense"], "Instance": {"id": "task034-8663a23ba7624510963d15b406c982b8", "input": "Context Word: smoking. \nQuestion: The wood was still smoking while the grass was not since _ was on fire. \nAnswer: wood.", "output": ["The wood was still smoking while the grass was not since _ was on doused."]}, "Instance License": ["Apache 2.0"], "prediction": "The grass was still smoking while the wood was still smoking."}
+{"id": "task133-2bc69d144fa74791be2ebe9d607b1177", "Task": "task133_winowhy_reason_plausibility_detection", "Contributors": "['Xinran Zhao', 'Hongming Zhang', 'Yangqiu Song']", "Source": ["winowhy"], "URL": ["https://github.com/HKUST-KnowComp/WinoWhy"], "Categories": ["Coreference Resolution"], "Reasoning": ["Commonsense Reasoning"], "Definition": ["In this task you need to indicate the plausibility of reasoning for the pronoun coreference relations. Each of the provided inputs contains a sentence with a target pronoun and a sentence that justifies which noun phrase the pronoun refers to. Correct reasons do not need to use all the knowledge from the sentence. The resolution of the pronoun coreference relations typically involve one or multiple following knowledge types about commonsense: First: 'Property', the knowledge about property of objects (e.g., ice is cold). Second: 'Object', the knowledge about objects (e.g., cats have ears). Third: 'Eventuality', the knowledge about eventuality (e.g., 'wake up' happens before 'open eyes'). Forth: 'Spatial', the knowledge about spatial position (e.g., object at the back can be blocked). Fifth: 'Quantity', the knowledge about numbers (e.g., 2 is smaller than 10). Sixth: all other knowledge if above ones are not suitable. You should answer 'Correct' if the reasoning made sense, otherwise, you should answer 'Wrong'."], "Positive Examples": [{"input": "Sentence: The city councilmen refused the demonstrators a permit because they feared violence. \n Reason: The 'they' refers to the city councilmen because city councilmen are administrative so they are more likely to fear. \n Question: Is the above reasoning correct or wrong? ", "output": "Correct", "explanation": "This is a correct reason since the pronoun in the sentence is descibed as ones who fear violence and the city councilmen are attached with this property."}, {"input": "Sentence: The city councilmen refused the demonstrators a permit because they feared violence. \n Reason: The 'they' refers to the city councilmen because of the city's history of racial discrimination. \n Question: Is the above reasoning correct or wrong? ", "output": "Wrong", "explanation": "This is a wrong reason since the reason is descibing issue that does not relates to who will fear the violence."}, {"input": "Sentence: Sentence: The trophy doesn't fit into the brown suitcase because it is too large. \n Reason: The 'it' refers to the trophy because The trophy was to be carried inside the suitcase. \n Question: Is the above reasoning correct or wrong? ", "output": "Correct", "explanation": "This is a correct reason since it suggests that the large size is more likely to become a fitting problem when it is carried insdie."}], "Negative Examples": [{"input": "Sentence: The city councilmen refused the demonstrators a permit because they feared violence. \n Reason: The 'they' refers to the city councilmen because of the city's history of racial discrimination. \n Question: Is the above reasoning correct or wrong? ", "output": "Wrong Reason", "explanation": "This is a bad example, since your answer should be 'Correct' or 'Wrong' and other answers are not acceptable."}, {"input": "Sentence: I stuck a pin through a carrot. When I pulled the pin out, it had a hole.\n Reason: The 'it' refers to the carrot because it refereed to the carrot because the pin made a hole through the carrot. \n Question: Is the above reasoning correct or wrong? ", "output": "Wrong", "explanation": "This is a correct reason since the 'it' refers to the carrot. So, the output should be 'Correct'."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Commonsense -> Concepts and Relations"], "Instance": {"id": "task133-2bc69d144fa74791be2ebe9d607b1177", "input": "Sentence: Many people start to read Paul's books and can't put them down. They are gripped because Paul writes so well.\n Reason: The 'They' refers to people because People love Paul's books. They are popular. So the books are popular, not the people. \n Question: Is the above reasoning correct or wrong? ", "output": ["Wrong"]}, "Instance License": ["MIT"], "prediction": "True"}
+{"id": "task133-819f4360df8b4823ba2c1976a4a613e4", "Task": "task133_winowhy_reason_plausibility_detection", "Contributors": "['Xinran Zhao', 'Hongming Zhang', 'Yangqiu Song']", "Source": ["winowhy"], "URL": ["https://github.com/HKUST-KnowComp/WinoWhy"], "Categories": ["Coreference Resolution"], "Reasoning": ["Commonsense Reasoning"], "Definition": ["In this task you need to indicate the plausibility of reasoning for the pronoun coreference relations. Each of the provided inputs contains a sentence with a target pronoun and a sentence that justifies which noun phrase the pronoun refers to. Correct reasons do not need to use all the knowledge from the sentence. The resolution of the pronoun coreference relations typically involve one or multiple following knowledge types about commonsense: First: 'Property', the knowledge about property of objects (e.g., ice is cold). Second: 'Object', the knowledge about objects (e.g., cats have ears). Third: 'Eventuality', the knowledge about eventuality (e.g., 'wake up' happens before 'open eyes'). Forth: 'Spatial', the knowledge about spatial position (e.g., object at the back can be blocked). Fifth: 'Quantity', the knowledge about numbers (e.g., 2 is smaller than 10). Sixth: all other knowledge if above ones are not suitable. You should answer 'Correct' if the reasoning made sense, otherwise, you should answer 'Wrong'."], "Positive Examples": [{"input": "Sentence: The city councilmen refused the demonstrators a permit because they feared violence. \n Reason: The 'they' refers to the city councilmen because city councilmen are administrative so they are more likely to fear. \n Question: Is the above reasoning correct or wrong? ", "output": "Correct", "explanation": "This is a correct reason since the pronoun in the sentence is descibed as ones who fear violence and the city councilmen are attached with this property."}, {"input": "Sentence: The city councilmen refused the demonstrators a permit because they feared violence. \n Reason: The 'they' refers to the city councilmen because of the city's history of racial discrimination. \n Question: Is the above reasoning correct or wrong? ", "output": "Wrong", "explanation": "This is a wrong reason since the reason is descibing issue that does not relates to who will fear the violence."}, {"input": "Sentence: Sentence: The trophy doesn't fit into the brown suitcase because it is too large. \n Reason: The 'it' refers to the trophy because The trophy was to be carried inside the suitcase. \n Question: Is the above reasoning correct or wrong? ", "output": "Correct", "explanation": "This is a correct reason since it suggests that the large size is more likely to become a fitting problem when it is carried insdie."}], "Negative Examples": [{"input": "Sentence: The city councilmen refused the demonstrators a permit because they feared violence. \n Reason: The 'they' refers to the city councilmen because of the city's history of racial discrimination. \n Question: Is the above reasoning correct or wrong? ", "output": "Wrong Reason", "explanation": "This is a bad example, since your answer should be 'Correct' or 'Wrong' and other answers are not acceptable."}, {"input": "Sentence: I stuck a pin through a carrot. When I pulled the pin out, it had a hole.\n Reason: The 'it' refers to the carrot because it refereed to the carrot because the pin made a hole through the carrot. \n Question: Is the above reasoning correct or wrong? ", "output": "Wrong", "explanation": "This is a correct reason since the 'it' refers to the carrot. So, the output should be 'Correct'."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Commonsense -> Concepts and Relations"], "Instance": {"id": "task133-819f4360df8b4823ba2c1976a4a613e4", "input": "Sentence: Steve follows Fred's example in everything. He admires him hugely.\n Reason: The 'He' refers to steve because fred was role model for steve. \n Question: Is the above reasoning correct or wrong? ", "output": ["Correct"]}, "Instance License": ["MIT"], "prediction": "True"}
+{"id": "task133-c282ea1a44cb4becb9dcb8a1f72cb70c", "Task": "task133_winowhy_reason_plausibility_detection", "Contributors": "['Xinran Zhao', 'Hongming Zhang', 'Yangqiu Song']", "Source": ["winowhy"], "URL": ["https://github.com/HKUST-KnowComp/WinoWhy"], "Categories": ["Coreference Resolution"], "Reasoning": ["Commonsense Reasoning"], "Definition": ["In this task you need to indicate the plausibility of reasoning for the pronoun coreference relations. Each of the provided inputs contains a sentence with a target pronoun and a sentence that justifies which noun phrase the pronoun refers to. Correct reasons do not need to use all the knowledge from the sentence. The resolution of the pronoun coreference relations typically involve one or multiple following knowledge types about commonsense: First: 'Property', the knowledge about property of objects (e.g., ice is cold). Second: 'Object', the knowledge about objects (e.g., cats have ears). Third: 'Eventuality', the knowledge about eventuality (e.g., 'wake up' happens before 'open eyes'). Forth: 'Spatial', the knowledge about spatial position (e.g., object at the back can be blocked). Fifth: 'Quantity', the knowledge about numbers (e.g., 2 is smaller than 10). Sixth: all other knowledge if above ones are not suitable. You should answer 'Correct' if the reasoning made sense, otherwise, you should answer 'Wrong'."], "Positive Examples": [{"input": "Sentence: The city councilmen refused the demonstrators a permit because they feared violence. \n Reason: The 'they' refers to the city councilmen because city councilmen are administrative so they are more likely to fear. \n Question: Is the above reasoning correct or wrong? ", "output": "Correct", "explanation": "This is a correct reason since the pronoun in the sentence is descibed as ones who fear violence and the city councilmen are attached with this property."}, {"input": "Sentence: The city councilmen refused the demonstrators a permit because they feared violence. \n Reason: The 'they' refers to the city councilmen because of the city's history of racial discrimination. \n Question: Is the above reasoning correct or wrong? ", "output": "Wrong", "explanation": "This is a wrong reason since the reason is descibing issue that does not relates to who will fear the violence."}, {"input": "Sentence: Sentence: The trophy doesn't fit into the brown suitcase because it is too large. \n Reason: The 'it' refers to the trophy because The trophy was to be carried inside the suitcase. \n Question: Is the above reasoning correct or wrong? ", "output": "Correct", "explanation": "This is a correct reason since it suggests that the large size is more likely to become a fitting problem when it is carried insdie."}], "Negative Examples": [{"input": "Sentence: The city councilmen refused the demonstrators a permit because they feared violence. \n Reason: The 'they' refers to the city councilmen because of the city's history of racial discrimination. \n Question: Is the above reasoning correct or wrong? ", "output": "Wrong Reason", "explanation": "This is a bad example, since your answer should be 'Correct' or 'Wrong' and other answers are not acceptable."}, {"input": "Sentence: I stuck a pin through a carrot. When I pulled the pin out, it had a hole.\n Reason: The 'it' refers to the carrot because it refereed to the carrot because the pin made a hole through the carrot. \n Question: Is the above reasoning correct or wrong? ", "output": "Wrong", "explanation": "This is a correct reason since the 'it' refers to the carrot. So, the output should be 'Correct'."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Commonsense -> Concepts and Relations"], "Instance": {"id": "task133-c282ea1a44cb4becb9dcb8a1f72cb70c", "input": "Sentence: I tried to paint a picture of an orchard, with lemons in the lemon trees,  but they came out looking more like light bulbs.\n Reason: The 'they' refers to lemons because lemons are round look more like a light bulb. \n Question: Is the above reasoning correct or wrong? ", "output": ["Correct"]}, "Instance License": ["MIT"], "prediction": "True"}
+{"id": "task133-64f2a52992a943cb9712a2851c343a8e", "Task": "task133_winowhy_reason_plausibility_detection", "Contributors": "['Xinran Zhao', 'Hongming Zhang', 'Yangqiu Song']", "Source": ["winowhy"], "URL": ["https://github.com/HKUST-KnowComp/WinoWhy"], "Categories": ["Coreference Resolution"], "Reasoning": ["Commonsense Reasoning"], "Definition": ["In this task you need to indicate the plausibility of reasoning for the pronoun coreference relations. Each of the provided inputs contains a sentence with a target pronoun and a sentence that justifies which noun phrase the pronoun refers to. Correct reasons do not need to use all the knowledge from the sentence. The resolution of the pronoun coreference relations typically involve one or multiple following knowledge types about commonsense: First: 'Property', the knowledge about property of objects (e.g., ice is cold). Second: 'Object', the knowledge about objects (e.g., cats have ears). Third: 'Eventuality', the knowledge about eventuality (e.g., 'wake up' happens before 'open eyes'). Forth: 'Spatial', the knowledge about spatial position (e.g., object at the back can be blocked). Fifth: 'Quantity', the knowledge about numbers (e.g., 2 is smaller than 10). Sixth: all other knowledge if above ones are not suitable. You should answer 'Correct' if the reasoning made sense, otherwise, you should answer 'Wrong'."], "Positive Examples": [{"input": "Sentence: The city councilmen refused the demonstrators a permit because they feared violence. \n Reason: The 'they' refers to the city councilmen because city councilmen are administrative so they are more likely to fear. \n Question: Is the above reasoning correct or wrong? ", "output": "Correct", "explanation": "This is a correct reason since the pronoun in the sentence is descibed as ones who fear violence and the city councilmen are attached with this property."}, {"input": "Sentence: The city councilmen refused the demonstrators a permit because they feared violence. \n Reason: The 'they' refers to the city councilmen because of the city's history of racial discrimination. \n Question: Is the above reasoning correct or wrong? ", "output": "Wrong", "explanation": "This is a wrong reason since the reason is descibing issue that does not relates to who will fear the violence."}, {"input": "Sentence: Sentence: The trophy doesn't fit into the brown suitcase because it is too large. \n Reason: The 'it' refers to the trophy because The trophy was to be carried inside the suitcase. \n Question: Is the above reasoning correct or wrong? ", "output": "Correct", "explanation": "This is a correct reason since it suggests that the large size is more likely to become a fitting problem when it is carried insdie."}], "Negative Examples": [{"input": "Sentence: The city councilmen refused the demonstrators a permit because they feared violence. \n Reason: The 'they' refers to the city councilmen because of the city's history of racial discrimination. \n Question: Is the above reasoning correct or wrong? ", "output": "Wrong Reason", "explanation": "This is a bad example, since your answer should be 'Correct' or 'Wrong' and other answers are not acceptable."}, {"input": "Sentence: I stuck a pin through a carrot. When I pulled the pin out, it had a hole.\n Reason: The 'it' refers to the carrot because it refereed to the carrot because the pin made a hole through the carrot. \n Question: Is the above reasoning correct or wrong? ", "output": "Wrong", "explanation": "This is a correct reason since the 'it' refers to the carrot. So, the output should be 'Correct'."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Commonsense -> Concepts and Relations"], "Instance": {"id": "task133-64f2a52992a943cb9712a2851c343a8e", "input": "Sentence: Alice tried frantically to stop her daughter from chatting at the party, leaving us to wonder why she was behaving so strangely.\n Reason: The 'she' refers to alice because she was the one who called out to her. \n Question: Is the above reasoning correct or wrong? ", "output": ["Wrong"]}, "Instance License": ["MIT"], "prediction": "True"}
+{"id": "task133-90cf4dc5bee9449590a7e3e6cbd91c5e", "Task": "task133_winowhy_reason_plausibility_detection", "Contributors": "['Xinran Zhao', 'Hongming Zhang', 'Yangqiu Song']", "Source": ["winowhy"], "URL": ["https://github.com/HKUST-KnowComp/WinoWhy"], "Categories": ["Coreference Resolution"], "Reasoning": ["Commonsense Reasoning"], "Definition": ["In this task you need to indicate the plausibility of reasoning for the pronoun coreference relations. Each of the provided inputs contains a sentence with a target pronoun and a sentence that justifies which noun phrase the pronoun refers to. Correct reasons do not need to use all the knowledge from the sentence. The resolution of the pronoun coreference relations typically involve one or multiple following knowledge types about commonsense: First: 'Property', the knowledge about property of objects (e.g., ice is cold). Second: 'Object', the knowledge about objects (e.g., cats have ears). Third: 'Eventuality', the knowledge about eventuality (e.g., 'wake up' happens before 'open eyes'). Forth: 'Spatial', the knowledge about spatial position (e.g., object at the back can be blocked). Fifth: 'Quantity', the knowledge about numbers (e.g., 2 is smaller than 10). Sixth: all other knowledge if above ones are not suitable. You should answer 'Correct' if the reasoning made sense, otherwise, you should answer 'Wrong'."], "Positive Examples": [{"input": "Sentence: The city councilmen refused the demonstrators a permit because they feared violence. \n Reason: The 'they' refers to the city councilmen because city councilmen are administrative so they are more likely to fear. \n Question: Is the above reasoning correct or wrong? ", "output": "Correct", "explanation": "This is a correct reason since the pronoun in the sentence is descibed as ones who fear violence and the city councilmen are attached with this property."}, {"input": "Sentence: The city councilmen refused the demonstrators a permit because they feared violence. \n Reason: The 'they' refers to the city councilmen because of the city's history of racial discrimination. \n Question: Is the above reasoning correct or wrong? ", "output": "Wrong", "explanation": "This is a wrong reason since the reason is descibing issue that does not relates to who will fear the violence."}, {"input": "Sentence: Sentence: The trophy doesn't fit into the brown suitcase because it is too large. \n Reason: The 'it' refers to the trophy because The trophy was to be carried inside the suitcase. \n Question: Is the above reasoning correct or wrong? ", "output": "Correct", "explanation": "This is a correct reason since it suggests that the large size is more likely to become a fitting problem when it is carried insdie."}], "Negative Examples": [{"input": "Sentence: The city councilmen refused the demonstrators a permit because they feared violence. \n Reason: The 'they' refers to the city councilmen because of the city's history of racial discrimination. \n Question: Is the above reasoning correct or wrong? ", "output": "Wrong Reason", "explanation": "This is a bad example, since your answer should be 'Correct' or 'Wrong' and other answers are not acceptable."}, {"input": "Sentence: I stuck a pin through a carrot. When I pulled the pin out, it had a hole.\n Reason: The 'it' refers to the carrot because it refereed to the carrot because the pin made a hole through the carrot. \n Question: Is the above reasoning correct or wrong? ", "output": "Wrong", "explanation": "This is a correct reason since the 'it' refers to the carrot. So, the output should be 'Correct'."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Commonsense -> Concepts and Relations"], "Instance": {"id": "task133-90cf4dc5bee9449590a7e3e6cbd91c5e", "input": "Sentence: John was jogging through the park when he saw a man juggling watermelons. He was very impressed.\n Reason: The 'He' refers to john because the man was the one juggling the watermelons so it's likely that John was the one impressed. \n Question: Is the above reasoning correct or wrong? ", "output": ["Correct"]}, "Instance License": ["MIT"], "prediction": "True"}
+{"id": "task226-7526fa1f4a3b4ad5951a774694afa943", "Task": "task226_english_language_answer_relevance_classification", "Contributors": "['Maitreya Patel']", "Source": ["curated_from_stack_overflow___english."], "URL": ["https://data.stackexchange.com/english/queries"], "Categories": ["Answerability Classification"], "Reasoning": [], "Definition": ["Given the Question and Answer pair, detect whether the answer is acceptable or not. Denote acceptable answer as \"yes\", otherwise denote as \"no\". An acceptable answer is consistent with the context in question, detailed, long, and uses general knowledge of English. Answers that are not definite and suggest a variety of options are not acceptable answers."], "Positive Examples": [{"input": "Question: What's the difference between the following examples: Neither of my teachers are mathematicians. None of my teachers are mathematicians. \nAnswer: Neither - not either - implies that there is a choice of only two. So 'neither of my teachers' is only correct if there are exactly two teachers, 'none of my teachers' can be any number.", "output": "yes", "explanation": "The answer is well in context with the question and gives a proper explanation to resolve it. Hence, the output \"yes\" is correct."}, {"input": "Question: If I were to try to achieve something you could say I 'had a go'. If I tried it multiple times, how would I write that down? I had many goes or I had many go's or I had many gos \nAnswer: The dictionaries I've checked seem to be unanimous that the plural of the noun 'go' is 'goes'. I didn't see one list its plural as 'gos'. However, I didn't check all dictionaries. American Heritage Dictionary: n. pl. goes Collins Dictionary: n, pl goes Merriam-Webster Dictionary: plural goes Cambridge Dictionary: plural goes Random House Unabridged Dictionary (dictionary.com): plural goes Google NGram Viewer does not show any results for 'two gos at' or 'two gos at', but does when written as 'goes'. A Google search shows the following results: 'two gos at' = 453 results. 'two goes at' = 19,500 results. 'three gos at' = 252 results. 'three goes at' = 20,200 results. Note that both Google search and Ngram Viewer may show false positives, as Google search, as far as I know, doesn't take punctuation into account when giving search results, ie., full stops, commas. But I think it's safe to assume the consensus is that the plural of go (attempt or try) is 'goes'. I think this is a good question, as somewhere in my head I have an instinct to write it 'gos'. However the answer is gotten easily by checking some dictionaries. Also, if you wrote 'I had three gos at it before giving up', I have a feeling the typical reader probably wouldn't even be surprised by it or notice it particularly as wrong. This is just my opinion. I have this feeling because the '-os'/'-oes' plural ending rules are wildly inconsistent. Potatoes, tomatoes and heroes are correct. But 'photos' and 'burritos' are correct. However most dictionaries seem to list either '-os' or '-oes' ending as acceptable in 'ghetto' and 'mosquito'. Both 'mosquito' and 'burrito' most likely come from Spanish, yet most dictionaries say only 'mosquito' can have plural ending either '-os' or 'oes', whereas they're consistent in listing '-os' for burrito plural. Same goes for 'canto', 'manifesto' and 'grotto'. These words most likely come from Italian, yet the plural of 'canto' is 'cantos', whereas the dictionaries say the plural of 'grotto' or 'manifesto' can end in either '-os' or '-oes'. Addendum As some people have claimed that the rules for -os or -oes plural endings are quite consistent (and I happen to disagree), I've included more examples to show just how unpredictable this can get. The claim generally is basically that borrowed words or imported words from other languages have -os as their endings and most everything else has -oes. The more specific claim is this rule applies for words from Romance languages specifically. embargo (Spanish): Dictionaries show only -oes plural. NGrams show -oes much more common. tornado (Spanish): Dictionaries show either -os or -oes plural. NGrams shows -oes much more common. desperado (Spanish): Dictionaries show either -os or -oes plural. NGrams shows -oes more common. cargo (Spanish) plural possibly as the pants: Dictionaries show either -os or -oes. NGrams shows -oes more common. mango (Portuguese): Dictionaries show both -os or -oes. NGrams shows -oes much more common. domino (uncertain exactly which language, but a Romance one, or maybe directly from Latin): Dictionaries give either -os or -oes. NGrams shows -oes much more common. volcano (Italian): Dictionaries give either -os or -oes. NGrams shows -oes much more common. motto (Italian): Dictionaries give either -os or -oes. NGrams shows -oes to be more common. Words taken directly from Latin many times have -oes plural ending, but not always: veto has plural vetoes torpedo has plural torpedoes However memento overwhelmingly has plural mementos. And embryo is always embryos. Echo, directly from Greek, has plural 'echoes'. hello (native English): Nearly always 'hellos'. no (native English): Much more common as 'nos', ie., 'yeses and nos'. do (native English): Dictionaries give plural as either 'dos' or 'do's'. The results for searches of these terms would be confounding to say the least. weirdo (native English): some dictionaries show both -os or -oes. NGrams shows -os is much more popular Unknown origin: hobo: Dictionaries give either -os or -oes. NGrams show roughly same frequency. gizmo: = Dictionaries only give -os, 'gizmoes' doesn't show anything in NGrams. gazebo: Dictionaries show both -os or -oes. NGrams shows -os more common. So I don't know about anyone else, but I personally need help, in many ways.", "output": "yes", "explanation": "The output is correct. Even though the answer is very long, it is in context and gives good examples to explain in every detail possible."}, {"input": "Question: I've read this and this. I know that the underlying question has been answered, my problem is of a different nature: I'm currently writing my master's thesis in CS and my professor thinks that the apostrophe possessive is only applicable to people. He claims to have spoken to a linguist from Cambridge who confirmed his opinion. Neither my professor nor I am a native speaker and the thesis is being written in Germany. Now, I know that he won't care if I just send him a couple of links to the answers here. So my question is: How do I convince my professor? Are there any 'more scientific\u2122' sources that I can point to? Examples of phrases: If each plant's humidity is displayed publicly [...] [...] shows an overview of the node's structure. Due to an issue in the network stack's IPv6 subsystem [...] \nAnswer: 'Examples of phrases: If each plant's humidity is displayed publicly [...] [...] shows an overview of the node's structure. Due to an issue in the network stack's IPv6 subsystem [...]' These examples are all good English.", "output": "no", "explanation": "The answer is not in context with the question and doesn't even provide examples for the explanation. Therefore, the output \"no\" is correct."}, {"input": "Question: Is there a noun or adjective for the following or similar: a pleading before a judge for clemency a prayer before God begging for mercy Is there a better word than 'begging', 'pleading', 'petitioning', etc.? \nAnswer: In the case of religion I would use the word 'prostrate' or 'prostration'. This is when you kneel down with your body flat before a God or religious icon. I have used the word in non religious instances too but this may not be correct.", "output": "no", "explanation": "The output is \"no\". Although it is in context with the question, it doesn't provide the definitions required to explain."}], "Negative Examples": [{"input": "Question: Possible Duplicates: How to phrase an asking sentence that must be answered with an ordinal number? Framing a question whose answer is an ordinal number Given that I want to know Barack Obama is the 44th President of U.S.A, how can I frame a question like: The how manyeth president is Barack Obama? \nAnswer: 'Which President of the United States is (or was) the 44th?' (But I'm not sure I understand the question.) EDIT: Now that I understand the question, I think you might need to put the question as How many Presidents of the US have there been, including the present one? Alternatively, Fill in the blank. 'Barack Obama is the - th President of the US'.", "output": "yes", "explanation": "The output is wrong. The correct output should be \"no\" because the answer does not clearly explain the asked question."}, {"input": "Question: Does 'egoistic' and 'egotistic' mean the same thing? \nAnswer: No. While similar, they have some important differences. Consider this note on usage from the Oxford Dictionaries: The words egoism and egotism are frequently confused, as though interchangeable, but there are distinctions worth noting. Both words derive from Latin ego ('I'), the first-person singular pronoun. Egotism, the more commonly used term , denotes an excessive sense of self-importance, too-frequent use of the word 'I,' and general arrogance and boastfulness. Egoism, a more subtle term , is perhaps best left to ethicists, for whom it denotes a view or theory of moral behavior in which self-interest is the root of moral conduct. An egoist, then , might devote considerable attention to introspection, but could be modest about it, whereas an egotist would have an exaggerated sense of the importance of his or her self-analysis, and would have to tell everyone.", "output": "no", "explanation": "The correct output should be \"yes\". Because the answer is in context with the question and provides various detailed examples with required definitions."}, {"input": "Question: We were discussing something like pre-boss era, post-boss era. What word describes the era where the boss is still there? \nAnswer: The word you might use to describe what is happening now is current. Era is rather a grand way of referring to periods with and without a boss, but I assume there is a tinge of irony in doing so.", "output": "yes", "explanation": "The output should be \"no\". Because the answer isn't providing any explanations and answer itself is wrong."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Code -> Repo -> Stack Overflow", "Linguistics"], "Instance": {"id": "task226-7526fa1f4a3b4ad5951a774694afa943", "input": "Question: Everybody deals with this phenomenon daily but I had my curiousity piqued when someone claimed that punishing the many for the actions of the few was just called \"group punishment.\" Group Punishment is simply punishing a large group of people. Is there a specific word for when a large group is punished because of the actions of the few? Such as in the following: Little Jimmy wasn't happy when the entire class was forced to work through recess because of 3 kids getting into a fight yesterday. \nAnswer: Collective punishment is the formal expression: Penalty imposed on every member of a group without regard to his or her involvement in the group's actions and conduct. Related: collective responsibility. (www.businessdictionary.com) Is collective punishment fair in the classroom?: Under the 1949 Geneva Conventions collective punishment is considered a war crime. \"No general penalty, pecuniary or otherwise, shall be inflicted upon the population on account of the acts of individuals for which they cannot be regarded as jointly and severally responsible.\" Unfortunately for our students they do not have rights as general citizens or even our war enemies and common criminals in society. They shed their rights as they enter the double doors of the school and us parents shed our ability to ask for fair treatment of our children.", "output": ["yes"]}, "Instance License": ["Unknown"], "prediction": "yes"}
+{"id": "task226-4c994ddc8d744da2b48ae9ea99d2e496", "Task": "task226_english_language_answer_relevance_classification", "Contributors": "['Maitreya Patel']", "Source": ["curated_from_stack_overflow___english."], "URL": ["https://data.stackexchange.com/english/queries"], "Categories": ["Answerability Classification"], "Reasoning": [], "Definition": ["Given the Question and Answer pair, detect whether the answer is acceptable or not. Denote acceptable answer as \"yes\", otherwise denote as \"no\". An acceptable answer is consistent with the context in question, detailed, long, and uses general knowledge of English. Answers that are not definite and suggest a variety of options are not acceptable answers."], "Positive Examples": [{"input": "Question: What's the difference between the following examples: Neither of my teachers are mathematicians. None of my teachers are mathematicians. \nAnswer: Neither - not either - implies that there is a choice of only two. So 'neither of my teachers' is only correct if there are exactly two teachers, 'none of my teachers' can be any number.", "output": "yes", "explanation": "The answer is well in context with the question and gives a proper explanation to resolve it. Hence, the output \"yes\" is correct."}, {"input": "Question: If I were to try to achieve something you could say I 'had a go'. If I tried it multiple times, how would I write that down? I had many goes or I had many go's or I had many gos \nAnswer: The dictionaries I've checked seem to be unanimous that the plural of the noun 'go' is 'goes'. I didn't see one list its plural as 'gos'. However, I didn't check all dictionaries. American Heritage Dictionary: n. pl. goes Collins Dictionary: n, pl goes Merriam-Webster Dictionary: plural goes Cambridge Dictionary: plural goes Random House Unabridged Dictionary (dictionary.com): plural goes Google NGram Viewer does not show any results for 'two gos at' or 'two gos at', but does when written as 'goes'. A Google search shows the following results: 'two gos at' = 453 results. 'two goes at' = 19,500 results. 'three gos at' = 252 results. 'three goes at' = 20,200 results. Note that both Google search and Ngram Viewer may show false positives, as Google search, as far as I know, doesn't take punctuation into account when giving search results, ie., full stops, commas. But I think it's safe to assume the consensus is that the plural of go (attempt or try) is 'goes'. I think this is a good question, as somewhere in my head I have an instinct to write it 'gos'. However the answer is gotten easily by checking some dictionaries. Also, if you wrote 'I had three gos at it before giving up', I have a feeling the typical reader probably wouldn't even be surprised by it or notice it particularly as wrong. This is just my opinion. I have this feeling because the '-os'/'-oes' plural ending rules are wildly inconsistent. Potatoes, tomatoes and heroes are correct. But 'photos' and 'burritos' are correct. However most dictionaries seem to list either '-os' or '-oes' ending as acceptable in 'ghetto' and 'mosquito'. Both 'mosquito' and 'burrito' most likely come from Spanish, yet most dictionaries say only 'mosquito' can have plural ending either '-os' or 'oes', whereas they're consistent in listing '-os' for burrito plural. Same goes for 'canto', 'manifesto' and 'grotto'. These words most likely come from Italian, yet the plural of 'canto' is 'cantos', whereas the dictionaries say the plural of 'grotto' or 'manifesto' can end in either '-os' or '-oes'. Addendum As some people have claimed that the rules for -os or -oes plural endings are quite consistent (and I happen to disagree), I've included more examples to show just how unpredictable this can get. The claim generally is basically that borrowed words or imported words from other languages have -os as their endings and most everything else has -oes. The more specific claim is this rule applies for words from Romance languages specifically. embargo (Spanish): Dictionaries show only -oes plural. NGrams show -oes much more common. tornado (Spanish): Dictionaries show either -os or -oes plural. NGrams shows -oes much more common. desperado (Spanish): Dictionaries show either -os or -oes plural. NGrams shows -oes more common. cargo (Spanish) plural possibly as the pants: Dictionaries show either -os or -oes. NGrams shows -oes more common. mango (Portuguese): Dictionaries show both -os or -oes. NGrams shows -oes much more common. domino (uncertain exactly which language, but a Romance one, or maybe directly from Latin): Dictionaries give either -os or -oes. NGrams shows -oes much more common. volcano (Italian): Dictionaries give either -os or -oes. NGrams shows -oes much more common. motto (Italian): Dictionaries give either -os or -oes. NGrams shows -oes to be more common. Words taken directly from Latin many times have -oes plural ending, but not always: veto has plural vetoes torpedo has plural torpedoes However memento overwhelmingly has plural mementos. And embryo is always embryos. Echo, directly from Greek, has plural 'echoes'. hello (native English): Nearly always 'hellos'. no (native English): Much more common as 'nos', ie., 'yeses and nos'. do (native English): Dictionaries give plural as either 'dos' or 'do's'. The results for searches of these terms would be confounding to say the least. weirdo (native English): some dictionaries show both -os or -oes. NGrams shows -os is much more popular Unknown origin: hobo: Dictionaries give either -os or -oes. NGrams show roughly same frequency. gizmo: = Dictionaries only give -os, 'gizmoes' doesn't show anything in NGrams. gazebo: Dictionaries show both -os or -oes. NGrams shows -os more common. So I don't know about anyone else, but I personally need help, in many ways.", "output": "yes", "explanation": "The output is correct. Even though the answer is very long, it is in context and gives good examples to explain in every detail possible."}, {"input": "Question: I've read this and this. I know that the underlying question has been answered, my problem is of a different nature: I'm currently writing my master's thesis in CS and my professor thinks that the apostrophe possessive is only applicable to people. He claims to have spoken to a linguist from Cambridge who confirmed his opinion. Neither my professor nor I am a native speaker and the thesis is being written in Germany. Now, I know that he won't care if I just send him a couple of links to the answers here. So my question is: How do I convince my professor? Are there any 'more scientific\u2122' sources that I can point to? Examples of phrases: If each plant's humidity is displayed publicly [...] [...] shows an overview of the node's structure. Due to an issue in the network stack's IPv6 subsystem [...] \nAnswer: 'Examples of phrases: If each plant's humidity is displayed publicly [...] [...] shows an overview of the node's structure. Due to an issue in the network stack's IPv6 subsystem [...]' These examples are all good English.", "output": "no", "explanation": "The answer is not in context with the question and doesn't even provide examples for the explanation. Therefore, the output \"no\" is correct."}, {"input": "Question: Is there a noun or adjective for the following or similar: a pleading before a judge for clemency a prayer before God begging for mercy Is there a better word than 'begging', 'pleading', 'petitioning', etc.? \nAnswer: In the case of religion I would use the word 'prostrate' or 'prostration'. This is when you kneel down with your body flat before a God or religious icon. I have used the word in non religious instances too but this may not be correct.", "output": "no", "explanation": "The output is \"no\". Although it is in context with the question, it doesn't provide the definitions required to explain."}], "Negative Examples": [{"input": "Question: Possible Duplicates: How to phrase an asking sentence that must be answered with an ordinal number? Framing a question whose answer is an ordinal number Given that I want to know Barack Obama is the 44th President of U.S.A, how can I frame a question like: The how manyeth president is Barack Obama? \nAnswer: 'Which President of the United States is (or was) the 44th?' (But I'm not sure I understand the question.) EDIT: Now that I understand the question, I think you might need to put the question as How many Presidents of the US have there been, including the present one? Alternatively, Fill in the blank. 'Barack Obama is the - th President of the US'.", "output": "yes", "explanation": "The output is wrong. The correct output should be \"no\" because the answer does not clearly explain the asked question."}, {"input": "Question: Does 'egoistic' and 'egotistic' mean the same thing? \nAnswer: No. While similar, they have some important differences. Consider this note on usage from the Oxford Dictionaries: The words egoism and egotism are frequently confused, as though interchangeable, but there are distinctions worth noting. Both words derive from Latin ego ('I'), the first-person singular pronoun. Egotism, the more commonly used term , denotes an excessive sense of self-importance, too-frequent use of the word 'I,' and general arrogance and boastfulness. Egoism, a more subtle term , is perhaps best left to ethicists, for whom it denotes a view or theory of moral behavior in which self-interest is the root of moral conduct. An egoist, then , might devote considerable attention to introspection, but could be modest about it, whereas an egotist would have an exaggerated sense of the importance of his or her self-analysis, and would have to tell everyone.", "output": "no", "explanation": "The correct output should be \"yes\". Because the answer is in context with the question and provides various detailed examples with required definitions."}, {"input": "Question: We were discussing something like pre-boss era, post-boss era. What word describes the era where the boss is still there? \nAnswer: The word you might use to describe what is happening now is current. Era is rather a grand way of referring to periods with and without a boss, but I assume there is a tinge of irony in doing so.", "output": "yes", "explanation": "The output should be \"no\". Because the answer isn't providing any explanations and answer itself is wrong."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Code -> Repo -> Stack Overflow", "Linguistics"], "Instance": {"id": "task226-4c994ddc8d744da2b48ae9ea99d2e496", "input": "Question: I must admit that I'm unsure whether or not this is the right forum for this question. It may belong to statistics and AI also. If there exists a more suitable forum, then tell me. The thing is, I want to analyse a lot of English text for an AI project (Confabulation theory). Is there an online collection of freely available English texts? Books, news would be preferred scientific texts will properly not do, due to large amounts of math etc. \nAnswer: And for modern texts, there are a lot of blogs which use various Creative Commons licenses, most commonly CC BY-SA.", "output": ["no"]}, "Instance License": ["Unknown"], "prediction": "no"}
+{"id": "task226-6e073655f7514b34a06c771ddc1e8016", "Task": "task226_english_language_answer_relevance_classification", "Contributors": "['Maitreya Patel']", "Source": ["curated_from_stack_overflow___english."], "URL": ["https://data.stackexchange.com/english/queries"], "Categories": ["Answerability Classification"], "Reasoning": [], "Definition": ["Given the Question and Answer pair, detect whether the answer is acceptable or not. Denote acceptable answer as \"yes\", otherwise denote as \"no\". An acceptable answer is consistent with the context in question, detailed, long, and uses general knowledge of English. Answers that are not definite and suggest a variety of options are not acceptable answers."], "Positive Examples": [{"input": "Question: What's the difference between the following examples: Neither of my teachers are mathematicians. None of my teachers are mathematicians. \nAnswer: Neither - not either - implies that there is a choice of only two. So 'neither of my teachers' is only correct if there are exactly two teachers, 'none of my teachers' can be any number.", "output": "yes", "explanation": "The answer is well in context with the question and gives a proper explanation to resolve it. Hence, the output \"yes\" is correct."}, {"input": "Question: If I were to try to achieve something you could say I 'had a go'. If I tried it multiple times, how would I write that down? I had many goes or I had many go's or I had many gos \nAnswer: The dictionaries I've checked seem to be unanimous that the plural of the noun 'go' is 'goes'. I didn't see one list its plural as 'gos'. However, I didn't check all dictionaries. American Heritage Dictionary: n. pl. goes Collins Dictionary: n, pl goes Merriam-Webster Dictionary: plural goes Cambridge Dictionary: plural goes Random House Unabridged Dictionary (dictionary.com): plural goes Google NGram Viewer does not show any results for 'two gos at' or 'two gos at', but does when written as 'goes'. A Google search shows the following results: 'two gos at' = 453 results. 'two goes at' = 19,500 results. 'three gos at' = 252 results. 'three goes at' = 20,200 results. Note that both Google search and Ngram Viewer may show false positives, as Google search, as far as I know, doesn't take punctuation into account when giving search results, ie., full stops, commas. But I think it's safe to assume the consensus is that the plural of go (attempt or try) is 'goes'. I think this is a good question, as somewhere in my head I have an instinct to write it 'gos'. However the answer is gotten easily by checking some dictionaries. Also, if you wrote 'I had three gos at it before giving up', I have a feeling the typical reader probably wouldn't even be surprised by it or notice it particularly as wrong. This is just my opinion. I have this feeling because the '-os'/'-oes' plural ending rules are wildly inconsistent. Potatoes, tomatoes and heroes are correct. But 'photos' and 'burritos' are correct. However most dictionaries seem to list either '-os' or '-oes' ending as acceptable in 'ghetto' and 'mosquito'. Both 'mosquito' and 'burrito' most likely come from Spanish, yet most dictionaries say only 'mosquito' can have plural ending either '-os' or 'oes', whereas they're consistent in listing '-os' for burrito plural. Same goes for 'canto', 'manifesto' and 'grotto'. These words most likely come from Italian, yet the plural of 'canto' is 'cantos', whereas the dictionaries say the plural of 'grotto' or 'manifesto' can end in either '-os' or '-oes'. Addendum As some people have claimed that the rules for -os or -oes plural endings are quite consistent (and I happen to disagree), I've included more examples to show just how unpredictable this can get. The claim generally is basically that borrowed words or imported words from other languages have -os as their endings and most everything else has -oes. The more specific claim is this rule applies for words from Romance languages specifically. embargo (Spanish): Dictionaries show only -oes plural. NGrams show -oes much more common. tornado (Spanish): Dictionaries show either -os or -oes plural. NGrams shows -oes much more common. desperado (Spanish): Dictionaries show either -os or -oes plural. NGrams shows -oes more common. cargo (Spanish) plural possibly as the pants: Dictionaries show either -os or -oes. NGrams shows -oes more common. mango (Portuguese): Dictionaries show both -os or -oes. NGrams shows -oes much more common. domino (uncertain exactly which language, but a Romance one, or maybe directly from Latin): Dictionaries give either -os or -oes. NGrams shows -oes much more common. volcano (Italian): Dictionaries give either -os or -oes. NGrams shows -oes much more common. motto (Italian): Dictionaries give either -os or -oes. NGrams shows -oes to be more common. Words taken directly from Latin many times have -oes plural ending, but not always: veto has plural vetoes torpedo has plural torpedoes However memento overwhelmingly has plural mementos. And embryo is always embryos. Echo, directly from Greek, has plural 'echoes'. hello (native English): Nearly always 'hellos'. no (native English): Much more common as 'nos', ie., 'yeses and nos'. do (native English): Dictionaries give plural as either 'dos' or 'do's'. The results for searches of these terms would be confounding to say the least. weirdo (native English): some dictionaries show both -os or -oes. NGrams shows -os is much more popular Unknown origin: hobo: Dictionaries give either -os or -oes. NGrams show roughly same frequency. gizmo: = Dictionaries only give -os, 'gizmoes' doesn't show anything in NGrams. gazebo: Dictionaries show both -os or -oes. NGrams shows -os more common. So I don't know about anyone else, but I personally need help, in many ways.", "output": "yes", "explanation": "The output is correct. Even though the answer is very long, it is in context and gives good examples to explain in every detail possible."}, {"input": "Question: I've read this and this. I know that the underlying question has been answered, my problem is of a different nature: I'm currently writing my master's thesis in CS and my professor thinks that the apostrophe possessive is only applicable to people. He claims to have spoken to a linguist from Cambridge who confirmed his opinion. Neither my professor nor I am a native speaker and the thesis is being written in Germany. Now, I know that he won't care if I just send him a couple of links to the answers here. So my question is: How do I convince my professor? Are there any 'more scientific\u2122' sources that I can point to? Examples of phrases: If each plant's humidity is displayed publicly [...] [...] shows an overview of the node's structure. Due to an issue in the network stack's IPv6 subsystem [...] \nAnswer: 'Examples of phrases: If each plant's humidity is displayed publicly [...] [...] shows an overview of the node's structure. Due to an issue in the network stack's IPv6 subsystem [...]' These examples are all good English.", "output": "no", "explanation": "The answer is not in context with the question and doesn't even provide examples for the explanation. Therefore, the output \"no\" is correct."}, {"input": "Question: Is there a noun or adjective for the following or similar: a pleading before a judge for clemency a prayer before God begging for mercy Is there a better word than 'begging', 'pleading', 'petitioning', etc.? \nAnswer: In the case of religion I would use the word 'prostrate' or 'prostration'. This is when you kneel down with your body flat before a God or religious icon. I have used the word in non religious instances too but this may not be correct.", "output": "no", "explanation": "The output is \"no\". Although it is in context with the question, it doesn't provide the definitions required to explain."}], "Negative Examples": [{"input": "Question: Possible Duplicates: How to phrase an asking sentence that must be answered with an ordinal number? Framing a question whose answer is an ordinal number Given that I want to know Barack Obama is the 44th President of U.S.A, how can I frame a question like: The how manyeth president is Barack Obama? \nAnswer: 'Which President of the United States is (or was) the 44th?' (But I'm not sure I understand the question.) EDIT: Now that I understand the question, I think you might need to put the question as How many Presidents of the US have there been, including the present one? Alternatively, Fill in the blank. 'Barack Obama is the - th President of the US'.", "output": "yes", "explanation": "The output is wrong. The correct output should be \"no\" because the answer does not clearly explain the asked question."}, {"input": "Question: Does 'egoistic' and 'egotistic' mean the same thing? \nAnswer: No. While similar, they have some important differences. Consider this note on usage from the Oxford Dictionaries: The words egoism and egotism are frequently confused, as though interchangeable, but there are distinctions worth noting. Both words derive from Latin ego ('I'), the first-person singular pronoun. Egotism, the more commonly used term , denotes an excessive sense of self-importance, too-frequent use of the word 'I,' and general arrogance and boastfulness. Egoism, a more subtle term , is perhaps best left to ethicists, for whom it denotes a view or theory of moral behavior in which self-interest is the root of moral conduct. An egoist, then , might devote considerable attention to introspection, but could be modest about it, whereas an egotist would have an exaggerated sense of the importance of his or her self-analysis, and would have to tell everyone.", "output": "no", "explanation": "The correct output should be \"yes\". Because the answer is in context with the question and provides various detailed examples with required definitions."}, {"input": "Question: We were discussing something like pre-boss era, post-boss era. What word describes the era where the boss is still there? \nAnswer: The word you might use to describe what is happening now is current. Era is rather a grand way of referring to periods with and without a boss, but I assume there is a tinge of irony in doing so.", "output": "yes", "explanation": "The output should be \"no\". Because the answer isn't providing any explanations and answer itself is wrong."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Code -> Repo -> Stack Overflow", "Linguistics"], "Instance": {"id": "task226-6e073655f7514b34a06c771ddc1e8016", "input": "Question: English isn't my mother tongue, and when we recently talked to a native speaker (during some company audit), he pointed out that the plural word \"trainings\" is actually wrong (he pointed that it is a very common mistake and was almost amused by it). I couldn't understand why and wondered what the correct plural of \"training\" would be. Online Dictionaries/Thesaurus don't answer it, so it's probably another opinion-based statement. I haven't found a source to back it up, though. \nAnswer: I agree with Mick that training is an uncountable noun. In the example given by Mr. Fine of a specific training event allowing training to become countable, I disagree. In the case of becoming countable, the portion being counted is the event. Therefor, it would be \"there are multiple training events available at the pavilion\" (or whatever). I see many cases where much effort is made to \"fix\" the plural when a simple rewording will eliminate the contentious context and allow an, arguably, better flow by using the standard form.", "output": ["no"]}, "Instance License": ["Unknown"], "prediction": "yes"}
+{"id": "task226-e76bf97a69654eb19a188f10034e5701", "Task": "task226_english_language_answer_relevance_classification", "Contributors": "['Maitreya Patel']", "Source": ["curated_from_stack_overflow___english."], "URL": ["https://data.stackexchange.com/english/queries"], "Categories": ["Answerability Classification"], "Reasoning": [], "Definition": ["Given the Question and Answer pair, detect whether the answer is acceptable or not. Denote acceptable answer as \"yes\", otherwise denote as \"no\". An acceptable answer is consistent with the context in question, detailed, long, and uses general knowledge of English. Answers that are not definite and suggest a variety of options are not acceptable answers."], "Positive Examples": [{"input": "Question: What's the difference between the following examples: Neither of my teachers are mathematicians. None of my teachers are mathematicians. \nAnswer: Neither - not either - implies that there is a choice of only two. So 'neither of my teachers' is only correct if there are exactly two teachers, 'none of my teachers' can be any number.", "output": "yes", "explanation": "The answer is well in context with the question and gives a proper explanation to resolve it. Hence, the output \"yes\" is correct."}, {"input": "Question: If I were to try to achieve something you could say I 'had a go'. If I tried it multiple times, how would I write that down? I had many goes or I had many go's or I had many gos \nAnswer: The dictionaries I've checked seem to be unanimous that the plural of the noun 'go' is 'goes'. I didn't see one list its plural as 'gos'. However, I didn't check all dictionaries. American Heritage Dictionary: n. pl. goes Collins Dictionary: n, pl goes Merriam-Webster Dictionary: plural goes Cambridge Dictionary: plural goes Random House Unabridged Dictionary (dictionary.com): plural goes Google NGram Viewer does not show any results for 'two gos at' or 'two gos at', but does when written as 'goes'. A Google search shows the following results: 'two gos at' = 453 results. 'two goes at' = 19,500 results. 'three gos at' = 252 results. 'three goes at' = 20,200 results. Note that both Google search and Ngram Viewer may show false positives, as Google search, as far as I know, doesn't take punctuation into account when giving search results, ie., full stops, commas. But I think it's safe to assume the consensus is that the plural of go (attempt or try) is 'goes'. I think this is a good question, as somewhere in my head I have an instinct to write it 'gos'. However the answer is gotten easily by checking some dictionaries. Also, if you wrote 'I had three gos at it before giving up', I have a feeling the typical reader probably wouldn't even be surprised by it or notice it particularly as wrong. This is just my opinion. I have this feeling because the '-os'/'-oes' plural ending rules are wildly inconsistent. Potatoes, tomatoes and heroes are correct. But 'photos' and 'burritos' are correct. However most dictionaries seem to list either '-os' or '-oes' ending as acceptable in 'ghetto' and 'mosquito'. Both 'mosquito' and 'burrito' most likely come from Spanish, yet most dictionaries say only 'mosquito' can have plural ending either '-os' or 'oes', whereas they're consistent in listing '-os' for burrito plural. Same goes for 'canto', 'manifesto' and 'grotto'. These words most likely come from Italian, yet the plural of 'canto' is 'cantos', whereas the dictionaries say the plural of 'grotto' or 'manifesto' can end in either '-os' or '-oes'. Addendum As some people have claimed that the rules for -os or -oes plural endings are quite consistent (and I happen to disagree), I've included more examples to show just how unpredictable this can get. The claim generally is basically that borrowed words or imported words from other languages have -os as their endings and most everything else has -oes. The more specific claim is this rule applies for words from Romance languages specifically. embargo (Spanish): Dictionaries show only -oes plural. NGrams show -oes much more common. tornado (Spanish): Dictionaries show either -os or -oes plural. NGrams shows -oes much more common. desperado (Spanish): Dictionaries show either -os or -oes plural. NGrams shows -oes more common. cargo (Spanish) plural possibly as the pants: Dictionaries show either -os or -oes. NGrams shows -oes more common. mango (Portuguese): Dictionaries show both -os or -oes. NGrams shows -oes much more common. domino (uncertain exactly which language, but a Romance one, or maybe directly from Latin): Dictionaries give either -os or -oes. NGrams shows -oes much more common. volcano (Italian): Dictionaries give either -os or -oes. NGrams shows -oes much more common. motto (Italian): Dictionaries give either -os or -oes. NGrams shows -oes to be more common. Words taken directly from Latin many times have -oes plural ending, but not always: veto has plural vetoes torpedo has plural torpedoes However memento overwhelmingly has plural mementos. And embryo is always embryos. Echo, directly from Greek, has plural 'echoes'. hello (native English): Nearly always 'hellos'. no (native English): Much more common as 'nos', ie., 'yeses and nos'. do (native English): Dictionaries give plural as either 'dos' or 'do's'. The results for searches of these terms would be confounding to say the least. weirdo (native English): some dictionaries show both -os or -oes. NGrams shows -os is much more popular Unknown origin: hobo: Dictionaries give either -os or -oes. NGrams show roughly same frequency. gizmo: = Dictionaries only give -os, 'gizmoes' doesn't show anything in NGrams. gazebo: Dictionaries show both -os or -oes. NGrams shows -os more common. So I don't know about anyone else, but I personally need help, in many ways.", "output": "yes", "explanation": "The output is correct. Even though the answer is very long, it is in context and gives good examples to explain in every detail possible."}, {"input": "Question: I've read this and this. I know that the underlying question has been answered, my problem is of a different nature: I'm currently writing my master's thesis in CS and my professor thinks that the apostrophe possessive is only applicable to people. He claims to have spoken to a linguist from Cambridge who confirmed his opinion. Neither my professor nor I am a native speaker and the thesis is being written in Germany. Now, I know that he won't care if I just send him a couple of links to the answers here. So my question is: How do I convince my professor? Are there any 'more scientific\u2122' sources that I can point to? Examples of phrases: If each plant's humidity is displayed publicly [...] [...] shows an overview of the node's structure. Due to an issue in the network stack's IPv6 subsystem [...] \nAnswer: 'Examples of phrases: If each plant's humidity is displayed publicly [...] [...] shows an overview of the node's structure. Due to an issue in the network stack's IPv6 subsystem [...]' These examples are all good English.", "output": "no", "explanation": "The answer is not in context with the question and doesn't even provide examples for the explanation. Therefore, the output \"no\" is correct."}, {"input": "Question: Is there a noun or adjective for the following or similar: a pleading before a judge for clemency a prayer before God begging for mercy Is there a better word than 'begging', 'pleading', 'petitioning', etc.? \nAnswer: In the case of religion I would use the word 'prostrate' or 'prostration'. This is when you kneel down with your body flat before a God or religious icon. I have used the word in non religious instances too but this may not be correct.", "output": "no", "explanation": "The output is \"no\". Although it is in context with the question, it doesn't provide the definitions required to explain."}], "Negative Examples": [{"input": "Question: Possible Duplicates: How to phrase an asking sentence that must be answered with an ordinal number? Framing a question whose answer is an ordinal number Given that I want to know Barack Obama is the 44th President of U.S.A, how can I frame a question like: The how manyeth president is Barack Obama? \nAnswer: 'Which President of the United States is (or was) the 44th?' (But I'm not sure I understand the question.) EDIT: Now that I understand the question, I think you might need to put the question as How many Presidents of the US have there been, including the present one? Alternatively, Fill in the blank. 'Barack Obama is the - th President of the US'.", "output": "yes", "explanation": "The output is wrong. The correct output should be \"no\" because the answer does not clearly explain the asked question."}, {"input": "Question: Does 'egoistic' and 'egotistic' mean the same thing? \nAnswer: No. While similar, they have some important differences. Consider this note on usage from the Oxford Dictionaries: The words egoism and egotism are frequently confused, as though interchangeable, but there are distinctions worth noting. Both words derive from Latin ego ('I'), the first-person singular pronoun. Egotism, the more commonly used term , denotes an excessive sense of self-importance, too-frequent use of the word 'I,' and general arrogance and boastfulness. Egoism, a more subtle term , is perhaps best left to ethicists, for whom it denotes a view or theory of moral behavior in which self-interest is the root of moral conduct. An egoist, then , might devote considerable attention to introspection, but could be modest about it, whereas an egotist would have an exaggerated sense of the importance of his or her self-analysis, and would have to tell everyone.", "output": "no", "explanation": "The correct output should be \"yes\". Because the answer is in context with the question and provides various detailed examples with required definitions."}, {"input": "Question: We were discussing something like pre-boss era, post-boss era. What word describes the era where the boss is still there? \nAnswer: The word you might use to describe what is happening now is current. Era is rather a grand way of referring to periods with and without a boss, but I assume there is a tinge of irony in doing so.", "output": "yes", "explanation": "The output should be \"no\". Because the answer isn't providing any explanations and answer itself is wrong."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Code -> Repo -> Stack Overflow", "Linguistics"], "Instance": {"id": "task226-e76bf97a69654eb19a188f10034e5701", "input": "Question: When it comes to cities and boats named after saints, it seems that \"Santa\" is always female and \"San\" is always male. e.g. Male Saints: San Diego, San Francisco, San Antonio Female Saints: Santa Barbara, Santa Maria So why isn't \"Santa Claus\" a woman like all the other \"Santa\"s? \nAnswer: The city names you quote are all derived from Spanish, where \"San\" (or \"Santo\", as @tchrist clarifies below) is the male inflection and \"Santa\" the female one. However, Santa Claus isn't derived from Spanish, but from Dutch, where it was originally rendered as Sante Klaas, and was modified to Santa when it was adopted into English (and from English, to the rest of the world). Here's Etymonline's take on it: from dialectal Dutch Sante Klaas, from Middle Dutch Sinter Niklaas \"Saint Nicholas,\" English, like all other languages, borrows words from many sources, and they often carry over remnants of their original grammar or usage, even when it makes for inconsistent usage in English.", "output": ["yes"]}, "Instance License": ["Unknown"], "prediction": "yes"}
+{"id": "task226-a1e97cfaba554ea6a32bf3c5ce379d75", "Task": "task226_english_language_answer_relevance_classification", "Contributors": "['Maitreya Patel']", "Source": ["curated_from_stack_overflow___english."], "URL": ["https://data.stackexchange.com/english/queries"], "Categories": ["Answerability Classification"], "Reasoning": [], "Definition": ["Given the Question and Answer pair, detect whether the answer is acceptable or not. Denote acceptable answer as \"yes\", otherwise denote as \"no\". An acceptable answer is consistent with the context in question, detailed, long, and uses general knowledge of English. Answers that are not definite and suggest a variety of options are not acceptable answers."], "Positive Examples": [{"input": "Question: What's the difference between the following examples: Neither of my teachers are mathematicians. None of my teachers are mathematicians. \nAnswer: Neither - not either - implies that there is a choice of only two. So 'neither of my teachers' is only correct if there are exactly two teachers, 'none of my teachers' can be any number.", "output": "yes", "explanation": "The answer is well in context with the question and gives a proper explanation to resolve it. Hence, the output \"yes\" is correct."}, {"input": "Question: If I were to try to achieve something you could say I 'had a go'. If I tried it multiple times, how would I write that down? I had many goes or I had many go's or I had many gos \nAnswer: The dictionaries I've checked seem to be unanimous that the plural of the noun 'go' is 'goes'. I didn't see one list its plural as 'gos'. However, I didn't check all dictionaries. American Heritage Dictionary: n. pl. goes Collins Dictionary: n, pl goes Merriam-Webster Dictionary: plural goes Cambridge Dictionary: plural goes Random House Unabridged Dictionary (dictionary.com): plural goes Google NGram Viewer does not show any results for 'two gos at' or 'two gos at', but does when written as 'goes'. A Google search shows the following results: 'two gos at' = 453 results. 'two goes at' = 19,500 results. 'three gos at' = 252 results. 'three goes at' = 20,200 results. Note that both Google search and Ngram Viewer may show false positives, as Google search, as far as I know, doesn't take punctuation into account when giving search results, ie., full stops, commas. But I think it's safe to assume the consensus is that the plural of go (attempt or try) is 'goes'. I think this is a good question, as somewhere in my head I have an instinct to write it 'gos'. However the answer is gotten easily by checking some dictionaries. Also, if you wrote 'I had three gos at it before giving up', I have a feeling the typical reader probably wouldn't even be surprised by it or notice it particularly as wrong. This is just my opinion. I have this feeling because the '-os'/'-oes' plural ending rules are wildly inconsistent. Potatoes, tomatoes and heroes are correct. But 'photos' and 'burritos' are correct. However most dictionaries seem to list either '-os' or '-oes' ending as acceptable in 'ghetto' and 'mosquito'. Both 'mosquito' and 'burrito' most likely come from Spanish, yet most dictionaries say only 'mosquito' can have plural ending either '-os' or 'oes', whereas they're consistent in listing '-os' for burrito plural. Same goes for 'canto', 'manifesto' and 'grotto'. These words most likely come from Italian, yet the plural of 'canto' is 'cantos', whereas the dictionaries say the plural of 'grotto' or 'manifesto' can end in either '-os' or '-oes'. Addendum As some people have claimed that the rules for -os or -oes plural endings are quite consistent (and I happen to disagree), I've included more examples to show just how unpredictable this can get. The claim generally is basically that borrowed words or imported words from other languages have -os as their endings and most everything else has -oes. The more specific claim is this rule applies for words from Romance languages specifically. embargo (Spanish): Dictionaries show only -oes plural. NGrams show -oes much more common. tornado (Spanish): Dictionaries show either -os or -oes plural. NGrams shows -oes much more common. desperado (Spanish): Dictionaries show either -os or -oes plural. NGrams shows -oes more common. cargo (Spanish) plural possibly as the pants: Dictionaries show either -os or -oes. NGrams shows -oes more common. mango (Portuguese): Dictionaries show both -os or -oes. NGrams shows -oes much more common. domino (uncertain exactly which language, but a Romance one, or maybe directly from Latin): Dictionaries give either -os or -oes. NGrams shows -oes much more common. volcano (Italian): Dictionaries give either -os or -oes. NGrams shows -oes much more common. motto (Italian): Dictionaries give either -os or -oes. NGrams shows -oes to be more common. Words taken directly from Latin many times have -oes plural ending, but not always: veto has plural vetoes torpedo has plural torpedoes However memento overwhelmingly has plural mementos. And embryo is always embryos. Echo, directly from Greek, has plural 'echoes'. hello (native English): Nearly always 'hellos'. no (native English): Much more common as 'nos', ie., 'yeses and nos'. do (native English): Dictionaries give plural as either 'dos' or 'do's'. The results for searches of these terms would be confounding to say the least. weirdo (native English): some dictionaries show both -os or -oes. NGrams shows -os is much more popular Unknown origin: hobo: Dictionaries give either -os or -oes. NGrams show roughly same frequency. gizmo: = Dictionaries only give -os, 'gizmoes' doesn't show anything in NGrams. gazebo: Dictionaries show both -os or -oes. NGrams shows -os more common. So I don't know about anyone else, but I personally need help, in many ways.", "output": "yes", "explanation": "The output is correct. Even though the answer is very long, it is in context and gives good examples to explain in every detail possible."}, {"input": "Question: I've read this and this. I know that the underlying question has been answered, my problem is of a different nature: I'm currently writing my master's thesis in CS and my professor thinks that the apostrophe possessive is only applicable to people. He claims to have spoken to a linguist from Cambridge who confirmed his opinion. Neither my professor nor I am a native speaker and the thesis is being written in Germany. Now, I know that he won't care if I just send him a couple of links to the answers here. So my question is: How do I convince my professor? Are there any 'more scientific\u2122' sources that I can point to? Examples of phrases: If each plant's humidity is displayed publicly [...] [...] shows an overview of the node's structure. Due to an issue in the network stack's IPv6 subsystem [...] \nAnswer: 'Examples of phrases: If each plant's humidity is displayed publicly [...] [...] shows an overview of the node's structure. Due to an issue in the network stack's IPv6 subsystem [...]' These examples are all good English.", "output": "no", "explanation": "The answer is not in context with the question and doesn't even provide examples for the explanation. Therefore, the output \"no\" is correct."}, {"input": "Question: Is there a noun or adjective for the following or similar: a pleading before a judge for clemency a prayer before God begging for mercy Is there a better word than 'begging', 'pleading', 'petitioning', etc.? \nAnswer: In the case of religion I would use the word 'prostrate' or 'prostration'. This is when you kneel down with your body flat before a God or religious icon. I have used the word in non religious instances too but this may not be correct.", "output": "no", "explanation": "The output is \"no\". Although it is in context with the question, it doesn't provide the definitions required to explain."}], "Negative Examples": [{"input": "Question: Possible Duplicates: How to phrase an asking sentence that must be answered with an ordinal number? Framing a question whose answer is an ordinal number Given that I want to know Barack Obama is the 44th President of U.S.A, how can I frame a question like: The how manyeth president is Barack Obama? \nAnswer: 'Which President of the United States is (or was) the 44th?' (But I'm not sure I understand the question.) EDIT: Now that I understand the question, I think you might need to put the question as How many Presidents of the US have there been, including the present one? Alternatively, Fill in the blank. 'Barack Obama is the - th President of the US'.", "output": "yes", "explanation": "The output is wrong. The correct output should be \"no\" because the answer does not clearly explain the asked question."}, {"input": "Question: Does 'egoistic' and 'egotistic' mean the same thing? \nAnswer: No. While similar, they have some important differences. Consider this note on usage from the Oxford Dictionaries: The words egoism and egotism are frequently confused, as though interchangeable, but there are distinctions worth noting. Both words derive from Latin ego ('I'), the first-person singular pronoun. Egotism, the more commonly used term , denotes an excessive sense of self-importance, too-frequent use of the word 'I,' and general arrogance and boastfulness. Egoism, a more subtle term , is perhaps best left to ethicists, for whom it denotes a view or theory of moral behavior in which self-interest is the root of moral conduct. An egoist, then , might devote considerable attention to introspection, but could be modest about it, whereas an egotist would have an exaggerated sense of the importance of his or her self-analysis, and would have to tell everyone.", "output": "no", "explanation": "The correct output should be \"yes\". Because the answer is in context with the question and provides various detailed examples with required definitions."}, {"input": "Question: We were discussing something like pre-boss era, post-boss era. What word describes the era where the boss is still there? \nAnswer: The word you might use to describe what is happening now is current. Era is rather a grand way of referring to periods with and without a boss, but I assume there is a tinge of irony in doing so.", "output": "yes", "explanation": "The output should be \"no\". Because the answer isn't providing any explanations and answer itself is wrong."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Code -> Repo -> Stack Overflow", "Linguistics"], "Instance": {"id": "task226-a1e97cfaba554ea6a32bf3c5ce379d75", "input": "Question: E.g. is short for exempli gratia, and is in common use to introduce an example within a sentence. Submit a sample of academic writing, e.g., a dissertation chapter. However, some authors use ex. or ex: (short for \"example\") for the same purpose, and this form is listed in some authorities like the Wiktionary. Submit a sample of academic writing, ex: a dissertation chapter. I know they both roughly mean \"example\", but which one should I use, and when? Are there connotations associated with one or the other? This question has been asked elsewhere, and this very answer comes up when you ask Google about the difference. It would be good to get an EL&U answer for it. \nAnswer: \"Ex.\" is not very common, but it may be used to refer to a cited example, eg \"See ex. 3\". \"E.g.\" is much more common, and is used to introduce an example, or series of examples. In speech, it is usually replaced by \"for example\".", "output": ["no"]}, "Instance License": ["Unknown"], "prediction": "yes"}
+{"id": "task510-98904f8af5604b228767e69389448468", "Task": "task510_reddit_tifu_title_summarization", "Contributors": "['Shailaja Keyur Sampat']", "Source": ["reddit_tifu_dataset"], "URL": ["https://aclanthology.org/N19-1260.pdf"], "Categories": ["Title Generation"], "Reasoning": ["Reasoning on Social Interactions", "Reasoning on Actions"], "Definition": ["In this task, you are given a Reddit post as a text. Your task is to generate a title for this text. The title should start with \"TIFU by\", followed by a situation that caused humor. The title should contain 7-12 words, ideally."], "Positive Examples": [{"input": "Text: title speaks for itself really... \ni just wasted $1500 of my parents' money.\ni feel terrible.\n\nedit: i guess it wasn't that i took the wrong class, but the class i was taking wouldn't transfer credits over to my university. so really it was my negligence to do more research in the matter. gg", "output": "TIFU by taking the wrong class for 2 weeks and only realizing it today", "explanation": "This title is appropriate for the given text post because the focus of this post is about a humorous situation caused by \"taking the wrong class\"."}, {"input": "Text: this happened several years ago. i had a friend \"jack\" (more like an acquaintance) who got married several years ago. i attended the wedding in houston and all was good. i had moved to chicago shortly after and didn't really keep in touch. about 2 years later, i was in houston over the holidays and ran into him at a family holiday party. the conversation went like this:\n\n&nbsp;\n\n\"hey jack, it's been a long time! how are you doing?! how's married life treating you?\"\n\n&nbsp;\n\n\"i got divorced.\"\n\n&nbsp;\n\n\"oh.\"  (fml, awkwardness ensues). feeling like a jackass, i apologized and did my best to end the conversation quickly.", "output": "TIFU by asking a friend about his married life", "explanation": "This title is appropriate for the given text post because the focus of this post is about a humorous situation caused by \"asking a friend about his married life who is divorced\"."}, {"input": "Text: this happened a couple of months ago. in my office we have pcs to work upon. i was due for a location change so i thought it would be good to just put the important data onto some shared folder and then access it from the other location when i reach there. i zipped all the official data and just when i was about to upload the company policy came to my mind. password protect all your data when on shared drives. i protected it using 7zip and put in onto the drive. reached the other location, opened the drive and realized i don't remember the password. tried everything that i could possibly think of (even 12345 & qwerty), even email passwords but it just would not open. could not even use cracks or anything in company systems. sadly gave up hope and lost around 3gb useful data. :/\n\nps: the shared folder was only accessible to me. setting a password for a file in a folder that is only accessible to me. it could not get worse than this.", "output": "TIFU by forgetting password", "explanation": "This title is appropriate for the given text post because the focus of this post is about a humorous situation caused by \"forgetting password\"."}], "Negative Examples": [{"input": "Text: i applied for a job a week or two back thinking that there was no way i was going to get it b/c i didn't 100% match up with the qualifications. i went to the 2nd round interview to practice/ know what to expect for next time. surprise! i am offered the job, much rejoicing. being the paranoid sort, i asked the people i told not to babble about it, until after i had done the drug test and started training. i don't do drugs but i just wanted everything set up before people got excited for me. which brings us to today. i go to in-processing appointment do the whole \" this is my social security card\" dance.  and then i must be tested. not worried, aside from wondering if i drank enough water. i am ready to go even have my temporary new parking pass in my hands. and\u2026i test positive for opioids. i am totally shocked for a second. she asks if i am on meds (and i am but not the kind that would show up on the test.) and then i remember. breakfast. the everything bagel and cream cheese i eat almost every morning. (my digestive system is weird so what i eat for breakfast is kind of limited.) soo\u2026they took my parking pass away and told me they would call me later in the week, after further testing. i have no idea what levels i have going on b/c again i eat them almost every morning.", "output": "TIFU by eating a pumpkin-pie.", "explanation": "This title is inappropriate for the given text post because the focus of this post is about a humorous situation caused by \"eating a bagel\" and not by \"eating a pumpkin-pie.\"."}, {"input": "Text: this happened about 30 minutes ago.  i am a 17 year old senior in high school with an important paper due tommorow.  i was trying to relax my nerves and get the creative juices flowing by lighting a candle. the pleasant scent did relax me and allowed me to bust out half this paper, while at the same time forcing me into a deep slumber. fast forward 45 mins and mama kirrydragons comes into the room screaming and yelling that i need to finish this paper. i frantically get up and try to focus. the candle is still lit and needs to be disposed. now in my half-asleep state i decided to dump all the wax down my bathroom sink. sadly wax has this amazing ability to cool and solidify in .3 seconds. now im frantically trying to finish this paper and pour drain-o through a clogged sink.", "output": "TIFU by fixing a sink.", "explanation": "This title is inappropriate for the given text post because the focus of this post is about a humorous situation caused by \"breaking a sink\" and not by \"fixing a sink.\"."}, {"input": "Text: i (22f) am a server at a restaurant. last week we had lone male customer come in, and asked to be seated by the window (my area of serving) we immediately hit it off. he was older than me, had a sexy scottish accent, hilariously witty and very out-going. i was thrilled when he left his number on the back of the bill. fast forward one week: after a few small talk texts we decided to meet up, and agree at 3:00pm at the city fountain, right downtown in a busy area. i arrive a few minutes early, and decide to sit in the shade of a nearby statue and wait. within seconds an older, relativley handsome guy wearing sunglasses approaches me. \"hey, it's great to see you!\"\ni smile and greet him, and he immediatley lunges into some big 5 minute long story about a fender bender he got into on his way driving to meet me, and apologized profusseley for being late. by this point i could clearly tell he didn't have a scottish accent. \"you don't have nearly as much of an accent that i thought you did, am i crazy?\", he laughed and gave me a weird look, agreeing how i must be crazy because he has never had an accent. we continue walking slowly on the downtown strip, making more small talk. by this point i had a feeling something was off.. i could've sworn the accent was the main reason i had been drawn to him in the first place. when he asks me how to produce my name, as the \"o with the dots\" is relativley uncommon in our country. i say my name (which has the letter o not \u00f6) and he is immediatley giving me a weird look. we stop in the middle of the pathway surrounded by people walking. he takes off his sunglasses, revealing an unfamiliar face. you're not ben are you?\" i ask awkwardly, to which he shakes his head. we both burst out in laughter, realizing we clearly fucked up. \"i'm supposed to be meeting a girl i've met online, down bedside that statue at 2:30! she's a redhead but i haven't a picture of her face!\" we speed walk back to the fountain, both almost in tears due to the hilariously embarrassing moment that we found ourselves in. we part ways just before the fountain, and i see my real date sitting reading a book. didnt mention the ridiculous event that happened moments before, and had a terrific date.", "output": "TIFU by going on a date with my boyfriend", "explanation": "This title is inappropriate for the given text post because the focus of this post is about a humorous situation caused by \"going on a date with the wrong stranger\" and not with \"person's boyfriend\"."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Social Media -> Reddit"], "Instance": {"id": "task510-98904f8af5604b228767e69389448468", "input": "Text: sorry for the formatting, i'm on mobile\nmandatory \"this happened 3years ago\"\n\nso this is my story. i live in a third world country (bangladesh) where gaming consoles and accessories are extremely overpriced. our family goes on yearly trips to australia to visit family and friends. being the avid gamer i am, i decided to buy the all new ps4. i had saved up my birthday money from the last 2 years and with a little bit of help from my mom, i would be able to afford the console. so when i arrive in australia, the first thing i do is i get the much awaited console in a bundle with killzone shadow fall, fifa 14 and need for speed rivals. i play on the console a couple of times before packing it up in the box itself. since the trip is so long, we have to stop by singapore for a couple of days. i travelled with the ps4 box like a briefcase and used it as hand luggage. so the day my family and i leave for bangladesh, we leave our luggage at the airport before, so we don't have to deal with the hassle with bringing them along. i only have my backpack and ps4 box in my hand as i move into immigration. i decided to put the box in one of those trolley things. as we entered the waiting room for the flight, i had returned the trolley with my ps4 in it. unbeknownst to me, i hoarded the plane all excited to play my console back at home. it was then i realised that i had lost my ps4. thats $550 aud i'll never get back and a broken heart.", "output": ["TIFU By losing my PS4"]}, "Instance License": ["MIT"], "prediction": "TIFU by buying a console in a third world country."}
+{"id": "task510-5348ce4bf822478d909e0d4deae016de", "Task": "task510_reddit_tifu_title_summarization", "Contributors": "['Shailaja Keyur Sampat']", "Source": ["reddit_tifu_dataset"], "URL": ["https://aclanthology.org/N19-1260.pdf"], "Categories": ["Title Generation"], "Reasoning": ["Reasoning on Social Interactions", "Reasoning on Actions"], "Definition": ["In this task, you are given a Reddit post as a text. Your task is to generate a title for this text. The title should start with \"TIFU by\", followed by a situation that caused humor. The title should contain 7-12 words, ideally."], "Positive Examples": [{"input": "Text: title speaks for itself really... \ni just wasted $1500 of my parents' money.\ni feel terrible.\n\nedit: i guess it wasn't that i took the wrong class, but the class i was taking wouldn't transfer credits over to my university. so really it was my negligence to do more research in the matter. gg", "output": "TIFU by taking the wrong class for 2 weeks and only realizing it today", "explanation": "This title is appropriate for the given text post because the focus of this post is about a humorous situation caused by \"taking the wrong class\"."}, {"input": "Text: this happened several years ago. i had a friend \"jack\" (more like an acquaintance) who got married several years ago. i attended the wedding in houston and all was good. i had moved to chicago shortly after and didn't really keep in touch. about 2 years later, i was in houston over the holidays and ran into him at a family holiday party. the conversation went like this:\n\n&nbsp;\n\n\"hey jack, it's been a long time! how are you doing?! how's married life treating you?\"\n\n&nbsp;\n\n\"i got divorced.\"\n\n&nbsp;\n\n\"oh.\"  (fml, awkwardness ensues). feeling like a jackass, i apologized and did my best to end the conversation quickly.", "output": "TIFU by asking a friend about his married life", "explanation": "This title is appropriate for the given text post because the focus of this post is about a humorous situation caused by \"asking a friend about his married life who is divorced\"."}, {"input": "Text: this happened a couple of months ago. in my office we have pcs to work upon. i was due for a location change so i thought it would be good to just put the important data onto some shared folder and then access it from the other location when i reach there. i zipped all the official data and just when i was about to upload the company policy came to my mind. password protect all your data when on shared drives. i protected it using 7zip and put in onto the drive. reached the other location, opened the drive and realized i don't remember the password. tried everything that i could possibly think of (even 12345 & qwerty), even email passwords but it just would not open. could not even use cracks or anything in company systems. sadly gave up hope and lost around 3gb useful data. :/\n\nps: the shared folder was only accessible to me. setting a password for a file in a folder that is only accessible to me. it could not get worse than this.", "output": "TIFU by forgetting password", "explanation": "This title is appropriate for the given text post because the focus of this post is about a humorous situation caused by \"forgetting password\"."}], "Negative Examples": [{"input": "Text: i applied for a job a week or two back thinking that there was no way i was going to get it b/c i didn't 100% match up with the qualifications. i went to the 2nd round interview to practice/ know what to expect for next time. surprise! i am offered the job, much rejoicing. being the paranoid sort, i asked the people i told not to babble about it, until after i had done the drug test and started training. i don't do drugs but i just wanted everything set up before people got excited for me. which brings us to today. i go to in-processing appointment do the whole \" this is my social security card\" dance.  and then i must be tested. not worried, aside from wondering if i drank enough water. i am ready to go even have my temporary new parking pass in my hands. and\u2026i test positive for opioids. i am totally shocked for a second. she asks if i am on meds (and i am but not the kind that would show up on the test.) and then i remember. breakfast. the everything bagel and cream cheese i eat almost every morning. (my digestive system is weird so what i eat for breakfast is kind of limited.) soo\u2026they took my parking pass away and told me they would call me later in the week, after further testing. i have no idea what levels i have going on b/c again i eat them almost every morning.", "output": "TIFU by eating a pumpkin-pie.", "explanation": "This title is inappropriate for the given text post because the focus of this post is about a humorous situation caused by \"eating a bagel\" and not by \"eating a pumpkin-pie.\"."}, {"input": "Text: this happened about 30 minutes ago.  i am a 17 year old senior in high school with an important paper due tommorow.  i was trying to relax my nerves and get the creative juices flowing by lighting a candle. the pleasant scent did relax me and allowed me to bust out half this paper, while at the same time forcing me into a deep slumber. fast forward 45 mins and mama kirrydragons comes into the room screaming and yelling that i need to finish this paper. i frantically get up and try to focus. the candle is still lit and needs to be disposed. now in my half-asleep state i decided to dump all the wax down my bathroom sink. sadly wax has this amazing ability to cool and solidify in .3 seconds. now im frantically trying to finish this paper and pour drain-o through a clogged sink.", "output": "TIFU by fixing a sink.", "explanation": "This title is inappropriate for the given text post because the focus of this post is about a humorous situation caused by \"breaking a sink\" and not by \"fixing a sink.\"."}, {"input": "Text: i (22f) am a server at a restaurant. last week we had lone male customer come in, and asked to be seated by the window (my area of serving) we immediately hit it off. he was older than me, had a sexy scottish accent, hilariously witty and very out-going. i was thrilled when he left his number on the back of the bill. fast forward one week: after a few small talk texts we decided to meet up, and agree at 3:00pm at the city fountain, right downtown in a busy area. i arrive a few minutes early, and decide to sit in the shade of a nearby statue and wait. within seconds an older, relativley handsome guy wearing sunglasses approaches me. \"hey, it's great to see you!\"\ni smile and greet him, and he immediatley lunges into some big 5 minute long story about a fender bender he got into on his way driving to meet me, and apologized profusseley for being late. by this point i could clearly tell he didn't have a scottish accent. \"you don't have nearly as much of an accent that i thought you did, am i crazy?\", he laughed and gave me a weird look, agreeing how i must be crazy because he has never had an accent. we continue walking slowly on the downtown strip, making more small talk. by this point i had a feeling something was off.. i could've sworn the accent was the main reason i had been drawn to him in the first place. when he asks me how to produce my name, as the \"o with the dots\" is relativley uncommon in our country. i say my name (which has the letter o not \u00f6) and he is immediatley giving me a weird look. we stop in the middle of the pathway surrounded by people walking. he takes off his sunglasses, revealing an unfamiliar face. you're not ben are you?\" i ask awkwardly, to which he shakes his head. we both burst out in laughter, realizing we clearly fucked up. \"i'm supposed to be meeting a girl i've met online, down bedside that statue at 2:30! she's a redhead but i haven't a picture of her face!\" we speed walk back to the fountain, both almost in tears due to the hilariously embarrassing moment that we found ourselves in. we part ways just before the fountain, and i see my real date sitting reading a book. didnt mention the ridiculous event that happened moments before, and had a terrific date.", "output": "TIFU by going on a date with my boyfriend", "explanation": "This title is inappropriate for the given text post because the focus of this post is about a humorous situation caused by \"going on a date with the wrong stranger\" and not with \"person's boyfriend\"."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Social Media -> Reddit"], "Instance": {"id": "task510-5348ce4bf822478d909e0d4deae016de", "input": "Text: after driving for 6 hours in canada, i waited over 2 hours to get through customs.  i was especially irritated at this point because a bunch of asshats were using the truck lanes to get ahead and cut in at the last minute.  when it was finally my turn the border patrol dude turns the green light to red and decides to take a 10 min smoke break. \n\nhttp://imgur.com/g7kymog\n\ni know he is entitled to one but it put me over the edge.  when it was my turn, i said as nicely as i could with a smile \"did you enjoy your cigarette break?\"  he said that he did.  after checking my passport and asking me the basic questions, he asked if i was under the influence of any drugs or alcohol.  he said my eyes were red and glassy.  he got out of his booth and escorted me to another area where my car was searched and i was harassed with a bunch of bs questions.  i knew they weren't really searching because it was hardly thorough.  the car next to me had all its luggages and contents spread out on the ground.  they just did a quick visual of mine even though i had 4 boxes that were sealed with tape.  they just wanted to teach me a lesson.  and it worked.  i felt like such a dumb ass.\n\nedit: meant tape, not rape.  doh", "output": ["Tifu by asking a border patrol officer if he enjoyed his cigarette"]}, "Instance License": ["MIT"], "prediction": "TIFU by waiting 2 hours in canada."}
+{"id": "task510-95e9410b143b41548eb59714bad1a2e9", "Task": "task510_reddit_tifu_title_summarization", "Contributors": "['Shailaja Keyur Sampat']", "Source": ["reddit_tifu_dataset"], "URL": ["https://aclanthology.org/N19-1260.pdf"], "Categories": ["Title Generation"], "Reasoning": ["Reasoning on Social Interactions", "Reasoning on Actions"], "Definition": ["In this task, you are given a Reddit post as a text. Your task is to generate a title for this text. The title should start with \"TIFU by\", followed by a situation that caused humor. The title should contain 7-12 words, ideally."], "Positive Examples": [{"input": "Text: title speaks for itself really... \ni just wasted $1500 of my parents' money.\ni feel terrible.\n\nedit: i guess it wasn't that i took the wrong class, but the class i was taking wouldn't transfer credits over to my university. so really it was my negligence to do more research in the matter. gg", "output": "TIFU by taking the wrong class for 2 weeks and only realizing it today", "explanation": "This title is appropriate for the given text post because the focus of this post is about a humorous situation caused by \"taking the wrong class\"."}, {"input": "Text: this happened several years ago. i had a friend \"jack\" (more like an acquaintance) who got married several years ago. i attended the wedding in houston and all was good. i had moved to chicago shortly after and didn't really keep in touch. about 2 years later, i was in houston over the holidays and ran into him at a family holiday party. the conversation went like this:\n\n&nbsp;\n\n\"hey jack, it's been a long time! how are you doing?! how's married life treating you?\"\n\n&nbsp;\n\n\"i got divorced.\"\n\n&nbsp;\n\n\"oh.\"  (fml, awkwardness ensues). feeling like a jackass, i apologized and did my best to end the conversation quickly.", "output": "TIFU by asking a friend about his married life", "explanation": "This title is appropriate for the given text post because the focus of this post is about a humorous situation caused by \"asking a friend about his married life who is divorced\"."}, {"input": "Text: this happened a couple of months ago. in my office we have pcs to work upon. i was due for a location change so i thought it would be good to just put the important data onto some shared folder and then access it from the other location when i reach there. i zipped all the official data and just when i was about to upload the company policy came to my mind. password protect all your data when on shared drives. i protected it using 7zip and put in onto the drive. reached the other location, opened the drive and realized i don't remember the password. tried everything that i could possibly think of (even 12345 & qwerty), even email passwords but it just would not open. could not even use cracks or anything in company systems. sadly gave up hope and lost around 3gb useful data. :/\n\nps: the shared folder was only accessible to me. setting a password for a file in a folder that is only accessible to me. it could not get worse than this.", "output": "TIFU by forgetting password", "explanation": "This title is appropriate for the given text post because the focus of this post is about a humorous situation caused by \"forgetting password\"."}], "Negative Examples": [{"input": "Text: i applied for a job a week or two back thinking that there was no way i was going to get it b/c i didn't 100% match up with the qualifications. i went to the 2nd round interview to practice/ know what to expect for next time. surprise! i am offered the job, much rejoicing. being the paranoid sort, i asked the people i told not to babble about it, until after i had done the drug test and started training. i don't do drugs but i just wanted everything set up before people got excited for me. which brings us to today. i go to in-processing appointment do the whole \" this is my social security card\" dance.  and then i must be tested. not worried, aside from wondering if i drank enough water. i am ready to go even have my temporary new parking pass in my hands. and\u2026i test positive for opioids. i am totally shocked for a second. she asks if i am on meds (and i am but not the kind that would show up on the test.) and then i remember. breakfast. the everything bagel and cream cheese i eat almost every morning. (my digestive system is weird so what i eat for breakfast is kind of limited.) soo\u2026they took my parking pass away and told me they would call me later in the week, after further testing. i have no idea what levels i have going on b/c again i eat them almost every morning.", "output": "TIFU by eating a pumpkin-pie.", "explanation": "This title is inappropriate for the given text post because the focus of this post is about a humorous situation caused by \"eating a bagel\" and not by \"eating a pumpkin-pie.\"."}, {"input": "Text: this happened about 30 minutes ago.  i am a 17 year old senior in high school with an important paper due tommorow.  i was trying to relax my nerves and get the creative juices flowing by lighting a candle. the pleasant scent did relax me and allowed me to bust out half this paper, while at the same time forcing me into a deep slumber. fast forward 45 mins and mama kirrydragons comes into the room screaming and yelling that i need to finish this paper. i frantically get up and try to focus. the candle is still lit and needs to be disposed. now in my half-asleep state i decided to dump all the wax down my bathroom sink. sadly wax has this amazing ability to cool and solidify in .3 seconds. now im frantically trying to finish this paper and pour drain-o through a clogged sink.", "output": "TIFU by fixing a sink.", "explanation": "This title is inappropriate for the given text post because the focus of this post is about a humorous situation caused by \"breaking a sink\" and not by \"fixing a sink.\"."}, {"input": "Text: i (22f) am a server at a restaurant. last week we had lone male customer come in, and asked to be seated by the window (my area of serving) we immediately hit it off. he was older than me, had a sexy scottish accent, hilariously witty and very out-going. i was thrilled when he left his number on the back of the bill. fast forward one week: after a few small talk texts we decided to meet up, and agree at 3:00pm at the city fountain, right downtown in a busy area. i arrive a few minutes early, and decide to sit in the shade of a nearby statue and wait. within seconds an older, relativley handsome guy wearing sunglasses approaches me. \"hey, it's great to see you!\"\ni smile and greet him, and he immediatley lunges into some big 5 minute long story about a fender bender he got into on his way driving to meet me, and apologized profusseley for being late. by this point i could clearly tell he didn't have a scottish accent. \"you don't have nearly as much of an accent that i thought you did, am i crazy?\", he laughed and gave me a weird look, agreeing how i must be crazy because he has never had an accent. we continue walking slowly on the downtown strip, making more small talk. by this point i had a feeling something was off.. i could've sworn the accent was the main reason i had been drawn to him in the first place. when he asks me how to produce my name, as the \"o with the dots\" is relativley uncommon in our country. i say my name (which has the letter o not \u00f6) and he is immediatley giving me a weird look. we stop in the middle of the pathway surrounded by people walking. he takes off his sunglasses, revealing an unfamiliar face. you're not ben are you?\" i ask awkwardly, to which he shakes his head. we both burst out in laughter, realizing we clearly fucked up. \"i'm supposed to be meeting a girl i've met online, down bedside that statue at 2:30! she's a redhead but i haven't a picture of her face!\" we speed walk back to the fountain, both almost in tears due to the hilariously embarrassing moment that we found ourselves in. we part ways just before the fountain, and i see my real date sitting reading a book. didnt mention the ridiculous event that happened moments before, and had a terrific date.", "output": "TIFU by going on a date with my boyfriend", "explanation": "This title is inappropriate for the given text post because the focus of this post is about a humorous situation caused by \"going on a date with the wrong stranger\" and not with \"person's boyfriend\"."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Social Media -> Reddit"], "Instance": {"id": "task510-95e9410b143b41548eb59714bad1a2e9", "input": "Text: so i managed to get into an arabic language program in jordan and i was stoked for some life experience and this kind of life experience required more than just clothes. i decided to bring my sentiment box for, duh, sentimental things like ticket stubs, the first album i ever bought, an ex\u2019s necklace, things like that. i figured it would be nice to have for the inevitable homesickness. a few days later i\u2019m standing in the amman airport listening to the muezzin, extremely bleary from the wine and xanax i had taken to make the flight bearable, shuffling with the rest of my group towards the baggage scanners. \n\ni don\u2019t know if anybody told you, but there are some security concerns in the middle east from time to time, so bags get scanned on their way out of the airport as well as on the way in. no matter, i\u2019m a law abiding not even remotely terroristic upstanding member of society who recycles and whatever. i plunk the suitcase down on the dirty folding table next to the scanner, walk through a metal detector, and turn around to collect my bag. \n\nexcept the previously friendly security guards were now looking quite stern and rifling through my bag, and they\u2019re digging for something, and they\u2019re pulling something out. it\u2019s the sentiment box, which i should mention has this picture on the top. the guard opens the box, and pulls out a fucking pair of fucking handcuffs (as in they were used for fucking) that i had tossed into the box weeks earlier in what was supposed to be a *temporary* storage arrangement for them, and had then forgotten about them. the guard holds them way up high so all of my new colleagues can see, then points at me (just in case anybody missed it) and says something in arabic. then two soldiers come and some guy in a leather jacket and jeans who speaks perfect english strides up and motions me into a back room. mind you this is happening in front of a group of people who i have just met, who i will have to live with for the next five and half months, who all now have to wait for me to sort this out. \n\nthe leather jacket guy turned out to be an intelligence agent, and he turned out to be pretty cool. he immediately figured out that i was way to un-smooth to be considered any sort of a threat. he let me go after ten minutes (didn't get the cuffs back), which allowed me to get into the bus with the rest of my classmates, who were about to leave without me. i sat in the back corner, did not introduce myself, and pretended to sleep for the entire five-hour ride to where we were staying. \n\ntr;dr a combination of kinkiness and forgetfulness resulted in me getting interrogated by a jordanian intelligence agent and almost abandoned at the amman airport.", "output": ["TIFU by being kinky in the Middle East."]}, "Instance License": ["MIT"], "prediction": "TIFU by a jordanian intelligence agent"}
+{"id": "task510-ef9aac56f95d4a8eb2e7223e89dce5bf", "Task": "task510_reddit_tifu_title_summarization", "Contributors": "['Shailaja Keyur Sampat']", "Source": ["reddit_tifu_dataset"], "URL": ["https://aclanthology.org/N19-1260.pdf"], "Categories": ["Title Generation"], "Reasoning": ["Reasoning on Social Interactions", "Reasoning on Actions"], "Definition": ["In this task, you are given a Reddit post as a text. Your task is to generate a title for this text. The title should start with \"TIFU by\", followed by a situation that caused humor. The title should contain 7-12 words, ideally."], "Positive Examples": [{"input": "Text: title speaks for itself really... \ni just wasted $1500 of my parents' money.\ni feel terrible.\n\nedit: i guess it wasn't that i took the wrong class, but the class i was taking wouldn't transfer credits over to my university. so really it was my negligence to do more research in the matter. gg", "output": "TIFU by taking the wrong class for 2 weeks and only realizing it today", "explanation": "This title is appropriate for the given text post because the focus of this post is about a humorous situation caused by \"taking the wrong class\"."}, {"input": "Text: this happened several years ago. i had a friend \"jack\" (more like an acquaintance) who got married several years ago. i attended the wedding in houston and all was good. i had moved to chicago shortly after and didn't really keep in touch. about 2 years later, i was in houston over the holidays and ran into him at a family holiday party. the conversation went like this:\n\n&nbsp;\n\n\"hey jack, it's been a long time! how are you doing?! how's married life treating you?\"\n\n&nbsp;\n\n\"i got divorced.\"\n\n&nbsp;\n\n\"oh.\"  (fml, awkwardness ensues). feeling like a jackass, i apologized and did my best to end the conversation quickly.", "output": "TIFU by asking a friend about his married life", "explanation": "This title is appropriate for the given text post because the focus of this post is about a humorous situation caused by \"asking a friend about his married life who is divorced\"."}, {"input": "Text: this happened a couple of months ago. in my office we have pcs to work upon. i was due for a location change so i thought it would be good to just put the important data onto some shared folder and then access it from the other location when i reach there. i zipped all the official data and just when i was about to upload the company policy came to my mind. password protect all your data when on shared drives. i protected it using 7zip and put in onto the drive. reached the other location, opened the drive and realized i don't remember the password. tried everything that i could possibly think of (even 12345 & qwerty), even email passwords but it just would not open. could not even use cracks or anything in company systems. sadly gave up hope and lost around 3gb useful data. :/\n\nps: the shared folder was only accessible to me. setting a password for a file in a folder that is only accessible to me. it could not get worse than this.", "output": "TIFU by forgetting password", "explanation": "This title is appropriate for the given text post because the focus of this post is about a humorous situation caused by \"forgetting password\"."}], "Negative Examples": [{"input": "Text: i applied for a job a week or two back thinking that there was no way i was going to get it b/c i didn't 100% match up with the qualifications. i went to the 2nd round interview to practice/ know what to expect for next time. surprise! i am offered the job, much rejoicing. being the paranoid sort, i asked the people i told not to babble about it, until after i had done the drug test and started training. i don't do drugs but i just wanted everything set up before people got excited for me. which brings us to today. i go to in-processing appointment do the whole \" this is my social security card\" dance.  and then i must be tested. not worried, aside from wondering if i drank enough water. i am ready to go even have my temporary new parking pass in my hands. and\u2026i test positive for opioids. i am totally shocked for a second. she asks if i am on meds (and i am but not the kind that would show up on the test.) and then i remember. breakfast. the everything bagel and cream cheese i eat almost every morning. (my digestive system is weird so what i eat for breakfast is kind of limited.) soo\u2026they took my parking pass away and told me they would call me later in the week, after further testing. i have no idea what levels i have going on b/c again i eat them almost every morning.", "output": "TIFU by eating a pumpkin-pie.", "explanation": "This title is inappropriate for the given text post because the focus of this post is about a humorous situation caused by \"eating a bagel\" and not by \"eating a pumpkin-pie.\"."}, {"input": "Text: this happened about 30 minutes ago.  i am a 17 year old senior in high school with an important paper due tommorow.  i was trying to relax my nerves and get the creative juices flowing by lighting a candle. the pleasant scent did relax me and allowed me to bust out half this paper, while at the same time forcing me into a deep slumber. fast forward 45 mins and mama kirrydragons comes into the room screaming and yelling that i need to finish this paper. i frantically get up and try to focus. the candle is still lit and needs to be disposed. now in my half-asleep state i decided to dump all the wax down my bathroom sink. sadly wax has this amazing ability to cool and solidify in .3 seconds. now im frantically trying to finish this paper and pour drain-o through a clogged sink.", "output": "TIFU by fixing a sink.", "explanation": "This title is inappropriate for the given text post because the focus of this post is about a humorous situation caused by \"breaking a sink\" and not by \"fixing a sink.\"."}, {"input": "Text: i (22f) am a server at a restaurant. last week we had lone male customer come in, and asked to be seated by the window (my area of serving) we immediately hit it off. he was older than me, had a sexy scottish accent, hilariously witty and very out-going. i was thrilled when he left his number on the back of the bill. fast forward one week: after a few small talk texts we decided to meet up, and agree at 3:00pm at the city fountain, right downtown in a busy area. i arrive a few minutes early, and decide to sit in the shade of a nearby statue and wait. within seconds an older, relativley handsome guy wearing sunglasses approaches me. \"hey, it's great to see you!\"\ni smile and greet him, and he immediatley lunges into some big 5 minute long story about a fender bender he got into on his way driving to meet me, and apologized profusseley for being late. by this point i could clearly tell he didn't have a scottish accent. \"you don't have nearly as much of an accent that i thought you did, am i crazy?\", he laughed and gave me a weird look, agreeing how i must be crazy because he has never had an accent. we continue walking slowly on the downtown strip, making more small talk. by this point i had a feeling something was off.. i could've sworn the accent was the main reason i had been drawn to him in the first place. when he asks me how to produce my name, as the \"o with the dots\" is relativley uncommon in our country. i say my name (which has the letter o not \u00f6) and he is immediatley giving me a weird look. we stop in the middle of the pathway surrounded by people walking. he takes off his sunglasses, revealing an unfamiliar face. you're not ben are you?\" i ask awkwardly, to which he shakes his head. we both burst out in laughter, realizing we clearly fucked up. \"i'm supposed to be meeting a girl i've met online, down bedside that statue at 2:30! she's a redhead but i haven't a picture of her face!\" we speed walk back to the fountain, both almost in tears due to the hilariously embarrassing moment that we found ourselves in. we part ways just before the fountain, and i see my real date sitting reading a book. didnt mention the ridiculous event that happened moments before, and had a terrific date.", "output": "TIFU by going on a date with my boyfriend", "explanation": "This title is inappropriate for the given text post because the focus of this post is about a humorous situation caused by \"going on a date with the wrong stranger\" and not with \"person's boyfriend\"."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Social Media -> Reddit"], "Instance": {"id": "task510-ef9aac56f95d4a8eb2e7223e89dce5bf", "input": "Text: throwaway.\n\ni am age 19, male, at the time i was young, living with my parents, age 16. i am into bdsm and stuff like that and three years ago, i thought it would be a good idea to try \"self bondage\".\n\nif only i wasn't an idiot, this would have been no problem at all.\n\nno one was home, and they weren't going to be home for 2-3 hours. basically i had set up a lock on my bed and the key was hanging on the ceiling connected by like a papery plastic thing to ice. when the ice cube melts, the key would drop and i would be free.\n\ni just locked myself in and then the phone was ringing and i figured i should just get and then i'll come back. i grabbed a sock off my bedroom floor and threw it at the key to make it fall down, but the key ended up swinging and flew across the room.\n\nmy heart started to panic. oh my god, what if i can't get out and a family member has to release me and finds me like this. i was panicking.\n\ni figured anything would be better than being stuck here, so i tried very hard to get my wrist out of the lock, i just hurt myself and it didn't work. the key was out of reach. i spent 45 minutes trying various things to no use.\n\nthen i thought, why don't i move the whole bed? i have a large, heavy wooden bed, i started to pull it, but it hurts my arm a lot. i end up getting a meter away from the key. my bed is diagonal in the room and touches the walls on both sides.\n\ni'm still screwed, stuck. i decide to keeping pulling the bed even though it scrapes the paint off the drywall of my wall. i can now pull myself closer but end up stuck again. i still can't reach the key.\n\ni end up grabbing a magazine with my toes and stretching and stretching until i can final just touch the key. i push the key slightly further away by accident. fuck.\n\ni have to be very careful this time, this is giving my toes a cramp. i forget what item it was, but i grab an item with my toes that was longer and i can finally pull the keys towards me.\n\ni unlock myself, and feel relived but quickly try to clean up as much of the locks and room mess as i can. after only a few minutes of release, my mom comes home and asks why i didn't pick up the phone when she called, she wanted to let me know she'd be home an hour earlier.\n\nthen she goes upstairs and asks what the heck happened to my room, i say i was cleaning and changing the layout of my room. she gives me a weird look but doesn't question me further.\n\ni still haven't painted the wall yet, i just covered it up with my bed, i should paint it soon though.\n\nbut yeah, this is the story where i dodged being completely humiliated for the rest of my life. i haven't tried something like this ever again.", "output": ["TIFU (3 years ago) by getting myself trapped in self bondage"]}, "Instance License": ["MIT"], "prediction": "TIFU by trying to lock myself in a bed and the key was hanging on the ceiling connected by like a papery plastic thing to ice."}
+{"id": "task510-0917b47646834fadb07ddfed79fd538e", "Task": "task510_reddit_tifu_title_summarization", "Contributors": "['Shailaja Keyur Sampat']", "Source": ["reddit_tifu_dataset"], "URL": ["https://aclanthology.org/N19-1260.pdf"], "Categories": ["Title Generation"], "Reasoning": ["Reasoning on Social Interactions", "Reasoning on Actions"], "Definition": ["In this task, you are given a Reddit post as a text. Your task is to generate a title for this text. The title should start with \"TIFU by\", followed by a situation that caused humor. The title should contain 7-12 words, ideally."], "Positive Examples": [{"input": "Text: title speaks for itself really... \ni just wasted $1500 of my parents' money.\ni feel terrible.\n\nedit: i guess it wasn't that i took the wrong class, but the class i was taking wouldn't transfer credits over to my university. so really it was my negligence to do more research in the matter. gg", "output": "TIFU by taking the wrong class for 2 weeks and only realizing it today", "explanation": "This title is appropriate for the given text post because the focus of this post is about a humorous situation caused by \"taking the wrong class\"."}, {"input": "Text: this happened several years ago. i had a friend \"jack\" (more like an acquaintance) who got married several years ago. i attended the wedding in houston and all was good. i had moved to chicago shortly after and didn't really keep in touch. about 2 years later, i was in houston over the holidays and ran into him at a family holiday party. the conversation went like this:\n\n&nbsp;\n\n\"hey jack, it's been a long time! how are you doing?! how's married life treating you?\"\n\n&nbsp;\n\n\"i got divorced.\"\n\n&nbsp;\n\n\"oh.\"  (fml, awkwardness ensues). feeling like a jackass, i apologized and did my best to end the conversation quickly.", "output": "TIFU by asking a friend about his married life", "explanation": "This title is appropriate for the given text post because the focus of this post is about a humorous situation caused by \"asking a friend about his married life who is divorced\"."}, {"input": "Text: this happened a couple of months ago. in my office we have pcs to work upon. i was due for a location change so i thought it would be good to just put the important data onto some shared folder and then access it from the other location when i reach there. i zipped all the official data and just when i was about to upload the company policy came to my mind. password protect all your data when on shared drives. i protected it using 7zip and put in onto the drive. reached the other location, opened the drive and realized i don't remember the password. tried everything that i could possibly think of (even 12345 & qwerty), even email passwords but it just would not open. could not even use cracks or anything in company systems. sadly gave up hope and lost around 3gb useful data. :/\n\nps: the shared folder was only accessible to me. setting a password for a file in a folder that is only accessible to me. it could not get worse than this.", "output": "TIFU by forgetting password", "explanation": "This title is appropriate for the given text post because the focus of this post is about a humorous situation caused by \"forgetting password\"."}], "Negative Examples": [{"input": "Text: i applied for a job a week or two back thinking that there was no way i was going to get it b/c i didn't 100% match up with the qualifications. i went to the 2nd round interview to practice/ know what to expect for next time. surprise! i am offered the job, much rejoicing. being the paranoid sort, i asked the people i told not to babble about it, until after i had done the drug test and started training. i don't do drugs but i just wanted everything set up before people got excited for me. which brings us to today. i go to in-processing appointment do the whole \" this is my social security card\" dance.  and then i must be tested. not worried, aside from wondering if i drank enough water. i am ready to go even have my temporary new parking pass in my hands. and\u2026i test positive for opioids. i am totally shocked for a second. she asks if i am on meds (and i am but not the kind that would show up on the test.) and then i remember. breakfast. the everything bagel and cream cheese i eat almost every morning. (my digestive system is weird so what i eat for breakfast is kind of limited.) soo\u2026they took my parking pass away and told me they would call me later in the week, after further testing. i have no idea what levels i have going on b/c again i eat them almost every morning.", "output": "TIFU by eating a pumpkin-pie.", "explanation": "This title is inappropriate for the given text post because the focus of this post is about a humorous situation caused by \"eating a bagel\" and not by \"eating a pumpkin-pie.\"."}, {"input": "Text: this happened about 30 minutes ago.  i am a 17 year old senior in high school with an important paper due tommorow.  i was trying to relax my nerves and get the creative juices flowing by lighting a candle. the pleasant scent did relax me and allowed me to bust out half this paper, while at the same time forcing me into a deep slumber. fast forward 45 mins and mama kirrydragons comes into the room screaming and yelling that i need to finish this paper. i frantically get up and try to focus. the candle is still lit and needs to be disposed. now in my half-asleep state i decided to dump all the wax down my bathroom sink. sadly wax has this amazing ability to cool and solidify in .3 seconds. now im frantically trying to finish this paper and pour drain-o through a clogged sink.", "output": "TIFU by fixing a sink.", "explanation": "This title is inappropriate for the given text post because the focus of this post is about a humorous situation caused by \"breaking a sink\" and not by \"fixing a sink.\"."}, {"input": "Text: i (22f) am a server at a restaurant. last week we had lone male customer come in, and asked to be seated by the window (my area of serving) we immediately hit it off. he was older than me, had a sexy scottish accent, hilariously witty and very out-going. i was thrilled when he left his number on the back of the bill. fast forward one week: after a few small talk texts we decided to meet up, and agree at 3:00pm at the city fountain, right downtown in a busy area. i arrive a few minutes early, and decide to sit in the shade of a nearby statue and wait. within seconds an older, relativley handsome guy wearing sunglasses approaches me. \"hey, it's great to see you!\"\ni smile and greet him, and he immediatley lunges into some big 5 minute long story about a fender bender he got into on his way driving to meet me, and apologized profusseley for being late. by this point i could clearly tell he didn't have a scottish accent. \"you don't have nearly as much of an accent that i thought you did, am i crazy?\", he laughed and gave me a weird look, agreeing how i must be crazy because he has never had an accent. we continue walking slowly on the downtown strip, making more small talk. by this point i had a feeling something was off.. i could've sworn the accent was the main reason i had been drawn to him in the first place. when he asks me how to produce my name, as the \"o with the dots\" is relativley uncommon in our country. i say my name (which has the letter o not \u00f6) and he is immediatley giving me a weird look. we stop in the middle of the pathway surrounded by people walking. he takes off his sunglasses, revealing an unfamiliar face. you're not ben are you?\" i ask awkwardly, to which he shakes his head. we both burst out in laughter, realizing we clearly fucked up. \"i'm supposed to be meeting a girl i've met online, down bedside that statue at 2:30! she's a redhead but i haven't a picture of her face!\" we speed walk back to the fountain, both almost in tears due to the hilariously embarrassing moment that we found ourselves in. we part ways just before the fountain, and i see my real date sitting reading a book. didnt mention the ridiculous event that happened moments before, and had a terrific date.", "output": "TIFU by going on a date with my boyfriend", "explanation": "This title is inappropriate for the given text post because the focus of this post is about a humorous situation caused by \"going on a date with the wrong stranger\" and not with \"person's boyfriend\"."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Social Media -> Reddit"], "Instance": {"id": "task510-0917b47646834fadb07ddfed79fd538e", "input": "Text: i was recently visiting the us for a conference and was waiting at the gate in the airport, thinking how well the week had gone and i how i hadn't fucked anything up, when the urge to make a significant deposit in the bowl hit me. i thought i'd better see to it before i boarded the 8 hour flight back, so i headed to the toilet.\n\nmy diet over the course of my visit hadn't been the best, lots of bbq, burgers, pizza and convenience food and, once i seated myself in a stall, i released a large quantity of matter with varying consistencies... this was going to require no small amount of wiping and this is where i fucked up.\n\nnow the walls in these toilet stalls are like those in many american public toilets and, rather than going all the way to the floor, they stopped about a foot or so from the floor and left a gap to the next stall. as i was wiping away, some stray toilet paper, with a good coating of my shit on it, fell loose and began to tumble to the floor. this might not have been a problem, except that it fell down and through the gap to the next stall, landing on the man in that stall's polished leather shoe. he was standing feet pointing to the wall, urinating, and i am certain that he noticed what had happened. as i looked down, after a short moment he shook his foot and the sticky bit of toilet paper eventually came loose. while this happened i kept my head down, kept very quiet and tried to hide my shoes from view lest he later be able to identify me by my footwear. i waited for him to leave before quickly finishing up and making an exit myself, then spent a large portion of the flight home worrying that my shoes might get spotted by the guy and i'd be found out.", "output": ["TIFU by indirectly pooping on a stranger's shoes"]}, "Instance License": ["MIT"], "prediction": "TIFU by urinating in a public toilet"}
+{"id": "task935-4d0b5ea493af4cc29583e9572288ea62", "Task": "task935_defeasible_nli_atomic_classification", "Contributors": "['Sujan Reddy A']", "Source": ["defeasible_nli_atomic"], "URL": ["https://github.com/rudinger/defeasible-nli"], "Categories": ["Textual Entailment"], "Reasoning": ["Logical Reasoning -> Reasoning with Symbols"], "Definition": ["In this task, you are given a premise, a hypothesis, and an update. The premise sentence describes a real-world situation and is always assumed to be true. The hypothesis sentence describes an assumption or inference that you might make about that situation having read the premise. The update provides additional information about the situation that might weaken or strengthen the hypothesis. A weakener is a statement that weakens the hypothesis. It makes you much less likely to believe the hypothesis is true. A strengthener is a statement that strengthens the hypothesis. It makes you much more likely to believe the hypothesis is true. Your task is to output 'strengthener' or 'weakener' if the update strengths or weakens the hypothesis, respectively."], "Positive Examples": [{"input": "Premise: PersonX seems interested\nHypothesis: PersonX then good activity\nUpdate: PersonX was a good student", "output": "strengthener", "explanation": "If PersonX was a good student, it is more likely that PersonX would do good activities."}, {"input": "Premise: PersonX seems interested\nHypothesis: PersonX then good activity\nUpdate: PersonX was faking to get close to a girl", "output": "weakener", "explanation": "If PersonX was faking to get close to a girl, it is less likely that PersonX would do good activities"}], "Negative Examples": [{"input": "Premise: PersonX seems interested\nHypothesis: PersonX then good activity\nUpdate: PersonX was a good student", "output": "I dont know.", "explanation": "Do not generate anything else apart from one of the following : 'strengthener', 'weakener' "}, {"input": "Premise: PersonX seems interested\nHypothesis: PersonX then good activity\nUpdate: PersonX was faking to get close to a girl", "output": "strengthener,weakener.", "explanation": "The update could either strengthen or weaken the hypothesis, not both."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Commonsense -> Concepts and Relations"], "Instance": {"id": "task935-4d0b5ea493af4cc29583e9572288ea62", "input": "Premise: PersonX transports PersonY to an island\nHypothesis: As a result, PersonX feels seafaring\nUpdate: PersonX is feeling nauseated from the boatride.", "output": ["weakener"]}, "Instance License": ["MIT"], "prediction": "weakener"}
+{"id": "task935-63c624b8a1944f859ab040e5262dfe59", "Task": "task935_defeasible_nli_atomic_classification", "Contributors": "['Sujan Reddy A']", "Source": ["defeasible_nli_atomic"], "URL": ["https://github.com/rudinger/defeasible-nli"], "Categories": ["Textual Entailment"], "Reasoning": ["Logical Reasoning -> Reasoning with Symbols"], "Definition": ["In this task, you are given a premise, a hypothesis, and an update. The premise sentence describes a real-world situation and is always assumed to be true. The hypothesis sentence describes an assumption or inference that you might make about that situation having read the premise. The update provides additional information about the situation that might weaken or strengthen the hypothesis. A weakener is a statement that weakens the hypothesis. It makes you much less likely to believe the hypothesis is true. A strengthener is a statement that strengthens the hypothesis. It makes you much more likely to believe the hypothesis is true. Your task is to output 'strengthener' or 'weakener' if the update strengths or weakens the hypothesis, respectively."], "Positive Examples": [{"input": "Premise: PersonX seems interested\nHypothesis: PersonX then good activity\nUpdate: PersonX was a good student", "output": "strengthener", "explanation": "If PersonX was a good student, it is more likely that PersonX would do good activities."}, {"input": "Premise: PersonX seems interested\nHypothesis: PersonX then good activity\nUpdate: PersonX was faking to get close to a girl", "output": "weakener", "explanation": "If PersonX was faking to get close to a girl, it is less likely that PersonX would do good activities"}], "Negative Examples": [{"input": "Premise: PersonX seems interested\nHypothesis: PersonX then good activity\nUpdate: PersonX was a good student", "output": "I dont know.", "explanation": "Do not generate anything else apart from one of the following : 'strengthener', 'weakener' "}, {"input": "Premise: PersonX seems interested\nHypothesis: PersonX then good activity\nUpdate: PersonX was faking to get close to a girl", "output": "strengthener,weakener.", "explanation": "The update could either strengthen or weaken the hypothesis, not both."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Commonsense -> Concepts and Relations"], "Instance": {"id": "task935-63c624b8a1944f859ab040e5262dfe59", "input": "Premise: PersonX sprains PersonX's wrist\nHypothesis: As a result, PersonX feels unfit\nUpdate: PersonX was trying to lift weights at the gym when they sprained their wrist.", "output": ["strengthener"]}, "Instance License": ["MIT"], "prediction": "weakener"}
+{"id": "task935-a426da86573b44038d6d92e57f146c6f", "Task": "task935_defeasible_nli_atomic_classification", "Contributors": "['Sujan Reddy A']", "Source": ["defeasible_nli_atomic"], "URL": ["https://github.com/rudinger/defeasible-nli"], "Categories": ["Textual Entailment"], "Reasoning": ["Logical Reasoning -> Reasoning with Symbols"], "Definition": ["In this task, you are given a premise, a hypothesis, and an update. The premise sentence describes a real-world situation and is always assumed to be true. The hypothesis sentence describes an assumption or inference that you might make about that situation having read the premise. The update provides additional information about the situation that might weaken or strengthen the hypothesis. A weakener is a statement that weakens the hypothesis. It makes you much less likely to believe the hypothesis is true. A strengthener is a statement that strengthens the hypothesis. It makes you much more likely to believe the hypothesis is true. Your task is to output 'strengthener' or 'weakener' if the update strengths or weakens the hypothesis, respectively."], "Positive Examples": [{"input": "Premise: PersonX seems interested\nHypothesis: PersonX then good activity\nUpdate: PersonX was a good student", "output": "strengthener", "explanation": "If PersonX was a good student, it is more likely that PersonX would do good activities."}, {"input": "Premise: PersonX seems interested\nHypothesis: PersonX then good activity\nUpdate: PersonX was faking to get close to a girl", "output": "weakener", "explanation": "If PersonX was faking to get close to a girl, it is less likely that PersonX would do good activities"}], "Negative Examples": [{"input": "Premise: PersonX seems interested\nHypothesis: PersonX then good activity\nUpdate: PersonX was a good student", "output": "I dont know.", "explanation": "Do not generate anything else apart from one of the following : 'strengthener', 'weakener' "}, {"input": "Premise: PersonX seems interested\nHypothesis: PersonX then good activity\nUpdate: PersonX was faking to get close to a girl", "output": "strengthener,weakener.", "explanation": "The update could either strengthen or weaken the hypothesis, not both."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Commonsense -> Concepts and Relations"], "Instance": {"id": "task935-a426da86573b44038d6d92e57f146c6f", "input": "Premise: PersonX keeps an eye peeled\nHypothesis: As a result, PersonX wants find what they were looking for\nUpdate: PersonX has been asked to look out for potential big spenders.", "output": ["strengthener"]}, "Instance License": ["MIT"], "prediction": "weakener"}
+{"id": "task935-39050c794dd74174a8551664de2572ba", "Task": "task935_defeasible_nli_atomic_classification", "Contributors": "['Sujan Reddy A']", "Source": ["defeasible_nli_atomic"], "URL": ["https://github.com/rudinger/defeasible-nli"], "Categories": ["Textual Entailment"], "Reasoning": ["Logical Reasoning -> Reasoning with Symbols"], "Definition": ["In this task, you are given a premise, a hypothesis, and an update. The premise sentence describes a real-world situation and is always assumed to be true. The hypothesis sentence describes an assumption or inference that you might make about that situation having read the premise. The update provides additional information about the situation that might weaken or strengthen the hypothesis. A weakener is a statement that weakens the hypothesis. It makes you much less likely to believe the hypothesis is true. A strengthener is a statement that strengthens the hypothesis. It makes you much more likely to believe the hypothesis is true. Your task is to output 'strengthener' or 'weakener' if the update strengths or weakens the hypothesis, respectively."], "Positive Examples": [{"input": "Premise: PersonX seems interested\nHypothesis: PersonX then good activity\nUpdate: PersonX was a good student", "output": "strengthener", "explanation": "If PersonX was a good student, it is more likely that PersonX would do good activities."}, {"input": "Premise: PersonX seems interested\nHypothesis: PersonX then good activity\nUpdate: PersonX was faking to get close to a girl", "output": "weakener", "explanation": "If PersonX was faking to get close to a girl, it is less likely that PersonX would do good activities"}], "Negative Examples": [{"input": "Premise: PersonX seems interested\nHypothesis: PersonX then good activity\nUpdate: PersonX was a good student", "output": "I dont know.", "explanation": "Do not generate anything else apart from one of the following : 'strengthener', 'weakener' "}, {"input": "Premise: PersonX seems interested\nHypothesis: PersonX then good activity\nUpdate: PersonX was faking to get close to a girl", "output": "strengthener,weakener.", "explanation": "The update could either strengthen or weaken the hypothesis, not both."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Commonsense -> Concepts and Relations"], "Instance": {"id": "task935-39050c794dd74174a8551664de2572ba", "input": "Premise: PersonX expresses PersonX's belief\nHypothesis: Because PersonX wanted to share what he believes in\nUpdate: PersonX had a speech assigned for class.", "output": ["weakener"]}, "Instance License": ["MIT"], "prediction": "weakener"}
+{"id": "task935-e9c537995afe4f82b5566baf56f348d7", "Task": "task935_defeasible_nli_atomic_classification", "Contributors": "['Sujan Reddy A']", "Source": ["defeasible_nli_atomic"], "URL": ["https://github.com/rudinger/defeasible-nli"], "Categories": ["Textual Entailment"], "Reasoning": ["Logical Reasoning -> Reasoning with Symbols"], "Definition": ["In this task, you are given a premise, a hypothesis, and an update. The premise sentence describes a real-world situation and is always assumed to be true. The hypothesis sentence describes an assumption or inference that you might make about that situation having read the premise. The update provides additional information about the situation that might weaken or strengthen the hypothesis. A weakener is a statement that weakens the hypothesis. It makes you much less likely to believe the hypothesis is true. A strengthener is a statement that strengthens the hypothesis. It makes you much more likely to believe the hypothesis is true. Your task is to output 'strengthener' or 'weakener' if the update strengths or weakens the hypothesis, respectively."], "Positive Examples": [{"input": "Premise: PersonX seems interested\nHypothesis: PersonX then good activity\nUpdate: PersonX was a good student", "output": "strengthener", "explanation": "If PersonX was a good student, it is more likely that PersonX would do good activities."}, {"input": "Premise: PersonX seems interested\nHypothesis: PersonX then good activity\nUpdate: PersonX was faking to get close to a girl", "output": "weakener", "explanation": "If PersonX was faking to get close to a girl, it is less likely that PersonX would do good activities"}], "Negative Examples": [{"input": "Premise: PersonX seems interested\nHypothesis: PersonX then good activity\nUpdate: PersonX was a good student", "output": "I dont know.", "explanation": "Do not generate anything else apart from one of the following : 'strengthener', 'weakener' "}, {"input": "Premise: PersonX seems interested\nHypothesis: PersonX then good activity\nUpdate: PersonX was faking to get close to a girl", "output": "strengthener,weakener.", "explanation": "The update could either strengthen or weaken the hypothesis, not both."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Commonsense -> Concepts and Relations"], "Instance": {"id": "task935-e9c537995afe4f82b5566baf56f348d7", "input": "Premise: PersonX plays so well\nHypothesis: As a result, PersonX wants find more people to play with\nUpdate: PersonX enjoys playing team sports.", "output": ["strengthener"]}, "Instance License": ["MIT"], "prediction": "stronger"}
+{"id": "task349-46fdccaf534d4344a8361ead55ab0a3d", "Task": "task349_squad2.0_answerable_unanswerable_question_classification", "Contributors": "['Shailaja Keyur Sampat']", "Source": ["squad2.0"], "URL": ["https://arxiv.org/pdf/1806.03822.pdf"], "Categories": ["Answerability Classification"], "Reasoning": [], "Definition": ["In this task, you are given a passage and a question regarding that passage. You must determine whether or not the question is answerable from the given passage. If a question is answerable, output should be 'True', otherwise 'False'. You must not consider any other information that is not provided in the passage while labelling True or False."], "Positive Examples": [{"input": "Passage: Madonna released the Material Girl clothing line, which she designed with her daughter, Lourdes. The 1980s inspired clothing line, borrowed from Madonna's punk-girl style when she rose to fame in the 1980s, was released under the Macy's label. Madonna also opened a series of fitness centers around the world named Hard Candy Fitness. In November 2011, Madonna and MG Icon announced the release of a second fashion brand called Truth or Dare by Madonna to include footwear, underclothing, and accessories. She also directed her second feature film, W.E., a biographic about the affair between King Edward VIII and Wallis Simpson; it was co-written with Alek Keshishian. Critical and commercial response to the film was negative. Madonna contributed the ballad \"Masterpiece\" for the film's soundtrack, which won her a Golden Globe Award for Best Original Song. Question: Material Girl clothing line is released under which brand?", "output": "True", "explanation": "The answer to given question is 'Macy's', which can be determined from the second sentence of the paragraph \"The 1980s inspired clothing line, borrowed from Madonna's punk-girl style when she rose to fame in the 1980s, was released under the Macy's label\". Since this question is answerable, the output is True."}, {"input": "Passage: In 1919 Father James Burns became president of Notre Dame, and in three years he produced an academic revolution that brought the school up to national standards by adopting the elective system and moving away from the university's traditional scholastic and classical emphasis. By contrast, the Jesuit colleges, bastions of academic conservatism, were reluctant to move to a system of electives. Their graduates were shut out of Harvard Law School for that reason. Notre Dame continued to grow over the years, adding more colleges, programs, and sports teams. By 1921, with the addition of the College of Commerce, Notre Dame had grown from a small college to a university with five colleges and a professional law school. The university continued to expand and add new residence halls and buildings with each subsequent president. Question: Over how many years did the change to national standards undertaken at Notre Dame in the early 20th century take place?", "output": "True", "explanation": "The answer to given question is 'three years', which can be determined from the first sentence of the paragraph \"In 1919 Father James Burns became president of Notre Dame, and in three years he produced an academic revolution that brought the school up to national standards by adopting the elective system and moving away from the university's traditional scholastic and classical emphasis\". Since this question is answerable, the output is True."}, {"input": "Passage: Exceptions to the restrictions faced by Windows Store apps are given to web browsers. The user's default browser can distribute a Metro-style web browser in same package as the desktop version, which has access to functionality unavailable to other apps, such as being able to permanently run in the background, use multiple background processes, and use Windows API code instead of WinRT (allowing for code to be re-used with the desktop version, while still taking advantage of features available to Windows Store apps, such as charms). Microsoft advertises this exception privilege \"New experience enabled\" (formerly \"Metro-style enabled\"). Question: What term did Microsoft give to its exception privilige for file browsing?", "output": "False", "explanation": "The passage talks about exception privilege given with respect to the entity 'web browser'. Whereas in question, this entity is replaced with 'file browser', which makes it unanswerable from the passage. Therefore, the answer is False."}, {"input": "Passage: The descendants of Rollo's Vikings and their Frankish wives would replace the Norse religion and Old Norse language with Catholicism (Christianity) and the Gallo-Romance language of the local people, blending their maternal Frankish heritage with Old Norse traditions and customs to synthesize a unique \"Norman\" culture in the north of France. The Norman language was forged by the adoption of the indigenous langue d'o\u00efl branch of Romance by a Norse-speaking ruling class, and it developed into the regional language that survives today. Question: What was replaced with the Norse religion?", "output": "False", "explanation": "In the passage, it is mentioned that Norse religion was replaced with Catholicism. Whereas, question asks about the entity which was replaced by Norse religion. No such information is provided in the passage which makes this question unanswerable from the passage hence output is False."}, {"input": "Passage: St. Anselm's approach was to define God as, \"that than which nothing greater can be conceived\". Famed pantheist philosopher Baruch Spinoza would later carry this idea to its extreme: \"By God I understand a being absolutely infinite, i.e., a substance consisting of infinite attributes, of which each one expresses an eternal and infinite essence.\" For Spinoza, the whole of the natural universe is made of one substance, God, or its equivalent, Nature. His proof for the existence of God was a variation of the Ontological argument. Question: What does St. Anselm used to prove God's existence?", "output": "False", "explanation": "The passage mentions about St. Anselm's definition of God and Spinoza's proof for the existence of God. Whereas, the question asks about proof given by St. Anselm's, which cannot be concluded from the paragraph. Hence, the quesiton is unanswerable and output is False."}], "Negative Examples": [{"input": "Passage: The pound-force has a metric counterpart, less commonly used than the newton: the kilogram-force (kgf) (sometimes kilopond), is the force exerted by standard gravity on one kilogram of mass. The kilogram-force leads to an alternate, but rarely used unit of mass: the metric slug (sometimes mug or hyl) is that mass that accelerates at 1 m\u00b7s\u22122 when subjected to a force of 1 kgf. The kilogram-force is not a part of the modern SI system, and is generally deprecated; however it still sees use for some purposes as expressing aircraft weight, jet thrust, bicycle spoke tension, torque wrench settings and engine output torque. Other arcane units of force include the sth\u00e8ne, which is equivalent to 1000 N, and the kip, which is equivalent to 1000 lbf. Question: What seldom used term of a unit of force equal to 1000 pound s of force?", "output": "kip", "explanation": "The output of this task must be True or False. In this task, you do not have to answer the question. Instead, you have to determine whether or not the question is answerable given a passage."}, {"input": "Passage: Exceptions to the restrictions faced by Windows Store apps are given to web browsers. The user's default browser can distribute a Metro-style web browser in same package as the desktop version, which has access to functionality unavailable to other apps, such as being able to permanently run in the background, use multiple background processes, and use Windows API code instead of WinRT (allowing for code to be re-used with the desktop version, while still taking advantage of features available to Windows Store apps, such as charms). Microsoft advertises this exception privilege \"New experience enabled\" (formerly \"Metro-style enabled\"). Question: What term did Microsoft give to its exception privilige for file browsing?", "output": "False", "explanation": "The passage talks about \"New experience enabled\" exception privilege for web browser. Whereas in question, this entity is replaced with 'file browser', which makes it unanswerable from the passage. Therefore, the answer should be False."}, {"input": "Passage: In addition to a spoken standard and a closely related written standard, Czech has several regional dialects primarily used in rural areas by speakers less proficient in other dialects or standard Czech. During the second half of the twentieth century, Czech dialect use began to weaken. By the early 1990s dialect use was stigmatized, associated with the shrinking lower class and used in literature or other media for comedic effect. Increased travel and media availability to dialect-speaking populations has encouraged them to shift to (or add to their own dialect) standard Czech. Although Czech has received considerable scholarly interest for a Slavic language, this interest has focused primarily on modern standard Czech and ancient texts rather than dialects. Standard Czech is still the norm for politicians, businesspeople and other Czechs in formal situations, but Common Czech is gaining ground in journalism and the mass media. Question: How many regional dialects does Czech have?", "output": "True", "explanation": "The answer to given question is 'several', which can be determined from the first sentence of the paragraph \"In addition to a spoken standard and a closely related written standard, Czech has several regional dialects primarily used in rural areas by speakers less proficient in other dialects or standard Czech\". Since this question is answerable, the output must be True."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Wikipedia"], "Instance": {"id": "task349-46fdccaf534d4344a8361ead55ab0a3d", "input": "Passage: In Japan, at the end of the Asuka period (538\u2013710) and the early Nara period (710\u2013794), the men who fulfilled roles similar to those of modern pharmacists were highly respected. The place of pharmacists in society was expressly defined in the Taih\u014d Code (701) and re-stated in the Y\u014dr\u014d Code (718). Ranked positions in the pre-Heian Imperial court were established; and this organizational structure remained largely intact until the Meiji Restoration (1868). In this highly stable hierarchy, the pharmacists\u2014and even pharmacist assistants\u2014were assigned status superior to all others in health-related fields such as physicians and acupuncturists. In the Imperial household, the pharmacist was even ranked above the two personal physicians of the Emperor. Question: Which two codes were the roles of pharmacists destroyed?", "output": ["False"]}, "Instance License": ["CC BY-SA 4.0"], "prediction": "True"}
+{"id": "task349-9579a8718c6c4199bef289e46035188f", "Task": "task349_squad2.0_answerable_unanswerable_question_classification", "Contributors": "['Shailaja Keyur Sampat']", "Source": ["squad2.0"], "URL": ["https://arxiv.org/pdf/1806.03822.pdf"], "Categories": ["Answerability Classification"], "Reasoning": [], "Definition": ["In this task, you are given a passage and a question regarding that passage. You must determine whether or not the question is answerable from the given passage. If a question is answerable, output should be 'True', otherwise 'False'. You must not consider any other information that is not provided in the passage while labelling True or False."], "Positive Examples": [{"input": "Passage: Madonna released the Material Girl clothing line, which she designed with her daughter, Lourdes. The 1980s inspired clothing line, borrowed from Madonna's punk-girl style when she rose to fame in the 1980s, was released under the Macy's label. Madonna also opened a series of fitness centers around the world named Hard Candy Fitness. In November 2011, Madonna and MG Icon announced the release of a second fashion brand called Truth or Dare by Madonna to include footwear, underclothing, and accessories. She also directed her second feature film, W.E., a biographic about the affair between King Edward VIII and Wallis Simpson; it was co-written with Alek Keshishian. Critical and commercial response to the film was negative. Madonna contributed the ballad \"Masterpiece\" for the film's soundtrack, which won her a Golden Globe Award for Best Original Song. Question: Material Girl clothing line is released under which brand?", "output": "True", "explanation": "The answer to given question is 'Macy's', which can be determined from the second sentence of the paragraph \"The 1980s inspired clothing line, borrowed from Madonna's punk-girl style when she rose to fame in the 1980s, was released under the Macy's label\". Since this question is answerable, the output is True."}, {"input": "Passage: In 1919 Father James Burns became president of Notre Dame, and in three years he produced an academic revolution that brought the school up to national standards by adopting the elective system and moving away from the university's traditional scholastic and classical emphasis. By contrast, the Jesuit colleges, bastions of academic conservatism, were reluctant to move to a system of electives. Their graduates were shut out of Harvard Law School for that reason. Notre Dame continued to grow over the years, adding more colleges, programs, and sports teams. By 1921, with the addition of the College of Commerce, Notre Dame had grown from a small college to a university with five colleges and a professional law school. The university continued to expand and add new residence halls and buildings with each subsequent president. Question: Over how many years did the change to national standards undertaken at Notre Dame in the early 20th century take place?", "output": "True", "explanation": "The answer to given question is 'three years', which can be determined from the first sentence of the paragraph \"In 1919 Father James Burns became president of Notre Dame, and in three years he produced an academic revolution that brought the school up to national standards by adopting the elective system and moving away from the university's traditional scholastic and classical emphasis\". Since this question is answerable, the output is True."}, {"input": "Passage: Exceptions to the restrictions faced by Windows Store apps are given to web browsers. The user's default browser can distribute a Metro-style web browser in same package as the desktop version, which has access to functionality unavailable to other apps, such as being able to permanently run in the background, use multiple background processes, and use Windows API code instead of WinRT (allowing for code to be re-used with the desktop version, while still taking advantage of features available to Windows Store apps, such as charms). Microsoft advertises this exception privilege \"New experience enabled\" (formerly \"Metro-style enabled\"). Question: What term did Microsoft give to its exception privilige for file browsing?", "output": "False", "explanation": "The passage talks about exception privilege given with respect to the entity 'web browser'. Whereas in question, this entity is replaced with 'file browser', which makes it unanswerable from the passage. Therefore, the answer is False."}, {"input": "Passage: The descendants of Rollo's Vikings and their Frankish wives would replace the Norse religion and Old Norse language with Catholicism (Christianity) and the Gallo-Romance language of the local people, blending their maternal Frankish heritage with Old Norse traditions and customs to synthesize a unique \"Norman\" culture in the north of France. The Norman language was forged by the adoption of the indigenous langue d'o\u00efl branch of Romance by a Norse-speaking ruling class, and it developed into the regional language that survives today. Question: What was replaced with the Norse religion?", "output": "False", "explanation": "In the passage, it is mentioned that Norse religion was replaced with Catholicism. Whereas, question asks about the entity which was replaced by Norse religion. No such information is provided in the passage which makes this question unanswerable from the passage hence output is False."}, {"input": "Passage: St. Anselm's approach was to define God as, \"that than which nothing greater can be conceived\". Famed pantheist philosopher Baruch Spinoza would later carry this idea to its extreme: \"By God I understand a being absolutely infinite, i.e., a substance consisting of infinite attributes, of which each one expresses an eternal and infinite essence.\" For Spinoza, the whole of the natural universe is made of one substance, God, or its equivalent, Nature. His proof for the existence of God was a variation of the Ontological argument. Question: What does St. Anselm used to prove God's existence?", "output": "False", "explanation": "The passage mentions about St. Anselm's definition of God and Spinoza's proof for the existence of God. Whereas, the question asks about proof given by St. Anselm's, which cannot be concluded from the paragraph. Hence, the quesiton is unanswerable and output is False."}], "Negative Examples": [{"input": "Passage: The pound-force has a metric counterpart, less commonly used than the newton: the kilogram-force (kgf) (sometimes kilopond), is the force exerted by standard gravity on one kilogram of mass. The kilogram-force leads to an alternate, but rarely used unit of mass: the metric slug (sometimes mug or hyl) is that mass that accelerates at 1 m\u00b7s\u22122 when subjected to a force of 1 kgf. The kilogram-force is not a part of the modern SI system, and is generally deprecated; however it still sees use for some purposes as expressing aircraft weight, jet thrust, bicycle spoke tension, torque wrench settings and engine output torque. Other arcane units of force include the sth\u00e8ne, which is equivalent to 1000 N, and the kip, which is equivalent to 1000 lbf. Question: What seldom used term of a unit of force equal to 1000 pound s of force?", "output": "kip", "explanation": "The output of this task must be True or False. In this task, you do not have to answer the question. Instead, you have to determine whether or not the question is answerable given a passage."}, {"input": "Passage: Exceptions to the restrictions faced by Windows Store apps are given to web browsers. The user's default browser can distribute a Metro-style web browser in same package as the desktop version, which has access to functionality unavailable to other apps, such as being able to permanently run in the background, use multiple background processes, and use Windows API code instead of WinRT (allowing for code to be re-used with the desktop version, while still taking advantage of features available to Windows Store apps, such as charms). Microsoft advertises this exception privilege \"New experience enabled\" (formerly \"Metro-style enabled\"). Question: What term did Microsoft give to its exception privilige for file browsing?", "output": "False", "explanation": "The passage talks about \"New experience enabled\" exception privilege for web browser. Whereas in question, this entity is replaced with 'file browser', which makes it unanswerable from the passage. Therefore, the answer should be False."}, {"input": "Passage: In addition to a spoken standard and a closely related written standard, Czech has several regional dialects primarily used in rural areas by speakers less proficient in other dialects or standard Czech. During the second half of the twentieth century, Czech dialect use began to weaken. By the early 1990s dialect use was stigmatized, associated with the shrinking lower class and used in literature or other media for comedic effect. Increased travel and media availability to dialect-speaking populations has encouraged them to shift to (or add to their own dialect) standard Czech. Although Czech has received considerable scholarly interest for a Slavic language, this interest has focused primarily on modern standard Czech and ancient texts rather than dialects. Standard Czech is still the norm for politicians, businesspeople and other Czechs in formal situations, but Common Czech is gaining ground in journalism and the mass media. Question: How many regional dialects does Czech have?", "output": "True", "explanation": "The answer to given question is 'several', which can be determined from the first sentence of the paragraph \"In addition to a spoken standard and a closely related written standard, Czech has several regional dialects primarily used in rural areas by speakers less proficient in other dialects or standard Czech\". Since this question is answerable, the output must be True."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Wikipedia"], "Instance": {"id": "task349-9579a8718c6c4199bef289e46035188f", "input": "Passage: In 1891 Scottish chemist James Dewar was able to produce enough liquid oxygen to study. The first commercially viable process for producing liquid oxygen was independently developed in 1895 by German engineer Carl von Linde and British engineer William Hampson. Both men lowered the temperature of air until it liquefied and then distilled the component gases by boiling them off one at a time and capturing them. Later, in 1901, oxyacetylene welding was demonstrated for the first time by burning a mixture of acetylene and compressed O\n2. This method of welding and cutting metal later became common. Question: When was liquid oxygen developed for commercial use?", "output": ["True"]}, "Instance License": ["CC BY-SA 4.0"], "prediction": "True"}
+{"id": "task349-ce7f255da3974eae879c0dce941ab019", "Task": "task349_squad2.0_answerable_unanswerable_question_classification", "Contributors": "['Shailaja Keyur Sampat']", "Source": ["squad2.0"], "URL": ["https://arxiv.org/pdf/1806.03822.pdf"], "Categories": ["Answerability Classification"], "Reasoning": [], "Definition": ["In this task, you are given a passage and a question regarding that passage. You must determine whether or not the question is answerable from the given passage. If a question is answerable, output should be 'True', otherwise 'False'. You must not consider any other information that is not provided in the passage while labelling True or False."], "Positive Examples": [{"input": "Passage: Madonna released the Material Girl clothing line, which she designed with her daughter, Lourdes. The 1980s inspired clothing line, borrowed from Madonna's punk-girl style when she rose to fame in the 1980s, was released under the Macy's label. Madonna also opened a series of fitness centers around the world named Hard Candy Fitness. In November 2011, Madonna and MG Icon announced the release of a second fashion brand called Truth or Dare by Madonna to include footwear, underclothing, and accessories. She also directed her second feature film, W.E., a biographic about the affair between King Edward VIII and Wallis Simpson; it was co-written with Alek Keshishian. Critical and commercial response to the film was negative. Madonna contributed the ballad \"Masterpiece\" for the film's soundtrack, which won her a Golden Globe Award for Best Original Song. Question: Material Girl clothing line is released under which brand?", "output": "True", "explanation": "The answer to given question is 'Macy's', which can be determined from the second sentence of the paragraph \"The 1980s inspired clothing line, borrowed from Madonna's punk-girl style when she rose to fame in the 1980s, was released under the Macy's label\". Since this question is answerable, the output is True."}, {"input": "Passage: In 1919 Father James Burns became president of Notre Dame, and in three years he produced an academic revolution that brought the school up to national standards by adopting the elective system and moving away from the university's traditional scholastic and classical emphasis. By contrast, the Jesuit colleges, bastions of academic conservatism, were reluctant to move to a system of electives. Their graduates were shut out of Harvard Law School for that reason. Notre Dame continued to grow over the years, adding more colleges, programs, and sports teams. By 1921, with the addition of the College of Commerce, Notre Dame had grown from a small college to a university with five colleges and a professional law school. The university continued to expand and add new residence halls and buildings with each subsequent president. Question: Over how many years did the change to national standards undertaken at Notre Dame in the early 20th century take place?", "output": "True", "explanation": "The answer to given question is 'three years', which can be determined from the first sentence of the paragraph \"In 1919 Father James Burns became president of Notre Dame, and in three years he produced an academic revolution that brought the school up to national standards by adopting the elective system and moving away from the university's traditional scholastic and classical emphasis\". Since this question is answerable, the output is True."}, {"input": "Passage: Exceptions to the restrictions faced by Windows Store apps are given to web browsers. The user's default browser can distribute a Metro-style web browser in same package as the desktop version, which has access to functionality unavailable to other apps, such as being able to permanently run in the background, use multiple background processes, and use Windows API code instead of WinRT (allowing for code to be re-used with the desktop version, while still taking advantage of features available to Windows Store apps, such as charms). Microsoft advertises this exception privilege \"New experience enabled\" (formerly \"Metro-style enabled\"). Question: What term did Microsoft give to its exception privilige for file browsing?", "output": "False", "explanation": "The passage talks about exception privilege given with respect to the entity 'web browser'. Whereas in question, this entity is replaced with 'file browser', which makes it unanswerable from the passage. Therefore, the answer is False."}, {"input": "Passage: The descendants of Rollo's Vikings and their Frankish wives would replace the Norse religion and Old Norse language with Catholicism (Christianity) and the Gallo-Romance language of the local people, blending their maternal Frankish heritage with Old Norse traditions and customs to synthesize a unique \"Norman\" culture in the north of France. The Norman language was forged by the adoption of the indigenous langue d'o\u00efl branch of Romance by a Norse-speaking ruling class, and it developed into the regional language that survives today. Question: What was replaced with the Norse religion?", "output": "False", "explanation": "In the passage, it is mentioned that Norse religion was replaced with Catholicism. Whereas, question asks about the entity which was replaced by Norse religion. No such information is provided in the passage which makes this question unanswerable from the passage hence output is False."}, {"input": "Passage: St. Anselm's approach was to define God as, \"that than which nothing greater can be conceived\". Famed pantheist philosopher Baruch Spinoza would later carry this idea to its extreme: \"By God I understand a being absolutely infinite, i.e., a substance consisting of infinite attributes, of which each one expresses an eternal and infinite essence.\" For Spinoza, the whole of the natural universe is made of one substance, God, or its equivalent, Nature. His proof for the existence of God was a variation of the Ontological argument. Question: What does St. Anselm used to prove God's existence?", "output": "False", "explanation": "The passage mentions about St. Anselm's definition of God and Spinoza's proof for the existence of God. Whereas, the question asks about proof given by St. Anselm's, which cannot be concluded from the paragraph. Hence, the quesiton is unanswerable and output is False."}], "Negative Examples": [{"input": "Passage: The pound-force has a metric counterpart, less commonly used than the newton: the kilogram-force (kgf) (sometimes kilopond), is the force exerted by standard gravity on one kilogram of mass. The kilogram-force leads to an alternate, but rarely used unit of mass: the metric slug (sometimes mug or hyl) is that mass that accelerates at 1 m\u00b7s\u22122 when subjected to a force of 1 kgf. The kilogram-force is not a part of the modern SI system, and is generally deprecated; however it still sees use for some purposes as expressing aircraft weight, jet thrust, bicycle spoke tension, torque wrench settings and engine output torque. Other arcane units of force include the sth\u00e8ne, which is equivalent to 1000 N, and the kip, which is equivalent to 1000 lbf. Question: What seldom used term of a unit of force equal to 1000 pound s of force?", "output": "kip", "explanation": "The output of this task must be True or False. In this task, you do not have to answer the question. Instead, you have to determine whether or not the question is answerable given a passage."}, {"input": "Passage: Exceptions to the restrictions faced by Windows Store apps are given to web browsers. The user's default browser can distribute a Metro-style web browser in same package as the desktop version, which has access to functionality unavailable to other apps, such as being able to permanently run in the background, use multiple background processes, and use Windows API code instead of WinRT (allowing for code to be re-used with the desktop version, while still taking advantage of features available to Windows Store apps, such as charms). Microsoft advertises this exception privilege \"New experience enabled\" (formerly \"Metro-style enabled\"). Question: What term did Microsoft give to its exception privilige for file browsing?", "output": "False", "explanation": "The passage talks about \"New experience enabled\" exception privilege for web browser. Whereas in question, this entity is replaced with 'file browser', which makes it unanswerable from the passage. Therefore, the answer should be False."}, {"input": "Passage: In addition to a spoken standard and a closely related written standard, Czech has several regional dialects primarily used in rural areas by speakers less proficient in other dialects or standard Czech. During the second half of the twentieth century, Czech dialect use began to weaken. By the early 1990s dialect use was stigmatized, associated with the shrinking lower class and used in literature or other media for comedic effect. Increased travel and media availability to dialect-speaking populations has encouraged them to shift to (or add to their own dialect) standard Czech. Although Czech has received considerable scholarly interest for a Slavic language, this interest has focused primarily on modern standard Czech and ancient texts rather than dialects. Standard Czech is still the norm for politicians, businesspeople and other Czechs in formal situations, but Common Czech is gaining ground in journalism and the mass media. Question: How many regional dialects does Czech have?", "output": "True", "explanation": "The answer to given question is 'several', which can be determined from the first sentence of the paragraph \"In addition to a spoken standard and a closely related written standard, Czech has several regional dialects primarily used in rural areas by speakers less proficient in other dialects or standard Czech\". Since this question is answerable, the output must be True."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Wikipedia"], "Instance": {"id": "task349-ce7f255da3974eae879c0dce941ab019", "input": "Passage: In 1872, the Central Pacific Railroad established a station near Easterby's\u2014by now a hugely productive wheat farm\u2014for its new Southern Pacific line. Soon there was a store around the station and the store grew the town of Fresno Station, later called Fresno. Many Millerton residents, drawn by the convenience of the railroad and worried about flooding, moved to the new community. Fresno became an incorporated city in 1885. By 1931 the Fresno Traction Company operated 47 streetcars over 49 miles of track. Question: How many streetcars did the Fresno Traction Company operate in 1931?", "output": ["True"]}, "Instance License": ["CC BY-SA 4.0"], "prediction": "True"}
+{"id": "task349-125230fe7bad4cec92f49363e8b49131", "Task": "task349_squad2.0_answerable_unanswerable_question_classification", "Contributors": "['Shailaja Keyur Sampat']", "Source": ["squad2.0"], "URL": ["https://arxiv.org/pdf/1806.03822.pdf"], "Categories": ["Answerability Classification"], "Reasoning": [], "Definition": ["In this task, you are given a passage and a question regarding that passage. You must determine whether or not the question is answerable from the given passage. If a question is answerable, output should be 'True', otherwise 'False'. You must not consider any other information that is not provided in the passage while labelling True or False."], "Positive Examples": [{"input": "Passage: Madonna released the Material Girl clothing line, which she designed with her daughter, Lourdes. The 1980s inspired clothing line, borrowed from Madonna's punk-girl style when she rose to fame in the 1980s, was released under the Macy's label. Madonna also opened a series of fitness centers around the world named Hard Candy Fitness. In November 2011, Madonna and MG Icon announced the release of a second fashion brand called Truth or Dare by Madonna to include footwear, underclothing, and accessories. She also directed her second feature film, W.E., a biographic about the affair between King Edward VIII and Wallis Simpson; it was co-written with Alek Keshishian. Critical and commercial response to the film was negative. Madonna contributed the ballad \"Masterpiece\" for the film's soundtrack, which won her a Golden Globe Award for Best Original Song. Question: Material Girl clothing line is released under which brand?", "output": "True", "explanation": "The answer to given question is 'Macy's', which can be determined from the second sentence of the paragraph \"The 1980s inspired clothing line, borrowed from Madonna's punk-girl style when she rose to fame in the 1980s, was released under the Macy's label\". Since this question is answerable, the output is True."}, {"input": "Passage: In 1919 Father James Burns became president of Notre Dame, and in three years he produced an academic revolution that brought the school up to national standards by adopting the elective system and moving away from the university's traditional scholastic and classical emphasis. By contrast, the Jesuit colleges, bastions of academic conservatism, were reluctant to move to a system of electives. Their graduates were shut out of Harvard Law School for that reason. Notre Dame continued to grow over the years, adding more colleges, programs, and sports teams. By 1921, with the addition of the College of Commerce, Notre Dame had grown from a small college to a university with five colleges and a professional law school. The university continued to expand and add new residence halls and buildings with each subsequent president. Question: Over how many years did the change to national standards undertaken at Notre Dame in the early 20th century take place?", "output": "True", "explanation": "The answer to given question is 'three years', which can be determined from the first sentence of the paragraph \"In 1919 Father James Burns became president of Notre Dame, and in three years he produced an academic revolution that brought the school up to national standards by adopting the elective system and moving away from the university's traditional scholastic and classical emphasis\". Since this question is answerable, the output is True."}, {"input": "Passage: Exceptions to the restrictions faced by Windows Store apps are given to web browsers. The user's default browser can distribute a Metro-style web browser in same package as the desktop version, which has access to functionality unavailable to other apps, such as being able to permanently run in the background, use multiple background processes, and use Windows API code instead of WinRT (allowing for code to be re-used with the desktop version, while still taking advantage of features available to Windows Store apps, such as charms). Microsoft advertises this exception privilege \"New experience enabled\" (formerly \"Metro-style enabled\"). Question: What term did Microsoft give to its exception privilige for file browsing?", "output": "False", "explanation": "The passage talks about exception privilege given with respect to the entity 'web browser'. Whereas in question, this entity is replaced with 'file browser', which makes it unanswerable from the passage. Therefore, the answer is False."}, {"input": "Passage: The descendants of Rollo's Vikings and their Frankish wives would replace the Norse religion and Old Norse language with Catholicism (Christianity) and the Gallo-Romance language of the local people, blending their maternal Frankish heritage with Old Norse traditions and customs to synthesize a unique \"Norman\" culture in the north of France. The Norman language was forged by the adoption of the indigenous langue d'o\u00efl branch of Romance by a Norse-speaking ruling class, and it developed into the regional language that survives today. Question: What was replaced with the Norse religion?", "output": "False", "explanation": "In the passage, it is mentioned that Norse religion was replaced with Catholicism. Whereas, question asks about the entity which was replaced by Norse religion. No such information is provided in the passage which makes this question unanswerable from the passage hence output is False."}, {"input": "Passage: St. Anselm's approach was to define God as, \"that than which nothing greater can be conceived\". Famed pantheist philosopher Baruch Spinoza would later carry this idea to its extreme: \"By God I understand a being absolutely infinite, i.e., a substance consisting of infinite attributes, of which each one expresses an eternal and infinite essence.\" For Spinoza, the whole of the natural universe is made of one substance, God, or its equivalent, Nature. His proof for the existence of God was a variation of the Ontological argument. Question: What does St. Anselm used to prove God's existence?", "output": "False", "explanation": "The passage mentions about St. Anselm's definition of God and Spinoza's proof for the existence of God. Whereas, the question asks about proof given by St. Anselm's, which cannot be concluded from the paragraph. Hence, the quesiton is unanswerable and output is False."}], "Negative Examples": [{"input": "Passage: The pound-force has a metric counterpart, less commonly used than the newton: the kilogram-force (kgf) (sometimes kilopond), is the force exerted by standard gravity on one kilogram of mass. The kilogram-force leads to an alternate, but rarely used unit of mass: the metric slug (sometimes mug or hyl) is that mass that accelerates at 1 m\u00b7s\u22122 when subjected to a force of 1 kgf. The kilogram-force is not a part of the modern SI system, and is generally deprecated; however it still sees use for some purposes as expressing aircraft weight, jet thrust, bicycle spoke tension, torque wrench settings and engine output torque. Other arcane units of force include the sth\u00e8ne, which is equivalent to 1000 N, and the kip, which is equivalent to 1000 lbf. Question: What seldom used term of a unit of force equal to 1000 pound s of force?", "output": "kip", "explanation": "The output of this task must be True or False. In this task, you do not have to answer the question. Instead, you have to determine whether or not the question is answerable given a passage."}, {"input": "Passage: Exceptions to the restrictions faced by Windows Store apps are given to web browsers. The user's default browser can distribute a Metro-style web browser in same package as the desktop version, which has access to functionality unavailable to other apps, such as being able to permanently run in the background, use multiple background processes, and use Windows API code instead of WinRT (allowing for code to be re-used with the desktop version, while still taking advantage of features available to Windows Store apps, such as charms). Microsoft advertises this exception privilege \"New experience enabled\" (formerly \"Metro-style enabled\"). Question: What term did Microsoft give to its exception privilige for file browsing?", "output": "False", "explanation": "The passage talks about \"New experience enabled\" exception privilege for web browser. Whereas in question, this entity is replaced with 'file browser', which makes it unanswerable from the passage. Therefore, the answer should be False."}, {"input": "Passage: In addition to a spoken standard and a closely related written standard, Czech has several regional dialects primarily used in rural areas by speakers less proficient in other dialects or standard Czech. During the second half of the twentieth century, Czech dialect use began to weaken. By the early 1990s dialect use was stigmatized, associated with the shrinking lower class and used in literature or other media for comedic effect. Increased travel and media availability to dialect-speaking populations has encouraged them to shift to (or add to their own dialect) standard Czech. Although Czech has received considerable scholarly interest for a Slavic language, this interest has focused primarily on modern standard Czech and ancient texts rather than dialects. Standard Czech is still the norm for politicians, businesspeople and other Czechs in formal situations, but Common Czech is gaining ground in journalism and the mass media. Question: How many regional dialects does Czech have?", "output": "True", "explanation": "The answer to given question is 'several', which can be determined from the first sentence of the paragraph \"In addition to a spoken standard and a closely related written standard, Czech has several regional dialects primarily used in rural areas by speakers less proficient in other dialects or standard Czech\". Since this question is answerable, the output must be True."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Wikipedia"], "Instance": {"id": "task349-125230fe7bad4cec92f49363e8b49131", "input": "Passage: Between Bingen and Bonn, the Middle Rhine flows through the Rhine Gorge, a formation which was created by erosion. The rate of erosion equaled the uplift in the region, such that the river was left at about its original level while the surrounding lands raised. The gorge is quite deep and is the stretch of the river which is known for its many castles and vineyards. It is a UNESCO World Heritage Site (2002) and known as \"the Romantic Rhine\", with more than 40 castles and fortresses from the Middle Ages and many quaint and lovely country villages. Question: How many country villages can be found at the UNESCO World Heritage Site?", "output": ["False"]}, "Instance License": ["CC BY-SA 4.0"], "prediction": "True"}
+{"id": "task349-eac98d8de9d94dfc90f00aad73658938", "Task": "task349_squad2.0_answerable_unanswerable_question_classification", "Contributors": "['Shailaja Keyur Sampat']", "Source": ["squad2.0"], "URL": ["https://arxiv.org/pdf/1806.03822.pdf"], "Categories": ["Answerability Classification"], "Reasoning": [], "Definition": ["In this task, you are given a passage and a question regarding that passage. You must determine whether or not the question is answerable from the given passage. If a question is answerable, output should be 'True', otherwise 'False'. You must not consider any other information that is not provided in the passage while labelling True or False."], "Positive Examples": [{"input": "Passage: Madonna released the Material Girl clothing line, which she designed with her daughter, Lourdes. The 1980s inspired clothing line, borrowed from Madonna's punk-girl style when she rose to fame in the 1980s, was released under the Macy's label. Madonna also opened a series of fitness centers around the world named Hard Candy Fitness. In November 2011, Madonna and MG Icon announced the release of a second fashion brand called Truth or Dare by Madonna to include footwear, underclothing, and accessories. She also directed her second feature film, W.E., a biographic about the affair between King Edward VIII and Wallis Simpson; it was co-written with Alek Keshishian. Critical and commercial response to the film was negative. Madonna contributed the ballad \"Masterpiece\" for the film's soundtrack, which won her a Golden Globe Award for Best Original Song. Question: Material Girl clothing line is released under which brand?", "output": "True", "explanation": "The answer to given question is 'Macy's', which can be determined from the second sentence of the paragraph \"The 1980s inspired clothing line, borrowed from Madonna's punk-girl style when she rose to fame in the 1980s, was released under the Macy's label\". Since this question is answerable, the output is True."}, {"input": "Passage: In 1919 Father James Burns became president of Notre Dame, and in three years he produced an academic revolution that brought the school up to national standards by adopting the elective system and moving away from the university's traditional scholastic and classical emphasis. By contrast, the Jesuit colleges, bastions of academic conservatism, were reluctant to move to a system of electives. Their graduates were shut out of Harvard Law School for that reason. Notre Dame continued to grow over the years, adding more colleges, programs, and sports teams. By 1921, with the addition of the College of Commerce, Notre Dame had grown from a small college to a university with five colleges and a professional law school. The university continued to expand and add new residence halls and buildings with each subsequent president. Question: Over how many years did the change to national standards undertaken at Notre Dame in the early 20th century take place?", "output": "True", "explanation": "The answer to given question is 'three years', which can be determined from the first sentence of the paragraph \"In 1919 Father James Burns became president of Notre Dame, and in three years he produced an academic revolution that brought the school up to national standards by adopting the elective system and moving away from the university's traditional scholastic and classical emphasis\". Since this question is answerable, the output is True."}, {"input": "Passage: Exceptions to the restrictions faced by Windows Store apps are given to web browsers. The user's default browser can distribute a Metro-style web browser in same package as the desktop version, which has access to functionality unavailable to other apps, such as being able to permanently run in the background, use multiple background processes, and use Windows API code instead of WinRT (allowing for code to be re-used with the desktop version, while still taking advantage of features available to Windows Store apps, such as charms). Microsoft advertises this exception privilege \"New experience enabled\" (formerly \"Metro-style enabled\"). Question: What term did Microsoft give to its exception privilige for file browsing?", "output": "False", "explanation": "The passage talks about exception privilege given with respect to the entity 'web browser'. Whereas in question, this entity is replaced with 'file browser', which makes it unanswerable from the passage. Therefore, the answer is False."}, {"input": "Passage: The descendants of Rollo's Vikings and their Frankish wives would replace the Norse religion and Old Norse language with Catholicism (Christianity) and the Gallo-Romance language of the local people, blending their maternal Frankish heritage with Old Norse traditions and customs to synthesize a unique \"Norman\" culture in the north of France. The Norman language was forged by the adoption of the indigenous langue d'o\u00efl branch of Romance by a Norse-speaking ruling class, and it developed into the regional language that survives today. Question: What was replaced with the Norse religion?", "output": "False", "explanation": "In the passage, it is mentioned that Norse religion was replaced with Catholicism. Whereas, question asks about the entity which was replaced by Norse religion. No such information is provided in the passage which makes this question unanswerable from the passage hence output is False."}, {"input": "Passage: St. Anselm's approach was to define God as, \"that than which nothing greater can be conceived\". Famed pantheist philosopher Baruch Spinoza would later carry this idea to its extreme: \"By God I understand a being absolutely infinite, i.e., a substance consisting of infinite attributes, of which each one expresses an eternal and infinite essence.\" For Spinoza, the whole of the natural universe is made of one substance, God, or its equivalent, Nature. His proof for the existence of God was a variation of the Ontological argument. Question: What does St. Anselm used to prove God's existence?", "output": "False", "explanation": "The passage mentions about St. Anselm's definition of God and Spinoza's proof for the existence of God. Whereas, the question asks about proof given by St. Anselm's, which cannot be concluded from the paragraph. Hence, the quesiton is unanswerable and output is False."}], "Negative Examples": [{"input": "Passage: The pound-force has a metric counterpart, less commonly used than the newton: the kilogram-force (kgf) (sometimes kilopond), is the force exerted by standard gravity on one kilogram of mass. The kilogram-force leads to an alternate, but rarely used unit of mass: the metric slug (sometimes mug or hyl) is that mass that accelerates at 1 m\u00b7s\u22122 when subjected to a force of 1 kgf. The kilogram-force is not a part of the modern SI system, and is generally deprecated; however it still sees use for some purposes as expressing aircraft weight, jet thrust, bicycle spoke tension, torque wrench settings and engine output torque. Other arcane units of force include the sth\u00e8ne, which is equivalent to 1000 N, and the kip, which is equivalent to 1000 lbf. Question: What seldom used term of a unit of force equal to 1000 pound s of force?", "output": "kip", "explanation": "The output of this task must be True or False. In this task, you do not have to answer the question. Instead, you have to determine whether or not the question is answerable given a passage."}, {"input": "Passage: Exceptions to the restrictions faced by Windows Store apps are given to web browsers. The user's default browser can distribute a Metro-style web browser in same package as the desktop version, which has access to functionality unavailable to other apps, such as being able to permanently run in the background, use multiple background processes, and use Windows API code instead of WinRT (allowing for code to be re-used with the desktop version, while still taking advantage of features available to Windows Store apps, such as charms). Microsoft advertises this exception privilege \"New experience enabled\" (formerly \"Metro-style enabled\"). Question: What term did Microsoft give to its exception privilige for file browsing?", "output": "False", "explanation": "The passage talks about \"New experience enabled\" exception privilege for web browser. Whereas in question, this entity is replaced with 'file browser', which makes it unanswerable from the passage. Therefore, the answer should be False."}, {"input": "Passage: In addition to a spoken standard and a closely related written standard, Czech has several regional dialects primarily used in rural areas by speakers less proficient in other dialects or standard Czech. During the second half of the twentieth century, Czech dialect use began to weaken. By the early 1990s dialect use was stigmatized, associated with the shrinking lower class and used in literature or other media for comedic effect. Increased travel and media availability to dialect-speaking populations has encouraged them to shift to (or add to their own dialect) standard Czech. Although Czech has received considerable scholarly interest for a Slavic language, this interest has focused primarily on modern standard Czech and ancient texts rather than dialects. Standard Czech is still the norm for politicians, businesspeople and other Czechs in formal situations, but Common Czech is gaining ground in journalism and the mass media. Question: How many regional dialects does Czech have?", "output": "True", "explanation": "The answer to given question is 'several', which can be determined from the first sentence of the paragraph \"In addition to a spoken standard and a closely related written standard, Czech has several regional dialects primarily used in rural areas by speakers less proficient in other dialects or standard Czech\". Since this question is answerable, the output must be True."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Wikipedia"], "Instance": {"id": "task349-eac98d8de9d94dfc90f00aad73658938", "input": "Passage: First, if a Directive's deadline for implementation is not met, the member state cannot enforce conflicting laws, and a citizen may rely on the Directive in such an action (so called \"vertical\" direct effect). So, in Pubblico Ministero v Ratti because the Italian government had failed to implement a Directive 73/173/EEC on packaging and labelling solvents by the deadline, it was estopped from enforcing a conflicting national law from 1963 against Mr Ratti's solvent and varnish business. A member state could \"not rely, as against individuals, on its own failure to perform the obligations which the Directive entails.\" Second, a citizen or company can invoke a Directive, not just in a dispute with a public authority, but in a dispute with another citizen or company. So, in CIA Security v Signalson and Securitel the Court of Justice held that a business called CIA Security could defend itself from allegations by competitors that it had not complied with a Belgian decree from 1991 about alarm systems, on the basis that it had not been notified to the Commission as a Directive required. Third, if a Directive gives expression to a \"general principle\" of EU law, it can be invoked between private non-state parties before its deadline for implementation. This follows from K\u00fcc\u00fckdeveci v Swedex GmbH & Co KG where the German Civil Code \u00a7622 stated that the years people worked under the age of 25 would not count towards the increasing statutory notice before dismissal. Ms K\u00fcc\u00fckdeveci worked for 10 years, from age 18 to 28, for Swedex GmbH & Co KG before her dismissal. She claimed that the law not counting her years under age 25 was unlawful age discrimination under the Employment Equality Framework Directive. The Court of Justice held that the Directive could be relied on by her because equality was also a general principle of EU law. Third, if the defendant is an emanation of the state, even if not central government, it can still be bound by Directives. In Foster v British Gas plc the Court of Justice held that Mrs Foster was entitled to bring a sex discrimination claim against her employer, British Gas plc, which made women retire at age 60 and men at 65, if (1) pursuant to a state measure, (2) it provided a public service, and (3) had special powers. This could also be true if the enterprise is privatised, as it was held with a water company that was responsible for basic water provision. Question: How long did Ms Kucukdeveci work for Swedex Gmbh & Co KG before she was dismissed?", "output": ["True"]}, "Instance License": ["CC BY-SA 4.0"], "prediction": "True"}
+{"id": "task1157-eb1bc51df9f342878fc934657485fd57", "Task": "task1157_bard_analogical_reasoning_rooms_for_containers", "Contributors": "['Arjun Ashok']", "Source": ["bard"], "URL": ["https://github.com/NancyFulda/BYU-Analogical-Reasoning-Dataset"], "Categories": ["Word Analogy"], "Reasoning": ["Relational Reasoning", "Commonsense Reasoning", "Analogical Reasoning"], "Definition": ["Two analogies that relate objects to the associated rooms is given in the form \"A : B. C : ?\". \"A : B\" relates object A to room B. Your task is to replace the question mark (?) with the appropriate room for the given object C, following the \"A : B\" relation."], "Positive Examples": [{"input": "shelf : nursury. cabinet : ?", "output": "bathroom", "explanation": "The given analogy relates objects to their rooms. A shelf is associated with a nursery. A cabinet is associated with a bathroom"}, {"input": "dresser : bedroom. boxes : ?", "output": "garage", "explanation": "The given analogy relates objects to their rooms. A dresser is associated with a bedroom. Boxes are associated with a garage"}, {"input": "refrigerator : kitchen. crib : ?", "output": "nursery", "explanation": "The given analogy relates objects to their rooms. A refrigerator is associated with a kitchen. A crib is associated with a nursery"}], "Negative Examples": [{"input": "dresser : bedroom. boxes : ?", "output": "fill", "explanation": "The given analogy relates objects to their rooms. A dresser is associated with a bedroom. Fill is not a room, and hence the answer does not model containment"}, {"input": "workbench : garage. pantry : ?", "output": "store", "explanation": "The given analogy relates objects to their rooms. A workbench is associated with a garage. Store is not a room, and hence the answer does not model containment"}, {"input": "bookshelf : library. shelf : ?", "output": "driveway", "explanation": "The given analogy relates objects to their rooms. A bookshelf is associated with a library. Shelf is not associated with driveway, and hence the answer does not model containment"}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Commonsense"], "Instance": {"id": "task1157-eb1bc51df9f342878fc934657485fd57", "input": "table : kitchen. nightstand : ?", "output": ["bedroom"]}, "Instance License": ["Apache 2.0"], "prediction": "bedroom"}
+{"id": "task1157-e7d794429aca4f1dbda5c69204805883", "Task": "task1157_bard_analogical_reasoning_rooms_for_containers", "Contributors": "['Arjun Ashok']", "Source": ["bard"], "URL": ["https://github.com/NancyFulda/BYU-Analogical-Reasoning-Dataset"], "Categories": ["Word Analogy"], "Reasoning": ["Relational Reasoning", "Commonsense Reasoning", "Analogical Reasoning"], "Definition": ["Two analogies that relate objects to the associated rooms is given in the form \"A : B. C : ?\". \"A : B\" relates object A to room B. Your task is to replace the question mark (?) with the appropriate room for the given object C, following the \"A : B\" relation."], "Positive Examples": [{"input": "shelf : nursury. cabinet : ?", "output": "bathroom", "explanation": "The given analogy relates objects to their rooms. A shelf is associated with a nursery. A cabinet is associated with a bathroom"}, {"input": "dresser : bedroom. boxes : ?", "output": "garage", "explanation": "The given analogy relates objects to their rooms. A dresser is associated with a bedroom. Boxes are associated with a garage"}, {"input": "refrigerator : kitchen. crib : ?", "output": "nursery", "explanation": "The given analogy relates objects to their rooms. A refrigerator is associated with a kitchen. A crib is associated with a nursery"}], "Negative Examples": [{"input": "dresser : bedroom. boxes : ?", "output": "fill", "explanation": "The given analogy relates objects to their rooms. A dresser is associated with a bedroom. Fill is not a room, and hence the answer does not model containment"}, {"input": "workbench : garage. pantry : ?", "output": "store", "explanation": "The given analogy relates objects to their rooms. A workbench is associated with a garage. Store is not a room, and hence the answer does not model containment"}, {"input": "bookshelf : library. shelf : ?", "output": "driveway", "explanation": "The given analogy relates objects to their rooms. A bookshelf is associated with a library. Shelf is not associated with driveway, and hence the answer does not model containment"}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Commonsense"], "Instance": {"id": "task1157-e7d794429aca4f1dbda5c69204805883", "input": "shed : garden. desk : ?", "output": ["office"]}, "Instance License": ["Apache 2.0"], "prediction": "office"}
+{"id": "task1157-53134a8972344334afccb8a03f5d75e4", "Task": "task1157_bard_analogical_reasoning_rooms_for_containers", "Contributors": "['Arjun Ashok']", "Source": ["bard"], "URL": ["https://github.com/NancyFulda/BYU-Analogical-Reasoning-Dataset"], "Categories": ["Word Analogy"], "Reasoning": ["Relational Reasoning", "Commonsense Reasoning", "Analogical Reasoning"], "Definition": ["Two analogies that relate objects to the associated rooms is given in the form \"A : B. C : ?\". \"A : B\" relates object A to room B. Your task is to replace the question mark (?) with the appropriate room for the given object C, following the \"A : B\" relation."], "Positive Examples": [{"input": "shelf : nursury. cabinet : ?", "output": "bathroom", "explanation": "The given analogy relates objects to their rooms. A shelf is associated with a nursery. A cabinet is associated with a bathroom"}, {"input": "dresser : bedroom. boxes : ?", "output": "garage", "explanation": "The given analogy relates objects to their rooms. A dresser is associated with a bedroom. Boxes are associated with a garage"}, {"input": "refrigerator : kitchen. crib : ?", "output": "nursery", "explanation": "The given analogy relates objects to their rooms. A refrigerator is associated with a kitchen. A crib is associated with a nursery"}], "Negative Examples": [{"input": "dresser : bedroom. boxes : ?", "output": "fill", "explanation": "The given analogy relates objects to their rooms. A dresser is associated with a bedroom. Fill is not a room, and hence the answer does not model containment"}, {"input": "workbench : garage. pantry : ?", "output": "store", "explanation": "The given analogy relates objects to their rooms. A workbench is associated with a garage. Store is not a room, and hence the answer does not model containment"}, {"input": "bookshelf : library. shelf : ?", "output": "driveway", "explanation": "The given analogy relates objects to their rooms. A bookshelf is associated with a library. Shelf is not associated with driveway, and hence the answer does not model containment"}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Commonsense"], "Instance": {"id": "task1157-53134a8972344334afccb8a03f5d75e4", "input": "counter : kitchen. shelf : ?", "output": ["kitchen", "pantry", "nursury"]}, "Instance License": ["Apache 2.0"], "prediction": "bathroom"}
+{"id": "task1157-c95a573c139240639d1b4e89d149e2fb", "Task": "task1157_bard_analogical_reasoning_rooms_for_containers", "Contributors": "['Arjun Ashok']", "Source": ["bard"], "URL": ["https://github.com/NancyFulda/BYU-Analogical-Reasoning-Dataset"], "Categories": ["Word Analogy"], "Reasoning": ["Relational Reasoning", "Commonsense Reasoning", "Analogical Reasoning"], "Definition": ["Two analogies that relate objects to the associated rooms is given in the form \"A : B. C : ?\". \"A : B\" relates object A to room B. Your task is to replace the question mark (?) with the appropriate room for the given object C, following the \"A : B\" relation."], "Positive Examples": [{"input": "shelf : nursury. cabinet : ?", "output": "bathroom", "explanation": "The given analogy relates objects to their rooms. A shelf is associated with a nursery. A cabinet is associated with a bathroom"}, {"input": "dresser : bedroom. boxes : ?", "output": "garage", "explanation": "The given analogy relates objects to their rooms. A dresser is associated with a bedroom. Boxes are associated with a garage"}, {"input": "refrigerator : kitchen. crib : ?", "output": "nursery", "explanation": "The given analogy relates objects to their rooms. A refrigerator is associated with a kitchen. A crib is associated with a nursery"}], "Negative Examples": [{"input": "dresser : bedroom. boxes : ?", "output": "fill", "explanation": "The given analogy relates objects to their rooms. A dresser is associated with a bedroom. Fill is not a room, and hence the answer does not model containment"}, {"input": "workbench : garage. pantry : ?", "output": "store", "explanation": "The given analogy relates objects to their rooms. A workbench is associated with a garage. Store is not a room, and hence the answer does not model containment"}, {"input": "bookshelf : library. shelf : ?", "output": "driveway", "explanation": "The given analogy relates objects to their rooms. A bookshelf is associated with a library. Shelf is not associated with driveway, and hence the answer does not model containment"}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Commonsense"], "Instance": {"id": "task1157-c95a573c139240639d1b4e89d149e2fb", "input": "microwave : kitchen. cabinet : ?", "output": ["bathroom"]}, "Instance License": ["Apache 2.0"], "prediction": "bathroom"}
+{"id": "task1157-b2368b6a74204322ba1a36f4e0463f70", "Task": "task1157_bard_analogical_reasoning_rooms_for_containers", "Contributors": "['Arjun Ashok']", "Source": ["bard"], "URL": ["https://github.com/NancyFulda/BYU-Analogical-Reasoning-Dataset"], "Categories": ["Word Analogy"], "Reasoning": ["Relational Reasoning", "Commonsense Reasoning", "Analogical Reasoning"], "Definition": ["Two analogies that relate objects to the associated rooms is given in the form \"A : B. C : ?\". \"A : B\" relates object A to room B. Your task is to replace the question mark (?) with the appropriate room for the given object C, following the \"A : B\" relation."], "Positive Examples": [{"input": "shelf : nursury. cabinet : ?", "output": "bathroom", "explanation": "The given analogy relates objects to their rooms. A shelf is associated with a nursery. A cabinet is associated with a bathroom"}, {"input": "dresser : bedroom. boxes : ?", "output": "garage", "explanation": "The given analogy relates objects to their rooms. A dresser is associated with a bedroom. Boxes are associated with a garage"}, {"input": "refrigerator : kitchen. crib : ?", "output": "nursery", "explanation": "The given analogy relates objects to their rooms. A refrigerator is associated with a kitchen. A crib is associated with a nursery"}], "Negative Examples": [{"input": "dresser : bedroom. boxes : ?", "output": "fill", "explanation": "The given analogy relates objects to their rooms. A dresser is associated with a bedroom. Fill is not a room, and hence the answer does not model containment"}, {"input": "workbench : garage. pantry : ?", "output": "store", "explanation": "The given analogy relates objects to their rooms. A workbench is associated with a garage. Store is not a room, and hence the answer does not model containment"}, {"input": "bookshelf : library. shelf : ?", "output": "driveway", "explanation": "The given analogy relates objects to their rooms. A bookshelf is associated with a library. Shelf is not associated with driveway, and hence the answer does not model containment"}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Commonsense"], "Instance": {"id": "task1157-b2368b6a74204322ba1a36f4e0463f70", "input": "couch : parlor. closet : ?", "output": ["hallway", "bedroom"]}, "Instance License": ["Apache 2.0"], "prediction": "bedroom"}
+{"id": "task937-b2c6f4e5306b42e2909dc328c67f5ca8", "Task": "task937_defeasible_nli_social_classification", "Contributors": "['Sujan Reddy A']", "Source": ["defeasible_nli_atomic"], "URL": ["https://github.com/rudinger/defeasible-nli"], "Categories": ["Textual Entailment"], "Reasoning": ["Commonsense Reasoning -> Social Situations"], "Definition": ["In this task, you are given a hypothesis and an update. The hypothesis sentence is a statement that speaks of a socially normative behavior. In other words, it is a generalizing statement about how we expect people to behave in society. The update provides additional contexts about the situation that might UNDERMINE or SUPPORT the generalization. An undermining context provides a situation that weakens the hypothesis. A supporting context provides a situation that strengthens the generalization. Your task is to output 'strengthener' or 'weakener' if the update supports or undermines the hypothesis, respectively"], "Positive Examples": [{"input": "Hypothesis: You should help your family with funeral expenses.\nUpdate: They have asked you to chip in", "output": "strengthener", "explanation": "If your family has asked you to chip in for the funeral expenses, you should help them."}, {"input": "Hypothesis: It's good to protect your property.\nUpdate: you don't care what happens to your property.", "output": "weakener", "explanation": "You can't protect your property if you don't care what happens to your property."}, {"input": "Hypothesis: You should help your family with funeral expenses.\nUpdate: You are not financially stable to help out", "output": "weakener", "explanation": "If you are not financially stable, you will not be able to help your family with funeral expenses."}], "Negative Examples": [{"input": "Hypothesis: You should help your family with funeral expenses.\nUpdate: They have asked you to chip in", "output": "I dont know.", "explanation": "Do not generate anything else apart from one of the following : 'strengthener', 'weakener' "}, {"input": "Hypothesis: You should help your family with funeral expenses.\nUpdate: You are not financially stable to help out", "output": "strengthener,weakener.", "explanation": "The update could either strengthen or weaken the hypothesis, not both."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Commonsense -> Concepts and Relations"], "Instance": {"id": "task937-b2c6f4e5306b42e2909dc328c67f5ca8", "input": "Hypothesis: It is wrong to sign someone up for something without their permission.\nUpdate: They will receive a full scholarship to their favorite university.", "output": ["weakener"]}, "Instance License": ["MIT"], "prediction": "weakener"}
+{"id": "task937-9d0b6f791f3a4d7d84bbb793e5fa2dff", "Task": "task937_defeasible_nli_social_classification", "Contributors": "['Sujan Reddy A']", "Source": ["defeasible_nli_atomic"], "URL": ["https://github.com/rudinger/defeasible-nli"], "Categories": ["Textual Entailment"], "Reasoning": ["Commonsense Reasoning -> Social Situations"], "Definition": ["In this task, you are given a hypothesis and an update. The hypothesis sentence is a statement that speaks of a socially normative behavior. In other words, it is a generalizing statement about how we expect people to behave in society. The update provides additional contexts about the situation that might UNDERMINE or SUPPORT the generalization. An undermining context provides a situation that weakens the hypothesis. A supporting context provides a situation that strengthens the generalization. Your task is to output 'strengthener' or 'weakener' if the update supports or undermines the hypothesis, respectively"], "Positive Examples": [{"input": "Hypothesis: You should help your family with funeral expenses.\nUpdate: They have asked you to chip in", "output": "strengthener", "explanation": "If your family has asked you to chip in for the funeral expenses, you should help them."}, {"input": "Hypothesis: It's good to protect your property.\nUpdate: you don't care what happens to your property.", "output": "weakener", "explanation": "You can't protect your property if you don't care what happens to your property."}, {"input": "Hypothesis: You should help your family with funeral expenses.\nUpdate: You are not financially stable to help out", "output": "weakener", "explanation": "If you are not financially stable, you will not be able to help your family with funeral expenses."}], "Negative Examples": [{"input": "Hypothesis: You should help your family with funeral expenses.\nUpdate: They have asked you to chip in", "output": "I dont know.", "explanation": "Do not generate anything else apart from one of the following : 'strengthener', 'weakener' "}, {"input": "Hypothesis: You should help your family with funeral expenses.\nUpdate: You are not financially stable to help out", "output": "strengthener,weakener.", "explanation": "The update could either strengthen or weaken the hypothesis, not both."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Commonsense -> Concepts and Relations"], "Instance": {"id": "task937-9d0b6f791f3a4d7d84bbb793e5fa2dff", "input": "Hypothesis: It is wrong to bring up family troubles to people outside the family without consent.\nUpdate: You don't know the person you are talking to about your problems.", "output": ["strengthener"]}, "Instance License": ["MIT"], "prediction": "weakener"}
+{"id": "task937-e9b78ac4e8b94bfd8231c96db16afeaa", "Task": "task937_defeasible_nli_social_classification", "Contributors": "['Sujan Reddy A']", "Source": ["defeasible_nli_atomic"], "URL": ["https://github.com/rudinger/defeasible-nli"], "Categories": ["Textual Entailment"], "Reasoning": ["Commonsense Reasoning -> Social Situations"], "Definition": ["In this task, you are given a hypothesis and an update. The hypothesis sentence is a statement that speaks of a socially normative behavior. In other words, it is a generalizing statement about how we expect people to behave in society. The update provides additional contexts about the situation that might UNDERMINE or SUPPORT the generalization. An undermining context provides a situation that weakens the hypothesis. A supporting context provides a situation that strengthens the generalization. Your task is to output 'strengthener' or 'weakener' if the update supports or undermines the hypothesis, respectively"], "Positive Examples": [{"input": "Hypothesis: You should help your family with funeral expenses.\nUpdate: They have asked you to chip in", "output": "strengthener", "explanation": "If your family has asked you to chip in for the funeral expenses, you should help them."}, {"input": "Hypothesis: It's good to protect your property.\nUpdate: you don't care what happens to your property.", "output": "weakener", "explanation": "You can't protect your property if you don't care what happens to your property."}, {"input": "Hypothesis: You should help your family with funeral expenses.\nUpdate: You are not financially stable to help out", "output": "weakener", "explanation": "If you are not financially stable, you will not be able to help your family with funeral expenses."}], "Negative Examples": [{"input": "Hypothesis: You should help your family with funeral expenses.\nUpdate: They have asked you to chip in", "output": "I dont know.", "explanation": "Do not generate anything else apart from one of the following : 'strengthener', 'weakener' "}, {"input": "Hypothesis: You should help your family with funeral expenses.\nUpdate: You are not financially stable to help out", "output": "strengthener,weakener.", "explanation": "The update could either strengthen or weaken the hypothesis, not both."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Commonsense -> Concepts and Relations"], "Instance": {"id": "task937-e9b78ac4e8b94bfd8231c96db16afeaa", "input": "Hypothesis: It's okay to be attracted to some people and not others.\nUpdate: You are looking for a romantic partner.", "output": ["strengthener"]}, "Instance License": ["MIT"], "prediction": "weakener"}
+{"id": "task937-ed511d1643b841e8962326272cd82057", "Task": "task937_defeasible_nli_social_classification", "Contributors": "['Sujan Reddy A']", "Source": ["defeasible_nli_atomic"], "URL": ["https://github.com/rudinger/defeasible-nli"], "Categories": ["Textual Entailment"], "Reasoning": ["Commonsense Reasoning -> Social Situations"], "Definition": ["In this task, you are given a hypothesis and an update. The hypothesis sentence is a statement that speaks of a socially normative behavior. In other words, it is a generalizing statement about how we expect people to behave in society. The update provides additional contexts about the situation that might UNDERMINE or SUPPORT the generalization. An undermining context provides a situation that weakens the hypothesis. A supporting context provides a situation that strengthens the generalization. Your task is to output 'strengthener' or 'weakener' if the update supports or undermines the hypothesis, respectively"], "Positive Examples": [{"input": "Hypothesis: You should help your family with funeral expenses.\nUpdate: They have asked you to chip in", "output": "strengthener", "explanation": "If your family has asked you to chip in for the funeral expenses, you should help them."}, {"input": "Hypothesis: It's good to protect your property.\nUpdate: you don't care what happens to your property.", "output": "weakener", "explanation": "You can't protect your property if you don't care what happens to your property."}, {"input": "Hypothesis: You should help your family with funeral expenses.\nUpdate: You are not financially stable to help out", "output": "weakener", "explanation": "If you are not financially stable, you will not be able to help your family with funeral expenses."}], "Negative Examples": [{"input": "Hypothesis: You should help your family with funeral expenses.\nUpdate: They have asked you to chip in", "output": "I dont know.", "explanation": "Do not generate anything else apart from one of the following : 'strengthener', 'weakener' "}, {"input": "Hypothesis: You should help your family with funeral expenses.\nUpdate: You are not financially stable to help out", "output": "strengthener,weakener.", "explanation": "The update could either strengthen or weaken the hypothesis, not both."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Commonsense -> Concepts and Relations"], "Instance": {"id": "task937-ed511d1643b841e8962326272cd82057", "input": "Hypothesis: It is okay to think your friend might be self-entitled.\nUpdate: Your friend donated all their money to charity", "output": ["weakener"]}, "Instance License": ["MIT"], "prediction": "weakener"}
+{"id": "task937-6d5d60a2df3247bcb9acf8728c610b99", "Task": "task937_defeasible_nli_social_classification", "Contributors": "['Sujan Reddy A']", "Source": ["defeasible_nli_atomic"], "URL": ["https://github.com/rudinger/defeasible-nli"], "Categories": ["Textual Entailment"], "Reasoning": ["Commonsense Reasoning -> Social Situations"], "Definition": ["In this task, you are given a hypothesis and an update. The hypothesis sentence is a statement that speaks of a socially normative behavior. In other words, it is a generalizing statement about how we expect people to behave in society. The update provides additional contexts about the situation that might UNDERMINE or SUPPORT the generalization. An undermining context provides a situation that weakens the hypothesis. A supporting context provides a situation that strengthens the generalization. Your task is to output 'strengthener' or 'weakener' if the update supports or undermines the hypothesis, respectively"], "Positive Examples": [{"input": "Hypothesis: You should help your family with funeral expenses.\nUpdate: They have asked you to chip in", "output": "strengthener", "explanation": "If your family has asked you to chip in for the funeral expenses, you should help them."}, {"input": "Hypothesis: It's good to protect your property.\nUpdate: you don't care what happens to your property.", "output": "weakener", "explanation": "You can't protect your property if you don't care what happens to your property."}, {"input": "Hypothesis: You should help your family with funeral expenses.\nUpdate: You are not financially stable to help out", "output": "weakener", "explanation": "If you are not financially stable, you will not be able to help your family with funeral expenses."}], "Negative Examples": [{"input": "Hypothesis: You should help your family with funeral expenses.\nUpdate: They have asked you to chip in", "output": "I dont know.", "explanation": "Do not generate anything else apart from one of the following : 'strengthener', 'weakener' "}, {"input": "Hypothesis: You should help your family with funeral expenses.\nUpdate: You are not financially stable to help out", "output": "strengthener,weakener.", "explanation": "The update could either strengthen or weaken the hypothesis, not both."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Commonsense -> Concepts and Relations"], "Instance": {"id": "task937-6d5d60a2df3247bcb9acf8728c610b99", "input": "Hypothesis: It is important to be able to admit you've made mistakes.\nUpdate: You want to maintain healthy relationships with people.", "output": ["strengthener"]}, "Instance License": ["MIT"], "prediction": "weakener"}
+{"id": "task743-32f70e1defd545f79bdc19bbd3d1f735", "Task": "task743_eurlex_summarization", "Contributors": "['Raghul Raj Manogeran']", "Source": ["eurlex"], "URL": ["https://huggingface.co/datasets/eurlex"], "Categories": ["Title Generation"], "Reasoning": [], "Definition": ["In this task, you are provided with an article about the legal acts. Your task is to generate a headline for that article."], "Positive Examples": [{"input": "Articles 52 to 58 of the Treaty shall apply to the French overseas departments under the conditions laid down in this Decision.At the time when the directives implementing the General Programme for the Abolition of Restrictions on Freedom of Establishment are adopted, the Council may as an exception and to the extent necessary issue special directives on the establishment of persons and companies or firms in the French overseas departments. Without prejudice to the implementation of the measures adopted pursuant to the Treaty and to the Implementing Convention of 25 March 1957 and of those to be adopted pursuant to Article 1, the right of establishment in the French overseas departments shall be progressively extended to the companies or firms and nationals of Member States other than France, so that all discrimination may disappear not later than three years after the application of this Decision.The Council, acting by a qualified majority on a proposal from the Commission, shall issue the necessary directives for the implementation of that progressive extension.However, the nationals and companies or firms of a Member State shall only be able to benefit, in respect of a given activity, in a French overseas department from the provisions of the first paragraph to the extent to which the State of which they are nationals grants in respect of the same activity advantages of the same kind to French nationals and companies or firms. The provisions of Article 106 of the Treaty, in so far as they are not affected by the Council Decision of 11 May 1960 on the application to Algeria and to the French overseas departments of the provisions of the Treaty concerning capital movements, shall apply to the French overseas departments. This Decision shall be applied by the Member States on the same date as the Council Decision on the association of the overseas countries and territories with the European Economic Community.That date shall be published in the Official Journal of the European Communities.", "output": "Council Decision on the application to the French overseas departments of certain provisions of the Treaty relating to the right of establishment and to payments", "explanation": "The article discusses about the conditions laid for the French overseas department. This can be observed in multiple sentences of this article."}, {"input": "The Rules of the Transport Committee shall be amended as follows:    A. The following sentence shall be added to the first paragraph of Article 4:'Save for the cases specified in the two following paragraphs, Committee members and their alternates shall remain in office until replaced.'B. The following article shall be added after Article 5:'Article 5aAfter expiry of the term of office of the Chairman and Vice-Chairman, the chair shall be taken, until the election provided for in Article 5, by the oldest of the members referred to in the first paragraph of that Article.", "output": "Council Decision amending the Rules of the Transport Committee", "explanation": "The first sentence summarizes what this article is about and the rules are laid out after that. These discuss the rules of the transport committee."}, {"input": "Member States shall not authorise the use, for the protection of foodstuffs intended for human consumption (hereinafter called 'foodstuffs') against deterioration caused by micro-organisms, of any preservatives other than those listed in the Annex to this Directive. 1. Member States shall take all measures necessary to ensure that the preservatives for whose use the 1 OJ No 106, 12.7.1963, p. 1923/63.  2 OJ No 161, 27.1.1964, p. 169/64.   Annex lays down certain conditions are used solely in accordance with those conditions.2. Save as otherwise provided in paragraph 1, this Directive shall not affect provisions of national laws specifying the foodstuffs to which the preservatives listed in the Annex may be added and the conditions governing the addition of such preservatives ; however, such provisions must not have the effect of totally excluding the use in foodstuffs of any of the preservatives listed in the Annex. Member States shall authorise the smoking of certain foodstuffs only in smoke produced from wood or woody plants in the natural state, excluding wood or plants which have been impregnated, coloured, gummed, painted or treated in a similar manner, and provided that such smoking does not create any risk to human health. 1. Where the use in foodstuffs of one of the preservatives listed in the Annex, or the level of one or more of the components referred to in Article 7 contained in such preservative, might endanger human health, a Member State may, for a maximum period of one year, suspend the authorisation to use that preservative or reduce the maximum authorised level of one or more of the components in question. It shall inform the other Member States and the Commission thereof within one month.2. The Council, acting unanimously on a proposal from the Commission, shall decide without delay whether the list given in the Annex should be amended and, if so, adopt by directive the necessary amendments. The Council, acting by a qualified majority on a proposal from the Commission, may also, if necessary, extend for a maximum of one year the period set in the first sentence of paragraph 1. By way of derogation from Article 1, Member States may:    (a) for a period of three years following notification of this Directive, maintain in force the provisions of their national laws relating to the use in foodstuffs of formic acid and its salts, boric acid and its salts, organo-borated compounds and hexamethylene-tetramine;(b) until 31 December 1965 maintain in force the provisions of their national laws relating to the surface treatment of citrus fruit with diphenyl, orthophenylphenol and sodium orthophenylphenate. This Directive shall not affect the provisions of national laws concerning:    (a) products used as foodstuffs but which may also have preservative properties, for example vinegar, sodium chloride, ethanol, edible oils, and sugars in particular;(b) nisin;(c) products used for coating foodstuffs;(d) products used to protect plants and plant products against harmful organisms;(e) anti-microbial products used for the treatment of drinking water;(f) antioxidants. Member States shall take all measures necessary to ensure that the preservatives listed in the Annex and intended for use in foodstuffs satisfy:    (a) the following general criteria of purity:      - they must contain not more than 3 mg/kg of arsenic and not more than 10 mg/kg of lead;- they must contain not more than 50 mg/kg of copper and zinc taken together, of which the zinc content must not be higher than 25 mg/kg, nor must they contain any measurable trace of toxicologically dangerous elements, in particular other heavy metals, always subject however to any exceptions implicit in the specific criteria referred to in subparagraph (b);(b) the specific criteria of purity laid down where appropriate and in accordance with Article 8 (1). 1. The Council shall, acting unanimously on a proposal from the Commission, lay down by directive the specific criteria of purity referred to in Article 7 (b).2. After consulting the Member States, the Commission shall establish by directive the methods of analysis needed to verify that the general and specific criteria referred to in Article 7 are satisfied. 1. The Member States shall take all measures necessary to ensure that the preservatives listed in the Annex and intended for use in foodstuffs are placed on the market only if their packagings or containers bear the following information:    (a) the name and address of the manufacturer, or of a seller responsible within the meaning of the laws of the Member State in which he is resident ; a person importing a product from a third country shall be treated as the manufacturer;(b) the number and name of the preservative as they are given in the Annex;(c) the words 'for foodstuffs (restricted use)';(d) in the case of a mixture composed of preservatives and other products, the percentage of the preservative and the name of the mixture.2. If the information required under paragraph 1 appears on the packagings or containers, and if the information required under paragraphs (b) and (c) is given in two of the official languages of the Community, one of Germanic and the other of Latin origin, Member States shall not prohibit the introduction into their territory and the placing on the market of preservatives listed in the Annex solely on the grounds that they consider the labelling inadequate. 01. This Directive shall also apply to preservatives intended for use in foodstuffs and to foodstuffs imported into the Community.2. This Directive shall not apply to preservatives and foodstuffs intended for exportation from the Community. 11. Member States shall, within a period of one year following notification of this Directive, amend their laws in accordance with the above provisions and shall forthwith inform the Commission thereof. The laws thus amended shall apply to preservatives and foodstuffs placed on the market in Member States not later than two years after that notification.2. Where Article 5 (a) is applicable the date of expiry of the period set in that Article shall be substituted for the date of notification referred to in paragraph 1. 2This Directive shall also apply in the French overseas departments. 3This Directive is addressed to the Member States.", "output": "Council Directive on the approximation of the laws of the Member States concerning the preservatives authorized for use in foodstuffs intended for human consumption", "explanation": "The first sentence summarizes what this article is about followed by rules are laid out for the same. The discussion is about authorized preservatives used in foodstuffs which are consumed by humans."}, {"input": "1. Member States, acting in accordance with the provisions hereinafter laid down, shall adopt the following transitional measures in respect of establishment or provision of services in their territories by natural persons or companies or firms covered by Title I of the General Programmes wishing to engage in activities in wholesale trade or as intermediaries in commerce, industry and small craft industries.2. The activities in question are those covered by the Council Directive of 25 February 1964 concerning the attainment of freedom of establishment and freedom to provide services in respect of activities in wholesale trade and by the Council Directive of 25 February 1964 concerning the attainment of freedom of establishment and freedom to provide services in respect of activities of intermediaries in commerce, industry and small craft industries. Where, in a Member State, the taking up or pursuit of any activity referred to in Article 1 (2) is dependent on the possession of general commercial or professional knowledge, that Member State shall accept as sufficient evidence of such knowledge the fact that the activity in question has been pursued in another Member State for a period of three consecutive years either in an independent capacity or in a managerial capacity, on condition that such activity shall not have ceased more than two years before the date when the application provided for in Article 4 (2) is made. 1. Where, in a Member State, the taking up or pursuit of any activity referred to in Article 1 (2) is not subject to the possession of general, commercial, or professional knowledge, and where that State faces serious and damaging consequences as a result of the application of the Council Directive referred to in Article 1 (2), that Member State may request from the Commission authorisation, for a limited period and in respect of one or more specified activities, to require from nationals of other Member States who wish to pursue those activities in its territory proof that they possess the qualifications required for the pursuit of such activities, either in an independent capacity or in a managerial capacity, in the country whence they come.Use shall not be made of this power in respect of a person who comes from a country which does not make the taking up of the activity in question subject to proof of particular knowledge, or in respect of a person who has lived in the host country for at least five years.2. On receipt of a request from the Member State concerned stating the reasons on which it is based, the Commission shall forthwith specify the conditions on which the authorisation provided for in paragraph 1 of this Article will be granted and lay down detailed rules concerning its implementation. 1. A person shall be regarded as having pursued an activity in a managerial capacity within the meaning of Articles 2 and 3 if he has pursued such activity in an industrial or commercial undertaking in the field in question:    (a) as manager of an undertaking or manager of a branch of an undertaking ; or(b) as deputy to the proprietor or to the manager of an undertaking, where such post involves responsibility equivalent to that of the proprietor or manager represented.2. Proof that the conditions laid down in Article 2 or in Article 3 (1) are satisfied shall be established by certificates issued by the competent authority or body in the country whence the person concerned comes, which such person shall submit in support of his application for authorisation to pursue the activity or activities in question in the host country.3. Member States shall, within the time limit laid down in Article 6, designate the authorities and bodies competent to issue these certificates and shall forthwith inform the other Member States and the Commission thereof. The provisions of this Directive shall remain applicable until the entry into force of provisions relating to the co-ordination of national rules concerning the taking up and pursuit of the activities in question. Member States shall adopt the measures necessary to comply with this Directive within six months of its notification and shall forthwith inform the Commission thereof. Member States shall ensure that the texts of the main provisions of national law which they adopt in the field covered by this Directive are communicated to the Commission. This Directive is addressed to the Member States.", "output": "Council Directive laying down detailed provisions concerning transitional measures in respect of activities in wholesale trade and activities of intermediaries in commerce, industry and small craft industries", "explanation": "The summary of the passage is introduced right at the top. The discussion is about transitional measures in wholesale trading and activities of intermediaries in commerce, industry and small craft industries."}], "Negative Examples": [{"input": "Member States shall abolish, in respect of the natural persons and companies or firms covered by Title I of the General Programmes for the abolition of restrictions on freedom of establishment and freedom to provide services the restrictions referred to in Title III of those General Programmes affecting the right to take up and pursue the activities specified in Article 2 of this Directive. The provisions of this Directive shall apply:    1. to activities of self-employed persons in reinsurance and retrocession falling within Group ex 630  1 OJ No 2, 15.1.1962, p. 36/62.  2 OJ No 2, 15.1.1962, p. 32/62.  3 OJ No 33, 4.3.1963, p. 482/63.  4 OJ No 56, 4.4.1963, p. 882/64.  in Annex I to the General Programme for the abolition of restrictions on freedom of establishment;2. in the special case of natural persons, companies or firms referred to in Article 1 which deal both in direct insurance and in reinsurance and retrocession, to that part of their activities which is concerned with reinsurance and retrocession. Article 1 shall apply in particular to restrictions arising out of the following provisions:    (a) with regard to freedom of establishment:  - in the Federal Republic of Germany      (1) Versicherungsaufsichtsgesetz of 6 June 1931, last sentence of Article 106 (2), and Article 111 (2), whereby the Federal Minister of Economic Affairs is given discretionary powers to impose on foreign nationals conditions for taking up activities in insurance and to prohibit such nationals from pursuing such activities in the territory of the Federal Republic;(2) Gewerbeordnung, paragraph 12, and Law of 30 January 1937, Article 292, whereby foreign companies and firms are required to obtain prior authorisation;- in the Kingdom of BelgiumArr\u00eat\u00e9 royal No 62 of 16 November 1939 and Arr\u00eat\u00e9 minist\u00e9riel of 17 December 1945, which require the possession of a carte professionelle;- in the French Republic      (1) D\u00e9cret-loi of 12 November 1938 and D\u00e9cret of 2 February 1939, both as amended by the Law of 8 October 1940, which require the possession of a carte d'identit\u00e9 de commer\u00e7ant;(2) Second paragraph of Article 2 of the Law of 15 February 1917, as amended and supplemented by D\u00e9cret-loi of 30 October 1935, which requires that special authorisation be obtained;- in the Grand Duchy of LuxembourgLaw of 2 June 1962, Articles 19 and 21 (M\u00e9morial A No 31 of 19 June 1962).(b) with regard to freedom to provide services:  - in the French RepublicLaw of 15 February 1917, as amended by D\u00e9cret-loi of 30 October 1935, namely:      (1) The second paragraph of Article 1, which empowers the Minister of Finance to draw up a list of specified undertakings, or of undertakings of a specified country, with which no contract for reinsurance or retrocession of any risk in respect of any person, property or liability in France may be concluded;(2) the last paragraph of Article 1, which prohibits the acceptance of reinsurance or of retrocession risks insured by the undertakings referred to in (b) (1) above;(3) the first paragraph of Article 2, which requires that the name of the person referred to in that Article must be submitted to the Minister of Finance for approval;- in the Republic of ItalyThe second paragraph of Article 73 of the consolidated text approved by Decreto No 449 of 13 February 1959, which empowers the Minister of Industry and Commerce to prohibit the transfer of reinsurance or retrocession risks to specified foreign undertakings which have not established legal representation in Italian territory. Member States shall adopt the measures necessary to comply with this Directive within six months of its notification and shall forthwith inform the Commission thereof. This Directive is addressed to the Member States.", "output": "Council Directive on activities of self-employed persons in reinsurance and retrocession falling within certains group", "explanation": "Though the article does talk about the activities of self-employed persons in reinsurance and retrocession, it is only a small portion in the whole article. Summary would be something generic on the lines of Council Directive on the abolition of restrictions on freedom of establishment and freedom to provide services in respect of reinsurance and retrocession"}, {"input": "The specific criteria of purity referred to in Article 7 (b) of the Directive of 5 November 1963 are given in the Annex to this Directive. Member States shall so amend their laws in accordance with the provisions of Article 1 that by 1 June 1966 the new measures apply to preservatives placed on the market. This Directive is addressed to the Member States.", "output": "Addressing the member states", "explanation": "The information about the directive is more important than on whom it is being addressed to. Hence the suitable title would be Council Directive laying down new measures for preservatives."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Law"], "Instance": {"id": "task743-32f70e1defd545f79bdc19bbd3d1f735", "input": "1. The Commission shall determine a world market price for colza and rape seeds and a world market price for sunflower seeds at regular intervals.2. When the world market price is being determined, the Commission shall take into account all offers made on the world market of which it has been informed by the Member States or which are known to it through its own inquiries, and prices quoted on those exchanges which are important for international trade.3. The Commission shall determine this price on the basis of the most favourable actual purchasing opportunities, excluding offers and quotations,  (1) OJ No 172, 30.9.1966, p. 3025/66.  (a) which do not relate to shipments to be effected within a given period, which has not yet been fixed, after the date on which the world market price is determined,(b) which cannot be regarded as representative of the actual market trend. Where no offer or quotation can be used as a basis for determining the world market price for a type of seed, the Commission shall determine this price on the basis of the value of average quantities of oil and oil-cake resulting from the processing of 100 kilogrammes of this type of seed in the Community less an amount corresponding to the cost of processing these seeds into oil and oil-cake. Where no offer or quotation can be used as a basis for determining the world market price for a type of seed and further, where it is impossible to establish the value of the oil-cake or oil processed from such seeds, the world market price shall be determined on the basis of the last recorded value for the oil or oil-cake, adjusted to take account of the trend of world prices for competing products in accordance with Article 2. For the purpose of determining the prices referred to in Article 1, the Community frontier crossing point shall be Rotterdam. The Commission shall determine the world market price for seeds of the standard quality for which the target price has been fixed, delivered in bulk at Rotterdam.Where offers and quotations do not fulfil the conditions set out above, the Commission shall make the necessary adjustments. 1. When the world market price for a type of seed is being determined, the price used shall be adjusted by an amount not exceeding the margin between:  - the difference between the price of 100 kilogrammes of colza, rape or sunflower seeds, plus processing costs, and the total of the prices of the quantities of oil and oil-cake resulting from the processing of the type of seed in question and- the difference between the price of 100 kilogrammes of one or more other seeds, plus processing costs, and the total of the prices of the quantities of oil and oil-cake resulting from processing these seeds.2. When the amount referred to in paragraph 1 is being determined, account shall be taken of the incidence of the margin in question (a) on marketing operations of Community traders,(b) on the disposal of the various types of seed on the world market. Detailed rules for the application of this Regulation shall be adopted in accordance with the procedure laid down in Article 38 of Regulation No 136/66/EEC.This Regulation shall be binding in its entirety and directly applicable in all Member States.", "output": ["Regulation laying down criteria for determining world market prices for oil seeds and fixing the frontier crossing point"]}, "Instance License": ["\u00a9 European Union, 1998-2021 (https://huggingface.co/datasets/eurlex#licensing-information)"], "prediction": "The Commission shall determine a world market price for colza and rape seeds and a world market price for sunflower seeds at regular intervals."}
+{"id": "task743-c80f7ee08dfd48938490379ba3a199ec", "Task": "task743_eurlex_summarization", "Contributors": "['Raghul Raj Manogeran']", "Source": ["eurlex"], "URL": ["https://huggingface.co/datasets/eurlex"], "Categories": ["Title Generation"], "Reasoning": [], "Definition": ["In this task, you are provided with an article about the legal acts. Your task is to generate a headline for that article."], "Positive Examples": [{"input": "Articles 52 to 58 of the Treaty shall apply to the French overseas departments under the conditions laid down in this Decision.At the time when the directives implementing the General Programme for the Abolition of Restrictions on Freedom of Establishment are adopted, the Council may as an exception and to the extent necessary issue special directives on the establishment of persons and companies or firms in the French overseas departments. Without prejudice to the implementation of the measures adopted pursuant to the Treaty and to the Implementing Convention of 25 March 1957 and of those to be adopted pursuant to Article 1, the right of establishment in the French overseas departments shall be progressively extended to the companies or firms and nationals of Member States other than France, so that all discrimination may disappear not later than three years after the application of this Decision.The Council, acting by a qualified majority on a proposal from the Commission, shall issue the necessary directives for the implementation of that progressive extension.However, the nationals and companies or firms of a Member State shall only be able to benefit, in respect of a given activity, in a French overseas department from the provisions of the first paragraph to the extent to which the State of which they are nationals grants in respect of the same activity advantages of the same kind to French nationals and companies or firms. The provisions of Article 106 of the Treaty, in so far as they are not affected by the Council Decision of 11 May 1960 on the application to Algeria and to the French overseas departments of the provisions of the Treaty concerning capital movements, shall apply to the French overseas departments. This Decision shall be applied by the Member States on the same date as the Council Decision on the association of the overseas countries and territories with the European Economic Community.That date shall be published in the Official Journal of the European Communities.", "output": "Council Decision on the application to the French overseas departments of certain provisions of the Treaty relating to the right of establishment and to payments", "explanation": "The article discusses about the conditions laid for the French overseas department. This can be observed in multiple sentences of this article."}, {"input": "The Rules of the Transport Committee shall be amended as follows:    A. The following sentence shall be added to the first paragraph of Article 4:'Save for the cases specified in the two following paragraphs, Committee members and their alternates shall remain in office until replaced.'B. The following article shall be added after Article 5:'Article 5aAfter expiry of the term of office of the Chairman and Vice-Chairman, the chair shall be taken, until the election provided for in Article 5, by the oldest of the members referred to in the first paragraph of that Article.", "output": "Council Decision amending the Rules of the Transport Committee", "explanation": "The first sentence summarizes what this article is about and the rules are laid out after that. These discuss the rules of the transport committee."}, {"input": "Member States shall not authorise the use, for the protection of foodstuffs intended for human consumption (hereinafter called 'foodstuffs') against deterioration caused by micro-organisms, of any preservatives other than those listed in the Annex to this Directive. 1. Member States shall take all measures necessary to ensure that the preservatives for whose use the 1 OJ No 106, 12.7.1963, p. 1923/63.  2 OJ No 161, 27.1.1964, p. 169/64.   Annex lays down certain conditions are used solely in accordance with those conditions.2. Save as otherwise provided in paragraph 1, this Directive shall not affect provisions of national laws specifying the foodstuffs to which the preservatives listed in the Annex may be added and the conditions governing the addition of such preservatives ; however, such provisions must not have the effect of totally excluding the use in foodstuffs of any of the preservatives listed in the Annex. Member States shall authorise the smoking of certain foodstuffs only in smoke produced from wood or woody plants in the natural state, excluding wood or plants which have been impregnated, coloured, gummed, painted or treated in a similar manner, and provided that such smoking does not create any risk to human health. 1. Where the use in foodstuffs of one of the preservatives listed in the Annex, or the level of one or more of the components referred to in Article 7 contained in such preservative, might endanger human health, a Member State may, for a maximum period of one year, suspend the authorisation to use that preservative or reduce the maximum authorised level of one or more of the components in question. It shall inform the other Member States and the Commission thereof within one month.2. The Council, acting unanimously on a proposal from the Commission, shall decide without delay whether the list given in the Annex should be amended and, if so, adopt by directive the necessary amendments. The Council, acting by a qualified majority on a proposal from the Commission, may also, if necessary, extend for a maximum of one year the period set in the first sentence of paragraph 1. By way of derogation from Article 1, Member States may:    (a) for a period of three years following notification of this Directive, maintain in force the provisions of their national laws relating to the use in foodstuffs of formic acid and its salts, boric acid and its salts, organo-borated compounds and hexamethylene-tetramine;(b) until 31 December 1965 maintain in force the provisions of their national laws relating to the surface treatment of citrus fruit with diphenyl, orthophenylphenol and sodium orthophenylphenate. This Directive shall not affect the provisions of national laws concerning:    (a) products used as foodstuffs but which may also have preservative properties, for example vinegar, sodium chloride, ethanol, edible oils, and sugars in particular;(b) nisin;(c) products used for coating foodstuffs;(d) products used to protect plants and plant products against harmful organisms;(e) anti-microbial products used for the treatment of drinking water;(f) antioxidants. Member States shall take all measures necessary to ensure that the preservatives listed in the Annex and intended for use in foodstuffs satisfy:    (a) the following general criteria of purity:      - they must contain not more than 3 mg/kg of arsenic and not more than 10 mg/kg of lead;- they must contain not more than 50 mg/kg of copper and zinc taken together, of which the zinc content must not be higher than 25 mg/kg, nor must they contain any measurable trace of toxicologically dangerous elements, in particular other heavy metals, always subject however to any exceptions implicit in the specific criteria referred to in subparagraph (b);(b) the specific criteria of purity laid down where appropriate and in accordance with Article 8 (1). 1. The Council shall, acting unanimously on a proposal from the Commission, lay down by directive the specific criteria of purity referred to in Article 7 (b).2. After consulting the Member States, the Commission shall establish by directive the methods of analysis needed to verify that the general and specific criteria referred to in Article 7 are satisfied. 1. The Member States shall take all measures necessary to ensure that the preservatives listed in the Annex and intended for use in foodstuffs are placed on the market only if their packagings or containers bear the following information:    (a) the name and address of the manufacturer, or of a seller responsible within the meaning of the laws of the Member State in which he is resident ; a person importing a product from a third country shall be treated as the manufacturer;(b) the number and name of the preservative as they are given in the Annex;(c) the words 'for foodstuffs (restricted use)';(d) in the case of a mixture composed of preservatives and other products, the percentage of the preservative and the name of the mixture.2. If the information required under paragraph 1 appears on the packagings or containers, and if the information required under paragraphs (b) and (c) is given in two of the official languages of the Community, one of Germanic and the other of Latin origin, Member States shall not prohibit the introduction into their territory and the placing on the market of preservatives listed in the Annex solely on the grounds that they consider the labelling inadequate. 01. This Directive shall also apply to preservatives intended for use in foodstuffs and to foodstuffs imported into the Community.2. This Directive shall not apply to preservatives and foodstuffs intended for exportation from the Community. 11. Member States shall, within a period of one year following notification of this Directive, amend their laws in accordance with the above provisions and shall forthwith inform the Commission thereof. The laws thus amended shall apply to preservatives and foodstuffs placed on the market in Member States not later than two years after that notification.2. Where Article 5 (a) is applicable the date of expiry of the period set in that Article shall be substituted for the date of notification referred to in paragraph 1. 2This Directive shall also apply in the French overseas departments. 3This Directive is addressed to the Member States.", "output": "Council Directive on the approximation of the laws of the Member States concerning the preservatives authorized for use in foodstuffs intended for human consumption", "explanation": "The first sentence summarizes what this article is about followed by rules are laid out for the same. The discussion is about authorized preservatives used in foodstuffs which are consumed by humans."}, {"input": "1. Member States, acting in accordance with the provisions hereinafter laid down, shall adopt the following transitional measures in respect of establishment or provision of services in their territories by natural persons or companies or firms covered by Title I of the General Programmes wishing to engage in activities in wholesale trade or as intermediaries in commerce, industry and small craft industries.2. The activities in question are those covered by the Council Directive of 25 February 1964 concerning the attainment of freedom of establishment and freedom to provide services in respect of activities in wholesale trade and by the Council Directive of 25 February 1964 concerning the attainment of freedom of establishment and freedom to provide services in respect of activities of intermediaries in commerce, industry and small craft industries. Where, in a Member State, the taking up or pursuit of any activity referred to in Article 1 (2) is dependent on the possession of general commercial or professional knowledge, that Member State shall accept as sufficient evidence of such knowledge the fact that the activity in question has been pursued in another Member State for a period of three consecutive years either in an independent capacity or in a managerial capacity, on condition that such activity shall not have ceased more than two years before the date when the application provided for in Article 4 (2) is made. 1. Where, in a Member State, the taking up or pursuit of any activity referred to in Article 1 (2) is not subject to the possession of general, commercial, or professional knowledge, and where that State faces serious and damaging consequences as a result of the application of the Council Directive referred to in Article 1 (2), that Member State may request from the Commission authorisation, for a limited period and in respect of one or more specified activities, to require from nationals of other Member States who wish to pursue those activities in its territory proof that they possess the qualifications required for the pursuit of such activities, either in an independent capacity or in a managerial capacity, in the country whence they come.Use shall not be made of this power in respect of a person who comes from a country which does not make the taking up of the activity in question subject to proof of particular knowledge, or in respect of a person who has lived in the host country for at least five years.2. On receipt of a request from the Member State concerned stating the reasons on which it is based, the Commission shall forthwith specify the conditions on which the authorisation provided for in paragraph 1 of this Article will be granted and lay down detailed rules concerning its implementation. 1. A person shall be regarded as having pursued an activity in a managerial capacity within the meaning of Articles 2 and 3 if he has pursued such activity in an industrial or commercial undertaking in the field in question:    (a) as manager of an undertaking or manager of a branch of an undertaking ; or(b) as deputy to the proprietor or to the manager of an undertaking, where such post involves responsibility equivalent to that of the proprietor or manager represented.2. Proof that the conditions laid down in Article 2 or in Article 3 (1) are satisfied shall be established by certificates issued by the competent authority or body in the country whence the person concerned comes, which such person shall submit in support of his application for authorisation to pursue the activity or activities in question in the host country.3. Member States shall, within the time limit laid down in Article 6, designate the authorities and bodies competent to issue these certificates and shall forthwith inform the other Member States and the Commission thereof. The provisions of this Directive shall remain applicable until the entry into force of provisions relating to the co-ordination of national rules concerning the taking up and pursuit of the activities in question. Member States shall adopt the measures necessary to comply with this Directive within six months of its notification and shall forthwith inform the Commission thereof. Member States shall ensure that the texts of the main provisions of national law which they adopt in the field covered by this Directive are communicated to the Commission. This Directive is addressed to the Member States.", "output": "Council Directive laying down detailed provisions concerning transitional measures in respect of activities in wholesale trade and activities of intermediaries in commerce, industry and small craft industries", "explanation": "The summary of the passage is introduced right at the top. The discussion is about transitional measures in wholesale trading and activities of intermediaries in commerce, industry and small craft industries."}], "Negative Examples": [{"input": "Member States shall abolish, in respect of the natural persons and companies or firms covered by Title I of the General Programmes for the abolition of restrictions on freedom of establishment and freedom to provide services the restrictions referred to in Title III of those General Programmes affecting the right to take up and pursue the activities specified in Article 2 of this Directive. The provisions of this Directive shall apply:    1. to activities of self-employed persons in reinsurance and retrocession falling within Group ex 630  1 OJ No 2, 15.1.1962, p. 36/62.  2 OJ No 2, 15.1.1962, p. 32/62.  3 OJ No 33, 4.3.1963, p. 482/63.  4 OJ No 56, 4.4.1963, p. 882/64.  in Annex I to the General Programme for the abolition of restrictions on freedom of establishment;2. in the special case of natural persons, companies or firms referred to in Article 1 which deal both in direct insurance and in reinsurance and retrocession, to that part of their activities which is concerned with reinsurance and retrocession. Article 1 shall apply in particular to restrictions arising out of the following provisions:    (a) with regard to freedom of establishment:  - in the Federal Republic of Germany      (1) Versicherungsaufsichtsgesetz of 6 June 1931, last sentence of Article 106 (2), and Article 111 (2), whereby the Federal Minister of Economic Affairs is given discretionary powers to impose on foreign nationals conditions for taking up activities in insurance and to prohibit such nationals from pursuing such activities in the territory of the Federal Republic;(2) Gewerbeordnung, paragraph 12, and Law of 30 January 1937, Article 292, whereby foreign companies and firms are required to obtain prior authorisation;- in the Kingdom of BelgiumArr\u00eat\u00e9 royal No 62 of 16 November 1939 and Arr\u00eat\u00e9 minist\u00e9riel of 17 December 1945, which require the possession of a carte professionelle;- in the French Republic      (1) D\u00e9cret-loi of 12 November 1938 and D\u00e9cret of 2 February 1939, both as amended by the Law of 8 October 1940, which require the possession of a carte d'identit\u00e9 de commer\u00e7ant;(2) Second paragraph of Article 2 of the Law of 15 February 1917, as amended and supplemented by D\u00e9cret-loi of 30 October 1935, which requires that special authorisation be obtained;- in the Grand Duchy of LuxembourgLaw of 2 June 1962, Articles 19 and 21 (M\u00e9morial A No 31 of 19 June 1962).(b) with regard to freedom to provide services:  - in the French RepublicLaw of 15 February 1917, as amended by D\u00e9cret-loi of 30 October 1935, namely:      (1) The second paragraph of Article 1, which empowers the Minister of Finance to draw up a list of specified undertakings, or of undertakings of a specified country, with which no contract for reinsurance or retrocession of any risk in respect of any person, property or liability in France may be concluded;(2) the last paragraph of Article 1, which prohibits the acceptance of reinsurance or of retrocession risks insured by the undertakings referred to in (b) (1) above;(3) the first paragraph of Article 2, which requires that the name of the person referred to in that Article must be submitted to the Minister of Finance for approval;- in the Republic of ItalyThe second paragraph of Article 73 of the consolidated text approved by Decreto No 449 of 13 February 1959, which empowers the Minister of Industry and Commerce to prohibit the transfer of reinsurance or retrocession risks to specified foreign undertakings which have not established legal representation in Italian territory. Member States shall adopt the measures necessary to comply with this Directive within six months of its notification and shall forthwith inform the Commission thereof. This Directive is addressed to the Member States.", "output": "Council Directive on activities of self-employed persons in reinsurance and retrocession falling within certains group", "explanation": "Though the article does talk about the activities of self-employed persons in reinsurance and retrocession, it is only a small portion in the whole article. Summary would be something generic on the lines of Council Directive on the abolition of restrictions on freedom of establishment and freedom to provide services in respect of reinsurance and retrocession"}, {"input": "The specific criteria of purity referred to in Article 7 (b) of the Directive of 5 November 1963 are given in the Annex to this Directive. Member States shall so amend their laws in accordance with the provisions of Article 1 that by 1 June 1966 the new measures apply to preservatives placed on the market. This Directive is addressed to the Member States.", "output": "Addressing the member states", "explanation": "The information about the directive is more important than on whom it is being addressed to. Hence the suitable title would be Council Directive laying down new measures for preservatives."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Law"], "Instance": {"id": "task743-c80f7ee08dfd48938490379ba3a199ec", "input": "The tax on salaries, wages and emoluments paid by the Communities to their officials and other servants, indicated by the first paragraph of Article 13 of the Protocol on the Privileges and Immunities of the European Communities, shall be determined under the conditions and collected according to the procedure laid down in this Regulation. The following shall be liable to the tax:\u2014 persons coming under the Staff Regulations of Officials or the Conditions of Employment of Other Servants of the Communities, including recipients of the compensation provided for in the event of removal from post in the interests of the service, but excluding local staff;\u2014 recipients of the compensation on termination of service provided for in Article 5 of Council Regulation (EEC, Euratom, ECSC) No 259/68xa0(1). 1.xa0xa0xa0The tax shall be payable each month on salaries, wages and emoluments paid by the Communities to each person liable.2.xa0xa0xa0However, monies and allowances, whether lump sums or not, which represent compensation for expenses incurred in the perfomance of official duties, shall be excluded from the basic taxable amount.3.xa0xa0xa0The family allowance and social benefits listed below shall be deducted from the basic taxable amount:(a) family allowances:\u2014 head of household allowance,\u2014 dependent child's allowance,\u2014 education allowance,\u2014 allowance on the birth of a child;(b) social assistance;(c) allowances paid on account of occupational disease or accident;(d) that part of any payment which represents family allowances.The amount to be deducted shall be calculated, with due regard, where appropriate, to the provisions of Article 5.4.xa0xa0xa0Subject to the provisions of Article 5, an abatement of 10% for occupational and personal expenses shall be made from the amount obtained by applying the preceding provisions.An additional abatement equivalent to twice the amount of the allowance for a dependent child shall be made for each dependent child of the person liable as well as for each person treated as a dependent child within the meaning of Article 2 (4) of Annex VII to the Staff Regulations.5.xa0xa0xa0Deductions from remuneration of persons liable on account of pensions and retirement allowances or of social security shall be deducted from the basic taxable amount. The tax shall be calculated, subject to the provisions of Article 5, on the taxable amount obtained by applying Article 3 and disregarding any amount not exceeding Bfrs 803 and by applying the rate of:8% to amounts between Bfrs 803 and 14xa017810% to amounts between Bfrs 14xa0179 and 19xa052812\u038750% to amounts between Bfrs 19xa0529 and 22xa038015% to amounts between Bfrs 22xa0381 and 25xa041317\u038750% to amounts, between Bfrs 22xa0414 and 28xa026520% to amounts between Bfrs 28xa0266 and 31xa003022\u038750% to amounts between Bfrs 31xa0031 and 33xa088325% to amounts between Bfrs 33xa0884 and 36xa064827\u038750% to amounts between Bfrs 36xa0649 and 39xa050030% to amounts between Bfrs 39xa0501 and 42xa026532\u038750% to amounts between Bfrs 42xa0266 and 45xa011835% to amounts between Bfrs 45xa0119 and 47xa088340% to amounts between Bfrs 47xa0884 and 50xa073545% to amounts above Bfrs 50xa0735. When salaries, wages and emoluments are subject to a corrective factor:\u2014 the amount of each of the elements included in the calculation of the tax, except deductions made from the remuneration of persons liable on account of pensions, and retirement allowances or of social security, shall, for the application of this Regulation, be obtained by applying the corrective factor to the amount of this element as calculated before applying any corrective factor to the remuneration;\u2014 the amount of abatements mentioned in Article 3 (4) shall be obtained by applying the corrective factor to the amount of the abatements as calculated before applying any corrective factor to the remuneration;\u2014 the amounts of income shown in Article 4 shall be subject to the corrective factor. 1.xa0xa0xa0By way of derogation from the provisions of Articles 3 and 4:(a) the sums paid\u2014 as compensation for overtime,\u2014 for work of a particularly arduous nature,\u2014 for exceptional services,\u2014 for patented inventions,(b) payments made on account of termination of service shall be taxed, after applying the abatements laid down in Article 3 (4), at a rate equal to two thirds of the ratio existing, at the time of last salary payment, between:\u2014 the amount of tax payable and\u2014 the basic taxable amount as defined in Article 3.2.xa0xa0xa0The application of this Regulation shall not have the effect of reducing salaries, wages and emoluments of any kind paid by the Communities to an amount less than the minimum subsistence rate as defined in Article 6 of Annex VIII to the Staff Regulations of Officials of the Communities. When the taxable payment covers a period of less than one month, the rate of the tax shall be that which is applicable to the corresponding monthly payment.When the taxable payment covers a period of more than one month the tax shall be calculated as if this payment had been spread evenly over the months to which it relates.Corrective payments not related to the month during which they are paid shall be subject to the tax to which they would have been subject had they been made at the proper time. Tax shall be collected by means of deduction at source. The amount shall be rounded off at the lower unit. The tax proceeds shall be entered as revenue in the budgets of the Communities. 0The governing bodies of institutions of the Communities shall co-operate for the purpose of applying this Regulation in a uniform manner.The Council, acting on a proposal from the Commission, shall adopt any provisions necessary for the application of this Regulation. 1This Regulation shall also apply:\u2014 to members of the Commission,\u2014 to Judges, Advocates General, the Registrar and Assistant Rapporteurs at the Court of Justice,\u2014 to members of the Audit Board. 2This Regulation shall apply to members of the organs of the European Investment Bank, and to members of its staff and recipients of the pensions it pays, who are included in the categories determined by the Council in application of the first paragraph of Article 16 of the Protocol on Privileges and Immunities, with regard to salaries, wages and emoluments and to disability, retirement and survivors' pensions paid by the Bank. 3The compensation and payments referred to in Article 13 of Regulation No 32 (EEC) 12 (EAEC)xa0(2) shall be exempt from the tax. 4Regulation No 32 (EEC), 12 (EAEC) is hereby repealed. 5This Regulation shall enter into force on the day following its publication in the Official Journal of the European Communities.This Regulation shall be binding in its entirety and directly applicable in all Member States.", "output": ["Regulation laying down the conditions and procedure for applying the tax for the benefit of the European Communities"]}, "Instance License": ["\u00a9 European Union, 1998-2021 (https://huggingface.co/datasets/eurlex#licensing-information)"], "prediction": "The tax on salaries, wages and emoluments paid by the Communities to their officials and other servants, indicated by the first paragraph of Article 13 of the Protocol on the Privileges and Immunities of the European Communities, shall be determined under the conditions and collected according to the procedure laid down in this Regulation"}
+{"id": "task743-3f50de0342bd468f8e078d051fa06266", "Task": "task743_eurlex_summarization", "Contributors": "['Raghul Raj Manogeran']", "Source": ["eurlex"], "URL": ["https://huggingface.co/datasets/eurlex"], "Categories": ["Title Generation"], "Reasoning": [], "Definition": ["In this task, you are provided with an article about the legal acts. Your task is to generate a headline for that article."], "Positive Examples": [{"input": "Articles 52 to 58 of the Treaty shall apply to the French overseas departments under the conditions laid down in this Decision.At the time when the directives implementing the General Programme for the Abolition of Restrictions on Freedom of Establishment are adopted, the Council may as an exception and to the extent necessary issue special directives on the establishment of persons and companies or firms in the French overseas departments. Without prejudice to the implementation of the measures adopted pursuant to the Treaty and to the Implementing Convention of 25 March 1957 and of those to be adopted pursuant to Article 1, the right of establishment in the French overseas departments shall be progressively extended to the companies or firms and nationals of Member States other than France, so that all discrimination may disappear not later than three years after the application of this Decision.The Council, acting by a qualified majority on a proposal from the Commission, shall issue the necessary directives for the implementation of that progressive extension.However, the nationals and companies or firms of a Member State shall only be able to benefit, in respect of a given activity, in a French overseas department from the provisions of the first paragraph to the extent to which the State of which they are nationals grants in respect of the same activity advantages of the same kind to French nationals and companies or firms. The provisions of Article 106 of the Treaty, in so far as they are not affected by the Council Decision of 11 May 1960 on the application to Algeria and to the French overseas departments of the provisions of the Treaty concerning capital movements, shall apply to the French overseas departments. This Decision shall be applied by the Member States on the same date as the Council Decision on the association of the overseas countries and territories with the European Economic Community.That date shall be published in the Official Journal of the European Communities.", "output": "Council Decision on the application to the French overseas departments of certain provisions of the Treaty relating to the right of establishment and to payments", "explanation": "The article discusses about the conditions laid for the French overseas department. This can be observed in multiple sentences of this article."}, {"input": "The Rules of the Transport Committee shall be amended as follows:    A. The following sentence shall be added to the first paragraph of Article 4:'Save for the cases specified in the two following paragraphs, Committee members and their alternates shall remain in office until replaced.'B. The following article shall be added after Article 5:'Article 5aAfter expiry of the term of office of the Chairman and Vice-Chairman, the chair shall be taken, until the election provided for in Article 5, by the oldest of the members referred to in the first paragraph of that Article.", "output": "Council Decision amending the Rules of the Transport Committee", "explanation": "The first sentence summarizes what this article is about and the rules are laid out after that. These discuss the rules of the transport committee."}, {"input": "Member States shall not authorise the use, for the protection of foodstuffs intended for human consumption (hereinafter called 'foodstuffs') against deterioration caused by micro-organisms, of any preservatives other than those listed in the Annex to this Directive. 1. Member States shall take all measures necessary to ensure that the preservatives for whose use the 1 OJ No 106, 12.7.1963, p. 1923/63.  2 OJ No 161, 27.1.1964, p. 169/64.   Annex lays down certain conditions are used solely in accordance with those conditions.2. Save as otherwise provided in paragraph 1, this Directive shall not affect provisions of national laws specifying the foodstuffs to which the preservatives listed in the Annex may be added and the conditions governing the addition of such preservatives ; however, such provisions must not have the effect of totally excluding the use in foodstuffs of any of the preservatives listed in the Annex. Member States shall authorise the smoking of certain foodstuffs only in smoke produced from wood or woody plants in the natural state, excluding wood or plants which have been impregnated, coloured, gummed, painted or treated in a similar manner, and provided that such smoking does not create any risk to human health. 1. Where the use in foodstuffs of one of the preservatives listed in the Annex, or the level of one or more of the components referred to in Article 7 contained in such preservative, might endanger human health, a Member State may, for a maximum period of one year, suspend the authorisation to use that preservative or reduce the maximum authorised level of one or more of the components in question. It shall inform the other Member States and the Commission thereof within one month.2. The Council, acting unanimously on a proposal from the Commission, shall decide without delay whether the list given in the Annex should be amended and, if so, adopt by directive the necessary amendments. The Council, acting by a qualified majority on a proposal from the Commission, may also, if necessary, extend for a maximum of one year the period set in the first sentence of paragraph 1. By way of derogation from Article 1, Member States may:    (a) for a period of three years following notification of this Directive, maintain in force the provisions of their national laws relating to the use in foodstuffs of formic acid and its salts, boric acid and its salts, organo-borated compounds and hexamethylene-tetramine;(b) until 31 December 1965 maintain in force the provisions of their national laws relating to the surface treatment of citrus fruit with diphenyl, orthophenylphenol and sodium orthophenylphenate. This Directive shall not affect the provisions of national laws concerning:    (a) products used as foodstuffs but which may also have preservative properties, for example vinegar, sodium chloride, ethanol, edible oils, and sugars in particular;(b) nisin;(c) products used for coating foodstuffs;(d) products used to protect plants and plant products against harmful organisms;(e) anti-microbial products used for the treatment of drinking water;(f) antioxidants. Member States shall take all measures necessary to ensure that the preservatives listed in the Annex and intended for use in foodstuffs satisfy:    (a) the following general criteria of purity:      - they must contain not more than 3 mg/kg of arsenic and not more than 10 mg/kg of lead;- they must contain not more than 50 mg/kg of copper and zinc taken together, of which the zinc content must not be higher than 25 mg/kg, nor must they contain any measurable trace of toxicologically dangerous elements, in particular other heavy metals, always subject however to any exceptions implicit in the specific criteria referred to in subparagraph (b);(b) the specific criteria of purity laid down where appropriate and in accordance with Article 8 (1). 1. The Council shall, acting unanimously on a proposal from the Commission, lay down by directive the specific criteria of purity referred to in Article 7 (b).2. After consulting the Member States, the Commission shall establish by directive the methods of analysis needed to verify that the general and specific criteria referred to in Article 7 are satisfied. 1. The Member States shall take all measures necessary to ensure that the preservatives listed in the Annex and intended for use in foodstuffs are placed on the market only if their packagings or containers bear the following information:    (a) the name and address of the manufacturer, or of a seller responsible within the meaning of the laws of the Member State in which he is resident ; a person importing a product from a third country shall be treated as the manufacturer;(b) the number and name of the preservative as they are given in the Annex;(c) the words 'for foodstuffs (restricted use)';(d) in the case of a mixture composed of preservatives and other products, the percentage of the preservative and the name of the mixture.2. If the information required under paragraph 1 appears on the packagings or containers, and if the information required under paragraphs (b) and (c) is given in two of the official languages of the Community, one of Germanic and the other of Latin origin, Member States shall not prohibit the introduction into their territory and the placing on the market of preservatives listed in the Annex solely on the grounds that they consider the labelling inadequate. 01. This Directive shall also apply to preservatives intended for use in foodstuffs and to foodstuffs imported into the Community.2. This Directive shall not apply to preservatives and foodstuffs intended for exportation from the Community. 11. Member States shall, within a period of one year following notification of this Directive, amend their laws in accordance with the above provisions and shall forthwith inform the Commission thereof. The laws thus amended shall apply to preservatives and foodstuffs placed on the market in Member States not later than two years after that notification.2. Where Article 5 (a) is applicable the date of expiry of the period set in that Article shall be substituted for the date of notification referred to in paragraph 1. 2This Directive shall also apply in the French overseas departments. 3This Directive is addressed to the Member States.", "output": "Council Directive on the approximation of the laws of the Member States concerning the preservatives authorized for use in foodstuffs intended for human consumption", "explanation": "The first sentence summarizes what this article is about followed by rules are laid out for the same. The discussion is about authorized preservatives used in foodstuffs which are consumed by humans."}, {"input": "1. Member States, acting in accordance with the provisions hereinafter laid down, shall adopt the following transitional measures in respect of establishment or provision of services in their territories by natural persons or companies or firms covered by Title I of the General Programmes wishing to engage in activities in wholesale trade or as intermediaries in commerce, industry and small craft industries.2. The activities in question are those covered by the Council Directive of 25 February 1964 concerning the attainment of freedom of establishment and freedom to provide services in respect of activities in wholesale trade and by the Council Directive of 25 February 1964 concerning the attainment of freedom of establishment and freedom to provide services in respect of activities of intermediaries in commerce, industry and small craft industries. Where, in a Member State, the taking up or pursuit of any activity referred to in Article 1 (2) is dependent on the possession of general commercial or professional knowledge, that Member State shall accept as sufficient evidence of such knowledge the fact that the activity in question has been pursued in another Member State for a period of three consecutive years either in an independent capacity or in a managerial capacity, on condition that such activity shall not have ceased more than two years before the date when the application provided for in Article 4 (2) is made. 1. Where, in a Member State, the taking up or pursuit of any activity referred to in Article 1 (2) is not subject to the possession of general, commercial, or professional knowledge, and where that State faces serious and damaging consequences as a result of the application of the Council Directive referred to in Article 1 (2), that Member State may request from the Commission authorisation, for a limited period and in respect of one or more specified activities, to require from nationals of other Member States who wish to pursue those activities in its territory proof that they possess the qualifications required for the pursuit of such activities, either in an independent capacity or in a managerial capacity, in the country whence they come.Use shall not be made of this power in respect of a person who comes from a country which does not make the taking up of the activity in question subject to proof of particular knowledge, or in respect of a person who has lived in the host country for at least five years.2. On receipt of a request from the Member State concerned stating the reasons on which it is based, the Commission shall forthwith specify the conditions on which the authorisation provided for in paragraph 1 of this Article will be granted and lay down detailed rules concerning its implementation. 1. A person shall be regarded as having pursued an activity in a managerial capacity within the meaning of Articles 2 and 3 if he has pursued such activity in an industrial or commercial undertaking in the field in question:    (a) as manager of an undertaking or manager of a branch of an undertaking ; or(b) as deputy to the proprietor or to the manager of an undertaking, where such post involves responsibility equivalent to that of the proprietor or manager represented.2. Proof that the conditions laid down in Article 2 or in Article 3 (1) are satisfied shall be established by certificates issued by the competent authority or body in the country whence the person concerned comes, which such person shall submit in support of his application for authorisation to pursue the activity or activities in question in the host country.3. Member States shall, within the time limit laid down in Article 6, designate the authorities and bodies competent to issue these certificates and shall forthwith inform the other Member States and the Commission thereof. The provisions of this Directive shall remain applicable until the entry into force of provisions relating to the co-ordination of national rules concerning the taking up and pursuit of the activities in question. Member States shall adopt the measures necessary to comply with this Directive within six months of its notification and shall forthwith inform the Commission thereof. Member States shall ensure that the texts of the main provisions of national law which they adopt in the field covered by this Directive are communicated to the Commission. This Directive is addressed to the Member States.", "output": "Council Directive laying down detailed provisions concerning transitional measures in respect of activities in wholesale trade and activities of intermediaries in commerce, industry and small craft industries", "explanation": "The summary of the passage is introduced right at the top. The discussion is about transitional measures in wholesale trading and activities of intermediaries in commerce, industry and small craft industries."}], "Negative Examples": [{"input": "Member States shall abolish, in respect of the natural persons and companies or firms covered by Title I of the General Programmes for the abolition of restrictions on freedom of establishment and freedom to provide services the restrictions referred to in Title III of those General Programmes affecting the right to take up and pursue the activities specified in Article 2 of this Directive. The provisions of this Directive shall apply:    1. to activities of self-employed persons in reinsurance and retrocession falling within Group ex 630  1 OJ No 2, 15.1.1962, p. 36/62.  2 OJ No 2, 15.1.1962, p. 32/62.  3 OJ No 33, 4.3.1963, p. 482/63.  4 OJ No 56, 4.4.1963, p. 882/64.  in Annex I to the General Programme for the abolition of restrictions on freedom of establishment;2. in the special case of natural persons, companies or firms referred to in Article 1 which deal both in direct insurance and in reinsurance and retrocession, to that part of their activities which is concerned with reinsurance and retrocession. Article 1 shall apply in particular to restrictions arising out of the following provisions:    (a) with regard to freedom of establishment:  - in the Federal Republic of Germany      (1) Versicherungsaufsichtsgesetz of 6 June 1931, last sentence of Article 106 (2), and Article 111 (2), whereby the Federal Minister of Economic Affairs is given discretionary powers to impose on foreign nationals conditions for taking up activities in insurance and to prohibit such nationals from pursuing such activities in the territory of the Federal Republic;(2) Gewerbeordnung, paragraph 12, and Law of 30 January 1937, Article 292, whereby foreign companies and firms are required to obtain prior authorisation;- in the Kingdom of BelgiumArr\u00eat\u00e9 royal No 62 of 16 November 1939 and Arr\u00eat\u00e9 minist\u00e9riel of 17 December 1945, which require the possession of a carte professionelle;- in the French Republic      (1) D\u00e9cret-loi of 12 November 1938 and D\u00e9cret of 2 February 1939, both as amended by the Law of 8 October 1940, which require the possession of a carte d'identit\u00e9 de commer\u00e7ant;(2) Second paragraph of Article 2 of the Law of 15 February 1917, as amended and supplemented by D\u00e9cret-loi of 30 October 1935, which requires that special authorisation be obtained;- in the Grand Duchy of LuxembourgLaw of 2 June 1962, Articles 19 and 21 (M\u00e9morial A No 31 of 19 June 1962).(b) with regard to freedom to provide services:  - in the French RepublicLaw of 15 February 1917, as amended by D\u00e9cret-loi of 30 October 1935, namely:      (1) The second paragraph of Article 1, which empowers the Minister of Finance to draw up a list of specified undertakings, or of undertakings of a specified country, with which no contract for reinsurance or retrocession of any risk in respect of any person, property or liability in France may be concluded;(2) the last paragraph of Article 1, which prohibits the acceptance of reinsurance or of retrocession risks insured by the undertakings referred to in (b) (1) above;(3) the first paragraph of Article 2, which requires that the name of the person referred to in that Article must be submitted to the Minister of Finance for approval;- in the Republic of ItalyThe second paragraph of Article 73 of the consolidated text approved by Decreto No 449 of 13 February 1959, which empowers the Minister of Industry and Commerce to prohibit the transfer of reinsurance or retrocession risks to specified foreign undertakings which have not established legal representation in Italian territory. Member States shall adopt the measures necessary to comply with this Directive within six months of its notification and shall forthwith inform the Commission thereof. This Directive is addressed to the Member States.", "output": "Council Directive on activities of self-employed persons in reinsurance and retrocession falling within certains group", "explanation": "Though the article does talk about the activities of self-employed persons in reinsurance and retrocession, it is only a small portion in the whole article. Summary would be something generic on the lines of Council Directive on the abolition of restrictions on freedom of establishment and freedom to provide services in respect of reinsurance and retrocession"}, {"input": "The specific criteria of purity referred to in Article 7 (b) of the Directive of 5 November 1963 are given in the Annex to this Directive. Member States shall so amend their laws in accordance with the provisions of Article 1 that by 1 June 1966 the new measures apply to preservatives placed on the market. This Directive is addressed to the Member States.", "output": "Addressing the member states", "explanation": "The information about the directive is more important than on whom it is being addressed to. Hence the suitable title would be Council Directive laying down new measures for preservatives."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Law"], "Instance": {"id": "task743-3f50de0342bd468f8e078d051fa06266", "input": "This Regulation lays down rules for fixing and granting refunds on the products listed in Article 1 of Regulation (EEC) No 804/68 exported in the state referred to therein. The following shall be taken into account when refunds are being fixed:    (a) the existing situation and the future trend with regard to:      - prices and availabilities of milk and milk products on the Community market;- prices for milk and milk products in international trade;  1OJ No L 148, 28.6.1968, p. 13.(b) marketing costs and the most favourable transport charges from Community markets to ports and other points of export in the Community, as well as costs incurred in placing the goods on the market of the country of destination;(c) the aims of the common organisation of the market in milk and milk products, which are to ensure equilibrium and the natural development of prices and trade on this market;(d) the need to avoid disturbances on the Community market;(e) the economic aspect of the proposed exports. 1. When prices within the Community are being determined the ruling prices which are the most favourable from the exportation point of view shall be taken into account.2. When prices in international trade are being determined particular account shall be taken of:    (a) prices ruling on third country markets;(b) the most favourable prices in third countries of destination for third country imports;(c) producer prices recorded in exporting third countries, account being taken, where appropriate, of subsidies granted by those countries ; and(d) free-at-Community-frontier offer prices. Where the world market situation or the specific requirements of certain markets make this necessary, the refund for the Community may be varied according to the destination of the products listed in Article 1 of Regulation (EEC) No 804/68. 1. The list of products on which an export refund is granted and the amount of such refund shall be fixed at least once every four weeks.The amount of the refund may, however, remain at the same level for more than four weeks.2. Without prejudice to the provisions of paragraph 3, the amount of the export refund on the products listed in Article 1 of Regulation (EEC) No 804/68 shall be that applicable on the day of exportation.3. The amount of the refund may be fixed in advance.In that event, if the party concerned so requests when applying for the licence, the refund applicable on the day on which the application for a licence is lodged shall be applied to exports effected during the period of validity of the licence.The refund fixed in advance shall however be adjusted:    (a) on the basis of the threshold price in force at the time of exportation for the pilot product of the group to which the product in question belongs, and(b) on the basis of the aid applicable at the time of exportation for products entitled to aid and for those in which such products are incorporated.The provisions of the preceding subparagraphs may be applied in whole or in part to each of the products listed in Article 1 of Regulation (EEC) No 804/68.The pilot products and product groups referred to in the third subparagraph are those set out in Annex I to Regulation (EEC) No 823/68 1. 1. The refund shall be paid upon proof:    - that the products have been exported from the Community, and- that the products are of Community origin, except where the provisions of Article 7 apply.2. Where Article 4 applies, the refund shall be paid under the conditions laid down in paragraph 1, provided it is proved that the product has reached the destination for which the refund was fixed.Exceptions may be made to this rule in accordance with the procedure referred to in paragraph 3 of this Article, provided conditions are laid down which offer equivalent guarantees.3. Additional provisions may be adopted in accordance with the procedure laid down in Article 30 of Regulation (EEC) No 804/68. 1. No export refund shall be granted on products listed in Article 1 of Regulation (EEC) No 804/68 which are imported from third countries and re-exported to third countries, unless the exporter proves:    - that the product to be exported and the product previously imported are one and the same, and- that the levy was collected on importation.2. In such cases the refund on each product shall be equal to the levy collected on importation where  1OJ No L 151, 30.6.1968, p. 3.this levy is equal to or lower than the refund applicable on the day of exportation ; the refund shall be equal to the refund applicable on the day of exportation where the levy collected on importation is higher than this refund. This Regulation shall enter into force on 4 July 1968.It shall apply from 29 July 1968.This Regulation shall be binding in its entirety and directly applicable in all Member States.", "output": ["Regulation laying down general rules for granting export refunds on milk and milk products and criteria for fixing the amount of such refunds"]}, "Instance License": ["\u00a9 European Union, 1998-2021 (https://huggingface.co/datasets/eurlex#licensing-information)"], "prediction": "The Commission shall take into account the following when determining the amount of the refund: (a) the price of milk and milk products on the Community market; (b) the price of the products in third countries of destination for third country imports; (c) the price of the products in the pilot product of the group to which the product in question belongs; (d) the economic aspect of the proposed exports; (e) the need to avoid disturbances on the Community market;"}
+{"id": "task743-facdc03f3c34457cbf862e1bc8aac31a", "Task": "task743_eurlex_summarization", "Contributors": "['Raghul Raj Manogeran']", "Source": ["eurlex"], "URL": ["https://huggingface.co/datasets/eurlex"], "Categories": ["Title Generation"], "Reasoning": [], "Definition": ["In this task, you are provided with an article about the legal acts. Your task is to generate a headline for that article."], "Positive Examples": [{"input": "Articles 52 to 58 of the Treaty shall apply to the French overseas departments under the conditions laid down in this Decision.At the time when the directives implementing the General Programme for the Abolition of Restrictions on Freedom of Establishment are adopted, the Council may as an exception and to the extent necessary issue special directives on the establishment of persons and companies or firms in the French overseas departments. Without prejudice to the implementation of the measures adopted pursuant to the Treaty and to the Implementing Convention of 25 March 1957 and of those to be adopted pursuant to Article 1, the right of establishment in the French overseas departments shall be progressively extended to the companies or firms and nationals of Member States other than France, so that all discrimination may disappear not later than three years after the application of this Decision.The Council, acting by a qualified majority on a proposal from the Commission, shall issue the necessary directives for the implementation of that progressive extension.However, the nationals and companies or firms of a Member State shall only be able to benefit, in respect of a given activity, in a French overseas department from the provisions of the first paragraph to the extent to which the State of which they are nationals grants in respect of the same activity advantages of the same kind to French nationals and companies or firms. The provisions of Article 106 of the Treaty, in so far as they are not affected by the Council Decision of 11 May 1960 on the application to Algeria and to the French overseas departments of the provisions of the Treaty concerning capital movements, shall apply to the French overseas departments. This Decision shall be applied by the Member States on the same date as the Council Decision on the association of the overseas countries and territories with the European Economic Community.That date shall be published in the Official Journal of the European Communities.", "output": "Council Decision on the application to the French overseas departments of certain provisions of the Treaty relating to the right of establishment and to payments", "explanation": "The article discusses about the conditions laid for the French overseas department. This can be observed in multiple sentences of this article."}, {"input": "The Rules of the Transport Committee shall be amended as follows:    A. The following sentence shall be added to the first paragraph of Article 4:'Save for the cases specified in the two following paragraphs, Committee members and their alternates shall remain in office until replaced.'B. The following article shall be added after Article 5:'Article 5aAfter expiry of the term of office of the Chairman and Vice-Chairman, the chair shall be taken, until the election provided for in Article 5, by the oldest of the members referred to in the first paragraph of that Article.", "output": "Council Decision amending the Rules of the Transport Committee", "explanation": "The first sentence summarizes what this article is about and the rules are laid out after that. These discuss the rules of the transport committee."}, {"input": "Member States shall not authorise the use, for the protection of foodstuffs intended for human consumption (hereinafter called 'foodstuffs') against deterioration caused by micro-organisms, of any preservatives other than those listed in the Annex to this Directive. 1. Member States shall take all measures necessary to ensure that the preservatives for whose use the 1 OJ No 106, 12.7.1963, p. 1923/63.  2 OJ No 161, 27.1.1964, p. 169/64.   Annex lays down certain conditions are used solely in accordance with those conditions.2. Save as otherwise provided in paragraph 1, this Directive shall not affect provisions of national laws specifying the foodstuffs to which the preservatives listed in the Annex may be added and the conditions governing the addition of such preservatives ; however, such provisions must not have the effect of totally excluding the use in foodstuffs of any of the preservatives listed in the Annex. Member States shall authorise the smoking of certain foodstuffs only in smoke produced from wood or woody plants in the natural state, excluding wood or plants which have been impregnated, coloured, gummed, painted or treated in a similar manner, and provided that such smoking does not create any risk to human health. 1. Where the use in foodstuffs of one of the preservatives listed in the Annex, or the level of one or more of the components referred to in Article 7 contained in such preservative, might endanger human health, a Member State may, for a maximum period of one year, suspend the authorisation to use that preservative or reduce the maximum authorised level of one or more of the components in question. It shall inform the other Member States and the Commission thereof within one month.2. The Council, acting unanimously on a proposal from the Commission, shall decide without delay whether the list given in the Annex should be amended and, if so, adopt by directive the necessary amendments. The Council, acting by a qualified majority on a proposal from the Commission, may also, if necessary, extend for a maximum of one year the period set in the first sentence of paragraph 1. By way of derogation from Article 1, Member States may:    (a) for a period of three years following notification of this Directive, maintain in force the provisions of their national laws relating to the use in foodstuffs of formic acid and its salts, boric acid and its salts, organo-borated compounds and hexamethylene-tetramine;(b) until 31 December 1965 maintain in force the provisions of their national laws relating to the surface treatment of citrus fruit with diphenyl, orthophenylphenol and sodium orthophenylphenate. This Directive shall not affect the provisions of national laws concerning:    (a) products used as foodstuffs but which may also have preservative properties, for example vinegar, sodium chloride, ethanol, edible oils, and sugars in particular;(b) nisin;(c) products used for coating foodstuffs;(d) products used to protect plants and plant products against harmful organisms;(e) anti-microbial products used for the treatment of drinking water;(f) antioxidants. Member States shall take all measures necessary to ensure that the preservatives listed in the Annex and intended for use in foodstuffs satisfy:    (a) the following general criteria of purity:      - they must contain not more than 3 mg/kg of arsenic and not more than 10 mg/kg of lead;- they must contain not more than 50 mg/kg of copper and zinc taken together, of which the zinc content must not be higher than 25 mg/kg, nor must they contain any measurable trace of toxicologically dangerous elements, in particular other heavy metals, always subject however to any exceptions implicit in the specific criteria referred to in subparagraph (b);(b) the specific criteria of purity laid down where appropriate and in accordance with Article 8 (1). 1. The Council shall, acting unanimously on a proposal from the Commission, lay down by directive the specific criteria of purity referred to in Article 7 (b).2. After consulting the Member States, the Commission shall establish by directive the methods of analysis needed to verify that the general and specific criteria referred to in Article 7 are satisfied. 1. The Member States shall take all measures necessary to ensure that the preservatives listed in the Annex and intended for use in foodstuffs are placed on the market only if their packagings or containers bear the following information:    (a) the name and address of the manufacturer, or of a seller responsible within the meaning of the laws of the Member State in which he is resident ; a person importing a product from a third country shall be treated as the manufacturer;(b) the number and name of the preservative as they are given in the Annex;(c) the words 'for foodstuffs (restricted use)';(d) in the case of a mixture composed of preservatives and other products, the percentage of the preservative and the name of the mixture.2. If the information required under paragraph 1 appears on the packagings or containers, and if the information required under paragraphs (b) and (c) is given in two of the official languages of the Community, one of Germanic and the other of Latin origin, Member States shall not prohibit the introduction into their territory and the placing on the market of preservatives listed in the Annex solely on the grounds that they consider the labelling inadequate. 01. This Directive shall also apply to preservatives intended for use in foodstuffs and to foodstuffs imported into the Community.2. This Directive shall not apply to preservatives and foodstuffs intended for exportation from the Community. 11. Member States shall, within a period of one year following notification of this Directive, amend their laws in accordance with the above provisions and shall forthwith inform the Commission thereof. The laws thus amended shall apply to preservatives and foodstuffs placed on the market in Member States not later than two years after that notification.2. Where Article 5 (a) is applicable the date of expiry of the period set in that Article shall be substituted for the date of notification referred to in paragraph 1. 2This Directive shall also apply in the French overseas departments. 3This Directive is addressed to the Member States.", "output": "Council Directive on the approximation of the laws of the Member States concerning the preservatives authorized for use in foodstuffs intended for human consumption", "explanation": "The first sentence summarizes what this article is about followed by rules are laid out for the same. The discussion is about authorized preservatives used in foodstuffs which are consumed by humans."}, {"input": "1. Member States, acting in accordance with the provisions hereinafter laid down, shall adopt the following transitional measures in respect of establishment or provision of services in their territories by natural persons or companies or firms covered by Title I of the General Programmes wishing to engage in activities in wholesale trade or as intermediaries in commerce, industry and small craft industries.2. The activities in question are those covered by the Council Directive of 25 February 1964 concerning the attainment of freedom of establishment and freedom to provide services in respect of activities in wholesale trade and by the Council Directive of 25 February 1964 concerning the attainment of freedom of establishment and freedom to provide services in respect of activities of intermediaries in commerce, industry and small craft industries. Where, in a Member State, the taking up or pursuit of any activity referred to in Article 1 (2) is dependent on the possession of general commercial or professional knowledge, that Member State shall accept as sufficient evidence of such knowledge the fact that the activity in question has been pursued in another Member State for a period of three consecutive years either in an independent capacity or in a managerial capacity, on condition that such activity shall not have ceased more than two years before the date when the application provided for in Article 4 (2) is made. 1. Where, in a Member State, the taking up or pursuit of any activity referred to in Article 1 (2) is not subject to the possession of general, commercial, or professional knowledge, and where that State faces serious and damaging consequences as a result of the application of the Council Directive referred to in Article 1 (2), that Member State may request from the Commission authorisation, for a limited period and in respect of one or more specified activities, to require from nationals of other Member States who wish to pursue those activities in its territory proof that they possess the qualifications required for the pursuit of such activities, either in an independent capacity or in a managerial capacity, in the country whence they come.Use shall not be made of this power in respect of a person who comes from a country which does not make the taking up of the activity in question subject to proof of particular knowledge, or in respect of a person who has lived in the host country for at least five years.2. On receipt of a request from the Member State concerned stating the reasons on which it is based, the Commission shall forthwith specify the conditions on which the authorisation provided for in paragraph 1 of this Article will be granted and lay down detailed rules concerning its implementation. 1. A person shall be regarded as having pursued an activity in a managerial capacity within the meaning of Articles 2 and 3 if he has pursued such activity in an industrial or commercial undertaking in the field in question:    (a) as manager of an undertaking or manager of a branch of an undertaking ; or(b) as deputy to the proprietor or to the manager of an undertaking, where such post involves responsibility equivalent to that of the proprietor or manager represented.2. Proof that the conditions laid down in Article 2 or in Article 3 (1) are satisfied shall be established by certificates issued by the competent authority or body in the country whence the person concerned comes, which such person shall submit in support of his application for authorisation to pursue the activity or activities in question in the host country.3. Member States shall, within the time limit laid down in Article 6, designate the authorities and bodies competent to issue these certificates and shall forthwith inform the other Member States and the Commission thereof. The provisions of this Directive shall remain applicable until the entry into force of provisions relating to the co-ordination of national rules concerning the taking up and pursuit of the activities in question. Member States shall adopt the measures necessary to comply with this Directive within six months of its notification and shall forthwith inform the Commission thereof. Member States shall ensure that the texts of the main provisions of national law which they adopt in the field covered by this Directive are communicated to the Commission. This Directive is addressed to the Member States.", "output": "Council Directive laying down detailed provisions concerning transitional measures in respect of activities in wholesale trade and activities of intermediaries in commerce, industry and small craft industries", "explanation": "The summary of the passage is introduced right at the top. The discussion is about transitional measures in wholesale trading and activities of intermediaries in commerce, industry and small craft industries."}], "Negative Examples": [{"input": "Member States shall abolish, in respect of the natural persons and companies or firms covered by Title I of the General Programmes for the abolition of restrictions on freedom of establishment and freedom to provide services the restrictions referred to in Title III of those General Programmes affecting the right to take up and pursue the activities specified in Article 2 of this Directive. The provisions of this Directive shall apply:    1. to activities of self-employed persons in reinsurance and retrocession falling within Group ex 630  1 OJ No 2, 15.1.1962, p. 36/62.  2 OJ No 2, 15.1.1962, p. 32/62.  3 OJ No 33, 4.3.1963, p. 482/63.  4 OJ No 56, 4.4.1963, p. 882/64.  in Annex I to the General Programme for the abolition of restrictions on freedom of establishment;2. in the special case of natural persons, companies or firms referred to in Article 1 which deal both in direct insurance and in reinsurance and retrocession, to that part of their activities which is concerned with reinsurance and retrocession. Article 1 shall apply in particular to restrictions arising out of the following provisions:    (a) with regard to freedom of establishment:  - in the Federal Republic of Germany      (1) Versicherungsaufsichtsgesetz of 6 June 1931, last sentence of Article 106 (2), and Article 111 (2), whereby the Federal Minister of Economic Affairs is given discretionary powers to impose on foreign nationals conditions for taking up activities in insurance and to prohibit such nationals from pursuing such activities in the territory of the Federal Republic;(2) Gewerbeordnung, paragraph 12, and Law of 30 January 1937, Article 292, whereby foreign companies and firms are required to obtain prior authorisation;- in the Kingdom of BelgiumArr\u00eat\u00e9 royal No 62 of 16 November 1939 and Arr\u00eat\u00e9 minist\u00e9riel of 17 December 1945, which require the possession of a carte professionelle;- in the French Republic      (1) D\u00e9cret-loi of 12 November 1938 and D\u00e9cret of 2 February 1939, both as amended by the Law of 8 October 1940, which require the possession of a carte d'identit\u00e9 de commer\u00e7ant;(2) Second paragraph of Article 2 of the Law of 15 February 1917, as amended and supplemented by D\u00e9cret-loi of 30 October 1935, which requires that special authorisation be obtained;- in the Grand Duchy of LuxembourgLaw of 2 June 1962, Articles 19 and 21 (M\u00e9morial A No 31 of 19 June 1962).(b) with regard to freedom to provide services:  - in the French RepublicLaw of 15 February 1917, as amended by D\u00e9cret-loi of 30 October 1935, namely:      (1) The second paragraph of Article 1, which empowers the Minister of Finance to draw up a list of specified undertakings, or of undertakings of a specified country, with which no contract for reinsurance or retrocession of any risk in respect of any person, property or liability in France may be concluded;(2) the last paragraph of Article 1, which prohibits the acceptance of reinsurance or of retrocession risks insured by the undertakings referred to in (b) (1) above;(3) the first paragraph of Article 2, which requires that the name of the person referred to in that Article must be submitted to the Minister of Finance for approval;- in the Republic of ItalyThe second paragraph of Article 73 of the consolidated text approved by Decreto No 449 of 13 February 1959, which empowers the Minister of Industry and Commerce to prohibit the transfer of reinsurance or retrocession risks to specified foreign undertakings which have not established legal representation in Italian territory. Member States shall adopt the measures necessary to comply with this Directive within six months of its notification and shall forthwith inform the Commission thereof. This Directive is addressed to the Member States.", "output": "Council Directive on activities of self-employed persons in reinsurance and retrocession falling within certains group", "explanation": "Though the article does talk about the activities of self-employed persons in reinsurance and retrocession, it is only a small portion in the whole article. Summary would be something generic on the lines of Council Directive on the abolition of restrictions on freedom of establishment and freedom to provide services in respect of reinsurance and retrocession"}, {"input": "The specific criteria of purity referred to in Article 7 (b) of the Directive of 5 November 1963 are given in the Annex to this Directive. Member States shall so amend their laws in accordance with the provisions of Article 1 that by 1 June 1966 the new measures apply to preservatives placed on the market. This Directive is addressed to the Member States.", "output": "Addressing the member states", "explanation": "The information about the directive is more important than on whom it is being addressed to. Hence the suitable title would be Council Directive laying down new measures for preservatives."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Law"], "Instance": {"id": "task743-facdc03f3c34457cbf862e1bc8aac31a", "input": "1. Member States, acting in accordance with the provisions hereinafter laid down, shall adopt the following transitional measures in respect of establishment or provision of services in their territories by natural persons or companies or firms covered by Title I of the General Programmes (hereinafter called 'beneficiaries') wishing to engage in the activities of self-employed persons referred to in paragraph 2.2. The activities in question are those covered by the Council Directive of 15 October 1968 concerning the attainment of freedom of establishment and freedom to provide services in respect of activities of self-employed persons in the personal services sector (ISIC ex Major Group 85) ; 1 : Restaurants, cafes, taverns and other drinking and eating places (ISIC Group 852) ; 2 : Hotels, rooming houses, camps and other lodging places (ISIC Group 853). Where, according to the laws of a Member State, certain activities fall not within the personal services sector but rather within the food manufacturing and beverage industries, the appropriate Directive laying down detailed provisions concerning transitional measures in the field in question shall apply to those activities in that Member State. Member States in which the taking up or pursuit of any activity referred to in Article 1 (2) is subject to possession of certain qualifications shall ensure that any beneficiary who applies therefor be provided, before he establishes himself or before he begins to pursue any activity on a temporary basis, with information as to the rules governing the occupation which he proposes to pursue. 1. Where, in a Member State, the taking up or pursuit of any activity referred to in Article 1 (2) is dependent on the possession of general, commercial or professional knowledge and ability, that Member State shall accept as sufficient evidence of such knowledge and ability the fact that the activity in question has been pursued in another Member State for any of the following periods:    (a) three consecutive years either in an independent capacity or in a managerial capacity ; or(b) two consecutive years either in an independent capacity or in a managerial capacity, where the beneficiary can prove that for the occupation in question he has received previous training, attested by a certificate recognised by the State, or regarded by the competent professional or trade body as fully satisfying its requirements ; or(c) two consecutive years in an independent capacity or in a managerial capacity, where the beneficiary can prove that he has pursued the occupation in question for at least three years in a non-independent capacity ; or  1OJ No L 260, 22.10.1968, p. 9.(d) three consecutive years in a non-independent capacity, where the beneficiary can prove that for the occupation in question he has received previous training, attested by a certificate recognised by the State, or regarded by the competent professional or trade body as fully satisfying its requirements.The host Member State may require of nationals of other Member States, in so far as it so requires of its own nationals, that the activity in question should have been pursued, and vocational training received, in the branch of trade in the host country in which the beneficiary wishes to establish himself.2. In the cases referred to in subparagraphs (a) and (c) of paragraph 1 pursuit of the activity shall not have ceased more than ten years before the date when the application provided for in Article 6 (2) is made. However, where a shorter period is laid down in a Member State for its nationals, that period may also be applied in respect of beneficiaries. 1. Where, in a Member State, the taking up or pursuit of any activity referred to in Article 1 (2) is not subject to the possession of general, commercial or professional knowledge or ability, that State may, if serious difficulties result from the application of the Council Directive referred to in Article 1 (2), request from the Commission authorisation, for a limited period and in respect of one or more specified activities, to require from nationals of other Member States who wish to pursue those activities in its territory proof that they possess the qualifications required for the pursuit of such activities, either in an independent capacity or in a managerial capacity, in the country whence they come.Use shall not be made of this power in respect of a person who comes from a country which does not make the taking up of the activity in question subject to proof of particular knowledge, or in respect of a person who has lived in the host country for at least five years.2. On receipt of a request from the Member State concerned stating the reasons on which it is based, the Commission shall forthwith specify the conditions on which the authorisation provided for in paragraph 1 of this Article will be granted and lay down detailed rules concerning its implementation. 1. A person shall be regarded as having pursued an activity in a managerial capacity within the meaning of Articles 4 and 5 if he has pursued such activity in an industrial or commercial undertaking in the field in question:    (a) as manager of an undertaking or manager of a branch of an undertaking ; or(b) as deputy to the proprietor or to the manager of an undertaking, where such post involves responsibility equivalent to that of the proprietor or manager represented ; or(c) in a managerial post with duties of a type normally pertaining to the occupation in question and with responsibility for one or more departments of the undertaking.2. Proof that the conditions laid down in Article 4 (1) or in Article 5 (1) are satisfied shall be established by certificates issued by the competent authority or body in the country whence the person concerned comes, which such person shall submit in support of his application for authorisation to pursue the activity or activities in question in the host country.3. Member States shall, within the time limit laid down in Article 8, designate the authorities and bodies competent to issue these certificates and shall forthwith inform the other Member States and the Commission thereof. The provisions of this Directive shall remain applicable until the entry into force of provisions relating to the co-ordination of national rules concerning the taking up and pursuit of the activities in question. Member States shall adopt the measures necessary to comply with this Directive within six months of its notification and shall forthwith inform the Commission thereof. Member States shall ensure that the texts of the main provisions of national law which they adopt in the field covered by this Directive are communicated to the Commission. 0This Directive is addressed to the Member States.", "output": ["Council Directive laying down detailed provisions concerning transitional measures in respect of activities of self-employed persons in the personal services sector (ISIC ex Major Group 85): 1. Restaurants, cafes, taverns and other drinking and eating places (ISIC Group 852), 2. Hotels, rooming houses, camps and other lodging places (ISIC Group 853)"]}, "Instance License": ["\u00a9 European Union, 1998-2021 (https://huggingface.co/datasets/eurlex#licensing-information)"], "prediction": "The Commission shall, in the case of a Member State, require from nationals of other Member States, in so far as it so requires of its own nationals, that the activity in question should have been pursued, and vocational training received, in the branch of trade in the host country in which the beneficiary wishes to establish himself ; or 1OJ No L 260, 22.10.1968, p. 9"}
+{"id": "task743-6bef5f3145e043e3af084358a6d65c20", "Task": "task743_eurlex_summarization", "Contributors": "['Raghul Raj Manogeran']", "Source": ["eurlex"], "URL": ["https://huggingface.co/datasets/eurlex"], "Categories": ["Title Generation"], "Reasoning": [], "Definition": ["In this task, you are provided with an article about the legal acts. Your task is to generate a headline for that article."], "Positive Examples": [{"input": "Articles 52 to 58 of the Treaty shall apply to the French overseas departments under the conditions laid down in this Decision.At the time when the directives implementing the General Programme for the Abolition of Restrictions on Freedom of Establishment are adopted, the Council may as an exception and to the extent necessary issue special directives on the establishment of persons and companies or firms in the French overseas departments. Without prejudice to the implementation of the measures adopted pursuant to the Treaty and to the Implementing Convention of 25 March 1957 and of those to be adopted pursuant to Article 1, the right of establishment in the French overseas departments shall be progressively extended to the companies or firms and nationals of Member States other than France, so that all discrimination may disappear not later than three years after the application of this Decision.The Council, acting by a qualified majority on a proposal from the Commission, shall issue the necessary directives for the implementation of that progressive extension.However, the nationals and companies or firms of a Member State shall only be able to benefit, in respect of a given activity, in a French overseas department from the provisions of the first paragraph to the extent to which the State of which they are nationals grants in respect of the same activity advantages of the same kind to French nationals and companies or firms. The provisions of Article 106 of the Treaty, in so far as they are not affected by the Council Decision of 11 May 1960 on the application to Algeria and to the French overseas departments of the provisions of the Treaty concerning capital movements, shall apply to the French overseas departments. This Decision shall be applied by the Member States on the same date as the Council Decision on the association of the overseas countries and territories with the European Economic Community.That date shall be published in the Official Journal of the European Communities.", "output": "Council Decision on the application to the French overseas departments of certain provisions of the Treaty relating to the right of establishment and to payments", "explanation": "The article discusses about the conditions laid for the French overseas department. This can be observed in multiple sentences of this article."}, {"input": "The Rules of the Transport Committee shall be amended as follows:    A. The following sentence shall be added to the first paragraph of Article 4:'Save for the cases specified in the two following paragraphs, Committee members and their alternates shall remain in office until replaced.'B. The following article shall be added after Article 5:'Article 5aAfter expiry of the term of office of the Chairman and Vice-Chairman, the chair shall be taken, until the election provided for in Article 5, by the oldest of the members referred to in the first paragraph of that Article.", "output": "Council Decision amending the Rules of the Transport Committee", "explanation": "The first sentence summarizes what this article is about and the rules are laid out after that. These discuss the rules of the transport committee."}, {"input": "Member States shall not authorise the use, for the protection of foodstuffs intended for human consumption (hereinafter called 'foodstuffs') against deterioration caused by micro-organisms, of any preservatives other than those listed in the Annex to this Directive. 1. Member States shall take all measures necessary to ensure that the preservatives for whose use the 1 OJ No 106, 12.7.1963, p. 1923/63.  2 OJ No 161, 27.1.1964, p. 169/64.   Annex lays down certain conditions are used solely in accordance with those conditions.2. Save as otherwise provided in paragraph 1, this Directive shall not affect provisions of national laws specifying the foodstuffs to which the preservatives listed in the Annex may be added and the conditions governing the addition of such preservatives ; however, such provisions must not have the effect of totally excluding the use in foodstuffs of any of the preservatives listed in the Annex. Member States shall authorise the smoking of certain foodstuffs only in smoke produced from wood or woody plants in the natural state, excluding wood or plants which have been impregnated, coloured, gummed, painted or treated in a similar manner, and provided that such smoking does not create any risk to human health. 1. Where the use in foodstuffs of one of the preservatives listed in the Annex, or the level of one or more of the components referred to in Article 7 contained in such preservative, might endanger human health, a Member State may, for a maximum period of one year, suspend the authorisation to use that preservative or reduce the maximum authorised level of one or more of the components in question. It shall inform the other Member States and the Commission thereof within one month.2. The Council, acting unanimously on a proposal from the Commission, shall decide without delay whether the list given in the Annex should be amended and, if so, adopt by directive the necessary amendments. The Council, acting by a qualified majority on a proposal from the Commission, may also, if necessary, extend for a maximum of one year the period set in the first sentence of paragraph 1. By way of derogation from Article 1, Member States may:    (a) for a period of three years following notification of this Directive, maintain in force the provisions of their national laws relating to the use in foodstuffs of formic acid and its salts, boric acid and its salts, organo-borated compounds and hexamethylene-tetramine;(b) until 31 December 1965 maintain in force the provisions of their national laws relating to the surface treatment of citrus fruit with diphenyl, orthophenylphenol and sodium orthophenylphenate. This Directive shall not affect the provisions of national laws concerning:    (a) products used as foodstuffs but which may also have preservative properties, for example vinegar, sodium chloride, ethanol, edible oils, and sugars in particular;(b) nisin;(c) products used for coating foodstuffs;(d) products used to protect plants and plant products against harmful organisms;(e) anti-microbial products used for the treatment of drinking water;(f) antioxidants. Member States shall take all measures necessary to ensure that the preservatives listed in the Annex and intended for use in foodstuffs satisfy:    (a) the following general criteria of purity:      - they must contain not more than 3 mg/kg of arsenic and not more than 10 mg/kg of lead;- they must contain not more than 50 mg/kg of copper and zinc taken together, of which the zinc content must not be higher than 25 mg/kg, nor must they contain any measurable trace of toxicologically dangerous elements, in particular other heavy metals, always subject however to any exceptions implicit in the specific criteria referred to in subparagraph (b);(b) the specific criteria of purity laid down where appropriate and in accordance with Article 8 (1). 1. The Council shall, acting unanimously on a proposal from the Commission, lay down by directive the specific criteria of purity referred to in Article 7 (b).2. After consulting the Member States, the Commission shall establish by directive the methods of analysis needed to verify that the general and specific criteria referred to in Article 7 are satisfied. 1. The Member States shall take all measures necessary to ensure that the preservatives listed in the Annex and intended for use in foodstuffs are placed on the market only if their packagings or containers bear the following information:    (a) the name and address of the manufacturer, or of a seller responsible within the meaning of the laws of the Member State in which he is resident ; a person importing a product from a third country shall be treated as the manufacturer;(b) the number and name of the preservative as they are given in the Annex;(c) the words 'for foodstuffs (restricted use)';(d) in the case of a mixture composed of preservatives and other products, the percentage of the preservative and the name of the mixture.2. If the information required under paragraph 1 appears on the packagings or containers, and if the information required under paragraphs (b) and (c) is given in two of the official languages of the Community, one of Germanic and the other of Latin origin, Member States shall not prohibit the introduction into their territory and the placing on the market of preservatives listed in the Annex solely on the grounds that they consider the labelling inadequate. 01. This Directive shall also apply to preservatives intended for use in foodstuffs and to foodstuffs imported into the Community.2. This Directive shall not apply to preservatives and foodstuffs intended for exportation from the Community. 11. Member States shall, within a period of one year following notification of this Directive, amend their laws in accordance with the above provisions and shall forthwith inform the Commission thereof. The laws thus amended shall apply to preservatives and foodstuffs placed on the market in Member States not later than two years after that notification.2. Where Article 5 (a) is applicable the date of expiry of the period set in that Article shall be substituted for the date of notification referred to in paragraph 1. 2This Directive shall also apply in the French overseas departments. 3This Directive is addressed to the Member States.", "output": "Council Directive on the approximation of the laws of the Member States concerning the preservatives authorized for use in foodstuffs intended for human consumption", "explanation": "The first sentence summarizes what this article is about followed by rules are laid out for the same. The discussion is about authorized preservatives used in foodstuffs which are consumed by humans."}, {"input": "1. Member States, acting in accordance with the provisions hereinafter laid down, shall adopt the following transitional measures in respect of establishment or provision of services in their territories by natural persons or companies or firms covered by Title I of the General Programmes wishing to engage in activities in wholesale trade or as intermediaries in commerce, industry and small craft industries.2. The activities in question are those covered by the Council Directive of 25 February 1964 concerning the attainment of freedom of establishment and freedom to provide services in respect of activities in wholesale trade and by the Council Directive of 25 February 1964 concerning the attainment of freedom of establishment and freedom to provide services in respect of activities of intermediaries in commerce, industry and small craft industries. Where, in a Member State, the taking up or pursuit of any activity referred to in Article 1 (2) is dependent on the possession of general commercial or professional knowledge, that Member State shall accept as sufficient evidence of such knowledge the fact that the activity in question has been pursued in another Member State for a period of three consecutive years either in an independent capacity or in a managerial capacity, on condition that such activity shall not have ceased more than two years before the date when the application provided for in Article 4 (2) is made. 1. Where, in a Member State, the taking up or pursuit of any activity referred to in Article 1 (2) is not subject to the possession of general, commercial, or professional knowledge, and where that State faces serious and damaging consequences as a result of the application of the Council Directive referred to in Article 1 (2), that Member State may request from the Commission authorisation, for a limited period and in respect of one or more specified activities, to require from nationals of other Member States who wish to pursue those activities in its territory proof that they possess the qualifications required for the pursuit of such activities, either in an independent capacity or in a managerial capacity, in the country whence they come.Use shall not be made of this power in respect of a person who comes from a country which does not make the taking up of the activity in question subject to proof of particular knowledge, or in respect of a person who has lived in the host country for at least five years.2. On receipt of a request from the Member State concerned stating the reasons on which it is based, the Commission shall forthwith specify the conditions on which the authorisation provided for in paragraph 1 of this Article will be granted and lay down detailed rules concerning its implementation. 1. A person shall be regarded as having pursued an activity in a managerial capacity within the meaning of Articles 2 and 3 if he has pursued such activity in an industrial or commercial undertaking in the field in question:    (a) as manager of an undertaking or manager of a branch of an undertaking ; or(b) as deputy to the proprietor or to the manager of an undertaking, where such post involves responsibility equivalent to that of the proprietor or manager represented.2. Proof that the conditions laid down in Article 2 or in Article 3 (1) are satisfied shall be established by certificates issued by the competent authority or body in the country whence the person concerned comes, which such person shall submit in support of his application for authorisation to pursue the activity or activities in question in the host country.3. Member States shall, within the time limit laid down in Article 6, designate the authorities and bodies competent to issue these certificates and shall forthwith inform the other Member States and the Commission thereof. The provisions of this Directive shall remain applicable until the entry into force of provisions relating to the co-ordination of national rules concerning the taking up and pursuit of the activities in question. Member States shall adopt the measures necessary to comply with this Directive within six months of its notification and shall forthwith inform the Commission thereof. Member States shall ensure that the texts of the main provisions of national law which they adopt in the field covered by this Directive are communicated to the Commission. This Directive is addressed to the Member States.", "output": "Council Directive laying down detailed provisions concerning transitional measures in respect of activities in wholesale trade and activities of intermediaries in commerce, industry and small craft industries", "explanation": "The summary of the passage is introduced right at the top. The discussion is about transitional measures in wholesale trading and activities of intermediaries in commerce, industry and small craft industries."}], "Negative Examples": [{"input": "Member States shall abolish, in respect of the natural persons and companies or firms covered by Title I of the General Programmes for the abolition of restrictions on freedom of establishment and freedom to provide services the restrictions referred to in Title III of those General Programmes affecting the right to take up and pursue the activities specified in Article 2 of this Directive. The provisions of this Directive shall apply:    1. to activities of self-employed persons in reinsurance and retrocession falling within Group ex 630  1 OJ No 2, 15.1.1962, p. 36/62.  2 OJ No 2, 15.1.1962, p. 32/62.  3 OJ No 33, 4.3.1963, p. 482/63.  4 OJ No 56, 4.4.1963, p. 882/64.  in Annex I to the General Programme for the abolition of restrictions on freedom of establishment;2. in the special case of natural persons, companies or firms referred to in Article 1 which deal both in direct insurance and in reinsurance and retrocession, to that part of their activities which is concerned with reinsurance and retrocession. Article 1 shall apply in particular to restrictions arising out of the following provisions:    (a) with regard to freedom of establishment:  - in the Federal Republic of Germany      (1) Versicherungsaufsichtsgesetz of 6 June 1931, last sentence of Article 106 (2), and Article 111 (2), whereby the Federal Minister of Economic Affairs is given discretionary powers to impose on foreign nationals conditions for taking up activities in insurance and to prohibit such nationals from pursuing such activities in the territory of the Federal Republic;(2) Gewerbeordnung, paragraph 12, and Law of 30 January 1937, Article 292, whereby foreign companies and firms are required to obtain prior authorisation;- in the Kingdom of BelgiumArr\u00eat\u00e9 royal No 62 of 16 November 1939 and Arr\u00eat\u00e9 minist\u00e9riel of 17 December 1945, which require the possession of a carte professionelle;- in the French Republic      (1) D\u00e9cret-loi of 12 November 1938 and D\u00e9cret of 2 February 1939, both as amended by the Law of 8 October 1940, which require the possession of a carte d'identit\u00e9 de commer\u00e7ant;(2) Second paragraph of Article 2 of the Law of 15 February 1917, as amended and supplemented by D\u00e9cret-loi of 30 October 1935, which requires that special authorisation be obtained;- in the Grand Duchy of LuxembourgLaw of 2 June 1962, Articles 19 and 21 (M\u00e9morial A No 31 of 19 June 1962).(b) with regard to freedom to provide services:  - in the French RepublicLaw of 15 February 1917, as amended by D\u00e9cret-loi of 30 October 1935, namely:      (1) The second paragraph of Article 1, which empowers the Minister of Finance to draw up a list of specified undertakings, or of undertakings of a specified country, with which no contract for reinsurance or retrocession of any risk in respect of any person, property or liability in France may be concluded;(2) the last paragraph of Article 1, which prohibits the acceptance of reinsurance or of retrocession risks insured by the undertakings referred to in (b) (1) above;(3) the first paragraph of Article 2, which requires that the name of the person referred to in that Article must be submitted to the Minister of Finance for approval;- in the Republic of ItalyThe second paragraph of Article 73 of the consolidated text approved by Decreto No 449 of 13 February 1959, which empowers the Minister of Industry and Commerce to prohibit the transfer of reinsurance or retrocession risks to specified foreign undertakings which have not established legal representation in Italian territory. Member States shall adopt the measures necessary to comply with this Directive within six months of its notification and shall forthwith inform the Commission thereof. This Directive is addressed to the Member States.", "output": "Council Directive on activities of self-employed persons in reinsurance and retrocession falling within certains group", "explanation": "Though the article does talk about the activities of self-employed persons in reinsurance and retrocession, it is only a small portion in the whole article. Summary would be something generic on the lines of Council Directive on the abolition of restrictions on freedom of establishment and freedom to provide services in respect of reinsurance and retrocession"}, {"input": "The specific criteria of purity referred to in Article 7 (b) of the Directive of 5 November 1963 are given in the Annex to this Directive. Member States shall so amend their laws in accordance with the provisions of Article 1 that by 1 June 1966 the new measures apply to preservatives placed on the market. This Directive is addressed to the Member States.", "output": "Addressing the member states", "explanation": "The information about the directive is more important than on whom it is being addressed to. Hence the suitable title would be Council Directive laying down new measures for preservatives."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Law"], "Instance": {"id": "task743-6bef5f3145e043e3af084358a6d65c20", "input": "The common quality standards for cauliflowers, tomatoes, apples and pears, peaches, citrus fruits and table grapes shall be supplemented by the addition of a further quality class described as 'Class III'.Class III is defined for each product in the Annexes to this Regulation. This Regulation shall enter into force on 1 January 1967.This Regulation shall be binding in its entirety and directly applicable in all Member States.", "output": ["Regulation adding a supplementary quality class to the common quality standards for certain fruits and vegetables"]}, "Instance License": ["\u00a9 European Union, 1998-2021 (https://huggingface.co/datasets/eurlex#licensing-information)"], "prediction": "The common quality standards for cauliflowers, tomatoes, apples and pears, peaches, citrus fruits and table grapes shall be supplemented by a further quality class described as Class III."}
+{"id": "task1388-5f17ad50c9c64652a3aadde5af93ef0e", "Task": "task1388_cb_entailment", "Contributors": "['Yeganeh Kordi']", "Source": ["cb"], "URL": ["https://huggingface.co/datasets/super_glue"], "Categories": ["Textual Entailment"], "Reasoning": ["Textual Entailment", "Commonsense Reasoning", "Causal Reasoning"], "Definition": ["In this task, you will be presented with a premise and a hypothesis sentence. Determine whether the hypothesis sentence entails (implies), contradicts (opposes), or is neutral with respect to the given premise. Please answer with \"Contradiction\", \"Neutral\", or \"Entailment\"."], "Positive Examples": [{"input": "Premise: Ockleton, Morpurgo, Cornelius, Dysart and half a dozen others too drunk to mention. But there was so much coming and going that any one of us could have slipped out, pushed Everett through the window and slipped back again without being noticed. Damn it all we didn't even notice Everett was missing until a porter tripped over him in the quad so anything's theoretically possible. <sep> Hypothesis: Everett was missing", "output": "Entailment", "explanation": "This is a good example. Everett was missing. So, the hypothesis sentence entails the given premise."}, {"input": "Premise: I should dearly have liked to know whether they were Europeans or Americans, but I couldn't hear the accents. They appeared to be arguing. I hoped the white men weren't telling him to eliminate all witnesses because I don't believe it would have needed much persuasion. <sep> Hypothesis: eliminating all witnesses would have needed much persuasion", "output": "Contradiction", "explanation": "The speaker doesn't believe eliminating all witnesses would have needed much persuasion. In this example hypothesis sentence contradicts the given premise."}, {"input": "Premise: B: All right, well. A: Um, short term, I don't think anything's going to be done about it or probably should be done about it. B: Right.  Uh, are you saying you don't think anything should be done in the short term? <sep> Hypothesis: anything should be done in the short term", "output": "Neutral", "explanation": "In this example we don't know anything should be done in the short term or not. So, hypothesis sentence is neutral with respect to a given premise."}], "Negative Examples": [{"input": "Premise: B: If, uh, you've some kid uh, who's from a broken family, the schools are supposed to fill that void. It's gotten way beyond uh, you know, teaching classes and maybe providing extracurricular sports activities or something like, oh, were kind of traditionally the school's roles. A: Yeah.  Yeah, it's interesting because, uh, we're just having conversation on this, uh, with a couple of people yesterday. And I was expressing my frustrations that, uh, so many problems, I work in a high school, are that kids don't have a degree of self-discipline which may be reflected in society at large. Uh, and you can't expect in a classroom for a particular course an hour a day to counteract, uh, sixteen or seventeen years of influence at home. B: Right. A: Um, and, it's seen more so because when you call parents up, many parents won't even recognize that there is a problem <sep> Hypothesis: there is a problem", "output": "Neutral", "explanation": "The hypothesis sentence entails the given premise sentence and \"Neutral\" is incorrect."}, {"input": "Premise: A: And, uh, I got to stay home with my kids, which I really wanted to do, but now I could not go back and do it. B: Yeah. A: I really couldn't, I don't think I could stay home all the time and do nothing. <sep> Hypothesis: he could stay home all the time and do nothing", "output": "Entailment", "explanation": "He couldn't stay home all the time and do nothing. So, the answer should be \"Contradiction\"."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Dialogue"], "Instance": {"id": "task1388-5f17ad50c9c64652a3aadde5af93ef0e", "input": "Premise: And I resent what happened to my flat. A couple of guys think they can stake it out and wait for me, rub their filthy fingers on my clothes, piss in my bathroom, and I'm supposed to ignore it. I know what I said about possessions being like leeches but that don't mean I 'll surrender them to a pair of punks. <sep> Hypothesis: he will surrender his possessions to a pair of punks", "output": ["Contradiction"]}, "Instance License": ["CC BY-SA 3.0"], "prediction": "Entails"}
+{"id": "task1388-780616a33f9346b4b00822dd6ca0659e", "Task": "task1388_cb_entailment", "Contributors": "['Yeganeh Kordi']", "Source": ["cb"], "URL": ["https://huggingface.co/datasets/super_glue"], "Categories": ["Textual Entailment"], "Reasoning": ["Textual Entailment", "Commonsense Reasoning", "Causal Reasoning"], "Definition": ["In this task, you will be presented with a premise and a hypothesis sentence. Determine whether the hypothesis sentence entails (implies), contradicts (opposes), or is neutral with respect to the given premise. Please answer with \"Contradiction\", \"Neutral\", or \"Entailment\"."], "Positive Examples": [{"input": "Premise: Ockleton, Morpurgo, Cornelius, Dysart and half a dozen others too drunk to mention. But there was so much coming and going that any one of us could have slipped out, pushed Everett through the window and slipped back again without being noticed. Damn it all we didn't even notice Everett was missing until a porter tripped over him in the quad so anything's theoretically possible. <sep> Hypothesis: Everett was missing", "output": "Entailment", "explanation": "This is a good example. Everett was missing. So, the hypothesis sentence entails the given premise."}, {"input": "Premise: I should dearly have liked to know whether they were Europeans or Americans, but I couldn't hear the accents. They appeared to be arguing. I hoped the white men weren't telling him to eliminate all witnesses because I don't believe it would have needed much persuasion. <sep> Hypothesis: eliminating all witnesses would have needed much persuasion", "output": "Contradiction", "explanation": "The speaker doesn't believe eliminating all witnesses would have needed much persuasion. In this example hypothesis sentence contradicts the given premise."}, {"input": "Premise: B: All right, well. A: Um, short term, I don't think anything's going to be done about it or probably should be done about it. B: Right.  Uh, are you saying you don't think anything should be done in the short term? <sep> Hypothesis: anything should be done in the short term", "output": "Neutral", "explanation": "In this example we don't know anything should be done in the short term or not. So, hypothesis sentence is neutral with respect to a given premise."}], "Negative Examples": [{"input": "Premise: B: If, uh, you've some kid uh, who's from a broken family, the schools are supposed to fill that void. It's gotten way beyond uh, you know, teaching classes and maybe providing extracurricular sports activities or something like, oh, were kind of traditionally the school's roles. A: Yeah.  Yeah, it's interesting because, uh, we're just having conversation on this, uh, with a couple of people yesterday. And I was expressing my frustrations that, uh, so many problems, I work in a high school, are that kids don't have a degree of self-discipline which may be reflected in society at large. Uh, and you can't expect in a classroom for a particular course an hour a day to counteract, uh, sixteen or seventeen years of influence at home. B: Right. A: Um, and, it's seen more so because when you call parents up, many parents won't even recognize that there is a problem <sep> Hypothesis: there is a problem", "output": "Neutral", "explanation": "The hypothesis sentence entails the given premise sentence and \"Neutral\" is incorrect."}, {"input": "Premise: A: And, uh, I got to stay home with my kids, which I really wanted to do, but now I could not go back and do it. B: Yeah. A: I really couldn't, I don't think I could stay home all the time and do nothing. <sep> Hypothesis: he could stay home all the time and do nothing", "output": "Entailment", "explanation": "He couldn't stay home all the time and do nothing. So, the answer should be \"Contradiction\"."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Dialogue"], "Instance": {"id": "task1388-780616a33f9346b4b00822dd6ca0659e", "input": "Premise: ``Clever''. Klug means ``clever''. Would you say that Abie was clever? <sep> Hypothesis: Abie was clever", "output": ["Neutral"]}, "Instance License": ["CC BY-SA 3.0"], "prediction": "Entails"}
+{"id": "task1388-54093d0c6d144587a448bb31cc5ed4e9", "Task": "task1388_cb_entailment", "Contributors": "['Yeganeh Kordi']", "Source": ["cb"], "URL": ["https://huggingface.co/datasets/super_glue"], "Categories": ["Textual Entailment"], "Reasoning": ["Textual Entailment", "Commonsense Reasoning", "Causal Reasoning"], "Definition": ["In this task, you will be presented with a premise and a hypothesis sentence. Determine whether the hypothesis sentence entails (implies), contradicts (opposes), or is neutral with respect to the given premise. Please answer with \"Contradiction\", \"Neutral\", or \"Entailment\"."], "Positive Examples": [{"input": "Premise: Ockleton, Morpurgo, Cornelius, Dysart and half a dozen others too drunk to mention. But there was so much coming and going that any one of us could have slipped out, pushed Everett through the window and slipped back again without being noticed. Damn it all we didn't even notice Everett was missing until a porter tripped over him in the quad so anything's theoretically possible. <sep> Hypothesis: Everett was missing", "output": "Entailment", "explanation": "This is a good example. Everett was missing. So, the hypothesis sentence entails the given premise."}, {"input": "Premise: I should dearly have liked to know whether they were Europeans or Americans, but I couldn't hear the accents. They appeared to be arguing. I hoped the white men weren't telling him to eliminate all witnesses because I don't believe it would have needed much persuasion. <sep> Hypothesis: eliminating all witnesses would have needed much persuasion", "output": "Contradiction", "explanation": "The speaker doesn't believe eliminating all witnesses would have needed much persuasion. In this example hypothesis sentence contradicts the given premise."}, {"input": "Premise: B: All right, well. A: Um, short term, I don't think anything's going to be done about it or probably should be done about it. B: Right.  Uh, are you saying you don't think anything should be done in the short term? <sep> Hypothesis: anything should be done in the short term", "output": "Neutral", "explanation": "In this example we don't know anything should be done in the short term or not. So, hypothesis sentence is neutral with respect to a given premise."}], "Negative Examples": [{"input": "Premise: B: If, uh, you've some kid uh, who's from a broken family, the schools are supposed to fill that void. It's gotten way beyond uh, you know, teaching classes and maybe providing extracurricular sports activities or something like, oh, were kind of traditionally the school's roles. A: Yeah.  Yeah, it's interesting because, uh, we're just having conversation on this, uh, with a couple of people yesterday. And I was expressing my frustrations that, uh, so many problems, I work in a high school, are that kids don't have a degree of self-discipline which may be reflected in society at large. Uh, and you can't expect in a classroom for a particular course an hour a day to counteract, uh, sixteen or seventeen years of influence at home. B: Right. A: Um, and, it's seen more so because when you call parents up, many parents won't even recognize that there is a problem <sep> Hypothesis: there is a problem", "output": "Neutral", "explanation": "The hypothesis sentence entails the given premise sentence and \"Neutral\" is incorrect."}, {"input": "Premise: A: And, uh, I got to stay home with my kids, which I really wanted to do, but now I could not go back and do it. B: Yeah. A: I really couldn't, I don't think I could stay home all the time and do nothing. <sep> Hypothesis: he could stay home all the time and do nothing", "output": "Entailment", "explanation": "He couldn't stay home all the time and do nothing. So, the answer should be \"Contradiction\"."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Dialogue"], "Instance": {"id": "task1388-54093d0c6d144587a448bb31cc5ed4e9", "input": "Premise: A: I, that would have been stupid, B: Yeah. A: and I don't think we did it. Everything else we handled in this seemed to be perfectly right. I don't think they would have done that. <sep> Hypothesis: they would have done that", "output": ["Contradiction"]}, "Instance License": ["CC BY-SA 3.0"], "prediction": "Entails"}
+{"id": "task1388-4cfa750e91ae40549c3c4f66f5dd60a1", "Task": "task1388_cb_entailment", "Contributors": "['Yeganeh Kordi']", "Source": ["cb"], "URL": ["https://huggingface.co/datasets/super_glue"], "Categories": ["Textual Entailment"], "Reasoning": ["Textual Entailment", "Commonsense Reasoning", "Causal Reasoning"], "Definition": ["In this task, you will be presented with a premise and a hypothesis sentence. Determine whether the hypothesis sentence entails (implies), contradicts (opposes), or is neutral with respect to the given premise. Please answer with \"Contradiction\", \"Neutral\", or \"Entailment\"."], "Positive Examples": [{"input": "Premise: Ockleton, Morpurgo, Cornelius, Dysart and half a dozen others too drunk to mention. But there was so much coming and going that any one of us could have slipped out, pushed Everett through the window and slipped back again without being noticed. Damn it all we didn't even notice Everett was missing until a porter tripped over him in the quad so anything's theoretically possible. <sep> Hypothesis: Everett was missing", "output": "Entailment", "explanation": "This is a good example. Everett was missing. So, the hypothesis sentence entails the given premise."}, {"input": "Premise: I should dearly have liked to know whether they were Europeans or Americans, but I couldn't hear the accents. They appeared to be arguing. I hoped the white men weren't telling him to eliminate all witnesses because I don't believe it would have needed much persuasion. <sep> Hypothesis: eliminating all witnesses would have needed much persuasion", "output": "Contradiction", "explanation": "The speaker doesn't believe eliminating all witnesses would have needed much persuasion. In this example hypothesis sentence contradicts the given premise."}, {"input": "Premise: B: All right, well. A: Um, short term, I don't think anything's going to be done about it or probably should be done about it. B: Right.  Uh, are you saying you don't think anything should be done in the short term? <sep> Hypothesis: anything should be done in the short term", "output": "Neutral", "explanation": "In this example we don't know anything should be done in the short term or not. So, hypothesis sentence is neutral with respect to a given premise."}], "Negative Examples": [{"input": "Premise: B: If, uh, you've some kid uh, who's from a broken family, the schools are supposed to fill that void. It's gotten way beyond uh, you know, teaching classes and maybe providing extracurricular sports activities or something like, oh, were kind of traditionally the school's roles. A: Yeah.  Yeah, it's interesting because, uh, we're just having conversation on this, uh, with a couple of people yesterday. And I was expressing my frustrations that, uh, so many problems, I work in a high school, are that kids don't have a degree of self-discipline which may be reflected in society at large. Uh, and you can't expect in a classroom for a particular course an hour a day to counteract, uh, sixteen or seventeen years of influence at home. B: Right. A: Um, and, it's seen more so because when you call parents up, many parents won't even recognize that there is a problem <sep> Hypothesis: there is a problem", "output": "Neutral", "explanation": "The hypothesis sentence entails the given premise sentence and \"Neutral\" is incorrect."}, {"input": "Premise: A: And, uh, I got to stay home with my kids, which I really wanted to do, but now I could not go back and do it. B: Yeah. A: I really couldn't, I don't think I could stay home all the time and do nothing. <sep> Hypothesis: he could stay home all the time and do nothing", "output": "Entailment", "explanation": "He couldn't stay home all the time and do nothing. So, the answer should be \"Contradiction\"."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Dialogue"], "Instance": {"id": "task1388-4cfa750e91ae40549c3c4f66f5dd60a1", "input": "Premise: She said good morning to Alice and Alice said hallo. She was thin and rather tall with a very lined gentle face and hair that was white but which Alice could see had once been blonde. She could also have told this was Tina's mother before Mrs Darne went off down the passage that led to the Headmaster's Flat. <sep> Hypothesis: this was Tina's mother", "output": ["Entailment"]}, "Instance License": ["CC BY-SA 3.0"], "prediction": "Entails"}
+{"id": "task1388-3b098b849ff743278dc0514bf076c878", "Task": "task1388_cb_entailment", "Contributors": "['Yeganeh Kordi']", "Source": ["cb"], "URL": ["https://huggingface.co/datasets/super_glue"], "Categories": ["Textual Entailment"], "Reasoning": ["Textual Entailment", "Commonsense Reasoning", "Causal Reasoning"], "Definition": ["In this task, you will be presented with a premise and a hypothesis sentence. Determine whether the hypothesis sentence entails (implies), contradicts (opposes), or is neutral with respect to the given premise. Please answer with \"Contradiction\", \"Neutral\", or \"Entailment\"."], "Positive Examples": [{"input": "Premise: Ockleton, Morpurgo, Cornelius, Dysart and half a dozen others too drunk to mention. But there was so much coming and going that any one of us could have slipped out, pushed Everett through the window and slipped back again without being noticed. Damn it all we didn't even notice Everett was missing until a porter tripped over him in the quad so anything's theoretically possible. <sep> Hypothesis: Everett was missing", "output": "Entailment", "explanation": "This is a good example. Everett was missing. So, the hypothesis sentence entails the given premise."}, {"input": "Premise: I should dearly have liked to know whether they were Europeans or Americans, but I couldn't hear the accents. They appeared to be arguing. I hoped the white men weren't telling him to eliminate all witnesses because I don't believe it would have needed much persuasion. <sep> Hypothesis: eliminating all witnesses would have needed much persuasion", "output": "Contradiction", "explanation": "The speaker doesn't believe eliminating all witnesses would have needed much persuasion. In this example hypothesis sentence contradicts the given premise."}, {"input": "Premise: B: All right, well. A: Um, short term, I don't think anything's going to be done about it or probably should be done about it. B: Right.  Uh, are you saying you don't think anything should be done in the short term? <sep> Hypothesis: anything should be done in the short term", "output": "Neutral", "explanation": "In this example we don't know anything should be done in the short term or not. So, hypothesis sentence is neutral with respect to a given premise."}], "Negative Examples": [{"input": "Premise: B: If, uh, you've some kid uh, who's from a broken family, the schools are supposed to fill that void. It's gotten way beyond uh, you know, teaching classes and maybe providing extracurricular sports activities or something like, oh, were kind of traditionally the school's roles. A: Yeah.  Yeah, it's interesting because, uh, we're just having conversation on this, uh, with a couple of people yesterday. And I was expressing my frustrations that, uh, so many problems, I work in a high school, are that kids don't have a degree of self-discipline which may be reflected in society at large. Uh, and you can't expect in a classroom for a particular course an hour a day to counteract, uh, sixteen or seventeen years of influence at home. B: Right. A: Um, and, it's seen more so because when you call parents up, many parents won't even recognize that there is a problem <sep> Hypothesis: there is a problem", "output": "Neutral", "explanation": "The hypothesis sentence entails the given premise sentence and \"Neutral\" is incorrect."}, {"input": "Premise: A: And, uh, I got to stay home with my kids, which I really wanted to do, but now I could not go back and do it. B: Yeah. A: I really couldn't, I don't think I could stay home all the time and do nothing. <sep> Hypothesis: he could stay home all the time and do nothing", "output": "Entailment", "explanation": "He couldn't stay home all the time and do nothing. So, the answer should be \"Contradiction\"."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Dialogue"], "Instance": {"id": "task1388-3b098b849ff743278dc0514bf076c878", "input": "Premise: B: So again, it never really penalizes, the company doing the wrong. A: Right. That will, B: They can go right on doing the same old thing they always used to. A: Huh. B: And if they know some practice is wrong, you know, <sep> Hypothesis: some practice is wrong", "output": ["Entailment"]}, "Instance License": ["CC BY-SA 3.0"], "prediction": "Entails"}
+{"id": "task671-c424f91a0728404b859abcf5658cb9c2", "Task": "task671_ambigqa_text_generation", "Contributors": "['Mirali Purohit']", "Source": ["ambigqa"], "URL": ["https://nlp.cs.washington.edu/ambigqa/"], "Categories": ["Question Rewriting"], "Reasoning": ["Abductive Reasoning"], "Definition": ["In this task, you're given an ambiguous question (which can be answered in more than one way). Your task is to provide one question which clarifies the input question and it has one unique answer, and also provide an answer to the generated question. Generated question and answer should be separated with a new line."], "Positive Examples": [{"input": "Lucifer how many episodes are in season 3?", "output": "How many episodes of season 3 of Lucifer were there, including bonus episodes? \n 26", "explanation": "The generated question clarifies the input question by asking about bonus episodes because if the question is about regular episodes only then the answer will be different than including the bonus episodes. Also, the answer to the generated question is provided."}, {"input": "What is the tallest ride at six flags over texas?", "output": "What is the tallest roller coaster at six flags over texas 2001? \n The Titan", "explanation": "The generated output elaborates the input question by mentioning the year in question because there is a different answer for this question for the year 1990, 2001 and 2011. Also, the answer to the generated question is provided."}, {"input": "Who won the final hoh big brother 20?", "output": "Who won the Final HoH in the American reality show Big Brother 20? \n Kaycee Clark", "explanation": "The generated output elaborates the input question that which reality show because there is two 'Big brother 20' show, American and British. Also, the answer to the generated question is provided."}], "Negative Examples": [{"input": "Lucifer how many episodes are in season 3?", "output": "How many episodes of season 3 of Lucifer were there, including bonus episodes? 26", "explanation": "The generated question clarifies the input question by asking about bonus episodes because if the question is about regular episodes only then the answer will be different than including the bonus episodes. However, output just writes the answer directly without adding a separator, i.e., \n."}, {"input": "What is the tallest ride at six flags over texas?", "output": "What is the tallest roller coaster at six flags over Texas 2001?", "explanation": "The generated output elaborates the input question by mentioning the year in question because there is a different answer for this question for the year 1990, 2001 and 2011. However, the answer to the generated question is not provided."}, {"input": "Who won the final hoh big brother 20?", "output": "Who lose the Final HoH in the American reality show Big Brother 20? \n Sarah Harding", "explanation": "The generated output elaborates the input question that which reality show because there is two 'Big brother 20' show, American and British. Also, an answer to the generated question is provided. However, the output of the generated question is incorrect; Sarah Harding won the British reality show not American."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Wikipedia"], "Instance": {"id": "task671-c424f91a0728404b859abcf5658cb9c2", "input": "Who invented the process to remove impurities by blasts of cold air blown through heated iron?", "output": ["What Englishman invented the process to remove impurities by blasts of cold air blown through heated iron? \n Henry Bessemer"]}, "Instance License": ["Unknown"], "prediction": "Who invented the process to remove impurities by blasts of cold air blown through heated iron?"}
+{"id": "task671-cf65bb72b8154fad847563db88c2373e", "Task": "task671_ambigqa_text_generation", "Contributors": "['Mirali Purohit']", "Source": ["ambigqa"], "URL": ["https://nlp.cs.washington.edu/ambigqa/"], "Categories": ["Question Rewriting"], "Reasoning": ["Abductive Reasoning"], "Definition": ["In this task, you're given an ambiguous question (which can be answered in more than one way). Your task is to provide one question which clarifies the input question and it has one unique answer, and also provide an answer to the generated question. Generated question and answer should be separated with a new line."], "Positive Examples": [{"input": "Lucifer how many episodes are in season 3?", "output": "How many episodes of season 3 of Lucifer were there, including bonus episodes? \n 26", "explanation": "The generated question clarifies the input question by asking about bonus episodes because if the question is about regular episodes only then the answer will be different than including the bonus episodes. Also, the answer to the generated question is provided."}, {"input": "What is the tallest ride at six flags over texas?", "output": "What is the tallest roller coaster at six flags over texas 2001? \n The Titan", "explanation": "The generated output elaborates the input question by mentioning the year in question because there is a different answer for this question for the year 1990, 2001 and 2011. Also, the answer to the generated question is provided."}, {"input": "Who won the final hoh big brother 20?", "output": "Who won the Final HoH in the American reality show Big Brother 20? \n Kaycee Clark", "explanation": "The generated output elaborates the input question that which reality show because there is two 'Big brother 20' show, American and British. Also, the answer to the generated question is provided."}], "Negative Examples": [{"input": "Lucifer how many episodes are in season 3?", "output": "How many episodes of season 3 of Lucifer were there, including bonus episodes? 26", "explanation": "The generated question clarifies the input question by asking about bonus episodes because if the question is about regular episodes only then the answer will be different than including the bonus episodes. However, output just writes the answer directly without adding a separator, i.e., \n."}, {"input": "What is the tallest ride at six flags over texas?", "output": "What is the tallest roller coaster at six flags over Texas 2001?", "explanation": "The generated output elaborates the input question by mentioning the year in question because there is a different answer for this question for the year 1990, 2001 and 2011. However, the answer to the generated question is not provided."}, {"input": "Who won the final hoh big brother 20?", "output": "Who lose the Final HoH in the American reality show Big Brother 20? \n Sarah Harding", "explanation": "The generated output elaborates the input question that which reality show because there is two 'Big brother 20' show, American and British. Also, an answer to the generated question is provided. However, the output of the generated question is incorrect; Sarah Harding won the British reality show not American."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Wikipedia"], "Instance": {"id": "task671-cf65bb72b8154fad847563db88c2373e", "input": "How old do you have to be to get a tattoo in indiana?", "output": ["How old do you have to be to get a tattoo in Indiana without parental consent? \n 18"]}, "Instance License": ["Unknown"], "prediction": "How old do you have to be to get a tattoo in Indiana?"}
+{"id": "task671-e57ef62ea85e4198b854f74f8666ccb5", "Task": "task671_ambigqa_text_generation", "Contributors": "['Mirali Purohit']", "Source": ["ambigqa"], "URL": ["https://nlp.cs.washington.edu/ambigqa/"], "Categories": ["Question Rewriting"], "Reasoning": ["Abductive Reasoning"], "Definition": ["In this task, you're given an ambiguous question (which can be answered in more than one way). Your task is to provide one question which clarifies the input question and it has one unique answer, and also provide an answer to the generated question. Generated question and answer should be separated with a new line."], "Positive Examples": [{"input": "Lucifer how many episodes are in season 3?", "output": "How many episodes of season 3 of Lucifer were there, including bonus episodes? \n 26", "explanation": "The generated question clarifies the input question by asking about bonus episodes because if the question is about regular episodes only then the answer will be different than including the bonus episodes. Also, the answer to the generated question is provided."}, {"input": "What is the tallest ride at six flags over texas?", "output": "What is the tallest roller coaster at six flags over texas 2001? \n The Titan", "explanation": "The generated output elaborates the input question by mentioning the year in question because there is a different answer for this question for the year 1990, 2001 and 2011. Also, the answer to the generated question is provided."}, {"input": "Who won the final hoh big brother 20?", "output": "Who won the Final HoH in the American reality show Big Brother 20? \n Kaycee Clark", "explanation": "The generated output elaborates the input question that which reality show because there is two 'Big brother 20' show, American and British. Also, the answer to the generated question is provided."}], "Negative Examples": [{"input": "Lucifer how many episodes are in season 3?", "output": "How many episodes of season 3 of Lucifer were there, including bonus episodes? 26", "explanation": "The generated question clarifies the input question by asking about bonus episodes because if the question is about regular episodes only then the answer will be different than including the bonus episodes. However, output just writes the answer directly without adding a separator, i.e., \n."}, {"input": "What is the tallest ride at six flags over texas?", "output": "What is the tallest roller coaster at six flags over Texas 2001?", "explanation": "The generated output elaborates the input question by mentioning the year in question because there is a different answer for this question for the year 1990, 2001 and 2011. However, the answer to the generated question is not provided."}, {"input": "Who won the final hoh big brother 20?", "output": "Who lose the Final HoH in the American reality show Big Brother 20? \n Sarah Harding", "explanation": "The generated output elaborates the input question that which reality show because there is two 'Big brother 20' show, American and British. Also, an answer to the generated question is provided. However, the output of the generated question is incorrect; Sarah Harding won the British reality show not American."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Wikipedia"], "Instance": {"id": "task671-e57ef62ea85e4198b854f74f8666ccb5", "input": "When did the old age pension start in australia?", "output": ["When did an old age pension start in parts of australia? \n 1900"]}, "Instance License": ["Unknown"], "prediction": "What year did the old age pension start in Australia?"}
+{"id": "task671-c443b946b54040119324257e70e4a081", "Task": "task671_ambigqa_text_generation", "Contributors": "['Mirali Purohit']", "Source": ["ambigqa"], "URL": ["https://nlp.cs.washington.edu/ambigqa/"], "Categories": ["Question Rewriting"], "Reasoning": ["Abductive Reasoning"], "Definition": ["In this task, you're given an ambiguous question (which can be answered in more than one way). Your task is to provide one question which clarifies the input question and it has one unique answer, and also provide an answer to the generated question. Generated question and answer should be separated with a new line."], "Positive Examples": [{"input": "Lucifer how many episodes are in season 3?", "output": "How many episodes of season 3 of Lucifer were there, including bonus episodes? \n 26", "explanation": "The generated question clarifies the input question by asking about bonus episodes because if the question is about regular episodes only then the answer will be different than including the bonus episodes. Also, the answer to the generated question is provided."}, {"input": "What is the tallest ride at six flags over texas?", "output": "What is the tallest roller coaster at six flags over texas 2001? \n The Titan", "explanation": "The generated output elaborates the input question by mentioning the year in question because there is a different answer for this question for the year 1990, 2001 and 2011. Also, the answer to the generated question is provided."}, {"input": "Who won the final hoh big brother 20?", "output": "Who won the Final HoH in the American reality show Big Brother 20? \n Kaycee Clark", "explanation": "The generated output elaborates the input question that which reality show because there is two 'Big brother 20' show, American and British. Also, the answer to the generated question is provided."}], "Negative Examples": [{"input": "Lucifer how many episodes are in season 3?", "output": "How many episodes of season 3 of Lucifer were there, including bonus episodes? 26", "explanation": "The generated question clarifies the input question by asking about bonus episodes because if the question is about regular episodes only then the answer will be different than including the bonus episodes. However, output just writes the answer directly without adding a separator, i.e., \n."}, {"input": "What is the tallest ride at six flags over texas?", "output": "What is the tallest roller coaster at six flags over Texas 2001?", "explanation": "The generated output elaborates the input question by mentioning the year in question because there is a different answer for this question for the year 1990, 2001 and 2011. However, the answer to the generated question is not provided."}, {"input": "Who won the final hoh big brother 20?", "output": "Who lose the Final HoH in the American reality show Big Brother 20? \n Sarah Harding", "explanation": "The generated output elaborates the input question that which reality show because there is two 'Big brother 20' show, American and British. Also, an answer to the generated question is provided. However, the output of the generated question is incorrect; Sarah Harding won the British reality show not American."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Wikipedia"], "Instance": {"id": "task671-c443b946b54040119324257e70e4a081", "input": "Who wrote the music for shrek the musical?", "output": ["Who wrote the music scores for shrek the musical? \n Jeanine Tesori"]}, "Instance License": ["Unknown"], "prediction": "Who wrote the music for Shrek the Musical?"}
+{"id": "task671-7fa35c1d80c94845ba6420f4e649176b", "Task": "task671_ambigqa_text_generation", "Contributors": "['Mirali Purohit']", "Source": ["ambigqa"], "URL": ["https://nlp.cs.washington.edu/ambigqa/"], "Categories": ["Question Rewriting"], "Reasoning": ["Abductive Reasoning"], "Definition": ["In this task, you're given an ambiguous question (which can be answered in more than one way). Your task is to provide one question which clarifies the input question and it has one unique answer, and also provide an answer to the generated question. Generated question and answer should be separated with a new line."], "Positive Examples": [{"input": "Lucifer how many episodes are in season 3?", "output": "How many episodes of season 3 of Lucifer were there, including bonus episodes? \n 26", "explanation": "The generated question clarifies the input question by asking about bonus episodes because if the question is about regular episodes only then the answer will be different than including the bonus episodes. Also, the answer to the generated question is provided."}, {"input": "What is the tallest ride at six flags over texas?", "output": "What is the tallest roller coaster at six flags over texas 2001? \n The Titan", "explanation": "The generated output elaborates the input question by mentioning the year in question because there is a different answer for this question for the year 1990, 2001 and 2011. Also, the answer to the generated question is provided."}, {"input": "Who won the final hoh big brother 20?", "output": "Who won the Final HoH in the American reality show Big Brother 20? \n Kaycee Clark", "explanation": "The generated output elaborates the input question that which reality show because there is two 'Big brother 20' show, American and British. Also, the answer to the generated question is provided."}], "Negative Examples": [{"input": "Lucifer how many episodes are in season 3?", "output": "How many episodes of season 3 of Lucifer were there, including bonus episodes? 26", "explanation": "The generated question clarifies the input question by asking about bonus episodes because if the question is about regular episodes only then the answer will be different than including the bonus episodes. However, output just writes the answer directly without adding a separator, i.e., \n."}, {"input": "What is the tallest ride at six flags over texas?", "output": "What is the tallest roller coaster at six flags over Texas 2001?", "explanation": "The generated output elaborates the input question by mentioning the year in question because there is a different answer for this question for the year 1990, 2001 and 2011. However, the answer to the generated question is not provided."}, {"input": "Who won the final hoh big brother 20?", "output": "Who lose the Final HoH in the American reality show Big Brother 20? \n Sarah Harding", "explanation": "The generated output elaborates the input question that which reality show because there is two 'Big brother 20' show, American and British. Also, an answer to the generated question is provided. However, the output of the generated question is incorrect; Sarah Harding won the British reality show not American."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Wikipedia"], "Instance": {"id": "task671-7fa35c1d80c94845ba6420f4e649176b", "input": "What is the scientific name for a red fox?", "output": ["What is the scientific name for all red foxes? \n Vulpes vulpes"]}, "Instance License": ["Unknown"], "prediction": "What is the scientific name for a red fox?"}
+{"id": "task121-6887f42733cc49ab93685b33f9c1584c", "Task": "task121_zest_text_modification", "Contributors": "['Yeganeh Kordi']", "Source": ["zest"], "URL": ["https://github.com/allenai/zest"], "Categories": ["Question Rewriting"], "Reasoning": [], "Definition": ["In this task, you are given two questions about a domain. Your task is to combine the main subjects of the questions to write a new, natural-sounding question. For example, if the first question is about the tallness of the president and the second question is about his performance at college, the new question can be about his tallness at college. Try to find the main idea of each question, then combine them; you can use different words or make the subjects negative (i.e., ask about shortness instead of tallness) to combine the subjects. The questions are in three domains: presidents, national parks, and dogs. Each question has a keyword indicating its domain. Keywords are \"this national park\", \"this dog breed\", and \"this president\", which will be replaced with the name of an actual president, a national park, or a breed of dog. Hence, in the new question, this keyword should also be used the same way. Do not write unnatural questions. (i.e., would not be a question someone might normally ask about domains). Do not write open-ended or subjective questions. (e.g., questions that can be answered differently by different people.) If you couldn't find the answer to your question from a single Google search, try to write a different question. You do not have to stick with the original question word for word, but you should try to create a question that combines the main subjects of the question."], "Positive Examples": [{"input": "What college did this president attend? Where did this president meet his wife?", "output": "Did this president meet his wife in college?", "explanation": "This is a good question. By combining \"meet wife\" and \"college\" we get to a new question."}, {"input": "Is this president over 6 feet tall? What college did this president attend?", "output": "Was this president shorter than six feet when they attended college?", "explanation": "In this question, by making \"tall\" in the first question negative and combining it with \"attend at college\" we get to the new question. Note that the new question sounds natural as well."}, {"input": "Is this president in favor of abortion? What college did this president attend?", "output": "Is this president against abortion even though they attended a liberal arts college?", "explanation": "In this question, by making \"favor of abortion\" in the first question negative and combining it with \"attend at college\" we get to the new question."}], "Negative Examples": [{"input": "Is this president over 6 feet tall? Is this president in favor of abortion?", "output": "Does this president support abortion and is he taller than 6 feet?", "explanation": "This question is relatively unnatural and is not something someone would usually ask in one sentence."}, {"input": "What college did this president attend? Where did this president meet his wife?", "output": "Did president meet his wife in college?", "explanation": "The keywords should be the same as the given question. So the \"president\" should be replaced with \"this president\"."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Government and Politics"], "Instance": {"id": "task121-6887f42733cc49ab93685b33f9c1584c", "input": "Is the number of caves in this national park greater than 2? Can you go spelunking in this national park?", "output": ["Can you go spelunking in more than one cave at this national park?"]}, "Instance License": ["Apache 2.0"], "prediction": "Are there more caves in this national park than 2?"}
+{"id": "task121-fed553f892f7483784efc072f0c071fb", "Task": "task121_zest_text_modification", "Contributors": "['Yeganeh Kordi']", "Source": ["zest"], "URL": ["https://github.com/allenai/zest"], "Categories": ["Question Rewriting"], "Reasoning": [], "Definition": ["In this task, you are given two questions about a domain. Your task is to combine the main subjects of the questions to write a new, natural-sounding question. For example, if the first question is about the tallness of the president and the second question is about his performance at college, the new question can be about his tallness at college. Try to find the main idea of each question, then combine them; you can use different words or make the subjects negative (i.e., ask about shortness instead of tallness) to combine the subjects. The questions are in three domains: presidents, national parks, and dogs. Each question has a keyword indicating its domain. Keywords are \"this national park\", \"this dog breed\", and \"this president\", which will be replaced with the name of an actual president, a national park, or a breed of dog. Hence, in the new question, this keyword should also be used the same way. Do not write unnatural questions. (i.e., would not be a question someone might normally ask about domains). Do not write open-ended or subjective questions. (e.g., questions that can be answered differently by different people.) If you couldn't find the answer to your question from a single Google search, try to write a different question. You do not have to stick with the original question word for word, but you should try to create a question that combines the main subjects of the question."], "Positive Examples": [{"input": "What college did this president attend? Where did this president meet his wife?", "output": "Did this president meet his wife in college?", "explanation": "This is a good question. By combining \"meet wife\" and \"college\" we get to a new question."}, {"input": "Is this president over 6 feet tall? What college did this president attend?", "output": "Was this president shorter than six feet when they attended college?", "explanation": "In this question, by making \"tall\" in the first question negative and combining it with \"attend at college\" we get to the new question. Note that the new question sounds natural as well."}, {"input": "Is this president in favor of abortion? What college did this president attend?", "output": "Is this president against abortion even though they attended a liberal arts college?", "explanation": "In this question, by making \"favor of abortion\" in the first question negative and combining it with \"attend at college\" we get to the new question."}], "Negative Examples": [{"input": "Is this president over 6 feet tall? Is this president in favor of abortion?", "output": "Does this president support abortion and is he taller than 6 feet?", "explanation": "This question is relatively unnatural and is not something someone would usually ask in one sentence."}, {"input": "What college did this president attend? Where did this president meet his wife?", "output": "Did president meet his wife in college?", "explanation": "The keywords should be the same as the given question. So the \"president\" should be replaced with \"this president\"."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Government and Politics"], "Instance": {"id": "task121-fed553f892f7483784efc072f0c071fb", "input": "Does this national park feature more than two restaurants? Is there a hotel you can sleep at in this national park?", "output": ["Is there a restaurant to eat at or a hotel you can sleep in at this national park?"]}, "Instance License": ["Apache 2.0"], "prediction": "Are there more than two restaurants in this national park?"}
+{"id": "task121-05f0f85e86e34378a6b90384397d2e3e", "Task": "task121_zest_text_modification", "Contributors": "['Yeganeh Kordi']", "Source": ["zest"], "URL": ["https://github.com/allenai/zest"], "Categories": ["Question Rewriting"], "Reasoning": [], "Definition": ["In this task, you are given two questions about a domain. Your task is to combine the main subjects of the questions to write a new, natural-sounding question. For example, if the first question is about the tallness of the president and the second question is about his performance at college, the new question can be about his tallness at college. Try to find the main idea of each question, then combine them; you can use different words or make the subjects negative (i.e., ask about shortness instead of tallness) to combine the subjects. The questions are in three domains: presidents, national parks, and dogs. Each question has a keyword indicating its domain. Keywords are \"this national park\", \"this dog breed\", and \"this president\", which will be replaced with the name of an actual president, a national park, or a breed of dog. Hence, in the new question, this keyword should also be used the same way. Do not write unnatural questions. (i.e., would not be a question someone might normally ask about domains). Do not write open-ended or subjective questions. (e.g., questions that can be answered differently by different people.) If you couldn't find the answer to your question from a single Google search, try to write a different question. You do not have to stick with the original question word for word, but you should try to create a question that combines the main subjects of the question."], "Positive Examples": [{"input": "What college did this president attend? Where did this president meet his wife?", "output": "Did this president meet his wife in college?", "explanation": "This is a good question. By combining \"meet wife\" and \"college\" we get to a new question."}, {"input": "Is this president over 6 feet tall? What college did this president attend?", "output": "Was this president shorter than six feet when they attended college?", "explanation": "In this question, by making \"tall\" in the first question negative and combining it with \"attend at college\" we get to the new question. Note that the new question sounds natural as well."}, {"input": "Is this president in favor of abortion? What college did this president attend?", "output": "Is this president against abortion even though they attended a liberal arts college?", "explanation": "In this question, by making \"favor of abortion\" in the first question negative and combining it with \"attend at college\" we get to the new question."}], "Negative Examples": [{"input": "Is this president over 6 feet tall? Is this president in favor of abortion?", "output": "Does this president support abortion and is he taller than 6 feet?", "explanation": "This question is relatively unnatural and is not something someone would usually ask in one sentence."}, {"input": "What college did this president attend? Where did this president meet his wife?", "output": "Did president meet his wife in college?", "explanation": "The keywords should be the same as the given question. So the \"president\" should be replaced with \"this president\"."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Government and Politics"], "Instance": {"id": "task121-05f0f85e86e34378a6b90384397d2e3e", "input": "Is white an acceptable color for this dog breed? Can a dog from this dog breed have only one color on their fur?", "output": ["Is white the only acceptable color for this dog breed?"]}, "Instance License": ["Apache 2.0"], "prediction": "Are white and black acceptable colors for this dog breed?"}
+{"id": "task121-1a06908cd9cc43d88ffb36f3066f34b1", "Task": "task121_zest_text_modification", "Contributors": "['Yeganeh Kordi']", "Source": ["zest"], "URL": ["https://github.com/allenai/zest"], "Categories": ["Question Rewriting"], "Reasoning": [], "Definition": ["In this task, you are given two questions about a domain. Your task is to combine the main subjects of the questions to write a new, natural-sounding question. For example, if the first question is about the tallness of the president and the second question is about his performance at college, the new question can be about his tallness at college. Try to find the main idea of each question, then combine them; you can use different words or make the subjects negative (i.e., ask about shortness instead of tallness) to combine the subjects. The questions are in three domains: presidents, national parks, and dogs. Each question has a keyword indicating its domain. Keywords are \"this national park\", \"this dog breed\", and \"this president\", which will be replaced with the name of an actual president, a national park, or a breed of dog. Hence, in the new question, this keyword should also be used the same way. Do not write unnatural questions. (i.e., would not be a question someone might normally ask about domains). Do not write open-ended or subjective questions. (e.g., questions that can be answered differently by different people.) If you couldn't find the answer to your question from a single Google search, try to write a different question. You do not have to stick with the original question word for word, but you should try to create a question that combines the main subjects of the question."], "Positive Examples": [{"input": "What college did this president attend? Where did this president meet his wife?", "output": "Did this president meet his wife in college?", "explanation": "This is a good question. By combining \"meet wife\" and \"college\" we get to a new question."}, {"input": "Is this president over 6 feet tall? What college did this president attend?", "output": "Was this president shorter than six feet when they attended college?", "explanation": "In this question, by making \"tall\" in the first question negative and combining it with \"attend at college\" we get to the new question. Note that the new question sounds natural as well."}, {"input": "Is this president in favor of abortion? What college did this president attend?", "output": "Is this president against abortion even though they attended a liberal arts college?", "explanation": "In this question, by making \"favor of abortion\" in the first question negative and combining it with \"attend at college\" we get to the new question."}], "Negative Examples": [{"input": "Is this president over 6 feet tall? Is this president in favor of abortion?", "output": "Does this president support abortion and is he taller than 6 feet?", "explanation": "This question is relatively unnatural and is not something someone would usually ask in one sentence."}, {"input": "What college did this president attend? Where did this president meet his wife?", "output": "Did president meet his wife in college?", "explanation": "The keywords should be the same as the given question. So the \"president\" should be replaced with \"this president\"."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Government and Politics"], "Instance": {"id": "task121-1a06908cd9cc43d88ffb36f3066f34b1", "input": "What year was the last year this president was in office? How did the stock market perform while this president was in office?", "output": ["How did the economy perform as this president took office?"]}, "Instance License": ["Apache 2.0"], "prediction": "Was this president the last president in office?"}
+{"id": "task121-868517cceacd4a31b2134a81291cd899", "Task": "task121_zest_text_modification", "Contributors": "['Yeganeh Kordi']", "Source": ["zest"], "URL": ["https://github.com/allenai/zest"], "Categories": ["Question Rewriting"], "Reasoning": [], "Definition": ["In this task, you are given two questions about a domain. Your task is to combine the main subjects of the questions to write a new, natural-sounding question. For example, if the first question is about the tallness of the president and the second question is about his performance at college, the new question can be about his tallness at college. Try to find the main idea of each question, then combine them; you can use different words or make the subjects negative (i.e., ask about shortness instead of tallness) to combine the subjects. The questions are in three domains: presidents, national parks, and dogs. Each question has a keyword indicating its domain. Keywords are \"this national park\", \"this dog breed\", and \"this president\", which will be replaced with the name of an actual president, a national park, or a breed of dog. Hence, in the new question, this keyword should also be used the same way. Do not write unnatural questions. (i.e., would not be a question someone might normally ask about domains). Do not write open-ended or subjective questions. (e.g., questions that can be answered differently by different people.) If you couldn't find the answer to your question from a single Google search, try to write a different question. You do not have to stick with the original question word for word, but you should try to create a question that combines the main subjects of the question."], "Positive Examples": [{"input": "What college did this president attend? Where did this president meet his wife?", "output": "Did this president meet his wife in college?", "explanation": "This is a good question. By combining \"meet wife\" and \"college\" we get to a new question."}, {"input": "Is this president over 6 feet tall? What college did this president attend?", "output": "Was this president shorter than six feet when they attended college?", "explanation": "In this question, by making \"tall\" in the first question negative and combining it with \"attend at college\" we get to the new question. Note that the new question sounds natural as well."}, {"input": "Is this president in favor of abortion? What college did this president attend?", "output": "Is this president against abortion even though they attended a liberal arts college?", "explanation": "In this question, by making \"favor of abortion\" in the first question negative and combining it with \"attend at college\" we get to the new question."}], "Negative Examples": [{"input": "Is this president over 6 feet tall? Is this president in favor of abortion?", "output": "Does this president support abortion and is he taller than 6 feet?", "explanation": "This question is relatively unnatural and is not something someone would usually ask in one sentence."}, {"input": "What college did this president attend? Where did this president meet his wife?", "output": "Did president meet his wife in college?", "explanation": "The keywords should be the same as the given question. So the \"president\" should be replaced with \"this president\"."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Government and Politics"], "Instance": {"id": "task121-868517cceacd4a31b2134a81291cd899", "input": "Can this dog breed have black or brown spots? Is white an acceptable color for this dog breed?", "output": ["Can this dog breed be white, black, or brown?"]}, "Instance License": ["Apache 2.0"], "prediction": "Are black or brown spots acceptable for this dog breed?"}
+{"id": "task1345-2ca8293fc79644ed811ecd82bf1f18d7", "Task": "task1345_glue_qqp_question_paraprashing", "Contributors": "['Arit Chanda']", "Source": ["qqp"], "URL": ["https://dl.fbaipublicfiles.com/glue/data/QQP-clean.zip"], "Categories": ["Question Rewriting"], "Reasoning": [], "Definition": ["In this task you're given a question and you have to paraphrase the question to create the output question while retaining the meaning of the original question."], "Positive Examples": [{"input": "What can one do after MBBS?", "output": "What do i do after my MBBS ?", "explanation": "In this example both the question ask the same thing about what to do after MBBS hence second question is the correct output "}, {"input": "Which is the best book to study TENSOR for general relativity from basic?", "output": "Which is the best book for tensor calculus?", "explanation": "In this example first question is asking for a good book for learning tensor hence the second question will be a valid output."}, {"input": "What are the coolest Android hacks and tricks you know?", "output": "What are some cool hacks for Android phones?", "explanation": "In this example question 1 is asking about some of the coolest Android hacks and tricks and the same is being done by the question 2. Hence, second question is a valid output."}, {"input": "Which are the best motivational videos?", "output": "What are some of the best motivational clips?", "explanation": "In this example second question is a valid example as both the questions are asking for the best motivational videos."}], "Negative Examples": [{"input": "Do you need a passport to go to Jamaica from the United States?", "output": "How can I move to Jamaica?", "explanation": "In this example even though both questions have the same overall theme of moving to Jamaica the first question is only asking if Passport will be required for travelling to Jamaica from United States where the second quesition is just asking how do we move to Jamaica in general.Hence, second question is not a valid output."}, {"input": "How is the life of a math student? Could you describe your own experiences?", "output": "Which level of prepration is enough for the exam jlpt5?", "explanation": "In this example first question is asking about life of a math student wheras the second question is asking about preparation for jlpt5 exam. Since both do not mean the same thing this will not be a valid output."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Books", "Dialogue"], "Instance": {"id": "task1345-2ca8293fc79644ed811ecd82bf1f18d7", "input": "What are the options if my daughter not got seat in IIT or NIT. At present she is under coaching in Allen, Kota. This year she is in class 11th.?", "output": ["Who is won indutal medal?"]}, "Instance License": ["Quora Terms of Service (https://www.quora.com/about/tos)"], "prediction": "What are the options if my daughter not got seat in IIT or NIT?"}
+{"id": "task1345-740c14a386ca4d0189102bd337f5c34d", "Task": "task1345_glue_qqp_question_paraprashing", "Contributors": "['Arit Chanda']", "Source": ["qqp"], "URL": ["https://dl.fbaipublicfiles.com/glue/data/QQP-clean.zip"], "Categories": ["Question Rewriting"], "Reasoning": [], "Definition": ["In this task you're given a question and you have to paraphrase the question to create the output question while retaining the meaning of the original question."], "Positive Examples": [{"input": "What can one do after MBBS?", "output": "What do i do after my MBBS ?", "explanation": "In this example both the question ask the same thing about what to do after MBBS hence second question is the correct output "}, {"input": "Which is the best book to study TENSOR for general relativity from basic?", "output": "Which is the best book for tensor calculus?", "explanation": "In this example first question is asking for a good book for learning tensor hence the second question will be a valid output."}, {"input": "What are the coolest Android hacks and tricks you know?", "output": "What are some cool hacks for Android phones?", "explanation": "In this example question 1 is asking about some of the coolest Android hacks and tricks and the same is being done by the question 2. Hence, second question is a valid output."}, {"input": "Which are the best motivational videos?", "output": "What are some of the best motivational clips?", "explanation": "In this example second question is a valid example as both the questions are asking for the best motivational videos."}], "Negative Examples": [{"input": "Do you need a passport to go to Jamaica from the United States?", "output": "How can I move to Jamaica?", "explanation": "In this example even though both questions have the same overall theme of moving to Jamaica the first question is only asking if Passport will be required for travelling to Jamaica from United States where the second quesition is just asking how do we move to Jamaica in general.Hence, second question is not a valid output."}, {"input": "How is the life of a math student? Could you describe your own experiences?", "output": "Which level of prepration is enough for the exam jlpt5?", "explanation": "In this example first question is asking about life of a math student wheras the second question is asking about preparation for jlpt5 exam. Since both do not mean the same thing this will not be a valid output."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Books", "Dialogue"], "Instance": {"id": "task1345-740c14a386ca4d0189102bd337f5c34d", "input": "Do employees at Select Income REIT have a good work-life balance? Does this differ across positions and departments?", "output": ["Do employees at Pennsylvania REIT have a good work-life balance? Does this differ across positions and departments?"]}, "Instance License": ["Quora Terms of Service (https://www.quora.com/about/tos)"], "prediction": "Do employees at Select Income REIT have a good work-life balance?"}
+{"id": "task1345-0931b1915b994c01a54722498770c863", "Task": "task1345_glue_qqp_question_paraprashing", "Contributors": "['Arit Chanda']", "Source": ["qqp"], "URL": ["https://dl.fbaipublicfiles.com/glue/data/QQP-clean.zip"], "Categories": ["Question Rewriting"], "Reasoning": [], "Definition": ["In this task you're given a question and you have to paraphrase the question to create the output question while retaining the meaning of the original question."], "Positive Examples": [{"input": "What can one do after MBBS?", "output": "What do i do after my MBBS ?", "explanation": "In this example both the question ask the same thing about what to do after MBBS hence second question is the correct output "}, {"input": "Which is the best book to study TENSOR for general relativity from basic?", "output": "Which is the best book for tensor calculus?", "explanation": "In this example first question is asking for a good book for learning tensor hence the second question will be a valid output."}, {"input": "What are the coolest Android hacks and tricks you know?", "output": "What are some cool hacks for Android phones?", "explanation": "In this example question 1 is asking about some of the coolest Android hacks and tricks and the same is being done by the question 2. Hence, second question is a valid output."}, {"input": "Which are the best motivational videos?", "output": "What are some of the best motivational clips?", "explanation": "In this example second question is a valid example as both the questions are asking for the best motivational videos."}], "Negative Examples": [{"input": "Do you need a passport to go to Jamaica from the United States?", "output": "How can I move to Jamaica?", "explanation": "In this example even though both questions have the same overall theme of moving to Jamaica the first question is only asking if Passport will be required for travelling to Jamaica from United States where the second quesition is just asking how do we move to Jamaica in general.Hence, second question is not a valid output."}, {"input": "How is the life of a math student? Could you describe your own experiences?", "output": "Which level of prepration is enough for the exam jlpt5?", "explanation": "In this example first question is asking about life of a math student wheras the second question is asking about preparation for jlpt5 exam. Since both do not mean the same thing this will not be a valid output."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Books", "Dialogue"], "Instance": {"id": "task1345-0931b1915b994c01a54722498770c863", "input": "? to be deleted", "output": ["Did Hitler underestimate the jewish mafia-nation?"]}, "Instance License": ["Quora Terms of Service (https://www.quora.com/about/tos)"], "prediction": "? to be deleted"}
+{"id": "task1345-d17816f0fe5a4a5492534bcbda2ba135", "Task": "task1345_glue_qqp_question_paraprashing", "Contributors": "['Arit Chanda']", "Source": ["qqp"], "URL": ["https://dl.fbaipublicfiles.com/glue/data/QQP-clean.zip"], "Categories": ["Question Rewriting"], "Reasoning": [], "Definition": ["In this task you're given a question and you have to paraphrase the question to create the output question while retaining the meaning of the original question."], "Positive Examples": [{"input": "What can one do after MBBS?", "output": "What do i do after my MBBS ?", "explanation": "In this example both the question ask the same thing about what to do after MBBS hence second question is the correct output "}, {"input": "Which is the best book to study TENSOR for general relativity from basic?", "output": "Which is the best book for tensor calculus?", "explanation": "In this example first question is asking for a good book for learning tensor hence the second question will be a valid output."}, {"input": "What are the coolest Android hacks and tricks you know?", "output": "What are some cool hacks for Android phones?", "explanation": "In this example question 1 is asking about some of the coolest Android hacks and tricks and the same is being done by the question 2. Hence, second question is a valid output."}, {"input": "Which are the best motivational videos?", "output": "What are some of the best motivational clips?", "explanation": "In this example second question is a valid example as both the questions are asking for the best motivational videos."}], "Negative Examples": [{"input": "Do you need a passport to go to Jamaica from the United States?", "output": "How can I move to Jamaica?", "explanation": "In this example even though both questions have the same overall theme of moving to Jamaica the first question is only asking if Passport will be required for travelling to Jamaica from United States where the second quesition is just asking how do we move to Jamaica in general.Hence, second question is not a valid output."}, {"input": "How is the life of a math student? Could you describe your own experiences?", "output": "Which level of prepration is enough for the exam jlpt5?", "explanation": "In this example first question is asking about life of a math student wheras the second question is asking about preparation for jlpt5 exam. Since both do not mean the same thing this will not be a valid output."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Books", "Dialogue"], "Instance": {"id": "task1345-d17816f0fe5a4a5492534bcbda2ba135", "input": "When should you lose your virginity?", "output": ["Why did you lose your virginity?"]}, "Instance License": ["Quora Terms of Service (https://www.quora.com/about/tos)"], "prediction": "When should you lose your virginity?"}
+{"id": "task1345-3da463def78d4e1087d980de867aa6aa", "Task": "task1345_glue_qqp_question_paraprashing", "Contributors": "['Arit Chanda']", "Source": ["qqp"], "URL": ["https://dl.fbaipublicfiles.com/glue/data/QQP-clean.zip"], "Categories": ["Question Rewriting"], "Reasoning": [], "Definition": ["In this task you're given a question and you have to paraphrase the question to create the output question while retaining the meaning of the original question."], "Positive Examples": [{"input": "What can one do after MBBS?", "output": "What do i do after my MBBS ?", "explanation": "In this example both the question ask the same thing about what to do after MBBS hence second question is the correct output "}, {"input": "Which is the best book to study TENSOR for general relativity from basic?", "output": "Which is the best book for tensor calculus?", "explanation": "In this example first question is asking for a good book for learning tensor hence the second question will be a valid output."}, {"input": "What are the coolest Android hacks and tricks you know?", "output": "What are some cool hacks for Android phones?", "explanation": "In this example question 1 is asking about some of the coolest Android hacks and tricks and the same is being done by the question 2. Hence, second question is a valid output."}, {"input": "Which are the best motivational videos?", "output": "What are some of the best motivational clips?", "explanation": "In this example second question is a valid example as both the questions are asking for the best motivational videos."}], "Negative Examples": [{"input": "Do you need a passport to go to Jamaica from the United States?", "output": "How can I move to Jamaica?", "explanation": "In this example even though both questions have the same overall theme of moving to Jamaica the first question is only asking if Passport will be required for travelling to Jamaica from United States where the second quesition is just asking how do we move to Jamaica in general.Hence, second question is not a valid output."}, {"input": "How is the life of a math student? Could you describe your own experiences?", "output": "Which level of prepration is enough for the exam jlpt5?", "explanation": "In this example first question is asking about life of a math student wheras the second question is asking about preparation for jlpt5 exam. Since both do not mean the same thing this will not be a valid output."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Books", "Dialogue"], "Instance": {"id": "task1345-3da463def78d4e1087d980de867aa6aa", "input": "Fetch jobs from job portals through API calls?", "output": ["What are some creative ideas for arranging a freshers' party?"]}, "Instance License": ["Quora Terms of Service (https://www.quora.com/about/tos)"], "prediction": "What is the best way to get jobs from job portals?"}
+{"id": "task330-64d9a82a31e649428d61fa4deabf470a", "Task": "task330_gap_answer_generation", "Contributors": "['Yeganeh Kordi']", "Source": ["gap"], "URL": ["https://github.com/google-research-datasets/gap-coreference"], "Categories": ["Coreference Resolution"], "Reasoning": [], "Definition": ["In this task, you will be presented with a text and a pronoun. You should write the name that the pronoun refers to. Position of the pronoun in the text is showed within two \"_\"s."], "Positive Examples": [{"input": "He grew up in Evanston, Illinois the second oldest of five children including his brothers, Fred and Gordon and sisters, Marge (Peppy) and Marilyn. His high school days were spent at New Trier High School in Winnetka, Illinois. MacKenzie studied with Bernard Leach from 1949 to 1952. _His_ simple, wheel-thrown functional pottery is heavily influenced by the oriental aesthetic of Shoji Hamada and Kanjiro Kawai. <sep>, Pronoun: His", "output": "MacKenzie", "explanation": "Based on the sentence before the pronoun, \"his\" refers to MacKenzie."}, {"input": "The current members of Crime have also performed in San Francisco under the band name ''Remote Viewers``. Strike has published two works of fiction in recent years: Ports of Hell, which is listed in the Rock and Roll Hall of Fame Library, and A Loud Humming Sound Came from Above. Rank has produced numerous films (under _his_ real name, Henry Rosenthal) including the hit The Devil and Daniel Johnston. <sep>, Pronoun: his", "output": "Henry Rosenthal", "explanation": "Based on the text, his refers to Henry Rosenthal."}, {"input": "Kathleen Nott was born in Camberwell, London. Her father, Philip, was a lithographic printer, and her mother, Ellen, ran a boarding house in Brixton; Kathleen was their third daughter. _She_ was educated at Mary Datchelor Girls' School (now closed), London, before attending King's College, London. <sep>, Pronoun: She", "output": "Kathleen", "explanation": "Since the sentence before the pronoun is speaking about Kathleen, the pronoun \"she\" refers to Kathleen."}], "Negative Examples": [{"input": "He had been reelected to Congress, but resigned in 1990 to accept a post as Ambassador to Brazil. De la Sota again ran for governor of C*rdoba in 1991. Defeated by Governor Angeloz by over 15%, this latter setback was significant because it cost De la Sota much of _his_ support within the Justicialist Party (which was flush with victory in the 1991 mid-terms), leading to President Carlos Menem 's endorsement of a separate party list in C*rdoba for the 1993 mid-term elections, and to De la Sota's failure to regain a seat in Congress. <sep>, Pronoun: his", "output": "Angeloz", "explanation": "Based on the text, his refers to De la Sota, and Angeloz is incorrect"}, {"input": "When she returns to her hotel room, a Liberian man (Tony Todd) forces her to smuggle $20 million worth of conflict diamonds to New York, or else fellow fight attendant and friend Angela will die. She is caught before she can board the flight, and the team now have nine hours until the plane lands, and save Angela. After the confiscated diamonds are stolen by the brother of Kaleo (Jason Scott Lee), whom Danny put away for murdering _his_ partner last year, Five-0 and Chief Fryer team up and enlist the help of August March (Ed Asner), who served a 30-year sentence for smuggling diamonds. <sep>, Pronoun: his", "output": "Tony", "explanation": "Based on the text, his refers to Danny, and Tony is incorrect"}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Wikipedia"], "Instance": {"id": "task330-64d9a82a31e649428d61fa4deabf470a", "input": "General Adkins served in the Maryland Military Department as chief of staff and assistant adjutant general for state operations. He also served as director of the Cemetery and Memorial Programs and as the deputy secretary of Veterans Affairs. In May 2007, Governor Martin O*Malley appointed General Adkins to _his_ cabinet as the secretary of Veterans Affairs. <sep>, Pronoun: his", "output": ["Martin O*Malley"]}, "Instance License": ["Apache 2.0"], "prediction": "General Adkins"}
+{"id": "task330-d21ed172a6d0420d850b7a43494cf12f", "Task": "task330_gap_answer_generation", "Contributors": "['Yeganeh Kordi']", "Source": ["gap"], "URL": ["https://github.com/google-research-datasets/gap-coreference"], "Categories": ["Coreference Resolution"], "Reasoning": [], "Definition": ["In this task, you will be presented with a text and a pronoun. You should write the name that the pronoun refers to. Position of the pronoun in the text is showed within two \"_\"s."], "Positive Examples": [{"input": "He grew up in Evanston, Illinois the second oldest of five children including his brothers, Fred and Gordon and sisters, Marge (Peppy) and Marilyn. His high school days were spent at New Trier High School in Winnetka, Illinois. MacKenzie studied with Bernard Leach from 1949 to 1952. _His_ simple, wheel-thrown functional pottery is heavily influenced by the oriental aesthetic of Shoji Hamada and Kanjiro Kawai. <sep>, Pronoun: His", "output": "MacKenzie", "explanation": "Based on the sentence before the pronoun, \"his\" refers to MacKenzie."}, {"input": "The current members of Crime have also performed in San Francisco under the band name ''Remote Viewers``. Strike has published two works of fiction in recent years: Ports of Hell, which is listed in the Rock and Roll Hall of Fame Library, and A Loud Humming Sound Came from Above. Rank has produced numerous films (under _his_ real name, Henry Rosenthal) including the hit The Devil and Daniel Johnston. <sep>, Pronoun: his", "output": "Henry Rosenthal", "explanation": "Based on the text, his refers to Henry Rosenthal."}, {"input": "Kathleen Nott was born in Camberwell, London. Her father, Philip, was a lithographic printer, and her mother, Ellen, ran a boarding house in Brixton; Kathleen was their third daughter. _She_ was educated at Mary Datchelor Girls' School (now closed), London, before attending King's College, London. <sep>, Pronoun: She", "output": "Kathleen", "explanation": "Since the sentence before the pronoun is speaking about Kathleen, the pronoun \"she\" refers to Kathleen."}], "Negative Examples": [{"input": "He had been reelected to Congress, but resigned in 1990 to accept a post as Ambassador to Brazil. De la Sota again ran for governor of C*rdoba in 1991. Defeated by Governor Angeloz by over 15%, this latter setback was significant because it cost De la Sota much of _his_ support within the Justicialist Party (which was flush with victory in the 1991 mid-terms), leading to President Carlos Menem 's endorsement of a separate party list in C*rdoba for the 1993 mid-term elections, and to De la Sota's failure to regain a seat in Congress. <sep>, Pronoun: his", "output": "Angeloz", "explanation": "Based on the text, his refers to De la Sota, and Angeloz is incorrect"}, {"input": "When she returns to her hotel room, a Liberian man (Tony Todd) forces her to smuggle $20 million worth of conflict diamonds to New York, or else fellow fight attendant and friend Angela will die. She is caught before she can board the flight, and the team now have nine hours until the plane lands, and save Angela. After the confiscated diamonds are stolen by the brother of Kaleo (Jason Scott Lee), whom Danny put away for murdering _his_ partner last year, Five-0 and Chief Fryer team up and enlist the help of August March (Ed Asner), who served a 30-year sentence for smuggling diamonds. <sep>, Pronoun: his", "output": "Tony", "explanation": "Based on the text, his refers to Danny, and Tony is incorrect"}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Wikipedia"], "Instance": {"id": "task330-d21ed172a6d0420d850b7a43494cf12f", "input": "Mike D'Angelo of The A.V. Club also praised Forster's performance and the tone of the film, saying ``If the film came across as jaded and cynical, it might well be hard to take. Instead, it seems weary and defeated, as if some people are simply born to fail.'' Conversely, Kristy Puchko of The Playlist criticized the film's humor and called it ``one note''. While _she_ praised the performances of Daniela Sandiford, Cole, Weaver, Forster, and Healy, Puchko stated that Coster-Waldau's performance ``keeps us at a distance, unable to connect, empathize, or care''. <sep>, Pronoun: she", "output": ["Kristy Puchko"]}, "Instance License": ["Apache 2.0"], "prediction": "Kristy Puchko"}
+{"id": "task330-e4965efde018479e9660076781b51d09", "Task": "task330_gap_answer_generation", "Contributors": "['Yeganeh Kordi']", "Source": ["gap"], "URL": ["https://github.com/google-research-datasets/gap-coreference"], "Categories": ["Coreference Resolution"], "Reasoning": [], "Definition": ["In this task, you will be presented with a text and a pronoun. You should write the name that the pronoun refers to. Position of the pronoun in the text is showed within two \"_\"s."], "Positive Examples": [{"input": "He grew up in Evanston, Illinois the second oldest of five children including his brothers, Fred and Gordon and sisters, Marge (Peppy) and Marilyn. His high school days were spent at New Trier High School in Winnetka, Illinois. MacKenzie studied with Bernard Leach from 1949 to 1952. _His_ simple, wheel-thrown functional pottery is heavily influenced by the oriental aesthetic of Shoji Hamada and Kanjiro Kawai. <sep>, Pronoun: His", "output": "MacKenzie", "explanation": "Based on the sentence before the pronoun, \"his\" refers to MacKenzie."}, {"input": "The current members of Crime have also performed in San Francisco under the band name ''Remote Viewers``. Strike has published two works of fiction in recent years: Ports of Hell, which is listed in the Rock and Roll Hall of Fame Library, and A Loud Humming Sound Came from Above. Rank has produced numerous films (under _his_ real name, Henry Rosenthal) including the hit The Devil and Daniel Johnston. <sep>, Pronoun: his", "output": "Henry Rosenthal", "explanation": "Based on the text, his refers to Henry Rosenthal."}, {"input": "Kathleen Nott was born in Camberwell, London. Her father, Philip, was a lithographic printer, and her mother, Ellen, ran a boarding house in Brixton; Kathleen was their third daughter. _She_ was educated at Mary Datchelor Girls' School (now closed), London, before attending King's College, London. <sep>, Pronoun: She", "output": "Kathleen", "explanation": "Since the sentence before the pronoun is speaking about Kathleen, the pronoun \"she\" refers to Kathleen."}], "Negative Examples": [{"input": "He had been reelected to Congress, but resigned in 1990 to accept a post as Ambassador to Brazil. De la Sota again ran for governor of C*rdoba in 1991. Defeated by Governor Angeloz by over 15%, this latter setback was significant because it cost De la Sota much of _his_ support within the Justicialist Party (which was flush with victory in the 1991 mid-terms), leading to President Carlos Menem 's endorsement of a separate party list in C*rdoba for the 1993 mid-term elections, and to De la Sota's failure to regain a seat in Congress. <sep>, Pronoun: his", "output": "Angeloz", "explanation": "Based on the text, his refers to De la Sota, and Angeloz is incorrect"}, {"input": "When she returns to her hotel room, a Liberian man (Tony Todd) forces her to smuggle $20 million worth of conflict diamonds to New York, or else fellow fight attendant and friend Angela will die. She is caught before she can board the flight, and the team now have nine hours until the plane lands, and save Angela. After the confiscated diamonds are stolen by the brother of Kaleo (Jason Scott Lee), whom Danny put away for murdering _his_ partner last year, Five-0 and Chief Fryer team up and enlist the help of August March (Ed Asner), who served a 30-year sentence for smuggling diamonds. <sep>, Pronoun: his", "output": "Tony", "explanation": "Based on the text, his refers to Danny, and Tony is incorrect"}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Wikipedia"], "Instance": {"id": "task330-e4965efde018479e9660076781b51d09", "input": "While walking across the front lawn, Gasazi reveals that when he sees dogs digging up his flowers and chewing on his trees in the garden, he turns them into ducks. When one duck comes towards Alan, Gasazi tells _him_ to take Fritz (who's now a duck) home and throws him out. <sep>, Pronoun: him", "output": ["Alan"]}, "Instance License": ["Apache 2.0"], "prediction": "Alan"}
+{"id": "task330-7a910140c3b249a8abc7685e8ec151b3", "Task": "task330_gap_answer_generation", "Contributors": "['Yeganeh Kordi']", "Source": ["gap"], "URL": ["https://github.com/google-research-datasets/gap-coreference"], "Categories": ["Coreference Resolution"], "Reasoning": [], "Definition": ["In this task, you will be presented with a text and a pronoun. You should write the name that the pronoun refers to. Position of the pronoun in the text is showed within two \"_\"s."], "Positive Examples": [{"input": "He grew up in Evanston, Illinois the second oldest of five children including his brothers, Fred and Gordon and sisters, Marge (Peppy) and Marilyn. His high school days were spent at New Trier High School in Winnetka, Illinois. MacKenzie studied with Bernard Leach from 1949 to 1952. _His_ simple, wheel-thrown functional pottery is heavily influenced by the oriental aesthetic of Shoji Hamada and Kanjiro Kawai. <sep>, Pronoun: His", "output": "MacKenzie", "explanation": "Based on the sentence before the pronoun, \"his\" refers to MacKenzie."}, {"input": "The current members of Crime have also performed in San Francisco under the band name ''Remote Viewers``. Strike has published two works of fiction in recent years: Ports of Hell, which is listed in the Rock and Roll Hall of Fame Library, and A Loud Humming Sound Came from Above. Rank has produced numerous films (under _his_ real name, Henry Rosenthal) including the hit The Devil and Daniel Johnston. <sep>, Pronoun: his", "output": "Henry Rosenthal", "explanation": "Based on the text, his refers to Henry Rosenthal."}, {"input": "Kathleen Nott was born in Camberwell, London. Her father, Philip, was a lithographic printer, and her mother, Ellen, ran a boarding house in Brixton; Kathleen was their third daughter. _She_ was educated at Mary Datchelor Girls' School (now closed), London, before attending King's College, London. <sep>, Pronoun: She", "output": "Kathleen", "explanation": "Since the sentence before the pronoun is speaking about Kathleen, the pronoun \"she\" refers to Kathleen."}], "Negative Examples": [{"input": "He had been reelected to Congress, but resigned in 1990 to accept a post as Ambassador to Brazil. De la Sota again ran for governor of C*rdoba in 1991. Defeated by Governor Angeloz by over 15%, this latter setback was significant because it cost De la Sota much of _his_ support within the Justicialist Party (which was flush with victory in the 1991 mid-terms), leading to President Carlos Menem 's endorsement of a separate party list in C*rdoba for the 1993 mid-term elections, and to De la Sota's failure to regain a seat in Congress. <sep>, Pronoun: his", "output": "Angeloz", "explanation": "Based on the text, his refers to De la Sota, and Angeloz is incorrect"}, {"input": "When she returns to her hotel room, a Liberian man (Tony Todd) forces her to smuggle $20 million worth of conflict diamonds to New York, or else fellow fight attendant and friend Angela will die. She is caught before she can board the flight, and the team now have nine hours until the plane lands, and save Angela. After the confiscated diamonds are stolen by the brother of Kaleo (Jason Scott Lee), whom Danny put away for murdering _his_ partner last year, Five-0 and Chief Fryer team up and enlist the help of August March (Ed Asner), who served a 30-year sentence for smuggling diamonds. <sep>, Pronoun: his", "output": "Tony", "explanation": "Based on the text, his refers to Danny, and Tony is incorrect"}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Wikipedia"], "Instance": {"id": "task330-7a910140c3b249a8abc7685e8ec151b3", "input": "Luigi Infantino (April 24, 1921, Racalmuto -- June 22, 1991, Rome) was an Italian operatic tenor, particularly associated with the lyric Italian and French repertories. Luigi Infantino studied at the Parma Conservatory with Italo Brancucci. _He_made his debut in 1943, at the Teatro Regio in Parma, as Rodolfo in La boh*me, which was also his debut role at the Teatro San Carlo in Naples, in 1945. <sep>, Pronoun: He", "output": ["Luigi Infantino"]}, "Instance License": ["Apache 2.0"], "prediction": "Luigi Infantino"}
+{"id": "task330-81c5b4e540854c65ad9e9247c684c295", "Task": "task330_gap_answer_generation", "Contributors": "['Yeganeh Kordi']", "Source": ["gap"], "URL": ["https://github.com/google-research-datasets/gap-coreference"], "Categories": ["Coreference Resolution"], "Reasoning": [], "Definition": ["In this task, you will be presented with a text and a pronoun. You should write the name that the pronoun refers to. Position of the pronoun in the text is showed within two \"_\"s."], "Positive Examples": [{"input": "He grew up in Evanston, Illinois the second oldest of five children including his brothers, Fred and Gordon and sisters, Marge (Peppy) and Marilyn. His high school days were spent at New Trier High School in Winnetka, Illinois. MacKenzie studied with Bernard Leach from 1949 to 1952. _His_ simple, wheel-thrown functional pottery is heavily influenced by the oriental aesthetic of Shoji Hamada and Kanjiro Kawai. <sep>, Pronoun: His", "output": "MacKenzie", "explanation": "Based on the sentence before the pronoun, \"his\" refers to MacKenzie."}, {"input": "The current members of Crime have also performed in San Francisco under the band name ''Remote Viewers``. Strike has published two works of fiction in recent years: Ports of Hell, which is listed in the Rock and Roll Hall of Fame Library, and A Loud Humming Sound Came from Above. Rank has produced numerous films (under _his_ real name, Henry Rosenthal) including the hit The Devil and Daniel Johnston. <sep>, Pronoun: his", "output": "Henry Rosenthal", "explanation": "Based on the text, his refers to Henry Rosenthal."}, {"input": "Kathleen Nott was born in Camberwell, London. Her father, Philip, was a lithographic printer, and her mother, Ellen, ran a boarding house in Brixton; Kathleen was their third daughter. _She_ was educated at Mary Datchelor Girls' School (now closed), London, before attending King's College, London. <sep>, Pronoun: She", "output": "Kathleen", "explanation": "Since the sentence before the pronoun is speaking about Kathleen, the pronoun \"she\" refers to Kathleen."}], "Negative Examples": [{"input": "He had been reelected to Congress, but resigned in 1990 to accept a post as Ambassador to Brazil. De la Sota again ran for governor of C*rdoba in 1991. Defeated by Governor Angeloz by over 15%, this latter setback was significant because it cost De la Sota much of _his_ support within the Justicialist Party (which was flush with victory in the 1991 mid-terms), leading to President Carlos Menem 's endorsement of a separate party list in C*rdoba for the 1993 mid-term elections, and to De la Sota's failure to regain a seat in Congress. <sep>, Pronoun: his", "output": "Angeloz", "explanation": "Based on the text, his refers to De la Sota, and Angeloz is incorrect"}, {"input": "When she returns to her hotel room, a Liberian man (Tony Todd) forces her to smuggle $20 million worth of conflict diamonds to New York, or else fellow fight attendant and friend Angela will die. She is caught before she can board the flight, and the team now have nine hours until the plane lands, and save Angela. After the confiscated diamonds are stolen by the brother of Kaleo (Jason Scott Lee), whom Danny put away for murdering _his_ partner last year, Five-0 and Chief Fryer team up and enlist the help of August March (Ed Asner), who served a 30-year sentence for smuggling diamonds. <sep>, Pronoun: his", "output": "Tony", "explanation": "Based on the text, his refers to Danny, and Tony is incorrect"}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Wikipedia"], "Instance": {"id": "task330-81c5b4e540854c65ad9e9247c684c295", "input": "Significant places listed individually on the National Register of Historic Places include: Boswell's Tavern, an important meeting place during the American Revolution and a well-preserved example of a Colonial-era tavern. Grassdale, an Italianate villa built in 1861 by the Morris family, later home of Rear Admiral David W. Taylor and _his_ wife Imogene Morris Taylor. <sep>, Pronoun: his", "output": ["David W. Taylor"]}, "Instance License": ["Apache 2.0"], "prediction": "Imogene Morris Taylor"}
+{"id": "task1342-6d10f4abfd7a4eab86384d15df98d8f9", "Task": "task1342_amazon_us_reviews_title", "Contributors": "['Vinayak Kothari']", "Source": ["amazon_us_reviews"], "URL": ["https://huggingface.co/datasets/amazon_us_reviews"], "Categories": ["Title Generation"], "Reasoning": [], "Definition": ["Given an Amazon customer review, write a title for the review. The preferred titles are under fifteen words."], "Positive Examples": [{"input": "I was very surprised at the high quality of the stitching, the sturdiness of the handles and the padding for my laptop. The price is amazingly low and the look is very good. I am quite happy with this purchase. It fit my MacBook Pro perfectly, with a little bit of room to spare.", "output": "Pleasantly surprised", "explanation": "The review is positive and the user liked the product very much based on the given review, and the title correctly resembles to review."}, {"input": "Bought cables in 3ft, 6ft and 9ft.  NONE of them worked.  NO FUNCTIONALITY WHATSOEVER.  Tested many times, its as if the copper wires are just not connected to the terminations.  Do these even go through Quality Control before they leave the factory?  Waste of money and time.", "output": "None of them worked.  No functionality at all.", "explanation": "The user did not like the product as it was not having any functionality and the title also states that the product was not useful."}], "Negative Examples": [{"input": "I was very surprised at the high quality of the stitching, the sturdiness of the handles and the padding for my laptop. The price is amazingly low and the look is very good. I am quite happy with this purchase. It fit my MacBook Pro perfectly, with a little bit of room to spare.", "output": "One Star", "explanation": "Here review states that the user has liked the product but the negative title of one star is in contrast to the review body."}, {"input": "Bought cables in 3ft, 6ft and 9ft.  NONE of them worked.  NO FUNCTIONALITY WHATSOEVER.  Tested many times, its as if the copper wires are just not connected to the terminations.  Do these even go through Quality Control before they leave the factory?  Waste of money and time.", "output": "The \"M\" key fell off after three days of light ...", "explanation": "User did not like cables he bought but the title states that \"M\" key fell off after three days of light which does not correctly define review body."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Reviews"], "Instance": {"id": "task1342-6d10f4abfd7a4eab86384d15df98d8f9", "input": "I got this Hub to help add additional ports for my laptop.  I definitely do not NEED 4 more 3.0 ports at this point, but its great to have this plug in to the existing 3.0 port and be hidden under my laptop stand to create more space on the sides of my laptop.", "output": ["Perfect space saver for your desk"]}, "Instance License": ["Amazon License (https://s3.amazonaws.com/amazon-reviews-pds/license.txt)"], "prediction": "Great to have this hidden under my laptop stand"}
+{"id": "task1342-8909f0c6a0354f9888dec31f315b932b", "Task": "task1342_amazon_us_reviews_title", "Contributors": "['Vinayak Kothari']", "Source": ["amazon_us_reviews"], "URL": ["https://huggingface.co/datasets/amazon_us_reviews"], "Categories": ["Title Generation"], "Reasoning": [], "Definition": ["Given an Amazon customer review, write a title for the review. The preferred titles are under fifteen words."], "Positive Examples": [{"input": "I was very surprised at the high quality of the stitching, the sturdiness of the handles and the padding for my laptop. The price is amazingly low and the look is very good. I am quite happy with this purchase. It fit my MacBook Pro perfectly, with a little bit of room to spare.", "output": "Pleasantly surprised", "explanation": "The review is positive and the user liked the product very much based on the given review, and the title correctly resembles to review."}, {"input": "Bought cables in 3ft, 6ft and 9ft.  NONE of them worked.  NO FUNCTIONALITY WHATSOEVER.  Tested many times, its as if the copper wires are just not connected to the terminations.  Do these even go through Quality Control before they leave the factory?  Waste of money and time.", "output": "None of them worked.  No functionality at all.", "explanation": "The user did not like the product as it was not having any functionality and the title also states that the product was not useful."}], "Negative Examples": [{"input": "I was very surprised at the high quality of the stitching, the sturdiness of the handles and the padding for my laptop. The price is amazingly low and the look is very good. I am quite happy with this purchase. It fit my MacBook Pro perfectly, with a little bit of room to spare.", "output": "One Star", "explanation": "Here review states that the user has liked the product but the negative title of one star is in contrast to the review body."}, {"input": "Bought cables in 3ft, 6ft and 9ft.  NONE of them worked.  NO FUNCTIONALITY WHATSOEVER.  Tested many times, its as if the copper wires are just not connected to the terminations.  Do these even go through Quality Control before they leave the factory?  Waste of money and time.", "output": "The \"M\" key fell off after three days of light ...", "explanation": "User did not like cables he bought but the title states that \"M\" key fell off after three days of light which does not correctly define review body."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Reviews"], "Instance": {"id": "task1342-8909f0c6a0354f9888dec31f315b932b", "input": "I love this little device.  Yesterday, I was waiting in an ungodly long line at the post office and luckily had my library at my fingertips.  The size of the Kindle makes it easy to transport with you wherever you are.  Also, the 3G internet is a great perk.  I was able to check my email as well as read some articles using google reader in the middle of the post office.  If you like to read, then this is the e-reader you should get.  Use it for books, and think of the internet as just a perk.", "output": ["Extremely pleased"]}, "Instance License": ["Amazon License (https://s3.amazonaws.com/amazon-reviews-pds/license.txt)"], "prediction": "I love this little device"}
+{"id": "task1342-8bca08d4262f466c9cee933cf7d86c6e", "Task": "task1342_amazon_us_reviews_title", "Contributors": "['Vinayak Kothari']", "Source": ["amazon_us_reviews"], "URL": ["https://huggingface.co/datasets/amazon_us_reviews"], "Categories": ["Title Generation"], "Reasoning": [], "Definition": ["Given an Amazon customer review, write a title for the review. The preferred titles are under fifteen words."], "Positive Examples": [{"input": "I was very surprised at the high quality of the stitching, the sturdiness of the handles and the padding for my laptop. The price is amazingly low and the look is very good. I am quite happy with this purchase. It fit my MacBook Pro perfectly, with a little bit of room to spare.", "output": "Pleasantly surprised", "explanation": "The review is positive and the user liked the product very much based on the given review, and the title correctly resembles to review."}, {"input": "Bought cables in 3ft, 6ft and 9ft.  NONE of them worked.  NO FUNCTIONALITY WHATSOEVER.  Tested many times, its as if the copper wires are just not connected to the terminations.  Do these even go through Quality Control before they leave the factory?  Waste of money and time.", "output": "None of them worked.  No functionality at all.", "explanation": "The user did not like the product as it was not having any functionality and the title also states that the product was not useful."}], "Negative Examples": [{"input": "I was very surprised at the high quality of the stitching, the sturdiness of the handles and the padding for my laptop. The price is amazingly low and the look is very good. I am quite happy with this purchase. It fit my MacBook Pro perfectly, with a little bit of room to spare.", "output": "One Star", "explanation": "Here review states that the user has liked the product but the negative title of one star is in contrast to the review body."}, {"input": "Bought cables in 3ft, 6ft and 9ft.  NONE of them worked.  NO FUNCTIONALITY WHATSOEVER.  Tested many times, its as if the copper wires are just not connected to the terminations.  Do these even go through Quality Control before they leave the factory?  Waste of money and time.", "output": "The \"M\" key fell off after three days of light ...", "explanation": "User did not like cables he bought but the title states that \"M\" key fell off after three days of light which does not correctly define review body."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Reviews"], "Instance": {"id": "task1342-8bca08d4262f466c9cee933cf7d86c6e", "input": "The monitor I received as an A0 version but manufactured in July of 2014. I ordered it in October of 2014 so clearly this is current product. I suspect the versions indicated the plant where the monitor was manufactured not the technology in the unit. My monitor has an excellent picture and no buzzing. The only area that I feel needs clarifying is that the monitor can only display WQHD (1440) graphics on Dual Link DVI graphics interfaces with the Dual Link DVI cable or the Displayport. The VGA and HMDI interfaces cannot  go past HD resolution. This resulted in my needing to get a suitable graphics card and cable. This can be harder than it seems as most DVI are single link.  I found an EVGA card with an Nvidia GeForce GT610 GPU with 1 GB of ram works fabulously with my standard HP Pavillion power supply and delivers excellent performance. However, I am not gaming full screen and full resolution most of the time but instead doing Photo editing and CAD work.<br /><br />Bottom line: This is an excellent monitor with a minor restriction.", "output": ["My monitor has an excellent picture and no buzzing"]}, "Instance License": ["Amazon License (https://s3.amazonaws.com/amazon-reviews-pds/license.txt)"], "prediction": "Excellent picture and no buzzing"}
+{"id": "task1342-940bf08db2474b8eb0cc865e9e037f9b", "Task": "task1342_amazon_us_reviews_title", "Contributors": "['Vinayak Kothari']", "Source": ["amazon_us_reviews"], "URL": ["https://huggingface.co/datasets/amazon_us_reviews"], "Categories": ["Title Generation"], "Reasoning": [], "Definition": ["Given an Amazon customer review, write a title for the review. The preferred titles are under fifteen words."], "Positive Examples": [{"input": "I was very surprised at the high quality of the stitching, the sturdiness of the handles and the padding for my laptop. The price is amazingly low and the look is very good. I am quite happy with this purchase. It fit my MacBook Pro perfectly, with a little bit of room to spare.", "output": "Pleasantly surprised", "explanation": "The review is positive and the user liked the product very much based on the given review, and the title correctly resembles to review."}, {"input": "Bought cables in 3ft, 6ft and 9ft.  NONE of them worked.  NO FUNCTIONALITY WHATSOEVER.  Tested many times, its as if the copper wires are just not connected to the terminations.  Do these even go through Quality Control before they leave the factory?  Waste of money and time.", "output": "None of them worked.  No functionality at all.", "explanation": "The user did not like the product as it was not having any functionality and the title also states that the product was not useful."}], "Negative Examples": [{"input": "I was very surprised at the high quality of the stitching, the sturdiness of the handles and the padding for my laptop. The price is amazingly low and the look is very good. I am quite happy with this purchase. It fit my MacBook Pro perfectly, with a little bit of room to spare.", "output": "One Star", "explanation": "Here review states that the user has liked the product but the negative title of one star is in contrast to the review body."}, {"input": "Bought cables in 3ft, 6ft and 9ft.  NONE of them worked.  NO FUNCTIONALITY WHATSOEVER.  Tested many times, its as if the copper wires are just not connected to the terminations.  Do these even go through Quality Control before they leave the factory?  Waste of money and time.", "output": "The \"M\" key fell off after three days of light ...", "explanation": "User did not like cables he bought but the title states that \"M\" key fell off after three days of light which does not correctly define review body."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Reviews"], "Instance": {"id": "task1342-940bf08db2474b8eb0cc865e9e037f9b", "input": "What can I say - everything about this Kindle is great! I have read many books, papers and played games on it and all have been very enjoyable. And when I compared it to other Ebooks the Kindle in my opinion was the better choice. The only thing I wish it had is if you could get it in different colors. Graphite gray and white are the only colors.  If you do decide to buy the Kindle make sure you buy a case for it. I bought the Amazon leather case with the light - the case is kind of expensive but well worth it - you won't be disappointed with it and I especially enjoy the light.", "output": ["An Awesome Ebook."]}, "Instance License": ["Amazon License (https://s3.amazonaws.com/amazon-reviews-pds/license.txt)"], "prediction": "Great!"}
+{"id": "task1342-c62b5103336a4a5da4b80c93554d9bbc", "Task": "task1342_amazon_us_reviews_title", "Contributors": "['Vinayak Kothari']", "Source": ["amazon_us_reviews"], "URL": ["https://huggingface.co/datasets/amazon_us_reviews"], "Categories": ["Title Generation"], "Reasoning": [], "Definition": ["Given an Amazon customer review, write a title for the review. The preferred titles are under fifteen words."], "Positive Examples": [{"input": "I was very surprised at the high quality of the stitching, the sturdiness of the handles and the padding for my laptop. The price is amazingly low and the look is very good. I am quite happy with this purchase. It fit my MacBook Pro perfectly, with a little bit of room to spare.", "output": "Pleasantly surprised", "explanation": "The review is positive and the user liked the product very much based on the given review, and the title correctly resembles to review."}, {"input": "Bought cables in 3ft, 6ft and 9ft.  NONE of them worked.  NO FUNCTIONALITY WHATSOEVER.  Tested many times, its as if the copper wires are just not connected to the terminations.  Do these even go through Quality Control before they leave the factory?  Waste of money and time.", "output": "None of them worked.  No functionality at all.", "explanation": "The user did not like the product as it was not having any functionality and the title also states that the product was not useful."}], "Negative Examples": [{"input": "I was very surprised at the high quality of the stitching, the sturdiness of the handles and the padding for my laptop. The price is amazingly low and the look is very good. I am quite happy with this purchase. It fit my MacBook Pro perfectly, with a little bit of room to spare.", "output": "One Star", "explanation": "Here review states that the user has liked the product but the negative title of one star is in contrast to the review body."}, {"input": "Bought cables in 3ft, 6ft and 9ft.  NONE of them worked.  NO FUNCTIONALITY WHATSOEVER.  Tested many times, its as if the copper wires are just not connected to the terminations.  Do these even go through Quality Control before they leave the factory?  Waste of money and time.", "output": "The \"M\" key fell off after three days of light ...", "explanation": "User did not like cables he bought but the title states that \"M\" key fell off after three days of light which does not correctly define review body."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Reviews"], "Instance": {"id": "task1342-c62b5103336a4a5da4b80c93554d9bbc", "input": "AMAZING! These speakers are so good for what you pay for. If you want to be able to blast music and make it sound rich and have bass this is the best option. With 5,000+ reviews and over 4 stars this is a must! This thing is awesome!", "output": ["Outstanding!"]}, "Instance License": ["Amazon License (https://s3.amazonaws.com/amazon-reviews-pds/license.txt)"], "prediction": "Amazing! These speakers are so good for what they pay for. If you want to be able to blast music and make it sound rich and have bass this is the best option."}
+{"id": "task329-f241c2f855234c589e7281866627da68", "Task": "task329_gap_classification", "Contributors": "['Yeganeh Kordi']", "Source": ["gap"], "URL": ["https://github.com/google-research-datasets/gap-coreference"], "Categories": ["Coreference Resolution"], "Reasoning": [], "Definition": ["In this task, you will be presented with a text, a pronoun from the text, and two candidate names. You should determine what the pronoun refers to and classify the answers into A, B, or Neither. A and B here are referring to option A and option B. Position of the pronoun in the text is showed within two \"_\"s."], "Positive Examples": [{"input": "He grew up in Evanston, Illinois the second oldest of five children including his brothers, Fred and Gordon and sisters, Marge (Peppy) and Marilyn. His high school days were spent at New Trier High School in Winnetka, Illinois. MacKenzie studied with Bernard Leach from 1949 to 1952. _His_ simple, wheel-thrown functional pottery is heavily influenced by the oriental aesthetic of Shoji Hamada and Kanjiro Kawai. <sep>, Pronoun: His <sep>, A: MacKenzie <sep>, B: Bernard Leach", "output": "A", "explanation": "Based on the text, his refers to MacKenzie so option A is correct."}, {"input": "Reb Chaim Yaakov's wife is the sister of Rabbi Moishe Sternbuch, as is the wife of Rabbi Meshulam Dovid Soloveitchik, making the two Rabbis his uncles. Reb Asher's brother Rabbi Shlomo Arieli is the author of a critical edition of the novallae of Rabbi Akiva Eiger. Before _his_ marriage, Rabbi Arieli studied in the Ponevezh Yeshiva headed by Rabbi Shmuel Rozovsky, and he later studied under his father-in-law in the Mirrer Yeshiva. <sep>, Pronoun: his <sep>, A: Reb Asher <sep>, B: Akiva Eiger", "output": "Neither", "explanation": "Based on the text, his refers to Rabbi Arieli, and neither is correct."}, {"input": "Kathleen Nott was born in Camberwell, London. Her father, Philip, was a lithographic printer, and her mother, Ellen, ran a boarding house in Brixton; Kathleen was their third daughter. _She_ was educated at Mary Datchelor Girls' School (now closed), London, before attending King's College, London. <sep>, Pronoun: She <sep>, A: Ellen <sep>, B: Kathleen", "output": "B", "explanation": "Based on the text, she refers to Kathleen, and option B is correct."}], "Negative Examples": [{"input": "He had been reelected to Congress, but resigned in 1990 to accept a post as Ambassador to Brazil. De la Sota again ran for governor of C*rdoba in 1991. Defeated by Governor Angeloz by over 15%, this latter setback was significant because it cost De la Sota much of _his_ support within the Justicialist Party (which was flush with victory in the 1991 mid-terms), leading to President Carlos Menem 's endorsement of a separate party list in C*rdoba for the 1993 mid-term elections, and to De la Sota's failure to regain a seat in Congress. <sep>, Pronoun: his <sep>, A: Angeloz <sep>, B: De la Sota", "output": "Neither", "explanation": "Based on the text, his refers to De la Sota, and Neither is incorrect."}, {"input": "On 19 March 2007, during a campaign appearance for the New South Wales State Election, the then opposition leader Peter Debnam was confronted by Reucassel wearing nothing but Speedos and a baseball cap, making fun of Debnam's campaign appearances in the swimwear. When TV cameras remained focused on Reucassel rather than Mr Debnam, _he_said, ``Sorry, I'm not Peter Debnam, he's over there. <sep>, Pronoun: he <sep>, A: Reucassel <sep>, B: Debnam", "output": "B", "explanation": "Based on the text, he refers to Reucassel, and option B is incorrect."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Wikipedia"], "Instance": {"id": "task329-f241c2f855234c589e7281866627da68", "input": "Coal was first reported in Brunei Darussalam near Muara as early as 1837. in Serai Pimping. The Muara coalmine was first mined commercially in 1883, when William Cowie was given the concession rights to mine the coal in exchange for $1,200 per year. However, Cowie later sold _his_ rights to Rajah Charles Brooke and the Rajah renamed the mine Brooketon (Brooke Town). <sep>, Pronoun: his <sep>, A: Rajah Charles Brooke <sep>, B: Rajah", "output": ["Neither"]}, "Instance License": ["Apache 2.0"], "prediction": "Neither"}
+{"id": "task329-c75f6b713bb844b9929d835c78d916b2", "Task": "task329_gap_classification", "Contributors": "['Yeganeh Kordi']", "Source": ["gap"], "URL": ["https://github.com/google-research-datasets/gap-coreference"], "Categories": ["Coreference Resolution"], "Reasoning": [], "Definition": ["In this task, you will be presented with a text, a pronoun from the text, and two candidate names. You should determine what the pronoun refers to and classify the answers into A, B, or Neither. A and B here are referring to option A and option B. Position of the pronoun in the text is showed within two \"_\"s."], "Positive Examples": [{"input": "He grew up in Evanston, Illinois the second oldest of five children including his brothers, Fred and Gordon and sisters, Marge (Peppy) and Marilyn. His high school days were spent at New Trier High School in Winnetka, Illinois. MacKenzie studied with Bernard Leach from 1949 to 1952. _His_ simple, wheel-thrown functional pottery is heavily influenced by the oriental aesthetic of Shoji Hamada and Kanjiro Kawai. <sep>, Pronoun: His <sep>, A: MacKenzie <sep>, B: Bernard Leach", "output": "A", "explanation": "Based on the text, his refers to MacKenzie so option A is correct."}, {"input": "Reb Chaim Yaakov's wife is the sister of Rabbi Moishe Sternbuch, as is the wife of Rabbi Meshulam Dovid Soloveitchik, making the two Rabbis his uncles. Reb Asher's brother Rabbi Shlomo Arieli is the author of a critical edition of the novallae of Rabbi Akiva Eiger. Before _his_ marriage, Rabbi Arieli studied in the Ponevezh Yeshiva headed by Rabbi Shmuel Rozovsky, and he later studied under his father-in-law in the Mirrer Yeshiva. <sep>, Pronoun: his <sep>, A: Reb Asher <sep>, B: Akiva Eiger", "output": "Neither", "explanation": "Based on the text, his refers to Rabbi Arieli, and neither is correct."}, {"input": "Kathleen Nott was born in Camberwell, London. Her father, Philip, was a lithographic printer, and her mother, Ellen, ran a boarding house in Brixton; Kathleen was their third daughter. _She_ was educated at Mary Datchelor Girls' School (now closed), London, before attending King's College, London. <sep>, Pronoun: She <sep>, A: Ellen <sep>, B: Kathleen", "output": "B", "explanation": "Based on the text, she refers to Kathleen, and option B is correct."}], "Negative Examples": [{"input": "He had been reelected to Congress, but resigned in 1990 to accept a post as Ambassador to Brazil. De la Sota again ran for governor of C*rdoba in 1991. Defeated by Governor Angeloz by over 15%, this latter setback was significant because it cost De la Sota much of _his_ support within the Justicialist Party (which was flush with victory in the 1991 mid-terms), leading to President Carlos Menem 's endorsement of a separate party list in C*rdoba for the 1993 mid-term elections, and to De la Sota's failure to regain a seat in Congress. <sep>, Pronoun: his <sep>, A: Angeloz <sep>, B: De la Sota", "output": "Neither", "explanation": "Based on the text, his refers to De la Sota, and Neither is incorrect."}, {"input": "On 19 March 2007, during a campaign appearance for the New South Wales State Election, the then opposition leader Peter Debnam was confronted by Reucassel wearing nothing but Speedos and a baseball cap, making fun of Debnam's campaign appearances in the swimwear. When TV cameras remained focused on Reucassel rather than Mr Debnam, _he_said, ``Sorry, I'm not Peter Debnam, he's over there. <sep>, Pronoun: he <sep>, A: Reucassel <sep>, B: Debnam", "output": "B", "explanation": "Based on the text, he refers to Reucassel, and option B is incorrect."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Wikipedia"], "Instance": {"id": "task329-c75f6b713bb844b9929d835c78d916b2", "input": "Martha tells Ted he values the wrong things and Ted calls Martha a freeloader. That night she attempts to contact the cult but is greeted by a girl named Marlene Miller. Martha loses her nerve and hangs up. In a flashback at the cult, Martha helps a girl named Sally integrate into the cult. _She_ helps Patrick drug and rape Sally, as had been done to her. <sep>, Pronoun: She <sep>, A: Martha <sep>, B: Sally", "output": ["A"]}, "Instance License": ["Apache 2.0"], "prediction": "A"}
+{"id": "task329-7a61c12a9150439c9ef4c1ed395640b2", "Task": "task329_gap_classification", "Contributors": "['Yeganeh Kordi']", "Source": ["gap"], "URL": ["https://github.com/google-research-datasets/gap-coreference"], "Categories": ["Coreference Resolution"], "Reasoning": [], "Definition": ["In this task, you will be presented with a text, a pronoun from the text, and two candidate names. You should determine what the pronoun refers to and classify the answers into A, B, or Neither. A and B here are referring to option A and option B. Position of the pronoun in the text is showed within two \"_\"s."], "Positive Examples": [{"input": "He grew up in Evanston, Illinois the second oldest of five children including his brothers, Fred and Gordon and sisters, Marge (Peppy) and Marilyn. His high school days were spent at New Trier High School in Winnetka, Illinois. MacKenzie studied with Bernard Leach from 1949 to 1952. _His_ simple, wheel-thrown functional pottery is heavily influenced by the oriental aesthetic of Shoji Hamada and Kanjiro Kawai. <sep>, Pronoun: His <sep>, A: MacKenzie <sep>, B: Bernard Leach", "output": "A", "explanation": "Based on the text, his refers to MacKenzie so option A is correct."}, {"input": "Reb Chaim Yaakov's wife is the sister of Rabbi Moishe Sternbuch, as is the wife of Rabbi Meshulam Dovid Soloveitchik, making the two Rabbis his uncles. Reb Asher's brother Rabbi Shlomo Arieli is the author of a critical edition of the novallae of Rabbi Akiva Eiger. Before _his_ marriage, Rabbi Arieli studied in the Ponevezh Yeshiva headed by Rabbi Shmuel Rozovsky, and he later studied under his father-in-law in the Mirrer Yeshiva. <sep>, Pronoun: his <sep>, A: Reb Asher <sep>, B: Akiva Eiger", "output": "Neither", "explanation": "Based on the text, his refers to Rabbi Arieli, and neither is correct."}, {"input": "Kathleen Nott was born in Camberwell, London. Her father, Philip, was a lithographic printer, and her mother, Ellen, ran a boarding house in Brixton; Kathleen was their third daughter. _She_ was educated at Mary Datchelor Girls' School (now closed), London, before attending King's College, London. <sep>, Pronoun: She <sep>, A: Ellen <sep>, B: Kathleen", "output": "B", "explanation": "Based on the text, she refers to Kathleen, and option B is correct."}], "Negative Examples": [{"input": "He had been reelected to Congress, but resigned in 1990 to accept a post as Ambassador to Brazil. De la Sota again ran for governor of C*rdoba in 1991. Defeated by Governor Angeloz by over 15%, this latter setback was significant because it cost De la Sota much of _his_ support within the Justicialist Party (which was flush with victory in the 1991 mid-terms), leading to President Carlos Menem 's endorsement of a separate party list in C*rdoba for the 1993 mid-term elections, and to De la Sota's failure to regain a seat in Congress. <sep>, Pronoun: his <sep>, A: Angeloz <sep>, B: De la Sota", "output": "Neither", "explanation": "Based on the text, his refers to De la Sota, and Neither is incorrect."}, {"input": "On 19 March 2007, during a campaign appearance for the New South Wales State Election, the then opposition leader Peter Debnam was confronted by Reucassel wearing nothing but Speedos and a baseball cap, making fun of Debnam's campaign appearances in the swimwear. When TV cameras remained focused on Reucassel rather than Mr Debnam, _he_said, ``Sorry, I'm not Peter Debnam, he's over there. <sep>, Pronoun: he <sep>, A: Reucassel <sep>, B: Debnam", "output": "B", "explanation": "Based on the text, he refers to Reucassel, and option B is incorrect."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Wikipedia"], "Instance": {"id": "task329-7a61c12a9150439c9ef4c1ed395640b2", "input": "He drew obsessively from childhood obsessed, both from his own imagination and by copying images that particularly pleased him. 1913 after his return from Ascona, he attended painting school in Munich for a total of eight days. But doubt in his ability was so strong that he hid his work from all but _his_ friend, the writer Oskar Maria Graf (as Schrimpf former baker). <sep>, Pronoun: his <sep>, A: Oskar Maria Graf <sep>, B: Schrimpf", "output": ["Neither"]}, "Instance License": ["Apache 2.0"], "prediction": "A"}
+{"id": "task329-1f72b43ce4a84f739a5a2915fcd82922", "Task": "task329_gap_classification", "Contributors": "['Yeganeh Kordi']", "Source": ["gap"], "URL": ["https://github.com/google-research-datasets/gap-coreference"], "Categories": ["Coreference Resolution"], "Reasoning": [], "Definition": ["In this task, you will be presented with a text, a pronoun from the text, and two candidate names. You should determine what the pronoun refers to and classify the answers into A, B, or Neither. A and B here are referring to option A and option B. Position of the pronoun in the text is showed within two \"_\"s."], "Positive Examples": [{"input": "He grew up in Evanston, Illinois the second oldest of five children including his brothers, Fred and Gordon and sisters, Marge (Peppy) and Marilyn. His high school days were spent at New Trier High School in Winnetka, Illinois. MacKenzie studied with Bernard Leach from 1949 to 1952. _His_ simple, wheel-thrown functional pottery is heavily influenced by the oriental aesthetic of Shoji Hamada and Kanjiro Kawai. <sep>, Pronoun: His <sep>, A: MacKenzie <sep>, B: Bernard Leach", "output": "A", "explanation": "Based on the text, his refers to MacKenzie so option A is correct."}, {"input": "Reb Chaim Yaakov's wife is the sister of Rabbi Moishe Sternbuch, as is the wife of Rabbi Meshulam Dovid Soloveitchik, making the two Rabbis his uncles. Reb Asher's brother Rabbi Shlomo Arieli is the author of a critical edition of the novallae of Rabbi Akiva Eiger. Before _his_ marriage, Rabbi Arieli studied in the Ponevezh Yeshiva headed by Rabbi Shmuel Rozovsky, and he later studied under his father-in-law in the Mirrer Yeshiva. <sep>, Pronoun: his <sep>, A: Reb Asher <sep>, B: Akiva Eiger", "output": "Neither", "explanation": "Based on the text, his refers to Rabbi Arieli, and neither is correct."}, {"input": "Kathleen Nott was born in Camberwell, London. Her father, Philip, was a lithographic printer, and her mother, Ellen, ran a boarding house in Brixton; Kathleen was their third daughter. _She_ was educated at Mary Datchelor Girls' School (now closed), London, before attending King's College, London. <sep>, Pronoun: She <sep>, A: Ellen <sep>, B: Kathleen", "output": "B", "explanation": "Based on the text, she refers to Kathleen, and option B is correct."}], "Negative Examples": [{"input": "He had been reelected to Congress, but resigned in 1990 to accept a post as Ambassador to Brazil. De la Sota again ran for governor of C*rdoba in 1991. Defeated by Governor Angeloz by over 15%, this latter setback was significant because it cost De la Sota much of _his_ support within the Justicialist Party (which was flush with victory in the 1991 mid-terms), leading to President Carlos Menem 's endorsement of a separate party list in C*rdoba for the 1993 mid-term elections, and to De la Sota's failure to regain a seat in Congress. <sep>, Pronoun: his <sep>, A: Angeloz <sep>, B: De la Sota", "output": "Neither", "explanation": "Based on the text, his refers to De la Sota, and Neither is incorrect."}, {"input": "On 19 March 2007, during a campaign appearance for the New South Wales State Election, the then opposition leader Peter Debnam was confronted by Reucassel wearing nothing but Speedos and a baseball cap, making fun of Debnam's campaign appearances in the swimwear. When TV cameras remained focused on Reucassel rather than Mr Debnam, _he_said, ``Sorry, I'm not Peter Debnam, he's over there. <sep>, Pronoun: he <sep>, A: Reucassel <sep>, B: Debnam", "output": "B", "explanation": "Based on the text, he refers to Reucassel, and option B is incorrect."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Wikipedia"], "Instance": {"id": "task329-1f72b43ce4a84f739a5a2915fcd82922", "input": "In Bram Stoker's Dracula (1992), directed by Francis Ford Coppola, Lucy is played by Sadie Frost. Lucy is eroticized much further than her literary incarnation, becoming more than seductive and coquettish, even tempting, and what she says often refers to sex. As a spoiled child of aristocracy, she talks with artlessness and frankness, bordering on the indecent. Unlike _her_ friend Mina, who stays resolute, Lucy's sexual tendencies are to be her downfall. <sep>, Pronoun: her <sep>, A: Mina <sep>, B: Lucy", "output": ["B"]}, "Instance License": ["Apache 2.0"], "prediction": "A"}
+{"id": "task329-129a42586bcd4d3bae176fe9a976db09", "Task": "task329_gap_classification", "Contributors": "['Yeganeh Kordi']", "Source": ["gap"], "URL": ["https://github.com/google-research-datasets/gap-coreference"], "Categories": ["Coreference Resolution"], "Reasoning": [], "Definition": ["In this task, you will be presented with a text, a pronoun from the text, and two candidate names. You should determine what the pronoun refers to and classify the answers into A, B, or Neither. A and B here are referring to option A and option B. Position of the pronoun in the text is showed within two \"_\"s."], "Positive Examples": [{"input": "He grew up in Evanston, Illinois the second oldest of five children including his brothers, Fred and Gordon and sisters, Marge (Peppy) and Marilyn. His high school days were spent at New Trier High School in Winnetka, Illinois. MacKenzie studied with Bernard Leach from 1949 to 1952. _His_ simple, wheel-thrown functional pottery is heavily influenced by the oriental aesthetic of Shoji Hamada and Kanjiro Kawai. <sep>, Pronoun: His <sep>, A: MacKenzie <sep>, B: Bernard Leach", "output": "A", "explanation": "Based on the text, his refers to MacKenzie so option A is correct."}, {"input": "Reb Chaim Yaakov's wife is the sister of Rabbi Moishe Sternbuch, as is the wife of Rabbi Meshulam Dovid Soloveitchik, making the two Rabbis his uncles. Reb Asher's brother Rabbi Shlomo Arieli is the author of a critical edition of the novallae of Rabbi Akiva Eiger. Before _his_ marriage, Rabbi Arieli studied in the Ponevezh Yeshiva headed by Rabbi Shmuel Rozovsky, and he later studied under his father-in-law in the Mirrer Yeshiva. <sep>, Pronoun: his <sep>, A: Reb Asher <sep>, B: Akiva Eiger", "output": "Neither", "explanation": "Based on the text, his refers to Rabbi Arieli, and neither is correct."}, {"input": "Kathleen Nott was born in Camberwell, London. Her father, Philip, was a lithographic printer, and her mother, Ellen, ran a boarding house in Brixton; Kathleen was their third daughter. _She_ was educated at Mary Datchelor Girls' School (now closed), London, before attending King's College, London. <sep>, Pronoun: She <sep>, A: Ellen <sep>, B: Kathleen", "output": "B", "explanation": "Based on the text, she refers to Kathleen, and option B is correct."}], "Negative Examples": [{"input": "He had been reelected to Congress, but resigned in 1990 to accept a post as Ambassador to Brazil. De la Sota again ran for governor of C*rdoba in 1991. Defeated by Governor Angeloz by over 15%, this latter setback was significant because it cost De la Sota much of _his_ support within the Justicialist Party (which was flush with victory in the 1991 mid-terms), leading to President Carlos Menem 's endorsement of a separate party list in C*rdoba for the 1993 mid-term elections, and to De la Sota's failure to regain a seat in Congress. <sep>, Pronoun: his <sep>, A: Angeloz <sep>, B: De la Sota", "output": "Neither", "explanation": "Based on the text, his refers to De la Sota, and Neither is incorrect."}, {"input": "On 19 March 2007, during a campaign appearance for the New South Wales State Election, the then opposition leader Peter Debnam was confronted by Reucassel wearing nothing but Speedos and a baseball cap, making fun of Debnam's campaign appearances in the swimwear. When TV cameras remained focused on Reucassel rather than Mr Debnam, _he_said, ``Sorry, I'm not Peter Debnam, he's over there. <sep>, Pronoun: he <sep>, A: Reucassel <sep>, B: Debnam", "output": "B", "explanation": "Based on the text, he refers to Reucassel, and option B is incorrect."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Wikipedia"], "Instance": {"id": "task329-129a42586bcd4d3bae176fe9a976db09", "input": "I thought the best way to do that was to transfer.'' After Cruthers' decision to leave USMA he called Derek Schooley, the new head coach of RMU Mens Hockey Team. Schooley, formerly assistant coach for Air Force, had recruited Ryan before _his_ decision to attend West Point and was more than happy to take Ryan on the team. <sep>, Pronoun: his <sep>, A: Schooley <sep>, B: Ryan", "output": ["B"]}, "Instance License": ["Apache 2.0"], "prediction": "A"}
+{"id": "task281-936c6407ecc14bd2a998cac04cacfdbe", "Task": "task281_points_of_correspondence", "Contributors": "['Pegah Alipoormolabashi']", "Source": ["points_of_correspondence"], "URL": ["https://github.com/ucfnlp/points-of-correspondence"], "Categories": ["Overlap Extraction"], "Reasoning": [], "Definition": ["You will be given three sentences. Read them, then identify a noun phrase (person, place, or thing) or event that is shared between all three sentences. As the output, write the span of the text corresponding to that phrase in each sentence. Keep the order of the sentences, that is, your answer should look like: 1: *a phras from sentence 1e* 2: *a phras from sentence 2* 3: *a phrase from sentence 3*"], "Positive Examples": [{"input": "1: Four employees of the store have been arrested , but its manager -- herself a woman -- was still at large Saturday , said Goa police superintendent Kartik Kashyap . 2: If convicted , they could spend up to three years in jail , Kashyap said . 3: The four store workers arrested could spend 3 years each in prison if convicted .", "output": "1: Four employees of the store 2: they 3: The four store workers", "explanation": "All three mentioned parts refer to the same entity, the four eployees. \"Of the store\" in first sentence must be included, since it is part of the same noun phrase describing the employees."}, {"input": "1: Stewart said that she and her husband , Joseph Naaman , booked Felix on their Etihad Airways flight from the United Arab Emirates to New York 's John F . Kennedy International Airport on April 1 . 2: The couple said they spent $ 1,200 to ship Felix on the 14-hour flight . 3: Couple spends $ 1,200 to ship their cat , Felix , on a flight from the United Arab Emirates .", "output": "1: their Etihad Airways flight from the United Arab Emirates to New York 's John F . Kennedy International Airport 2: the 14-hour flight 3: a flight from the United Arab Emirates", "explanation": "All the words that are part of the phrase should be mentioned. In this case, mentioning only the \"Etihad Airways flight\" was not enough."}, {"input": "1: But an Arizona official told CNN Bates never trained with the agency . 2:  He did n't come to Arizona ,  the official from the Maricopa County Sheriff 's Office said ,  and he certainly did n't train with us .  3: Maricopa County Sheriff 's Office in Arizona says Robert Bates never trained with them .", "output": "1: never trained 2: did n't train 3: never trained", "explanation": "This is an example where the point of correspondence between three sentences is an event, described by verbs."}], "Negative Examples": [{"input": "1: Stewart said that she and her husband , Joseph Naaman , booked Felix on their Etihad Airways flight from the United Arab Emirates to New York 's John F . Kennedy International Airport on April 1 . 2: The couple said they spent $ 1,200 to ship Felix on the 14-hour flight . 3: Couple spends $ 1,200 to ship their cat , Felix , on a flight from the United Arab Emirates .", "output": "1: she and her husband 2: couple 3: Couple", "explanation": " Mentioning only \"she and her husband\" in sentence 1 would be incorrect, because \"Joseph Naaman\" is part of the same noun phrase. Similarly, mentioning only \"couple\" in sentence 2 would be incorrect; you must mention \"the couple.\""}, {"input": "1: But an Arizona official told CNN Bates never trained with the agency . 2:  He did n't come to Arizona ,  the official from the Maricopa County Sheriff 's Office said ,  and he certainly did n't train with us .  3: Maricopa County Sheriff 's Office in Arizona says Robert Bates never trained with them .", "output": "1: the agency 3: Maricopa County Sheriff 's Office in Arizona", "explanation": "The two noun phrases given in this example are correct, but there's no noun phrase from sentence 2. You should include all three sentences in your response."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["News"], "Instance": {"id": "task281-936c6407ecc14bd2a998cac04cacfdbe", "input": "1: When Moynihan opened the driver 's - side door , the video shows , West sprang out and fired a shot with a pistol at the officer 's face . 2:  His condition is best described as serious but improving ,  Boston police said in a statement . 3: Video shows that the man later shot dead by police in Boston opened fire first .", "output": ["1: Moynihan 2: His 3: police"]}, "Instance License": ["BSD"], "prediction": "Video shows, West sprang out and fired a shot with a pistol at the officer's face."}
+{"id": "task281-2418da355ca54a838ee933a02170afaa", "Task": "task281_points_of_correspondence", "Contributors": "['Pegah Alipoormolabashi']", "Source": ["points_of_correspondence"], "URL": ["https://github.com/ucfnlp/points-of-correspondence"], "Categories": ["Overlap Extraction"], "Reasoning": [], "Definition": ["You will be given three sentences. Read them, then identify a noun phrase (person, place, or thing) or event that is shared between all three sentences. As the output, write the span of the text corresponding to that phrase in each sentence. Keep the order of the sentences, that is, your answer should look like: 1: *a phras from sentence 1e* 2: *a phras from sentence 2* 3: *a phrase from sentence 3*"], "Positive Examples": [{"input": "1: Four employees of the store have been arrested , but its manager -- herself a woman -- was still at large Saturday , said Goa police superintendent Kartik Kashyap . 2: If convicted , they could spend up to three years in jail , Kashyap said . 3: The four store workers arrested could spend 3 years each in prison if convicted .", "output": "1: Four employees of the store 2: they 3: The four store workers", "explanation": "All three mentioned parts refer to the same entity, the four eployees. \"Of the store\" in first sentence must be included, since it is part of the same noun phrase describing the employees."}, {"input": "1: Stewart said that she and her husband , Joseph Naaman , booked Felix on their Etihad Airways flight from the United Arab Emirates to New York 's John F . Kennedy International Airport on April 1 . 2: The couple said they spent $ 1,200 to ship Felix on the 14-hour flight . 3: Couple spends $ 1,200 to ship their cat , Felix , on a flight from the United Arab Emirates .", "output": "1: their Etihad Airways flight from the United Arab Emirates to New York 's John F . Kennedy International Airport 2: the 14-hour flight 3: a flight from the United Arab Emirates", "explanation": "All the words that are part of the phrase should be mentioned. In this case, mentioning only the \"Etihad Airways flight\" was not enough."}, {"input": "1: But an Arizona official told CNN Bates never trained with the agency . 2:  He did n't come to Arizona ,  the official from the Maricopa County Sheriff 's Office said ,  and he certainly did n't train with us .  3: Maricopa County Sheriff 's Office in Arizona says Robert Bates never trained with them .", "output": "1: never trained 2: did n't train 3: never trained", "explanation": "This is an example where the point of correspondence between three sentences is an event, described by verbs."}], "Negative Examples": [{"input": "1: Stewart said that she and her husband , Joseph Naaman , booked Felix on their Etihad Airways flight from the United Arab Emirates to New York 's John F . Kennedy International Airport on April 1 . 2: The couple said they spent $ 1,200 to ship Felix on the 14-hour flight . 3: Couple spends $ 1,200 to ship their cat , Felix , on a flight from the United Arab Emirates .", "output": "1: she and her husband 2: couple 3: Couple", "explanation": " Mentioning only \"she and her husband\" in sentence 1 would be incorrect, because \"Joseph Naaman\" is part of the same noun phrase. Similarly, mentioning only \"couple\" in sentence 2 would be incorrect; you must mention \"the couple.\""}, {"input": "1: But an Arizona official told CNN Bates never trained with the agency . 2:  He did n't come to Arizona ,  the official from the Maricopa County Sheriff 's Office said ,  and he certainly did n't train with us .  3: Maricopa County Sheriff 's Office in Arizona says Robert Bates never trained with them .", "output": "1: the agency 3: Maricopa County Sheriff 's Office in Arizona", "explanation": "The two noun phrases given in this example are correct, but there's no noun phrase from sentence 2. You should include all three sentences in your response."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["News"], "Instance": {"id": "task281-2418da355ca54a838ee933a02170afaa", "input": "1: I would n't , and neither did Ben Affleck , who lobbied producers of a PBS show ,  Finding Your Roots ,  to remove any reference to his great-great-great grandfather Benjamin Cole , a Georgia slave owner in the mid-1800 's , in an episode that looked at Affleck 's family history . 2: And on Tuesday , Affleck , via Facebook , admitted that he had urged Gates to excise any reference to his slave-owning relative . 3: Ben Affleck admits he asked PBS show  Finding Your Roots  to avoid mentioning his slave-owning ancestor .", "output": ["1: Ben Affleck 2: Affleck 3: Ben Affleck", "1: his great-great-great grandfather Benjamin Cole , a Georgia slave owner in the mid-1800 2: his slave-owning relative 3: his slave-owning ancestor", "1: remove 2: excise 3: avoid"]}, "Instance License": ["BSD"], "prediction": "And on Tuesday, Affleck, via Facebook, admitted that he had urged Gates to excise any reference to his slave-owning ancestor."}
+{"id": "task281-1856f4ff4f964fbdb715929e990ac1b8", "Task": "task281_points_of_correspondence", "Contributors": "['Pegah Alipoormolabashi']", "Source": ["points_of_correspondence"], "URL": ["https://github.com/ucfnlp/points-of-correspondence"], "Categories": ["Overlap Extraction"], "Reasoning": [], "Definition": ["You will be given three sentences. Read them, then identify a noun phrase (person, place, or thing) or event that is shared between all three sentences. As the output, write the span of the text corresponding to that phrase in each sentence. Keep the order of the sentences, that is, your answer should look like: 1: *a phras from sentence 1e* 2: *a phras from sentence 2* 3: *a phrase from sentence 3*"], "Positive Examples": [{"input": "1: Four employees of the store have been arrested , but its manager -- herself a woman -- was still at large Saturday , said Goa police superintendent Kartik Kashyap . 2: If convicted , they could spend up to three years in jail , Kashyap said . 3: The four store workers arrested could spend 3 years each in prison if convicted .", "output": "1: Four employees of the store 2: they 3: The four store workers", "explanation": "All three mentioned parts refer to the same entity, the four eployees. \"Of the store\" in first sentence must be included, since it is part of the same noun phrase describing the employees."}, {"input": "1: Stewart said that she and her husband , Joseph Naaman , booked Felix on their Etihad Airways flight from the United Arab Emirates to New York 's John F . Kennedy International Airport on April 1 . 2: The couple said they spent $ 1,200 to ship Felix on the 14-hour flight . 3: Couple spends $ 1,200 to ship their cat , Felix , on a flight from the United Arab Emirates .", "output": "1: their Etihad Airways flight from the United Arab Emirates to New York 's John F . Kennedy International Airport 2: the 14-hour flight 3: a flight from the United Arab Emirates", "explanation": "All the words that are part of the phrase should be mentioned. In this case, mentioning only the \"Etihad Airways flight\" was not enough."}, {"input": "1: But an Arizona official told CNN Bates never trained with the agency . 2:  He did n't come to Arizona ,  the official from the Maricopa County Sheriff 's Office said ,  and he certainly did n't train with us .  3: Maricopa County Sheriff 's Office in Arizona says Robert Bates never trained with them .", "output": "1: never trained 2: did n't train 3: never trained", "explanation": "This is an example where the point of correspondence between three sentences is an event, described by verbs."}], "Negative Examples": [{"input": "1: Stewart said that she and her husband , Joseph Naaman , booked Felix on their Etihad Airways flight from the United Arab Emirates to New York 's John F . Kennedy International Airport on April 1 . 2: The couple said they spent $ 1,200 to ship Felix on the 14-hour flight . 3: Couple spends $ 1,200 to ship their cat , Felix , on a flight from the United Arab Emirates .", "output": "1: she and her husband 2: couple 3: Couple", "explanation": " Mentioning only \"she and her husband\" in sentence 1 would be incorrect, because \"Joseph Naaman\" is part of the same noun phrase. Similarly, mentioning only \"couple\" in sentence 2 would be incorrect; you must mention \"the couple.\""}, {"input": "1: But an Arizona official told CNN Bates never trained with the agency . 2:  He did n't come to Arizona ,  the official from the Maricopa County Sheriff 's Office said ,  and he certainly did n't train with us .  3: Maricopa County Sheriff 's Office in Arizona says Robert Bates never trained with them .", "output": "1: the agency 3: Maricopa County Sheriff 's Office in Arizona", "explanation": "The two noun phrases given in this example are correct, but there's no noun phrase from sentence 2. You should include all three sentences in your response."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["News"], "Instance": {"id": "task281-1856f4ff4f964fbdb715929e990ac1b8", "input": "1: ( CNN ) When ISIS overran their villages near Mosul in August 2014 , a small group of Assyrians , a Middle Eastern minority with a history reaching back more than 4,000 years , picked up weapons and formed their own militia : Dwekh Nawsha --  The Sacrificers .  2: Assyrians belong to the rapidly dwindling Christian population of Iraq -- recent estimates from CAPNI , the largest Christian relief organization in northern Iraq put the number as low as 300,000 compared with 1.5 million 20 years ago -- and many among them see the fight with ISIS as a final battle for survival against the Islamists .  3: Assyrians are an ancient Middle Eastern minority -- they are part of the rapidly dwindling Christian population of Iraq .", "output": ["1: of Assyrians , a Middle Eastern minority with a history reaching back more than 4,000 years 2: Assyrians 3: Assyrians"]}, "Instance License": ["BSD"], "prediction": "( CNN ) When ISIS overran their villages near Mosul in August 2014, a small group of Assyrians, a Middle Eastern minority with a history reaching back more than 4,000 years, picked up weapons and formed their own militia : Dwekh Nawsha -- The Sacrificers."}
+{"id": "task281-bec8786b3fdd415fa931bb98f30da950", "Task": "task281_points_of_correspondence", "Contributors": "['Pegah Alipoormolabashi']", "Source": ["points_of_correspondence"], "URL": ["https://github.com/ucfnlp/points-of-correspondence"], "Categories": ["Overlap Extraction"], "Reasoning": [], "Definition": ["You will be given three sentences. Read them, then identify a noun phrase (person, place, or thing) or event that is shared between all three sentences. As the output, write the span of the text corresponding to that phrase in each sentence. Keep the order of the sentences, that is, your answer should look like: 1: *a phras from sentence 1e* 2: *a phras from sentence 2* 3: *a phrase from sentence 3*"], "Positive Examples": [{"input": "1: Four employees of the store have been arrested , but its manager -- herself a woman -- was still at large Saturday , said Goa police superintendent Kartik Kashyap . 2: If convicted , they could spend up to three years in jail , Kashyap said . 3: The four store workers arrested could spend 3 years each in prison if convicted .", "output": "1: Four employees of the store 2: they 3: The four store workers", "explanation": "All three mentioned parts refer to the same entity, the four eployees. \"Of the store\" in first sentence must be included, since it is part of the same noun phrase describing the employees."}, {"input": "1: Stewart said that she and her husband , Joseph Naaman , booked Felix on their Etihad Airways flight from the United Arab Emirates to New York 's John F . Kennedy International Airport on April 1 . 2: The couple said they spent $ 1,200 to ship Felix on the 14-hour flight . 3: Couple spends $ 1,200 to ship their cat , Felix , on a flight from the United Arab Emirates .", "output": "1: their Etihad Airways flight from the United Arab Emirates to New York 's John F . Kennedy International Airport 2: the 14-hour flight 3: a flight from the United Arab Emirates", "explanation": "All the words that are part of the phrase should be mentioned. In this case, mentioning only the \"Etihad Airways flight\" was not enough."}, {"input": "1: But an Arizona official told CNN Bates never trained with the agency . 2:  He did n't come to Arizona ,  the official from the Maricopa County Sheriff 's Office said ,  and he certainly did n't train with us .  3: Maricopa County Sheriff 's Office in Arizona says Robert Bates never trained with them .", "output": "1: never trained 2: did n't train 3: never trained", "explanation": "This is an example where the point of correspondence between three sentences is an event, described by verbs."}], "Negative Examples": [{"input": "1: Stewart said that she and her husband , Joseph Naaman , booked Felix on their Etihad Airways flight from the United Arab Emirates to New York 's John F . Kennedy International Airport on April 1 . 2: The couple said they spent $ 1,200 to ship Felix on the 14-hour flight . 3: Couple spends $ 1,200 to ship their cat , Felix , on a flight from the United Arab Emirates .", "output": "1: she and her husband 2: couple 3: Couple", "explanation": " Mentioning only \"she and her husband\" in sentence 1 would be incorrect, because \"Joseph Naaman\" is part of the same noun phrase. Similarly, mentioning only \"couple\" in sentence 2 would be incorrect; you must mention \"the couple.\""}, {"input": "1: But an Arizona official told CNN Bates never trained with the agency . 2:  He did n't come to Arizona ,  the official from the Maricopa County Sheriff 's Office said ,  and he certainly did n't train with us .  3: Maricopa County Sheriff 's Office in Arizona says Robert Bates never trained with them .", "output": "1: the agency 3: Maricopa County Sheriff 's Office in Arizona", "explanation": "The two noun phrases given in this example are correct, but there's no noun phrase from sentence 2. You should include all three sentences in your response."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["News"], "Instance": {"id": "task281-bec8786b3fdd415fa931bb98f30da950", "input": "1: The decimation of our people , too , was reduced to a footnote -- if we were lucky -- in tomes about World War I , when more than one million Armenians were killed during the last days of the Ottoman Empire . 2: As Kim Kardashian , sister Khloe and their two cousins recently toured Armenia -- on the eve of the 100th anniversary of the mass killings , which is marked on April 24 -- they spotlighted a humanitarian crime that Pope Francis recently called  the first genocide of the 20th century .  3: Dawn MacKeen : 2015 marks 100th anniversary of slaughter of Armenians by Ottoman Empire . Kim Kardashian has used fame to spotlight this .", "output": ["1: more than one million Armenians were killed 2: the mass killings 3: slaughter of Armenians by Ottoman Empire"]}, "Instance License": ["BSD"], "prediction": "Dawn MacKeen : 2015 marks 100th anniversary of slaughter of Armenians by Ottoman Empire"}
+{"id": "task281-d52e67b97a8949639e02a3e4d0d6101b", "Task": "task281_points_of_correspondence", "Contributors": "['Pegah Alipoormolabashi']", "Source": ["points_of_correspondence"], "URL": ["https://github.com/ucfnlp/points-of-correspondence"], "Categories": ["Overlap Extraction"], "Reasoning": [], "Definition": ["You will be given three sentences. Read them, then identify a noun phrase (person, place, or thing) or event that is shared between all three sentences. As the output, write the span of the text corresponding to that phrase in each sentence. Keep the order of the sentences, that is, your answer should look like: 1: *a phras from sentence 1e* 2: *a phras from sentence 2* 3: *a phrase from sentence 3*"], "Positive Examples": [{"input": "1: Four employees of the store have been arrested , but its manager -- herself a woman -- was still at large Saturday , said Goa police superintendent Kartik Kashyap . 2: If convicted , they could spend up to three years in jail , Kashyap said . 3: The four store workers arrested could spend 3 years each in prison if convicted .", "output": "1: Four employees of the store 2: they 3: The four store workers", "explanation": "All three mentioned parts refer to the same entity, the four eployees. \"Of the store\" in first sentence must be included, since it is part of the same noun phrase describing the employees."}, {"input": "1: Stewart said that she and her husband , Joseph Naaman , booked Felix on their Etihad Airways flight from the United Arab Emirates to New York 's John F . Kennedy International Airport on April 1 . 2: The couple said they spent $ 1,200 to ship Felix on the 14-hour flight . 3: Couple spends $ 1,200 to ship their cat , Felix , on a flight from the United Arab Emirates .", "output": "1: their Etihad Airways flight from the United Arab Emirates to New York 's John F . Kennedy International Airport 2: the 14-hour flight 3: a flight from the United Arab Emirates", "explanation": "All the words that are part of the phrase should be mentioned. In this case, mentioning only the \"Etihad Airways flight\" was not enough."}, {"input": "1: But an Arizona official told CNN Bates never trained with the agency . 2:  He did n't come to Arizona ,  the official from the Maricopa County Sheriff 's Office said ,  and he certainly did n't train with us .  3: Maricopa County Sheriff 's Office in Arizona says Robert Bates never trained with them .", "output": "1: never trained 2: did n't train 3: never trained", "explanation": "This is an example where the point of correspondence between three sentences is an event, described by verbs."}], "Negative Examples": [{"input": "1: Stewart said that she and her husband , Joseph Naaman , booked Felix on their Etihad Airways flight from the United Arab Emirates to New York 's John F . Kennedy International Airport on April 1 . 2: The couple said they spent $ 1,200 to ship Felix on the 14-hour flight . 3: Couple spends $ 1,200 to ship their cat , Felix , on a flight from the United Arab Emirates .", "output": "1: she and her husband 2: couple 3: Couple", "explanation": " Mentioning only \"she and her husband\" in sentence 1 would be incorrect, because \"Joseph Naaman\" is part of the same noun phrase. Similarly, mentioning only \"couple\" in sentence 2 would be incorrect; you must mention \"the couple.\""}, {"input": "1: But an Arizona official told CNN Bates never trained with the agency . 2:  He did n't come to Arizona ,  the official from the Maricopa County Sheriff 's Office said ,  and he certainly did n't train with us .  3: Maricopa County Sheriff 's Office in Arizona says Robert Bates never trained with them .", "output": "1: the agency 3: Maricopa County Sheriff 's Office in Arizona", "explanation": "The two noun phrases given in this example are correct, but there's no noun phrase from sentence 2. You should include all three sentences in your response."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["News"], "Instance": {"id": "task281-d52e67b97a8949639e02a3e4d0d6101b", "input": "1: Later that month , the ICC opened a preliminary examination into the situation in Palestinian territories , paving the way for possible war crimes investigations against Israelis . 2: Israel and the United States , neither of which is an ICC member , opposed the Palestinians ' efforts to join the body . 3: Israel and the United States opposed the move , which could open the door to war crimes investigations against Israelis .", "output": ["1: Israelis 2: Israel 3: Israelis"]}, "Instance License": ["BSD"], "prediction": "1: Later that month, the ICC opened a preliminary examination into the situation in Palestinian territories, paving the way for possible war crimes investigations against Israelis 2: Israel and the United States, neither of which is an ICC member, opposed the Palestinians'efforts to join the body 3: Israel and the United States"}
+{"id": "task036-fcb1706f71934d34a8d3d82b29ae17f0", "Task": "task036_qasc_topic_word_to_generate_related_fact", "Contributors": "['Swaroop Mishra', 'Daniel Khashabi']", "Source": ["qasc"], "URL": ["https://allenai.org/data/qasc"], "Categories": ["Keyword Tagging"], "Reasoning": [], "Definition": ["In this task, you need to write a topic word from the given fact. The topic word must have at least one word overlap with the given fact. The topic word often involves adding a new word from a related concept. In your topic word, use at least one word from the given fact. Topic words with two or more words work best."], "Positive Examples": [{"input": "Fact: pesticides cause pollution.", "output": "pollution harms.", "explanation": "This is a good topic word, because it contains one overlapping word \"pollution\"."}, {"input": "Fact: pesticides cause pollution.", "output": "modern farming pesticide.", "explanation": "The word \"pesticide\" is the overlapping word."}, {"input": "Fact: a solar panel converts sunlight into electricity.", "output": "sunlight sun.", "explanation": "The word \"sunlight\" is the overlapping word."}, {"input": "Fact: running requires a lot of energy.", "output": "marathon running.", "explanation": "The word \"running\" is the overlapping word."}, {"input": "Fact: soil is formed by rocks eroding.", "output": "rain erode rock.", "explanation": "The word \"erode rock\" is the overlapping word."}, {"input": "Fact: a plant requires water for survival.", "output": "rain water.", "explanation": "The word \"water\" is the overlapping word."}, {"input": "Fact: a radio converts electrical energy into vibrations.", "output": "vibrations sound.", "explanation": "The word \"vibrations\" is the overlapping word."}, {"input": "Fact: habitat destruction causes animals to move to find shelter in another habitat.", "output": "chopping down trees habitat destruction.", "explanation": "The word \"habitat destruction\" is the overlapping word."}, {"input": "Fact: a protractor is used for measuring the angles of a triangular object.", "output": "prism triangular.", "explanation": "The word \"triangular\" is the overlapping word."}, {"input": "Fact: lightning can cause a forest fire.", "output": "forest fire harms.", "explanation": "The word \"forest fire\" is the overlapping word."}], "Negative Examples": [{"input": "Fact: pesticides cause pollution.", "output": "computer harms.", "explanation": "This is a bad topic word, because it has no overlapping word with the given fact."}, {"input": "Fact: pesticides cause pollution.", "output": "toopaste helps.", "explanation": "This is a bad topic word, because it has no overlapping word with the given fact."}, {"input": "Fact: a solar panel converts sunlight into electricity.", "output": "moon around earth.", "explanation": "Even thought the topic seems related, this is a bad topic word, because it has no overlapping word with the given fact."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Natural Science"], "Instance": {"id": "task036-fcb1706f71934d34a8d3d82b29ae17f0", "input": "Fact: folding an object causes that object to change shape.", "output": ["folding an object.", "folding chair.", "folding objects.", "folding origami.", "folding paper origami.", "origami fold.", "solid objects."]}, "Instance License": ["CC BY 4.0"], "prediction": "folds an object"}
+{"id": "task036-952b8d7f9f154ea2b193e720fc9f34c3", "Task": "task036_qasc_topic_word_to_generate_related_fact", "Contributors": "['Swaroop Mishra', 'Daniel Khashabi']", "Source": ["qasc"], "URL": ["https://allenai.org/data/qasc"], "Categories": ["Keyword Tagging"], "Reasoning": [], "Definition": ["In this task, you need to write a topic word from the given fact. The topic word must have at least one word overlap with the given fact. The topic word often involves adding a new word from a related concept. In your topic word, use at least one word from the given fact. Topic words with two or more words work best."], "Positive Examples": [{"input": "Fact: pesticides cause pollution.", "output": "pollution harms.", "explanation": "This is a good topic word, because it contains one overlapping word \"pollution\"."}, {"input": "Fact: pesticides cause pollution.", "output": "modern farming pesticide.", "explanation": "The word \"pesticide\" is the overlapping word."}, {"input": "Fact: a solar panel converts sunlight into electricity.", "output": "sunlight sun.", "explanation": "The word \"sunlight\" is the overlapping word."}, {"input": "Fact: running requires a lot of energy.", "output": "marathon running.", "explanation": "The word \"running\" is the overlapping word."}, {"input": "Fact: soil is formed by rocks eroding.", "output": "rain erode rock.", "explanation": "The word \"erode rock\" is the overlapping word."}, {"input": "Fact: a plant requires water for survival.", "output": "rain water.", "explanation": "The word \"water\" is the overlapping word."}, {"input": "Fact: a radio converts electrical energy into vibrations.", "output": "vibrations sound.", "explanation": "The word \"vibrations\" is the overlapping word."}, {"input": "Fact: habitat destruction causes animals to move to find shelter in another habitat.", "output": "chopping down trees habitat destruction.", "explanation": "The word \"habitat destruction\" is the overlapping word."}, {"input": "Fact: a protractor is used for measuring the angles of a triangular object.", "output": "prism triangular.", "explanation": "The word \"triangular\" is the overlapping word."}, {"input": "Fact: lightning can cause a forest fire.", "output": "forest fire harms.", "explanation": "The word \"forest fire\" is the overlapping word."}], "Negative Examples": [{"input": "Fact: pesticides cause pollution.", "output": "computer harms.", "explanation": "This is a bad topic word, because it has no overlapping word with the given fact."}, {"input": "Fact: pesticides cause pollution.", "output": "toopaste helps.", "explanation": "This is a bad topic word, because it has no overlapping word with the given fact."}, {"input": "Fact: a solar panel converts sunlight into electricity.", "output": "moon around earth.", "explanation": "Even thought the topic seems related, this is a bad topic word, because it has no overlapping word with the given fact."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Natural Science"], "Instance": {"id": "task036-952b8d7f9f154ea2b193e720fc9f34c3", "input": "Fact: a balance is used for measuring mass of an object.", "output": ["a balance measure weight.", "balance mass.", "mass grams.", "mass kilograms.", "mass of an object.", "measuring mass units.", "object mass grams."]}, "Instance License": ["CC BY 4.0"], "prediction": "a balance"}
+{"id": "task036-a9328252a30f49678e4e8ba2c4dbe750", "Task": "task036_qasc_topic_word_to_generate_related_fact", "Contributors": "['Swaroop Mishra', 'Daniel Khashabi']", "Source": ["qasc"], "URL": ["https://allenai.org/data/qasc"], "Categories": ["Keyword Tagging"], "Reasoning": [], "Definition": ["In this task, you need to write a topic word from the given fact. The topic word must have at least one word overlap with the given fact. The topic word often involves adding a new word from a related concept. In your topic word, use at least one word from the given fact. Topic words with two or more words work best."], "Positive Examples": [{"input": "Fact: pesticides cause pollution.", "output": "pollution harms.", "explanation": "This is a good topic word, because it contains one overlapping word \"pollution\"."}, {"input": "Fact: pesticides cause pollution.", "output": "modern farming pesticide.", "explanation": "The word \"pesticide\" is the overlapping word."}, {"input": "Fact: a solar panel converts sunlight into electricity.", "output": "sunlight sun.", "explanation": "The word \"sunlight\" is the overlapping word."}, {"input": "Fact: running requires a lot of energy.", "output": "marathon running.", "explanation": "The word \"running\" is the overlapping word."}, {"input": "Fact: soil is formed by rocks eroding.", "output": "rain erode rock.", "explanation": "The word \"erode rock\" is the overlapping word."}, {"input": "Fact: a plant requires water for survival.", "output": "rain water.", "explanation": "The word \"water\" is the overlapping word."}, {"input": "Fact: a radio converts electrical energy into vibrations.", "output": "vibrations sound.", "explanation": "The word \"vibrations\" is the overlapping word."}, {"input": "Fact: habitat destruction causes animals to move to find shelter in another habitat.", "output": "chopping down trees habitat destruction.", "explanation": "The word \"habitat destruction\" is the overlapping word."}, {"input": "Fact: a protractor is used for measuring the angles of a triangular object.", "output": "prism triangular.", "explanation": "The word \"triangular\" is the overlapping word."}, {"input": "Fact: lightning can cause a forest fire.", "output": "forest fire harms.", "explanation": "The word \"forest fire\" is the overlapping word."}], "Negative Examples": [{"input": "Fact: pesticides cause pollution.", "output": "computer harms.", "explanation": "This is a bad topic word, because it has no overlapping word with the given fact."}, {"input": "Fact: pesticides cause pollution.", "output": "toopaste helps.", "explanation": "This is a bad topic word, because it has no overlapping word with the given fact."}, {"input": "Fact: a solar panel converts sunlight into electricity.", "output": "moon around earth.", "explanation": "Even thought the topic seems related, this is a bad topic word, because it has no overlapping word with the given fact."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Natural Science"], "Instance": {"id": "task036-a9328252a30f49678e4e8ba2c4dbe750", "input": "Fact: Sweating reduces body heat.", "output": ["\"body heat\" reduces sweating.", "Sweating is.", "body heat necessary.", "body heat.", "sweat evaporation cooling.", "sweating body heat.", "sweating body.", "sweating perspiration.", "sweating perspire.", "sweating water.", "sweating."]}, "Instance License": ["CC BY 4.0"], "prediction": "sweating"}
+{"id": "task036-726bb202e1f24c759838cf98242acab7", "Task": "task036_qasc_topic_word_to_generate_related_fact", "Contributors": "['Swaroop Mishra', 'Daniel Khashabi']", "Source": ["qasc"], "URL": ["https://allenai.org/data/qasc"], "Categories": ["Keyword Tagging"], "Reasoning": [], "Definition": ["In this task, you need to write a topic word from the given fact. The topic word must have at least one word overlap with the given fact. The topic word often involves adding a new word from a related concept. In your topic word, use at least one word from the given fact. Topic words with two or more words work best."], "Positive Examples": [{"input": "Fact: pesticides cause pollution.", "output": "pollution harms.", "explanation": "This is a good topic word, because it contains one overlapping word \"pollution\"."}, {"input": "Fact: pesticides cause pollution.", "output": "modern farming pesticide.", "explanation": "The word \"pesticide\" is the overlapping word."}, {"input": "Fact: a solar panel converts sunlight into electricity.", "output": "sunlight sun.", "explanation": "The word \"sunlight\" is the overlapping word."}, {"input": "Fact: running requires a lot of energy.", "output": "marathon running.", "explanation": "The word \"running\" is the overlapping word."}, {"input": "Fact: soil is formed by rocks eroding.", "output": "rain erode rock.", "explanation": "The word \"erode rock\" is the overlapping word."}, {"input": "Fact: a plant requires water for survival.", "output": "rain water.", "explanation": "The word \"water\" is the overlapping word."}, {"input": "Fact: a radio converts electrical energy into vibrations.", "output": "vibrations sound.", "explanation": "The word \"vibrations\" is the overlapping word."}, {"input": "Fact: habitat destruction causes animals to move to find shelter in another habitat.", "output": "chopping down trees habitat destruction.", "explanation": "The word \"habitat destruction\" is the overlapping word."}, {"input": "Fact: a protractor is used for measuring the angles of a triangular object.", "output": "prism triangular.", "explanation": "The word \"triangular\" is the overlapping word."}, {"input": "Fact: lightning can cause a forest fire.", "output": "forest fire harms.", "explanation": "The word \"forest fire\" is the overlapping word."}], "Negative Examples": [{"input": "Fact: pesticides cause pollution.", "output": "computer harms.", "explanation": "This is a bad topic word, because it has no overlapping word with the given fact."}, {"input": "Fact: pesticides cause pollution.", "output": "toopaste helps.", "explanation": "This is a bad topic word, because it has no overlapping word with the given fact."}, {"input": "Fact: a solar panel converts sunlight into electricity.", "output": "moon around earth.", "explanation": "Even thought the topic seems related, this is a bad topic word, because it has no overlapping word with the given fact."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Natural Science"], "Instance": {"id": "task036-726bb202e1f24c759838cf98242acab7", "input": "Fact: a black hole is formed by a high-mass star collapses.", "output": ["black hole.", "collapsed stars.", "high mass star.", "mass star.", "star celestial body.", "star collapse.", "star sun.", "why a star collapses."]}, "Instance License": ["CC BY 4.0"], "prediction": "a black hole"}
+{"id": "task036-be679ce566fb422f8575765a5fccb1b1", "Task": "task036_qasc_topic_word_to_generate_related_fact", "Contributors": "['Swaroop Mishra', 'Daniel Khashabi']", "Source": ["qasc"], "URL": ["https://allenai.org/data/qasc"], "Categories": ["Keyword Tagging"], "Reasoning": [], "Definition": ["In this task, you need to write a topic word from the given fact. The topic word must have at least one word overlap with the given fact. The topic word often involves adding a new word from a related concept. In your topic word, use at least one word from the given fact. Topic words with two or more words work best."], "Positive Examples": [{"input": "Fact: pesticides cause pollution.", "output": "pollution harms.", "explanation": "This is a good topic word, because it contains one overlapping word \"pollution\"."}, {"input": "Fact: pesticides cause pollution.", "output": "modern farming pesticide.", "explanation": "The word \"pesticide\" is the overlapping word."}, {"input": "Fact: a solar panel converts sunlight into electricity.", "output": "sunlight sun.", "explanation": "The word \"sunlight\" is the overlapping word."}, {"input": "Fact: running requires a lot of energy.", "output": "marathon running.", "explanation": "The word \"running\" is the overlapping word."}, {"input": "Fact: soil is formed by rocks eroding.", "output": "rain erode rock.", "explanation": "The word \"erode rock\" is the overlapping word."}, {"input": "Fact: a plant requires water for survival.", "output": "rain water.", "explanation": "The word \"water\" is the overlapping word."}, {"input": "Fact: a radio converts electrical energy into vibrations.", "output": "vibrations sound.", "explanation": "The word \"vibrations\" is the overlapping word."}, {"input": "Fact: habitat destruction causes animals to move to find shelter in another habitat.", "output": "chopping down trees habitat destruction.", "explanation": "The word \"habitat destruction\" is the overlapping word."}, {"input": "Fact: a protractor is used for measuring the angles of a triangular object.", "output": "prism triangular.", "explanation": "The word \"triangular\" is the overlapping word."}, {"input": "Fact: lightning can cause a forest fire.", "output": "forest fire harms.", "explanation": "The word \"forest fire\" is the overlapping word."}], "Negative Examples": [{"input": "Fact: pesticides cause pollution.", "output": "computer harms.", "explanation": "This is a bad topic word, because it has no overlapping word with the given fact."}, {"input": "Fact: pesticides cause pollution.", "output": "toopaste helps.", "explanation": "This is a bad topic word, because it has no overlapping word with the given fact."}, {"input": "Fact: a solar panel converts sunlight into electricity.", "output": "moon around earth.", "explanation": "Even thought the topic seems related, this is a bad topic word, because it has no overlapping word with the given fact."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Natural Science"], "Instance": {"id": "task036-be679ce566fb422f8575765a5fccb1b1", "input": "Fact: hurricanes convert heat energy into mechanical energy.", "output": ["hurricane is a.", "hurricane saffir-simpson.", "hurricanes damage buildings.", "hurricanes.", "hurricans.", "mechanical energy and heat energy.", "mechanical energy."]}, "Instance License": ["CC BY 4.0"], "prediction": "hurricanes convert heat energy into mechanical energy"}
+{"id": "task1554-1398238a733441398f12b5ee795e05fe", "Task": "task1554_scitail_classification", "Contributors": "['Nishtha Bhimte']", "Source": ["scitail"], "URL": ["http://data.allenai.org.s3.amazonaws.com/downloads/SciTailV1.1.zip"], "Categories": ["Textual Entailment"], "Reasoning": ["Textual Entailment -> Deductive Reasoning"], "Definition": ["In this task, you are given two statements. The task is to output whether a given textual premise, i.e. Statement 2, entails or implies a given scientific fact, i.e. Statement 1. The output should be 'entails' if Statement 2 supports Statement 1 and should be 'neutral' otherwise."], "Positive Examples": [{"input": "Sentence 1: The sum of all chemical reactions that take place within an organism is known as metabolism. Sentence 2: Metabolism is the sum total of all chemical reactions performed by an organism.", "output": "entails", "explanation": "Sentence 2 gives out supporting information about the Metabolism hence it is correct"}, {"input": "Sentence 1: The endocrine system produces most of the hormones that regulate body functions. Sentence 2: Your endocrine glands produce hormones that control all your body functions.", "output": "entails", "explanation": "Sentence 2 explains and supports Statement 1 by explaining which part of the system produces the hormones, and hence is correct "}, {"input": "Sentence 1: Warm and humid temperature and moisture conditions describe an air mass that originates over the Atlantic ocean near the equator. Sentence 2: Maritime tropical air Warm, humid air mass that forms over tropical and subtropical oceans.", "output": "neutral", "explanation": "Sentence 2 talks about Maritime tropical air which is completely disjoint from the fact stated in Statement 1 about the air mass near the equator and hence the classification is correct."}], "Negative Examples": [{"input": "Sentence 1: A fewer predators is most likely to cause the number of rabbits living in an area to increase. Sentence 2: A predator of rodents, rabbits, birds and the like, this is a sizeable snake.", "output": "entails", "explanation": "Sentence 2 doesn't give out more information about the Sentence 1 or support the fact stated in Statement 1 but list out one of the predator. The output has been wrongly classified it as entails and hence is wrong."}, {"input": "Sentence 1: Genes are composed of dna. Sentence 2: Composed of DNA, genes are the basic unit of inheritance and provide the instruction manual for how to make the body function.", "output": "neutral", "explanation": "Sentence 2 gives out more information about the dna but is marked neutral, hence it is incorrect"}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Web", "Natural Science -> School Science Textbooks"], "Instance": {"id": "task1554-1398238a733441398f12b5ee795e05fe", "input": "Sentence 1: Motion can be defined simply as a change in position. Sentence 2: Motion can be determined by change in position over time.", "output": ["entails"]}, "Instance License": ["Apache 2.0"], "prediction": "entails"}
+{"id": "task1554-e27ba6f94a1d49c5a3cc1e529e443d57", "Task": "task1554_scitail_classification", "Contributors": "['Nishtha Bhimte']", "Source": ["scitail"], "URL": ["http://data.allenai.org.s3.amazonaws.com/downloads/SciTailV1.1.zip"], "Categories": ["Textual Entailment"], "Reasoning": ["Textual Entailment -> Deductive Reasoning"], "Definition": ["In this task, you are given two statements. The task is to output whether a given textual premise, i.e. Statement 2, entails or implies a given scientific fact, i.e. Statement 1. The output should be 'entails' if Statement 2 supports Statement 1 and should be 'neutral' otherwise."], "Positive Examples": [{"input": "Sentence 1: The sum of all chemical reactions that take place within an organism is known as metabolism. Sentence 2: Metabolism is the sum total of all chemical reactions performed by an organism.", "output": "entails", "explanation": "Sentence 2 gives out supporting information about the Metabolism hence it is correct"}, {"input": "Sentence 1: The endocrine system produces most of the hormones that regulate body functions. Sentence 2: Your endocrine glands produce hormones that control all your body functions.", "output": "entails", "explanation": "Sentence 2 explains and supports Statement 1 by explaining which part of the system produces the hormones, and hence is correct "}, {"input": "Sentence 1: Warm and humid temperature and moisture conditions describe an air mass that originates over the Atlantic ocean near the equator. Sentence 2: Maritime tropical air Warm, humid air mass that forms over tropical and subtropical oceans.", "output": "neutral", "explanation": "Sentence 2 talks about Maritime tropical air which is completely disjoint from the fact stated in Statement 1 about the air mass near the equator and hence the classification is correct."}], "Negative Examples": [{"input": "Sentence 1: A fewer predators is most likely to cause the number of rabbits living in an area to increase. Sentence 2: A predator of rodents, rabbits, birds and the like, this is a sizeable snake.", "output": "entails", "explanation": "Sentence 2 doesn't give out more information about the Sentence 1 or support the fact stated in Statement 1 but list out one of the predator. The output has been wrongly classified it as entails and hence is wrong."}, {"input": "Sentence 1: Genes are composed of dna. Sentence 2: Composed of DNA, genes are the basic unit of inheritance and provide the instruction manual for how to make the body function.", "output": "neutral", "explanation": "Sentence 2 gives out more information about the dna but is marked neutral, hence it is incorrect"}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Web", "Natural Science -> School Science Textbooks"], "Instance": {"id": "task1554-e27ba6f94a1d49c5a3cc1e529e443d57", "input": "Sentence 1: Range is the term for the horizontal displacement of a projectile from its starting point. Sentence 2: These range from prehistoric projectile points to jewelry made from shells and bone.", "output": ["neutral"]}, "Instance License": ["Apache 2.0"], "prediction": "neutral"}
+{"id": "task1554-2ed050fe000d40cd8f0b60e15f66838f", "Task": "task1554_scitail_classification", "Contributors": "['Nishtha Bhimte']", "Source": ["scitail"], "URL": ["http://data.allenai.org.s3.amazonaws.com/downloads/SciTailV1.1.zip"], "Categories": ["Textual Entailment"], "Reasoning": ["Textual Entailment -> Deductive Reasoning"], "Definition": ["In this task, you are given two statements. The task is to output whether a given textual premise, i.e. Statement 2, entails or implies a given scientific fact, i.e. Statement 1. The output should be 'entails' if Statement 2 supports Statement 1 and should be 'neutral' otherwise."], "Positive Examples": [{"input": "Sentence 1: The sum of all chemical reactions that take place within an organism is known as metabolism. Sentence 2: Metabolism is the sum total of all chemical reactions performed by an organism.", "output": "entails", "explanation": "Sentence 2 gives out supporting information about the Metabolism hence it is correct"}, {"input": "Sentence 1: The endocrine system produces most of the hormones that regulate body functions. Sentence 2: Your endocrine glands produce hormones that control all your body functions.", "output": "entails", "explanation": "Sentence 2 explains and supports Statement 1 by explaining which part of the system produces the hormones, and hence is correct "}, {"input": "Sentence 1: Warm and humid temperature and moisture conditions describe an air mass that originates over the Atlantic ocean near the equator. Sentence 2: Maritime tropical air Warm, humid air mass that forms over tropical and subtropical oceans.", "output": "neutral", "explanation": "Sentence 2 talks about Maritime tropical air which is completely disjoint from the fact stated in Statement 1 about the air mass near the equator and hence the classification is correct."}], "Negative Examples": [{"input": "Sentence 1: A fewer predators is most likely to cause the number of rabbits living in an area to increase. Sentence 2: A predator of rodents, rabbits, birds and the like, this is a sizeable snake.", "output": "entails", "explanation": "Sentence 2 doesn't give out more information about the Sentence 1 or support the fact stated in Statement 1 but list out one of the predator. The output has been wrongly classified it as entails and hence is wrong."}, {"input": "Sentence 1: Genes are composed of dna. Sentence 2: Composed of DNA, genes are the basic unit of inheritance and provide the instruction manual for how to make the body function.", "output": "neutral", "explanation": "Sentence 2 gives out more information about the dna but is marked neutral, hence it is incorrect"}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Web", "Natural Science -> School Science Textbooks"], "Instance": {"id": "task1554-2ed050fe000d40cd8f0b60e15f66838f", "input": "Sentence 1: A complex machine is described by: it is made of more than one simple machine. Sentence 2: A turing machine is a simple theoritical machine that should be able to solve any problem that a more complex machine can, and hence, is used in proofs on complexity theory.", "output": ["neutral"]}, "Instance License": ["Apache 2.0"], "prediction": "entails"}
+{"id": "task1554-d004b4c91a784306ad7385e7b868e471", "Task": "task1554_scitail_classification", "Contributors": "['Nishtha Bhimte']", "Source": ["scitail"], "URL": ["http://data.allenai.org.s3.amazonaws.com/downloads/SciTailV1.1.zip"], "Categories": ["Textual Entailment"], "Reasoning": ["Textual Entailment -> Deductive Reasoning"], "Definition": ["In this task, you are given two statements. The task is to output whether a given textual premise, i.e. Statement 2, entails or implies a given scientific fact, i.e. Statement 1. The output should be 'entails' if Statement 2 supports Statement 1 and should be 'neutral' otherwise."], "Positive Examples": [{"input": "Sentence 1: The sum of all chemical reactions that take place within an organism is known as metabolism. Sentence 2: Metabolism is the sum total of all chemical reactions performed by an organism.", "output": "entails", "explanation": "Sentence 2 gives out supporting information about the Metabolism hence it is correct"}, {"input": "Sentence 1: The endocrine system produces most of the hormones that regulate body functions. Sentence 2: Your endocrine glands produce hormones that control all your body functions.", "output": "entails", "explanation": "Sentence 2 explains and supports Statement 1 by explaining which part of the system produces the hormones, and hence is correct "}, {"input": "Sentence 1: Warm and humid temperature and moisture conditions describe an air mass that originates over the Atlantic ocean near the equator. Sentence 2: Maritime tropical air Warm, humid air mass that forms over tropical and subtropical oceans.", "output": "neutral", "explanation": "Sentence 2 talks about Maritime tropical air which is completely disjoint from the fact stated in Statement 1 about the air mass near the equator and hence the classification is correct."}], "Negative Examples": [{"input": "Sentence 1: A fewer predators is most likely to cause the number of rabbits living in an area to increase. Sentence 2: A predator of rodents, rabbits, birds and the like, this is a sizeable snake.", "output": "entails", "explanation": "Sentence 2 doesn't give out more information about the Sentence 1 or support the fact stated in Statement 1 but list out one of the predator. The output has been wrongly classified it as entails and hence is wrong."}, {"input": "Sentence 1: Genes are composed of dna. Sentence 2: Composed of DNA, genes are the basic unit of inheritance and provide the instruction manual for how to make the body function.", "output": "neutral", "explanation": "Sentence 2 gives out more information about the dna but is marked neutral, hence it is incorrect"}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Web", "Natural Science -> School Science Textbooks"], "Instance": {"id": "task1554-d004b4c91a784306ad7385e7b868e471", "input": "Sentence 1: In the nuclear fusion process, two light nuclei combine to produce a heavier nucleus and great energy. Sentence 2: nuclear fusion A nuclear process that releases energy when lightweight nuclei combine to form heavy-weight nuclei.", "output": ["entails"]}, "Instance License": ["Apache 2.0"], "prediction": "entails"}
+{"id": "task1554-398c6b3743a84ceaaa3067567b6b2d94", "Task": "task1554_scitail_classification", "Contributors": "['Nishtha Bhimte']", "Source": ["scitail"], "URL": ["http://data.allenai.org.s3.amazonaws.com/downloads/SciTailV1.1.zip"], "Categories": ["Textual Entailment"], "Reasoning": ["Textual Entailment -> Deductive Reasoning"], "Definition": ["In this task, you are given two statements. The task is to output whether a given textual premise, i.e. Statement 2, entails or implies a given scientific fact, i.e. Statement 1. The output should be 'entails' if Statement 2 supports Statement 1 and should be 'neutral' otherwise."], "Positive Examples": [{"input": "Sentence 1: The sum of all chemical reactions that take place within an organism is known as metabolism. Sentence 2: Metabolism is the sum total of all chemical reactions performed by an organism.", "output": "entails", "explanation": "Sentence 2 gives out supporting information about the Metabolism hence it is correct"}, {"input": "Sentence 1: The endocrine system produces most of the hormones that regulate body functions. Sentence 2: Your endocrine glands produce hormones that control all your body functions.", "output": "entails", "explanation": "Sentence 2 explains and supports Statement 1 by explaining which part of the system produces the hormones, and hence is correct "}, {"input": "Sentence 1: Warm and humid temperature and moisture conditions describe an air mass that originates over the Atlantic ocean near the equator. Sentence 2: Maritime tropical air Warm, humid air mass that forms over tropical and subtropical oceans.", "output": "neutral", "explanation": "Sentence 2 talks about Maritime tropical air which is completely disjoint from the fact stated in Statement 1 about the air mass near the equator and hence the classification is correct."}], "Negative Examples": [{"input": "Sentence 1: A fewer predators is most likely to cause the number of rabbits living in an area to increase. Sentence 2: A predator of rodents, rabbits, birds and the like, this is a sizeable snake.", "output": "entails", "explanation": "Sentence 2 doesn't give out more information about the Sentence 1 or support the fact stated in Statement 1 but list out one of the predator. The output has been wrongly classified it as entails and hence is wrong."}, {"input": "Sentence 1: Genes are composed of dna. Sentence 2: Composed of DNA, genes are the basic unit of inheritance and provide the instruction manual for how to make the body function.", "output": "neutral", "explanation": "Sentence 2 gives out more information about the dna but is marked neutral, hence it is incorrect"}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Web", "Natural Science -> School Science Textbooks"], "Instance": {"id": "task1554-398c6b3743a84ceaaa3067567b6b2d94", "input": "Sentence 1: You decrease errors in an experiment by take many measurements. Sentence 2: This decreases the chance of measurement error due to sound reflections from the body of the technician.", "output": ["neutral"]}, "Instance License": ["Apache 2.0"], "prediction": "entails"}
+{"id": "task050-dfc4a7889da54e398033e75ac4fbc6fb", "Task": "task050_multirc_answerability", "Contributors": "['Swaroop Mishra', 'Daniel Khashabi']", "Source": ["multirc"], "URL": ["https://github.com/CogComp/multirc"], "Categories": ["Answerability Classification"], "Reasoning": [], "Definition": ["You are given a sentence and a question in the input. If the information provided in the sentence is enough to answer the question, label \"Yes\", otherwise label \"No\". Do not use any facts other than those provided in the sentence while labeling \"Yes\" or \"No\". There are only two types of valid responses: Yes and No."], "Positive Examples": [{"input": "Sentence: GOP leaders submitted the new offer Tuesday afternoon in an effort to appease Democrats, whose votes are needed to avert a shutdown of federal agencies, several House and Senate aides said. Question: Who has to be appeased to keep the government open?", "output": "Yes.", "explanation": "The sentence says that \"the Democrats\" have to be appeased, which answers the question. So, the correct label should be \"Yes\"."}, {"input": "Sentence: His mother, Ann Dunham (1942\u20131995), was born in Wichita, Kansas, of mostly English descent, with some German, Irish, Scottish, Swiss, and Welsh ancestry. Question: How old was Obama\u2019s mother when he was born?", "output": "No.", "explanation": "The sentence mentions the birth year of Ann Dunham but it does not say that she is Obama\u2019s mother. It also doesn't say when her son was born. Note that, any information other than that mentioned in the sentence cannot be used to answer the question. So, the correct label should be \"No\"."}], "Negative Examples": [{"input": "Sentence: GOP leaders submitted the new offer Tuesday afternoon in an effort to appease Democrats, whose votes are needed to avert a shutdown of federal agencies, several House and Senate aides said. Question: Who has to be appeased to keep the government open?", "output": "Democrats.", "explanation": "Your response should only be \"yes\" or \"no\" based on whether information in the given sentence is enough to answer the given question or not. The correct response here would have been a \"Yes\"."}, {"input": "Sentence: His mother, Ann Dunham (1942\u20131995), was born in Wichita, Kansas, of mostly English descent, with some German, Irish, Scottish, Swiss, and Welsh ancestry. Question: How old was Obama\u2019s mother when he was born?", "output": "Information not enough.", "explanation": "Even though information provided in the sentence is not enough to answer the question, you should not write that explicitly in your response. Instead you should indicate it with label \"No\". Remember that there are only 2 types of possible responses: \"Yes\" and \"No\"."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["News", "Wikipedia", "Law", "Justice", "History", "History -> 9/11 Reports", "Anthropology", "School Science Textbooks", "Fiction"], "Instance": {"id": "task050-dfc4a7889da54e398033e75ac4fbc6fb", "input": "Sentence: Within the districts lie VDCs (villages), 3 municipalities (Bhaktapur, Kirtipur, Madhyapur Thimi), 1 sub-metropolitan city (Lalitpur), and 1 metropolitan city (Kathmandu). \nQuestion: How many sub-metropolitan cities are present in the districts that make up the Kathmandu valley?", "output": ["Yes."]}, "Instance License": ["CCG licence (https://github.com/CogComp/multirc/blob/master/LICENSE)"], "prediction": "No"}
+{"id": "task050-aa3e0831142743d5b7a9faa1dc46d93a", "Task": "task050_multirc_answerability", "Contributors": "['Swaroop Mishra', 'Daniel Khashabi']", "Source": ["multirc"], "URL": ["https://github.com/CogComp/multirc"], "Categories": ["Answerability Classification"], "Reasoning": [], "Definition": ["You are given a sentence and a question in the input. If the information provided in the sentence is enough to answer the question, label \"Yes\", otherwise label \"No\". Do not use any facts other than those provided in the sentence while labeling \"Yes\" or \"No\". There are only two types of valid responses: Yes and No."], "Positive Examples": [{"input": "Sentence: GOP leaders submitted the new offer Tuesday afternoon in an effort to appease Democrats, whose votes are needed to avert a shutdown of federal agencies, several House and Senate aides said. Question: Who has to be appeased to keep the government open?", "output": "Yes.", "explanation": "The sentence says that \"the Democrats\" have to be appeased, which answers the question. So, the correct label should be \"Yes\"."}, {"input": "Sentence: His mother, Ann Dunham (1942\u20131995), was born in Wichita, Kansas, of mostly English descent, with some German, Irish, Scottish, Swiss, and Welsh ancestry. Question: How old was Obama\u2019s mother when he was born?", "output": "No.", "explanation": "The sentence mentions the birth year of Ann Dunham but it does not say that she is Obama\u2019s mother. It also doesn't say when her son was born. Note that, any information other than that mentioned in the sentence cannot be used to answer the question. So, the correct label should be \"No\"."}], "Negative Examples": [{"input": "Sentence: GOP leaders submitted the new offer Tuesday afternoon in an effort to appease Democrats, whose votes are needed to avert a shutdown of federal agencies, several House and Senate aides said. Question: Who has to be appeased to keep the government open?", "output": "Democrats.", "explanation": "Your response should only be \"yes\" or \"no\" based on whether information in the given sentence is enough to answer the given question or not. The correct response here would have been a \"Yes\"."}, {"input": "Sentence: His mother, Ann Dunham (1942\u20131995), was born in Wichita, Kansas, of mostly English descent, with some German, Irish, Scottish, Swiss, and Welsh ancestry. Question: How old was Obama\u2019s mother when he was born?", "output": "Information not enough.", "explanation": "Even though information provided in the sentence is not enough to answer the question, you should not write that explicitly in your response. Instead you should indicate it with label \"No\". Remember that there are only 2 types of possible responses: \"Yes\" and \"No\"."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["News", "Wikipedia", "Law", "Justice", "History", "History -> 9/11 Reports", "Anthropology", "School Science Textbooks", "Fiction"], "Instance": {"id": "task050-aa3e0831142743d5b7a9faa1dc46d93a", "input": "Sentence: Noodle found a long brown stick. \nQuestion: Where was Jack when he saw the pond with ducks in it?", "output": ["No."]}, "Instance License": ["CCG licence (https://github.com/CogComp/multirc/blob/master/LICENSE)"], "prediction": "No"}
+{"id": "task050-9a54695b449746a7a516504bed0e285c", "Task": "task050_multirc_answerability", "Contributors": "['Swaroop Mishra', 'Daniel Khashabi']", "Source": ["multirc"], "URL": ["https://github.com/CogComp/multirc"], "Categories": ["Answerability Classification"], "Reasoning": [], "Definition": ["You are given a sentence and a question in the input. If the information provided in the sentence is enough to answer the question, label \"Yes\", otherwise label \"No\". Do not use any facts other than those provided in the sentence while labeling \"Yes\" or \"No\". There are only two types of valid responses: Yes and No."], "Positive Examples": [{"input": "Sentence: GOP leaders submitted the new offer Tuesday afternoon in an effort to appease Democrats, whose votes are needed to avert a shutdown of federal agencies, several House and Senate aides said. Question: Who has to be appeased to keep the government open?", "output": "Yes.", "explanation": "The sentence says that \"the Democrats\" have to be appeased, which answers the question. So, the correct label should be \"Yes\"."}, {"input": "Sentence: His mother, Ann Dunham (1942\u20131995), was born in Wichita, Kansas, of mostly English descent, with some German, Irish, Scottish, Swiss, and Welsh ancestry. Question: How old was Obama\u2019s mother when he was born?", "output": "No.", "explanation": "The sentence mentions the birth year of Ann Dunham but it does not say that she is Obama\u2019s mother. It also doesn't say when her son was born. Note that, any information other than that mentioned in the sentence cannot be used to answer the question. So, the correct label should be \"No\"."}], "Negative Examples": [{"input": "Sentence: GOP leaders submitted the new offer Tuesday afternoon in an effort to appease Democrats, whose votes are needed to avert a shutdown of federal agencies, several House and Senate aides said. Question: Who has to be appeased to keep the government open?", "output": "Democrats.", "explanation": "Your response should only be \"yes\" or \"no\" based on whether information in the given sentence is enough to answer the given question or not. The correct response here would have been a \"Yes\"."}, {"input": "Sentence: His mother, Ann Dunham (1942\u20131995), was born in Wichita, Kansas, of mostly English descent, with some German, Irish, Scottish, Swiss, and Welsh ancestry. Question: How old was Obama\u2019s mother when he was born?", "output": "Information not enough.", "explanation": "Even though information provided in the sentence is not enough to answer the question, you should not write that explicitly in your response. Instead you should indicate it with label \"No\". Remember that there are only 2 types of possible responses: \"Yes\" and \"No\"."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["News", "Wikipedia", "Law", "Justice", "History", "History -> 9/11 Reports", "Anthropology", "School Science Textbooks", "Fiction"], "Instance": {"id": "task050-9a54695b449746a7a516504bed0e285c", "input": "Sentence: This made the robot very happy. \nQuestion: Where did Carl come from?", "output": ["No."]}, "Instance License": ["CCG licence (https://github.com/CogComp/multirc/blob/master/LICENSE)"], "prediction": "No"}
+{"id": "task050-bb25eeda67b749be973f765fe350badb", "Task": "task050_multirc_answerability", "Contributors": "['Swaroop Mishra', 'Daniel Khashabi']", "Source": ["multirc"], "URL": ["https://github.com/CogComp/multirc"], "Categories": ["Answerability Classification"], "Reasoning": [], "Definition": ["You are given a sentence and a question in the input. If the information provided in the sentence is enough to answer the question, label \"Yes\", otherwise label \"No\". Do not use any facts other than those provided in the sentence while labeling \"Yes\" or \"No\". There are only two types of valid responses: Yes and No."], "Positive Examples": [{"input": "Sentence: GOP leaders submitted the new offer Tuesday afternoon in an effort to appease Democrats, whose votes are needed to avert a shutdown of federal agencies, several House and Senate aides said. Question: Who has to be appeased to keep the government open?", "output": "Yes.", "explanation": "The sentence says that \"the Democrats\" have to be appeased, which answers the question. So, the correct label should be \"Yes\"."}, {"input": "Sentence: His mother, Ann Dunham (1942\u20131995), was born in Wichita, Kansas, of mostly English descent, with some German, Irish, Scottish, Swiss, and Welsh ancestry. Question: How old was Obama\u2019s mother when he was born?", "output": "No.", "explanation": "The sentence mentions the birth year of Ann Dunham but it does not say that she is Obama\u2019s mother. It also doesn't say when her son was born. Note that, any information other than that mentioned in the sentence cannot be used to answer the question. So, the correct label should be \"No\"."}], "Negative Examples": [{"input": "Sentence: GOP leaders submitted the new offer Tuesday afternoon in an effort to appease Democrats, whose votes are needed to avert a shutdown of federal agencies, several House and Senate aides said. Question: Who has to be appeased to keep the government open?", "output": "Democrats.", "explanation": "Your response should only be \"yes\" or \"no\" based on whether information in the given sentence is enough to answer the given question or not. The correct response here would have been a \"Yes\"."}, {"input": "Sentence: His mother, Ann Dunham (1942\u20131995), was born in Wichita, Kansas, of mostly English descent, with some German, Irish, Scottish, Swiss, and Welsh ancestry. Question: How old was Obama\u2019s mother when he was born?", "output": "Information not enough.", "explanation": "Even though information provided in the sentence is not enough to answer the question, you should not write that explicitly in your response. Instead you should indicate it with label \"No\". Remember that there are only 2 types of possible responses: \"Yes\" and \"No\"."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["News", "Wikipedia", "Law", "Justice", "History", "History -> 9/11 Reports", "Anthropology", "School Science Textbooks", "Fiction"], "Instance": {"id": "task050-bb25eeda67b749be973f765fe350badb", "input": "Sentence: - Mary said: Josh, Thank you - Excuse me, Mary ... I have to go ... Otherwise I'll be late for school ... And I would not want to upset the teacher. \nQuestion: Who are the principal characters of the story?", "output": ["Yes."]}, "Instance License": ["CCG licence (https://github.com/CogComp/multirc/blob/master/LICENSE)"], "prediction": "Yes"}
+{"id": "task050-078e69a0a4024dfc8126a435d7f4c75d", "Task": "task050_multirc_answerability", "Contributors": "['Swaroop Mishra', 'Daniel Khashabi']", "Source": ["multirc"], "URL": ["https://github.com/CogComp/multirc"], "Categories": ["Answerability Classification"], "Reasoning": [], "Definition": ["You are given a sentence and a question in the input. If the information provided in the sentence is enough to answer the question, label \"Yes\", otherwise label \"No\". Do not use any facts other than those provided in the sentence while labeling \"Yes\" or \"No\". There are only two types of valid responses: Yes and No."], "Positive Examples": [{"input": "Sentence: GOP leaders submitted the new offer Tuesday afternoon in an effort to appease Democrats, whose votes are needed to avert a shutdown of federal agencies, several House and Senate aides said. Question: Who has to be appeased to keep the government open?", "output": "Yes.", "explanation": "The sentence says that \"the Democrats\" have to be appeased, which answers the question. So, the correct label should be \"Yes\"."}, {"input": "Sentence: His mother, Ann Dunham (1942\u20131995), was born in Wichita, Kansas, of mostly English descent, with some German, Irish, Scottish, Swiss, and Welsh ancestry. Question: How old was Obama\u2019s mother when he was born?", "output": "No.", "explanation": "The sentence mentions the birth year of Ann Dunham but it does not say that she is Obama\u2019s mother. It also doesn't say when her son was born. Note that, any information other than that mentioned in the sentence cannot be used to answer the question. So, the correct label should be \"No\"."}], "Negative Examples": [{"input": "Sentence: GOP leaders submitted the new offer Tuesday afternoon in an effort to appease Democrats, whose votes are needed to avert a shutdown of federal agencies, several House and Senate aides said. Question: Who has to be appeased to keep the government open?", "output": "Democrats.", "explanation": "Your response should only be \"yes\" or \"no\" based on whether information in the given sentence is enough to answer the given question or not. The correct response here would have been a \"Yes\"."}, {"input": "Sentence: His mother, Ann Dunham (1942\u20131995), was born in Wichita, Kansas, of mostly English descent, with some German, Irish, Scottish, Swiss, and Welsh ancestry. Question: How old was Obama\u2019s mother when he was born?", "output": "Information not enough.", "explanation": "Even though information provided in the sentence is not enough to answer the question, you should not write that explicitly in your response. Instead you should indicate it with label \"No\". Remember that there are only 2 types of possible responses: \"Yes\" and \"No\"."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["News", "Wikipedia", "Law", "Justice", "History", "History -> 9/11 Reports", "Anthropology", "School Science Textbooks", "Fiction"], "Instance": {"id": "task050-078e69a0a4024dfc8126a435d7f4c75d", "input": "Sentence: When Jimmy got home his hat was sitting there next to his goldfish. \nQuestion: why couldn't he keep looking?", "output": ["No."]}, "Instance License": ["CCG licence (https://github.com/CogComp/multirc/blob/master/LICENSE)"], "prediction": "No"}
+{"id": "task362-da22c519ce2140cc82a3a3170ccc9d19", "Task": "task362_spolin_yesand_prompt_response_sub_classification", "Contributors": "['Maitreya Patel']", "Source": ["spolin"], "URL": ["https://justin-cho.com/spolin"], "Categories": ["Dialogue Act Recognition"], "Reasoning": [], "Definition": ["\"Yes, and\" is a rule-of-thumb in improvisational comedy that suggests that a participant in a dialogue should accept what another participant has stated (\"Yes\") and then expand on that line of thought or context (\"and...\"). Given a prompt and two responses, identify which response is the type of \"yes, and\". Indicate your answer by 'Response 1' if the first response is correct, otherwise 'Response 2'.  Note that a \"Yes, and\" does not require someone explicitly saying 'yes, and...' as part of a dialogue exchange."], "Positive Examples": [{"input": "Prompt: See, Arlene? That's why I don't talk to you like that because I'm afraid I'll scare our son. \n Response 1: I have 12. Wait, is the key to a success story getting the number to go down? \n Response 2: Oh, Dad. Even that wasn't great.", "output": "Response 2", "explanation": "Response 2 is correct answer because it agrees with the prompt and continues the conversation in the same context."}, {"input": "Prompt: Do you believe you're going to jail? Because you're going to jail. \n Response 1: That's what you say, but I believe jail doesn't exist, therefore I'm not scared. \n Response 2: OK. Should I go out there and admit that I brought him back here or should I play dumb?", "output": "Response 1", "explanation": "The answer is correct as Response 1 is in alignment with the prompt and believes it."}], "Negative Examples": [{"input": "Prompt: So you want obstacles to piloting the ship? \n Response 1: Yeah, and more buttons and switches than we possibly could need. \n Response 2: It's a security device for your breathing taint.", "output": "Response 2", "explanation": "This is incorrect answer. Because Response 2 is out of context and doesn't agree with the prompt."}, {"input": "Prompt: You know, I'm going to call you Swoop. \n Response 1: And the same with the Shamrock Shake. Did I ever tell you how I saved Ireland? \n Response 2: Alright, well that's better than Jim or whatever your name. is.", "output": "Response 1", "explanation": "The correct answer is \"Response 2\" as it is in context with the prompt and says yes indirectly to agree with it."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Dialogue"], "Instance": {"id": "task362-da22c519ce2140cc82a3a3170ccc9d19", "input": "Prompt: Well, were you attracted by the sounds of my working on this here contraption? \n Response 1: I was hiding under it, Cape Fear style. \n Response 2: I did. I was thinking \"I hear something behind my back, some kind of contraption is being worked on. But I can't see anyone here.\"", "output": ["Response 2"]}, "Instance License": ["CC BY-NC 4.0"], "prediction": "Answer 2"}
+{"id": "task362-e46d61f4805d4a65818351801e085ac8", "Task": "task362_spolin_yesand_prompt_response_sub_classification", "Contributors": "['Maitreya Patel']", "Source": ["spolin"], "URL": ["https://justin-cho.com/spolin"], "Categories": ["Dialogue Act Recognition"], "Reasoning": [], "Definition": ["\"Yes, and\" is a rule-of-thumb in improvisational comedy that suggests that a participant in a dialogue should accept what another participant has stated (\"Yes\") and then expand on that line of thought or context (\"and...\"). Given a prompt and two responses, identify which response is the type of \"yes, and\". Indicate your answer by 'Response 1' if the first response is correct, otherwise 'Response 2'.  Note that a \"Yes, and\" does not require someone explicitly saying 'yes, and...' as part of a dialogue exchange."], "Positive Examples": [{"input": "Prompt: See, Arlene? That's why I don't talk to you like that because I'm afraid I'll scare our son. \n Response 1: I have 12. Wait, is the key to a success story getting the number to go down? \n Response 2: Oh, Dad. Even that wasn't great.", "output": "Response 2", "explanation": "Response 2 is correct answer because it agrees with the prompt and continues the conversation in the same context."}, {"input": "Prompt: Do you believe you're going to jail? Because you're going to jail. \n Response 1: That's what you say, but I believe jail doesn't exist, therefore I'm not scared. \n Response 2: OK. Should I go out there and admit that I brought him back here or should I play dumb?", "output": "Response 1", "explanation": "The answer is correct as Response 1 is in alignment with the prompt and believes it."}], "Negative Examples": [{"input": "Prompt: So you want obstacles to piloting the ship? \n Response 1: Yeah, and more buttons and switches than we possibly could need. \n Response 2: It's a security device for your breathing taint.", "output": "Response 2", "explanation": "This is incorrect answer. Because Response 2 is out of context and doesn't agree with the prompt."}, {"input": "Prompt: You know, I'm going to call you Swoop. \n Response 1: And the same with the Shamrock Shake. Did I ever tell you how I saved Ireland? \n Response 2: Alright, well that's better than Jim or whatever your name. is.", "output": "Response 1", "explanation": "The correct answer is \"Response 2\" as it is in context with the prompt and says yes indirectly to agree with it."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Dialogue"], "Instance": {"id": "task362-e46d61f4805d4a65818351801e085ac8", "input": "Prompt: I would just like to discern what brow mopping exactly is. \n Response 1: It's like this. I take out my handkerchief and I mop my brow, so as to make a point and to say this is all very weary. \n Response 2: My goodness. You've been here since the beginning. Do you not remember?", "output": ["Response 1"]}, "Instance License": ["CC BY-NC 4.0"], "prediction": "Answer 1"}
+{"id": "task362-703c8005bf974e7591aa084384466e8d", "Task": "task362_spolin_yesand_prompt_response_sub_classification", "Contributors": "['Maitreya Patel']", "Source": ["spolin"], "URL": ["https://justin-cho.com/spolin"], "Categories": ["Dialogue Act Recognition"], "Reasoning": [], "Definition": ["\"Yes, and\" is a rule-of-thumb in improvisational comedy that suggests that a participant in a dialogue should accept what another participant has stated (\"Yes\") and then expand on that line of thought or context (\"and...\"). Given a prompt and two responses, identify which response is the type of \"yes, and\". Indicate your answer by 'Response 1' if the first response is correct, otherwise 'Response 2'.  Note that a \"Yes, and\" does not require someone explicitly saying 'yes, and...' as part of a dialogue exchange."], "Positive Examples": [{"input": "Prompt: See, Arlene? That's why I don't talk to you like that because I'm afraid I'll scare our son. \n Response 1: I have 12. Wait, is the key to a success story getting the number to go down? \n Response 2: Oh, Dad. Even that wasn't great.", "output": "Response 2", "explanation": "Response 2 is correct answer because it agrees with the prompt and continues the conversation in the same context."}, {"input": "Prompt: Do you believe you're going to jail? Because you're going to jail. \n Response 1: That's what you say, but I believe jail doesn't exist, therefore I'm not scared. \n Response 2: OK. Should I go out there and admit that I brought him back here or should I play dumb?", "output": "Response 1", "explanation": "The answer is correct as Response 1 is in alignment with the prompt and believes it."}], "Negative Examples": [{"input": "Prompt: So you want obstacles to piloting the ship? \n Response 1: Yeah, and more buttons and switches than we possibly could need. \n Response 2: It's a security device for your breathing taint.", "output": "Response 2", "explanation": "This is incorrect answer. Because Response 2 is out of context and doesn't agree with the prompt."}, {"input": "Prompt: You know, I'm going to call you Swoop. \n Response 1: And the same with the Shamrock Shake. Did I ever tell you how I saved Ireland? \n Response 2: Alright, well that's better than Jim or whatever your name. is.", "output": "Response 1", "explanation": "The correct answer is \"Response 2\" as it is in context with the prompt and says yes indirectly to agree with it."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Dialogue"], "Instance": {"id": "task362-703c8005bf974e7591aa084384466e8d", "input": "Prompt: Yeah, your hands look like two thunderclouds with lightening shooting out of them. \n Response 1: Like two horses with one too many legs each. \n Response 2: Thank you, Maybelline. I feel like I whittled it down really well.", "output": ["Response 1"]}, "Instance License": ["CC BY-NC 4.0"], "prediction": "Response 2"}
+{"id": "task362-f46e9fb6cf2c416381067489bba5805a", "Task": "task362_spolin_yesand_prompt_response_sub_classification", "Contributors": "['Maitreya Patel']", "Source": ["spolin"], "URL": ["https://justin-cho.com/spolin"], "Categories": ["Dialogue Act Recognition"], "Reasoning": [], "Definition": ["\"Yes, and\" is a rule-of-thumb in improvisational comedy that suggests that a participant in a dialogue should accept what another participant has stated (\"Yes\") and then expand on that line of thought or context (\"and...\"). Given a prompt and two responses, identify which response is the type of \"yes, and\". Indicate your answer by 'Response 1' if the first response is correct, otherwise 'Response 2'.  Note that a \"Yes, and\" does not require someone explicitly saying 'yes, and...' as part of a dialogue exchange."], "Positive Examples": [{"input": "Prompt: See, Arlene? That's why I don't talk to you like that because I'm afraid I'll scare our son. \n Response 1: I have 12. Wait, is the key to a success story getting the number to go down? \n Response 2: Oh, Dad. Even that wasn't great.", "output": "Response 2", "explanation": "Response 2 is correct answer because it agrees with the prompt and continues the conversation in the same context."}, {"input": "Prompt: Do you believe you're going to jail? Because you're going to jail. \n Response 1: That's what you say, but I believe jail doesn't exist, therefore I'm not scared. \n Response 2: OK. Should I go out there and admit that I brought him back here or should I play dumb?", "output": "Response 1", "explanation": "The answer is correct as Response 1 is in alignment with the prompt and believes it."}], "Negative Examples": [{"input": "Prompt: So you want obstacles to piloting the ship? \n Response 1: Yeah, and more buttons and switches than we possibly could need. \n Response 2: It's a security device for your breathing taint.", "output": "Response 2", "explanation": "This is incorrect answer. Because Response 2 is out of context and doesn't agree with the prompt."}, {"input": "Prompt: You know, I'm going to call you Swoop. \n Response 1: And the same with the Shamrock Shake. Did I ever tell you how I saved Ireland? \n Response 2: Alright, well that's better than Jim or whatever your name. is.", "output": "Response 1", "explanation": "The correct answer is \"Response 2\" as it is in context with the prompt and says yes indirectly to agree with it."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Dialogue"], "Instance": {"id": "task362-f46e9fb6cf2c416381067489bba5805a", "input": "Prompt: Guys, guys, Nixon is resigning. \n Response 1: I was having a great day, but I just realized there's only one channel on television and that's going to ruin my life forever. \n Response 2: The president?", "output": ["Response 2"]}, "Instance License": ["CC BY-NC 4.0"], "prediction": "Answer 2"}
+{"id": "task362-21dfc4e278684bf790d61a8220ce5685", "Task": "task362_spolin_yesand_prompt_response_sub_classification", "Contributors": "['Maitreya Patel']", "Source": ["spolin"], "URL": ["https://justin-cho.com/spolin"], "Categories": ["Dialogue Act Recognition"], "Reasoning": [], "Definition": ["\"Yes, and\" is a rule-of-thumb in improvisational comedy that suggests that a participant in a dialogue should accept what another participant has stated (\"Yes\") and then expand on that line of thought or context (\"and...\"). Given a prompt and two responses, identify which response is the type of \"yes, and\". Indicate your answer by 'Response 1' if the first response is correct, otherwise 'Response 2'.  Note that a \"Yes, and\" does not require someone explicitly saying 'yes, and...' as part of a dialogue exchange."], "Positive Examples": [{"input": "Prompt: See, Arlene? That's why I don't talk to you like that because I'm afraid I'll scare our son. \n Response 1: I have 12. Wait, is the key to a success story getting the number to go down? \n Response 2: Oh, Dad. Even that wasn't great.", "output": "Response 2", "explanation": "Response 2 is correct answer because it agrees with the prompt and continues the conversation in the same context."}, {"input": "Prompt: Do you believe you're going to jail? Because you're going to jail. \n Response 1: That's what you say, but I believe jail doesn't exist, therefore I'm not scared. \n Response 2: OK. Should I go out there and admit that I brought him back here or should I play dumb?", "output": "Response 1", "explanation": "The answer is correct as Response 1 is in alignment with the prompt and believes it."}], "Negative Examples": [{"input": "Prompt: So you want obstacles to piloting the ship? \n Response 1: Yeah, and more buttons and switches than we possibly could need. \n Response 2: It's a security device for your breathing taint.", "output": "Response 2", "explanation": "This is incorrect answer. Because Response 2 is out of context and doesn't agree with the prompt."}, {"input": "Prompt: You know, I'm going to call you Swoop. \n Response 1: And the same with the Shamrock Shake. Did I ever tell you how I saved Ireland? \n Response 2: Alright, well that's better than Jim or whatever your name. is.", "output": "Response 1", "explanation": "The correct answer is \"Response 2\" as it is in context with the prompt and says yes indirectly to agree with it."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Dialogue"], "Instance": {"id": "task362-21dfc4e278684bf790d61a8220ce5685", "input": "Prompt: Wait, they give you cups of coffee when you make it to the major leagues? \n Response 1: Yeah, rook, that's what happens. You get a cup of coffee. And if you can't stand the heat you're sent right back down to the minors. \n Response 2: Yeah. My boss says I'm in to weird music and thought I might like these. He doesn't know me at all.", "output": ["Response 1"]}, "Instance License": ["CC BY-NC 4.0"], "prediction": "Answer 2"}
+{"id": "task1557-b86c45563ff7453a927e4e6da9ec901a", "Task": "task1557_jfleg_answer_generation", "Contributors": "['Jonathan Reyes']", "Source": ["jfleg"], "URL": ["https://huggingface.co/datasets/jfleg"], "Categories": ["Grammar Error Correction"], "Reasoning": [], "Definition": ["In this task, you will be shown an incorrect English sentence. You need to generate a corrected form of the input sentence."], "Positive Examples": [{"input": "The car's wheel are loose.", "output": "The car's wheel is loose.", "explanation": "The instance of are is replaced by the word is, because the wheel is a singular word. This makes the sentence grammatically correct."}, {"input": "The value of the car is very less.", "output": "The value of the car is much less.", "explanation": "The instance of very is replaced by the word much. This makes the sentence grammatically correct."}, {"input": "To day is sunny.", "output": "Today is sunny.", "explanation": "'To day' is misspelled and needs to be replaced with today for this sentence to be correct."}], "Negative Examples": [{"input": "This way is the way to go.", "output": "This way may be the way to go.", "explanation": "The example does not correct the misuse of the word way. Instead, it should shorten the sentence to: this is the way to go."}, {"input": "The car is caught on fire.", "output": "The car is catch on fire", "explanation": "The example incorrectly uses is and catch to make a sentence."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["English Exams", "Miscellaneous"], "Instance": {"id": "task1557-b86c45563ff7453a927e4e6da9ec901a", "input": "However , all of them are limited . ", "output": ["However , all of them are limited . "]}, "Instance License": ["CC BY-NC-SA 4.0"], "prediction": "however, all of them are limited."}
+{"id": "task1557-9f595665ef224677902449295113f7b6", "Task": "task1557_jfleg_answer_generation", "Contributors": "['Jonathan Reyes']", "Source": ["jfleg"], "URL": ["https://huggingface.co/datasets/jfleg"], "Categories": ["Grammar Error Correction"], "Reasoning": [], "Definition": ["In this task, you will be shown an incorrect English sentence. You need to generate a corrected form of the input sentence."], "Positive Examples": [{"input": "The car's wheel are loose.", "output": "The car's wheel is loose.", "explanation": "The instance of are is replaced by the word is, because the wheel is a singular word. This makes the sentence grammatically correct."}, {"input": "The value of the car is very less.", "output": "The value of the car is much less.", "explanation": "The instance of very is replaced by the word much. This makes the sentence grammatically correct."}, {"input": "To day is sunny.", "output": "Today is sunny.", "explanation": "'To day' is misspelled and needs to be replaced with today for this sentence to be correct."}], "Negative Examples": [{"input": "This way is the way to go.", "output": "This way may be the way to go.", "explanation": "The example does not correct the misuse of the word way. Instead, it should shorten the sentence to: this is the way to go."}, {"input": "The car is caught on fire.", "output": "The car is catch on fire", "explanation": "The example incorrectly uses is and catch to make a sentence."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["English Exams", "Miscellaneous"], "Instance": {"id": "task1557-9f595665ef224677902449295113f7b6", "input": "However , there were n't any particles . ", "output": ["However , there were n't any particles . "]}, "Instance License": ["CC BY-NC-SA 4.0"], "prediction": "however, there weren't any particles."}
+{"id": "task1557-00d36742ce044b73af2ef2924a7fd5d4", "Task": "task1557_jfleg_answer_generation", "Contributors": "['Jonathan Reyes']", "Source": ["jfleg"], "URL": ["https://huggingface.co/datasets/jfleg"], "Categories": ["Grammar Error Correction"], "Reasoning": [], "Definition": ["In this task, you will be shown an incorrect English sentence. You need to generate a corrected form of the input sentence."], "Positive Examples": [{"input": "The car's wheel are loose.", "output": "The car's wheel is loose.", "explanation": "The instance of are is replaced by the word is, because the wheel is a singular word. This makes the sentence grammatically correct."}, {"input": "The value of the car is very less.", "output": "The value of the car is much less.", "explanation": "The instance of very is replaced by the word much. This makes the sentence grammatically correct."}, {"input": "To day is sunny.", "output": "Today is sunny.", "explanation": "'To day' is misspelled and needs to be replaced with today for this sentence to be correct."}], "Negative Examples": [{"input": "This way is the way to go.", "output": "This way may be the way to go.", "explanation": "The example does not correct the misuse of the word way. Instead, it should shorten the sentence to: this is the way to go."}, {"input": "The car is caught on fire.", "output": "The car is catch on fire", "explanation": "The example incorrectly uses is and catch to make a sentence."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["English Exams", "Miscellaneous"], "Instance": {"id": "task1557-00d36742ce044b73af2ef2924a7fd5d4", "input": "Specializing in one particular subject does not suit our life in this era which is characterized by diversity and innovation ", "output": ["Specializing in one particular subject does not suit our lives in this era which is characterized by diversity and innovation . "]}, "Instance License": ["CC BY-NC-SA 4.0"], "prediction": "Specializing in one particular subject does not suit our life in this era which is characterized by diversity and innovation"}
+{"id": "task1557-ff55c90fd2084ac790d0ccbad2f6bc9a", "Task": "task1557_jfleg_answer_generation", "Contributors": "['Jonathan Reyes']", "Source": ["jfleg"], "URL": ["https://huggingface.co/datasets/jfleg"], "Categories": ["Grammar Error Correction"], "Reasoning": [], "Definition": ["In this task, you will be shown an incorrect English sentence. You need to generate a corrected form of the input sentence."], "Positive Examples": [{"input": "The car's wheel are loose.", "output": "The car's wheel is loose.", "explanation": "The instance of are is replaced by the word is, because the wheel is a singular word. This makes the sentence grammatically correct."}, {"input": "The value of the car is very less.", "output": "The value of the car is much less.", "explanation": "The instance of very is replaced by the word much. This makes the sentence grammatically correct."}, {"input": "To day is sunny.", "output": "Today is sunny.", "explanation": "'To day' is misspelled and needs to be replaced with today for this sentence to be correct."}], "Negative Examples": [{"input": "This way is the way to go.", "output": "This way may be the way to go.", "explanation": "The example does not correct the misuse of the word way. Instead, it should shorten the sentence to: this is the way to go."}, {"input": "The car is caught on fire.", "output": "The car is catch on fire", "explanation": "The example incorrectly uses is and catch to make a sentence."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["English Exams", "Miscellaneous"], "Instance": {"id": "task1557-ff55c90fd2084ac790d0ccbad2f6bc9a", "input": "For example one man is a football club fans . ", "output": ["For example , one man is a football club fan . "]}, "Instance License": ["CC BY-NC-SA 4.0"], "prediction": "For example one man is a football club fans."}
+{"id": "task1557-8c43c9d7d33b49a0a28b94201e8ece86", "Task": "task1557_jfleg_answer_generation", "Contributors": "['Jonathan Reyes']", "Source": ["jfleg"], "URL": ["https://huggingface.co/datasets/jfleg"], "Categories": ["Grammar Error Correction"], "Reasoning": [], "Definition": ["In this task, you will be shown an incorrect English sentence. You need to generate a corrected form of the input sentence."], "Positive Examples": [{"input": "The car's wheel are loose.", "output": "The car's wheel is loose.", "explanation": "The instance of are is replaced by the word is, because the wheel is a singular word. This makes the sentence grammatically correct."}, {"input": "The value of the car is very less.", "output": "The value of the car is much less.", "explanation": "The instance of very is replaced by the word much. This makes the sentence grammatically correct."}, {"input": "To day is sunny.", "output": "Today is sunny.", "explanation": "'To day' is misspelled and needs to be replaced with today for this sentence to be correct."}], "Negative Examples": [{"input": "This way is the way to go.", "output": "This way may be the way to go.", "explanation": "The example does not correct the misuse of the word way. Instead, it should shorten the sentence to: this is the way to go."}, {"input": "The car is caught on fire.", "output": "The car is catch on fire", "explanation": "The example incorrectly uses is and catch to make a sentence."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["English Exams", "Miscellaneous"], "Instance": {"id": "task1557-8c43c9d7d33b49a0a28b94201e8ece86", "input": "Fish firming uses the lots of special products such as fish meal . ", "output": ["Fish farming uses lots of special products such as fish meal . "]}, "Instance License": ["CC BY-NC-SA 4.0"], "prediction": "Fish firming uses the lots of special products such as fish meal."}
+{"id": "task249-a325178dd5b84177a8cfde4aeba27075", "Task": "task249_enhanced_wsc_pronoun_disambiguation", "Contributors": "['Pegah Alipoormolabashi']", "Source": ["enhanced_wsc"], "URL": ["https://github.com/mhany90/perturbed-wsc"], "Categories": ["Coreference Resolution"], "Reasoning": [], "Definition": ["In each example you will read a short sentence (or two). Then, a pronoun in the text is mentioned. Your task is to choose a referent which the mentioned pronoun refers to. You will be given two options in each case and one choice should seem much more likely to you than the other."], "Positive Examples": [{"input": "sentence: I couldn't put the saucepan on the rack because it was too tall .pronoun: it. A) the saucepan B) the rack", "output": "the rack", "explanation": "If the saucepan couldn't be put on the rack, the rack was probably taller than the person's reach. The pronoun \"it\" refers to the rack."}, {"input": "sentence: Arnold greatly influenced Jackson , though he lived two centuries earlier .pronoun: he. A) jackson B) arnold", "output": "arnold", "explanation": "For one person to influence another person, they should leave earlier than them, or contemporary to them. So the pronoun must refer to the influencer, which is Arnold."}, {"input": "sentence: cory knocked on dolly's door , but there was no answer . she was out .pronoun: she. A) cory B) dolly", "output": "dolly", "explanation": "From the context of the sentence, we know that the sentence \"She was out\" is resulted from Dolly not answering the door, so the pronoun \"she\" must refer to dolly."}, {"input": "sentence: There are pillars between me and the stages , and I can't see them .pronoun: them. A) the pillars B) the stages", "output": "the stages", "explanation": "The pillars are between someone and the stages, so they can probably see the pillars and not the stages."}], "Negative Examples": [{"input": "sentence: Joe and David's uncles can still beat them at tennis , even though they are 30 years younger .pronoun: they. A) joe and david B) joe and david's uncles", "output": "joe and david's uncles", "explanation": "There're two clues for resolving this pronoun. First, one's uncle is not usually 30 years younger than them. Second, younger people are usualy better at sports. The expression \"even though\" shows that there's a certain surprise in the sentence, so the person with better tennis performance should be the older one."}, {"input": "sentence: gaston passed the half-empty plate to hershel because he was full .pronoun: he. A) Gaston B) hershel", "output": "hershel", "explanation": "The person passing the leftover food must be the one who is full, so in this example \"he\" must refer to gatson."}, {"input": "sentence: The policeman arrested the gang member . He was trying to stop the drug trade in the neighborhood .pronoun: He. A) the police B) the gang member", "output": "the gang member", "explanation": "Deciding between a police and a gang member, it makes sense that the police is the one stopping the drug trade, not the gang member."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Dialogue", "Narrative"], "Instance": {"id": "task249-a325178dd5b84177a8cfde4aeba27075", "input": "sentence: Emma and Julia did not pass the ball to Janie and Anne although they saw that they were open .pronoun: they. A) emma and julia B) janie and anne", "output": ["emma and julia"]}, "Instance License": ["CC BY 4.0"], "prediction": "janie and anne"}
+{"id": "task249-b545c540e3814ff0b896b29b509573b8", "Task": "task249_enhanced_wsc_pronoun_disambiguation", "Contributors": "['Pegah Alipoormolabashi']", "Source": ["enhanced_wsc"], "URL": ["https://github.com/mhany90/perturbed-wsc"], "Categories": ["Coreference Resolution"], "Reasoning": [], "Definition": ["In each example you will read a short sentence (or two). Then, a pronoun in the text is mentioned. Your task is to choose a referent which the mentioned pronoun refers to. You will be given two options in each case and one choice should seem much more likely to you than the other."], "Positive Examples": [{"input": "sentence: I couldn't put the saucepan on the rack because it was too tall .pronoun: it. A) the saucepan B) the rack", "output": "the rack", "explanation": "If the saucepan couldn't be put on the rack, the rack was probably taller than the person's reach. The pronoun \"it\" refers to the rack."}, {"input": "sentence: Arnold greatly influenced Jackson , though he lived two centuries earlier .pronoun: he. A) jackson B) arnold", "output": "arnold", "explanation": "For one person to influence another person, they should leave earlier than them, or contemporary to them. So the pronoun must refer to the influencer, which is Arnold."}, {"input": "sentence: cory knocked on dolly's door , but there was no answer . she was out .pronoun: she. A) cory B) dolly", "output": "dolly", "explanation": "From the context of the sentence, we know that the sentence \"She was out\" is resulted from Dolly not answering the door, so the pronoun \"she\" must refer to dolly."}, {"input": "sentence: There are pillars between me and the stages , and I can't see them .pronoun: them. A) the pillars B) the stages", "output": "the stages", "explanation": "The pillars are between someone and the stages, so they can probably see the pillars and not the stages."}], "Negative Examples": [{"input": "sentence: Joe and David's uncles can still beat them at tennis , even though they are 30 years younger .pronoun: they. A) joe and david B) joe and david's uncles", "output": "joe and david's uncles", "explanation": "There're two clues for resolving this pronoun. First, one's uncle is not usually 30 years younger than them. Second, younger people are usualy better at sports. The expression \"even though\" shows that there's a certain surprise in the sentence, so the person with better tennis performance should be the older one."}, {"input": "sentence: gaston passed the half-empty plate to hershel because he was full .pronoun: he. A) Gaston B) hershel", "output": "hershel", "explanation": "The person passing the leftover food must be the one who is full, so in this example \"he\" must refer to gatson."}, {"input": "sentence: The policeman arrested the gang member . He was trying to stop the drug trade in the neighborhood .pronoun: He. A) the police B) the gang member", "output": "the gang member", "explanation": "Deciding between a police and a gang member, it makes sense that the police is the one stopping the drug trade, not the gang member."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Dialogue", "Narrative"], "Instance": {"id": "task249-b545c540e3814ff0b896b29b509573b8", "input": "sentence: Sam and Henry pulled up chairs to the pianos , but they were broken , so they had to stand instead .pronoun: they. A) the chairs B) the pianos", "output": ["the chairs"]}, "Instance License": ["CC BY 4.0"], "prediction": "Henry"}
+{"id": "task249-8d1c81418c984c70bc7bc0c226a0c6b7", "Task": "task249_enhanced_wsc_pronoun_disambiguation", "Contributors": "['Pegah Alipoormolabashi']", "Source": ["enhanced_wsc"], "URL": ["https://github.com/mhany90/perturbed-wsc"], "Categories": ["Coreference Resolution"], "Reasoning": [], "Definition": ["In each example you will read a short sentence (or two). Then, a pronoun in the text is mentioned. Your task is to choose a referent which the mentioned pronoun refers to. You will be given two options in each case and one choice should seem much more likely to you than the other."], "Positive Examples": [{"input": "sentence: I couldn't put the saucepan on the rack because it was too tall .pronoun: it. A) the saucepan B) the rack", "output": "the rack", "explanation": "If the saucepan couldn't be put on the rack, the rack was probably taller than the person's reach. The pronoun \"it\" refers to the rack."}, {"input": "sentence: Arnold greatly influenced Jackson , though he lived two centuries earlier .pronoun: he. A) jackson B) arnold", "output": "arnold", "explanation": "For one person to influence another person, they should leave earlier than them, or contemporary to them. So the pronoun must refer to the influencer, which is Arnold."}, {"input": "sentence: cory knocked on dolly's door , but there was no answer . she was out .pronoun: she. A) cory B) dolly", "output": "dolly", "explanation": "From the context of the sentence, we know that the sentence \"She was out\" is resulted from Dolly not answering the door, so the pronoun \"she\" must refer to dolly."}, {"input": "sentence: There are pillars between me and the stages , and I can't see them .pronoun: them. A) the pillars B) the stages", "output": "the stages", "explanation": "The pillars are between someone and the stages, so they can probably see the pillars and not the stages."}], "Negative Examples": [{"input": "sentence: Joe and David's uncles can still beat them at tennis , even though they are 30 years younger .pronoun: they. A) joe and david B) joe and david's uncles", "output": "joe and david's uncles", "explanation": "There're two clues for resolving this pronoun. First, one's uncle is not usually 30 years younger than them. Second, younger people are usualy better at sports. The expression \"even though\" shows that there's a certain surprise in the sentence, so the person with better tennis performance should be the older one."}, {"input": "sentence: gaston passed the half-empty plate to hershel because he was full .pronoun: he. A) Gaston B) hershel", "output": "hershel", "explanation": "The person passing the leftover food must be the one who is full, so in this example \"he\" must refer to gatson."}, {"input": "sentence: The policeman arrested the gang member . He was trying to stop the drug trade in the neighborhood .pronoun: He. A) the police B) the gang member", "output": "the gang member", "explanation": "Deciding between a police and a gang member, it makes sense that the police is the one stopping the drug trade, not the gang member."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Dialogue", "Narrative"], "Instance": {"id": "task249-8d1c81418c984c70bc7bc0c226a0c6b7", "input": "sentence: Frank and Steve felt vindicated when their longtime rivals Bill and Pete revealed that they were the winners of the competition .pronoun: they. A) frank and steve B) bill and pete", "output": ["frank and steve"]}, "Instance License": ["CC BY 4.0"], "prediction": "frank and steve"}
+{"id": "task249-2665f00f94c44e01b545f734e71efda8", "Task": "task249_enhanced_wsc_pronoun_disambiguation", "Contributors": "['Pegah Alipoormolabashi']", "Source": ["enhanced_wsc"], "URL": ["https://github.com/mhany90/perturbed-wsc"], "Categories": ["Coreference Resolution"], "Reasoning": [], "Definition": ["In each example you will read a short sentence (or two). Then, a pronoun in the text is mentioned. Your task is to choose a referent which the mentioned pronoun refers to. You will be given two options in each case and one choice should seem much more likely to you than the other."], "Positive Examples": [{"input": "sentence: I couldn't put the saucepan on the rack because it was too tall .pronoun: it. A) the saucepan B) the rack", "output": "the rack", "explanation": "If the saucepan couldn't be put on the rack, the rack was probably taller than the person's reach. The pronoun \"it\" refers to the rack."}, {"input": "sentence: Arnold greatly influenced Jackson , though he lived two centuries earlier .pronoun: he. A) jackson B) arnold", "output": "arnold", "explanation": "For one person to influence another person, they should leave earlier than them, or contemporary to them. So the pronoun must refer to the influencer, which is Arnold."}, {"input": "sentence: cory knocked on dolly's door , but there was no answer . she was out .pronoun: she. A) cory B) dolly", "output": "dolly", "explanation": "From the context of the sentence, we know that the sentence \"She was out\" is resulted from Dolly not answering the door, so the pronoun \"she\" must refer to dolly."}, {"input": "sentence: There are pillars between me and the stages , and I can't see them .pronoun: them. A) the pillars B) the stages", "output": "the stages", "explanation": "The pillars are between someone and the stages, so they can probably see the pillars and not the stages."}], "Negative Examples": [{"input": "sentence: Joe and David's uncles can still beat them at tennis , even though they are 30 years younger .pronoun: they. A) joe and david B) joe and david's uncles", "output": "joe and david's uncles", "explanation": "There're two clues for resolving this pronoun. First, one's uncle is not usually 30 years younger than them. Second, younger people are usualy better at sports. The expression \"even though\" shows that there's a certain surprise in the sentence, so the person with better tennis performance should be the older one."}, {"input": "sentence: gaston passed the half-empty plate to hershel because he was full .pronoun: he. A) Gaston B) hershel", "output": "hershel", "explanation": "The person passing the leftover food must be the one who is full, so in this example \"he\" must refer to gatson."}, {"input": "sentence: The policeman arrested the gang member . He was trying to stop the drug trade in the neighborhood .pronoun: He. A) the police B) the gang member", "output": "the gang member", "explanation": "Deciding between a police and a gang member, it makes sense that the police is the one stopping the drug trade, not the gang member."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Dialogue", "Narrative"], "Instance": {"id": "task249-2665f00f94c44e01b545f734e71efda8", "input": "sentence: rick said \"check\" to grover as he took his bishop .pronoun: his. A) rick B) grover", "output": ["grover"]}, "Instance License": ["CC BY 4.0"], "prediction": "grover"}
+{"id": "task249-0ff580848bf24026a7a360aabe5451e1", "Task": "task249_enhanced_wsc_pronoun_disambiguation", "Contributors": "['Pegah Alipoormolabashi']", "Source": ["enhanced_wsc"], "URL": ["https://github.com/mhany90/perturbed-wsc"], "Categories": ["Coreference Resolution"], "Reasoning": [], "Definition": ["In each example you will read a short sentence (or two). Then, a pronoun in the text is mentioned. Your task is to choose a referent which the mentioned pronoun refers to. You will be given two options in each case and one choice should seem much more likely to you than the other."], "Positive Examples": [{"input": "sentence: I couldn't put the saucepan on the rack because it was too tall .pronoun: it. A) the saucepan B) the rack", "output": "the rack", "explanation": "If the saucepan couldn't be put on the rack, the rack was probably taller than the person's reach. The pronoun \"it\" refers to the rack."}, {"input": "sentence: Arnold greatly influenced Jackson , though he lived two centuries earlier .pronoun: he. A) jackson B) arnold", "output": "arnold", "explanation": "For one person to influence another person, they should leave earlier than them, or contemporary to them. So the pronoun must refer to the influencer, which is Arnold."}, {"input": "sentence: cory knocked on dolly's door , but there was no answer . she was out .pronoun: she. A) cory B) dolly", "output": "dolly", "explanation": "From the context of the sentence, we know that the sentence \"She was out\" is resulted from Dolly not answering the door, so the pronoun \"she\" must refer to dolly."}, {"input": "sentence: There are pillars between me and the stages , and I can't see them .pronoun: them. A) the pillars B) the stages", "output": "the stages", "explanation": "The pillars are between someone and the stages, so they can probably see the pillars and not the stages."}], "Negative Examples": [{"input": "sentence: Joe and David's uncles can still beat them at tennis , even though they are 30 years younger .pronoun: they. A) joe and david B) joe and david's uncles", "output": "joe and david's uncles", "explanation": "There're two clues for resolving this pronoun. First, one's uncle is not usually 30 years younger than them. Second, younger people are usualy better at sports. The expression \"even though\" shows that there's a certain surprise in the sentence, so the person with better tennis performance should be the older one."}, {"input": "sentence: gaston passed the half-empty plate to hershel because he was full .pronoun: he. A) Gaston B) hershel", "output": "hershel", "explanation": "The person passing the leftover food must be the one who is full, so in this example \"he\" must refer to gatson."}, {"input": "sentence: The policeman arrested the gang member . He was trying to stop the drug trade in the neighborhood .pronoun: He. A) the police B) the gang member", "output": "the gang member", "explanation": "Deciding between a police and a gang member, it makes sense that the police is the one stopping the drug trade, not the gang member."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Dialogue", "Narrative"], "Instance": {"id": "task249-0ff580848bf24026a7a360aabe5451e1", "input": "sentence: the mold rolled off the rack because it wasn't level .pronoun: it. A) the mold B) the rack", "output": ["the rack"]}, "Instance License": ["CC BY 4.0"], "prediction": "the mold"}
+{"id": "task957-aed1fc627aaa499895974355dd89bf3c", "Task": "task957_e2e_nlg_text_generation_generate", "Contributors": "['Gary Haizhi Lai']", "Source": ["e2e"], "URL": ["https://arxiv.org/abs/1706.09254"], "Categories": ["Data to Text"], "Reasoning": ["Reasoning on Objects"], "Definition": ["In this task, we ask you convert a data table of restaurant descriptions into fluent natural-sounding English sentences. The input is a string of key-value pairs; the output should be a natural and grammatical English sentence containing all the information from the input."], "Positive Examples": [{"input": "name[Aromi], eatType[restaurant], food[English], area[city centre]", "output": "Aromi is an English restaurant in the city centre.", "explanation": "The output sentence faithfully converts the data in the input into a natural-sounding sentence."}, {"input": "name[The Rice Boat], food[Indian], priceRange[cheap], customer rating[5 out of 5], area[city centre], familyFriendly[yes], near[Express by Holiday Inn]", "output": "The Rice Boat is a cheap Indian restaurant in the center of the city near Express by Holiday Inn. It is family friendly and has the highest customer rating.", "explanation": "The output sentence correctly contains all the information from the input. It is grammatical and idiomatic."}], "Negative Examples": [{"input": "name[Blue Spice], eatType[coffee shop], priceRange[more than \u00a330], customer rating[5 out of 5], area[riverside], familyFriendly[yes], near[Avalon]", "output": "Blue Spice is a Colombian coffee shop located by the riverside, near Avalon in Boston. Its prices are over \u00a330. Its customer ratings are 5 out of 5.", "explanation": "While the output contains most of the information from the input, it hallucinates by adding ungrounded information such as \"Colombian\" and \"Boston\"."}, {"input": "name[The Mill], eatType[restaurant], area[riverside], near[The Rice Boat]", "output": "A restaurant The Mill, can find near the riverside next to The Rice Boat.", "explanation": "Note that your answers should be grammatically correct and fluent. So, this is a bad example."}, {"input": "name[The Waterman], food[Japanese], priceRange[less than \u00a320], customer rating[average], area[riverside], familyFriendly[yes]", "output": "The Waterman is an expensive family-friendly Chinese restaurant with average customer rating in riverside", "explanation": "The output contains incorrect information such as \"expensive\" and \"Chinese restaurant\""}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Public Places -> Restaurants"], "Instance": {"id": "task957-aed1fc627aaa499895974355dd89bf3c", "input": "name[Zizzi], eatType[restaurant], priceRange[cheap], area[riverside]", "output": ["Zizzi is a cheap restaurant in the riverside area."]}, "Instance License": ["CC BY-SA 4.0"], "prediction": "The Zizzi is a cheap Italian restaurant in the riverside."}
+{"id": "task957-4b6d2b2162c743648253c07e96c27576", "Task": "task957_e2e_nlg_text_generation_generate", "Contributors": "['Gary Haizhi Lai']", "Source": ["e2e"], "URL": ["https://arxiv.org/abs/1706.09254"], "Categories": ["Data to Text"], "Reasoning": ["Reasoning on Objects"], "Definition": ["In this task, we ask you convert a data table of restaurant descriptions into fluent natural-sounding English sentences. The input is a string of key-value pairs; the output should be a natural and grammatical English sentence containing all the information from the input."], "Positive Examples": [{"input": "name[Aromi], eatType[restaurant], food[English], area[city centre]", "output": "Aromi is an English restaurant in the city centre.", "explanation": "The output sentence faithfully converts the data in the input into a natural-sounding sentence."}, {"input": "name[The Rice Boat], food[Indian], priceRange[cheap], customer rating[5 out of 5], area[city centre], familyFriendly[yes], near[Express by Holiday Inn]", "output": "The Rice Boat is a cheap Indian restaurant in the center of the city near Express by Holiday Inn. It is family friendly and has the highest customer rating.", "explanation": "The output sentence correctly contains all the information from the input. It is grammatical and idiomatic."}], "Negative Examples": [{"input": "name[Blue Spice], eatType[coffee shop], priceRange[more than \u00a330], customer rating[5 out of 5], area[riverside], familyFriendly[yes], near[Avalon]", "output": "Blue Spice is a Colombian coffee shop located by the riverside, near Avalon in Boston. Its prices are over \u00a330. Its customer ratings are 5 out of 5.", "explanation": "While the output contains most of the information from the input, it hallucinates by adding ungrounded information such as \"Colombian\" and \"Boston\"."}, {"input": "name[The Mill], eatType[restaurant], area[riverside], near[The Rice Boat]", "output": "A restaurant The Mill, can find near the riverside next to The Rice Boat.", "explanation": "Note that your answers should be grammatically correct and fluent. So, this is a bad example."}, {"input": "name[The Waterman], food[Japanese], priceRange[less than \u00a320], customer rating[average], area[riverside], familyFriendly[yes]", "output": "The Waterman is an expensive family-friendly Chinese restaurant with average customer rating in riverside", "explanation": "The output contains incorrect information such as \"expensive\" and \"Chinese restaurant\""}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Public Places -> Restaurants"], "Instance": {"id": "task957-4b6d2b2162c743648253c07e96c27576", "input": "name[The Vaults], food[French], priceRange[more than \u00a330], familyFriendly[yes]", "output": ["There is a child friendly French restaurant with a price range of more than \u00a330 called The Vaults."]}, "Instance License": ["CC BY-SA 4.0"], "prediction": "The Vaults is a French restaurant in the city centre. It has a family friendly atmosphere and is located near the city centre."}
+{"id": "task957-6993553ec46346b6bf962e7fe6813d15", "Task": "task957_e2e_nlg_text_generation_generate", "Contributors": "['Gary Haizhi Lai']", "Source": ["e2e"], "URL": ["https://arxiv.org/abs/1706.09254"], "Categories": ["Data to Text"], "Reasoning": ["Reasoning on Objects"], "Definition": ["In this task, we ask you convert a data table of restaurant descriptions into fluent natural-sounding English sentences. The input is a string of key-value pairs; the output should be a natural and grammatical English sentence containing all the information from the input."], "Positive Examples": [{"input": "name[Aromi], eatType[restaurant], food[English], area[city centre]", "output": "Aromi is an English restaurant in the city centre.", "explanation": "The output sentence faithfully converts the data in the input into a natural-sounding sentence."}, {"input": "name[The Rice Boat], food[Indian], priceRange[cheap], customer rating[5 out of 5], area[city centre], familyFriendly[yes], near[Express by Holiday Inn]", "output": "The Rice Boat is a cheap Indian restaurant in the center of the city near Express by Holiday Inn. It is family friendly and has the highest customer rating.", "explanation": "The output sentence correctly contains all the information from the input. It is grammatical and idiomatic."}], "Negative Examples": [{"input": "name[Blue Spice], eatType[coffee shop], priceRange[more than \u00a330], customer rating[5 out of 5], area[riverside], familyFriendly[yes], near[Avalon]", "output": "Blue Spice is a Colombian coffee shop located by the riverside, near Avalon in Boston. Its prices are over \u00a330. Its customer ratings are 5 out of 5.", "explanation": "While the output contains most of the information from the input, it hallucinates by adding ungrounded information such as \"Colombian\" and \"Boston\"."}, {"input": "name[The Mill], eatType[restaurant], area[riverside], near[The Rice Boat]", "output": "A restaurant The Mill, can find near the riverside next to The Rice Boat.", "explanation": "Note that your answers should be grammatically correct and fluent. So, this is a bad example."}, {"input": "name[The Waterman], food[Japanese], priceRange[less than \u00a320], customer rating[average], area[riverside], familyFriendly[yes]", "output": "The Waterman is an expensive family-friendly Chinese restaurant with average customer rating in riverside", "explanation": "The output contains incorrect information such as \"expensive\" and \"Chinese restaurant\""}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Public Places -> Restaurants"], "Instance": {"id": "task957-6993553ec46346b6bf962e7fe6813d15", "input": "name[The Olive Grove], eatType[pub], food[French], priceRange[more than \u00a330], area[riverside], familyFriendly[yes]", "output": ["The Olive Grove is a child-friendly pub, serving French food and is suitable for those with a budget of more than \u00a330."]}, "Instance License": ["CC BY-SA 4.0"], "prediction": "The Olive Grove is a pub in the centre of the city. It has a good customer rating and is family friendly."}
+{"id": "task957-b877c721990546eca8bf56bfc48ba142", "Task": "task957_e2e_nlg_text_generation_generate", "Contributors": "['Gary Haizhi Lai']", "Source": ["e2e"], "URL": ["https://arxiv.org/abs/1706.09254"], "Categories": ["Data to Text"], "Reasoning": ["Reasoning on Objects"], "Definition": ["In this task, we ask you convert a data table of restaurant descriptions into fluent natural-sounding English sentences. The input is a string of key-value pairs; the output should be a natural and grammatical English sentence containing all the information from the input."], "Positive Examples": [{"input": "name[Aromi], eatType[restaurant], food[English], area[city centre]", "output": "Aromi is an English restaurant in the city centre.", "explanation": "The output sentence faithfully converts the data in the input into a natural-sounding sentence."}, {"input": "name[The Rice Boat], food[Indian], priceRange[cheap], customer rating[5 out of 5], area[city centre], familyFriendly[yes], near[Express by Holiday Inn]", "output": "The Rice Boat is a cheap Indian restaurant in the center of the city near Express by Holiday Inn. It is family friendly and has the highest customer rating.", "explanation": "The output sentence correctly contains all the information from the input. It is grammatical and idiomatic."}], "Negative Examples": [{"input": "name[Blue Spice], eatType[coffee shop], priceRange[more than \u00a330], customer rating[5 out of 5], area[riverside], familyFriendly[yes], near[Avalon]", "output": "Blue Spice is a Colombian coffee shop located by the riverside, near Avalon in Boston. Its prices are over \u00a330. Its customer ratings are 5 out of 5.", "explanation": "While the output contains most of the information from the input, it hallucinates by adding ungrounded information such as \"Colombian\" and \"Boston\"."}, {"input": "name[The Mill], eatType[restaurant], area[riverside], near[The Rice Boat]", "output": "A restaurant The Mill, can find near the riverside next to The Rice Boat.", "explanation": "Note that your answers should be grammatically correct and fluent. So, this is a bad example."}, {"input": "name[The Waterman], food[Japanese], priceRange[less than \u00a320], customer rating[average], area[riverside], familyFriendly[yes]", "output": "The Waterman is an expensive family-friendly Chinese restaurant with average customer rating in riverside", "explanation": "The output contains incorrect information such as \"expensive\" and \"Chinese restaurant\""}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Public Places -> Restaurants"], "Instance": {"id": "task957-b877c721990546eca8bf56bfc48ba142", "input": "name[The Eagle], eatType[coffee shop], food[Indian], priceRange[cheap], customer rating[5 out of 5], area[riverside], familyFriendly[yes], near[Burger King]", "output": ["The Eagle is in the riverside area near Burger King.  It serves cheap Indian food and has a customer rating of 5 out of 5.  It is family friendly."]}, "Instance License": ["CC BY-SA 4.0"], "prediction": "The Eagle is a coffee shop in the riverside. It has a good customer rating and is near Burger King."}
+{"id": "task957-86e2be5f64ef4be88bd6a4826f1c46d4", "Task": "task957_e2e_nlg_text_generation_generate", "Contributors": "['Gary Haizhi Lai']", "Source": ["e2e"], "URL": ["https://arxiv.org/abs/1706.09254"], "Categories": ["Data to Text"], "Reasoning": ["Reasoning on Objects"], "Definition": ["In this task, we ask you convert a data table of restaurant descriptions into fluent natural-sounding English sentences. The input is a string of key-value pairs; the output should be a natural and grammatical English sentence containing all the information from the input."], "Positive Examples": [{"input": "name[Aromi], eatType[restaurant], food[English], area[city centre]", "output": "Aromi is an English restaurant in the city centre.", "explanation": "The output sentence faithfully converts the data in the input into a natural-sounding sentence."}, {"input": "name[The Rice Boat], food[Indian], priceRange[cheap], customer rating[5 out of 5], area[city centre], familyFriendly[yes], near[Express by Holiday Inn]", "output": "The Rice Boat is a cheap Indian restaurant in the center of the city near Express by Holiday Inn. It is family friendly and has the highest customer rating.", "explanation": "The output sentence correctly contains all the information from the input. It is grammatical and idiomatic."}], "Negative Examples": [{"input": "name[Blue Spice], eatType[coffee shop], priceRange[more than \u00a330], customer rating[5 out of 5], area[riverside], familyFriendly[yes], near[Avalon]", "output": "Blue Spice is a Colombian coffee shop located by the riverside, near Avalon in Boston. Its prices are over \u00a330. Its customer ratings are 5 out of 5.", "explanation": "While the output contains most of the information from the input, it hallucinates by adding ungrounded information such as \"Colombian\" and \"Boston\"."}, {"input": "name[The Mill], eatType[restaurant], area[riverside], near[The Rice Boat]", "output": "A restaurant The Mill, can find near the riverside next to The Rice Boat.", "explanation": "Note that your answers should be grammatically correct and fluent. So, this is a bad example."}, {"input": "name[The Waterman], food[Japanese], priceRange[less than \u00a320], customer rating[average], area[riverside], familyFriendly[yes]", "output": "The Waterman is an expensive family-friendly Chinese restaurant with average customer rating in riverside", "explanation": "The output contains incorrect information such as \"expensive\" and \"Chinese restaurant\""}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Public Places -> Restaurants"], "Instance": {"id": "task957-86e2be5f64ef4be88bd6a4826f1c46d4", "input": "name[Midsummer House], food[Italian], priceRange[high], customer rating[1 out of 5], near[All Bar One]", "output": ["There is a restaurant near All Bar One called Midsummer House that is expensive."]}, "Instance License": ["CC BY-SA 4.0"], "prediction": "Midsummer House is a Italian restaurant in the city centre near All Bar One."}
+{"id": "task418-9f8dc85573f546dda8ac6fb24f77ef0c", "Task": "task418_persent_title_generation", "Contributors": "['Kuntal Kumar Pal']", "Source": ["persent"], "URL": ["https://github.com/MHDBST/PerSenT"], "Categories": ["Title Generation"], "Reasoning": [], "Definition": ["Given a document, generate a short title of the document. The title should convey the main idea/event/topic about which the document is being written. Note that URLs in the text have been replaced with [Link]."], "Positive Examples": [{"input": "In a letter posted on the White House web site Tuesday  John Brennan  assistant to President Barack Obama for homeland security and counterterrorism  said Schmidt will have regular access to the president and play a vital role in the country's security.\n Schmidt's selection comes more than 10 months after Obama declared cyber security a priority and ordered a broad administration review.\n A senior White House official said Obama was personally involved in the selection process and chose Schmidt because of his unique background and skills. Schmidt will have regular and direct access to the president for cyber security issues  the official said. The official spoke on the condition of anonymity to discuss the selection process.\n At the same time  cyber experts and potential job candidates have complained that the position lacks the budgetary and policy-making authority needed to be successful. Schmidt will report to the National Security Council and closely support the National Economic Council on cyber issues.\n Schmidt's selection suggests that economic and business interests in the White House held more sway in the selection process. Schmidt  president and CEO of the Information Security Forum  a nonprofit international consortium that conducts research in information security  has served as chief security officer for Microsoft and as cyber security chief for online auction giant eBay. He was reportedly preferred by Lawrence Summers  director of the economic council. A good format for the titel can be the simple subject + object + verb.", "output": "White House picks new cyber coordinator", "explanation": "The title is relevant to the main topic of document, that is, the selection of Schmidt as the cybersecutiy chief."}, {"input": "India's financial capital Mumbai will get another airport  the Navi Mumbai airport  after the central government Monday gave a go-ahead to the project  after months of uncertainty over flouting of environmental norms.\n will get another airport  the Navi Mumbai airport  after the central government Monday gave a go-ahead to the project  after months of uncertainty over flouting of environmental norms.\n \"Around 85 to 90 percent of our (environmental) concerns have been addressed. The process of building the Navi Mumbai airport can start today. With these compromises we are fully on board and will ensure speedy work \" Indian Environment Minister Jairam Ramesh told the media here.\n The Navi Mumbai airport  which has been planned some 30 kilometers away from the current Chattrapati Shivaji airport in Mumbai  had been a contentious issue because of its environmental impact due to its location. But  the Indian Environment Ministry finally cleared the project.\n Claiming that the plans for the airport have been modified so that one river instead of two will be diverted  the minister said: \"River Gadhi would not be diverted to make way for the airport and added that 161 hectares of mangroves would fall under Navi Mumbai airport.\"\n and added that 161 hectares of mangroves would fall under Navi Mumbai airport.\"\n \"We cannot leave aside the environmental concerns and Navi Mumbai airport sanction is classic example of respecting the norms. This should be the same for all mega projects. The Navi Mumbai airport clearance is crucial for Maharashtra. Relocation of some 3  000 families will be done at a fast pace. Some forest clearance is awaited but should not be a problem \" Chavan said.", "output": "Indian govt gives go-ahead to second commercial airport in Mumbai", "explanation": "The title describes the main event of the document. Rest of the information in the paragraph support that Mumbai is getting a second commercial airport. "}], "Negative Examples": [{"input": "LeBron  James  has had a strong response after a Fox News host said that instead of criticizing President Donald Trump  he should just \"shut up and dribble.\"\nThis isn't the first time  James  has used  his  shoes to make a statement.\nIn December when the Cavs played in D.C. he  wore black and white sneakers that said \"Equality.\"", "output": "Fox News host asked LeBron to shut up", "explanation": "This is not the main topic of the document. The main topic is about LeBron wearing shoes to make public statements which is supported by the last sentence as well."}, {"input": "Lauren Cohan's Walking Dead fate may be written in the Whiskey Cavalier. While the show hasn't been picked up yet   Cohan  hasn't yet signed on for season 9 of Walking Dead and rumors have circulated for months about her possible exit from the zombie show. Just two days ago  showrunner Scott Gimple told TVLine that  he is incredibly hopeful about working out a new deal with  Cohan   who has played Maggie since the second season. \"These things do happen in TV\" he  said. But we are talking.", "output": "Scott Gimple signed Lauren Cohan for season 9", "explanation": "Though the topic is relevant  and have correct names from the document, this is incorrect fact, as it is mentioned that Cohan hasn't yet signed. "}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["News"], "Instance": {"id": "task418-9f8dc85573f546dda8ac6fb24f77ef0c", "input": "Billionaire Prince Alwaleed bin Talal  was picked up at  his  desert camp  the senior official said. Authorities did not disclose the evidence that prompted the arrests.\n Prince Alwaleed bin Talal  presides over a vast financial empire (estimated $35 billion in 2015):\nAlwaleed is the largest individual shareholder of Citigroup  the second-largest voting shareholder in 21st Century Fox and owns a number of hotels. TIME even called  him  \"Arabian Warren Buffet\".\nMBS  as  the Crown Prince  is known  is the leader who is launching what modernizers hope will be a Saudi Version of the Meiji Restoration[ii] in Japan  transforming the political economy and culture out of necessity \u00e2\u0080\u0093 in order to survive in the modern world system. The Saudis have practiced religious and cultural isolationism  while their oil allowed the country to avoid the necessity of building an economy that could supply anything else that the rest of the world would be willing to pay for.\nOf the people arrested   Alwaleed bin Tala  is the most intriguing for Americans thanks to  his  Twitter sparring with candidate Trump during the election  and for a startling connection unearthed by Jack Cashill more than five years ago in World New Daily.", "output": ["Modernizers launch a coup within the House of Saud"]}, "Instance License": ["Unknown"], "prediction": "Billionaire Prince Alwaleed bin Talal arrested at desert camp"}
+{"id": "task418-eb9846da5af04293a3b08f426db46e7e", "Task": "task418_persent_title_generation", "Contributors": "['Kuntal Kumar Pal']", "Source": ["persent"], "URL": ["https://github.com/MHDBST/PerSenT"], "Categories": ["Title Generation"], "Reasoning": [], "Definition": ["Given a document, generate a short title of the document. The title should convey the main idea/event/topic about which the document is being written. Note that URLs in the text have been replaced with [Link]."], "Positive Examples": [{"input": "In a letter posted on the White House web site Tuesday  John Brennan  assistant to President Barack Obama for homeland security and counterterrorism  said Schmidt will have regular access to the president and play a vital role in the country's security.\n Schmidt's selection comes more than 10 months after Obama declared cyber security a priority and ordered a broad administration review.\n A senior White House official said Obama was personally involved in the selection process and chose Schmidt because of his unique background and skills. Schmidt will have regular and direct access to the president for cyber security issues  the official said. The official spoke on the condition of anonymity to discuss the selection process.\n At the same time  cyber experts and potential job candidates have complained that the position lacks the budgetary and policy-making authority needed to be successful. Schmidt will report to the National Security Council and closely support the National Economic Council on cyber issues.\n Schmidt's selection suggests that economic and business interests in the White House held more sway in the selection process. Schmidt  president and CEO of the Information Security Forum  a nonprofit international consortium that conducts research in information security  has served as chief security officer for Microsoft and as cyber security chief for online auction giant eBay. He was reportedly preferred by Lawrence Summers  director of the economic council. A good format for the titel can be the simple subject + object + verb.", "output": "White House picks new cyber coordinator", "explanation": "The title is relevant to the main topic of document, that is, the selection of Schmidt as the cybersecutiy chief."}, {"input": "India's financial capital Mumbai will get another airport  the Navi Mumbai airport  after the central government Monday gave a go-ahead to the project  after months of uncertainty over flouting of environmental norms.\n will get another airport  the Navi Mumbai airport  after the central government Monday gave a go-ahead to the project  after months of uncertainty over flouting of environmental norms.\n \"Around 85 to 90 percent of our (environmental) concerns have been addressed. The process of building the Navi Mumbai airport can start today. With these compromises we are fully on board and will ensure speedy work \" Indian Environment Minister Jairam Ramesh told the media here.\n The Navi Mumbai airport  which has been planned some 30 kilometers away from the current Chattrapati Shivaji airport in Mumbai  had been a contentious issue because of its environmental impact due to its location. But  the Indian Environment Ministry finally cleared the project.\n Claiming that the plans for the airport have been modified so that one river instead of two will be diverted  the minister said: \"River Gadhi would not be diverted to make way for the airport and added that 161 hectares of mangroves would fall under Navi Mumbai airport.\"\n and added that 161 hectares of mangroves would fall under Navi Mumbai airport.\"\n \"We cannot leave aside the environmental concerns and Navi Mumbai airport sanction is classic example of respecting the norms. This should be the same for all mega projects. The Navi Mumbai airport clearance is crucial for Maharashtra. Relocation of some 3  000 families will be done at a fast pace. Some forest clearance is awaited but should not be a problem \" Chavan said.", "output": "Indian govt gives go-ahead to second commercial airport in Mumbai", "explanation": "The title describes the main event of the document. Rest of the information in the paragraph support that Mumbai is getting a second commercial airport. "}], "Negative Examples": [{"input": "LeBron  James  has had a strong response after a Fox News host said that instead of criticizing President Donald Trump  he should just \"shut up and dribble.\"\nThis isn't the first time  James  has used  his  shoes to make a statement.\nIn December when the Cavs played in D.C. he  wore black and white sneakers that said \"Equality.\"", "output": "Fox News host asked LeBron to shut up", "explanation": "This is not the main topic of the document. The main topic is about LeBron wearing shoes to make public statements which is supported by the last sentence as well."}, {"input": "Lauren Cohan's Walking Dead fate may be written in the Whiskey Cavalier. While the show hasn't been picked up yet   Cohan  hasn't yet signed on for season 9 of Walking Dead and rumors have circulated for months about her possible exit from the zombie show. Just two days ago  showrunner Scott Gimple told TVLine that  he is incredibly hopeful about working out a new deal with  Cohan   who has played Maggie since the second season. \"These things do happen in TV\" he  said. But we are talking.", "output": "Scott Gimple signed Lauren Cohan for season 9", "explanation": "Though the topic is relevant  and have correct names from the document, this is incorrect fact, as it is mentioned that Cohan hasn't yet signed. "}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["News"], "Instance": {"id": "task418-eb9846da5af04293a3b08f426db46e7e", "input": "YouTube star Logan Paul  says  he 's going to grow from  his  mistakes after last month's incident  in which  he  received news-making backlash after posting images of what appeared to be a suicide victim online.  Paul  says  he 's a \"good guy who made a bad decision \" and says some of the \"tough\" comments  he  has received have even included people calling on  him  to kill  himself .\n\"It's been tough  'cause ironically I'm being told to commit suicide  myself  \"  he  said on ABC's \"Good Morning America\" on Thursday. \"Millions of people literally telling me they hate me  to go die in a fire. Like  the most horrible  horrific things.\"\n Paul  says that  he  realizes the impact of  his  actions  and accepts the criticism  he  has received as fair. At the same time   he  also said that parents should monitor what their children watch.\n He  added that  he  does not think of  his  target audience as children.\n\"Sometimes I cuss. Sometimes I make inappropriate jokes \"  he  said. \"I want to make jokes that kids my age are going to like ... Now I will say I'm much more aware of the impact that my actions have on  myself  and others.\"\nLast month   Paul  posted video of  him  in a forest near Mount Fuji in Japan near what seemed to be a body hanging from a tree. YouTube says the images violated its policies and suspended  him .\n Paul  called the posting a \"horrible lack of judgment.\"  He  says  he 'll \"think twice ... maybe three times\" about what  he  posts.\nLast week   Paul  returned to the video sharing platform with a suicide prevention video.  He  told \"Good Morning America\"  he 's hopeful for  his  future.\n\"I think I'm going to earn a second chance \"  he  said. \"I don't think everyone should get a second chance.\"", "output": ["YouTube star Logan Paul wants \"second chance\" after \" suicide forest\" video"]}, "Instance License": ["Unknown"], "prediction": "YouTube star Logan Paul says he's going to grow from his mistakes after posting images of what appeared to be a suicide victim online."}
+{"id": "task418-15186779caff4c729de76646e880d4f9", "Task": "task418_persent_title_generation", "Contributors": "['Kuntal Kumar Pal']", "Source": ["persent"], "URL": ["https://github.com/MHDBST/PerSenT"], "Categories": ["Title Generation"], "Reasoning": [], "Definition": ["Given a document, generate a short title of the document. The title should convey the main idea/event/topic about which the document is being written. Note that URLs in the text have been replaced with [Link]."], "Positive Examples": [{"input": "In a letter posted on the White House web site Tuesday  John Brennan  assistant to President Barack Obama for homeland security and counterterrorism  said Schmidt will have regular access to the president and play a vital role in the country's security.\n Schmidt's selection comes more than 10 months after Obama declared cyber security a priority and ordered a broad administration review.\n A senior White House official said Obama was personally involved in the selection process and chose Schmidt because of his unique background and skills. Schmidt will have regular and direct access to the president for cyber security issues  the official said. The official spoke on the condition of anonymity to discuss the selection process.\n At the same time  cyber experts and potential job candidates have complained that the position lacks the budgetary and policy-making authority needed to be successful. Schmidt will report to the National Security Council and closely support the National Economic Council on cyber issues.\n Schmidt's selection suggests that economic and business interests in the White House held more sway in the selection process. Schmidt  president and CEO of the Information Security Forum  a nonprofit international consortium that conducts research in information security  has served as chief security officer for Microsoft and as cyber security chief for online auction giant eBay. He was reportedly preferred by Lawrence Summers  director of the economic council. A good format for the titel can be the simple subject + object + verb.", "output": "White House picks new cyber coordinator", "explanation": "The title is relevant to the main topic of document, that is, the selection of Schmidt as the cybersecutiy chief."}, {"input": "India's financial capital Mumbai will get another airport  the Navi Mumbai airport  after the central government Monday gave a go-ahead to the project  after months of uncertainty over flouting of environmental norms.\n will get another airport  the Navi Mumbai airport  after the central government Monday gave a go-ahead to the project  after months of uncertainty over flouting of environmental norms.\n \"Around 85 to 90 percent of our (environmental) concerns have been addressed. The process of building the Navi Mumbai airport can start today. With these compromises we are fully on board and will ensure speedy work \" Indian Environment Minister Jairam Ramesh told the media here.\n The Navi Mumbai airport  which has been planned some 30 kilometers away from the current Chattrapati Shivaji airport in Mumbai  had been a contentious issue because of its environmental impact due to its location. But  the Indian Environment Ministry finally cleared the project.\n Claiming that the plans for the airport have been modified so that one river instead of two will be diverted  the minister said: \"River Gadhi would not be diverted to make way for the airport and added that 161 hectares of mangroves would fall under Navi Mumbai airport.\"\n and added that 161 hectares of mangroves would fall under Navi Mumbai airport.\"\n \"We cannot leave aside the environmental concerns and Navi Mumbai airport sanction is classic example of respecting the norms. This should be the same for all mega projects. The Navi Mumbai airport clearance is crucial for Maharashtra. Relocation of some 3  000 families will be done at a fast pace. Some forest clearance is awaited but should not be a problem \" Chavan said.", "output": "Indian govt gives go-ahead to second commercial airport in Mumbai", "explanation": "The title describes the main event of the document. Rest of the information in the paragraph support that Mumbai is getting a second commercial airport. "}], "Negative Examples": [{"input": "LeBron  James  has had a strong response after a Fox News host said that instead of criticizing President Donald Trump  he should just \"shut up and dribble.\"\nThis isn't the first time  James  has used  his  shoes to make a statement.\nIn December when the Cavs played in D.C. he  wore black and white sneakers that said \"Equality.\"", "output": "Fox News host asked LeBron to shut up", "explanation": "This is not the main topic of the document. The main topic is about LeBron wearing shoes to make public statements which is supported by the last sentence as well."}, {"input": "Lauren Cohan's Walking Dead fate may be written in the Whiskey Cavalier. While the show hasn't been picked up yet   Cohan  hasn't yet signed on for season 9 of Walking Dead and rumors have circulated for months about her possible exit from the zombie show. Just two days ago  showrunner Scott Gimple told TVLine that  he is incredibly hopeful about working out a new deal with  Cohan   who has played Maggie since the second season. \"These things do happen in TV\" he  said. But we are talking.", "output": "Scott Gimple signed Lauren Cohan for season 9", "explanation": "Though the topic is relevant  and have correct names from the document, this is incorrect fact, as it is mentioned that Cohan hasn't yet signed. "}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["News"], "Instance": {"id": "task418-15186779caff4c729de76646e880d4f9", "input": "\"Our coaches in our league stand up for what\u00e2\u0080\u0099s right  \" South Carolina coach Dawn Staley  said. \"The fact that they can speak out on it  it\u00e2\u0080\u0099s a great thing. It\u00e2\u0080\u0099s what America is all about  being able to exercise your First Amendment right.\"\n Staley  said  her  team  which won the NCAA title in April  still has not been invited to the White House.\n\"What I am most looking forward to is getting an invitation to the NCAA tournament in 2018  \" Staley  said. \"That's more important.\"\n\u00e2\u0080\u009cFrom someone who has had that experience and understanding what that experience means and for  Dawn  and their team  it\u00e2\u0080\u0099s kind of (a) slap in the face \" White said.\n\"We enjoyed the White House \" Warlick said. \"I hope that if  Dawn  wants to go and take  her  team  I hope  she  gets that opportunity. It's a special time.\"\nMore:  Dawn Staley  done discussing possible White House invite\nWhen Fargas went as a Tennessee player in 1991  the men's and women's national champion teams visited the White House together. So  she  was there to see President George H. W. Bush with the Duke team that featured Christian Laettner and Grant Hill.", "output": ["White House snub of South Carolina basketball 'a slap in the face'"]}, "Instance License": ["Unknown"], "prediction": "South Carolina coach Dawn Staley says her team still has not been invited to the White House."}
+{"id": "task418-3790d48a99034f8b8de77b362e822d39", "Task": "task418_persent_title_generation", "Contributors": "['Kuntal Kumar Pal']", "Source": ["persent"], "URL": ["https://github.com/MHDBST/PerSenT"], "Categories": ["Title Generation"], "Reasoning": [], "Definition": ["Given a document, generate a short title of the document. The title should convey the main idea/event/topic about which the document is being written. Note that URLs in the text have been replaced with [Link]."], "Positive Examples": [{"input": "In a letter posted on the White House web site Tuesday  John Brennan  assistant to President Barack Obama for homeland security and counterterrorism  said Schmidt will have regular access to the president and play a vital role in the country's security.\n Schmidt's selection comes more than 10 months after Obama declared cyber security a priority and ordered a broad administration review.\n A senior White House official said Obama was personally involved in the selection process and chose Schmidt because of his unique background and skills. Schmidt will have regular and direct access to the president for cyber security issues  the official said. The official spoke on the condition of anonymity to discuss the selection process.\n At the same time  cyber experts and potential job candidates have complained that the position lacks the budgetary and policy-making authority needed to be successful. Schmidt will report to the National Security Council and closely support the National Economic Council on cyber issues.\n Schmidt's selection suggests that economic and business interests in the White House held more sway in the selection process. Schmidt  president and CEO of the Information Security Forum  a nonprofit international consortium that conducts research in information security  has served as chief security officer for Microsoft and as cyber security chief for online auction giant eBay. He was reportedly preferred by Lawrence Summers  director of the economic council. A good format for the titel can be the simple subject + object + verb.", "output": "White House picks new cyber coordinator", "explanation": "The title is relevant to the main topic of document, that is, the selection of Schmidt as the cybersecutiy chief."}, {"input": "India's financial capital Mumbai will get another airport  the Navi Mumbai airport  after the central government Monday gave a go-ahead to the project  after months of uncertainty over flouting of environmental norms.\n will get another airport  the Navi Mumbai airport  after the central government Monday gave a go-ahead to the project  after months of uncertainty over flouting of environmental norms.\n \"Around 85 to 90 percent of our (environmental) concerns have been addressed. The process of building the Navi Mumbai airport can start today. With these compromises we are fully on board and will ensure speedy work \" Indian Environment Minister Jairam Ramesh told the media here.\n The Navi Mumbai airport  which has been planned some 30 kilometers away from the current Chattrapati Shivaji airport in Mumbai  had been a contentious issue because of its environmental impact due to its location. But  the Indian Environment Ministry finally cleared the project.\n Claiming that the plans for the airport have been modified so that one river instead of two will be diverted  the minister said: \"River Gadhi would not be diverted to make way for the airport and added that 161 hectares of mangroves would fall under Navi Mumbai airport.\"\n and added that 161 hectares of mangroves would fall under Navi Mumbai airport.\"\n \"We cannot leave aside the environmental concerns and Navi Mumbai airport sanction is classic example of respecting the norms. This should be the same for all mega projects. The Navi Mumbai airport clearance is crucial for Maharashtra. Relocation of some 3  000 families will be done at a fast pace. Some forest clearance is awaited but should not be a problem \" Chavan said.", "output": "Indian govt gives go-ahead to second commercial airport in Mumbai", "explanation": "The title describes the main event of the document. Rest of the information in the paragraph support that Mumbai is getting a second commercial airport. "}], "Negative Examples": [{"input": "LeBron  James  has had a strong response after a Fox News host said that instead of criticizing President Donald Trump  he should just \"shut up and dribble.\"\nThis isn't the first time  James  has used  his  shoes to make a statement.\nIn December when the Cavs played in D.C. he  wore black and white sneakers that said \"Equality.\"", "output": "Fox News host asked LeBron to shut up", "explanation": "This is not the main topic of the document. The main topic is about LeBron wearing shoes to make public statements which is supported by the last sentence as well."}, {"input": "Lauren Cohan's Walking Dead fate may be written in the Whiskey Cavalier. While the show hasn't been picked up yet   Cohan  hasn't yet signed on for season 9 of Walking Dead and rumors have circulated for months about her possible exit from the zombie show. Just two days ago  showrunner Scott Gimple told TVLine that  he is incredibly hopeful about working out a new deal with  Cohan   who has played Maggie since the second season. \"These things do happen in TV\" he  said. But we are talking.", "output": "Scott Gimple signed Lauren Cohan for season 9", "explanation": "Though the topic is relevant  and have correct names from the document, this is incorrect fact, as it is mentioned that Cohan hasn't yet signed. "}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["News"], "Instance": {"id": "task418-3790d48a99034f8b8de77b362e822d39", "input": "Skip in Skip  x Embed x Share CLOSE Michigan football coach Jim Harbaugh  discusses the quarterback situation Oct. 30  2017  heading into the Minnesota game. By Nick Baumgardner  DFP.\n Jim Harbaugh  didn't declare Brandon Peters as  his  starting quarterback after Saturday's win over Rutgers.\nAnd while  he  wasn't quite ready to do it Monday   he  more or less tabbed Michigan's redshirt freshman as the starter for Saturday night's game against Minnesota.\n\"Brandon will play  it's likely  he 'll start \"  Harbaugh  said Monday afternoon in Ann Arbor. \"We'll see.\"\nMinutes earlier   Harbaugh  told reporters  he  wasn't prepared to officially name a starter for Saturday (7:30 p.m.  Fox).  He  said Michigan would prepare both Peters and fifth-year senior John O'Korn to play against the Golden Gophers  as  he  says  he  did a week ago.\nWhen pressed   Harbaugh  said odds are Peters will be the starting quarterback this weekend.\n\"We're going to try to really build on what Brandon did in the ballgame  we're going into this game and we're going to prepare both quarterbacks \"  Harbaugh  said. \"Brandon's definitely going to play. The 51 percent would be on the side of him starting.\n Harbaugh  said  he  didn't want to jump the gun too fast  though  as  he 'd like to have Peters build off  his  impressive debut with a better week of practice heading into what appears to be  his  first college start.\nIn other words: It's all set up for  him   but Peters has to earn it this week.\n\"Our system is a meritocracy  where the best players play \"  Harbaugh  said. \"It was time for Brandon to play   he  went in and acquitted  himself  very well.  He  will play again this week.\n\"Build on the successes that  he  had in the ball game. Have a real good full week of practice.\"", "output": ["Brandon Peters will 'likely' start at QB for Michigan vs. Minnesota"]}, "Instance License": ["Unknown"], "prediction": "Michigan quarterback says he'll play Saturday game against Minnesota"}
+{"id": "task418-fcaae05f3ab446688654209184f5fbe7", "Task": "task418_persent_title_generation", "Contributors": "['Kuntal Kumar Pal']", "Source": ["persent"], "URL": ["https://github.com/MHDBST/PerSenT"], "Categories": ["Title Generation"], "Reasoning": [], "Definition": ["Given a document, generate a short title of the document. The title should convey the main idea/event/topic about which the document is being written. Note that URLs in the text have been replaced with [Link]."], "Positive Examples": [{"input": "In a letter posted on the White House web site Tuesday  John Brennan  assistant to President Barack Obama for homeland security and counterterrorism  said Schmidt will have regular access to the president and play a vital role in the country's security.\n Schmidt's selection comes more than 10 months after Obama declared cyber security a priority and ordered a broad administration review.\n A senior White House official said Obama was personally involved in the selection process and chose Schmidt because of his unique background and skills. Schmidt will have regular and direct access to the president for cyber security issues  the official said. The official spoke on the condition of anonymity to discuss the selection process.\n At the same time  cyber experts and potential job candidates have complained that the position lacks the budgetary and policy-making authority needed to be successful. Schmidt will report to the National Security Council and closely support the National Economic Council on cyber issues.\n Schmidt's selection suggests that economic and business interests in the White House held more sway in the selection process. Schmidt  president and CEO of the Information Security Forum  a nonprofit international consortium that conducts research in information security  has served as chief security officer for Microsoft and as cyber security chief for online auction giant eBay. He was reportedly preferred by Lawrence Summers  director of the economic council. A good format for the titel can be the simple subject + object + verb.", "output": "White House picks new cyber coordinator", "explanation": "The title is relevant to the main topic of document, that is, the selection of Schmidt as the cybersecutiy chief."}, {"input": "India's financial capital Mumbai will get another airport  the Navi Mumbai airport  after the central government Monday gave a go-ahead to the project  after months of uncertainty over flouting of environmental norms.\n will get another airport  the Navi Mumbai airport  after the central government Monday gave a go-ahead to the project  after months of uncertainty over flouting of environmental norms.\n \"Around 85 to 90 percent of our (environmental) concerns have been addressed. The process of building the Navi Mumbai airport can start today. With these compromises we are fully on board and will ensure speedy work \" Indian Environment Minister Jairam Ramesh told the media here.\n The Navi Mumbai airport  which has been planned some 30 kilometers away from the current Chattrapati Shivaji airport in Mumbai  had been a contentious issue because of its environmental impact due to its location. But  the Indian Environment Ministry finally cleared the project.\n Claiming that the plans for the airport have been modified so that one river instead of two will be diverted  the minister said: \"River Gadhi would not be diverted to make way for the airport and added that 161 hectares of mangroves would fall under Navi Mumbai airport.\"\n and added that 161 hectares of mangroves would fall under Navi Mumbai airport.\"\n \"We cannot leave aside the environmental concerns and Navi Mumbai airport sanction is classic example of respecting the norms. This should be the same for all mega projects. The Navi Mumbai airport clearance is crucial for Maharashtra. Relocation of some 3  000 families will be done at a fast pace. Some forest clearance is awaited but should not be a problem \" Chavan said.", "output": "Indian govt gives go-ahead to second commercial airport in Mumbai", "explanation": "The title describes the main event of the document. Rest of the information in the paragraph support that Mumbai is getting a second commercial airport. "}], "Negative Examples": [{"input": "LeBron  James  has had a strong response after a Fox News host said that instead of criticizing President Donald Trump  he should just \"shut up and dribble.\"\nThis isn't the first time  James  has used  his  shoes to make a statement.\nIn December when the Cavs played in D.C. he  wore black and white sneakers that said \"Equality.\"", "output": "Fox News host asked LeBron to shut up", "explanation": "This is not the main topic of the document. The main topic is about LeBron wearing shoes to make public statements which is supported by the last sentence as well."}, {"input": "Lauren Cohan's Walking Dead fate may be written in the Whiskey Cavalier. While the show hasn't been picked up yet   Cohan  hasn't yet signed on for season 9 of Walking Dead and rumors have circulated for months about her possible exit from the zombie show. Just two days ago  showrunner Scott Gimple told TVLine that  he is incredibly hopeful about working out a new deal with  Cohan   who has played Maggie since the second season. \"These things do happen in TV\" he  said. But we are talking.", "output": "Scott Gimple signed Lauren Cohan for season 9", "explanation": "Though the topic is relevant  and have correct names from the document, this is incorrect fact, as it is mentioned that Cohan hasn't yet signed. "}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["News"], "Instance": {"id": "task418-fcaae05f3ab446688654209184f5fbe7", "input": "Melanie Oudin and Francesca Schiavone also know how quickly perceptions can change. Oudin struggled with higher expectations since her crowd-pleasing run to the U.S. Open quarterfinals last year. So did Schiavone after her breakthrough French Open title in June.\n Oudin  18  needed just 56 minutes to beat Olga Savchuk of Ukraine 6-3  6-0. Schiavone  the Italian who won her first Grand Slam weeks before her 30th birthday  dispatched Ayumi Morita of Japan 6-1  6-0 in 58 minutes.\n If anything  Schiavone seems to be having fun in the spotlight. Asked why she's a fan favorite  she playfully replied  \"I attract them because I'm beautiful.\"\n Schiavone acknowledged that maybe she's a bit more motivated at a Grand Slam than at other tournaments. Schiavone  seeded No. 6  had been just 3-6 since winning at Roland Garros. She lost in the first round at Wimbledon and dropped her opening match at three other tournaments.\n She was pleased that her first-round match was in the grandstand -- a year ago  she was relegated to an outer court.\n \"I like to do it  because adrenaline is coming up and I enjoy much more than play in faraway court \" she said with a laugh. \"Maybe because I am 30 years old and now I want to enjoy with people.\"", "output": ["Clijsters wins 1st US Open match in straight sets"]}, "Instance License": ["Unknown"], "prediction": "French Open champions upset No. 1 seed in a flash."}
+{"id": "task614-cece91159e5f4ff1848a52c3e58d0ee3", "Task": "task614_glucose_cause_event_detection", "Contributors": "['Pegah Alipoormolabashi']", "Source": ["glucose"], "URL": ["https://github.com/ElementalCognition/glucose/"], "Categories": ["Cause Effect Classification"], "Reasoning": ["Reasoning on Actions"], "Definition": ["In this task, you will be given a short story. One sentence from the story is chosen. Consider the events that happen before that sentence, or are likely to have happened before it. Does any of them directly cause it, or simply make it possible? You should write your answer in the form \" A >causes/enables> B\". Try to use phrases and sentences from the story to compose your answer when possible."], "Positive Examples": [{"input": "story: It was bedtime at our house. Two of the three kids hit the pillow and fall asleep. The third is a trouble maker. For two hours he continues to get out of bed and want to play. Finally he becomes tired and falls asleep.\n selected sentence: Finally he becomes tired and falls asleep.", "output": "A kid wants to play before sleep >Causes/Enables> A kid eventually falls asleep", "explanation": "The selected sentence is about a kid falling sleep, the answer correctly identifices an event causing the sentence to happen."}, {"input": "story: Cindy woke up late. Cindy forgot her homework. Cindy dropped food on her skirt. She thought it was the worst day ever. She got home and her parents took her for ice cream and it wasn't bad.\n selected sentence: Cindy dropped food on her skirt.", "output": "Cindy eats >Causes/Enables> Cindy drops food on  her skirt", "explanation": "In this example the event causing Cindy to drop food on her skirt is not explicitly in the story, but the events imply that it might have happened."}, {"input": "story: Neil took a ferry to the island of Tasmania. There he admired the beautiful beaches. The sands were white and lovely. But try as he might, Neil missed seeing one thing. He could not find any Tasmanian devils!\n selected sentence: There he admired the beautiful beaches.", "output": "Neil goes to the island >Causes/Enables> Neil admires the beaches", "explanation": "In this exmple, Neil going to the island causes him to admire the beaches(It couldn't have happened if he hadn't gone to the island.)"}], "Negative Examples": [{"input": "story: Cheyenne was home from her vacation and she was tired. She slept until noon and then took a long shower. For the rest of the day she just laid around the house being lazy. Cheyenne's mom decided to give her a couple days to rest. However, after that there would be no more sitting around the house.\n selected sentence: Cheyenne's mom decided to give her a couple days to rest.", "output": "Cheyenne is tired from her vacation so Cheyenne's mom gives Cheyenne a couple of days to rest", "explanation": "The cause of the event is correctly chosen, but the answer format is incorrect. There should be >Causes/Enables> between the two events in your answer."}, {"input": "Sara was invited to the football game. She showed up at the gates early. Then, she went inside. She spent most of the game wandering around. At the end of the game, her team won.", "output": "Sara  goes  to  a football game  >Causes/Enables> Her team  wins ", "explanation": "The given answer is not the cause of the selected sentence."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Story"], "Instance": {"id": "task614-cece91159e5f4ff1848a52c3e58d0ee3", "input": "story: It was a cloudy day outside. Tina thought that it would rainy outside. She brought her umbrella with her on the bus. Tina lost her umbrella on the bus. She got rained on as she walked to work.\n selected sentence: Tina thought that it would rainy outside.", "output": ["Tina sees clouds >Causes/Enables> Tina thinks it will rain"]}, "Instance License": ["CC BY-NC 4.0"], "prediction": "Tina brought her umbrella with her on the bus."}
+{"id": "task614-71604f320dd54d508ac2f0485a576f1c", "Task": "task614_glucose_cause_event_detection", "Contributors": "['Pegah Alipoormolabashi']", "Source": ["glucose"], "URL": ["https://github.com/ElementalCognition/glucose/"], "Categories": ["Cause Effect Classification"], "Reasoning": ["Reasoning on Actions"], "Definition": ["In this task, you will be given a short story. One sentence from the story is chosen. Consider the events that happen before that sentence, or are likely to have happened before it. Does any of them directly cause it, or simply make it possible? You should write your answer in the form \" A >causes/enables> B\". Try to use phrases and sentences from the story to compose your answer when possible."], "Positive Examples": [{"input": "story: It was bedtime at our house. Two of the three kids hit the pillow and fall asleep. The third is a trouble maker. For two hours he continues to get out of bed and want to play. Finally he becomes tired and falls asleep.\n selected sentence: Finally he becomes tired and falls asleep.", "output": "A kid wants to play before sleep >Causes/Enables> A kid eventually falls asleep", "explanation": "The selected sentence is about a kid falling sleep, the answer correctly identifices an event causing the sentence to happen."}, {"input": "story: Cindy woke up late. Cindy forgot her homework. Cindy dropped food on her skirt. She thought it was the worst day ever. She got home and her parents took her for ice cream and it wasn't bad.\n selected sentence: Cindy dropped food on her skirt.", "output": "Cindy eats >Causes/Enables> Cindy drops food on  her skirt", "explanation": "In this example the event causing Cindy to drop food on her skirt is not explicitly in the story, but the events imply that it might have happened."}, {"input": "story: Neil took a ferry to the island of Tasmania. There he admired the beautiful beaches. The sands were white and lovely. But try as he might, Neil missed seeing one thing. He could not find any Tasmanian devils!\n selected sentence: There he admired the beautiful beaches.", "output": "Neil goes to the island >Causes/Enables> Neil admires the beaches", "explanation": "In this exmple, Neil going to the island causes him to admire the beaches(It couldn't have happened if he hadn't gone to the island.)"}], "Negative Examples": [{"input": "story: Cheyenne was home from her vacation and she was tired. She slept until noon and then took a long shower. For the rest of the day she just laid around the house being lazy. Cheyenne's mom decided to give her a couple days to rest. However, after that there would be no more sitting around the house.\n selected sentence: Cheyenne's mom decided to give her a couple days to rest.", "output": "Cheyenne is tired from her vacation so Cheyenne's mom gives Cheyenne a couple of days to rest", "explanation": "The cause of the event is correctly chosen, but the answer format is incorrect. There should be >Causes/Enables> between the two events in your answer."}, {"input": "Sara was invited to the football game. She showed up at the gates early. Then, she went inside. She spent most of the game wandering around. At the end of the game, her team won.", "output": "Sara  goes  to  a football game  >Causes/Enables> Her team  wins ", "explanation": "The given answer is not the cause of the selected sentence."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Story"], "Instance": {"id": "task614-71604f320dd54d508ac2f0485a576f1c", "input": "story: Nessa wanted to sing in the choir. She tried out for her school's choir. She sang her best, but it wasn't very good. She did not make the cut. Nessa was disappointed, but not very surprised.\n selected sentence: Nessa was disappointed, but not very surprised.", "output": ["Nessa doesn't make the cut >Causes/Enables> Nessa is disappointed"]}, "Instance License": ["CC BY-NC 4.0"], "prediction": "Nessa was disappointed."}
+{"id": "task614-8e107f3483684f22aca510016a472971", "Task": "task614_glucose_cause_event_detection", "Contributors": "['Pegah Alipoormolabashi']", "Source": ["glucose"], "URL": ["https://github.com/ElementalCognition/glucose/"], "Categories": ["Cause Effect Classification"], "Reasoning": ["Reasoning on Actions"], "Definition": ["In this task, you will be given a short story. One sentence from the story is chosen. Consider the events that happen before that sentence, or are likely to have happened before it. Does any of them directly cause it, or simply make it possible? You should write your answer in the form \" A >causes/enables> B\". Try to use phrases and sentences from the story to compose your answer when possible."], "Positive Examples": [{"input": "story: It was bedtime at our house. Two of the three kids hit the pillow and fall asleep. The third is a trouble maker. For two hours he continues to get out of bed and want to play. Finally he becomes tired and falls asleep.\n selected sentence: Finally he becomes tired and falls asleep.", "output": "A kid wants to play before sleep >Causes/Enables> A kid eventually falls asleep", "explanation": "The selected sentence is about a kid falling sleep, the answer correctly identifices an event causing the sentence to happen."}, {"input": "story: Cindy woke up late. Cindy forgot her homework. Cindy dropped food on her skirt. She thought it was the worst day ever. She got home and her parents took her for ice cream and it wasn't bad.\n selected sentence: Cindy dropped food on her skirt.", "output": "Cindy eats >Causes/Enables> Cindy drops food on  her skirt", "explanation": "In this example the event causing Cindy to drop food on her skirt is not explicitly in the story, but the events imply that it might have happened."}, {"input": "story: Neil took a ferry to the island of Tasmania. There he admired the beautiful beaches. The sands were white and lovely. But try as he might, Neil missed seeing one thing. He could not find any Tasmanian devils!\n selected sentence: There he admired the beautiful beaches.", "output": "Neil goes to the island >Causes/Enables> Neil admires the beaches", "explanation": "In this exmple, Neil going to the island causes him to admire the beaches(It couldn't have happened if he hadn't gone to the island.)"}], "Negative Examples": [{"input": "story: Cheyenne was home from her vacation and she was tired. She slept until noon and then took a long shower. For the rest of the day she just laid around the house being lazy. Cheyenne's mom decided to give her a couple days to rest. However, after that there would be no more sitting around the house.\n selected sentence: Cheyenne's mom decided to give her a couple days to rest.", "output": "Cheyenne is tired from her vacation so Cheyenne's mom gives Cheyenne a couple of days to rest", "explanation": "The cause of the event is correctly chosen, but the answer format is incorrect. There should be >Causes/Enables> between the two events in your answer."}, {"input": "Sara was invited to the football game. She showed up at the gates early. Then, she went inside. She spent most of the game wandering around. At the end of the game, her team won.", "output": "Sara  goes  to  a football game  >Causes/Enables> Her team  wins ", "explanation": "The given answer is not the cause of the selected sentence."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Story"], "Instance": {"id": "task614-8e107f3483684f22aca510016a472971", "input": "story: Edna was born the last of 14 kids. She grew up much younger than most of her siblings. When she became an adult, a few of her siblings has died. Edna lived to be 90 years old. When she died, she was the last of her siblings.\n selected sentence: When she died, she was the last of her siblings.", "output": ["Edna's siblings die before Edna >Causes/Enables> She is the last sibling to die"]}, "Instance License": ["CC BY-NC 4.0"], "prediction": "Edna grew up much younger than most of her siblings."}
+{"id": "task614-f9122ebdf11c4c5b96bc2380248113d3", "Task": "task614_glucose_cause_event_detection", "Contributors": "['Pegah Alipoormolabashi']", "Source": ["glucose"], "URL": ["https://github.com/ElementalCognition/glucose/"], "Categories": ["Cause Effect Classification"], "Reasoning": ["Reasoning on Actions"], "Definition": ["In this task, you will be given a short story. One sentence from the story is chosen. Consider the events that happen before that sentence, or are likely to have happened before it. Does any of them directly cause it, or simply make it possible? You should write your answer in the form \" A >causes/enables> B\". Try to use phrases and sentences from the story to compose your answer when possible."], "Positive Examples": [{"input": "story: It was bedtime at our house. Two of the three kids hit the pillow and fall asleep. The third is a trouble maker. For two hours he continues to get out of bed and want to play. Finally he becomes tired and falls asleep.\n selected sentence: Finally he becomes tired and falls asleep.", "output": "A kid wants to play before sleep >Causes/Enables> A kid eventually falls asleep", "explanation": "The selected sentence is about a kid falling sleep, the answer correctly identifices an event causing the sentence to happen."}, {"input": "story: Cindy woke up late. Cindy forgot her homework. Cindy dropped food on her skirt. She thought it was the worst day ever. She got home and her parents took her for ice cream and it wasn't bad.\n selected sentence: Cindy dropped food on her skirt.", "output": "Cindy eats >Causes/Enables> Cindy drops food on  her skirt", "explanation": "In this example the event causing Cindy to drop food on her skirt is not explicitly in the story, but the events imply that it might have happened."}, {"input": "story: Neil took a ferry to the island of Tasmania. There he admired the beautiful beaches. The sands were white and lovely. But try as he might, Neil missed seeing one thing. He could not find any Tasmanian devils!\n selected sentence: There he admired the beautiful beaches.", "output": "Neil goes to the island >Causes/Enables> Neil admires the beaches", "explanation": "In this exmple, Neil going to the island causes him to admire the beaches(It couldn't have happened if he hadn't gone to the island.)"}], "Negative Examples": [{"input": "story: Cheyenne was home from her vacation and she was tired. She slept until noon and then took a long shower. For the rest of the day she just laid around the house being lazy. Cheyenne's mom decided to give her a couple days to rest. However, after that there would be no more sitting around the house.\n selected sentence: Cheyenne's mom decided to give her a couple days to rest.", "output": "Cheyenne is tired from her vacation so Cheyenne's mom gives Cheyenne a couple of days to rest", "explanation": "The cause of the event is correctly chosen, but the answer format is incorrect. There should be >Causes/Enables> between the two events in your answer."}, {"input": "Sara was invited to the football game. She showed up at the gates early. Then, she went inside. She spent most of the game wandering around. At the end of the game, her team won.", "output": "Sara  goes  to  a football game  >Causes/Enables> Her team  wins ", "explanation": "The given answer is not the cause of the selected sentence."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Story"], "Instance": {"id": "task614-f9122ebdf11c4c5b96bc2380248113d3", "input": "story: One day, Billy's family went on a trip to the zoo. Billy went to see the lion's den with his sister. Billy walked up to the den and tapped on the glass. One of the lions leaped into the air and swung a paw at Billy. Billy was scared to approach any other animals from then on.\n selected sentence: Billy walked up to the den and tapped on the glass.", "output": ["Billy goes to the zoo >Causes/Enables> Billy taps on the glass"]}, "Instance License": ["CC BY-NC 4.0"], "prediction": "One of the lions leaped into the air and swung a paw at Billy."}
+{"id": "task614-4720962e9e5e472e9f334335f511a627", "Task": "task614_glucose_cause_event_detection", "Contributors": "['Pegah Alipoormolabashi']", "Source": ["glucose"], "URL": ["https://github.com/ElementalCognition/glucose/"], "Categories": ["Cause Effect Classification"], "Reasoning": ["Reasoning on Actions"], "Definition": ["In this task, you will be given a short story. One sentence from the story is chosen. Consider the events that happen before that sentence, or are likely to have happened before it. Does any of them directly cause it, or simply make it possible? You should write your answer in the form \" A >causes/enables> B\". Try to use phrases and sentences from the story to compose your answer when possible."], "Positive Examples": [{"input": "story: It was bedtime at our house. Two of the three kids hit the pillow and fall asleep. The third is a trouble maker. For two hours he continues to get out of bed and want to play. Finally he becomes tired and falls asleep.\n selected sentence: Finally he becomes tired and falls asleep.", "output": "A kid wants to play before sleep >Causes/Enables> A kid eventually falls asleep", "explanation": "The selected sentence is about a kid falling sleep, the answer correctly identifices an event causing the sentence to happen."}, {"input": "story: Cindy woke up late. Cindy forgot her homework. Cindy dropped food on her skirt. She thought it was the worst day ever. She got home and her parents took her for ice cream and it wasn't bad.\n selected sentence: Cindy dropped food on her skirt.", "output": "Cindy eats >Causes/Enables> Cindy drops food on  her skirt", "explanation": "In this example the event causing Cindy to drop food on her skirt is not explicitly in the story, but the events imply that it might have happened."}, {"input": "story: Neil took a ferry to the island of Tasmania. There he admired the beautiful beaches. The sands were white and lovely. But try as he might, Neil missed seeing one thing. He could not find any Tasmanian devils!\n selected sentence: There he admired the beautiful beaches.", "output": "Neil goes to the island >Causes/Enables> Neil admires the beaches", "explanation": "In this exmple, Neil going to the island causes him to admire the beaches(It couldn't have happened if he hadn't gone to the island.)"}], "Negative Examples": [{"input": "story: Cheyenne was home from her vacation and she was tired. She slept until noon and then took a long shower. For the rest of the day she just laid around the house being lazy. Cheyenne's mom decided to give her a couple days to rest. However, after that there would be no more sitting around the house.\n selected sentence: Cheyenne's mom decided to give her a couple days to rest.", "output": "Cheyenne is tired from her vacation so Cheyenne's mom gives Cheyenne a couple of days to rest", "explanation": "The cause of the event is correctly chosen, but the answer format is incorrect. There should be >Causes/Enables> between the two events in your answer."}, {"input": "Sara was invited to the football game. She showed up at the gates early. Then, she went inside. She spent most of the game wandering around. At the end of the game, her team won.", "output": "Sara  goes  to  a football game  >Causes/Enables> Her team  wins ", "explanation": "The given answer is not the cause of the selected sentence."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Story"], "Instance": {"id": "task614-4720962e9e5e472e9f334335f511a627", "input": "story: Tina borrowed my mom's car. She was on the way to her boyfriend's house. However, my mom needed to go Somewhere and tried to call Tina. Tina didn't pick up. My mom decided to drive my car to go to Tina.\n selected sentence: My mom decided to drive my car to go to Tina.", "output": ["Tina doesn't pick up her phone >Causes/Enables> My mom drives to TIna", "My mom borrows my car >Causes/Enables> My mom drives"]}, "Instance License": ["CC BY-NC 4.0"], "prediction": "Tina didn't pick up."}
+{"id": "task677-47f80bf3c7174813bca431c5da1fc493", "Task": "task677_ollie_sentence_answer_generation", "Contributors": "['Sai Surya Kaushik, Punyamurthula']", "Source": ["ollie"], "URL": ["https://huggingface.co/datasets/ollie"], "Categories": ["Data to Text"], "Reasoning": ["Relational Reasoning"], "Definition": ["Given two noun phrases (arguments) and relationship between them, form a sentence that expresses theses arguments with the given relationship."], "Positive Examples": [{"input": "Relationship: 'knock', Argument/Subject 1: 'someone', Argument/Subject 2: 'it'", "output": "The mailbox was bent and broken and looked like someone had knocked it over on purpose.", "explanation": "The generated sentence contains the two given subjects - someone and it, and they are related to each other on the basis of the given relationship - knocked"}, {"input": "Relationship: 'talk', Argument/Subject 1: 'you', Argument/Subject 2: 'me'", "output": "Are you seriously going to talk about me that way?", "explanation": "The generated sentence contains the two given subjects - you and me, and have the given relationship - talk, between them"}, {"input": "Relationship: 'read', Argument/Subject 1: 'I', Argument/Subject 2: 'book'", "output": "To expand my knowledge on the topic, I read a book.", "explanation": "The generated sentence contains the subjects - I and book, and they are related to each other on the basis of the given relation - read"}], "Negative Examples": [{"input": "Relationship: 'enter', Argument/Subject 1: 'I', Argument/Subject 2: 'name'", "output": "I erased Tom's name on the list of candidates.", "explanation": "The generated sentence contains the two given subjects - I and name, but they are not related to each other on the basis of the given relationship"}, {"input": "Relationship: 'officiate', Argument/Subject 1: 'stranger', Argument/Subject 2: 'game'", "output": "The stranger officiates the meal.", "explanation": "The generated sentence contains only one of the two given subjects - stranger and game, although they are related to each other on the basis of the given relationship - officiates"}, {"input": "Relationship: 'receive', Argument/Subject 1: 'You', Argument/Subject 2: 'fine'", "output": "I received a heavy fine but it failed to crush my spirit.", "explanation": "The generated sentence contains none of the two given subjects - You and fine, although they are related to each other on the basis of the given relationship - received"}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Narrative"], "Instance": {"id": "task677-47f80bf3c7174813bca431c5da1fc493", "input": "Relationship: 'return to', Argument/Subject 1: 'karsh', Argument/Subject 2: 'canada'", "output": ["Karsh returned to Canada four years later , eager to make his mark ."]}, "Instance License": ["University of Washington Academic License (https://raw.githubusercontent.com/knowitall/ollie/master/LICENSE)"], "prediction": "I'm going to Canada."}
+{"id": "task677-8ea83a5275014fca9ba95095cd5ff50c", "Task": "task677_ollie_sentence_answer_generation", "Contributors": "['Sai Surya Kaushik, Punyamurthula']", "Source": ["ollie"], "URL": ["https://huggingface.co/datasets/ollie"], "Categories": ["Data to Text"], "Reasoning": ["Relational Reasoning"], "Definition": ["Given two noun phrases (arguments) and relationship between them, form a sentence that expresses theses arguments with the given relationship."], "Positive Examples": [{"input": "Relationship: 'knock', Argument/Subject 1: 'someone', Argument/Subject 2: 'it'", "output": "The mailbox was bent and broken and looked like someone had knocked it over on purpose.", "explanation": "The generated sentence contains the two given subjects - someone and it, and they are related to each other on the basis of the given relationship - knocked"}, {"input": "Relationship: 'talk', Argument/Subject 1: 'you', Argument/Subject 2: 'me'", "output": "Are you seriously going to talk about me that way?", "explanation": "The generated sentence contains the two given subjects - you and me, and have the given relationship - talk, between them"}, {"input": "Relationship: 'read', Argument/Subject 1: 'I', Argument/Subject 2: 'book'", "output": "To expand my knowledge on the topic, I read a book.", "explanation": "The generated sentence contains the subjects - I and book, and they are related to each other on the basis of the given relation - read"}], "Negative Examples": [{"input": "Relationship: 'enter', Argument/Subject 1: 'I', Argument/Subject 2: 'name'", "output": "I erased Tom's name on the list of candidates.", "explanation": "The generated sentence contains the two given subjects - I and name, but they are not related to each other on the basis of the given relationship"}, {"input": "Relationship: 'officiate', Argument/Subject 1: 'stranger', Argument/Subject 2: 'game'", "output": "The stranger officiates the meal.", "explanation": "The generated sentence contains only one of the two given subjects - stranger and game, although they are related to each other on the basis of the given relationship - officiates"}, {"input": "Relationship: 'receive', Argument/Subject 1: 'You', Argument/Subject 2: 'fine'", "output": "I received a heavy fine but it failed to crush my spirit.", "explanation": "The generated sentence contains none of the two given subjects - You and fine, although they are related to each other on the basis of the given relationship - received"}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Narrative"], "Instance": {"id": "task677-8ea83a5275014fca9ba95095cd5ff50c", "input": "Relationship: 'be grow in', Argument/Subject 1: 'cotton', Argument/Subject 2: 'indium'", "output": ["Cotton is known to have been grown in India as early as 3,000 BC , but was almost ceratinly grown much earlier ."]}, "Instance License": ["University of Washington Academic License (https://raw.githubusercontent.com/knowitall/ollie/master/LICENSE)"], "prediction": "Be growing in with the other people."}
+{"id": "task677-f9739663ff294836baadb4aaa16f9558", "Task": "task677_ollie_sentence_answer_generation", "Contributors": "['Sai Surya Kaushik, Punyamurthula']", "Source": ["ollie"], "URL": ["https://huggingface.co/datasets/ollie"], "Categories": ["Data to Text"], "Reasoning": ["Relational Reasoning"], "Definition": ["Given two noun phrases (arguments) and relationship between them, form a sentence that expresses theses arguments with the given relationship."], "Positive Examples": [{"input": "Relationship: 'knock', Argument/Subject 1: 'someone', Argument/Subject 2: 'it'", "output": "The mailbox was bent and broken and looked like someone had knocked it over on purpose.", "explanation": "The generated sentence contains the two given subjects - someone and it, and they are related to each other on the basis of the given relationship - knocked"}, {"input": "Relationship: 'talk', Argument/Subject 1: 'you', Argument/Subject 2: 'me'", "output": "Are you seriously going to talk about me that way?", "explanation": "The generated sentence contains the two given subjects - you and me, and have the given relationship - talk, between them"}, {"input": "Relationship: 'read', Argument/Subject 1: 'I', Argument/Subject 2: 'book'", "output": "To expand my knowledge on the topic, I read a book.", "explanation": "The generated sentence contains the subjects - I and book, and they are related to each other on the basis of the given relation - read"}], "Negative Examples": [{"input": "Relationship: 'enter', Argument/Subject 1: 'I', Argument/Subject 2: 'name'", "output": "I erased Tom's name on the list of candidates.", "explanation": "The generated sentence contains the two given subjects - I and name, but they are not related to each other on the basis of the given relationship"}, {"input": "Relationship: 'officiate', Argument/Subject 1: 'stranger', Argument/Subject 2: 'game'", "output": "The stranger officiates the meal.", "explanation": "The generated sentence contains only one of the two given subjects - stranger and game, although they are related to each other on the basis of the given relationship - officiates"}, {"input": "Relationship: 'receive', Argument/Subject 1: 'You', Argument/Subject 2: 'fine'", "output": "I received a heavy fine but it failed to crush my spirit.", "explanation": "The generated sentence contains none of the two given subjects - You and fine, although they are related to each other on the basis of the given relationship - received"}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Narrative"], "Instance": {"id": "task677-f9739663ff294836baadb4aaa16f9558", "input": "Relationship: 'be bear in', Argument/Subject 1: 'david', Argument/Subject 2: 'virginium'", "output": ["David Commons was born 7/18/1800 in Virginia ."]}, "Instance License": ["University of Washington Academic License (https://raw.githubusercontent.com/knowitall/ollie/master/LICENSE)"], "prediction": "Be bear in."}
+{"id": "task677-6c55780f08404bc09ac7902daaea3d3e", "Task": "task677_ollie_sentence_answer_generation", "Contributors": "['Sai Surya Kaushik, Punyamurthula']", "Source": ["ollie"], "URL": ["https://huggingface.co/datasets/ollie"], "Categories": ["Data to Text"], "Reasoning": ["Relational Reasoning"], "Definition": ["Given two noun phrases (arguments) and relationship between them, form a sentence that expresses theses arguments with the given relationship."], "Positive Examples": [{"input": "Relationship: 'knock', Argument/Subject 1: 'someone', Argument/Subject 2: 'it'", "output": "The mailbox was bent and broken and looked like someone had knocked it over on purpose.", "explanation": "The generated sentence contains the two given subjects - someone and it, and they are related to each other on the basis of the given relationship - knocked"}, {"input": "Relationship: 'talk', Argument/Subject 1: 'you', Argument/Subject 2: 'me'", "output": "Are you seriously going to talk about me that way?", "explanation": "The generated sentence contains the two given subjects - you and me, and have the given relationship - talk, between them"}, {"input": "Relationship: 'read', Argument/Subject 1: 'I', Argument/Subject 2: 'book'", "output": "To expand my knowledge on the topic, I read a book.", "explanation": "The generated sentence contains the subjects - I and book, and they are related to each other on the basis of the given relation - read"}], "Negative Examples": [{"input": "Relationship: 'enter', Argument/Subject 1: 'I', Argument/Subject 2: 'name'", "output": "I erased Tom's name on the list of candidates.", "explanation": "The generated sentence contains the two given subjects - I and name, but they are not related to each other on the basis of the given relationship"}, {"input": "Relationship: 'officiate', Argument/Subject 1: 'stranger', Argument/Subject 2: 'game'", "output": "The stranger officiates the meal.", "explanation": "The generated sentence contains only one of the two given subjects - stranger and game, although they are related to each other on the basis of the given relationship - officiates"}, {"input": "Relationship: 'receive', Argument/Subject 1: 'You', Argument/Subject 2: 'fine'", "output": "I received a heavy fine but it failed to crush my spirit.", "explanation": "The generated sentence contains none of the two given subjects - You and fine, although they are related to each other on the basis of the given relationship - received"}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Narrative"], "Instance": {"id": "task677-6c55780f08404bc09ac7902daaea3d3e", "input": "Relationship: 'turn to', Argument/Subject 1: 'koenig', Argument/Subject 2: 'helena'", "output": ["Koenig gently squeezed her shoulder in silent support and turned to stand by Helena ."]}, "Instance License": ["University of Washington Academic License (https://raw.githubusercontent.com/knowitall/ollie/master/LICENSE)"], "prediction": "I'm going to the doctor's office."}
+{"id": "task677-834d7719f309491295e6d3d1be24b658", "Task": "task677_ollie_sentence_answer_generation", "Contributors": "['Sai Surya Kaushik, Punyamurthula']", "Source": ["ollie"], "URL": ["https://huggingface.co/datasets/ollie"], "Categories": ["Data to Text"], "Reasoning": ["Relational Reasoning"], "Definition": ["Given two noun phrases (arguments) and relationship between them, form a sentence that expresses theses arguments with the given relationship."], "Positive Examples": [{"input": "Relationship: 'knock', Argument/Subject 1: 'someone', Argument/Subject 2: 'it'", "output": "The mailbox was bent and broken and looked like someone had knocked it over on purpose.", "explanation": "The generated sentence contains the two given subjects - someone and it, and they are related to each other on the basis of the given relationship - knocked"}, {"input": "Relationship: 'talk', Argument/Subject 1: 'you', Argument/Subject 2: 'me'", "output": "Are you seriously going to talk about me that way?", "explanation": "The generated sentence contains the two given subjects - you and me, and have the given relationship - talk, between them"}, {"input": "Relationship: 'read', Argument/Subject 1: 'I', Argument/Subject 2: 'book'", "output": "To expand my knowledge on the topic, I read a book.", "explanation": "The generated sentence contains the subjects - I and book, and they are related to each other on the basis of the given relation - read"}], "Negative Examples": [{"input": "Relationship: 'enter', Argument/Subject 1: 'I', Argument/Subject 2: 'name'", "output": "I erased Tom's name on the list of candidates.", "explanation": "The generated sentence contains the two given subjects - I and name, but they are not related to each other on the basis of the given relationship"}, {"input": "Relationship: 'officiate', Argument/Subject 1: 'stranger', Argument/Subject 2: 'game'", "output": "The stranger officiates the meal.", "explanation": "The generated sentence contains only one of the two given subjects - stranger and game, although they are related to each other on the basis of the given relationship - officiates"}, {"input": "Relationship: 'receive', Argument/Subject 1: 'You', Argument/Subject 2: 'fine'", "output": "I received a heavy fine but it failed to crush my spirit.", "explanation": "The generated sentence contains none of the two given subjects - You and fine, although they are related to each other on the basis of the given relationship - received"}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Narrative"], "Instance": {"id": "task677-834d7719f309491295e6d3d1be24b658", "input": "Relationship: 'be empress of', Argument/Subject 1: 'victorium', Argument/Subject 2: 'indium'", "output": ["He wants to make Victoria empress of India ."]}, "Instance License": ["University of Washington Academic License (https://raw.githubusercontent.com/knowitall/ollie/master/LICENSE)"], "prediction": "Be empress of the world."}
+{"id": "task220-f88b55aa5d2842ce8f8c53d0d69d23a6", "Task": "task220_rocstories_title_classification", "Contributors": "['Anjana Arunkumar']", "Source": ["rocstories"], "URL": ["https://arxiv.org/pdf/1604.01696.pdf"], "Categories": ["Title Generation"], "Reasoning": ["Deductive Reasoning"], "Definition": ["In this task, you're given five sentences, numbered 1 through 5, and two options a and b for possible titles for the story. Your job is to choose the title that better fits the story. Indicate your choice by 'a' or 'b'."], "Positive Examples": [{"input": "Sentence 1: Marcus needed clothing for a business casual event. Sentence 2: All of his clothes were either too formal or too casual. Sentence 3: He decided to buy a pair of khakis. Sentence 4: The pair he bought fit him perfectly. Sentence 5: Marcus was happy to have the right clothes for the event. Choices: a. Marcus Buys Khakis. b. Marcus Works.", "output": "a", "explanation": "Marcus's reasons for buying khakis is established, followed by his purchase of them and reaction."}, {"input": "Sentence 1: Laura loved corn. Sentence 2: So she decided to grow some in her backyard. Sentence 3: The whole process of growing them made her very excited. Sentence 4: But she realized that they required too much water. Sentence 5: So Laura quickly abandoned her corn garden idea. Choices: a. Water Scarcity. b. Corn.", "output": "b", "explanation": "Laura was planning to plant corn, realized the infeasibility of the idea and then decided against it."}, {"input": "Sentence 1: Larry worked at an accounting firm. Sentence 2: It was a boring job but it paid the bills. Sentence 3: Larry grew tired of doing the same thing every day. Sentence 4: He had the idea to have an office party. Sentence 5: By lunch the whole office had passed out and nothing got done. Choices: a. Office Party. b. Lunchtime.", "output": "a", "explanation": "Larry's workplace and need for an office party are established, followed by the events of the office party."}, {"input": "Sentence 1: Ben found a frog in the creek. Sentence 2: It was green and slimy. Sentence 3: He took it home and put it in a bucket. Sentence 4: The next day, the frog was gone. Sentence 5: He'd jumped out and escaped! Choices: a. The Boy. b. The Frog.", "output": "b", "explanation": "Ben caught a frog, could not find it the next day and realized it had escaped."}], "Negative Examples": [{"input": "Sentence 1: My grandparents and I were going for a walk. Sentence 2: Suddenly, right in front of us, was a huge moose. Sentence 3: We were walking near some pine trees and turned a corner. Sentence 4: It was so close that it scared us, but they told me not to run. Sentence 5: We all stood still and soon the moose walked away without harm. Choices: a. Move. b. Up Close.", "output": "a", "explanation": "The people saw a moose, stopped walking, and allowed it to pass. The title is therefore incorrect."}, {"input": "Sentence 1: Mary sliced the purple eggplant. Sentence 2: Then she breaded each slice carefully before frying them. Sentence 3: She layered each breaded slice into her casserole dish. Sentence 4: Finally, she sprinkled parmesan cheese on top and baked it. Sentence 5: She poured homemade marinara sauce in the dish. Choices: a. Eggplant Parmesan. b. Mary.", "output": "b", "explanation": "The story describes how eggplant parmesan is made step by step. The title is therefore incorrect."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Narrative", "Story"], "Instance": {"id": "task220-f88b55aa5d2842ce8f8c53d0d69d23a6", "input": "Sentence 1: Tony was playing outside with his friends. Sentence 2: They discovered a large bee's nest. Sentence 3: Tony poked it with a stick. Sentence 4: As the bees swarmed out, many stung Tony. Sentence 5: Tony discovered he is allergic to bees. Choices: a. Hannah and Nate. b. Bee Allergy.", "output": ["b"]}, "Instance License": ["Unknown"], "prediction": "b"}
+{"id": "task220-2e83707f746a4231a65af8c587f1fda8", "Task": "task220_rocstories_title_classification", "Contributors": "['Anjana Arunkumar']", "Source": ["rocstories"], "URL": ["https://arxiv.org/pdf/1604.01696.pdf"], "Categories": ["Title Generation"], "Reasoning": ["Deductive Reasoning"], "Definition": ["In this task, you're given five sentences, numbered 1 through 5, and two options a and b for possible titles for the story. Your job is to choose the title that better fits the story. Indicate your choice by 'a' or 'b'."], "Positive Examples": [{"input": "Sentence 1: Marcus needed clothing for a business casual event. Sentence 2: All of his clothes were either too formal or too casual. Sentence 3: He decided to buy a pair of khakis. Sentence 4: The pair he bought fit him perfectly. Sentence 5: Marcus was happy to have the right clothes for the event. Choices: a. Marcus Buys Khakis. b. Marcus Works.", "output": "a", "explanation": "Marcus's reasons for buying khakis is established, followed by his purchase of them and reaction."}, {"input": "Sentence 1: Laura loved corn. Sentence 2: So she decided to grow some in her backyard. Sentence 3: The whole process of growing them made her very excited. Sentence 4: But she realized that they required too much water. Sentence 5: So Laura quickly abandoned her corn garden idea. Choices: a. Water Scarcity. b. Corn.", "output": "b", "explanation": "Laura was planning to plant corn, realized the infeasibility of the idea and then decided against it."}, {"input": "Sentence 1: Larry worked at an accounting firm. Sentence 2: It was a boring job but it paid the bills. Sentence 3: Larry grew tired of doing the same thing every day. Sentence 4: He had the idea to have an office party. Sentence 5: By lunch the whole office had passed out and nothing got done. Choices: a. Office Party. b. Lunchtime.", "output": "a", "explanation": "Larry's workplace and need for an office party are established, followed by the events of the office party."}, {"input": "Sentence 1: Ben found a frog in the creek. Sentence 2: It was green and slimy. Sentence 3: He took it home and put it in a bucket. Sentence 4: The next day, the frog was gone. Sentence 5: He'd jumped out and escaped! Choices: a. The Boy. b. The Frog.", "output": "b", "explanation": "Ben caught a frog, could not find it the next day and realized it had escaped."}], "Negative Examples": [{"input": "Sentence 1: My grandparents and I were going for a walk. Sentence 2: Suddenly, right in front of us, was a huge moose. Sentence 3: We were walking near some pine trees and turned a corner. Sentence 4: It was so close that it scared us, but they told me not to run. Sentence 5: We all stood still and soon the moose walked away without harm. Choices: a. Move. b. Up Close.", "output": "a", "explanation": "The people saw a moose, stopped walking, and allowed it to pass. The title is therefore incorrect."}, {"input": "Sentence 1: Mary sliced the purple eggplant. Sentence 2: Then she breaded each slice carefully before frying them. Sentence 3: She layered each breaded slice into her casserole dish. Sentence 4: Finally, she sprinkled parmesan cheese on top and baked it. Sentence 5: She poured homemade marinara sauce in the dish. Choices: a. Eggplant Parmesan. b. Mary.", "output": "b", "explanation": "The story describes how eggplant parmesan is made step by step. The title is therefore incorrect."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Narrative", "Story"], "Instance": {"id": "task220-2e83707f746a4231a65af8c587f1fda8", "input": "Sentence 1: Steve got home late from work and pulled into his parking lot. Sentence 2: He was annoyed to see there was a car parked in his reserved spot. Sentence 3: He left a note on the car and went to find street parking. Sentence 4: The next morning, there was a note taped to Steve's front door. Sentence 5: It was from a new neighbor, who apologized profusely for the mistake. Choices: a. Parking Problems. b. A Weighty Problem.", "output": ["a"]}, "Instance License": ["Unknown"], "prediction": "b"}
+{"id": "task220-91af85e2b1b54a8a8097d11ab2dfa766", "Task": "task220_rocstories_title_classification", "Contributors": "['Anjana Arunkumar']", "Source": ["rocstories"], "URL": ["https://arxiv.org/pdf/1604.01696.pdf"], "Categories": ["Title Generation"], "Reasoning": ["Deductive Reasoning"], "Definition": ["In this task, you're given five sentences, numbered 1 through 5, and two options a and b for possible titles for the story. Your job is to choose the title that better fits the story. Indicate your choice by 'a' or 'b'."], "Positive Examples": [{"input": "Sentence 1: Marcus needed clothing for a business casual event. Sentence 2: All of his clothes were either too formal or too casual. Sentence 3: He decided to buy a pair of khakis. Sentence 4: The pair he bought fit him perfectly. Sentence 5: Marcus was happy to have the right clothes for the event. Choices: a. Marcus Buys Khakis. b. Marcus Works.", "output": "a", "explanation": "Marcus's reasons for buying khakis is established, followed by his purchase of them and reaction."}, {"input": "Sentence 1: Laura loved corn. Sentence 2: So she decided to grow some in her backyard. Sentence 3: The whole process of growing them made her very excited. Sentence 4: But she realized that they required too much water. Sentence 5: So Laura quickly abandoned her corn garden idea. Choices: a. Water Scarcity. b. Corn.", "output": "b", "explanation": "Laura was planning to plant corn, realized the infeasibility of the idea and then decided against it."}, {"input": "Sentence 1: Larry worked at an accounting firm. Sentence 2: It was a boring job but it paid the bills. Sentence 3: Larry grew tired of doing the same thing every day. Sentence 4: He had the idea to have an office party. Sentence 5: By lunch the whole office had passed out and nothing got done. Choices: a. Office Party. b. Lunchtime.", "output": "a", "explanation": "Larry's workplace and need for an office party are established, followed by the events of the office party."}, {"input": "Sentence 1: Ben found a frog in the creek. Sentence 2: It was green and slimy. Sentence 3: He took it home and put it in a bucket. Sentence 4: The next day, the frog was gone. Sentence 5: He'd jumped out and escaped! Choices: a. The Boy. b. The Frog.", "output": "b", "explanation": "Ben caught a frog, could not find it the next day and realized it had escaped."}], "Negative Examples": [{"input": "Sentence 1: My grandparents and I were going for a walk. Sentence 2: Suddenly, right in front of us, was a huge moose. Sentence 3: We were walking near some pine trees and turned a corner. Sentence 4: It was so close that it scared us, but they told me not to run. Sentence 5: We all stood still and soon the moose walked away without harm. Choices: a. Move. b. Up Close.", "output": "a", "explanation": "The people saw a moose, stopped walking, and allowed it to pass. The title is therefore incorrect."}, {"input": "Sentence 1: Mary sliced the purple eggplant. Sentence 2: Then she breaded each slice carefully before frying them. Sentence 3: She layered each breaded slice into her casserole dish. Sentence 4: Finally, she sprinkled parmesan cheese on top and baked it. Sentence 5: She poured homemade marinara sauce in the dish. Choices: a. Eggplant Parmesan. b. Mary.", "output": "b", "explanation": "The story describes how eggplant parmesan is made step by step. The title is therefore incorrect."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Narrative", "Story"], "Instance": {"id": "task220-91af85e2b1b54a8a8097d11ab2dfa766", "input": "Sentence 1: My wife and I are fairly wealthy. Sentence 2: The local zoo contacted us seeking a contribution. Sentence 3: We gave what we thought was a sizable sum. Sentence 4: We later learned they put our name on a bench. Sentence 5: We couldn't imagine how much other donors must have given. Choices: a. Bench Donation. b. Buying a Table.", "output": ["a"]}, "Instance License": ["Unknown"], "prediction": "b"}
+{"id": "task220-5847bcf293164899bcbec591a4ed4a80", "Task": "task220_rocstories_title_classification", "Contributors": "['Anjana Arunkumar']", "Source": ["rocstories"], "URL": ["https://arxiv.org/pdf/1604.01696.pdf"], "Categories": ["Title Generation"], "Reasoning": ["Deductive Reasoning"], "Definition": ["In this task, you're given five sentences, numbered 1 through 5, and two options a and b for possible titles for the story. Your job is to choose the title that better fits the story. Indicate your choice by 'a' or 'b'."], "Positive Examples": [{"input": "Sentence 1: Marcus needed clothing for a business casual event. Sentence 2: All of his clothes were either too formal or too casual. Sentence 3: He decided to buy a pair of khakis. Sentence 4: The pair he bought fit him perfectly. Sentence 5: Marcus was happy to have the right clothes for the event. Choices: a. Marcus Buys Khakis. b. Marcus Works.", "output": "a", "explanation": "Marcus's reasons for buying khakis is established, followed by his purchase of them and reaction."}, {"input": "Sentence 1: Laura loved corn. Sentence 2: So she decided to grow some in her backyard. Sentence 3: The whole process of growing them made her very excited. Sentence 4: But she realized that they required too much water. Sentence 5: So Laura quickly abandoned her corn garden idea. Choices: a. Water Scarcity. b. Corn.", "output": "b", "explanation": "Laura was planning to plant corn, realized the infeasibility of the idea and then decided against it."}, {"input": "Sentence 1: Larry worked at an accounting firm. Sentence 2: It was a boring job but it paid the bills. Sentence 3: Larry grew tired of doing the same thing every day. Sentence 4: He had the idea to have an office party. Sentence 5: By lunch the whole office had passed out and nothing got done. Choices: a. Office Party. b. Lunchtime.", "output": "a", "explanation": "Larry's workplace and need for an office party are established, followed by the events of the office party."}, {"input": "Sentence 1: Ben found a frog in the creek. Sentence 2: It was green and slimy. Sentence 3: He took it home and put it in a bucket. Sentence 4: The next day, the frog was gone. Sentence 5: He'd jumped out and escaped! Choices: a. The Boy. b. The Frog.", "output": "b", "explanation": "Ben caught a frog, could not find it the next day and realized it had escaped."}], "Negative Examples": [{"input": "Sentence 1: My grandparents and I were going for a walk. Sentence 2: Suddenly, right in front of us, was a huge moose. Sentence 3: We were walking near some pine trees and turned a corner. Sentence 4: It was so close that it scared us, but they told me not to run. Sentence 5: We all stood still and soon the moose walked away without harm. Choices: a. Move. b. Up Close.", "output": "a", "explanation": "The people saw a moose, stopped walking, and allowed it to pass. The title is therefore incorrect."}, {"input": "Sentence 1: Mary sliced the purple eggplant. Sentence 2: Then she breaded each slice carefully before frying them. Sentence 3: She layered each breaded slice into her casserole dish. Sentence 4: Finally, she sprinkled parmesan cheese on top and baked it. Sentence 5: She poured homemade marinara sauce in the dish. Choices: a. Eggplant Parmesan. b. Mary.", "output": "b", "explanation": "The story describes how eggplant parmesan is made step by step. The title is therefore incorrect."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Narrative", "Story"], "Instance": {"id": "task220-5847bcf293164899bcbec591a4ed4a80", "input": "Sentence 1: Abigail had been using the same phone for three years. Sentence 2: One day it finally broke for good. Sentence 3: She didn't know where to start with a new phone. Sentence 4: Her brother recommended her some brands. Sentence 5: Luckily, she found a great new phone that she loved. Choices: a. The Bus Fight. b. The New Phone.", "output": ["b"]}, "Instance License": ["Unknown"], "prediction": "b"}
+{"id": "task220-4893717dd3ff424a9b022071f13847e6", "Task": "task220_rocstories_title_classification", "Contributors": "['Anjana Arunkumar']", "Source": ["rocstories"], "URL": ["https://arxiv.org/pdf/1604.01696.pdf"], "Categories": ["Title Generation"], "Reasoning": ["Deductive Reasoning"], "Definition": ["In this task, you're given five sentences, numbered 1 through 5, and two options a and b for possible titles for the story. Your job is to choose the title that better fits the story. Indicate your choice by 'a' or 'b'."], "Positive Examples": [{"input": "Sentence 1: Marcus needed clothing for a business casual event. Sentence 2: All of his clothes were either too formal or too casual. Sentence 3: He decided to buy a pair of khakis. Sentence 4: The pair he bought fit him perfectly. Sentence 5: Marcus was happy to have the right clothes for the event. Choices: a. Marcus Buys Khakis. b. Marcus Works.", "output": "a", "explanation": "Marcus's reasons for buying khakis is established, followed by his purchase of them and reaction."}, {"input": "Sentence 1: Laura loved corn. Sentence 2: So she decided to grow some in her backyard. Sentence 3: The whole process of growing them made her very excited. Sentence 4: But she realized that they required too much water. Sentence 5: So Laura quickly abandoned her corn garden idea. Choices: a. Water Scarcity. b. Corn.", "output": "b", "explanation": "Laura was planning to plant corn, realized the infeasibility of the idea and then decided against it."}, {"input": "Sentence 1: Larry worked at an accounting firm. Sentence 2: It was a boring job but it paid the bills. Sentence 3: Larry grew tired of doing the same thing every day. Sentence 4: He had the idea to have an office party. Sentence 5: By lunch the whole office had passed out and nothing got done. Choices: a. Office Party. b. Lunchtime.", "output": "a", "explanation": "Larry's workplace and need for an office party are established, followed by the events of the office party."}, {"input": "Sentence 1: Ben found a frog in the creek. Sentence 2: It was green and slimy. Sentence 3: He took it home and put it in a bucket. Sentence 4: The next day, the frog was gone. Sentence 5: He'd jumped out and escaped! Choices: a. The Boy. b. The Frog.", "output": "b", "explanation": "Ben caught a frog, could not find it the next day and realized it had escaped."}], "Negative Examples": [{"input": "Sentence 1: My grandparents and I were going for a walk. Sentence 2: Suddenly, right in front of us, was a huge moose. Sentence 3: We were walking near some pine trees and turned a corner. Sentence 4: It was so close that it scared us, but they told me not to run. Sentence 5: We all stood still and soon the moose walked away without harm. Choices: a. Move. b. Up Close.", "output": "a", "explanation": "The people saw a moose, stopped walking, and allowed it to pass. The title is therefore incorrect."}, {"input": "Sentence 1: Mary sliced the purple eggplant. Sentence 2: Then she breaded each slice carefully before frying them. Sentence 3: She layered each breaded slice into her casserole dish. Sentence 4: Finally, she sprinkled parmesan cheese on top and baked it. Sentence 5: She poured homemade marinara sauce in the dish. Choices: a. Eggplant Parmesan. b. Mary.", "output": "b", "explanation": "The story describes how eggplant parmesan is made step by step. The title is therefore incorrect."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Narrative", "Story"], "Instance": {"id": "task220-4893717dd3ff424a9b022071f13847e6", "input": "Sentence 1: Darla wanted a new doll. Sentence 2: To earn the money she returned bottles to the store. Sentence 3: She also saved all of her birthday money and did chores for her mom. Sentence 4: The day finally came when she had saved enough money. Sentence 5: Darla went to the store and bought a brand new doll! Choices: a. Darla's New Doll. b. Perfect Chance.", "output": ["a"]}, "Instance License": ["Unknown"], "prediction": "b"}
+{"id": "task1631-2c38610efce54d2ba81f84e638c8a6bd", "Task": "task1631_openpi_answer_generation", "Contributors": "['Anshita Singh Bais']", "Source": ["open_pi"], "URL": ["https://allenai.org/data/openpi"], "Categories": ["Data to Text"], "Reasoning": [], "Definition": ["Given an entity, a before event, an after event, and an attribute related to the entity, generate a sentence as output. Your sentence should show the changes in the attribute of the entity."], "Positive Examples": [{"input": " entity: arm \nbefore: free \nafter: grasped \nattr: state", "output": "state of arm was free before and grasped afterwards", "explanation": "The state of the arm was free before and afterwards it was grasped hence the output is correct."}, {"input": "entity: person \nbefore: standing \nafter: in air \nattr: location", "output": "location of person was standing before and in air afterwards.", "explanation": "The attribute location of the entity person was in the standing state before and in air afterwards."}, {"input": "entity: mixture \nbefore: chunky \nafter: smoother \nattr: texture", "output": "texture of mixture was chunky before and smoother afterwards.", "explanation": "The attribute is concatenated with the entity using of and with the before state with was and the after state with and. The word afterwards is added at the end to complete the sentence."}], "Negative Examples": [{"input": "entity: buckles \nbefore: being worn \nafter: removed \nattr: wearing", "output": "wearing of buckles was being worn before and removed afterwards", "explanation": "Here wearing of buckles is grammatically incorrect and the output sentence should be the buckles were worn before and removed afterwards."}, {"input": "entity: tape measure \nbefore: in box \nafter: measured around head \nattr: tape measure", "output": "tape measure of tape measure was in box before and measured around head afterwards", "explanation": "Here the attribute is the same as entity and hence can be used only once in the output sentence. So the output should be tape measure was in box before and measured around head afterwards."}, {"input": "entity: person \nbefore: unskilled \nafter: skilled \nattr: skill", "output": "skill of person was unskilled before and skilled afterwards", "explanation": "The output sentence symantically incorrect. The output should be the person was unskilled before and skilled afterwards."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Web"], "Instance": {"id": "task1631-2c38610efce54d2ba81f84e638c8a6bd", "input": "entity: binder clip \nbefore: in original place \nafter: found \nattr: state", "output": ["state of binder clip was in original place before and found afterwards"]}, "Instance License": ["CC BY 4.0"], "prediction": "state of binder clip before and found afterwards"}
+{"id": "task1631-eb9dedaff2234cb7b1d13e6fc0d7389b", "Task": "task1631_openpi_answer_generation", "Contributors": "['Anshita Singh Bais']", "Source": ["open_pi"], "URL": ["https://allenai.org/data/openpi"], "Categories": ["Data to Text"], "Reasoning": [], "Definition": ["Given an entity, a before event, an after event, and an attribute related to the entity, generate a sentence as output. Your sentence should show the changes in the attribute of the entity."], "Positive Examples": [{"input": " entity: arm \nbefore: free \nafter: grasped \nattr: state", "output": "state of arm was free before and grasped afterwards", "explanation": "The state of the arm was free before and afterwards it was grasped hence the output is correct."}, {"input": "entity: person \nbefore: standing \nafter: in air \nattr: location", "output": "location of person was standing before and in air afterwards.", "explanation": "The attribute location of the entity person was in the standing state before and in air afterwards."}, {"input": "entity: mixture \nbefore: chunky \nafter: smoother \nattr: texture", "output": "texture of mixture was chunky before and smoother afterwards.", "explanation": "The attribute is concatenated with the entity using of and with the before state with was and the after state with and. The word afterwards is added at the end to complete the sentence."}], "Negative Examples": [{"input": "entity: buckles \nbefore: being worn \nafter: removed \nattr: wearing", "output": "wearing of buckles was being worn before and removed afterwards", "explanation": "Here wearing of buckles is grammatically incorrect and the output sentence should be the buckles were worn before and removed afterwards."}, {"input": "entity: tape measure \nbefore: in box \nafter: measured around head \nattr: tape measure", "output": "tape measure of tape measure was in box before and measured around head afterwards", "explanation": "Here the attribute is the same as entity and hence can be used only once in the output sentence. So the output should be tape measure was in box before and measured around head afterwards."}, {"input": "entity: person \nbefore: unskilled \nafter: skilled \nattr: skill", "output": "skill of person was unskilled before and skilled afterwards", "explanation": "The output sentence symantically incorrect. The output should be the person was unskilled before and skilled afterwards."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Web"], "Instance": {"id": "task1631-eb9dedaff2234cb7b1d13e6fc0d7389b", "input": "entity: arm \nbefore: at side \nafter: chin height \nattr: position", "output": ["position of arm was at side before and chin height afterwards"]}, "Instance License": ["CC BY 4.0"], "prediction": "position of arm at side after chin height"}
+{"id": "task1631-fde98abce4174842a83bb486f5c69e2e", "Task": "task1631_openpi_answer_generation", "Contributors": "['Anshita Singh Bais']", "Source": ["open_pi"], "URL": ["https://allenai.org/data/openpi"], "Categories": ["Data to Text"], "Reasoning": [], "Definition": ["Given an entity, a before event, an after event, and an attribute related to the entity, generate a sentence as output. Your sentence should show the changes in the attribute of the entity."], "Positive Examples": [{"input": " entity: arm \nbefore: free \nafter: grasped \nattr: state", "output": "state of arm was free before and grasped afterwards", "explanation": "The state of the arm was free before and afterwards it was grasped hence the output is correct."}, {"input": "entity: person \nbefore: standing \nafter: in air \nattr: location", "output": "location of person was standing before and in air afterwards.", "explanation": "The attribute location of the entity person was in the standing state before and in air afterwards."}, {"input": "entity: mixture \nbefore: chunky \nafter: smoother \nattr: texture", "output": "texture of mixture was chunky before and smoother afterwards.", "explanation": "The attribute is concatenated with the entity using of and with the before state with was and the after state with and. The word afterwards is added at the end to complete the sentence."}], "Negative Examples": [{"input": "entity: buckles \nbefore: being worn \nafter: removed \nattr: wearing", "output": "wearing of buckles was being worn before and removed afterwards", "explanation": "Here wearing of buckles is grammatically incorrect and the output sentence should be the buckles were worn before and removed afterwards."}, {"input": "entity: tape measure \nbefore: in box \nafter: measured around head \nattr: tape measure", "output": "tape measure of tape measure was in box before and measured around head afterwards", "explanation": "Here the attribute is the same as entity and hence can be used only once in the output sentence. So the output should be tape measure was in box before and measured around head afterwards."}, {"input": "entity: person \nbefore: unskilled \nafter: skilled \nattr: skill", "output": "skill of person was unskilled before and skilled afterwards", "explanation": "The output sentence symantically incorrect. The output should be the person was unskilled before and skilled afterwards."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Web"], "Instance": {"id": "task1631-fde98abce4174842a83bb486f5c69e2e", "input": "entity: person \nbefore: sitting on surfboard \nafter: standing on surfboard \nattr: state", "output": ["state of person was sitting on surfboard before and standing on surfboard afterwards"]}, "Instance License": ["CC BY 4.0"], "prediction": "state of person was sitting on surfboard before and standing on surfboard afterwards"}
+{"id": "task1631-c1f6b3caa9d84ed88eb179c2b3cfb682", "Task": "task1631_openpi_answer_generation", "Contributors": "['Anshita Singh Bais']", "Source": ["open_pi"], "URL": ["https://allenai.org/data/openpi"], "Categories": ["Data to Text"], "Reasoning": [], "Definition": ["Given an entity, a before event, an after event, and an attribute related to the entity, generate a sentence as output. Your sentence should show the changes in the attribute of the entity."], "Positive Examples": [{"input": " entity: arm \nbefore: free \nafter: grasped \nattr: state", "output": "state of arm was free before and grasped afterwards", "explanation": "The state of the arm was free before and afterwards it was grasped hence the output is correct."}, {"input": "entity: person \nbefore: standing \nafter: in air \nattr: location", "output": "location of person was standing before and in air afterwards.", "explanation": "The attribute location of the entity person was in the standing state before and in air afterwards."}, {"input": "entity: mixture \nbefore: chunky \nafter: smoother \nattr: texture", "output": "texture of mixture was chunky before and smoother afterwards.", "explanation": "The attribute is concatenated with the entity using of and with the before state with was and the after state with and. The word afterwards is added at the end to complete the sentence."}], "Negative Examples": [{"input": "entity: buckles \nbefore: being worn \nafter: removed \nattr: wearing", "output": "wearing of buckles was being worn before and removed afterwards", "explanation": "Here wearing of buckles is grammatically incorrect and the output sentence should be the buckles were worn before and removed afterwards."}, {"input": "entity: tape measure \nbefore: in box \nafter: measured around head \nattr: tape measure", "output": "tape measure of tape measure was in box before and measured around head afterwards", "explanation": "Here the attribute is the same as entity and hence can be used only once in the output sentence. So the output should be tape measure was in box before and measured around head afterwards."}, {"input": "entity: person \nbefore: unskilled \nafter: skilled \nattr: skill", "output": "skill of person was unskilled before and skilled afterwards", "explanation": "The output sentence symantically incorrect. The output should be the person was unskilled before and skilled afterwards."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Web"], "Instance": {"id": "task1631-c1f6b3caa9d84ed88eb179c2b3cfb682", "input": "entity: the laundry caps \nbefore: wet \nafter: dry \nattr: wetness", "output": ["wetness of the laundry caps was wet before and dry afterwards"]}, "Instance License": ["CC BY 4.0"], "prediction": "wetness of laundry caps before and dry afterwards"}
+{"id": "task1631-2d674a365dd0449b83f295375d6bfdd6", "Task": "task1631_openpi_answer_generation", "Contributors": "['Anshita Singh Bais']", "Source": ["open_pi"], "URL": ["https://allenai.org/data/openpi"], "Categories": ["Data to Text"], "Reasoning": [], "Definition": ["Given an entity, a before event, an after event, and an attribute related to the entity, generate a sentence as output. Your sentence should show the changes in the attribute of the entity."], "Positive Examples": [{"input": " entity: arm \nbefore: free \nafter: grasped \nattr: state", "output": "state of arm was free before and grasped afterwards", "explanation": "The state of the arm was free before and afterwards it was grasped hence the output is correct."}, {"input": "entity: person \nbefore: standing \nafter: in air \nattr: location", "output": "location of person was standing before and in air afterwards.", "explanation": "The attribute location of the entity person was in the standing state before and in air afterwards."}, {"input": "entity: mixture \nbefore: chunky \nafter: smoother \nattr: texture", "output": "texture of mixture was chunky before and smoother afterwards.", "explanation": "The attribute is concatenated with the entity using of and with the before state with was and the after state with and. The word afterwards is added at the end to complete the sentence."}], "Negative Examples": [{"input": "entity: buckles \nbefore: being worn \nafter: removed \nattr: wearing", "output": "wearing of buckles was being worn before and removed afterwards", "explanation": "Here wearing of buckles is grammatically incorrect and the output sentence should be the buckles were worn before and removed afterwards."}, {"input": "entity: tape measure \nbefore: in box \nafter: measured around head \nattr: tape measure", "output": "tape measure of tape measure was in box before and measured around head afterwards", "explanation": "Here the attribute is the same as entity and hence can be used only once in the output sentence. So the output should be tape measure was in box before and measured around head afterwards."}, {"input": "entity: person \nbefore: unskilled \nafter: skilled \nattr: skill", "output": "skill of person was unskilled before and skilled afterwards", "explanation": "The output sentence symantically incorrect. The output should be the person was unskilled before and skilled afterwards."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Web"], "Instance": {"id": "task1631-2d674a365dd0449b83f295375d6bfdd6", "input": "entity: project \nbefore: started \nafter: finished \nattr: complexity", "output": ["complexity of project was started before and finished afterwards"]}, "Instance License": ["CC BY 4.0"], "prediction": "complexity of project was started before and finished afterwards"}
+{"id": "task232-125f1cf098894b5b8534826f07c750a5", "Task": "task232_iirc_link_number_classification", "Contributors": "['Anjana Arunkumar']", "Source": ["iirc"], "URL": ["https://allenai.org/data/iirc"], "Categories": ["Answerability Classification"], "Reasoning": ["Multihop Reasoning", "Cross-document Reasoning", "Discrete Reasoning", "Numerical Reasoning", "Temporal Reasoning"], "Definition": ["In this task, you're given a question, along with a context passage which has extra information available on certain terms mentioned in it, i.e., the proper nouns in the passage. Your job is to determine whether information from more than one term is needed to answer the question. Indicate your choice as `a` for Yes or `b` for No."], "Positive Examples": [{"input": "Question: When did the operation during which the 704th dropped supplies to allied troops near Nijmegen begin? Passage: The group was occasionally diverted from strategic missions to carry out air support and interdiction missions. It supported Operation Overlord, the invasion of Normandy by attacking transportation targets, including bridges, along with airfields and strong points in France. On D Day, the squadron and the rest of the 446th Group led the first heavy bomber mission of the day. The 446th aided ground forces at Caen and Saint-L\u00f4 during July by hitting bridges, gun batteries, and enemy troops. During Operation Market Garden, the attempt to seize a bridgehead across the Rhine in the Netherlands, the 704th dropped supplies to allied troops near Nijmegen. It struck lines of communications during the Battle of the Bulge. During Operation Varsity in March 1945, it supplied ground and airborne troops near Wesel. The squadron flew its last combat mission on 25 April 1945 against Salzburg, Austria. The group had flown 273 missions and had lost 58 aircraft during the war,\n.", "output": "b", "explanation": "The passage describes the 704th's actions during Operation Market Garden so only information about the operation is needed."}, {"input": "Question: How old was Francis Ford when John Ford started his career in filmmaking? Passage: John Ford (1894\u20131973) was an American film director whose career spanned from 1913 to 1971. During this time he directed more than 140 films. Born in Maine, Ford entered the filmmaking industry shortly after graduating from high school with the help of his older brother, Francis Ford, who had established himself as a leading man and director for Universal Studios. After working as an actor, assistant director, stuntman, and prop man \u2013 often for his brother \u2013 Universal gave Ford the opportunity to direct in 1917. Initially working in short films, he quickly moved into features, largely with Harry Carey as his star. In 1920 Ford left Universal and began working for the Fox Film Corporation. During the next ten years he directed more than 30 films, including the westerns The Iron Horse (1924) and 3 Bad Men (1926), both starring George O'Brien, the war drama Four Sons and the Irish romantic drama Hangman's House (both 1928 and both starring Victor McLaglen). In the same year of these last two films, Ford directed his first all-talking film, the short Napoleon's Barber. The following year he directed his first all-talking feature, The Black Watch.\n.", "output": "a", "explanation": "The question is about both Francis and John Ford, so more details on both are needed to answer the question. There is no single entity in the passage that can lead to the answer."}, {"input": "Question: Is the woman who gave the starting command at the Indy 500 for the last time in 2016 still alive? Passage: In most cases, Tony Hulman would give the command, then ride in the pace car during the pace laps. Mary F. Hulman would give the command near the pace car, but rarely rode in the pace car due to her age and declining health. Eventually, the location was moved to near the start/finish line, and in 2001, it was moved to the new Victory Podium stage adjacent to the Pagoda. In 2011 only, Mari George moved back to the front of the starting grid to give the command, and then she rode in the pace car with A. J. Foyt. In 2014, as a special gesture to Jim Nabors's final performance at Indy, the starting command was given in unison by both Mari George and Nabors, marking the first time a non-member of the Hulman-George family had given the command for the 500 since 1954. In 2016 for the 100th Indianapolis 500, now-matriarch Mari was joined by three subsequent generations of the Hulman-George family, who gave the command together. Due to her advanced age, the 2016 race would be Mari's final turn giving the command. Later that same year, Tony George gave the starting command for the Brickyard 400, his first time giving a command since a restart command in 1986. For the 2017 Indianapolis 500, the duty was permanently assigned to Tony George. In that year, Tony George began using the phrase \"Drivers, start your engines\" instead of the more familiar \"Lady and gentlemen...\" variation. However, for the 2019 race, George recited that latter variation.\n'.", "output": "b", "explanation": "Mari Hulman George gave the starting command at the Indy 500 in 2016 so only information about her is needed."}], "Negative Examples": [{"input": "Question: How many Super Bowls did the team the Cardinals beat to make their first appearance in the Super Bowl win? Passage: The 2008 Arizona Cardinals season was the 89th season for the team in the National Football League and their 21st season in Arizona. The season marked the Cardinals' first Super Bowl appearance, coming as a result of their victory against the Philadelphia Eagles in the NFC Championship. The Cardinals slogan for the season was \"Shock The World!\" Riding the back of quarterback Kurt Warner, who had gone from being a backup for the St. Louis Rams in 1999 to leading the Greatest Show on Turf to a Super Bowl XXXIV victory, and franchise wide receiver Larry Fitzgerald, the Cardinals went on a playoff run for the ages after having won just one playoff game in the last sixty years, as Warner once again recreated the magic he had captured with the Rams. (Coincidentally, both teams were based in St Louis at one point or another, only to relocate to different cities.)\n.", "output": "a", "explanation": "The passage mentions that the Arizona Cardinals beat the Eagles, so any further information will only be available with respect to the Eagles' season meaning only one link is needed."}, {"input": "Question: How many NCAA football championships have been won by the college that Peyton Manning attended? Passage: In 1998 the Colts, for the 4th time in 15 years, held the 1st overall pick in the draft and for the 3rd time in 15 years selected a quarterback \u2013 this time Peyton Manning. Manning started the first game of his rookie season and started every single Colts game since until the start of the 2011 season, when a recurring neck injury sidelined him. Despite a difficult rookie season, where he threw a league high 28 interceptions, Manning and the Colts responded by finishing 13\u20133 in 1999. The 10 game turnaround from the previous year set an NFL record. Even with this turnaround, the Colts lost in the playoffs. The following years would be marked by a near constant pattern. The Colts and Manning successes in the regular season were matched only by their failures in the post season. Manning was named to the Pro Bowl in 1999, 2000, 2002, 2003 and 2004, as well as winning the NFL MVP award in both 2003 and 2004. In 2004 Manning set a then NFL record when he threw 49 touchdowns in a single season. In spite of this the team failed in the playoffs, including early round exits in 1999, 2000, 2002 and 2005. In both 2003 and 2004 the Colts would lose to eventual Super Bowl winning New England Patriots in the AFC Championship Game and the Divisional Round respectively. In 2006 the Colts and Manning were finally able to beat the Patriots and their quarterback Tom Brady in the AFC Championship Game on their way to a victory in Super Bowl XLI against the Chicago Bears. Manning was named the Super Bowl MVP. The Colts and Manning would continue to have success, with Manning winning two further MVP awards in 2008 and 2009. In 2009 the Colts would return to the Super Bowl where they would lose to the New Orleans Saints.\n.", "output": "b", "explanation": "Both information on Peyton Manning, and information on the college he attended are needed."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Wikipedia"], "Instance": {"id": "task232-125f1cf098894b5b8534826f07c750a5", "input": "Question: Which countries were both a member of the European Union and the Council of Europe when Albania was accepted into the Council of Europe? Passage:In 1991, the Socialist Party of Albania, with specific social democratic ideology took control of the country through democratic elections. One year later the Democratic Party of Albania won the new elections. After 1990, Albania has been seeking a closer relationship with the West. What followed were deliberate programs of economic and democratic reform, but Albanian inexperience with capitalism led to the proliferation of pyramid schemes \u2013 which were not banned due to the corruption of the government. Chaos in late 1996 to early 1997, as a result of the collapse of these pyramid schemes, alarmed the world and prompted the influx of international peacekeeping forces. In 1995, Albania was accepted into the Council of Europe and requested membership in NATO (obtained in 2009) and is a potential candidate country for accession to the European Union. The workforce of Albania has continued to emigrate to Western countries, especially Greece and Italy.\n", "output": ["a"]}, "Instance License": ["CC BY 4.0"], "prediction": "b"}
+{"id": "task232-b3c50d2b54114af780edc1f481198b34", "Task": "task232_iirc_link_number_classification", "Contributors": "['Anjana Arunkumar']", "Source": ["iirc"], "URL": ["https://allenai.org/data/iirc"], "Categories": ["Answerability Classification"], "Reasoning": ["Multihop Reasoning", "Cross-document Reasoning", "Discrete Reasoning", "Numerical Reasoning", "Temporal Reasoning"], "Definition": ["In this task, you're given a question, along with a context passage which has extra information available on certain terms mentioned in it, i.e., the proper nouns in the passage. Your job is to determine whether information from more than one term is needed to answer the question. Indicate your choice as `a` for Yes or `b` for No."], "Positive Examples": [{"input": "Question: When did the operation during which the 704th dropped supplies to allied troops near Nijmegen begin? Passage: The group was occasionally diverted from strategic missions to carry out air support and interdiction missions. It supported Operation Overlord, the invasion of Normandy by attacking transportation targets, including bridges, along with airfields and strong points in France. On D Day, the squadron and the rest of the 446th Group led the first heavy bomber mission of the day. The 446th aided ground forces at Caen and Saint-L\u00f4 during July by hitting bridges, gun batteries, and enemy troops. During Operation Market Garden, the attempt to seize a bridgehead across the Rhine in the Netherlands, the 704th dropped supplies to allied troops near Nijmegen. It struck lines of communications during the Battle of the Bulge. During Operation Varsity in March 1945, it supplied ground and airborne troops near Wesel. The squadron flew its last combat mission on 25 April 1945 against Salzburg, Austria. The group had flown 273 missions and had lost 58 aircraft during the war,\n.", "output": "b", "explanation": "The passage describes the 704th's actions during Operation Market Garden so only information about the operation is needed."}, {"input": "Question: How old was Francis Ford when John Ford started his career in filmmaking? Passage: John Ford (1894\u20131973) was an American film director whose career spanned from 1913 to 1971. During this time he directed more than 140 films. Born in Maine, Ford entered the filmmaking industry shortly after graduating from high school with the help of his older brother, Francis Ford, who had established himself as a leading man and director for Universal Studios. After working as an actor, assistant director, stuntman, and prop man \u2013 often for his brother \u2013 Universal gave Ford the opportunity to direct in 1917. Initially working in short films, he quickly moved into features, largely with Harry Carey as his star. In 1920 Ford left Universal and began working for the Fox Film Corporation. During the next ten years he directed more than 30 films, including the westerns The Iron Horse (1924) and 3 Bad Men (1926), both starring George O'Brien, the war drama Four Sons and the Irish romantic drama Hangman's House (both 1928 and both starring Victor McLaglen). In the same year of these last two films, Ford directed his first all-talking film, the short Napoleon's Barber. The following year he directed his first all-talking feature, The Black Watch.\n.", "output": "a", "explanation": "The question is about both Francis and John Ford, so more details on both are needed to answer the question. There is no single entity in the passage that can lead to the answer."}, {"input": "Question: Is the woman who gave the starting command at the Indy 500 for the last time in 2016 still alive? Passage: In most cases, Tony Hulman would give the command, then ride in the pace car during the pace laps. Mary F. Hulman would give the command near the pace car, but rarely rode in the pace car due to her age and declining health. Eventually, the location was moved to near the start/finish line, and in 2001, it was moved to the new Victory Podium stage adjacent to the Pagoda. In 2011 only, Mari George moved back to the front of the starting grid to give the command, and then she rode in the pace car with A. J. Foyt. In 2014, as a special gesture to Jim Nabors's final performance at Indy, the starting command was given in unison by both Mari George and Nabors, marking the first time a non-member of the Hulman-George family had given the command for the 500 since 1954. In 2016 for the 100th Indianapolis 500, now-matriarch Mari was joined by three subsequent generations of the Hulman-George family, who gave the command together. Due to her advanced age, the 2016 race would be Mari's final turn giving the command. Later that same year, Tony George gave the starting command for the Brickyard 400, his first time giving a command since a restart command in 1986. For the 2017 Indianapolis 500, the duty was permanently assigned to Tony George. In that year, Tony George began using the phrase \"Drivers, start your engines\" instead of the more familiar \"Lady and gentlemen...\" variation. However, for the 2019 race, George recited that latter variation.\n'.", "output": "b", "explanation": "Mari Hulman George gave the starting command at the Indy 500 in 2016 so only information about her is needed."}], "Negative Examples": [{"input": "Question: How many Super Bowls did the team the Cardinals beat to make their first appearance in the Super Bowl win? Passage: The 2008 Arizona Cardinals season was the 89th season for the team in the National Football League and their 21st season in Arizona. The season marked the Cardinals' first Super Bowl appearance, coming as a result of their victory against the Philadelphia Eagles in the NFC Championship. The Cardinals slogan for the season was \"Shock The World!\" Riding the back of quarterback Kurt Warner, who had gone from being a backup for the St. Louis Rams in 1999 to leading the Greatest Show on Turf to a Super Bowl XXXIV victory, and franchise wide receiver Larry Fitzgerald, the Cardinals went on a playoff run for the ages after having won just one playoff game in the last sixty years, as Warner once again recreated the magic he had captured with the Rams. (Coincidentally, both teams were based in St Louis at one point or another, only to relocate to different cities.)\n.", "output": "a", "explanation": "The passage mentions that the Arizona Cardinals beat the Eagles, so any further information will only be available with respect to the Eagles' season meaning only one link is needed."}, {"input": "Question: How many NCAA football championships have been won by the college that Peyton Manning attended? Passage: In 1998 the Colts, for the 4th time in 15 years, held the 1st overall pick in the draft and for the 3rd time in 15 years selected a quarterback \u2013 this time Peyton Manning. Manning started the first game of his rookie season and started every single Colts game since until the start of the 2011 season, when a recurring neck injury sidelined him. Despite a difficult rookie season, where he threw a league high 28 interceptions, Manning and the Colts responded by finishing 13\u20133 in 1999. The 10 game turnaround from the previous year set an NFL record. Even with this turnaround, the Colts lost in the playoffs. The following years would be marked by a near constant pattern. The Colts and Manning successes in the regular season were matched only by their failures in the post season. Manning was named to the Pro Bowl in 1999, 2000, 2002, 2003 and 2004, as well as winning the NFL MVP award in both 2003 and 2004. In 2004 Manning set a then NFL record when he threw 49 touchdowns in a single season. In spite of this the team failed in the playoffs, including early round exits in 1999, 2000, 2002 and 2005. In both 2003 and 2004 the Colts would lose to eventual Super Bowl winning New England Patriots in the AFC Championship Game and the Divisional Round respectively. In 2006 the Colts and Manning were finally able to beat the Patriots and their quarterback Tom Brady in the AFC Championship Game on their way to a victory in Super Bowl XLI against the Chicago Bears. Manning was named the Super Bowl MVP. The Colts and Manning would continue to have success, with Manning winning two further MVP awards in 2008 and 2009. In 2009 the Colts would return to the Super Bowl where they would lose to the New Orleans Saints.\n.", "output": "b", "explanation": "Both information on Peyton Manning, and information on the college he attended are needed."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Wikipedia"], "Instance": {"id": "task232-b3c50d2b54114af780edc1f481198b34", "input": "Question: Who was the leader of Moldova in 1917? Passage:Lazo was born in the village of Piatra, Orhei, now in Orhei district, Moldova. He was of boyar origin. In 1917, he was a cadet at the Imperial Russian military academy when he joined the Bolshevik forces and was entrusted with several missions in Siberia during the Russian Civil War. In March\u2013August 1918 he was a commander of the Zabaykalski (trans-Baikalan) Front, and fought against Ataman Grigory Semyonov. Later he fought in Bolshevik partisan units in the Vladivostok and Partizansk areas, commanding the Red Army during the Suchan Valley Campaign against American forces. On January 31, 1920 the Bolsheviks took power in Vladivostok, but on April 5, 1920 Lazo and other commanders were arrested by Japanese troops. Then, Lazo disappeared, along with Vsevolod Sibirtsev and Alexey Lutski. Reportedly they were shot shortly after, but the exact details of the execution have never been known yet. It is widely believed that the Japanese or Cossacks of the White movement burned them in the firebox of a steam engine in Muravyevo-Amurskaya (currently Lazo) station. \n", "output": ["b"]}, "Instance License": ["CC BY 4.0"], "prediction": "b"}
+{"id": "task232-75f9e9d1e35d423da90b99459ca6f494", "Task": "task232_iirc_link_number_classification", "Contributors": "['Anjana Arunkumar']", "Source": ["iirc"], "URL": ["https://allenai.org/data/iirc"], "Categories": ["Answerability Classification"], "Reasoning": ["Multihop Reasoning", "Cross-document Reasoning", "Discrete Reasoning", "Numerical Reasoning", "Temporal Reasoning"], "Definition": ["In this task, you're given a question, along with a context passage which has extra information available on certain terms mentioned in it, i.e., the proper nouns in the passage. Your job is to determine whether information from more than one term is needed to answer the question. Indicate your choice as `a` for Yes or `b` for No."], "Positive Examples": [{"input": "Question: When did the operation during which the 704th dropped supplies to allied troops near Nijmegen begin? Passage: The group was occasionally diverted from strategic missions to carry out air support and interdiction missions. It supported Operation Overlord, the invasion of Normandy by attacking transportation targets, including bridges, along with airfields and strong points in France. On D Day, the squadron and the rest of the 446th Group led the first heavy bomber mission of the day. The 446th aided ground forces at Caen and Saint-L\u00f4 during July by hitting bridges, gun batteries, and enemy troops. During Operation Market Garden, the attempt to seize a bridgehead across the Rhine in the Netherlands, the 704th dropped supplies to allied troops near Nijmegen. It struck lines of communications during the Battle of the Bulge. During Operation Varsity in March 1945, it supplied ground and airborne troops near Wesel. The squadron flew its last combat mission on 25 April 1945 against Salzburg, Austria. The group had flown 273 missions and had lost 58 aircraft during the war,\n.", "output": "b", "explanation": "The passage describes the 704th's actions during Operation Market Garden so only information about the operation is needed."}, {"input": "Question: How old was Francis Ford when John Ford started his career in filmmaking? Passage: John Ford (1894\u20131973) was an American film director whose career spanned from 1913 to 1971. During this time he directed more than 140 films. Born in Maine, Ford entered the filmmaking industry shortly after graduating from high school with the help of his older brother, Francis Ford, who had established himself as a leading man and director for Universal Studios. After working as an actor, assistant director, stuntman, and prop man \u2013 often for his brother \u2013 Universal gave Ford the opportunity to direct in 1917. Initially working in short films, he quickly moved into features, largely with Harry Carey as his star. In 1920 Ford left Universal and began working for the Fox Film Corporation. During the next ten years he directed more than 30 films, including the westerns The Iron Horse (1924) and 3 Bad Men (1926), both starring George O'Brien, the war drama Four Sons and the Irish romantic drama Hangman's House (both 1928 and both starring Victor McLaglen). In the same year of these last two films, Ford directed his first all-talking film, the short Napoleon's Barber. The following year he directed his first all-talking feature, The Black Watch.\n.", "output": "a", "explanation": "The question is about both Francis and John Ford, so more details on both are needed to answer the question. There is no single entity in the passage that can lead to the answer."}, {"input": "Question: Is the woman who gave the starting command at the Indy 500 for the last time in 2016 still alive? Passage: In most cases, Tony Hulman would give the command, then ride in the pace car during the pace laps. Mary F. Hulman would give the command near the pace car, but rarely rode in the pace car due to her age and declining health. Eventually, the location was moved to near the start/finish line, and in 2001, it was moved to the new Victory Podium stage adjacent to the Pagoda. In 2011 only, Mari George moved back to the front of the starting grid to give the command, and then she rode in the pace car with A. J. Foyt. In 2014, as a special gesture to Jim Nabors's final performance at Indy, the starting command was given in unison by both Mari George and Nabors, marking the first time a non-member of the Hulman-George family had given the command for the 500 since 1954. In 2016 for the 100th Indianapolis 500, now-matriarch Mari was joined by three subsequent generations of the Hulman-George family, who gave the command together. Due to her advanced age, the 2016 race would be Mari's final turn giving the command. Later that same year, Tony George gave the starting command for the Brickyard 400, his first time giving a command since a restart command in 1986. For the 2017 Indianapolis 500, the duty was permanently assigned to Tony George. In that year, Tony George began using the phrase \"Drivers, start your engines\" instead of the more familiar \"Lady and gentlemen...\" variation. However, for the 2019 race, George recited that latter variation.\n'.", "output": "b", "explanation": "Mari Hulman George gave the starting command at the Indy 500 in 2016 so only information about her is needed."}], "Negative Examples": [{"input": "Question: How many Super Bowls did the team the Cardinals beat to make their first appearance in the Super Bowl win? Passage: The 2008 Arizona Cardinals season was the 89th season for the team in the National Football League and their 21st season in Arizona. The season marked the Cardinals' first Super Bowl appearance, coming as a result of their victory against the Philadelphia Eagles in the NFC Championship. The Cardinals slogan for the season was \"Shock The World!\" Riding the back of quarterback Kurt Warner, who had gone from being a backup for the St. Louis Rams in 1999 to leading the Greatest Show on Turf to a Super Bowl XXXIV victory, and franchise wide receiver Larry Fitzgerald, the Cardinals went on a playoff run for the ages after having won just one playoff game in the last sixty years, as Warner once again recreated the magic he had captured with the Rams. (Coincidentally, both teams were based in St Louis at one point or another, only to relocate to different cities.)\n.", "output": "a", "explanation": "The passage mentions that the Arizona Cardinals beat the Eagles, so any further information will only be available with respect to the Eagles' season meaning only one link is needed."}, {"input": "Question: How many NCAA football championships have been won by the college that Peyton Manning attended? Passage: In 1998 the Colts, for the 4th time in 15 years, held the 1st overall pick in the draft and for the 3rd time in 15 years selected a quarterback \u2013 this time Peyton Manning. Manning started the first game of his rookie season and started every single Colts game since until the start of the 2011 season, when a recurring neck injury sidelined him. Despite a difficult rookie season, where he threw a league high 28 interceptions, Manning and the Colts responded by finishing 13\u20133 in 1999. The 10 game turnaround from the previous year set an NFL record. Even with this turnaround, the Colts lost in the playoffs. The following years would be marked by a near constant pattern. The Colts and Manning successes in the regular season were matched only by their failures in the post season. Manning was named to the Pro Bowl in 1999, 2000, 2002, 2003 and 2004, as well as winning the NFL MVP award in both 2003 and 2004. In 2004 Manning set a then NFL record when he threw 49 touchdowns in a single season. In spite of this the team failed in the playoffs, including early round exits in 1999, 2000, 2002 and 2005. In both 2003 and 2004 the Colts would lose to eventual Super Bowl winning New England Patriots in the AFC Championship Game and the Divisional Round respectively. In 2006 the Colts and Manning were finally able to beat the Patriots and their quarterback Tom Brady in the AFC Championship Game on their way to a victory in Super Bowl XLI against the Chicago Bears. Manning was named the Super Bowl MVP. The Colts and Manning would continue to have success, with Manning winning two further MVP awards in 2008 and 2009. In 2009 the Colts would return to the Super Bowl where they would lose to the New Orleans Saints.\n.", "output": "b", "explanation": "Both information on Peyton Manning, and information on the college he attended are needed."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Wikipedia"], "Instance": {"id": "task232-75f9e9d1e35d423da90b99459ca6f494", "input": "Question: Who won the all-around the year Filanovsky finished 7th at the Corbeil-Essonnes World Cup? Passage:In 2014, Veinberg Filanovsky finished 7th in all-around at the 2014 Corbeil-Essonnes World Cup, and qualified to all four event finals for the first time in her World Cup competitions. On May 30\u2013June 1, she competed at the 2014 Minsk World Cup. On June 10\u201315, she competed at the 2014 European Championships and finished 12th in the all-around final. On September 5\u20137, at the 2014 World World Cup Final in Kazan, Russia, Veinberg Filanovsky finished 9th in all-around behind Neta Rivkin, and qualified to one event final, finishing 7th in clubs. On September 22\u201328, Veinberg Filanovsky (along with teammates Neta Rivkin and Martina Poplinsky) represented Israel at the 2014 World Championships where Team Israel finished in 4th place. She finished 12th in the all-around finals behind Kseniya Moustafaeva of France. On October 18\u201320, Veinberg Filanovsky competed at the 2014 Grand Prix Berlin and won the all-around silver behind Russia's Maria Titova, while in event finals she won silver medals in hoop, clubs and ribbon. On November 1\u20133, Veinberg Filanovsky won the all-around bronze at the 2014 Grand Prix Brno behind compatriot Neta Rivkin. In November 14\u201316, at the 2014 Grand Prix Final in Innsbruck, Austria, Veinberg Filanovsky finished 4th in the all-around behind Bulgaria's Neviana Vladinova. In event finals, she won silver in ball and two bronze (clubs, ribbon).\n", "output": ["b"]}, "Instance License": ["CC BY 4.0"], "prediction": "b"}
+{"id": "task232-2b11973b1c874493b9bb429903034b2d", "Task": "task232_iirc_link_number_classification", "Contributors": "['Anjana Arunkumar']", "Source": ["iirc"], "URL": ["https://allenai.org/data/iirc"], "Categories": ["Answerability Classification"], "Reasoning": ["Multihop Reasoning", "Cross-document Reasoning", "Discrete Reasoning", "Numerical Reasoning", "Temporal Reasoning"], "Definition": ["In this task, you're given a question, along with a context passage which has extra information available on certain terms mentioned in it, i.e., the proper nouns in the passage. Your job is to determine whether information from more than one term is needed to answer the question. Indicate your choice as `a` for Yes or `b` for No."], "Positive Examples": [{"input": "Question: When did the operation during which the 704th dropped supplies to allied troops near Nijmegen begin? Passage: The group was occasionally diverted from strategic missions to carry out air support and interdiction missions. It supported Operation Overlord, the invasion of Normandy by attacking transportation targets, including bridges, along with airfields and strong points in France. On D Day, the squadron and the rest of the 446th Group led the first heavy bomber mission of the day. The 446th aided ground forces at Caen and Saint-L\u00f4 during July by hitting bridges, gun batteries, and enemy troops. During Operation Market Garden, the attempt to seize a bridgehead across the Rhine in the Netherlands, the 704th dropped supplies to allied troops near Nijmegen. It struck lines of communications during the Battle of the Bulge. During Operation Varsity in March 1945, it supplied ground and airborne troops near Wesel. The squadron flew its last combat mission on 25 April 1945 against Salzburg, Austria. The group had flown 273 missions and had lost 58 aircraft during the war,\n.", "output": "b", "explanation": "The passage describes the 704th's actions during Operation Market Garden so only information about the operation is needed."}, {"input": "Question: How old was Francis Ford when John Ford started his career in filmmaking? Passage: John Ford (1894\u20131973) was an American film director whose career spanned from 1913 to 1971. During this time he directed more than 140 films. Born in Maine, Ford entered the filmmaking industry shortly after graduating from high school with the help of his older brother, Francis Ford, who had established himself as a leading man and director for Universal Studios. After working as an actor, assistant director, stuntman, and prop man \u2013 often for his brother \u2013 Universal gave Ford the opportunity to direct in 1917. Initially working in short films, he quickly moved into features, largely with Harry Carey as his star. In 1920 Ford left Universal and began working for the Fox Film Corporation. During the next ten years he directed more than 30 films, including the westerns The Iron Horse (1924) and 3 Bad Men (1926), both starring George O'Brien, the war drama Four Sons and the Irish romantic drama Hangman's House (both 1928 and both starring Victor McLaglen). In the same year of these last two films, Ford directed his first all-talking film, the short Napoleon's Barber. The following year he directed his first all-talking feature, The Black Watch.\n.", "output": "a", "explanation": "The question is about both Francis and John Ford, so more details on both are needed to answer the question. There is no single entity in the passage that can lead to the answer."}, {"input": "Question: Is the woman who gave the starting command at the Indy 500 for the last time in 2016 still alive? Passage: In most cases, Tony Hulman would give the command, then ride in the pace car during the pace laps. Mary F. Hulman would give the command near the pace car, but rarely rode in the pace car due to her age and declining health. Eventually, the location was moved to near the start/finish line, and in 2001, it was moved to the new Victory Podium stage adjacent to the Pagoda. In 2011 only, Mari George moved back to the front of the starting grid to give the command, and then she rode in the pace car with A. J. Foyt. In 2014, as a special gesture to Jim Nabors's final performance at Indy, the starting command was given in unison by both Mari George and Nabors, marking the first time a non-member of the Hulman-George family had given the command for the 500 since 1954. In 2016 for the 100th Indianapolis 500, now-matriarch Mari was joined by three subsequent generations of the Hulman-George family, who gave the command together. Due to her advanced age, the 2016 race would be Mari's final turn giving the command. Later that same year, Tony George gave the starting command for the Brickyard 400, his first time giving a command since a restart command in 1986. For the 2017 Indianapolis 500, the duty was permanently assigned to Tony George. In that year, Tony George began using the phrase \"Drivers, start your engines\" instead of the more familiar \"Lady and gentlemen...\" variation. However, for the 2019 race, George recited that latter variation.\n'.", "output": "b", "explanation": "Mari Hulman George gave the starting command at the Indy 500 in 2016 so only information about her is needed."}], "Negative Examples": [{"input": "Question: How many Super Bowls did the team the Cardinals beat to make their first appearance in the Super Bowl win? Passage: The 2008 Arizona Cardinals season was the 89th season for the team in the National Football League and their 21st season in Arizona. The season marked the Cardinals' first Super Bowl appearance, coming as a result of their victory against the Philadelphia Eagles in the NFC Championship. The Cardinals slogan for the season was \"Shock The World!\" Riding the back of quarterback Kurt Warner, who had gone from being a backup for the St. Louis Rams in 1999 to leading the Greatest Show on Turf to a Super Bowl XXXIV victory, and franchise wide receiver Larry Fitzgerald, the Cardinals went on a playoff run for the ages after having won just one playoff game in the last sixty years, as Warner once again recreated the magic he had captured with the Rams. (Coincidentally, both teams were based in St Louis at one point or another, only to relocate to different cities.)\n.", "output": "a", "explanation": "The passage mentions that the Arizona Cardinals beat the Eagles, so any further information will only be available with respect to the Eagles' season meaning only one link is needed."}, {"input": "Question: How many NCAA football championships have been won by the college that Peyton Manning attended? Passage: In 1998 the Colts, for the 4th time in 15 years, held the 1st overall pick in the draft and for the 3rd time in 15 years selected a quarterback \u2013 this time Peyton Manning. Manning started the first game of his rookie season and started every single Colts game since until the start of the 2011 season, when a recurring neck injury sidelined him. Despite a difficult rookie season, where he threw a league high 28 interceptions, Manning and the Colts responded by finishing 13\u20133 in 1999. The 10 game turnaround from the previous year set an NFL record. Even with this turnaround, the Colts lost in the playoffs. The following years would be marked by a near constant pattern. The Colts and Manning successes in the regular season were matched only by their failures in the post season. Manning was named to the Pro Bowl in 1999, 2000, 2002, 2003 and 2004, as well as winning the NFL MVP award in both 2003 and 2004. In 2004 Manning set a then NFL record when he threw 49 touchdowns in a single season. In spite of this the team failed in the playoffs, including early round exits in 1999, 2000, 2002 and 2005. In both 2003 and 2004 the Colts would lose to eventual Super Bowl winning New England Patriots in the AFC Championship Game and the Divisional Round respectively. In 2006 the Colts and Manning were finally able to beat the Patriots and their quarterback Tom Brady in the AFC Championship Game on their way to a victory in Super Bowl XLI against the Chicago Bears. Manning was named the Super Bowl MVP. The Colts and Manning would continue to have success, with Manning winning two further MVP awards in 2008 and 2009. In 2009 the Colts would return to the Super Bowl where they would lose to the New Orleans Saints.\n.", "output": "b", "explanation": "Both information on Peyton Manning, and information on the college he attended are needed."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Wikipedia"], "Instance": {"id": "task232-2b11973b1c874493b9bb429903034b2d", "input": "Question: Which of the two states that some claim the treaty territory also includes parts of has a larger total area (sq mi.)? Passage:A Dish With One Spoon, also known as One Dish One Spoon, is a law used by indigenous peoples of the Americas since at least 1142 CE to describe an agreement for sharing hunting territory among two or more nations. People are all eating out of the single dish, that is, all hunting in the shared territory. One spoon signifies that all Peoples sharing the territory are expected to limit the game they take to leave enough for others, and for the continued abundance and viability of the hunting grounds into the future. Sometimes the Indigenous language word is rendered in English as bowl or kettle rather than dish. The Dish With One Spoon phrase is also used to denote the treaty or agreement itself. In particular, a treaty made between the Anishinaabe and Haudenosaunee nations at Montr\u00e9al in 1701, as part of the Great Peace of Montreal is usually called the Dish With One Spoon treaty and its associated wampum belt the Dish With One Spoon wampum. The treaty territory includes part of the current province of Ontario between the Great Lakes and extending east along the north shore of the St. Lawrence River up to the border with the current province of Quebec. Some claim it also includes parts of the current states of New York and Michigan.\n", "output": ["a"]}, "Instance License": ["CC BY 4.0"], "prediction": "b"}
+{"id": "task232-fad8a8639e4a4229a398a72aca44b2d2", "Task": "task232_iirc_link_number_classification", "Contributors": "['Anjana Arunkumar']", "Source": ["iirc"], "URL": ["https://allenai.org/data/iirc"], "Categories": ["Answerability Classification"], "Reasoning": ["Multihop Reasoning", "Cross-document Reasoning", "Discrete Reasoning", "Numerical Reasoning", "Temporal Reasoning"], "Definition": ["In this task, you're given a question, along with a context passage which has extra information available on certain terms mentioned in it, i.e., the proper nouns in the passage. Your job is to determine whether information from more than one term is needed to answer the question. Indicate your choice as `a` for Yes or `b` for No."], "Positive Examples": [{"input": "Question: When did the operation during which the 704th dropped supplies to allied troops near Nijmegen begin? Passage: The group was occasionally diverted from strategic missions to carry out air support and interdiction missions. It supported Operation Overlord, the invasion of Normandy by attacking transportation targets, including bridges, along with airfields and strong points in France. On D Day, the squadron and the rest of the 446th Group led the first heavy bomber mission of the day. The 446th aided ground forces at Caen and Saint-L\u00f4 during July by hitting bridges, gun batteries, and enemy troops. During Operation Market Garden, the attempt to seize a bridgehead across the Rhine in the Netherlands, the 704th dropped supplies to allied troops near Nijmegen. It struck lines of communications during the Battle of the Bulge. During Operation Varsity in March 1945, it supplied ground and airborne troops near Wesel. The squadron flew its last combat mission on 25 April 1945 against Salzburg, Austria. The group had flown 273 missions and had lost 58 aircraft during the war,\n.", "output": "b", "explanation": "The passage describes the 704th's actions during Operation Market Garden so only information about the operation is needed."}, {"input": "Question: How old was Francis Ford when John Ford started his career in filmmaking? Passage: John Ford (1894\u20131973) was an American film director whose career spanned from 1913 to 1971. During this time he directed more than 140 films. Born in Maine, Ford entered the filmmaking industry shortly after graduating from high school with the help of his older brother, Francis Ford, who had established himself as a leading man and director for Universal Studios. After working as an actor, assistant director, stuntman, and prop man \u2013 often for his brother \u2013 Universal gave Ford the opportunity to direct in 1917. Initially working in short films, he quickly moved into features, largely with Harry Carey as his star. In 1920 Ford left Universal and began working for the Fox Film Corporation. During the next ten years he directed more than 30 films, including the westerns The Iron Horse (1924) and 3 Bad Men (1926), both starring George O'Brien, the war drama Four Sons and the Irish romantic drama Hangman's House (both 1928 and both starring Victor McLaglen). In the same year of these last two films, Ford directed his first all-talking film, the short Napoleon's Barber. The following year he directed his first all-talking feature, The Black Watch.\n.", "output": "a", "explanation": "The question is about both Francis and John Ford, so more details on both are needed to answer the question. There is no single entity in the passage that can lead to the answer."}, {"input": "Question: Is the woman who gave the starting command at the Indy 500 for the last time in 2016 still alive? Passage: In most cases, Tony Hulman would give the command, then ride in the pace car during the pace laps. Mary F. Hulman would give the command near the pace car, but rarely rode in the pace car due to her age and declining health. Eventually, the location was moved to near the start/finish line, and in 2001, it was moved to the new Victory Podium stage adjacent to the Pagoda. In 2011 only, Mari George moved back to the front of the starting grid to give the command, and then she rode in the pace car with A. J. Foyt. In 2014, as a special gesture to Jim Nabors's final performance at Indy, the starting command was given in unison by both Mari George and Nabors, marking the first time a non-member of the Hulman-George family had given the command for the 500 since 1954. In 2016 for the 100th Indianapolis 500, now-matriarch Mari was joined by three subsequent generations of the Hulman-George family, who gave the command together. Due to her advanced age, the 2016 race would be Mari's final turn giving the command. Later that same year, Tony George gave the starting command for the Brickyard 400, his first time giving a command since a restart command in 1986. For the 2017 Indianapolis 500, the duty was permanently assigned to Tony George. In that year, Tony George began using the phrase \"Drivers, start your engines\" instead of the more familiar \"Lady and gentlemen...\" variation. However, for the 2019 race, George recited that latter variation.\n'.", "output": "b", "explanation": "Mari Hulman George gave the starting command at the Indy 500 in 2016 so only information about her is needed."}], "Negative Examples": [{"input": "Question: How many Super Bowls did the team the Cardinals beat to make their first appearance in the Super Bowl win? Passage: The 2008 Arizona Cardinals season was the 89th season for the team in the National Football League and their 21st season in Arizona. The season marked the Cardinals' first Super Bowl appearance, coming as a result of their victory against the Philadelphia Eagles in the NFC Championship. The Cardinals slogan for the season was \"Shock The World!\" Riding the back of quarterback Kurt Warner, who had gone from being a backup for the St. Louis Rams in 1999 to leading the Greatest Show on Turf to a Super Bowl XXXIV victory, and franchise wide receiver Larry Fitzgerald, the Cardinals went on a playoff run for the ages after having won just one playoff game in the last sixty years, as Warner once again recreated the magic he had captured with the Rams. (Coincidentally, both teams were based in St Louis at one point or another, only to relocate to different cities.)\n.", "output": "a", "explanation": "The passage mentions that the Arizona Cardinals beat the Eagles, so any further information will only be available with respect to the Eagles' season meaning only one link is needed."}, {"input": "Question: How many NCAA football championships have been won by the college that Peyton Manning attended? Passage: In 1998 the Colts, for the 4th time in 15 years, held the 1st overall pick in the draft and for the 3rd time in 15 years selected a quarterback \u2013 this time Peyton Manning. Manning started the first game of his rookie season and started every single Colts game since until the start of the 2011 season, when a recurring neck injury sidelined him. Despite a difficult rookie season, where he threw a league high 28 interceptions, Manning and the Colts responded by finishing 13\u20133 in 1999. The 10 game turnaround from the previous year set an NFL record. Even with this turnaround, the Colts lost in the playoffs. The following years would be marked by a near constant pattern. The Colts and Manning successes in the regular season were matched only by their failures in the post season. Manning was named to the Pro Bowl in 1999, 2000, 2002, 2003 and 2004, as well as winning the NFL MVP award in both 2003 and 2004. In 2004 Manning set a then NFL record when he threw 49 touchdowns in a single season. In spite of this the team failed in the playoffs, including early round exits in 1999, 2000, 2002 and 2005. In both 2003 and 2004 the Colts would lose to eventual Super Bowl winning New England Patriots in the AFC Championship Game and the Divisional Round respectively. In 2006 the Colts and Manning were finally able to beat the Patriots and their quarterback Tom Brady in the AFC Championship Game on their way to a victory in Super Bowl XLI against the Chicago Bears. Manning was named the Super Bowl MVP. The Colts and Manning would continue to have success, with Manning winning two further MVP awards in 2008 and 2009. In 2009 the Colts would return to the Super Bowl where they would lose to the New Orleans Saints.\n.", "output": "b", "explanation": "Both information on Peyton Manning, and information on the college he attended are needed."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Wikipedia"], "Instance": {"id": "task232-fad8a8639e4a4229a398a72aca44b2d2", "input": "Question: How many total people were killed in the Karachi bus bombing? Passage:Since its exposure in the news media of both France and Pakistan, the scandal has been involved in various investigative journalism and attracted sensations and conspiracy theories in both countries, including this scandal's allegement of financing the political campaign of then-Prime Minister Edouard Balladur in the presidential elections took place in 1995. Upon electing President Jacques Chirac cancelled the commissions and kickbacks, angering many officials in Pakistan and France according to the media reports. Other theories and subsequent investigative journalist reports alleged that the bus bombing on 8 May 2002 in Karachi that killed eleven French engineers in Karachi was in retaliation for the cancellation of these commissions. This theory was rejected by the Government of Pakistan when the FIA and the CID made potential discovery in linking the HuM and the al-Qaeda had carried out the terrorist attack in Karachi, mistaking the French nationals for the Americans.\n", "output": ["b"]}, "Instance License": ["CC BY 4.0"], "prediction": "b"}
+{"id": "task1391-0436bad782b6443582d037aec6b4b96e", "Task": "task1391_winogrande_easy_answer_generation", "Contributors": "['Yeganeh Kordi']", "Source": ["winogrande"], "URL": ["https://huggingface.co/datasets/winogrande/"], "Categories": ["Coreference Resolution"], "Reasoning": ["Commonsense Reasoning"], "Definition": ["In this task, you are given a question containing a blank (_) and two options. You should pick the best option to answer the question. Please answer with \"A\" or \"B\"."], "Positive Examples": [{"input": "Katrina gave Christine a stuffed animal for their birthday, but _ already had this one. (A) Katrina (B) Christine", "output": "B", "explanation": "Since the blank is someone who received the gift and already had a stuffed animal, the answer must be \"Christine\"."}, {"input": "Jessy decided to clean the floor but not the furniture, because the _ was dirty. (A) floor (B) furniture", "output": "A", "explanation": "The blank is \"dirty\", which has to be \"floor\"."}, {"input": "The man tried to put the beanie inside the drawer but the _ was too small. (A) beanie (B) drawer", "output": "B", "explanation": "Since the blank co-appears with \"too small\", it must be the object that the beanie didn't fit inside it (i.e., \"the drawer\")."}, {"input": "The girl took care of her skin with the cream instead of the ointment, because the _ was comfortable. (A) ointment (B) cream", "output": "B", "explanation": "Since _ was \"comfortable\", it must be something that the girl took care of her skin with (\"cream\")."}], "Negative Examples": [{"input": "Ian got into position and punched Lawrence so hard that his mouthpiece flew right out because _ was a quick fighter. (A) Ian (B) Lawrence", "output": "C", "explanation": "The issue is that the answer is not one of the options presented in the question which are \"A\" and \"B\". Note that, a valid answer must be one of the options."}, {"input": "Kevin had to use less sunscreen when at the beach tanning than Justin because _ had less sensitive skin. (A) Kevin (B) Justin", "output": "(A)", "explanation": "Here, an additonal parentheses has been added to the answer. Note that, a valid answer must be \"A\" or \"B\"."}, {"input": "John poured the entire bowl of fish into the hot pan on the stove until the _ was empty. (A) bowl (B) pan", "output": "B", "explanation": "Here, Since John poured the entire bowl of fish into the hot pan and blank was empty, the answer is \"Bowl\". So, option B is incorrect."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Commonsense -> Concepts and Relations -> Social Commonsense", "Commonsense -> Concepts and Relations -> Physical Commonsense"], "Instance": {"id": "task1391-0436bad782b6443582d037aec6b4b96e", "input": "Aaron was wrapping Jeffreys present when _ got more tape and let them finish the job. (A) Aaron (B) Jeffrey", "output": ["B"]}, "Instance License": ["Apache 2.0"], "prediction": "B"}
+{"id": "task1391-67d42151ec564c4dbed6a829f1592ea1", "Task": "task1391_winogrande_easy_answer_generation", "Contributors": "['Yeganeh Kordi']", "Source": ["winogrande"], "URL": ["https://huggingface.co/datasets/winogrande/"], "Categories": ["Coreference Resolution"], "Reasoning": ["Commonsense Reasoning"], "Definition": ["In this task, you are given a question containing a blank (_) and two options. You should pick the best option to answer the question. Please answer with \"A\" or \"B\"."], "Positive Examples": [{"input": "Katrina gave Christine a stuffed animal for their birthday, but _ already had this one. (A) Katrina (B) Christine", "output": "B", "explanation": "Since the blank is someone who received the gift and already had a stuffed animal, the answer must be \"Christine\"."}, {"input": "Jessy decided to clean the floor but not the furniture, because the _ was dirty. (A) floor (B) furniture", "output": "A", "explanation": "The blank is \"dirty\", which has to be \"floor\"."}, {"input": "The man tried to put the beanie inside the drawer but the _ was too small. (A) beanie (B) drawer", "output": "B", "explanation": "Since the blank co-appears with \"too small\", it must be the object that the beanie didn't fit inside it (i.e., \"the drawer\")."}, {"input": "The girl took care of her skin with the cream instead of the ointment, because the _ was comfortable. (A) ointment (B) cream", "output": "B", "explanation": "Since _ was \"comfortable\", it must be something that the girl took care of her skin with (\"cream\")."}], "Negative Examples": [{"input": "Ian got into position and punched Lawrence so hard that his mouthpiece flew right out because _ was a quick fighter. (A) Ian (B) Lawrence", "output": "C", "explanation": "The issue is that the answer is not one of the options presented in the question which are \"A\" and \"B\". Note that, a valid answer must be one of the options."}, {"input": "Kevin had to use less sunscreen when at the beach tanning than Justin because _ had less sensitive skin. (A) Kevin (B) Justin", "output": "(A)", "explanation": "Here, an additonal parentheses has been added to the answer. Note that, a valid answer must be \"A\" or \"B\"."}, {"input": "John poured the entire bowl of fish into the hot pan on the stove until the _ was empty. (A) bowl (B) pan", "output": "B", "explanation": "Here, Since John poured the entire bowl of fish into the hot pan and blank was empty, the answer is \"Bowl\". So, option B is incorrect."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Commonsense -> Concepts and Relations -> Social Commonsense", "Commonsense -> Concepts and Relations -> Physical Commonsense"], "Instance": {"id": "task1391-67d42151ec564c4dbed6a829f1592ea1", "input": "Jane decided to make changes to her kitchen by replacing the wood counters with granite. The _ is easier to clean. (A) granite (B) wood", "output": ["A"]}, "Instance License": ["Apache 2.0"], "prediction": "A"}
+{"id": "task1391-f4e9653bdd6e41f2ba797d336eb240b1", "Task": "task1391_winogrande_easy_answer_generation", "Contributors": "['Yeganeh Kordi']", "Source": ["winogrande"], "URL": ["https://huggingface.co/datasets/winogrande/"], "Categories": ["Coreference Resolution"], "Reasoning": ["Commonsense Reasoning"], "Definition": ["In this task, you are given a question containing a blank (_) and two options. You should pick the best option to answer the question. Please answer with \"A\" or \"B\"."], "Positive Examples": [{"input": "Katrina gave Christine a stuffed animal for their birthday, but _ already had this one. (A) Katrina (B) Christine", "output": "B", "explanation": "Since the blank is someone who received the gift and already had a stuffed animal, the answer must be \"Christine\"."}, {"input": "Jessy decided to clean the floor but not the furniture, because the _ was dirty. (A) floor (B) furniture", "output": "A", "explanation": "The blank is \"dirty\", which has to be \"floor\"."}, {"input": "The man tried to put the beanie inside the drawer but the _ was too small. (A) beanie (B) drawer", "output": "B", "explanation": "Since the blank co-appears with \"too small\", it must be the object that the beanie didn't fit inside it (i.e., \"the drawer\")."}, {"input": "The girl took care of her skin with the cream instead of the ointment, because the _ was comfortable. (A) ointment (B) cream", "output": "B", "explanation": "Since _ was \"comfortable\", it must be something that the girl took care of her skin with (\"cream\")."}], "Negative Examples": [{"input": "Ian got into position and punched Lawrence so hard that his mouthpiece flew right out because _ was a quick fighter. (A) Ian (B) Lawrence", "output": "C", "explanation": "The issue is that the answer is not one of the options presented in the question which are \"A\" and \"B\". Note that, a valid answer must be one of the options."}, {"input": "Kevin had to use less sunscreen when at the beach tanning than Justin because _ had less sensitive skin. (A) Kevin (B) Justin", "output": "(A)", "explanation": "Here, an additonal parentheses has been added to the answer. Note that, a valid answer must be \"A\" or \"B\"."}, {"input": "John poured the entire bowl of fish into the hot pan on the stove until the _ was empty. (A) bowl (B) pan", "output": "B", "explanation": "Here, Since John poured the entire bowl of fish into the hot pan and blank was empty, the answer is \"Bowl\". So, option B is incorrect."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Commonsense -> Concepts and Relations -> Social Commonsense", "Commonsense -> Concepts and Relations -> Physical Commonsense"], "Instance": {"id": "task1391-f4e9653bdd6e41f2ba797d336eb240b1", "input": "After cleaning the greenhouse, Felicia loved finding a butterfly, yet Rachel was scared when _ showed it to her. (A) Felicia (B) Rachel", "output": ["A"]}, "Instance License": ["Apache 2.0"], "prediction": "B"}
+{"id": "task1391-411cdb2c57484d869699857c7f8ce415", "Task": "task1391_winogrande_easy_answer_generation", "Contributors": "['Yeganeh Kordi']", "Source": ["winogrande"], "URL": ["https://huggingface.co/datasets/winogrande/"], "Categories": ["Coreference Resolution"], "Reasoning": ["Commonsense Reasoning"], "Definition": ["In this task, you are given a question containing a blank (_) and two options. You should pick the best option to answer the question. Please answer with \"A\" or \"B\"."], "Positive Examples": [{"input": "Katrina gave Christine a stuffed animal for their birthday, but _ already had this one. (A) Katrina (B) Christine", "output": "B", "explanation": "Since the blank is someone who received the gift and already had a stuffed animal, the answer must be \"Christine\"."}, {"input": "Jessy decided to clean the floor but not the furniture, because the _ was dirty. (A) floor (B) furniture", "output": "A", "explanation": "The blank is \"dirty\", which has to be \"floor\"."}, {"input": "The man tried to put the beanie inside the drawer but the _ was too small. (A) beanie (B) drawer", "output": "B", "explanation": "Since the blank co-appears with \"too small\", it must be the object that the beanie didn't fit inside it (i.e., \"the drawer\")."}, {"input": "The girl took care of her skin with the cream instead of the ointment, because the _ was comfortable. (A) ointment (B) cream", "output": "B", "explanation": "Since _ was \"comfortable\", it must be something that the girl took care of her skin with (\"cream\")."}], "Negative Examples": [{"input": "Ian got into position and punched Lawrence so hard that his mouthpiece flew right out because _ was a quick fighter. (A) Ian (B) Lawrence", "output": "C", "explanation": "The issue is that the answer is not one of the options presented in the question which are \"A\" and \"B\". Note that, a valid answer must be one of the options."}, {"input": "Kevin had to use less sunscreen when at the beach tanning than Justin because _ had less sensitive skin. (A) Kevin (B) Justin", "output": "(A)", "explanation": "Here, an additonal parentheses has been added to the answer. Note that, a valid answer must be \"A\" or \"B\"."}, {"input": "John poured the entire bowl of fish into the hot pan on the stove until the _ was empty. (A) bowl (B) pan", "output": "B", "explanation": "Here, Since John poured the entire bowl of fish into the hot pan and blank was empty, the answer is \"Bowl\". So, option B is incorrect."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Commonsense -> Concepts and Relations -> Social Commonsense", "Commonsense -> Concepts and Relations -> Physical Commonsense"], "Instance": {"id": "task1391-411cdb2c57484d869699857c7f8ce415", "input": "Benjamin was not allergic to cats but Matthew was, so _  went to the shelter and gave up two of them. (A) Benjamin (B) Matthew", "output": ["B"]}, "Instance License": ["Apache 2.0"], "prediction": "B"}
+{"id": "task1391-1115169a4e4d41ec9a7c5e89bd33d805", "Task": "task1391_winogrande_easy_answer_generation", "Contributors": "['Yeganeh Kordi']", "Source": ["winogrande"], "URL": ["https://huggingface.co/datasets/winogrande/"], "Categories": ["Coreference Resolution"], "Reasoning": ["Commonsense Reasoning"], "Definition": ["In this task, you are given a question containing a blank (_) and two options. You should pick the best option to answer the question. Please answer with \"A\" or \"B\"."], "Positive Examples": [{"input": "Katrina gave Christine a stuffed animal for their birthday, but _ already had this one. (A) Katrina (B) Christine", "output": "B", "explanation": "Since the blank is someone who received the gift and already had a stuffed animal, the answer must be \"Christine\"."}, {"input": "Jessy decided to clean the floor but not the furniture, because the _ was dirty. (A) floor (B) furniture", "output": "A", "explanation": "The blank is \"dirty\", which has to be \"floor\"."}, {"input": "The man tried to put the beanie inside the drawer but the _ was too small. (A) beanie (B) drawer", "output": "B", "explanation": "Since the blank co-appears with \"too small\", it must be the object that the beanie didn't fit inside it (i.e., \"the drawer\")."}, {"input": "The girl took care of her skin with the cream instead of the ointment, because the _ was comfortable. (A) ointment (B) cream", "output": "B", "explanation": "Since _ was \"comfortable\", it must be something that the girl took care of her skin with (\"cream\")."}], "Negative Examples": [{"input": "Ian got into position and punched Lawrence so hard that his mouthpiece flew right out because _ was a quick fighter. (A) Ian (B) Lawrence", "output": "C", "explanation": "The issue is that the answer is not one of the options presented in the question which are \"A\" and \"B\". Note that, a valid answer must be one of the options."}, {"input": "Kevin had to use less sunscreen when at the beach tanning than Justin because _ had less sensitive skin. (A) Kevin (B) Justin", "output": "(A)", "explanation": "Here, an additonal parentheses has been added to the answer. Note that, a valid answer must be \"A\" or \"B\"."}, {"input": "John poured the entire bowl of fish into the hot pan on the stove until the _ was empty. (A) bowl (B) pan", "output": "B", "explanation": "Here, Since John poured the entire bowl of fish into the hot pan and blank was empty, the answer is \"Bowl\". So, option B is incorrect."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Commonsense -> Concepts and Relations -> Social Commonsense", "Commonsense -> Concepts and Relations -> Physical Commonsense"], "Instance": {"id": "task1391-1115169a4e4d41ec9a7c5e89bd33d805", "input": "The head of Leslie is aching, but Justin feels just fine, so _ must be the one who is sick. (A) Leslie (B) Justin", "output": ["A"]}, "Instance License": ["Apache 2.0"], "prediction": "B"}
+{"id": "task1358-ad90b65c76bc43a8a9f336dcbb2a066d", "Task": "task1358_xlsum_title_generation", "Contributors": "['Krishna Sree G']", "Source": ["xlsum"], "URL": ["https://arxiv.org/abs/2106.13822"], "Categories": ["Title Generation"], "Reasoning": [], "Definition": ["In this task, you need to generate an appropriate title for the given summary of some paragraph. The generated title must be short and should include the main topic of the given text. Your summary should be less than 20 words long."], "Positive Examples": [{"input": "For many Brazilians, Michel Temer's ascension to president was surprising. But as the first Brazilian president to have charges brought against him while in office, his arrest is less unexpected.", "output": "Michel Temer: Brazil's arrested former president", "explanation": "The output is a relevant title for the given passage as it highlights the main crux of the given text."}, {"input": "Scientists say a new test for sepsis could cut diagnosis times from days to minutes.", "output": "Sepsis test could cut diagnosis time from days to minutes", "explanation": "The output provides a correct summary of the given text."}, {"input": "The recent high-profile spat with the US over the Hollywood film \"The Interview\" painted North Korea's enigmatic young leader Kim Jong-un as impetuous.", "output": "Impetuous Kim Jong-un in The Interview", "explanation": "Impetuous Kim Jong-un in The Interview is apt and appropriate title for the given text."}], "Negative Examples": [{"input": "The Scottish Conservatives have said radical changes are needed to Scottish schools to help youngsters from poorer families get to university.", "output": "Conservatives call for a reform", "explanation": "Although the text is about conservatives calling for a reform, it is too short and lacks important information, like \"Scottish\", or the type of the reform."}, {"input": "Two Labour politicians have called for the Welsh Government to make face masks mandatory for people visiting hospitals.", "output": "Two politicians have called for the Welsh Government to make face masks mandatory for people.", "explanation": "This is a misleading title, as it doesn't mention the requirement is not for all people, and also, it is just a butchered form of the actual text. This is not a good title."}, {"input": "High Covid-19 infection rates mean it is \"too risky\" to allow household support bubbles to be formed on the Isle of Man, the chief minister has told Tynwald.", "output": "Eric Clapton to sell off guitars for Crossroads Centre", "explanation": "The output is not at all relevant to the given text. Covid: Allowing support bubbles between Manx households 'too risky' would be a correct title."}, {"input": "A body has been found in the search for a woman who went missing in floods after her car got stuck in water.", "output": "Headline numbers: Feeling the OBR's pain", "explanation": "This is not the suitable title. Title can be: Body found in search for woman missing in floods."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["News"], "Instance": {"id": "task1358-ad90b65c76bc43a8a9f336dcbb2a066d", "input": "Scotland's fishing industry will have access to fewer cod, haddock, whiting and saithe under the new Brexit deal, according to the Scottish government.", "output": ["Scottish fishing industry 'deeply aggrieved' by Brexit deal"]}, "Instance License": ["CC BY-SA 4.0"], "prediction": "Scotland's fishing industry will have access to fewer cod, haddock, whiting and saithe under the new Brexit deal."}
+{"id": "task1358-b4567593f05541eca394b3b864562a8f", "Task": "task1358_xlsum_title_generation", "Contributors": "['Krishna Sree G']", "Source": ["xlsum"], "URL": ["https://arxiv.org/abs/2106.13822"], "Categories": ["Title Generation"], "Reasoning": [], "Definition": ["In this task, you need to generate an appropriate title for the given summary of some paragraph. The generated title must be short and should include the main topic of the given text. Your summary should be less than 20 words long."], "Positive Examples": [{"input": "For many Brazilians, Michel Temer's ascension to president was surprising. But as the first Brazilian president to have charges brought against him while in office, his arrest is less unexpected.", "output": "Michel Temer: Brazil's arrested former president", "explanation": "The output is a relevant title for the given passage as it highlights the main crux of the given text."}, {"input": "Scientists say a new test for sepsis could cut diagnosis times from days to minutes.", "output": "Sepsis test could cut diagnosis time from days to minutes", "explanation": "The output provides a correct summary of the given text."}, {"input": "The recent high-profile spat with the US over the Hollywood film \"The Interview\" painted North Korea's enigmatic young leader Kim Jong-un as impetuous.", "output": "Impetuous Kim Jong-un in The Interview", "explanation": "Impetuous Kim Jong-un in The Interview is apt and appropriate title for the given text."}], "Negative Examples": [{"input": "The Scottish Conservatives have said radical changes are needed to Scottish schools to help youngsters from poorer families get to university.", "output": "Conservatives call for a reform", "explanation": "Although the text is about conservatives calling for a reform, it is too short and lacks important information, like \"Scottish\", or the type of the reform."}, {"input": "Two Labour politicians have called for the Welsh Government to make face masks mandatory for people visiting hospitals.", "output": "Two politicians have called for the Welsh Government to make face masks mandatory for people.", "explanation": "This is a misleading title, as it doesn't mention the requirement is not for all people, and also, it is just a butchered form of the actual text. This is not a good title."}, {"input": "High Covid-19 infection rates mean it is \"too risky\" to allow household support bubbles to be formed on the Isle of Man, the chief minister has told Tynwald.", "output": "Eric Clapton to sell off guitars for Crossroads Centre", "explanation": "The output is not at all relevant to the given text. Covid: Allowing support bubbles between Manx households 'too risky' would be a correct title."}, {"input": "A body has been found in the search for a woman who went missing in floods after her car got stuck in water.", "output": "Headline numbers: Feeling the OBR's pain", "explanation": "This is not the suitable title. Title can be: Body found in search for woman missing in floods."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["News"], "Instance": {"id": "task1358-b4567593f05541eca394b3b864562a8f", "input": "The Chinese PC manufacturer Lenovo has been accused of running a \"massive security risk\" after researchers found flaws in its software.", "output": ["Lenovo: researchers find 'massive security risk'"]}, "Instance License": ["CC BY-SA 4.0"], "prediction": "Lenovo accused of running a \"massive security risk\""}
+{"id": "task1358-08222191baa44250a28c89bbb4581270", "Task": "task1358_xlsum_title_generation", "Contributors": "['Krishna Sree G']", "Source": ["xlsum"], "URL": ["https://arxiv.org/abs/2106.13822"], "Categories": ["Title Generation"], "Reasoning": [], "Definition": ["In this task, you need to generate an appropriate title for the given summary of some paragraph. The generated title must be short and should include the main topic of the given text. Your summary should be less than 20 words long."], "Positive Examples": [{"input": "For many Brazilians, Michel Temer's ascension to president was surprising. But as the first Brazilian president to have charges brought against him while in office, his arrest is less unexpected.", "output": "Michel Temer: Brazil's arrested former president", "explanation": "The output is a relevant title for the given passage as it highlights the main crux of the given text."}, {"input": "Scientists say a new test for sepsis could cut diagnosis times from days to minutes.", "output": "Sepsis test could cut diagnosis time from days to minutes", "explanation": "The output provides a correct summary of the given text."}, {"input": "The recent high-profile spat with the US over the Hollywood film \"The Interview\" painted North Korea's enigmatic young leader Kim Jong-un as impetuous.", "output": "Impetuous Kim Jong-un in The Interview", "explanation": "Impetuous Kim Jong-un in The Interview is apt and appropriate title for the given text."}], "Negative Examples": [{"input": "The Scottish Conservatives have said radical changes are needed to Scottish schools to help youngsters from poorer families get to university.", "output": "Conservatives call for a reform", "explanation": "Although the text is about conservatives calling for a reform, it is too short and lacks important information, like \"Scottish\", or the type of the reform."}, {"input": "Two Labour politicians have called for the Welsh Government to make face masks mandatory for people visiting hospitals.", "output": "Two politicians have called for the Welsh Government to make face masks mandatory for people.", "explanation": "This is a misleading title, as it doesn't mention the requirement is not for all people, and also, it is just a butchered form of the actual text. This is not a good title."}, {"input": "High Covid-19 infection rates mean it is \"too risky\" to allow household support bubbles to be formed on the Isle of Man, the chief minister has told Tynwald.", "output": "Eric Clapton to sell off guitars for Crossroads Centre", "explanation": "The output is not at all relevant to the given text. Covid: Allowing support bubbles between Manx households 'too risky' would be a correct title."}, {"input": "A body has been found in the search for a woman who went missing in floods after her car got stuck in water.", "output": "Headline numbers: Feeling the OBR's pain", "explanation": "This is not the suitable title. Title can be: Body found in search for woman missing in floods."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["News"], "Instance": {"id": "task1358-08222191baa44250a28c89bbb4581270", "input": "Proposals to close roads outside schools during drop-off and pick-up times are among plans to tackle air pollution in Bristol.", "output": ["Bristol mayor Marvin Rees makes clean air pledges for city"]}, "Instance License": ["CC BY-SA 4.0"], "prediction": "Proposals to close roads outside schools during drop-off and pick-up times are among plans to tackle air pollution in Bristol."}
+{"id": "task1358-018f52be78814968b79f14ab97a9d67b", "Task": "task1358_xlsum_title_generation", "Contributors": "['Krishna Sree G']", "Source": ["xlsum"], "URL": ["https://arxiv.org/abs/2106.13822"], "Categories": ["Title Generation"], "Reasoning": [], "Definition": ["In this task, you need to generate an appropriate title for the given summary of some paragraph. The generated title must be short and should include the main topic of the given text. Your summary should be less than 20 words long."], "Positive Examples": [{"input": "For many Brazilians, Michel Temer's ascension to president was surprising. But as the first Brazilian president to have charges brought against him while in office, his arrest is less unexpected.", "output": "Michel Temer: Brazil's arrested former president", "explanation": "The output is a relevant title for the given passage as it highlights the main crux of the given text."}, {"input": "Scientists say a new test for sepsis could cut diagnosis times from days to minutes.", "output": "Sepsis test could cut diagnosis time from days to minutes", "explanation": "The output provides a correct summary of the given text."}, {"input": "The recent high-profile spat with the US over the Hollywood film \"The Interview\" painted North Korea's enigmatic young leader Kim Jong-un as impetuous.", "output": "Impetuous Kim Jong-un in The Interview", "explanation": "Impetuous Kim Jong-un in The Interview is apt and appropriate title for the given text."}], "Negative Examples": [{"input": "The Scottish Conservatives have said radical changes are needed to Scottish schools to help youngsters from poorer families get to university.", "output": "Conservatives call for a reform", "explanation": "Although the text is about conservatives calling for a reform, it is too short and lacks important information, like \"Scottish\", or the type of the reform."}, {"input": "Two Labour politicians have called for the Welsh Government to make face masks mandatory for people visiting hospitals.", "output": "Two politicians have called for the Welsh Government to make face masks mandatory for people.", "explanation": "This is a misleading title, as it doesn't mention the requirement is not for all people, and also, it is just a butchered form of the actual text. This is not a good title."}, {"input": "High Covid-19 infection rates mean it is \"too risky\" to allow household support bubbles to be formed on the Isle of Man, the chief minister has told Tynwald.", "output": "Eric Clapton to sell off guitars for Crossroads Centre", "explanation": "The output is not at all relevant to the given text. Covid: Allowing support bubbles between Manx households 'too risky' would be a correct title."}, {"input": "A body has been found in the search for a woman who went missing in floods after her car got stuck in water.", "output": "Headline numbers: Feeling the OBR's pain", "explanation": "This is not the suitable title. Title can be: Body found in search for woman missing in floods."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["News"], "Instance": {"id": "task1358-018f52be78814968b79f14ab97a9d67b", "input": "The first \"Neolithic\" long barrow to be built in the UK for 5,000 years, is attracting interest from all over the world.", "output": ["All Cannings 'Neolithic' long barrow takes shape"]}, "Instance License": ["CC BY-SA 4.0"], "prediction": "The first Neolithic long barrow to be built in the UK for 5,000 years, is attracting interest from all over the world."}
+{"id": "task1358-3fc620b8565b4a7395cb5a4a7252a07f", "Task": "task1358_xlsum_title_generation", "Contributors": "['Krishna Sree G']", "Source": ["xlsum"], "URL": ["https://arxiv.org/abs/2106.13822"], "Categories": ["Title Generation"], "Reasoning": [], "Definition": ["In this task, you need to generate an appropriate title for the given summary of some paragraph. The generated title must be short and should include the main topic of the given text. Your summary should be less than 20 words long."], "Positive Examples": [{"input": "For many Brazilians, Michel Temer's ascension to president was surprising. But as the first Brazilian president to have charges brought against him while in office, his arrest is less unexpected.", "output": "Michel Temer: Brazil's arrested former president", "explanation": "The output is a relevant title for the given passage as it highlights the main crux of the given text."}, {"input": "Scientists say a new test for sepsis could cut diagnosis times from days to minutes.", "output": "Sepsis test could cut diagnosis time from days to minutes", "explanation": "The output provides a correct summary of the given text."}, {"input": "The recent high-profile spat with the US over the Hollywood film \"The Interview\" painted North Korea's enigmatic young leader Kim Jong-un as impetuous.", "output": "Impetuous Kim Jong-un in The Interview", "explanation": "Impetuous Kim Jong-un in The Interview is apt and appropriate title for the given text."}], "Negative Examples": [{"input": "The Scottish Conservatives have said radical changes are needed to Scottish schools to help youngsters from poorer families get to university.", "output": "Conservatives call for a reform", "explanation": "Although the text is about conservatives calling for a reform, it is too short and lacks important information, like \"Scottish\", or the type of the reform."}, {"input": "Two Labour politicians have called for the Welsh Government to make face masks mandatory for people visiting hospitals.", "output": "Two politicians have called for the Welsh Government to make face masks mandatory for people.", "explanation": "This is a misleading title, as it doesn't mention the requirement is not for all people, and also, it is just a butchered form of the actual text. This is not a good title."}, {"input": "High Covid-19 infection rates mean it is \"too risky\" to allow household support bubbles to be formed on the Isle of Man, the chief minister has told Tynwald.", "output": "Eric Clapton to sell off guitars for Crossroads Centre", "explanation": "The output is not at all relevant to the given text. Covid: Allowing support bubbles between Manx households 'too risky' would be a correct title."}, {"input": "A body has been found in the search for a woman who went missing in floods after her car got stuck in water.", "output": "Headline numbers: Feeling the OBR's pain", "explanation": "This is not the suitable title. Title can be: Body found in search for woman missing in floods."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["News"], "Instance": {"id": "task1358-3fc620b8565b4a7395cb5a4a7252a07f", "input": "Instagram star Essena O'Neill generated masses of coverage this week when she declared she would quit social media. Why has her announcement caused a big reaction?", "output": ["The fallout from a social media bombshell"]}, "Instance License": ["CC BY-SA 4.0"], "prediction": "Essena O'Neill: Why has her announcement caused a big reaction?"}
+{"id": "task1533-f8088b7ea96c4b0b92fb99ffba00767c", "Task": "task1533_daily_dialog_formal_classification", "Contributors": "['Krishna Sriharsha Gundu']", "Source": ["dailydialog"], "URL": ["https://huggingface.co/datasets/daily_dialog"], "Categories": ["Dialogue Act Recognition"], "Reasoning": [], "Definition": ["You are given a conversation between two people. 'Person1:' and 'Person2:' are used to separate their respective dialogues. You are required to assign a label 'formal' if there is an absence of emotion and a presence of questions anywhere within the conversation. If such pattern is not found assign the label 'informal'."], "Positive Examples": [{"input": "Person1:      Hey man , you wanna buy some weed ?  \n Person2:Some what ?  \n Person 1:Weed ! You know ? Pot , Ganja , Mary Jane some chronic !  \n Person2: Oh , umm , no thanks . \n Person1:      I also have blow if you prefer to do a few lines . \n Person2: No , I am ok , really . \n Person1:      Come on man ! I even got dope and acid ! Try some ! \n Person2: Do you really have all of these drugs ? Where do you get them from ? \n Person1:      I got my connections ! Just tell me what you want and I \u2019 ll even give you one ounce for free . \n Person2: Sounds good ! Let \u2019 s see , I want . \n Person1:      Yeah ?  \n Person2:I want you to put your hands behind your head ! You are under arrest ! ", "output": "informal", "explanation": "Based on the conversation, we can see that there is a presence of exclamation which is not present in a formal discussion. Therefore this is an informal conversation"}, {"input": "Person1:      The taxi drivers are on strike again . \n Person2: What for ? \n Person1:      They want the government to reduce the price of the gasoline . \n Person1:      It is really a hot potato . ", "output": "informal", "explanation": "The phrase hot potato is an informal phrase and is used in such context"}, {"input": "Person1:      We've managed to reduce our energy consumption in our factory by about 15 per cent in the last two years . \n Person2: That's excellent . How have you managed that ?  \n Person1:      Mainly because we've invested in a heat recovery system . \n Person2: What does that mean exactly ?  \n Person1:      Well , we use the exhaust gases from our printing presses to provide energy to heat our dryers .  \n Person2: What other sources of energy do you use ? \n Person1:      We don't use any fossil fuels . Most of our power comes from hydro-electric plants . We're hoping to use even more energy from alternative sources in the future - perhaps even wind power . ", "output": "formal", "explanation": "This sounds like a formal conversation about energy consumption. It neither has any detected emotion nor has a commissive statement."}], "Negative Examples": [{"input": "Person1:      What are your personal weaknesses ?  \n Person2: I \u2019 m afraid I \u2019 m a poor talker . I \u2019 m not comfortable talking with the people whom I have just met for the first time . That is not very good for business , so I have been studying public speaking .  \n Person1:      Are you more of a leader or a follower ?  \n Person2: I don \u2019 t try to lead people . I \u2019 d rather cooperate with everybody , and get the job done by working together . \n Person1:      Do you think you can make yourself easily understood in English ?  \n Person2:Yes , in most circumstances .  \n Person1:      Are you available for travel ?  \n Person2: Yes , I like travelling . I am young , and unmarried . It \u2019 s no problem for me to travel frequently . ", "output": "formal", "explanation": "The context of the conversation appears to be about personal traits which are expressed with a sad tone. Therefore this cannot be classified as a formal conversation. This should be classified as informal"}, {"input": "Person1:      Hello , this is Mike , Kara . \n Person2: Mike ! Good to hear from you . How are you ?  \n Person1:      Everything is fine , and how are you ?  \n Person2:Things are going well with me .  \n Person 1:Kara , I had fun the other night at the movies and was wondering if you would like to go out again this Friday . \n Person2: Mike , I don't think that it's a good idea to go out again . I really need to focus on getting packed and ready to move back home .  \n Person1:      Maybe we could just meet for coffee or something .  \n Person2: I can't really deal with any distractions right now , but I appreciate the nice evening we spent together . ", "output": "informal", "explanation": "The conversation does not have any detected emotion. This is a formal meet and greets kind of conversation. Therefore this should be classified as informal. This is formal conversation."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Dialogue"], "Instance": {"id": "task1533-f8088b7ea96c4b0b92fb99ffba00767c", "input": " Person1:       Welcome to Super Stereos . What can I do for you ?  \n Person2:I'd like to look at your stereo systems . Do you have anything on sale ?  \n Person1:        Yes , this system over here is on sale for $ 1,000 . As you can see , all of the components are brand-name .  \n Person2:But it doesn't have a turntable . I have a fair number of vinyl records , so I need something to play them on .  \n Person1:        Our selection of stereo systems with turntables is somewhat limited , but we do have this system over here . ", "output": ["formal"]}, "Instance License": ["CC BY-NC-SA 4.0"], "prediction": "formal"}
+{"id": "task1533-fb1a36db68254787bd73c6e41317f314", "Task": "task1533_daily_dialog_formal_classification", "Contributors": "['Krishna Sriharsha Gundu']", "Source": ["dailydialog"], "URL": ["https://huggingface.co/datasets/daily_dialog"], "Categories": ["Dialogue Act Recognition"], "Reasoning": [], "Definition": ["You are given a conversation between two people. 'Person1:' and 'Person2:' are used to separate their respective dialogues. You are required to assign a label 'formal' if there is an absence of emotion and a presence of questions anywhere within the conversation. If such pattern is not found assign the label 'informal'."], "Positive Examples": [{"input": "Person1:      Hey man , you wanna buy some weed ?  \n Person2:Some what ?  \n Person 1:Weed ! You know ? Pot , Ganja , Mary Jane some chronic !  \n Person2: Oh , umm , no thanks . \n Person1:      I also have blow if you prefer to do a few lines . \n Person2: No , I am ok , really . \n Person1:      Come on man ! I even got dope and acid ! Try some ! \n Person2: Do you really have all of these drugs ? Where do you get them from ? \n Person1:      I got my connections ! Just tell me what you want and I \u2019 ll even give you one ounce for free . \n Person2: Sounds good ! Let \u2019 s see , I want . \n Person1:      Yeah ?  \n Person2:I want you to put your hands behind your head ! You are under arrest ! ", "output": "informal", "explanation": "Based on the conversation, we can see that there is a presence of exclamation which is not present in a formal discussion. Therefore this is an informal conversation"}, {"input": "Person1:      The taxi drivers are on strike again . \n Person2: What for ? \n Person1:      They want the government to reduce the price of the gasoline . \n Person1:      It is really a hot potato . ", "output": "informal", "explanation": "The phrase hot potato is an informal phrase and is used in such context"}, {"input": "Person1:      We've managed to reduce our energy consumption in our factory by about 15 per cent in the last two years . \n Person2: That's excellent . How have you managed that ?  \n Person1:      Mainly because we've invested in a heat recovery system . \n Person2: What does that mean exactly ?  \n Person1:      Well , we use the exhaust gases from our printing presses to provide energy to heat our dryers .  \n Person2: What other sources of energy do you use ? \n Person1:      We don't use any fossil fuels . Most of our power comes from hydro-electric plants . We're hoping to use even more energy from alternative sources in the future - perhaps even wind power . ", "output": "formal", "explanation": "This sounds like a formal conversation about energy consumption. It neither has any detected emotion nor has a commissive statement."}], "Negative Examples": [{"input": "Person1:      What are your personal weaknesses ?  \n Person2: I \u2019 m afraid I \u2019 m a poor talker . I \u2019 m not comfortable talking with the people whom I have just met for the first time . That is not very good for business , so I have been studying public speaking .  \n Person1:      Are you more of a leader or a follower ?  \n Person2: I don \u2019 t try to lead people . I \u2019 d rather cooperate with everybody , and get the job done by working together . \n Person1:      Do you think you can make yourself easily understood in English ?  \n Person2:Yes , in most circumstances .  \n Person1:      Are you available for travel ?  \n Person2: Yes , I like travelling . I am young , and unmarried . It \u2019 s no problem for me to travel frequently . ", "output": "formal", "explanation": "The context of the conversation appears to be about personal traits which are expressed with a sad tone. Therefore this cannot be classified as a formal conversation. This should be classified as informal"}, {"input": "Person1:      Hello , this is Mike , Kara . \n Person2: Mike ! Good to hear from you . How are you ?  \n Person1:      Everything is fine , and how are you ?  \n Person2:Things are going well with me .  \n Person 1:Kara , I had fun the other night at the movies and was wondering if you would like to go out again this Friday . \n Person2: Mike , I don't think that it's a good idea to go out again . I really need to focus on getting packed and ready to move back home .  \n Person1:      Maybe we could just meet for coffee or something .  \n Person2: I can't really deal with any distractions right now , but I appreciate the nice evening we spent together . ", "output": "informal", "explanation": "The conversation does not have any detected emotion. This is a formal meet and greets kind of conversation. Therefore this should be classified as informal. This is formal conversation."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Dialogue"], "Instance": {"id": "task1533-fb1a36db68254787bd73c6e41317f314", "input": " Person1:       The last thing I want to see is to lose face before my friends .  \n Person2:That \u2019 s really unbearable .  \n Person1:        But you know , things cannot always go as you expect .  \n Person2:So get prepared for everything . ", "output": ["informal"]}, "Instance License": ["CC BY-NC-SA 4.0"], "prediction": "informal"}
+{"id": "task1533-cc717af3c69440c797c182cc8be61a5b", "Task": "task1533_daily_dialog_formal_classification", "Contributors": "['Krishna Sriharsha Gundu']", "Source": ["dailydialog"], "URL": ["https://huggingface.co/datasets/daily_dialog"], "Categories": ["Dialogue Act Recognition"], "Reasoning": [], "Definition": ["You are given a conversation between two people. 'Person1:' and 'Person2:' are used to separate their respective dialogues. You are required to assign a label 'formal' if there is an absence of emotion and a presence of questions anywhere within the conversation. If such pattern is not found assign the label 'informal'."], "Positive Examples": [{"input": "Person1:      Hey man , you wanna buy some weed ?  \n Person2:Some what ?  \n Person 1:Weed ! You know ? Pot , Ganja , Mary Jane some chronic !  \n Person2: Oh , umm , no thanks . \n Person1:      I also have blow if you prefer to do a few lines . \n Person2: No , I am ok , really . \n Person1:      Come on man ! I even got dope and acid ! Try some ! \n Person2: Do you really have all of these drugs ? Where do you get them from ? \n Person1:      I got my connections ! Just tell me what you want and I \u2019 ll even give you one ounce for free . \n Person2: Sounds good ! Let \u2019 s see , I want . \n Person1:      Yeah ?  \n Person2:I want you to put your hands behind your head ! You are under arrest ! ", "output": "informal", "explanation": "Based on the conversation, we can see that there is a presence of exclamation which is not present in a formal discussion. Therefore this is an informal conversation"}, {"input": "Person1:      The taxi drivers are on strike again . \n Person2: What for ? \n Person1:      They want the government to reduce the price of the gasoline . \n Person1:      It is really a hot potato . ", "output": "informal", "explanation": "The phrase hot potato is an informal phrase and is used in such context"}, {"input": "Person1:      We've managed to reduce our energy consumption in our factory by about 15 per cent in the last two years . \n Person2: That's excellent . How have you managed that ?  \n Person1:      Mainly because we've invested in a heat recovery system . \n Person2: What does that mean exactly ?  \n Person1:      Well , we use the exhaust gases from our printing presses to provide energy to heat our dryers .  \n Person2: What other sources of energy do you use ? \n Person1:      We don't use any fossil fuels . Most of our power comes from hydro-electric plants . We're hoping to use even more energy from alternative sources in the future - perhaps even wind power . ", "output": "formal", "explanation": "This sounds like a formal conversation about energy consumption. It neither has any detected emotion nor has a commissive statement."}], "Negative Examples": [{"input": "Person1:      What are your personal weaknesses ?  \n Person2: I \u2019 m afraid I \u2019 m a poor talker . I \u2019 m not comfortable talking with the people whom I have just met for the first time . That is not very good for business , so I have been studying public speaking .  \n Person1:      Are you more of a leader or a follower ?  \n Person2: I don \u2019 t try to lead people . I \u2019 d rather cooperate with everybody , and get the job done by working together . \n Person1:      Do you think you can make yourself easily understood in English ?  \n Person2:Yes , in most circumstances .  \n Person1:      Are you available for travel ?  \n Person2: Yes , I like travelling . I am young , and unmarried . It \u2019 s no problem for me to travel frequently . ", "output": "formal", "explanation": "The context of the conversation appears to be about personal traits which are expressed with a sad tone. Therefore this cannot be classified as a formal conversation. This should be classified as informal"}, {"input": "Person1:      Hello , this is Mike , Kara . \n Person2: Mike ! Good to hear from you . How are you ?  \n Person1:      Everything is fine , and how are you ?  \n Person2:Things are going well with me .  \n Person 1:Kara , I had fun the other night at the movies and was wondering if you would like to go out again this Friday . \n Person2: Mike , I don't think that it's a good idea to go out again . I really need to focus on getting packed and ready to move back home .  \n Person1:      Maybe we could just meet for coffee or something .  \n Person2: I can't really deal with any distractions right now , but I appreciate the nice evening we spent together . ", "output": "informal", "explanation": "The conversation does not have any detected emotion. This is a formal meet and greets kind of conversation. Therefore this should be classified as informal. This is formal conversation."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Dialogue"], "Instance": {"id": "task1533-cc717af3c69440c797c182cc8be61a5b", "input": " Person1:       Hi , Jenny . You look like you are in a hurry to somewhere . Where are you going ?  \n Person2:I am going to the bank . I need to cash some checks .  \n Person1:        That's great . We can go to the bank together .  \n Person2:Why are you going there ?  \n Person1:        I will go to Japan on business for 5 days next Tuesday . I want to exchange some Japanese yen .  \n Person2:I see . Will you bring a lot of money with you ?  \n Person1:        Not really . I plan to bring some cash and withdraw money at the ATM in Japan .  \n Person2:Do you have the bank card in Japan ?  \n Person1:        Nope . You can use the credit card to withdraw the money in foreign countries .  \n Person2:That sounds really convenient . Do you pay extra money to enjoy this service ?  \n Person1:        No . It is free of charge .  \n Person2:Great ! I will apply for a credit card when I go to the bank later .  \n Person1:        I think we are running out of time . The bank is going to close soon . ", "output": ["informal"]}, "Instance License": ["CC BY-NC-SA 4.0"], "prediction": "informal"}
+{"id": "task1533-93402e6db28b428da06c5d792469c6c6", "Task": "task1533_daily_dialog_formal_classification", "Contributors": "['Krishna Sriharsha Gundu']", "Source": ["dailydialog"], "URL": ["https://huggingface.co/datasets/daily_dialog"], "Categories": ["Dialogue Act Recognition"], "Reasoning": [], "Definition": ["You are given a conversation between two people. 'Person1:' and 'Person2:' are used to separate their respective dialogues. You are required to assign a label 'formal' if there is an absence of emotion and a presence of questions anywhere within the conversation. If such pattern is not found assign the label 'informal'."], "Positive Examples": [{"input": "Person1:      Hey man , you wanna buy some weed ?  \n Person2:Some what ?  \n Person 1:Weed ! You know ? Pot , Ganja , Mary Jane some chronic !  \n Person2: Oh , umm , no thanks . \n Person1:      I also have blow if you prefer to do a few lines . \n Person2: No , I am ok , really . \n Person1:      Come on man ! I even got dope and acid ! Try some ! \n Person2: Do you really have all of these drugs ? Where do you get them from ? \n Person1:      I got my connections ! Just tell me what you want and I \u2019 ll even give you one ounce for free . \n Person2: Sounds good ! Let \u2019 s see , I want . \n Person1:      Yeah ?  \n Person2:I want you to put your hands behind your head ! You are under arrest ! ", "output": "informal", "explanation": "Based on the conversation, we can see that there is a presence of exclamation which is not present in a formal discussion. Therefore this is an informal conversation"}, {"input": "Person1:      The taxi drivers are on strike again . \n Person2: What for ? \n Person1:      They want the government to reduce the price of the gasoline . \n Person1:      It is really a hot potato . ", "output": "informal", "explanation": "The phrase hot potato is an informal phrase and is used in such context"}, {"input": "Person1:      We've managed to reduce our energy consumption in our factory by about 15 per cent in the last two years . \n Person2: That's excellent . How have you managed that ?  \n Person1:      Mainly because we've invested in a heat recovery system . \n Person2: What does that mean exactly ?  \n Person1:      Well , we use the exhaust gases from our printing presses to provide energy to heat our dryers .  \n Person2: What other sources of energy do you use ? \n Person1:      We don't use any fossil fuels . Most of our power comes from hydro-electric plants . We're hoping to use even more energy from alternative sources in the future - perhaps even wind power . ", "output": "formal", "explanation": "This sounds like a formal conversation about energy consumption. It neither has any detected emotion nor has a commissive statement."}], "Negative Examples": [{"input": "Person1:      What are your personal weaknesses ?  \n Person2: I \u2019 m afraid I \u2019 m a poor talker . I \u2019 m not comfortable talking with the people whom I have just met for the first time . That is not very good for business , so I have been studying public speaking .  \n Person1:      Are you more of a leader or a follower ?  \n Person2: I don \u2019 t try to lead people . I \u2019 d rather cooperate with everybody , and get the job done by working together . \n Person1:      Do you think you can make yourself easily understood in English ?  \n Person2:Yes , in most circumstances .  \n Person1:      Are you available for travel ?  \n Person2: Yes , I like travelling . I am young , and unmarried . It \u2019 s no problem for me to travel frequently . ", "output": "formal", "explanation": "The context of the conversation appears to be about personal traits which are expressed with a sad tone. Therefore this cannot be classified as a formal conversation. This should be classified as informal"}, {"input": "Person1:      Hello , this is Mike , Kara . \n Person2: Mike ! Good to hear from you . How are you ?  \n Person1:      Everything is fine , and how are you ?  \n Person2:Things are going well with me .  \n Person 1:Kara , I had fun the other night at the movies and was wondering if you would like to go out again this Friday . \n Person2: Mike , I don't think that it's a good idea to go out again . I really need to focus on getting packed and ready to move back home .  \n Person1:      Maybe we could just meet for coffee or something .  \n Person2: I can't really deal with any distractions right now , but I appreciate the nice evening we spent together . ", "output": "informal", "explanation": "The conversation does not have any detected emotion. This is a formal meet and greets kind of conversation. Therefore this should be classified as informal. This is formal conversation."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Dialogue"], "Instance": {"id": "task1533-93402e6db28b428da06c5d792469c6c6", "input": " Person1:       My son is alway complaining that I dump on him . He was very rude and told me to mind my own business . I cannot put up with that .  \n Person2:What does his dad say ?  \n Person1:        John is a peacemaker . He simply doesn \u2019 t bother . He says he should give him a free hand . ", "output": ["formal"]}, "Instance License": ["CC BY-NC-SA 4.0"], "prediction": "informal"}
+{"id": "task1533-043ca63700b54dc5a3d1db59b52ccef7", "Task": "task1533_daily_dialog_formal_classification", "Contributors": "['Krishna Sriharsha Gundu']", "Source": ["dailydialog"], "URL": ["https://huggingface.co/datasets/daily_dialog"], "Categories": ["Dialogue Act Recognition"], "Reasoning": [], "Definition": ["You are given a conversation between two people. 'Person1:' and 'Person2:' are used to separate their respective dialogues. You are required to assign a label 'formal' if there is an absence of emotion and a presence of questions anywhere within the conversation. If such pattern is not found assign the label 'informal'."], "Positive Examples": [{"input": "Person1:      Hey man , you wanna buy some weed ?  \n Person2:Some what ?  \n Person 1:Weed ! You know ? Pot , Ganja , Mary Jane some chronic !  \n Person2: Oh , umm , no thanks . \n Person1:      I also have blow if you prefer to do a few lines . \n Person2: No , I am ok , really . \n Person1:      Come on man ! I even got dope and acid ! Try some ! \n Person2: Do you really have all of these drugs ? Where do you get them from ? \n Person1:      I got my connections ! Just tell me what you want and I \u2019 ll even give you one ounce for free . \n Person2: Sounds good ! Let \u2019 s see , I want . \n Person1:      Yeah ?  \n Person2:I want you to put your hands behind your head ! You are under arrest ! ", "output": "informal", "explanation": "Based on the conversation, we can see that there is a presence of exclamation which is not present in a formal discussion. Therefore this is an informal conversation"}, {"input": "Person1:      The taxi drivers are on strike again . \n Person2: What for ? \n Person1:      They want the government to reduce the price of the gasoline . \n Person1:      It is really a hot potato . ", "output": "informal", "explanation": "The phrase hot potato is an informal phrase and is used in such context"}, {"input": "Person1:      We've managed to reduce our energy consumption in our factory by about 15 per cent in the last two years . \n Person2: That's excellent . How have you managed that ?  \n Person1:      Mainly because we've invested in a heat recovery system . \n Person2: What does that mean exactly ?  \n Person1:      Well , we use the exhaust gases from our printing presses to provide energy to heat our dryers .  \n Person2: What other sources of energy do you use ? \n Person1:      We don't use any fossil fuels . Most of our power comes from hydro-electric plants . We're hoping to use even more energy from alternative sources in the future - perhaps even wind power . ", "output": "formal", "explanation": "This sounds like a formal conversation about energy consumption. It neither has any detected emotion nor has a commissive statement."}], "Negative Examples": [{"input": "Person1:      What are your personal weaknesses ?  \n Person2: I \u2019 m afraid I \u2019 m a poor talker . I \u2019 m not comfortable talking with the people whom I have just met for the first time . That is not very good for business , so I have been studying public speaking .  \n Person1:      Are you more of a leader or a follower ?  \n Person2: I don \u2019 t try to lead people . I \u2019 d rather cooperate with everybody , and get the job done by working together . \n Person1:      Do you think you can make yourself easily understood in English ?  \n Person2:Yes , in most circumstances .  \n Person1:      Are you available for travel ?  \n Person2: Yes , I like travelling . I am young , and unmarried . It \u2019 s no problem for me to travel frequently . ", "output": "formal", "explanation": "The context of the conversation appears to be about personal traits which are expressed with a sad tone. Therefore this cannot be classified as a formal conversation. This should be classified as informal"}, {"input": "Person1:      Hello , this is Mike , Kara . \n Person2: Mike ! Good to hear from you . How are you ?  \n Person1:      Everything is fine , and how are you ?  \n Person2:Things are going well with me .  \n Person 1:Kara , I had fun the other night at the movies and was wondering if you would like to go out again this Friday . \n Person2: Mike , I don't think that it's a good idea to go out again . I really need to focus on getting packed and ready to move back home .  \n Person1:      Maybe we could just meet for coffee or something .  \n Person2: I can't really deal with any distractions right now , but I appreciate the nice evening we spent together . ", "output": "informal", "explanation": "The conversation does not have any detected emotion. This is a formal meet and greets kind of conversation. Therefore this should be classified as informal. This is formal conversation."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Dialogue"], "Instance": {"id": "task1533-043ca63700b54dc5a3d1db59b52ccef7", "input": " Person1:       I lost my wallet .  \n Person2:I'm sorry , that's bad luck . ", "output": ["informal"]}, "Instance License": ["CC BY-NC-SA 4.0"], "prediction": "informal"}
+{"id": "task1156-eee061c19ebe498aa25558b0e3e58b33", "Task": "task1156_bard_analogical_reasoning_tools", "Contributors": "['Arjun Ashok']", "Source": ["bard"], "URL": ["https://github.com/NancyFulda/BYU-Analogical-Reasoning-Dataset"], "Categories": ["Word Analogy"], "Reasoning": ["Relational Reasoning", "Commonsense Reasoning", "Analogical Reasoning"], "Definition": ["Two analogies that relate actions to the tools used to perform the action is given in the form \"A : B. C : ?\". \"A : B\" relates action A to tool B. Your task is to replace the question mark (?) with the appropriate tool for the given action C, following the \"A : B\" relation."], "Positive Examples": [{"input": "eat : fork. cook : ?", "output": "pan", "explanation": "The given analogy relates actions to the tools used to perform them. A fork can be used to eat. To cook, a pan can be used."}, {"input": "wash : rag. mop : ?", "output": "mop", "explanation": "The given analogy relates actions to the tools used to perform them. A rag can be used to wash. To mop, a mop can be used."}, {"input": "cut : glass. cut : ?", "output": "scissors", "explanation": "The given analogy relates actions to the tools used to perform them. A knife can be used to cut. To cut, scissors can be used as well."}], "Negative Examples": [{"input": "dig : shovel. wash : ?", "output": "sink", "explanation": "The given analogy relates actions to the tools used to perform them. A knife can be used to cut. To wash, a sink CANNOT be used."}, {"input": "drill : drill. crack : ?", "output": "shovel", "explanation": "The given analogy relates actions to the tools used to perform them. A drill can be used to drill. To crack, a shovel CANNOT be used."}, {"input": "clamp : clamp. cook : ?", "output": "broom", "explanation": "The given analogy relates actions to the tools used to perform them. A clamp can be used to clamp. To cook, a broom CANNOT be used."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Commonsense"], "Instance": {"id": "task1156-eee061c19ebe498aa25558b0e3e58b33", "input": "wash : detergent. unlock : ?", "output": ["key"]}, "Instance License": ["Apache 2.0"], "prediction": "lock"}
+{"id": "task1156-07d449fa168b4240bdc7cb2ca88c2ab2", "Task": "task1156_bard_analogical_reasoning_tools", "Contributors": "['Arjun Ashok']", "Source": ["bard"], "URL": ["https://github.com/NancyFulda/BYU-Analogical-Reasoning-Dataset"], "Categories": ["Word Analogy"], "Reasoning": ["Relational Reasoning", "Commonsense Reasoning", "Analogical Reasoning"], "Definition": ["Two analogies that relate actions to the tools used to perform the action is given in the form \"A : B. C : ?\". \"A : B\" relates action A to tool B. Your task is to replace the question mark (?) with the appropriate tool for the given action C, following the \"A : B\" relation."], "Positive Examples": [{"input": "eat : fork. cook : ?", "output": "pan", "explanation": "The given analogy relates actions to the tools used to perform them. A fork can be used to eat. To cook, a pan can be used."}, {"input": "wash : rag. mop : ?", "output": "mop", "explanation": "The given analogy relates actions to the tools used to perform them. A rag can be used to wash. To mop, a mop can be used."}, {"input": "cut : glass. cut : ?", "output": "scissors", "explanation": "The given analogy relates actions to the tools used to perform them. A knife can be used to cut. To cut, scissors can be used as well."}], "Negative Examples": [{"input": "dig : shovel. wash : ?", "output": "sink", "explanation": "The given analogy relates actions to the tools used to perform them. A knife can be used to cut. To wash, a sink CANNOT be used."}, {"input": "drill : drill. crack : ?", "output": "shovel", "explanation": "The given analogy relates actions to the tools used to perform them. A drill can be used to drill. To crack, a shovel CANNOT be used."}, {"input": "clamp : clamp. cook : ?", "output": "broom", "explanation": "The given analogy relates actions to the tools used to perform them. A clamp can be used to clamp. To cook, a broom CANNOT be used."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Commonsense"], "Instance": {"id": "task1156-07d449fa168b4240bdc7cb2ca88c2ab2", "input": "vacuum : vacuum. spread : ?", "output": ["knife"]}, "Instance License": ["Apache 2.0"], "prediction": "spread"}
+{"id": "task1156-196b949b27a14f9d8b2789037d4c1202", "Task": "task1156_bard_analogical_reasoning_tools", "Contributors": "['Arjun Ashok']", "Source": ["bard"], "URL": ["https://github.com/NancyFulda/BYU-Analogical-Reasoning-Dataset"], "Categories": ["Word Analogy"], "Reasoning": ["Relational Reasoning", "Commonsense Reasoning", "Analogical Reasoning"], "Definition": ["Two analogies that relate actions to the tools used to perform the action is given in the form \"A : B. C : ?\". \"A : B\" relates action A to tool B. Your task is to replace the question mark (?) with the appropriate tool for the given action C, following the \"A : B\" relation."], "Positive Examples": [{"input": "eat : fork. cook : ?", "output": "pan", "explanation": "The given analogy relates actions to the tools used to perform them. A fork can be used to eat. To cook, a pan can be used."}, {"input": "wash : rag. mop : ?", "output": "mop", "explanation": "The given analogy relates actions to the tools used to perform them. A rag can be used to wash. To mop, a mop can be used."}, {"input": "cut : glass. cut : ?", "output": "scissors", "explanation": "The given analogy relates actions to the tools used to perform them. A knife can be used to cut. To cut, scissors can be used as well."}], "Negative Examples": [{"input": "dig : shovel. wash : ?", "output": "sink", "explanation": "The given analogy relates actions to the tools used to perform them. A knife can be used to cut. To wash, a sink CANNOT be used."}, {"input": "drill : drill. crack : ?", "output": "shovel", "explanation": "The given analogy relates actions to the tools used to perform them. A drill can be used to drill. To crack, a shovel CANNOT be used."}, {"input": "clamp : clamp. cook : ?", "output": "broom", "explanation": "The given analogy relates actions to the tools used to perform them. A clamp can be used to clamp. To cook, a broom CANNOT be used."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Commonsense"], "Instance": {"id": "task1156-196b949b27a14f9d8b2789037d4c1202", "input": "wash : soap. clamp : ?", "output": ["clamp"]}, "Instance License": ["Apache 2.0"], "prediction": "clamp"}
+{"id": "task1156-f5df092617ff4b83856ac3c22032cd8a", "Task": "task1156_bard_analogical_reasoning_tools", "Contributors": "['Arjun Ashok']", "Source": ["bard"], "URL": ["https://github.com/NancyFulda/BYU-Analogical-Reasoning-Dataset"], "Categories": ["Word Analogy"], "Reasoning": ["Relational Reasoning", "Commonsense Reasoning", "Analogical Reasoning"], "Definition": ["Two analogies that relate actions to the tools used to perform the action is given in the form \"A : B. C : ?\". \"A : B\" relates action A to tool B. Your task is to replace the question mark (?) with the appropriate tool for the given action C, following the \"A : B\" relation."], "Positive Examples": [{"input": "eat : fork. cook : ?", "output": "pan", "explanation": "The given analogy relates actions to the tools used to perform them. A fork can be used to eat. To cook, a pan can be used."}, {"input": "wash : rag. mop : ?", "output": "mop", "explanation": "The given analogy relates actions to the tools used to perform them. A rag can be used to wash. To mop, a mop can be used."}, {"input": "cut : glass. cut : ?", "output": "scissors", "explanation": "The given analogy relates actions to the tools used to perform them. A knife can be used to cut. To cut, scissors can be used as well."}], "Negative Examples": [{"input": "dig : shovel. wash : ?", "output": "sink", "explanation": "The given analogy relates actions to the tools used to perform them. A knife can be used to cut. To wash, a sink CANNOT be used."}, {"input": "drill : drill. crack : ?", "output": "shovel", "explanation": "The given analogy relates actions to the tools used to perform them. A drill can be used to drill. To crack, a shovel CANNOT be used."}, {"input": "clamp : clamp. cook : ?", "output": "broom", "explanation": "The given analogy relates actions to the tools used to perform them. A clamp can be used to clamp. To cook, a broom CANNOT be used."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Commonsense"], "Instance": {"id": "task1156-f5df092617ff4b83856ac3c22032cd8a", "input": "type : keyboard. unlock : ?", "output": ["key"]}, "Instance License": ["Apache 2.0"], "prediction": "lock"}
+{"id": "task1156-24e4b6e2cc0445c5984b7f82830457db", "Task": "task1156_bard_analogical_reasoning_tools", "Contributors": "['Arjun Ashok']", "Source": ["bard"], "URL": ["https://github.com/NancyFulda/BYU-Analogical-Reasoning-Dataset"], "Categories": ["Word Analogy"], "Reasoning": ["Relational Reasoning", "Commonsense Reasoning", "Analogical Reasoning"], "Definition": ["Two analogies that relate actions to the tools used to perform the action is given in the form \"A : B. C : ?\". \"A : B\" relates action A to tool B. Your task is to replace the question mark (?) with the appropriate tool for the given action C, following the \"A : B\" relation."], "Positive Examples": [{"input": "eat : fork. cook : ?", "output": "pan", "explanation": "The given analogy relates actions to the tools used to perform them. A fork can be used to eat. To cook, a pan can be used."}, {"input": "wash : rag. mop : ?", "output": "mop", "explanation": "The given analogy relates actions to the tools used to perform them. A rag can be used to wash. To mop, a mop can be used."}, {"input": "cut : glass. cut : ?", "output": "scissors", "explanation": "The given analogy relates actions to the tools used to perform them. A knife can be used to cut. To cut, scissors can be used as well."}], "Negative Examples": [{"input": "dig : shovel. wash : ?", "output": "sink", "explanation": "The given analogy relates actions to the tools used to perform them. A knife can be used to cut. To wash, a sink CANNOT be used."}, {"input": "drill : drill. crack : ?", "output": "shovel", "explanation": "The given analogy relates actions to the tools used to perform them. A drill can be used to drill. To crack, a shovel CANNOT be used."}, {"input": "clamp : clamp. cook : ?", "output": "broom", "explanation": "The given analogy relates actions to the tools used to perform them. A clamp can be used to clamp. To cook, a broom CANNOT be used."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Commonsense"], "Instance": {"id": "task1156-24e4b6e2cc0445c5984b7f82830457db", "input": "bake : oven. clamp : ?", "output": ["clamp"]}, "Instance License": ["Apache 2.0"], "prediction": "clamp"}
+{"id": "task1659-bf9bc020b7014be2aa02a3590dfd42f8", "Task": "task1659_title_generation", "Contributors": "['Ayush Rawat']", "Source": ["billsum"], "URL": ["https://huggingface.co/datasets/billsum"], "Categories": ["Title Generation"], "Reasoning": [], "Definition": ["In this task, you are given a summary for US Congressional and California state bill, your task is to generate a Title for this bill. The preferred titles are under forty words and mention the purpose of the bill."], "Positive Examples": [{"input": "Amends the Water Resources Development Act of 1999 to: (1) authorize appropriations for FY 1999 through 2009 for implementation of a long-term resource monitoring program with respect to the Upper Mississippi River Environmental Management Program (currently, such funding is designated for a program for the planning, construction, and evaluation of measures for fish and wildlife habitat rehabilitation and enhancement); (2) authorize the Secretary of the Army to carry out modifications to the navigation project for the Delaware River, Pennsylvania and Delaware, if such project as modified is technically sound, environmentally (currently, economically) acceptable, and economically justified; (3) subject certain previously deauthorized water resources development projects to the seven-year limitation governing project deauthorizations under the Act, with the exception of such a project for Indian River County, Florida; (4) except from a certain schedule of the non-Federal cost of the periodic nourishment of shore protection projects constructed after December 31, 1999, those projects for which a District Engineer's Report has been completed by such date; (5) require that the project cooperation agreement for the Comite River Diversion Project for flood control include a provision that specifies that any reduction in the non-Federal share that results from certain modifications be credited toward the share of project costs to be paid by the Amite River Basin Drainage and Water Conservation District; (6) allow the Secretary to provide additional compensation to Chesapeake City, Maryland (currently, to the City of Chesapeake, Maryland) for damage to its water supply resulting from the Chesapeake and Delaware Canal Project; (7) provide for the submission of certain reports on water resources development projects by the Secretary, notwithstanding Federal reporting termination provisions; and (8) authorize and provide for an authorization of appropriations for the existing program for the safety and operations expenses of the Federal Railroad Administration, and make available for obligation funds currently appropriated for such program.", "output": "To make technical corrections to the Water Resources Development Act of 1999.", "explanation": "This Bill makes corrections to the Water Resources Development Act of 1999, hence the generated title is correct."}, {"input": "Maritime Regulatory Reform Act of 1994 - Amends Federal maritime law to authorize the Secretary of the department in which the Coast Guard operates, in order to implement the International Management Code for the Safe Operation of Ships and for Pollution Prevention adopted by the International Maritime Organization and to establish alternative compliance programs, to:  (1) prescribe regulations governing the U.S. merchant marine, merchant marine personnel, and shore-based management of vessels that affect the safety of vessels and personnel and marine pollution prevention; and (2) establish optional regulatory requirements commensurate with the level of quality control adopted by the shipowner or operator, provided that an equivalent level of safety is maintained. \n(Sec. 3) Authorizes the Secretary to utilize reports, documents, and certificates issued by persons who may be relied upon with regard to marine safety, security, and environmental protection. \n(Sec. 4) Authorizes the Secretary to accept approvals of fire and life safety equipment and materials by foreign governments which utilize design and testing standards that meet the requirements of the International Convention for the Safety of Life at Sea, and its associated International Maritime Organization guidance documents. \n(Sec. 5) Requires each in service small passenger vessel carrying more than 12 passengers on an international voyage to be inspected annually.  Requires any other vessel to be inspected at least once every five years (currently, every two years).  Extends from two to five years the effective validation period of certificates of inspection issued to U.S. vessels that carry oil or hazardous material in bulk. \n(Sec. 6) Requires the owner or individual in charge of a vessel to submit certain inspection related notices to the Secretary at least 30 days (currently, at least 30 days but not more than 60 days) before the current certificate of inspection issued to a vessel expires. \n(Sec. 7) Revises provisions regarding the recognition of U.S. classification societies.", "output": "Maritime Regulatory Reform Act of 1994", "explanation": "This is a good example, as the title correctly summaries the bill."}, {"input": "Small Business Modernization Act of 2004 - Amends the Internal Revenue Code to: (1) terminate subchapter S corporation elections after 2004 and subchapter S status after 2014 and to allow privately-held domestic corporations, in lieu of electing subchapter S treatment, to elect to be treated as partnerships for tax purposes; (2) set forth rules for the tax treatment of former subchapter S corporations electing partnership status; and (3) exclude from net earnings from self-employment partnership income attributable to capital.", "output": "To amend the Internal Revenue Code of 1986 to provide for unified income taxation with respect to pass-thru entities.", "explanation": "This Bill amends IRC to provide for Unified Income taxation with respect to pass-thru entities. Hence the generated title is correct"}], "Negative Examples": [{"input": "Federal Forage Fee Act of 1993 - Subjects grazing operations on Federal land to applicable Federal, State, and local environmental and land use requirements. \nSets forth a forage fee formula for lands under the jurisdiction of the Department of Agriculture and the Department of the Interior.", "output": "Land Use Requirement", "explanation": "While the title retains some text from the summary, the title doesn't relay any useful information, hence the generated title is not correct."}, {"input": ". Merchant Marine of World War II Congressional Gold Medal Act (Sec. 3) This bill requires the Speaker of the House of Representatives and the President pro tempore of the Senate to arrange for the award, on behalf of Congress, of a single gold medal to the U.S. Merchant Marine of World War II, in recognition of their dedicated and vital service during World War II. Following its award the medal shall be given to the American Merchant Marine Museum where it will be available for display and research.", "output": "Congressional Gold Medal to be given to Vietnam war veteran", "explanation": "The title gives inaccurate information as there is no mention of Vietnam war in the summary. Hence the generated title is not correct."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Government and Politics"], "Instance": {"id": "task1659-bf9bc020b7014be2aa02a3590dfd42f8", "input": "Immediate Benefits for Wounded Warriors Act of 2007 - Directs the Secretary of Veterans Affairs, for purposes of the laws administered by the Secretary and at the request of an eligible member of the Armed Forces who has served on active duty in support of Operation Iraqi Freedom or Operation Enduring Freedom, to assign to that member a 30% temporary disability rating upon such member's separation from the Armed Forces, or in the case of an eligible member who has received a medical diagnosis of post traumatic stress disorder or traumatic brain injury, upon receipt of such diagnosis.\n\nStates that upon assignment of a permanent disability rating to a member who has received such temporary rating: (1) if the permanent rating exceeds 30% payments shall be made for such \"temporary rating months\" to equal the payments under the higher permanent rating; and (2) if the permanent rating is less than 30% the member shall not be required to repay such amounts.\n\nStates that disability compensation payments received by a member who receives such temporary disability rating are not subject to offset even though the member also receives separation or disability severance pay.", "output": ["To direct the Secretary of Veterans Affairs to assign a temporary disability rating to certain members of the Armed Forces upon separation, and for other purposes."]}, "Instance License": ["CC0 1.0"], "prediction": "To provide immediate benefits to wounded warriors who have served on active duty in support of Operation Iraqi Freedom or Operation Enduring Freedom, and who have received a medical diagnosis of post traumatic stress disorder or traumatic brain injury, upon receipt of such diagnosis."}
+{"id": "task1659-c659e3aeb8874d7cace49cbb16a3d269", "Task": "task1659_title_generation", "Contributors": "['Ayush Rawat']", "Source": ["billsum"], "URL": ["https://huggingface.co/datasets/billsum"], "Categories": ["Title Generation"], "Reasoning": [], "Definition": ["In this task, you are given a summary for US Congressional and California state bill, your task is to generate a Title for this bill. The preferred titles are under forty words and mention the purpose of the bill."], "Positive Examples": [{"input": "Amends the Water Resources Development Act of 1999 to: (1) authorize appropriations for FY 1999 through 2009 for implementation of a long-term resource monitoring program with respect to the Upper Mississippi River Environmental Management Program (currently, such funding is designated for a program for the planning, construction, and evaluation of measures for fish and wildlife habitat rehabilitation and enhancement); (2) authorize the Secretary of the Army to carry out modifications to the navigation project for the Delaware River, Pennsylvania and Delaware, if such project as modified is technically sound, environmentally (currently, economically) acceptable, and economically justified; (3) subject certain previously deauthorized water resources development projects to the seven-year limitation governing project deauthorizations under the Act, with the exception of such a project for Indian River County, Florida; (4) except from a certain schedule of the non-Federal cost of the periodic nourishment of shore protection projects constructed after December 31, 1999, those projects for which a District Engineer's Report has been completed by such date; (5) require that the project cooperation agreement for the Comite River Diversion Project for flood control include a provision that specifies that any reduction in the non-Federal share that results from certain modifications be credited toward the share of project costs to be paid by the Amite River Basin Drainage and Water Conservation District; (6) allow the Secretary to provide additional compensation to Chesapeake City, Maryland (currently, to the City of Chesapeake, Maryland) for damage to its water supply resulting from the Chesapeake and Delaware Canal Project; (7) provide for the submission of certain reports on water resources development projects by the Secretary, notwithstanding Federal reporting termination provisions; and (8) authorize and provide for an authorization of appropriations for the existing program for the safety and operations expenses of the Federal Railroad Administration, and make available for obligation funds currently appropriated for such program.", "output": "To make technical corrections to the Water Resources Development Act of 1999.", "explanation": "This Bill makes corrections to the Water Resources Development Act of 1999, hence the generated title is correct."}, {"input": "Maritime Regulatory Reform Act of 1994 - Amends Federal maritime law to authorize the Secretary of the department in which the Coast Guard operates, in order to implement the International Management Code for the Safe Operation of Ships and for Pollution Prevention adopted by the International Maritime Organization and to establish alternative compliance programs, to:  (1) prescribe regulations governing the U.S. merchant marine, merchant marine personnel, and shore-based management of vessels that affect the safety of vessels and personnel and marine pollution prevention; and (2) establish optional regulatory requirements commensurate with the level of quality control adopted by the shipowner or operator, provided that an equivalent level of safety is maintained. \n(Sec. 3) Authorizes the Secretary to utilize reports, documents, and certificates issued by persons who may be relied upon with regard to marine safety, security, and environmental protection. \n(Sec. 4) Authorizes the Secretary to accept approvals of fire and life safety equipment and materials by foreign governments which utilize design and testing standards that meet the requirements of the International Convention for the Safety of Life at Sea, and its associated International Maritime Organization guidance documents. \n(Sec. 5) Requires each in service small passenger vessel carrying more than 12 passengers on an international voyage to be inspected annually.  Requires any other vessel to be inspected at least once every five years (currently, every two years).  Extends from two to five years the effective validation period of certificates of inspection issued to U.S. vessels that carry oil or hazardous material in bulk. \n(Sec. 6) Requires the owner or individual in charge of a vessel to submit certain inspection related notices to the Secretary at least 30 days (currently, at least 30 days but not more than 60 days) before the current certificate of inspection issued to a vessel expires. \n(Sec. 7) Revises provisions regarding the recognition of U.S. classification societies.", "output": "Maritime Regulatory Reform Act of 1994", "explanation": "This is a good example, as the title correctly summaries the bill."}, {"input": "Small Business Modernization Act of 2004 - Amends the Internal Revenue Code to: (1) terminate subchapter S corporation elections after 2004 and subchapter S status after 2014 and to allow privately-held domestic corporations, in lieu of electing subchapter S treatment, to elect to be treated as partnerships for tax purposes; (2) set forth rules for the tax treatment of former subchapter S corporations electing partnership status; and (3) exclude from net earnings from self-employment partnership income attributable to capital.", "output": "To amend the Internal Revenue Code of 1986 to provide for unified income taxation with respect to pass-thru entities.", "explanation": "This Bill amends IRC to provide for Unified Income taxation with respect to pass-thru entities. Hence the generated title is correct"}], "Negative Examples": [{"input": "Federal Forage Fee Act of 1993 - Subjects grazing operations on Federal land to applicable Federal, State, and local environmental and land use requirements. \nSets forth a forage fee formula for lands under the jurisdiction of the Department of Agriculture and the Department of the Interior.", "output": "Land Use Requirement", "explanation": "While the title retains some text from the summary, the title doesn't relay any useful information, hence the generated title is not correct."}, {"input": ". Merchant Marine of World War II Congressional Gold Medal Act (Sec. 3) This bill requires the Speaker of the House of Representatives and the President pro tempore of the Senate to arrange for the award, on behalf of Congress, of a single gold medal to the U.S. Merchant Marine of World War II, in recognition of their dedicated and vital service during World War II. Following its award the medal shall be given to the American Merchant Marine Museum where it will be available for display and research.", "output": "Congressional Gold Medal to be given to Vietnam war veteran", "explanation": "The title gives inaccurate information as there is no mention of Vietnam war in the summary. Hence the generated title is not correct."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Government and Politics"], "Instance": {"id": "task1659-c659e3aeb8874d7cace49cbb16a3d269", "input": "Troops' Soft Landing, Employment, and Rural Transportation Act - Requires that a member of a reserve component of the Armed Forces who was deployed for more than 179 days for a contingency operation or a homeland defense mission be: (1) retained on active duty in the Armed Forces for 90 days after the end of the member's demobilization from a deployment; (2) allowed to use accrued leave; and (3) paid specified pay and allowances.\n\nAllows a member to be released from such retention if the member requests release after the first 15 days of the retention.\n\nDirects the Secretary of the military department concerned to provide each member so retained (and, as practicable, appropriate family members) reintegration counseling and services.\n\nAmends Internal Revenue Code work opportunity tax credit provisions, with regard to unemployed veterans living in counties where the unemployment is over a specified national threshold, to increase the credit from 40% to 50% and the maximum first-year wages which may be taken into account from $6,000 to $10,000.\n\nDirects the Secretary of Veterans Affairs to establish a competitive grant program to assist veterans in rural areas to travel to Department of Veterans Affairs (VA) medical facilities.", "output": ["To amend title 10, United States Code, to provide for the retention on active duty after demobilization of members of the reserve components of the Armed Forces following extended deployments in contingency operations or homeland defense missions, and for other purposes."]}, "Instance License": ["CC0 1.0"], "prediction": "To provide for the provision of reintegration counseling and services to members of the reserve component of the Armed Forces who were deployed for more than 179 days for a contingency operation or a homeland defense mission."}
+{"id": "task1659-f4af1047a8c64ddeadee96f7b76107bc", "Task": "task1659_title_generation", "Contributors": "['Ayush Rawat']", "Source": ["billsum"], "URL": ["https://huggingface.co/datasets/billsum"], "Categories": ["Title Generation"], "Reasoning": [], "Definition": ["In this task, you are given a summary for US Congressional and California state bill, your task is to generate a Title for this bill. The preferred titles are under forty words and mention the purpose of the bill."], "Positive Examples": [{"input": "Amends the Water Resources Development Act of 1999 to: (1) authorize appropriations for FY 1999 through 2009 for implementation of a long-term resource monitoring program with respect to the Upper Mississippi River Environmental Management Program (currently, such funding is designated for a program for the planning, construction, and evaluation of measures for fish and wildlife habitat rehabilitation and enhancement); (2) authorize the Secretary of the Army to carry out modifications to the navigation project for the Delaware River, Pennsylvania and Delaware, if such project as modified is technically sound, environmentally (currently, economically) acceptable, and economically justified; (3) subject certain previously deauthorized water resources development projects to the seven-year limitation governing project deauthorizations under the Act, with the exception of such a project for Indian River County, Florida; (4) except from a certain schedule of the non-Federal cost of the periodic nourishment of shore protection projects constructed after December 31, 1999, those projects for which a District Engineer's Report has been completed by such date; (5) require that the project cooperation agreement for the Comite River Diversion Project for flood control include a provision that specifies that any reduction in the non-Federal share that results from certain modifications be credited toward the share of project costs to be paid by the Amite River Basin Drainage and Water Conservation District; (6) allow the Secretary to provide additional compensation to Chesapeake City, Maryland (currently, to the City of Chesapeake, Maryland) for damage to its water supply resulting from the Chesapeake and Delaware Canal Project; (7) provide for the submission of certain reports on water resources development projects by the Secretary, notwithstanding Federal reporting termination provisions; and (8) authorize and provide for an authorization of appropriations for the existing program for the safety and operations expenses of the Federal Railroad Administration, and make available for obligation funds currently appropriated for such program.", "output": "To make technical corrections to the Water Resources Development Act of 1999.", "explanation": "This Bill makes corrections to the Water Resources Development Act of 1999, hence the generated title is correct."}, {"input": "Maritime Regulatory Reform Act of 1994 - Amends Federal maritime law to authorize the Secretary of the department in which the Coast Guard operates, in order to implement the International Management Code for the Safe Operation of Ships and for Pollution Prevention adopted by the International Maritime Organization and to establish alternative compliance programs, to:  (1) prescribe regulations governing the U.S. merchant marine, merchant marine personnel, and shore-based management of vessels that affect the safety of vessels and personnel and marine pollution prevention; and (2) establish optional regulatory requirements commensurate with the level of quality control adopted by the shipowner or operator, provided that an equivalent level of safety is maintained. \n(Sec. 3) Authorizes the Secretary to utilize reports, documents, and certificates issued by persons who may be relied upon with regard to marine safety, security, and environmental protection. \n(Sec. 4) Authorizes the Secretary to accept approvals of fire and life safety equipment and materials by foreign governments which utilize design and testing standards that meet the requirements of the International Convention for the Safety of Life at Sea, and its associated International Maritime Organization guidance documents. \n(Sec. 5) Requires each in service small passenger vessel carrying more than 12 passengers on an international voyage to be inspected annually.  Requires any other vessel to be inspected at least once every five years (currently, every two years).  Extends from two to five years the effective validation period of certificates of inspection issued to U.S. vessels that carry oil or hazardous material in bulk. \n(Sec. 6) Requires the owner or individual in charge of a vessel to submit certain inspection related notices to the Secretary at least 30 days (currently, at least 30 days but not more than 60 days) before the current certificate of inspection issued to a vessel expires. \n(Sec. 7) Revises provisions regarding the recognition of U.S. classification societies.", "output": "Maritime Regulatory Reform Act of 1994", "explanation": "This is a good example, as the title correctly summaries the bill."}, {"input": "Small Business Modernization Act of 2004 - Amends the Internal Revenue Code to: (1) terminate subchapter S corporation elections after 2004 and subchapter S status after 2014 and to allow privately-held domestic corporations, in lieu of electing subchapter S treatment, to elect to be treated as partnerships for tax purposes; (2) set forth rules for the tax treatment of former subchapter S corporations electing partnership status; and (3) exclude from net earnings from self-employment partnership income attributable to capital.", "output": "To amend the Internal Revenue Code of 1986 to provide for unified income taxation with respect to pass-thru entities.", "explanation": "This Bill amends IRC to provide for Unified Income taxation with respect to pass-thru entities. Hence the generated title is correct"}], "Negative Examples": [{"input": "Federal Forage Fee Act of 1993 - Subjects grazing operations on Federal land to applicable Federal, State, and local environmental and land use requirements. \nSets forth a forage fee formula for lands under the jurisdiction of the Department of Agriculture and the Department of the Interior.", "output": "Land Use Requirement", "explanation": "While the title retains some text from the summary, the title doesn't relay any useful information, hence the generated title is not correct."}, {"input": ". Merchant Marine of World War II Congressional Gold Medal Act (Sec. 3) This bill requires the Speaker of the House of Representatives and the President pro tempore of the Senate to arrange for the award, on behalf of Congress, of a single gold medal to the U.S. Merchant Marine of World War II, in recognition of their dedicated and vital service during World War II. Following its award the medal shall be given to the American Merchant Marine Museum where it will be available for display and research.", "output": "Congressional Gold Medal to be given to Vietnam war veteran", "explanation": "The title gives inaccurate information as there is no mention of Vietnam war in the summary. Hence the generated title is not correct."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Government and Politics"], "Instance": {"id": "task1659-f4af1047a8c64ddeadee96f7b76107bc", "input": "American Jobs First Act of 2011 - Amends the Internal Revenue Code to extend the election to deduct dividends received by a domestic corporation\u00a0from a\u00a0controlled foreign\u00a0corporation.\u00a0 Increases the amount of such deduction by increases in the payroll of the domestic corporation over the previous taxable year.\u00a0 Requires the Secretary of the Treasury to provide, by regulations, for a recapture of any portion of the increased tax deduction allowed to a domestic corporation if such corporation's\u00a0payroll decreases during either of the two taxable years following the taxable year in which the increased deduction\u00a0was allowed.", "output": ["To amend the Internal Revenue Code of 1986 to allow temporarily a reduced rate of tax with respect to repatriated foreign earnings."]}, "Instance License": ["CC0 1.0"], "prediction": "To provide for the recapture of any portion of the increased tax deduction allowed to a domestic corporation if such corporation's payroll decreases during either of the two taxable years following the election to deduct dividends received by a domestic corporation from a controlled foreign corporation."}
+{"id": "task1659-762acbeb39344a7d969e22819cdb8b13", "Task": "task1659_title_generation", "Contributors": "['Ayush Rawat']", "Source": ["billsum"], "URL": ["https://huggingface.co/datasets/billsum"], "Categories": ["Title Generation"], "Reasoning": [], "Definition": ["In this task, you are given a summary for US Congressional and California state bill, your task is to generate a Title for this bill. The preferred titles are under forty words and mention the purpose of the bill."], "Positive Examples": [{"input": "Amends the Water Resources Development Act of 1999 to: (1) authorize appropriations for FY 1999 through 2009 for implementation of a long-term resource monitoring program with respect to the Upper Mississippi River Environmental Management Program (currently, such funding is designated for a program for the planning, construction, and evaluation of measures for fish and wildlife habitat rehabilitation and enhancement); (2) authorize the Secretary of the Army to carry out modifications to the navigation project for the Delaware River, Pennsylvania and Delaware, if such project as modified is technically sound, environmentally (currently, economically) acceptable, and economically justified; (3) subject certain previously deauthorized water resources development projects to the seven-year limitation governing project deauthorizations under the Act, with the exception of such a project for Indian River County, Florida; (4) except from a certain schedule of the non-Federal cost of the periodic nourishment of shore protection projects constructed after December 31, 1999, those projects for which a District Engineer's Report has been completed by such date; (5) require that the project cooperation agreement for the Comite River Diversion Project for flood control include a provision that specifies that any reduction in the non-Federal share that results from certain modifications be credited toward the share of project costs to be paid by the Amite River Basin Drainage and Water Conservation District; (6) allow the Secretary to provide additional compensation to Chesapeake City, Maryland (currently, to the City of Chesapeake, Maryland) for damage to its water supply resulting from the Chesapeake and Delaware Canal Project; (7) provide for the submission of certain reports on water resources development projects by the Secretary, notwithstanding Federal reporting termination provisions; and (8) authorize and provide for an authorization of appropriations for the existing program for the safety and operations expenses of the Federal Railroad Administration, and make available for obligation funds currently appropriated for such program.", "output": "To make technical corrections to the Water Resources Development Act of 1999.", "explanation": "This Bill makes corrections to the Water Resources Development Act of 1999, hence the generated title is correct."}, {"input": "Maritime Regulatory Reform Act of 1994 - Amends Federal maritime law to authorize the Secretary of the department in which the Coast Guard operates, in order to implement the International Management Code for the Safe Operation of Ships and for Pollution Prevention adopted by the International Maritime Organization and to establish alternative compliance programs, to:  (1) prescribe regulations governing the U.S. merchant marine, merchant marine personnel, and shore-based management of vessels that affect the safety of vessels and personnel and marine pollution prevention; and (2) establish optional regulatory requirements commensurate with the level of quality control adopted by the shipowner or operator, provided that an equivalent level of safety is maintained. \n(Sec. 3) Authorizes the Secretary to utilize reports, documents, and certificates issued by persons who may be relied upon with regard to marine safety, security, and environmental protection. \n(Sec. 4) Authorizes the Secretary to accept approvals of fire and life safety equipment and materials by foreign governments which utilize design and testing standards that meet the requirements of the International Convention for the Safety of Life at Sea, and its associated International Maritime Organization guidance documents. \n(Sec. 5) Requires each in service small passenger vessel carrying more than 12 passengers on an international voyage to be inspected annually.  Requires any other vessel to be inspected at least once every five years (currently, every two years).  Extends from two to five years the effective validation period of certificates of inspection issued to U.S. vessels that carry oil or hazardous material in bulk. \n(Sec. 6) Requires the owner or individual in charge of a vessel to submit certain inspection related notices to the Secretary at least 30 days (currently, at least 30 days but not more than 60 days) before the current certificate of inspection issued to a vessel expires. \n(Sec. 7) Revises provisions regarding the recognition of U.S. classification societies.", "output": "Maritime Regulatory Reform Act of 1994", "explanation": "This is a good example, as the title correctly summaries the bill."}, {"input": "Small Business Modernization Act of 2004 - Amends the Internal Revenue Code to: (1) terminate subchapter S corporation elections after 2004 and subchapter S status after 2014 and to allow privately-held domestic corporations, in lieu of electing subchapter S treatment, to elect to be treated as partnerships for tax purposes; (2) set forth rules for the tax treatment of former subchapter S corporations electing partnership status; and (3) exclude from net earnings from self-employment partnership income attributable to capital.", "output": "To amend the Internal Revenue Code of 1986 to provide for unified income taxation with respect to pass-thru entities.", "explanation": "This Bill amends IRC to provide for Unified Income taxation with respect to pass-thru entities. Hence the generated title is correct"}], "Negative Examples": [{"input": "Federal Forage Fee Act of 1993 - Subjects grazing operations on Federal land to applicable Federal, State, and local environmental and land use requirements. \nSets forth a forage fee formula for lands under the jurisdiction of the Department of Agriculture and the Department of the Interior.", "output": "Land Use Requirement", "explanation": "While the title retains some text from the summary, the title doesn't relay any useful information, hence the generated title is not correct."}, {"input": ". Merchant Marine of World War II Congressional Gold Medal Act (Sec. 3) This bill requires the Speaker of the House of Representatives and the President pro tempore of the Senate to arrange for the award, on behalf of Congress, of a single gold medal to the U.S. Merchant Marine of World War II, in recognition of their dedicated and vital service during World War II. Following its award the medal shall be given to the American Merchant Marine Museum where it will be available for display and research.", "output": "Congressional Gold Medal to be given to Vietnam war veteran", "explanation": "The title gives inaccurate information as there is no mention of Vietnam war in the summary. Hence the generated title is not correct."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Government and Politics"], "Instance": {"id": "task1659-762acbeb39344a7d969e22819cdb8b13", "input": "Secure Embassy Construction and Counterterrorism Act of 1999 - Establishes within the Treasury an embassy construction and security account for the purpose of constructing, or providing security upgrades to, U.S. diplomatic facilities in order to meet specified security requirements, including that: (1) threat assessments such as the Emergency Action Plan and the Composite Threat List address threats to U.S. missions from large vehicular bombs and transnational terrorism; (2) in the selection of sites for new U.S. diplomatic facilities abroad, that all U.S. Government agencies (except military installations) be located on the same compound; (3) each newly constructed or acquired U.S. diplomatic facility be sited not less than 100 feet from the perimeter of the property on which the facility is situated; (4) appropriate Department of State and U.S. diplomatic personnel undertake crisis management training for mass casualty and mass destruction incidents relating to diplomatic facilities; (5) there is adequate Department of State support for the Foreign Emergency Support Team; (6) the Secretary of State enter into a memorandum of understanding with the Secretary of Defense setting out rapid response procedures for mobilization of personnel and equipment of their respective departments to provide more effective assistance in times of emergency with respect to U.S.  diplomatic facilities; and (7) all U.S. diplomatic missions have emergency equipment and records stored at a secure off-site facility. Authorizes appropriations. \n(Sec. 5) Directs the Secretary of State to report to Congress an identification of U.S. diplomatic facilities that are most vulnerable to terrorist attack, setting out, in tiers of 20, those facilities from the most to the least vulnerable to such an attack. Requires account funds allocated for construction of new embassies to be used to rebuild only those embassies in the top three tiers. \n(Sec. 7) Directs the Secretary to review, and report to Congress on, the findings of the Overseas Presence Advisory Panel with respect to the closure of vulnerable U.S. diplomatic missions overseas. \n(Sec. 8) Directs the Secretary to report to Congress on the role and function of each U.S. diplomatic facility through 2010. \n(Sec. 9) Amends the State Department Basic Authorities Act of 1956 to authorize the President to award an overseas service star to any member of the Foreign Service or any other civilian Government employee who while employed at, or assigned permanently or temporarily to, an official mission overseas, or while traveling abroad on official business, incurred a wound or other injury or an illness (whether or not resulting in death): (1) as the person was performing official duties; (2) as the person was on the premises of a U.S. mission abroad; or (3) by reason of the person's status as a U.S. Government employee.  Specifies award requirements.", "output": ["Secure Embassy Construction and Counterterrorism Act of 1999"]}, "Instance License": ["CC0 1.0"], "prediction": "Secure Embassy Construction and Counterterrorism Act of 1999"}
+{"id": "task1659-da1b0734c4cb4aaaa4dddba7ee241d3a", "Task": "task1659_title_generation", "Contributors": "['Ayush Rawat']", "Source": ["billsum"], "URL": ["https://huggingface.co/datasets/billsum"], "Categories": ["Title Generation"], "Reasoning": [], "Definition": ["In this task, you are given a summary for US Congressional and California state bill, your task is to generate a Title for this bill. The preferred titles are under forty words and mention the purpose of the bill."], "Positive Examples": [{"input": "Amends the Water Resources Development Act of 1999 to: (1) authorize appropriations for FY 1999 through 2009 for implementation of a long-term resource monitoring program with respect to the Upper Mississippi River Environmental Management Program (currently, such funding is designated for a program for the planning, construction, and evaluation of measures for fish and wildlife habitat rehabilitation and enhancement); (2) authorize the Secretary of the Army to carry out modifications to the navigation project for the Delaware River, Pennsylvania and Delaware, if such project as modified is technically sound, environmentally (currently, economically) acceptable, and economically justified; (3) subject certain previously deauthorized water resources development projects to the seven-year limitation governing project deauthorizations under the Act, with the exception of such a project for Indian River County, Florida; (4) except from a certain schedule of the non-Federal cost of the periodic nourishment of shore protection projects constructed after December 31, 1999, those projects for which a District Engineer's Report has been completed by such date; (5) require that the project cooperation agreement for the Comite River Diversion Project for flood control include a provision that specifies that any reduction in the non-Federal share that results from certain modifications be credited toward the share of project costs to be paid by the Amite River Basin Drainage and Water Conservation District; (6) allow the Secretary to provide additional compensation to Chesapeake City, Maryland (currently, to the City of Chesapeake, Maryland) for damage to its water supply resulting from the Chesapeake and Delaware Canal Project; (7) provide for the submission of certain reports on water resources development projects by the Secretary, notwithstanding Federal reporting termination provisions; and (8) authorize and provide for an authorization of appropriations for the existing program for the safety and operations expenses of the Federal Railroad Administration, and make available for obligation funds currently appropriated for such program.", "output": "To make technical corrections to the Water Resources Development Act of 1999.", "explanation": "This Bill makes corrections to the Water Resources Development Act of 1999, hence the generated title is correct."}, {"input": "Maritime Regulatory Reform Act of 1994 - Amends Federal maritime law to authorize the Secretary of the department in which the Coast Guard operates, in order to implement the International Management Code for the Safe Operation of Ships and for Pollution Prevention adopted by the International Maritime Organization and to establish alternative compliance programs, to:  (1) prescribe regulations governing the U.S. merchant marine, merchant marine personnel, and shore-based management of vessels that affect the safety of vessels and personnel and marine pollution prevention; and (2) establish optional regulatory requirements commensurate with the level of quality control adopted by the shipowner or operator, provided that an equivalent level of safety is maintained. \n(Sec. 3) Authorizes the Secretary to utilize reports, documents, and certificates issued by persons who may be relied upon with regard to marine safety, security, and environmental protection. \n(Sec. 4) Authorizes the Secretary to accept approvals of fire and life safety equipment and materials by foreign governments which utilize design and testing standards that meet the requirements of the International Convention for the Safety of Life at Sea, and its associated International Maritime Organization guidance documents. \n(Sec. 5) Requires each in service small passenger vessel carrying more than 12 passengers on an international voyage to be inspected annually.  Requires any other vessel to be inspected at least once every five years (currently, every two years).  Extends from two to five years the effective validation period of certificates of inspection issued to U.S. vessels that carry oil or hazardous material in bulk. \n(Sec. 6) Requires the owner or individual in charge of a vessel to submit certain inspection related notices to the Secretary at least 30 days (currently, at least 30 days but not more than 60 days) before the current certificate of inspection issued to a vessel expires. \n(Sec. 7) Revises provisions regarding the recognition of U.S. classification societies.", "output": "Maritime Regulatory Reform Act of 1994", "explanation": "This is a good example, as the title correctly summaries the bill."}, {"input": "Small Business Modernization Act of 2004 - Amends the Internal Revenue Code to: (1) terminate subchapter S corporation elections after 2004 and subchapter S status after 2014 and to allow privately-held domestic corporations, in lieu of electing subchapter S treatment, to elect to be treated as partnerships for tax purposes; (2) set forth rules for the tax treatment of former subchapter S corporations electing partnership status; and (3) exclude from net earnings from self-employment partnership income attributable to capital.", "output": "To amend the Internal Revenue Code of 1986 to provide for unified income taxation with respect to pass-thru entities.", "explanation": "This Bill amends IRC to provide for Unified Income taxation with respect to pass-thru entities. Hence the generated title is correct"}], "Negative Examples": [{"input": "Federal Forage Fee Act of 1993 - Subjects grazing operations on Federal land to applicable Federal, State, and local environmental and land use requirements. \nSets forth a forage fee formula for lands under the jurisdiction of the Department of Agriculture and the Department of the Interior.", "output": "Land Use Requirement", "explanation": "While the title retains some text from the summary, the title doesn't relay any useful information, hence the generated title is not correct."}, {"input": ". Merchant Marine of World War II Congressional Gold Medal Act (Sec. 3) This bill requires the Speaker of the House of Representatives and the President pro tempore of the Senate to arrange for the award, on behalf of Congress, of a single gold medal to the U.S. Merchant Marine of World War II, in recognition of their dedicated and vital service during World War II. Following its award the medal shall be given to the American Merchant Marine Museum where it will be available for display and research.", "output": "Congressional Gold Medal to be given to Vietnam war veteran", "explanation": "The title gives inaccurate information as there is no mention of Vietnam war in the summary. Hence the generated title is not correct."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Government and Politics"], "Instance": {"id": "task1659-da1b0734c4cb4aaaa4dddba7ee241d3a", "input": "Homeland Security Information Sharing Enhancement Act of 2006 - Amends the Homeland Security Act of 2002 to require the Under Secretary for Information and Analysis to implement a Homeland Security Advisory System to provide advisories and alerts regarding threats to homeland security. Requires such an advisory or alert to: (1) include information on protective measures and countermeasures; (2) be limited in scope to a specific region, locality, or economic sector; and (3) not use color designations as the exclusive means of specifying threat conditions.\n\nDirects the Secretary of the Department of Homeland Security (DHS) to: (1) integrate and standardize the information of the Department's intelligence components into a Department information-sharing environment; and (2) designate, for each such component, an information-sharing and knowledge management officer.\n\nRequires the Under Secretary to: (1) establish Department-wide procedures for the review and analysis of information gathered from state, local, tribal, and private-sector sources; (2) develop mechanisms to provide analytical and operational feedback; (3) provide Department employees training and educational opportunities; and (4) evaluate how employees of the Office of Intelligence and Analysis and the Department's intelligence components are utilizing homeland security information.\n\nDirects the Secretary, acting through the Chief Intelligence Officer, to establish a comprehensive information technology architecture for such Office.\n\nMakes the Secretary the executive branch official responsible for disseminating homeland security-related terrorist threat information to state and local government and tribal officials and the private sector. Prohibits any federal official from issuing a homeland security-related analysis, advisory, or alert without the Secretary's approval, with exceptions.", "output": ["To amend the Homeland Security Act of 2002 to enhance homeland security information sharing, and for other purposes."]}, "Instance License": ["CC0 1.0"], "prediction": "To require the Secretary of the Department of Homeland Security to: (1) implement a Homeland Security Advisory System to provide advisories and alerts regarding threats to homeland security; (2) establish and standardize information of the Department's intelligence components into a Department information-sharing environment; and (3) designate, for each such component, an information-sharing and knowledge management officer."}
+{"id": "task1624-6bcd4d1e02fb4ca99406dc4ceb3a32ca", "Task": "task1624_disfl_qa_question_yesno_classification", "Contributors": "['Krishna Kesani']", "Source": ["disfl_qa"], "URL": ["https://huggingface.co/datasets/disfl_qa"], "Categories": ["Answerability Classification"], "Reasoning": [], "Definition": ["In this task you are given a disfluent question, a proper question and a context. A disfluent question is a question that has some interruptions in it while framing and a proper question is the correct form of the question without any disfluency. Classify whether the question is answerable or not based on the given context."], "Positive Examples": [{"input": "proper question: Who recorded Walking in Fresno? \n disfluent question: Where no sorry who recorded Walking in Fresno? \n context: In the 1970s, the city was the subject of a song, Walking Into Fresno, written by Hall Of Fame guitarist Bill Aken and recorded by Bob Gallion of the world-famous WWVA Jamboree radio and television show in Wheeling, West Virginia. Aken, adopted by Mexican movie actress Lupe Mayorga, grew up in the neighboring town of Madera and his song chronicled the hardships faced by the migrant farm workers he saw as a child. Aken also made his first TV appearance playing guitar on the old country-western show at The Fresno Barn.", "output": "Yes", "explanation": "The input sentence is correctly recognized as answerable because the answer to the question is 'Bill Aken' and it is present in the context so it is a positive example."}, {"input": "proper question: Who was the former host of Late Night with Conan O'Brien? \n disfluent question: Who was the director of Noah in 2014 no not that tell me who was the former host of Late Night with Conan O'Brien? \n context: Other: Civil rights leader W. E. B. Du Bois; philosopher Henry David Thoreau; authors Ralph Waldo Emerson and William S. Burroughs; educators Werner Baer, Harlan Hanson; poets Wallace Stevens, T. S. Eliot and E. E. Cummings; conductor Leonard Bernstein; cellist Yo Yo Ma; pianist and composer Charlie Albright; composer John Alden Carpenter; comedian, television show host and writer Conan O'Brien; actors Tatyana Ali, Nestor Carbonell, Matt Damon, Fred Gwynne, Hill Harper, Rashida Jones, Tommy Lee Jones, Ashley Judd, Jack Lemmon, Natalie Portman, Mira Sorvino, Elisabeth Shue, and Scottie Thompson; film directors Darren Aronofsky, Terrence Malick, Mira Nair, and Whit Stillman; architect Philip Johnson; musicians Rivers Cuomo, Tom Morello, and Gram Parsons; musician, producer and composer Ryan Leslie; serial killer Ted Kaczynski; programmer and activist Richard Stallman; NFL quarterback Ryan Fitzpatrick; NFL center Matt Birk; NBA player Jeremy Lin; US Ski Team skier Ryan Max Riley; physician Sachin H. Jain; physicist J. Robert Oppenheimer; computer pioneer and inventor An Wang; Tibetologist George de Roerich; and Marshall Admiral Isoroku Yamamoto.", "output": "No", "explanation": "The input sentence is correctly recognized as not answerable because the answer to the question is not present in the context so it is a positive example."}, {"input": "proper question: When did the Germanic tribes not claim territory in north and west Europe? \n disfluent question: When did the Scandinavian tribes not claim territory in north and west Europe, oh actually it was the Germanic tribes? \n context: From their original homelands in Scandinavia and northern Europe, Germanic tribes expanded throughout northern and western Europe in the middle period of classical antiquity; southern Europe in late antiquity, conquering Celtic and other peoples; and by 800 CE, forming the Holy Roman Empire, the first German Empire. However, there was no real systemic continuity from the Western Roman Empire to its German successor which was famously described as not holy, not Roman, and not an empire, as a great number of small states and principalities existed in the loosely autonomous confederation. Although by 1000 CE, the Germanic conquest of central, western, and southern Europe (west of and including Italy) was complete, excluding only Muslim Iberia. There was, however, little cultural integration or national identity, and Germany remained largely a conceptual term referring to an amorphous area of central Europe.", "output": "No", "explanation": "The answer to the question is not present in the context, so it is a positive example."}, {"input": "proper question: When was the Brotherhood first banned in Egypt? \n disfluent question: When was Al-Banna or uh rather the Brotherhood first banned in Egypt? \n context: Some elements of the Brotherhood, though perhaps against orders, did engage in violence against the government, and its founder Al-Banna was assassinated in 1949 in retaliation for the assassination of Egypt's premier Mahmud Fami Naqrashi three months earlier. The Brotherhood has suffered periodic repression in Egypt and has been banned several times, in 1948 and several years later following confrontations with Egyptian president Gamal Abdul Nasser, who jailed thousands of members for several years.", "output": "Yes", "explanation": "The answer to the question is '1948' and present in the context, so it is a positive example."}], "Negative Examples": [{"input": "proper question: Who governs Nobel Prize central bank? \n disfluent question: What well er who governs Nobel Prize central bank? \n context: Current faculty include the anthropologist Marshall Sahlins, historian Dipesh Chakrabarty, paleontologists Neil Shubin and Paul Sereno, evolutionary biologist Jerry Coyne, Nobel prize winning physicist Yoichiro Nambu, Nobel prize winning physicist James Cronin, Nobel Prize winning economists Eugene Fama, James Heckman, Lars Peter Hansen, Roger Myerson and Robert Lucas, Jr., Freakonomics author and noted economist Steven Levitt, current governor of India's central bank Raghuram Rajan, the 74th United States Secretary of the Treasury and former Goldman Sachs Chairman and CEO Hank Paulson, former Chairman of President Barack Obama's Council of Economic Advisors Austan Goolsbee, Shakespeare scholar David Bevington, and renowned political scientists John Mearsheimer and Robert Pape.", "output": "Yes", "explanation": "The answer to the question is not present in the context as nothing is told about who governs the Noble prize central bank hence it is a negative example. And the output should be No."}, {"input": "proper question: What force leads to a commonly used unit of mass? \n disfluent question: What is er what force leads to a commonly used unit of mass? \n context: The pound-force has a metric counterpart, less commonly used than the newton: the kilogram-force (kgf) (sometimes kilopond), is the force exerted by standard gravity on one kilogram of mass. The kilogram-force leads to an alternate, but rarely used unit of mass: the metric slug (sometimes mug or hyl) is that mass that accelerates at 1 m\u00b7s\u22122 when subjected to a force of 1 kgf. The kilogram-force is not a part of the modern SI system, and is generally deprecated; however it still sees use for some purposes as expressing aircraft weight, jet thrust, bicycle spoke tension, torque wrench settings and engine output torque. Other arcane units of force include the sth\u00e8ne, which is equivalent to 1000 N, and the kip, which is equivalent to 1000 lbf.", "output": "Yes", "explanation": "The answer to the question is not present in the context but it is recognized as 'Yes', hence it is a negative example."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Wikipedia"], "Instance": {"id": "task1624-6bcd4d1e02fb4ca99406dc4ceb3a32ca", "input": "proper question: Why did Warsaw become the capital of the Commonwealth? \n disfluent question: Why did King Sigismund III no um why did Warsaw become the capital of the Commonwealth? \n context: In 1529, Warsaw for the first time became the seat of the General Sejm, permanent from 1569. In 1573 the city gave its name to the Warsaw Confederation, formally establishing religious freedom in the Polish\u2013Lithuanian Commonwealth. Due to its central location between the Commonwealth's capitals of Krak\u00f3w and Vilnius, Warsaw became the capital of the Commonwealth and the Crown of the Kingdom of Poland when King Sigismund III Vasa moved his court from Krak\u00f3w to Warsaw in 1596. In the following years the town expanded towards the suburbs. Several private independent districts were established, the property of aristocrats and the gentry, which were ruled by their own laws. Three times between 1655\u20131658 the city was under siege and three times it was taken and pillaged by the Swedish, Brandenburgian and Transylvanian forces.", "output": ["Yes"]}, "Instance License": ["CC BY 4.0"], "prediction": "Yes"}
+{"id": "task1624-81e4262b5d3c4bb38e0226ace8e9e3bc", "Task": "task1624_disfl_qa_question_yesno_classification", "Contributors": "['Krishna Kesani']", "Source": ["disfl_qa"], "URL": ["https://huggingface.co/datasets/disfl_qa"], "Categories": ["Answerability Classification"], "Reasoning": [], "Definition": ["In this task you are given a disfluent question, a proper question and a context. A disfluent question is a question that has some interruptions in it while framing and a proper question is the correct form of the question without any disfluency. Classify whether the question is answerable or not based on the given context."], "Positive Examples": [{"input": "proper question: Who recorded Walking in Fresno? \n disfluent question: Where no sorry who recorded Walking in Fresno? \n context: In the 1970s, the city was the subject of a song, Walking Into Fresno, written by Hall Of Fame guitarist Bill Aken and recorded by Bob Gallion of the world-famous WWVA Jamboree radio and television show in Wheeling, West Virginia. Aken, adopted by Mexican movie actress Lupe Mayorga, grew up in the neighboring town of Madera and his song chronicled the hardships faced by the migrant farm workers he saw as a child. Aken also made his first TV appearance playing guitar on the old country-western show at The Fresno Barn.", "output": "Yes", "explanation": "The input sentence is correctly recognized as answerable because the answer to the question is 'Bill Aken' and it is present in the context so it is a positive example."}, {"input": "proper question: Who was the former host of Late Night with Conan O'Brien? \n disfluent question: Who was the director of Noah in 2014 no not that tell me who was the former host of Late Night with Conan O'Brien? \n context: Other: Civil rights leader W. E. B. Du Bois; philosopher Henry David Thoreau; authors Ralph Waldo Emerson and William S. Burroughs; educators Werner Baer, Harlan Hanson; poets Wallace Stevens, T. S. Eliot and E. E. Cummings; conductor Leonard Bernstein; cellist Yo Yo Ma; pianist and composer Charlie Albright; composer John Alden Carpenter; comedian, television show host and writer Conan O'Brien; actors Tatyana Ali, Nestor Carbonell, Matt Damon, Fred Gwynne, Hill Harper, Rashida Jones, Tommy Lee Jones, Ashley Judd, Jack Lemmon, Natalie Portman, Mira Sorvino, Elisabeth Shue, and Scottie Thompson; film directors Darren Aronofsky, Terrence Malick, Mira Nair, and Whit Stillman; architect Philip Johnson; musicians Rivers Cuomo, Tom Morello, and Gram Parsons; musician, producer and composer Ryan Leslie; serial killer Ted Kaczynski; programmer and activist Richard Stallman; NFL quarterback Ryan Fitzpatrick; NFL center Matt Birk; NBA player Jeremy Lin; US Ski Team skier Ryan Max Riley; physician Sachin H. Jain; physicist J. Robert Oppenheimer; computer pioneer and inventor An Wang; Tibetologist George de Roerich; and Marshall Admiral Isoroku Yamamoto.", "output": "No", "explanation": "The input sentence is correctly recognized as not answerable because the answer to the question is not present in the context so it is a positive example."}, {"input": "proper question: When did the Germanic tribes not claim territory in north and west Europe? \n disfluent question: When did the Scandinavian tribes not claim territory in north and west Europe, oh actually it was the Germanic tribes? \n context: From their original homelands in Scandinavia and northern Europe, Germanic tribes expanded throughout northern and western Europe in the middle period of classical antiquity; southern Europe in late antiquity, conquering Celtic and other peoples; and by 800 CE, forming the Holy Roman Empire, the first German Empire. However, there was no real systemic continuity from the Western Roman Empire to its German successor which was famously described as not holy, not Roman, and not an empire, as a great number of small states and principalities existed in the loosely autonomous confederation. Although by 1000 CE, the Germanic conquest of central, western, and southern Europe (west of and including Italy) was complete, excluding only Muslim Iberia. There was, however, little cultural integration or national identity, and Germany remained largely a conceptual term referring to an amorphous area of central Europe.", "output": "No", "explanation": "The answer to the question is not present in the context, so it is a positive example."}, {"input": "proper question: When was the Brotherhood first banned in Egypt? \n disfluent question: When was Al-Banna or uh rather the Brotherhood first banned in Egypt? \n context: Some elements of the Brotherhood, though perhaps against orders, did engage in violence against the government, and its founder Al-Banna was assassinated in 1949 in retaliation for the assassination of Egypt's premier Mahmud Fami Naqrashi three months earlier. The Brotherhood has suffered periodic repression in Egypt and has been banned several times, in 1948 and several years later following confrontations with Egyptian president Gamal Abdul Nasser, who jailed thousands of members for several years.", "output": "Yes", "explanation": "The answer to the question is '1948' and present in the context, so it is a positive example."}], "Negative Examples": [{"input": "proper question: Who governs Nobel Prize central bank? \n disfluent question: What well er who governs Nobel Prize central bank? \n context: Current faculty include the anthropologist Marshall Sahlins, historian Dipesh Chakrabarty, paleontologists Neil Shubin and Paul Sereno, evolutionary biologist Jerry Coyne, Nobel prize winning physicist Yoichiro Nambu, Nobel prize winning physicist James Cronin, Nobel Prize winning economists Eugene Fama, James Heckman, Lars Peter Hansen, Roger Myerson and Robert Lucas, Jr., Freakonomics author and noted economist Steven Levitt, current governor of India's central bank Raghuram Rajan, the 74th United States Secretary of the Treasury and former Goldman Sachs Chairman and CEO Hank Paulson, former Chairman of President Barack Obama's Council of Economic Advisors Austan Goolsbee, Shakespeare scholar David Bevington, and renowned political scientists John Mearsheimer and Robert Pape.", "output": "Yes", "explanation": "The answer to the question is not present in the context as nothing is told about who governs the Noble prize central bank hence it is a negative example. And the output should be No."}, {"input": "proper question: What force leads to a commonly used unit of mass? \n disfluent question: What is er what force leads to a commonly used unit of mass? \n context: The pound-force has a metric counterpart, less commonly used than the newton: the kilogram-force (kgf) (sometimes kilopond), is the force exerted by standard gravity on one kilogram of mass. The kilogram-force leads to an alternate, but rarely used unit of mass: the metric slug (sometimes mug or hyl) is that mass that accelerates at 1 m\u00b7s\u22122 when subjected to a force of 1 kgf. The kilogram-force is not a part of the modern SI system, and is generally deprecated; however it still sees use for some purposes as expressing aircraft weight, jet thrust, bicycle spoke tension, torque wrench settings and engine output torque. Other arcane units of force include the sth\u00e8ne, which is equivalent to 1000 N, and the kip, which is equivalent to 1000 lbf.", "output": "Yes", "explanation": "The answer to the question is not present in the context but it is recognized as 'Yes', hence it is a negative example."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Wikipedia"], "Instance": {"id": "task1624-81e4262b5d3c4bb38e0226ace8e9e3bc", "input": "proper question: What metaphors explained global warming? \n disfluent question: What metaphors explained Kyoto Protocol no no um global warming? \n context: According to Sheldon Ungar's comparison with global warming, the actors in the ozone depletion case had a better understanding of scientific ignorance and uncertainties. The ozone case communicated to lay persons with easy-to-understand bridging metaphors derived from the popular culture and related to immediate risks with everyday relevance, while the public opinion on climate change sees no imminent danger. The stepwise mitigation of the ozone layer challenge was based as well on successfully reducing regional burden sharing conflicts. In case of the IPCC conclusions and the failure of the Kyoto Protocol, varying regional cost-benefit analysis and burden-sharing conflicts with regard to the distribution of emission reductions remain an unsolved problem. In the UK, a report for a House of Lords committee asked to urge the IPCC to involve better assessments of costs and benefits of climate change but the Stern Review ordered by the UK government made a stronger argument in favor to combat human-made climate change.", "output": ["No"]}, "Instance License": ["CC BY 4.0"], "prediction": "No"}
+{"id": "task1624-5c5c6180e5c44c448fc2db8c95cf3e4e", "Task": "task1624_disfl_qa_question_yesno_classification", "Contributors": "['Krishna Kesani']", "Source": ["disfl_qa"], "URL": ["https://huggingface.co/datasets/disfl_qa"], "Categories": ["Answerability Classification"], "Reasoning": [], "Definition": ["In this task you are given a disfluent question, a proper question and a context. A disfluent question is a question that has some interruptions in it while framing and a proper question is the correct form of the question without any disfluency. Classify whether the question is answerable or not based on the given context."], "Positive Examples": [{"input": "proper question: Who recorded Walking in Fresno? \n disfluent question: Where no sorry who recorded Walking in Fresno? \n context: In the 1970s, the city was the subject of a song, Walking Into Fresno, written by Hall Of Fame guitarist Bill Aken and recorded by Bob Gallion of the world-famous WWVA Jamboree radio and television show in Wheeling, West Virginia. Aken, adopted by Mexican movie actress Lupe Mayorga, grew up in the neighboring town of Madera and his song chronicled the hardships faced by the migrant farm workers he saw as a child. Aken also made his first TV appearance playing guitar on the old country-western show at The Fresno Barn.", "output": "Yes", "explanation": "The input sentence is correctly recognized as answerable because the answer to the question is 'Bill Aken' and it is present in the context so it is a positive example."}, {"input": "proper question: Who was the former host of Late Night with Conan O'Brien? \n disfluent question: Who was the director of Noah in 2014 no not that tell me who was the former host of Late Night with Conan O'Brien? \n context: Other: Civil rights leader W. E. B. Du Bois; philosopher Henry David Thoreau; authors Ralph Waldo Emerson and William S. Burroughs; educators Werner Baer, Harlan Hanson; poets Wallace Stevens, T. S. Eliot and E. E. Cummings; conductor Leonard Bernstein; cellist Yo Yo Ma; pianist and composer Charlie Albright; composer John Alden Carpenter; comedian, television show host and writer Conan O'Brien; actors Tatyana Ali, Nestor Carbonell, Matt Damon, Fred Gwynne, Hill Harper, Rashida Jones, Tommy Lee Jones, Ashley Judd, Jack Lemmon, Natalie Portman, Mira Sorvino, Elisabeth Shue, and Scottie Thompson; film directors Darren Aronofsky, Terrence Malick, Mira Nair, and Whit Stillman; architect Philip Johnson; musicians Rivers Cuomo, Tom Morello, and Gram Parsons; musician, producer and composer Ryan Leslie; serial killer Ted Kaczynski; programmer and activist Richard Stallman; NFL quarterback Ryan Fitzpatrick; NFL center Matt Birk; NBA player Jeremy Lin; US Ski Team skier Ryan Max Riley; physician Sachin H. Jain; physicist J. Robert Oppenheimer; computer pioneer and inventor An Wang; Tibetologist George de Roerich; and Marshall Admiral Isoroku Yamamoto.", "output": "No", "explanation": "The input sentence is correctly recognized as not answerable because the answer to the question is not present in the context so it is a positive example."}, {"input": "proper question: When did the Germanic tribes not claim territory in north and west Europe? \n disfluent question: When did the Scandinavian tribes not claim territory in north and west Europe, oh actually it was the Germanic tribes? \n context: From their original homelands in Scandinavia and northern Europe, Germanic tribes expanded throughout northern and western Europe in the middle period of classical antiquity; southern Europe in late antiquity, conquering Celtic and other peoples; and by 800 CE, forming the Holy Roman Empire, the first German Empire. However, there was no real systemic continuity from the Western Roman Empire to its German successor which was famously described as not holy, not Roman, and not an empire, as a great number of small states and principalities existed in the loosely autonomous confederation. Although by 1000 CE, the Germanic conquest of central, western, and southern Europe (west of and including Italy) was complete, excluding only Muslim Iberia. There was, however, little cultural integration or national identity, and Germany remained largely a conceptual term referring to an amorphous area of central Europe.", "output": "No", "explanation": "The answer to the question is not present in the context, so it is a positive example."}, {"input": "proper question: When was the Brotherhood first banned in Egypt? \n disfluent question: When was Al-Banna or uh rather the Brotherhood first banned in Egypt? \n context: Some elements of the Brotherhood, though perhaps against orders, did engage in violence against the government, and its founder Al-Banna was assassinated in 1949 in retaliation for the assassination of Egypt's premier Mahmud Fami Naqrashi three months earlier. The Brotherhood has suffered periodic repression in Egypt and has been banned several times, in 1948 and several years later following confrontations with Egyptian president Gamal Abdul Nasser, who jailed thousands of members for several years.", "output": "Yes", "explanation": "The answer to the question is '1948' and present in the context, so it is a positive example."}], "Negative Examples": [{"input": "proper question: Who governs Nobel Prize central bank? \n disfluent question: What well er who governs Nobel Prize central bank? \n context: Current faculty include the anthropologist Marshall Sahlins, historian Dipesh Chakrabarty, paleontologists Neil Shubin and Paul Sereno, evolutionary biologist Jerry Coyne, Nobel prize winning physicist Yoichiro Nambu, Nobel prize winning physicist James Cronin, Nobel Prize winning economists Eugene Fama, James Heckman, Lars Peter Hansen, Roger Myerson and Robert Lucas, Jr., Freakonomics author and noted economist Steven Levitt, current governor of India's central bank Raghuram Rajan, the 74th United States Secretary of the Treasury and former Goldman Sachs Chairman and CEO Hank Paulson, former Chairman of President Barack Obama's Council of Economic Advisors Austan Goolsbee, Shakespeare scholar David Bevington, and renowned political scientists John Mearsheimer and Robert Pape.", "output": "Yes", "explanation": "The answer to the question is not present in the context as nothing is told about who governs the Noble prize central bank hence it is a negative example. And the output should be No."}, {"input": "proper question: What force leads to a commonly used unit of mass? \n disfluent question: What is er what force leads to a commonly used unit of mass? \n context: The pound-force has a metric counterpart, less commonly used than the newton: the kilogram-force (kgf) (sometimes kilopond), is the force exerted by standard gravity on one kilogram of mass. The kilogram-force leads to an alternate, but rarely used unit of mass: the metric slug (sometimes mug or hyl) is that mass that accelerates at 1 m\u00b7s\u22122 when subjected to a force of 1 kgf. The kilogram-force is not a part of the modern SI system, and is generally deprecated; however it still sees use for some purposes as expressing aircraft weight, jet thrust, bicycle spoke tension, torque wrench settings and engine output torque. Other arcane units of force include the sth\u00e8ne, which is equivalent to 1000 N, and the kip, which is equivalent to 1000 lbf.", "output": "Yes", "explanation": "The answer to the question is not present in the context but it is recognized as 'Yes', hence it is a negative example."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Wikipedia"], "Instance": {"id": "task1624-5c5c6180e5c44c448fc2db8c95cf3e4e", "input": "proper question: What interpretation of Islam is, for many of the adherents, not the gold standard of their religion? \n disfluent question: When or wait what interpretation of Islam is, for many of the adherents, not the gold standard of their religion? \n context: The interpretation of Islam promoted by this funding was the strict, conservative Saudi-based Wahhabism or Salafism. In its harshest form it preached that Muslims should not only always oppose infidels in every way, but hate them for their religion ... for Allah's sake, that democracy is responsible for all the horrible wars of the 20th century, that Shia and other non-Wahhabi Muslims were infidels, etc. While this effort has by no means converted all, or even most Muslims to the Wahhabist interpretation of Islam, it has done much to overwhelm more moderate local interpretations, and has set the Saudi-interpretation of Islam as the gold standard of religion in minds of some or many Muslims.", "output": ["No"]}, "Instance License": ["CC BY 4.0"], "prediction": "Yes"}
+{"id": "task1624-656944ac7a4c46898653c829e7c3fd29", "Task": "task1624_disfl_qa_question_yesno_classification", "Contributors": "['Krishna Kesani']", "Source": ["disfl_qa"], "URL": ["https://huggingface.co/datasets/disfl_qa"], "Categories": ["Answerability Classification"], "Reasoning": [], "Definition": ["In this task you are given a disfluent question, a proper question and a context. A disfluent question is a question that has some interruptions in it while framing and a proper question is the correct form of the question without any disfluency. Classify whether the question is answerable or not based on the given context."], "Positive Examples": [{"input": "proper question: Who recorded Walking in Fresno? \n disfluent question: Where no sorry who recorded Walking in Fresno? \n context: In the 1970s, the city was the subject of a song, Walking Into Fresno, written by Hall Of Fame guitarist Bill Aken and recorded by Bob Gallion of the world-famous WWVA Jamboree radio and television show in Wheeling, West Virginia. Aken, adopted by Mexican movie actress Lupe Mayorga, grew up in the neighboring town of Madera and his song chronicled the hardships faced by the migrant farm workers he saw as a child. Aken also made his first TV appearance playing guitar on the old country-western show at The Fresno Barn.", "output": "Yes", "explanation": "The input sentence is correctly recognized as answerable because the answer to the question is 'Bill Aken' and it is present in the context so it is a positive example."}, {"input": "proper question: Who was the former host of Late Night with Conan O'Brien? \n disfluent question: Who was the director of Noah in 2014 no not that tell me who was the former host of Late Night with Conan O'Brien? \n context: Other: Civil rights leader W. E. B. Du Bois; philosopher Henry David Thoreau; authors Ralph Waldo Emerson and William S. Burroughs; educators Werner Baer, Harlan Hanson; poets Wallace Stevens, T. S. Eliot and E. E. Cummings; conductor Leonard Bernstein; cellist Yo Yo Ma; pianist and composer Charlie Albright; composer John Alden Carpenter; comedian, television show host and writer Conan O'Brien; actors Tatyana Ali, Nestor Carbonell, Matt Damon, Fred Gwynne, Hill Harper, Rashida Jones, Tommy Lee Jones, Ashley Judd, Jack Lemmon, Natalie Portman, Mira Sorvino, Elisabeth Shue, and Scottie Thompson; film directors Darren Aronofsky, Terrence Malick, Mira Nair, and Whit Stillman; architect Philip Johnson; musicians Rivers Cuomo, Tom Morello, and Gram Parsons; musician, producer and composer Ryan Leslie; serial killer Ted Kaczynski; programmer and activist Richard Stallman; NFL quarterback Ryan Fitzpatrick; NFL center Matt Birk; NBA player Jeremy Lin; US Ski Team skier Ryan Max Riley; physician Sachin H. Jain; physicist J. Robert Oppenheimer; computer pioneer and inventor An Wang; Tibetologist George de Roerich; and Marshall Admiral Isoroku Yamamoto.", "output": "No", "explanation": "The input sentence is correctly recognized as not answerable because the answer to the question is not present in the context so it is a positive example."}, {"input": "proper question: When did the Germanic tribes not claim territory in north and west Europe? \n disfluent question: When did the Scandinavian tribes not claim territory in north and west Europe, oh actually it was the Germanic tribes? \n context: From their original homelands in Scandinavia and northern Europe, Germanic tribes expanded throughout northern and western Europe in the middle period of classical antiquity; southern Europe in late antiquity, conquering Celtic and other peoples; and by 800 CE, forming the Holy Roman Empire, the first German Empire. However, there was no real systemic continuity from the Western Roman Empire to its German successor which was famously described as not holy, not Roman, and not an empire, as a great number of small states and principalities existed in the loosely autonomous confederation. Although by 1000 CE, the Germanic conquest of central, western, and southern Europe (west of and including Italy) was complete, excluding only Muslim Iberia. There was, however, little cultural integration or national identity, and Germany remained largely a conceptual term referring to an amorphous area of central Europe.", "output": "No", "explanation": "The answer to the question is not present in the context, so it is a positive example."}, {"input": "proper question: When was the Brotherhood first banned in Egypt? \n disfluent question: When was Al-Banna or uh rather the Brotherhood first banned in Egypt? \n context: Some elements of the Brotherhood, though perhaps against orders, did engage in violence against the government, and its founder Al-Banna was assassinated in 1949 in retaliation for the assassination of Egypt's premier Mahmud Fami Naqrashi three months earlier. The Brotherhood has suffered periodic repression in Egypt and has been banned several times, in 1948 and several years later following confrontations with Egyptian president Gamal Abdul Nasser, who jailed thousands of members for several years.", "output": "Yes", "explanation": "The answer to the question is '1948' and present in the context, so it is a positive example."}], "Negative Examples": [{"input": "proper question: Who governs Nobel Prize central bank? \n disfluent question: What well er who governs Nobel Prize central bank? \n context: Current faculty include the anthropologist Marshall Sahlins, historian Dipesh Chakrabarty, paleontologists Neil Shubin and Paul Sereno, evolutionary biologist Jerry Coyne, Nobel prize winning physicist Yoichiro Nambu, Nobel prize winning physicist James Cronin, Nobel Prize winning economists Eugene Fama, James Heckman, Lars Peter Hansen, Roger Myerson and Robert Lucas, Jr., Freakonomics author and noted economist Steven Levitt, current governor of India's central bank Raghuram Rajan, the 74th United States Secretary of the Treasury and former Goldman Sachs Chairman and CEO Hank Paulson, former Chairman of President Barack Obama's Council of Economic Advisors Austan Goolsbee, Shakespeare scholar David Bevington, and renowned political scientists John Mearsheimer and Robert Pape.", "output": "Yes", "explanation": "The answer to the question is not present in the context as nothing is told about who governs the Noble prize central bank hence it is a negative example. And the output should be No."}, {"input": "proper question: What force leads to a commonly used unit of mass? \n disfluent question: What is er what force leads to a commonly used unit of mass? \n context: The pound-force has a metric counterpart, less commonly used than the newton: the kilogram-force (kgf) (sometimes kilopond), is the force exerted by standard gravity on one kilogram of mass. The kilogram-force leads to an alternate, but rarely used unit of mass: the metric slug (sometimes mug or hyl) is that mass that accelerates at 1 m\u00b7s\u22122 when subjected to a force of 1 kgf. The kilogram-force is not a part of the modern SI system, and is generally deprecated; however it still sees use for some purposes as expressing aircraft weight, jet thrust, bicycle spoke tension, torque wrench settings and engine output torque. Other arcane units of force include the sth\u00e8ne, which is equivalent to 1000 N, and the kip, which is equivalent to 1000 lbf.", "output": "Yes", "explanation": "The answer to the question is not present in the context but it is recognized as 'Yes', hence it is a negative example."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Wikipedia"], "Instance": {"id": "task1624-656944ac7a4c46898653c829e7c3fd29", "input": "proper question: Who in Warsaw has the power of legislative action? \n disfluent question: How many er who in Warsaw has the power of legislative action? \n context: Legislative power in Warsaw is vested in a unicameral Warsaw City Council (Rada Miasta), which comprises 60 members. Council members are elected directly every four years. Like most legislative bodies, the City Council divides itself into committees which have the oversight of various functions of the city government. Bills passed by a simple majority are sent to the mayor (the President of Warsaw), who may sign them into law. If the mayor vetoes a bill, the Council has 30 days to override the veto by a two-thirds majority vote.", "output": ["Yes"]}, "Instance License": ["CC BY 4.0"], "prediction": "No"}
+{"id": "task1624-3c7cde165b5b417b96778f64b1bb4b35", "Task": "task1624_disfl_qa_question_yesno_classification", "Contributors": "['Krishna Kesani']", "Source": ["disfl_qa"], "URL": ["https://huggingface.co/datasets/disfl_qa"], "Categories": ["Answerability Classification"], "Reasoning": [], "Definition": ["In this task you are given a disfluent question, a proper question and a context. A disfluent question is a question that has some interruptions in it while framing and a proper question is the correct form of the question without any disfluency. Classify whether the question is answerable or not based on the given context."], "Positive Examples": [{"input": "proper question: Who recorded Walking in Fresno? \n disfluent question: Where no sorry who recorded Walking in Fresno? \n context: In the 1970s, the city was the subject of a song, Walking Into Fresno, written by Hall Of Fame guitarist Bill Aken and recorded by Bob Gallion of the world-famous WWVA Jamboree radio and television show in Wheeling, West Virginia. Aken, adopted by Mexican movie actress Lupe Mayorga, grew up in the neighboring town of Madera and his song chronicled the hardships faced by the migrant farm workers he saw as a child. Aken also made his first TV appearance playing guitar on the old country-western show at The Fresno Barn.", "output": "Yes", "explanation": "The input sentence is correctly recognized as answerable because the answer to the question is 'Bill Aken' and it is present in the context so it is a positive example."}, {"input": "proper question: Who was the former host of Late Night with Conan O'Brien? \n disfluent question: Who was the director of Noah in 2014 no not that tell me who was the former host of Late Night with Conan O'Brien? \n context: Other: Civil rights leader W. E. B. Du Bois; philosopher Henry David Thoreau; authors Ralph Waldo Emerson and William S. Burroughs; educators Werner Baer, Harlan Hanson; poets Wallace Stevens, T. S. Eliot and E. E. Cummings; conductor Leonard Bernstein; cellist Yo Yo Ma; pianist and composer Charlie Albright; composer John Alden Carpenter; comedian, television show host and writer Conan O'Brien; actors Tatyana Ali, Nestor Carbonell, Matt Damon, Fred Gwynne, Hill Harper, Rashida Jones, Tommy Lee Jones, Ashley Judd, Jack Lemmon, Natalie Portman, Mira Sorvino, Elisabeth Shue, and Scottie Thompson; film directors Darren Aronofsky, Terrence Malick, Mira Nair, and Whit Stillman; architect Philip Johnson; musicians Rivers Cuomo, Tom Morello, and Gram Parsons; musician, producer and composer Ryan Leslie; serial killer Ted Kaczynski; programmer and activist Richard Stallman; NFL quarterback Ryan Fitzpatrick; NFL center Matt Birk; NBA player Jeremy Lin; US Ski Team skier Ryan Max Riley; physician Sachin H. Jain; physicist J. Robert Oppenheimer; computer pioneer and inventor An Wang; Tibetologist George de Roerich; and Marshall Admiral Isoroku Yamamoto.", "output": "No", "explanation": "The input sentence is correctly recognized as not answerable because the answer to the question is not present in the context so it is a positive example."}, {"input": "proper question: When did the Germanic tribes not claim territory in north and west Europe? \n disfluent question: When did the Scandinavian tribes not claim territory in north and west Europe, oh actually it was the Germanic tribes? \n context: From their original homelands in Scandinavia and northern Europe, Germanic tribes expanded throughout northern and western Europe in the middle period of classical antiquity; southern Europe in late antiquity, conquering Celtic and other peoples; and by 800 CE, forming the Holy Roman Empire, the first German Empire. However, there was no real systemic continuity from the Western Roman Empire to its German successor which was famously described as not holy, not Roman, and not an empire, as a great number of small states and principalities existed in the loosely autonomous confederation. Although by 1000 CE, the Germanic conquest of central, western, and southern Europe (west of and including Italy) was complete, excluding only Muslim Iberia. There was, however, little cultural integration or national identity, and Germany remained largely a conceptual term referring to an amorphous area of central Europe.", "output": "No", "explanation": "The answer to the question is not present in the context, so it is a positive example."}, {"input": "proper question: When was the Brotherhood first banned in Egypt? \n disfluent question: When was Al-Banna or uh rather the Brotherhood first banned in Egypt? \n context: Some elements of the Brotherhood, though perhaps against orders, did engage in violence against the government, and its founder Al-Banna was assassinated in 1949 in retaliation for the assassination of Egypt's premier Mahmud Fami Naqrashi three months earlier. The Brotherhood has suffered periodic repression in Egypt and has been banned several times, in 1948 and several years later following confrontations with Egyptian president Gamal Abdul Nasser, who jailed thousands of members for several years.", "output": "Yes", "explanation": "The answer to the question is '1948' and present in the context, so it is a positive example."}], "Negative Examples": [{"input": "proper question: Who governs Nobel Prize central bank? \n disfluent question: What well er who governs Nobel Prize central bank? \n context: Current faculty include the anthropologist Marshall Sahlins, historian Dipesh Chakrabarty, paleontologists Neil Shubin and Paul Sereno, evolutionary biologist Jerry Coyne, Nobel prize winning physicist Yoichiro Nambu, Nobel prize winning physicist James Cronin, Nobel Prize winning economists Eugene Fama, James Heckman, Lars Peter Hansen, Roger Myerson and Robert Lucas, Jr., Freakonomics author and noted economist Steven Levitt, current governor of India's central bank Raghuram Rajan, the 74th United States Secretary of the Treasury and former Goldman Sachs Chairman and CEO Hank Paulson, former Chairman of President Barack Obama's Council of Economic Advisors Austan Goolsbee, Shakespeare scholar David Bevington, and renowned political scientists John Mearsheimer and Robert Pape.", "output": "Yes", "explanation": "The answer to the question is not present in the context as nothing is told about who governs the Noble prize central bank hence it is a negative example. And the output should be No."}, {"input": "proper question: What force leads to a commonly used unit of mass? \n disfluent question: What is er what force leads to a commonly used unit of mass? \n context: The pound-force has a metric counterpart, less commonly used than the newton: the kilogram-force (kgf) (sometimes kilopond), is the force exerted by standard gravity on one kilogram of mass. The kilogram-force leads to an alternate, but rarely used unit of mass: the metric slug (sometimes mug or hyl) is that mass that accelerates at 1 m\u00b7s\u22122 when subjected to a force of 1 kgf. The kilogram-force is not a part of the modern SI system, and is generally deprecated; however it still sees use for some purposes as expressing aircraft weight, jet thrust, bicycle spoke tension, torque wrench settings and engine output torque. Other arcane units of force include the sth\u00e8ne, which is equivalent to 1000 N, and the kip, which is equivalent to 1000 lbf.", "output": "Yes", "explanation": "The answer to the question is not present in the context but it is recognized as 'Yes', hence it is a negative example."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Wikipedia"], "Instance": {"id": "task1624-3c7cde165b5b417b96778f64b1bb4b35", "input": "proper question: What session did the IPCC panel attend before the opening ceremonies? \n disfluent question: What people did the IPCC panel I meant session did they attend before the opening ceremonies? \n context: The IPCC Panel is composed of representatives appointed by governments and organizations. Participation of delegates with appropriate expertise is encouraged. Plenary sessions of the IPCC and IPCC Working groups are held at the level of government representatives. Non Governmental and Intergovernmental Organizations may be allowed to attend as observers. Sessions of the IPCC Bureau, workshops, expert and lead authors meetings are by invitation only. Attendance at the 2003 meeting included 350 government officials and climate change experts. After the opening ceremonies, closed plenary sessions were held. The meeting report states there were 322 persons in attendance at Sessions with about seven-eighths of participants being from governmental organizations.", "output": ["No"]}, "Instance License": ["CC BY 4.0"], "prediction": "No"}
+{"id": "task1158-3fc1c1daae8c42f4a30eceef03affe94", "Task": "task1158_bard_analogical_reasoning_manipulating_items", "Contributors": "['Arjun Ashok']", "Source": ["bard"], "URL": ["https://github.com/NancyFulda/BYU-Analogical-Reasoning-Dataset"], "Categories": ["Word Analogy"], "Reasoning": ["Relational Reasoning", "Commonsense Reasoning", "Analogical Reasoning"], "Definition": ["Two analogies on manipulating items in a kitchen is given in the form \"A : B. C : ?\". The phrase \"A : B\" relates item A to its appropriate manipulation B. Your task is to replace the question mark (?) with the appropriate manipulation of item C, following the \"A : B\" relation. Your answer should be a verb which shows a way to manipulate the given object."], "Positive Examples": [{"input": "jug : pour. shoe : ?", "output": "untie", "explanation": "The given analogy relates items to how they are manipulated. Jugs can be poured into. Shoes can be untied."}, {"input": "jar : open. box : ?", "output": "open", "explanation": "The given analogy relates items to how they are manipulated. Jars can be opened. Boxes can be opened."}, {"input": "bottle : pour. safe : ?", "output": "unlock", "explanation": "Bottles can be poured into, and safes can be unlocked. So, unlock is a correct output here."}], "Negative Examples": [{"input": "backpack : unzip. safe : ?", "output": "travel", "explanation": "The given analogy relates items to how they are manipulated. Backpacks can be unzipped. Safes CANNOT be travelled, and so it not the correct answer."}, {"input": "faucet : turn. bag : ?", "output": "cupboard", "explanation": "The given analogy relates items to how they are manipulated. Faucets can be turned. Cupboard is not the right answer for bag, as it does not model the same relation, and it instead models containment."}, {"input": "peas : shell. present : ?", "output": "unlock", "explanation": "The given analogy relates items to how they are manipulated. Peas can be shelled. Unlock is not the right answer for present, as presents cannot be unlocked."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Commonsense"], "Instance": {"id": "task1158-3fc1c1daae8c42f4a30eceef03affe94", "input": "backpack : unzip. banana : ?", "output": ["peel"]}, "Instance License": ["Apache 2.0"], "prediction": "unripe"}
+{"id": "task1158-33a2fe0e03f04e63a471a75ecd72ee40", "Task": "task1158_bard_analogical_reasoning_manipulating_items", "Contributors": "['Arjun Ashok']", "Source": ["bard"], "URL": ["https://github.com/NancyFulda/BYU-Analogical-Reasoning-Dataset"], "Categories": ["Word Analogy"], "Reasoning": ["Relational Reasoning", "Commonsense Reasoning", "Analogical Reasoning"], "Definition": ["Two analogies on manipulating items in a kitchen is given in the form \"A : B. C : ?\". The phrase \"A : B\" relates item A to its appropriate manipulation B. Your task is to replace the question mark (?) with the appropriate manipulation of item C, following the \"A : B\" relation. Your answer should be a verb which shows a way to manipulate the given object."], "Positive Examples": [{"input": "jug : pour. shoe : ?", "output": "untie", "explanation": "The given analogy relates items to how they are manipulated. Jugs can be poured into. Shoes can be untied."}, {"input": "jar : open. box : ?", "output": "open", "explanation": "The given analogy relates items to how they are manipulated. Jars can be opened. Boxes can be opened."}, {"input": "bottle : pour. safe : ?", "output": "unlock", "explanation": "Bottles can be poured into, and safes can be unlocked. So, unlock is a correct output here."}], "Negative Examples": [{"input": "backpack : unzip. safe : ?", "output": "travel", "explanation": "The given analogy relates items to how they are manipulated. Backpacks can be unzipped. Safes CANNOT be travelled, and so it not the correct answer."}, {"input": "faucet : turn. bag : ?", "output": "cupboard", "explanation": "The given analogy relates items to how they are manipulated. Faucets can be turned. Cupboard is not the right answer for bag, as it does not model the same relation, and it instead models containment."}, {"input": "peas : shell. present : ?", "output": "unlock", "explanation": "The given analogy relates items to how they are manipulated. Peas can be shelled. Unlock is not the right answer for present, as presents cannot be unlocked."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Commonsense"], "Instance": {"id": "task1158-33a2fe0e03f04e63a471a75ecd72ee40", "input": "present : open. bottle : ?", "output": ["pour", "squeeze"]}, "Instance License": ["Apache 2.0"], "prediction": "open"}
+{"id": "task1158-0c8bafcca2104450938f7df7f0650960", "Task": "task1158_bard_analogical_reasoning_manipulating_items", "Contributors": "['Arjun Ashok']", "Source": ["bard"], "URL": ["https://github.com/NancyFulda/BYU-Analogical-Reasoning-Dataset"], "Categories": ["Word Analogy"], "Reasoning": ["Relational Reasoning", "Commonsense Reasoning", "Analogical Reasoning"], "Definition": ["Two analogies on manipulating items in a kitchen is given in the form \"A : B. C : ?\". The phrase \"A : B\" relates item A to its appropriate manipulation B. Your task is to replace the question mark (?) with the appropriate manipulation of item C, following the \"A : B\" relation. Your answer should be a verb which shows a way to manipulate the given object."], "Positive Examples": [{"input": "jug : pour. shoe : ?", "output": "untie", "explanation": "The given analogy relates items to how they are manipulated. Jugs can be poured into. Shoes can be untied."}, {"input": "jar : open. box : ?", "output": "open", "explanation": "The given analogy relates items to how they are manipulated. Jars can be opened. Boxes can be opened."}, {"input": "bottle : pour. safe : ?", "output": "unlock", "explanation": "Bottles can be poured into, and safes can be unlocked. So, unlock is a correct output here."}], "Negative Examples": [{"input": "backpack : unzip. safe : ?", "output": "travel", "explanation": "The given analogy relates items to how they are manipulated. Backpacks can be unzipped. Safes CANNOT be travelled, and so it not the correct answer."}, {"input": "faucet : turn. bag : ?", "output": "cupboard", "explanation": "The given analogy relates items to how they are manipulated. Faucets can be turned. Cupboard is not the right answer for bag, as it does not model the same relation, and it instead models containment."}, {"input": "peas : shell. present : ?", "output": "unlock", "explanation": "The given analogy relates items to how they are manipulated. Peas can be shelled. Unlock is not the right answer for present, as presents cannot be unlocked."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Commonsense"], "Instance": {"id": "task1158-0c8bafcca2104450938f7df7f0650960", "input": "jug : pour. bottle : ?", "output": ["pour", "squeeze"]}, "Instance License": ["Apache 2.0"], "prediction": "pour"}
+{"id": "task1158-2f43bbed041642eab500c98928ae2cbb", "Task": "task1158_bard_analogical_reasoning_manipulating_items", "Contributors": "['Arjun Ashok']", "Source": ["bard"], "URL": ["https://github.com/NancyFulda/BYU-Analogical-Reasoning-Dataset"], "Categories": ["Word Analogy"], "Reasoning": ["Relational Reasoning", "Commonsense Reasoning", "Analogical Reasoning"], "Definition": ["Two analogies on manipulating items in a kitchen is given in the form \"A : B. C : ?\". The phrase \"A : B\" relates item A to its appropriate manipulation B. Your task is to replace the question mark (?) with the appropriate manipulation of item C, following the \"A : B\" relation. Your answer should be a verb which shows a way to manipulate the given object."], "Positive Examples": [{"input": "jug : pour. shoe : ?", "output": "untie", "explanation": "The given analogy relates items to how they are manipulated. Jugs can be poured into. Shoes can be untied."}, {"input": "jar : open. box : ?", "output": "open", "explanation": "The given analogy relates items to how they are manipulated. Jars can be opened. Boxes can be opened."}, {"input": "bottle : pour. safe : ?", "output": "unlock", "explanation": "Bottles can be poured into, and safes can be unlocked. So, unlock is a correct output here."}], "Negative Examples": [{"input": "backpack : unzip. safe : ?", "output": "travel", "explanation": "The given analogy relates items to how they are manipulated. Backpacks can be unzipped. Safes CANNOT be travelled, and so it not the correct answer."}, {"input": "faucet : turn. bag : ?", "output": "cupboard", "explanation": "The given analogy relates items to how they are manipulated. Faucets can be turned. Cupboard is not the right answer for bag, as it does not model the same relation, and it instead models containment."}, {"input": "peas : shell. present : ?", "output": "unlock", "explanation": "The given analogy relates items to how they are manipulated. Peas can be shelled. Unlock is not the right answer for present, as presents cannot be unlocked."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Commonsense"], "Instance": {"id": "task1158-2f43bbed041642eab500c98928ae2cbb", "input": "banana : peel. faucet : ?", "output": ["turn"]}, "Instance License": ["Apache 2.0"], "prediction": "turn"}
+{"id": "task1158-0536e891cc994c09b329ab7686306734", "Task": "task1158_bard_analogical_reasoning_manipulating_items", "Contributors": "['Arjun Ashok']", "Source": ["bard"], "URL": ["https://github.com/NancyFulda/BYU-Analogical-Reasoning-Dataset"], "Categories": ["Word Analogy"], "Reasoning": ["Relational Reasoning", "Commonsense Reasoning", "Analogical Reasoning"], "Definition": ["Two analogies on manipulating items in a kitchen is given in the form \"A : B. C : ?\". The phrase \"A : B\" relates item A to its appropriate manipulation B. Your task is to replace the question mark (?) with the appropriate manipulation of item C, following the \"A : B\" relation. Your answer should be a verb which shows a way to manipulate the given object."], "Positive Examples": [{"input": "jug : pour. shoe : ?", "output": "untie", "explanation": "The given analogy relates items to how they are manipulated. Jugs can be poured into. Shoes can be untied."}, {"input": "jar : open. box : ?", "output": "open", "explanation": "The given analogy relates items to how they are manipulated. Jars can be opened. Boxes can be opened."}, {"input": "bottle : pour. safe : ?", "output": "unlock", "explanation": "Bottles can be poured into, and safes can be unlocked. So, unlock is a correct output here."}], "Negative Examples": [{"input": "backpack : unzip. safe : ?", "output": "travel", "explanation": "The given analogy relates items to how they are manipulated. Backpacks can be unzipped. Safes CANNOT be travelled, and so it not the correct answer."}, {"input": "faucet : turn. bag : ?", "output": "cupboard", "explanation": "The given analogy relates items to how they are manipulated. Faucets can be turned. Cupboard is not the right answer for bag, as it does not model the same relation, and it instead models containment."}, {"input": "peas : shell. present : ?", "output": "unlock", "explanation": "The given analogy relates items to how they are manipulated. Peas can be shelled. Unlock is not the right answer for present, as presents cannot be unlocked."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Commonsense"], "Instance": {"id": "task1158-0536e891cc994c09b329ab7686306734", "input": "shoe : untie. pump : ?", "output": ["pump"]}, "Instance License": ["Apache 2.0"], "prediction": "untie"}
+{"id": "task827-076d2731abb64f15a3dee995d7f2c65d", "Task": "task827_copa_commonsense_reasoning", "Contributors": "['Amirreza Mirzaei']", "Source": ["copa"], "URL": ["https://people.ict.usc.edu/~gordon/copa.html"], "Categories": ["Cause Effect Classification"], "Reasoning": ["Commonsense Reasoning"], "Definition": ["Given a premise and two alternatives, choose the alternative that is a more plausible cause or effect of the situation described by the premise. The input format is \"premise\n(1)alternative_1(2)alternative_2\", the output should either be \"1\" or \"2\" based on your judgment."], "Positive Examples": [{"input": "The women met for coffee.\n(1)The cafe reopened in a new location.(2)They wanted to catch up with each other.", "output": "2", "explanation": "The second alternative makes more sense because meeting for coffee could be because of wanting to catch up with each other."}, {"input": "My body cast a shadow over the grass.\n(1)The sun was rising.(2)The grass was cut.", "output": "1", "explanation": "The first alternative makes more sense because casting a shadow is the effect of the sun being in the sky."}, {"input": "The guests of the party hid behind the couch.\n(1)It was a surprise party.(2)It was a birthday party.", "output": "1", "explanation": "The first alternative makes more sense because the guest hiding behind the couch could be because the party being a surprise."}], "Negative Examples": [{"input": "My body cast a shadow over the grass.\n(1)The sun was rising.(2)The grass was cut.", "output": "2", "explanation": "Casting a shadow has nothing to do with the grass being cut."}, {"input": "The man got a discount on his groceries.\n(1)He greeted the cashier.(2)He used a coupon.", "output": "1", "explanation": "Using a coupon can be the reason of getting a discount on his groceries. But greeting the cashier can't be a plausible cause. So, the output should be 2."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Narrative"], "Instance": {"id": "task827-076d2731abb64f15a3dee995d7f2c65d", "input": "I added sugar to the coffee.\n(1)The coffee smelled strong.(2)The coffee tasted sweet.", "output": ["2"]}, "Instance License": ["BSD 2-Clause"], "prediction": "1"}
+{"id": "task827-c8951b482b914e709017d147a10ab463", "Task": "task827_copa_commonsense_reasoning", "Contributors": "['Amirreza Mirzaei']", "Source": ["copa"], "URL": ["https://people.ict.usc.edu/~gordon/copa.html"], "Categories": ["Cause Effect Classification"], "Reasoning": ["Commonsense Reasoning"], "Definition": ["Given a premise and two alternatives, choose the alternative that is a more plausible cause or effect of the situation described by the premise. The input format is \"premise\n(1)alternative_1(2)alternative_2\", the output should either be \"1\" or \"2\" based on your judgment."], "Positive Examples": [{"input": "The women met for coffee.\n(1)The cafe reopened in a new location.(2)They wanted to catch up with each other.", "output": "2", "explanation": "The second alternative makes more sense because meeting for coffee could be because of wanting to catch up with each other."}, {"input": "My body cast a shadow over the grass.\n(1)The sun was rising.(2)The grass was cut.", "output": "1", "explanation": "The first alternative makes more sense because casting a shadow is the effect of the sun being in the sky."}, {"input": "The guests of the party hid behind the couch.\n(1)It was a surprise party.(2)It was a birthday party.", "output": "1", "explanation": "The first alternative makes more sense because the guest hiding behind the couch could be because the party being a surprise."}], "Negative Examples": [{"input": "My body cast a shadow over the grass.\n(1)The sun was rising.(2)The grass was cut.", "output": "2", "explanation": "Casting a shadow has nothing to do with the grass being cut."}, {"input": "The man got a discount on his groceries.\n(1)He greeted the cashier.(2)He used a coupon.", "output": "1", "explanation": "Using a coupon can be the reason of getting a discount on his groceries. But greeting the cashier can't be a plausible cause. So, the output should be 2."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Narrative"], "Instance": {"id": "task827-c8951b482b914e709017d147a10ab463", "input": "The man was denied for a loan.\n(1)He was in debt.(2)He started a business.", "output": ["1"]}, "Instance License": ["BSD 2-Clause"], "prediction": "1"}
+{"id": "task827-6910511d2bcb4aa9b9e2ce08069d4a75", "Task": "task827_copa_commonsense_reasoning", "Contributors": "['Amirreza Mirzaei']", "Source": ["copa"], "URL": ["https://people.ict.usc.edu/~gordon/copa.html"], "Categories": ["Cause Effect Classification"], "Reasoning": ["Commonsense Reasoning"], "Definition": ["Given a premise and two alternatives, choose the alternative that is a more plausible cause or effect of the situation described by the premise. The input format is \"premise\n(1)alternative_1(2)alternative_2\", the output should either be \"1\" or \"2\" based on your judgment."], "Positive Examples": [{"input": "The women met for coffee.\n(1)The cafe reopened in a new location.(2)They wanted to catch up with each other.", "output": "2", "explanation": "The second alternative makes more sense because meeting for coffee could be because of wanting to catch up with each other."}, {"input": "My body cast a shadow over the grass.\n(1)The sun was rising.(2)The grass was cut.", "output": "1", "explanation": "The first alternative makes more sense because casting a shadow is the effect of the sun being in the sky."}, {"input": "The guests of the party hid behind the couch.\n(1)It was a surprise party.(2)It was a birthday party.", "output": "1", "explanation": "The first alternative makes more sense because the guest hiding behind the couch could be because the party being a surprise."}], "Negative Examples": [{"input": "My body cast a shadow over the grass.\n(1)The sun was rising.(2)The grass was cut.", "output": "2", "explanation": "Casting a shadow has nothing to do with the grass being cut."}, {"input": "The man got a discount on his groceries.\n(1)He greeted the cashier.(2)He used a coupon.", "output": "1", "explanation": "Using a coupon can be the reason of getting a discount on his groceries. But greeting the cashier can't be a plausible cause. So, the output should be 2."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Narrative"], "Instance": {"id": "task827-6910511d2bcb4aa9b9e2ce08069d4a75", "input": "The boy threw a temper tantrum.\n(1)His brother took his toys from him.(2)He shared his toys with his brother.", "output": ["1"]}, "Instance License": ["BSD 2-Clause"], "prediction": "1"}
+{"id": "task827-23345dfb9569411db8a3446e0dcbc65d", "Task": "task827_copa_commonsense_reasoning", "Contributors": "['Amirreza Mirzaei']", "Source": ["copa"], "URL": ["https://people.ict.usc.edu/~gordon/copa.html"], "Categories": ["Cause Effect Classification"], "Reasoning": ["Commonsense Reasoning"], "Definition": ["Given a premise and two alternatives, choose the alternative that is a more plausible cause or effect of the situation described by the premise. The input format is \"premise\n(1)alternative_1(2)alternative_2\", the output should either be \"1\" or \"2\" based on your judgment."], "Positive Examples": [{"input": "The women met for coffee.\n(1)The cafe reopened in a new location.(2)They wanted to catch up with each other.", "output": "2", "explanation": "The second alternative makes more sense because meeting for coffee could be because of wanting to catch up with each other."}, {"input": "My body cast a shadow over the grass.\n(1)The sun was rising.(2)The grass was cut.", "output": "1", "explanation": "The first alternative makes more sense because casting a shadow is the effect of the sun being in the sky."}, {"input": "The guests of the party hid behind the couch.\n(1)It was a surprise party.(2)It was a birthday party.", "output": "1", "explanation": "The first alternative makes more sense because the guest hiding behind the couch could be because the party being a surprise."}], "Negative Examples": [{"input": "My body cast a shadow over the grass.\n(1)The sun was rising.(2)The grass was cut.", "output": "2", "explanation": "Casting a shadow has nothing to do with the grass being cut."}, {"input": "The man got a discount on his groceries.\n(1)He greeted the cashier.(2)He used a coupon.", "output": "1", "explanation": "Using a coupon can be the reason of getting a discount on his groceries. But greeting the cashier can't be a plausible cause. So, the output should be 2."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Narrative"], "Instance": {"id": "task827-23345dfb9569411db8a3446e0dcbc65d", "input": "The boy put his feet up on the table.\n(1)His father sat down at the table.(2)His father lectured him.", "output": ["2"]}, "Instance License": ["BSD 2-Clause"], "prediction": "1"}
+{"id": "task827-c6796782acd240c3962e159f631ba920", "Task": "task827_copa_commonsense_reasoning", "Contributors": "['Amirreza Mirzaei']", "Source": ["copa"], "URL": ["https://people.ict.usc.edu/~gordon/copa.html"], "Categories": ["Cause Effect Classification"], "Reasoning": ["Commonsense Reasoning"], "Definition": ["Given a premise and two alternatives, choose the alternative that is a more plausible cause or effect of the situation described by the premise. The input format is \"premise\n(1)alternative_1(2)alternative_2\", the output should either be \"1\" or \"2\" based on your judgment."], "Positive Examples": [{"input": "The women met for coffee.\n(1)The cafe reopened in a new location.(2)They wanted to catch up with each other.", "output": "2", "explanation": "The second alternative makes more sense because meeting for coffee could be because of wanting to catch up with each other."}, {"input": "My body cast a shadow over the grass.\n(1)The sun was rising.(2)The grass was cut.", "output": "1", "explanation": "The first alternative makes more sense because casting a shadow is the effect of the sun being in the sky."}, {"input": "The guests of the party hid behind the couch.\n(1)It was a surprise party.(2)It was a birthday party.", "output": "1", "explanation": "The first alternative makes more sense because the guest hiding behind the couch could be because the party being a surprise."}], "Negative Examples": [{"input": "My body cast a shadow over the grass.\n(1)The sun was rising.(2)The grass was cut.", "output": "2", "explanation": "Casting a shadow has nothing to do with the grass being cut."}, {"input": "The man got a discount on his groceries.\n(1)He greeted the cashier.(2)He used a coupon.", "output": "1", "explanation": "Using a coupon can be the reason of getting a discount on his groceries. But greeting the cashier can't be a plausible cause. So, the output should be 2."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Narrative"], "Instance": {"id": "task827-c6796782acd240c3962e159f631ba920", "input": "The woman pressed down on the piano key.\n(1)A sound played.(2)The key got stuck.", "output": ["1"]}, "Instance License": ["BSD 2-Clause"], "prediction": "1"}
+{"id": "task1153-287b5b79f3da4a4e9f4c7c19243d4ff3", "Task": "task1153_bard_analogical_reasoning_affordance", "Contributors": "['Arjun Ashok']", "Source": ["bard"], "URL": ["https://github.com/NancyFulda/BYU-Analogical-Reasoning-Dataset"], "Categories": ["Word Analogy"], "Reasoning": ["Relational Reasoning", "Commonsense Reasoning", "Analogical Reasoning"], "Definition": ["Two analogies that signify affordances are given in the form \"A : B. C : ?\". Affordance is the possibility of an action being done on an object, for example book is an affordance of writing. The phrase \"A : B\" implies that B is an affordance of A. Your task is to replace the question mark (?) with the appropriate affordance of the given action C, following the \"A : B\" relation. Your answer should be a single object without further explanation."], "Positive Examples": [{"input": "cure : disease. swing : ?", "output": "sword", "explanation": "The given analogy implies that diseases can be cured - an affordance relation. Hence, the appropriate answer for swing is sword, since swords can be swung."}, {"input": "write : book. swear : ?", "output": "oath", "explanation": "The given analogy implies that books can be written - an affordance relation. Hence, the appropriate answer for swear is oath, since oaths can be sworn."}, {"input": "sing : song. drive : ?", "output": "car", "explanation": "The given analogy implies that songs can be sung - an affordance relation. Hence, the appropriate answer for drive is car, since cars can be driven."}], "Negative Examples": [{"input": "ride : horse. attack : ?", "output": "car", "explanation": "The given analogy implies that horses can be ridden - an affordance relation. But, car is not an appropriate answer for attack, since cars cannot be attacked."}, {"input": "swear : oath. drop : ?", "output": "fall", "explanation": "The given analogy implies that oaths can be sworn - an affordance relation. But, fall is not an appropriate answer for drop, since this models the causation relation."}, {"input": "drink : water. give : ?", "output": "enemy", "explanation": "The given analogy implies that water can be drunk - an affordance relation. But, enemy is not an appropriate answer for give"}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Commonsense"], "Instance": {"id": "task1153-287b5b79f3da4a4e9f4c7c19243d4ff3", "input": "drive : car. brush : ?", "output": ["hair"]}, "Instance License": ["Apache 2.0"], "prediction": "hair"}
+{"id": "task1153-d84f047be0ae46e8a9f42089f081df1a", "Task": "task1153_bard_analogical_reasoning_affordance", "Contributors": "['Arjun Ashok']", "Source": ["bard"], "URL": ["https://github.com/NancyFulda/BYU-Analogical-Reasoning-Dataset"], "Categories": ["Word Analogy"], "Reasoning": ["Relational Reasoning", "Commonsense Reasoning", "Analogical Reasoning"], "Definition": ["Two analogies that signify affordances are given in the form \"A : B. C : ?\". Affordance is the possibility of an action being done on an object, for example book is an affordance of writing. The phrase \"A : B\" implies that B is an affordance of A. Your task is to replace the question mark (?) with the appropriate affordance of the given action C, following the \"A : B\" relation. Your answer should be a single object without further explanation."], "Positive Examples": [{"input": "cure : disease. swing : ?", "output": "sword", "explanation": "The given analogy implies that diseases can be cured - an affordance relation. Hence, the appropriate answer for swing is sword, since swords can be swung."}, {"input": "write : book. swear : ?", "output": "oath", "explanation": "The given analogy implies that books can be written - an affordance relation. Hence, the appropriate answer for swear is oath, since oaths can be sworn."}, {"input": "sing : song. drive : ?", "output": "car", "explanation": "The given analogy implies that songs can be sung - an affordance relation. Hence, the appropriate answer for drive is car, since cars can be driven."}], "Negative Examples": [{"input": "ride : horse. attack : ?", "output": "car", "explanation": "The given analogy implies that horses can be ridden - an affordance relation. But, car is not an appropriate answer for attack, since cars cannot be attacked."}, {"input": "swear : oath. drop : ?", "output": "fall", "explanation": "The given analogy implies that oaths can be sworn - an affordance relation. But, fall is not an appropriate answer for drop, since this models the causation relation."}, {"input": "drink : water. give : ?", "output": "enemy", "explanation": "The given analogy implies that water can be drunk - an affordance relation. But, enemy is not an appropriate answer for give"}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Commonsense"], "Instance": {"id": "task1153-d84f047be0ae46e8a9f42089f081df1a", "input": "reload : gun. paint : ?", "output": ["picture"]}, "Instance License": ["Apache 2.0"], "prediction": "paint"}
+{"id": "task1153-38b046312fbf4d09bd1c37707395d95c", "Task": "task1153_bard_analogical_reasoning_affordance", "Contributors": "['Arjun Ashok']", "Source": ["bard"], "URL": ["https://github.com/NancyFulda/BYU-Analogical-Reasoning-Dataset"], "Categories": ["Word Analogy"], "Reasoning": ["Relational Reasoning", "Commonsense Reasoning", "Analogical Reasoning"], "Definition": ["Two analogies that signify affordances are given in the form \"A : B. C : ?\". Affordance is the possibility of an action being done on an object, for example book is an affordance of writing. The phrase \"A : B\" implies that B is an affordance of A. Your task is to replace the question mark (?) with the appropriate affordance of the given action C, following the \"A : B\" relation. Your answer should be a single object without further explanation."], "Positive Examples": [{"input": "cure : disease. swing : ?", "output": "sword", "explanation": "The given analogy implies that diseases can be cured - an affordance relation. Hence, the appropriate answer for swing is sword, since swords can be swung."}, {"input": "write : book. swear : ?", "output": "oath", "explanation": "The given analogy implies that books can be written - an affordance relation. Hence, the appropriate answer for swear is oath, since oaths can be sworn."}, {"input": "sing : song. drive : ?", "output": "car", "explanation": "The given analogy implies that songs can be sung - an affordance relation. Hence, the appropriate answer for drive is car, since cars can be driven."}], "Negative Examples": [{"input": "ride : horse. attack : ?", "output": "car", "explanation": "The given analogy implies that horses can be ridden - an affordance relation. But, car is not an appropriate answer for attack, since cars cannot be attacked."}, {"input": "swear : oath. drop : ?", "output": "fall", "explanation": "The given analogy implies that oaths can be sworn - an affordance relation. But, fall is not an appropriate answer for drop, since this models the causation relation."}, {"input": "drink : water. give : ?", "output": "enemy", "explanation": "The given analogy implies that water can be drunk - an affordance relation. But, enemy is not an appropriate answer for give"}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Commonsense"], "Instance": {"id": "task1153-38b046312fbf4d09bd1c37707395d95c", "input": "open : door. write : ?", "output": ["letter", "book"]}, "Instance License": ["Apache 2.0"], "prediction": "a letter"}
+{"id": "task1153-9891b804933e4da6a495170a0d6e48d5", "Task": "task1153_bard_analogical_reasoning_affordance", "Contributors": "['Arjun Ashok']", "Source": ["bard"], "URL": ["https://github.com/NancyFulda/BYU-Analogical-Reasoning-Dataset"], "Categories": ["Word Analogy"], "Reasoning": ["Relational Reasoning", "Commonsense Reasoning", "Analogical Reasoning"], "Definition": ["Two analogies that signify affordances are given in the form \"A : B. C : ?\". Affordance is the possibility of an action being done on an object, for example book is an affordance of writing. The phrase \"A : B\" implies that B is an affordance of A. Your task is to replace the question mark (?) with the appropriate affordance of the given action C, following the \"A : B\" relation. Your answer should be a single object without further explanation."], "Positive Examples": [{"input": "cure : disease. swing : ?", "output": "sword", "explanation": "The given analogy implies that diseases can be cured - an affordance relation. Hence, the appropriate answer for swing is sword, since swords can be swung."}, {"input": "write : book. swear : ?", "output": "oath", "explanation": "The given analogy implies that books can be written - an affordance relation. Hence, the appropriate answer for swear is oath, since oaths can be sworn."}, {"input": "sing : song. drive : ?", "output": "car", "explanation": "The given analogy implies that songs can be sung - an affordance relation. Hence, the appropriate answer for drive is car, since cars can be driven."}], "Negative Examples": [{"input": "ride : horse. attack : ?", "output": "car", "explanation": "The given analogy implies that horses can be ridden - an affordance relation. But, car is not an appropriate answer for attack, since cars cannot be attacked."}, {"input": "swear : oath. drop : ?", "output": "fall", "explanation": "The given analogy implies that oaths can be sworn - an affordance relation. But, fall is not an appropriate answer for drop, since this models the causation relation."}, {"input": "drink : water. give : ?", "output": "enemy", "explanation": "The given analogy implies that water can be drunk - an affordance relation. But, enemy is not an appropriate answer for give"}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Commonsense"], "Instance": {"id": "task1153-9891b804933e4da6a495170a0d6e48d5", "input": "hunt : goose. give : ?", "output": ["gift"]}, "Instance License": ["Apache 2.0"], "prediction": "acorn"}
+{"id": "task1153-e63cb4c989cd4189973c7f45e9f2c0ae", "Task": "task1153_bard_analogical_reasoning_affordance", "Contributors": "['Arjun Ashok']", "Source": ["bard"], "URL": ["https://github.com/NancyFulda/BYU-Analogical-Reasoning-Dataset"], "Categories": ["Word Analogy"], "Reasoning": ["Relational Reasoning", "Commonsense Reasoning", "Analogical Reasoning"], "Definition": ["Two analogies that signify affordances are given in the form \"A : B. C : ?\". Affordance is the possibility of an action being done on an object, for example book is an affordance of writing. The phrase \"A : B\" implies that B is an affordance of A. Your task is to replace the question mark (?) with the appropriate affordance of the given action C, following the \"A : B\" relation. Your answer should be a single object without further explanation."], "Positive Examples": [{"input": "cure : disease. swing : ?", "output": "sword", "explanation": "The given analogy implies that diseases can be cured - an affordance relation. Hence, the appropriate answer for swing is sword, since swords can be swung."}, {"input": "write : book. swear : ?", "output": "oath", "explanation": "The given analogy implies that books can be written - an affordance relation. Hence, the appropriate answer for swear is oath, since oaths can be sworn."}, {"input": "sing : song. drive : ?", "output": "car", "explanation": "The given analogy implies that songs can be sung - an affordance relation. Hence, the appropriate answer for drive is car, since cars can be driven."}], "Negative Examples": [{"input": "ride : horse. attack : ?", "output": "car", "explanation": "The given analogy implies that horses can be ridden - an affordance relation. But, car is not an appropriate answer for attack, since cars cannot be attacked."}, {"input": "swear : oath. drop : ?", "output": "fall", "explanation": "The given analogy implies that oaths can be sworn - an affordance relation. But, fall is not an appropriate answer for drop, since this models the causation relation."}, {"input": "drink : water. give : ?", "output": "enemy", "explanation": "The given analogy implies that water can be drunk - an affordance relation. But, enemy is not an appropriate answer for give"}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Commonsense"], "Instance": {"id": "task1153-e63cb4c989cd4189973c7f45e9f2c0ae", "input": "swat : fly. chase : ?", "output": ["thief"]}, "Instance License": ["Apache 2.0"], "prediction": "tiger"}
+{"id": "task393-efca5ba474e447d3802989cdb634d274", "Task": "task393_plausible_result_generation", "Contributors": "['Pegah Alipoormolabashi']", "Source": ["cod3s"], "URL": ["https://aclanthology.org/2020.emnlp-main.421.pdf"], "Categories": ["Cause Effect Classification"], "Reasoning": ["Causal Reasoning", "Textual Entailment"], "Definition": ["In this task, you will be given a sentence, followed by \", so\". You should complete the given text with another sentence, such that the whole text is plausible. The sentence you enter must be a likely result of the given sentence."], "Positive Examples": [{"input": "The woman went to the bank, so ", "output": "she will be out with some cash on her", "explanation": "The answer is a likely result of the sentence in the question."}, {"input": "They government banned abortions, so ", "output": "many unwanted children will be born", "explanation": "The answer is a likely result of the sentence in the question."}], "Negative Examples": [{"input": "The woman went to the bank, so ", "output": "she talked to the man.", "explanation": "This sentence is not a likely result of the question, so it's not a good completion."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Commonsense"], "Instance": {"id": "task393-efca5ba474e447d3802989cdb634d274", "input": "The cowgirl threw her lasso towards the horse, so ", "output": ["it worked out pretty well", "she was able to catch it quickly", "the lasso grabbed onto the horse", "the horse trotted into the barn", "I hopped on the horse"]}, "Instance License": ["MIT"], "prediction": "he threw it at the girl."}
+{"id": "task393-4759913505b2406e84bc998d70099787", "Task": "task393_plausible_result_generation", "Contributors": "['Pegah Alipoormolabashi']", "Source": ["cod3s"], "URL": ["https://aclanthology.org/2020.emnlp-main.421.pdf"], "Categories": ["Cause Effect Classification"], "Reasoning": ["Causal Reasoning", "Textual Entailment"], "Definition": ["In this task, you will be given a sentence, followed by \", so\". You should complete the given text with another sentence, such that the whole text is plausible. The sentence you enter must be a likely result of the given sentence."], "Positive Examples": [{"input": "The woman went to the bank, so ", "output": "she will be out with some cash on her", "explanation": "The answer is a likely result of the sentence in the question."}, {"input": "They government banned abortions, so ", "output": "many unwanted children will be born", "explanation": "The answer is a likely result of the sentence in the question."}], "Negative Examples": [{"input": "The woman went to the bank, so ", "output": "she talked to the man.", "explanation": "This sentence is not a likely result of the question, so it's not a good completion."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Commonsense"], "Instance": {"id": "task393-4759913505b2406e84bc998d70099787", "input": "The baby was wailing in his crib, so ", "output": ["I took him to the doctor", "the mother picked up the baby", "I went to check on him", "I got up to check on him", "we had to get up early", "I decided to take him to the doctor"]}, "Instance License": ["MIT"], "prediction": "he was asleep."}
+{"id": "task393-9b36ce67e210468fb558f4775227c877", "Task": "task393_plausible_result_generation", "Contributors": "['Pegah Alipoormolabashi']", "Source": ["cod3s"], "URL": ["https://aclanthology.org/2020.emnlp-main.421.pdf"], "Categories": ["Cause Effect Classification"], "Reasoning": ["Causal Reasoning", "Textual Entailment"], "Definition": ["In this task, you will be given a sentence, followed by \", so\". You should complete the given text with another sentence, such that the whole text is plausible. The sentence you enter must be a likely result of the given sentence."], "Positive Examples": [{"input": "The woman went to the bank, so ", "output": "she will be out with some cash on her", "explanation": "The answer is a likely result of the sentence in the question."}, {"input": "They government banned abortions, so ", "output": "many unwanted children will be born", "explanation": "The answer is a likely result of the sentence in the question."}], "Negative Examples": [{"input": "The woman went to the bank, so ", "output": "she talked to the man.", "explanation": "This sentence is not a likely result of the question, so it's not a good completion."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Commonsense"], "Instance": {"id": "task393-9b36ce67e210468fb558f4775227c877", "input": "The mirror in the bathroom fogged up, so ", "output": ["I could not see what was going on in the bathroom", "she couldn't see what was going on", "I couldn't see what was going on", "she turned to the other side of the room", "it was hard to tell what was going on", "I turned around to see what was going on", "I could not see what was going on", "I couldn't see what I was doing", "I could not see anything"]}, "Instance License": ["MIT"], "prediction": "it was difficult to see."}
+{"id": "task393-e686a173451d47ddaa56fc0797bfd05b", "Task": "task393_plausible_result_generation", "Contributors": "['Pegah Alipoormolabashi']", "Source": ["cod3s"], "URL": ["https://aclanthology.org/2020.emnlp-main.421.pdf"], "Categories": ["Cause Effect Classification"], "Reasoning": ["Causal Reasoning", "Textual Entailment"], "Definition": ["In this task, you will be given a sentence, followed by \", so\". You should complete the given text with another sentence, such that the whole text is plausible. The sentence you enter must be a likely result of the given sentence."], "Positive Examples": [{"input": "The woman went to the bank, so ", "output": "she will be out with some cash on her", "explanation": "The answer is a likely result of the sentence in the question."}, {"input": "They government banned abortions, so ", "output": "many unwanted children will be born", "explanation": "The answer is a likely result of the sentence in the question."}], "Negative Examples": [{"input": "The woman went to the bank, so ", "output": "she talked to the man.", "explanation": "This sentence is not a likely result of the question, so it's not a good completion."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Commonsense"], "Instance": {"id": "task393-e686a173451d47ddaa56fc0797bfd05b", "input": "The tenant misplaced his keys to his apartment, so ", "output": ["there was nothing he could do", "he had to leave the door open", "we had to take him home", "he went to his friend's house", "he took matters into his own hands", "he had to get a new one", "he went to his neighbor's house", "he couldn't call for help", "he couldn't get back to him", "he did the next best thing", "he couldn't go back to his home", "he left the door open", "his landlord repaired the door", "his landlord unlocked the door"]}, "Instance License": ["MIT"], "prediction": "he will have to go to the police station."}
+{"id": "task393-d11795119a7c4d21b49131cba46220cf", "Task": "task393_plausible_result_generation", "Contributors": "['Pegah Alipoormolabashi']", "Source": ["cod3s"], "URL": ["https://aclanthology.org/2020.emnlp-main.421.pdf"], "Categories": ["Cause Effect Classification"], "Reasoning": ["Causal Reasoning", "Textual Entailment"], "Definition": ["In this task, you will be given a sentence, followed by \", so\". You should complete the given text with another sentence, such that the whole text is plausible. The sentence you enter must be a likely result of the given sentence."], "Positive Examples": [{"input": "The woman went to the bank, so ", "output": "she will be out with some cash on her", "explanation": "The answer is a likely result of the sentence in the question."}, {"input": "They government banned abortions, so ", "output": "many unwanted children will be born", "explanation": "The answer is a likely result of the sentence in the question."}], "Negative Examples": [{"input": "The woman went to the bank, so ", "output": "she talked to the man.", "explanation": "This sentence is not a likely result of the question, so it's not a good completion."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Commonsense"], "Instance": {"id": "task393-d11795119a7c4d21b49131cba46220cf", "input": "The clock stopped ticking, so ", "output": ["I could get a good night's sleep", "I gave up and went to sleep", "we had to act fast", "i took extra time to get ready", "I was able to get a good look at the clock", "I went back to sleep", "I don't know what the problem was", "I thought it was time", "I could get my sleep", "I don't know what was going on", "I had to check it out", "I decided it was time", "I could get a good look at what was going on", "I called it a day", "the clock showed the wrong time", "I decided to try again"]}, "Instance License": ["MIT"], "prediction": "he was late."}
+{"id": "task879-cc88a1c6d5da4195b95af5d1ba30ea28", "Task": "task879_schema_guided_dstc8_classification", "Contributors": "['Subba Raja Kashyap Saligrama']", "Source": ["schema_guided_dstc8"], "URL": ["https://huggingface.co/datasets/schema_guided_dstc8"], "Categories": ["Dialogue Act Recognition"], "Reasoning": ["Reasoning on Social Interactions"], "Definition": ["You are given a sentence from a conversation between a human and a virtual assistant. Your task is to identify whether the sentence is a question or not. Answer with Yes or No."], "Positive Examples": [{"input": "I am feeling hungry so I would like to find a place to eat.", "output": "No", "explanation": "The user is informing the intent, but not asking any question here"}, {"input": "Do you have a specific which you want the eating place to be located at?", "output": "Yes", "explanation": "The system is asking the user for location preferences"}, {"input": "How would you like Bazille restaurant which is situated in San Jose.", "output": "No", "explanation": "Although there is 'How' phrase in the sentence, the system is just offering information about a restaurant and not asking any details from user"}], "Negative Examples": [{"input": "Is there some other restaurant which you can suggest?", "output": "No", "explanation": "The user is asking for other alternatives. So, its a question and output should be 1"}, {"input": "Can you please confirm that you want to book a table for 2 at 11:30 am at the Bird Dog restaurant in Palo Alto for today.", "output": "No", "explanation": "The system is asking the user to confirm the suggested booking. So, its a question and output should be 1"}, {"input": "Ok, Find me another restaurant", "output": "Yes", "explanation": "The user is suggesting to look for another restaurant. So, its not a question and output should be 0"}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Dialogue"], "Instance": {"id": "task879-cc88a1c6d5da4195b95af5d1ba30ea28", "input": "The restaurant is located in Burlingame.", "output": ["No"]}, "Instance License": ["CC BY-SA 4.0"], "prediction": "No"}
+{"id": "task879-e1f8539c5a2a4b92b410d45922a55900", "Task": "task879_schema_guided_dstc8_classification", "Contributors": "['Subba Raja Kashyap Saligrama']", "Source": ["schema_guided_dstc8"], "URL": ["https://huggingface.co/datasets/schema_guided_dstc8"], "Categories": ["Dialogue Act Recognition"], "Reasoning": ["Reasoning on Social Interactions"], "Definition": ["You are given a sentence from a conversation between a human and a virtual assistant. Your task is to identify whether the sentence is a question or not. Answer with Yes or No."], "Positive Examples": [{"input": "I am feeling hungry so I would like to find a place to eat.", "output": "No", "explanation": "The user is informing the intent, but not asking any question here"}, {"input": "Do you have a specific which you want the eating place to be located at?", "output": "Yes", "explanation": "The system is asking the user for location preferences"}, {"input": "How would you like Bazille restaurant which is situated in San Jose.", "output": "No", "explanation": "Although there is 'How' phrase in the sentence, the system is just offering information about a restaurant and not asking any details from user"}], "Negative Examples": [{"input": "Is there some other restaurant which you can suggest?", "output": "No", "explanation": "The user is asking for other alternatives. So, its a question and output should be 1"}, {"input": "Can you please confirm that you want to book a table for 2 at 11:30 am at the Bird Dog restaurant in Palo Alto for today.", "output": "No", "explanation": "The system is asking the user to confirm the suggested booking. So, its a question and output should be 1"}, {"input": "Ok, Find me another restaurant", "output": "Yes", "explanation": "The user is suggesting to look for another restaurant. So, its not a question and output should be 0"}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Dialogue"], "Instance": {"id": "task879-e1f8539c5a2a4b92b410d45922a55900", "input": "The reservation is for what time?", "output": ["Yes"]}, "Instance License": ["CC BY-SA 4.0"], "prediction": "Yes"}
+{"id": "task879-342891675ff7499386d2236fc7641a61", "Task": "task879_schema_guided_dstc8_classification", "Contributors": "['Subba Raja Kashyap Saligrama']", "Source": ["schema_guided_dstc8"], "URL": ["https://huggingface.co/datasets/schema_guided_dstc8"], "Categories": ["Dialogue Act Recognition"], "Reasoning": ["Reasoning on Social Interactions"], "Definition": ["You are given a sentence from a conversation between a human and a virtual assistant. Your task is to identify whether the sentence is a question or not. Answer with Yes or No."], "Positive Examples": [{"input": "I am feeling hungry so I would like to find a place to eat.", "output": "No", "explanation": "The user is informing the intent, but not asking any question here"}, {"input": "Do you have a specific which you want the eating place to be located at?", "output": "Yes", "explanation": "The system is asking the user for location preferences"}, {"input": "How would you like Bazille restaurant which is situated in San Jose.", "output": "No", "explanation": "Although there is 'How' phrase in the sentence, the system is just offering information about a restaurant and not asking any details from user"}], "Negative Examples": [{"input": "Is there some other restaurant which you can suggest?", "output": "No", "explanation": "The user is asking for other alternatives. So, its a question and output should be 1"}, {"input": "Can you please confirm that you want to book a table for 2 at 11:30 am at the Bird Dog restaurant in Palo Alto for today.", "output": "No", "explanation": "The system is asking the user to confirm the suggested booking. So, its a question and output should be 1"}, {"input": "Ok, Find me another restaurant", "output": "Yes", "explanation": "The user is suggesting to look for another restaurant. So, its not a question and output should be 0"}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Dialogue"], "Instance": {"id": "task879-342891675ff7499386d2236fc7641a61", "input": "Yes that is correct. Are the prices inexpensive and do they have live music?", "output": ["Yes"]}, "Instance License": ["CC BY-SA 4.0"], "prediction": "Yes"}
+{"id": "task879-d225764d8c4e456a87ff93733a7006e6", "Task": "task879_schema_guided_dstc8_classification", "Contributors": "['Subba Raja Kashyap Saligrama']", "Source": ["schema_guided_dstc8"], "URL": ["https://huggingface.co/datasets/schema_guided_dstc8"], "Categories": ["Dialogue Act Recognition"], "Reasoning": ["Reasoning on Social Interactions"], "Definition": ["You are given a sentence from a conversation between a human and a virtual assistant. Your task is to identify whether the sentence is a question or not. Answer with Yes or No."], "Positive Examples": [{"input": "I am feeling hungry so I would like to find a place to eat.", "output": "No", "explanation": "The user is informing the intent, but not asking any question here"}, {"input": "Do you have a specific which you want the eating place to be located at?", "output": "Yes", "explanation": "The system is asking the user for location preferences"}, {"input": "How would you like Bazille restaurant which is situated in San Jose.", "output": "No", "explanation": "Although there is 'How' phrase in the sentence, the system is just offering information about a restaurant and not asking any details from user"}], "Negative Examples": [{"input": "Is there some other restaurant which you can suggest?", "output": "No", "explanation": "The user is asking for other alternatives. So, its a question and output should be 1"}, {"input": "Can you please confirm that you want to book a table for 2 at 11:30 am at the Bird Dog restaurant in Palo Alto for today.", "output": "No", "explanation": "The system is asking the user to confirm the suggested booking. So, its a question and output should be 1"}, {"input": "Ok, Find me another restaurant", "output": "Yes", "explanation": "The user is suggesting to look for another restaurant. So, its not a question and output should be 0"}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Dialogue"], "Instance": {"id": "task879-d225764d8c4e456a87ff93733a7006e6", "input": "No, don't bother. I'm set.", "output": ["No"]}, "Instance License": ["CC BY-SA 4.0"], "prediction": "No"}
+{"id": "task879-c057b9ef878d4e4785936bbe36588a4f", "Task": "task879_schema_guided_dstc8_classification", "Contributors": "['Subba Raja Kashyap Saligrama']", "Source": ["schema_guided_dstc8"], "URL": ["https://huggingface.co/datasets/schema_guided_dstc8"], "Categories": ["Dialogue Act Recognition"], "Reasoning": ["Reasoning on Social Interactions"], "Definition": ["You are given a sentence from a conversation between a human and a virtual assistant. Your task is to identify whether the sentence is a question or not. Answer with Yes or No."], "Positive Examples": [{"input": "I am feeling hungry so I would like to find a place to eat.", "output": "No", "explanation": "The user is informing the intent, but not asking any question here"}, {"input": "Do you have a specific which you want the eating place to be located at?", "output": "Yes", "explanation": "The system is asking the user for location preferences"}, {"input": "How would you like Bazille restaurant which is situated in San Jose.", "output": "No", "explanation": "Although there is 'How' phrase in the sentence, the system is just offering information about a restaurant and not asking any details from user"}], "Negative Examples": [{"input": "Is there some other restaurant which you can suggest?", "output": "No", "explanation": "The user is asking for other alternatives. So, its a question and output should be 1"}, {"input": "Can you please confirm that you want to book a table for 2 at 11:30 am at the Bird Dog restaurant in Palo Alto for today.", "output": "No", "explanation": "The system is asking the user to confirm the suggested booking. So, its a question and output should be 1"}, {"input": "Ok, Find me another restaurant", "output": "Yes", "explanation": "The user is suggesting to look for another restaurant. So, its not a question and output should be 0"}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Dialogue"], "Instance": {"id": "task879-c057b9ef878d4e4785936bbe36588a4f", "input": "Yes, the information is correct. Is the restaurant very expensive? Do they have live music?", "output": ["Yes"]}, "Instance License": ["CC BY-SA 4.0"], "prediction": "No"}
+{"id": "task613-0e463643293041158dc200d4b7685f7a", "Task": "task613_politifact_text_generation", "Contributors": "['Ishan Purohit']", "Source": ["liar"], "URL": ["https://huggingface.co/datasets/liar"], "Categories": ["Keyword Tagging"], "Reasoning": ["Reasoning on Social Interactions"], "Definition": ["In this task, you are given a statement spoken by a politician in natural language. Your task is to generate the subject of the discussion for the given statement. The subject generated is not necessarily a part of the given input. Your answer should contain one or more words."], "Positive Examples": [{"input": "Says the Annies List political group supports third-trimester abortions on demand.", "output": "abortion", "explanation": "It's a correct subject of the statement because it talks about a political group supporting demans of abortions."}, {"input": "In this last election in November, ... 63 percent of the American people chose not to vote, ... 80 percent of young people, (and) 75 percent of low-income workers chose not to vote.", "output": "election", "explanation": "It's a correct subject of the statement because it talks about the percentage of different kinds of people who didn't choose to vote."}, {"input": "The nuclear test conducted in our nation this time is the Earth's 2,054th nuclear test. The five permanent members of the U.N. Security Council have conducted 99.99 percent of the total nuclear tests.", "output": "military", "explanation": "It's a correct subject of the statement because it talks about nuclear test that's been conducted in the nation. Other subjects like \"nuclear weapon\" would also be correct."}], "Negative Examples": [{"input": "We just had the best year for the auto industry in America in history.", "output": "election", "explanation": "It's a wrong subject of the statement. Because the statement talks about the success of an auto industry that year. So, the correct subject would be: economy."}, {"input": "We cut business taxes so today 70 percent of our businesses don't pay a business tax.", "output": "health care", "explanation": "It's a wrong subject of the statement. Because the statement talks about the business not paying taxes. So, the correct subject would be: taxes."}, {"input": "Says a U.S. Supreme Court justice suggested that some U.S. cases will be decided based on South African law.", "output": "military", "explanation": "It's a wrong subject of the statement. Because the statement talks about the suggestion of the U.S. Supreme Court. So, correct subjects would be: legal issues, or supreme court."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Government and Politics"], "Instance": {"id": "task613-0e463643293041158dc200d4b7685f7a", "input": "From 2008 to 2011, the pages in the conforming bills have gone from 400 pages to 2,200.", "output": ["state-budget"]}, "Instance License": ["Unknown"], "prediction": "conforming"}
+{"id": "task613-3e9538291d264825aa0db5c8017ee40e", "Task": "task613_politifact_text_generation", "Contributors": "['Ishan Purohit']", "Source": ["liar"], "URL": ["https://huggingface.co/datasets/liar"], "Categories": ["Keyword Tagging"], "Reasoning": ["Reasoning on Social Interactions"], "Definition": ["In this task, you are given a statement spoken by a politician in natural language. Your task is to generate the subject of the discussion for the given statement. The subject generated is not necessarily a part of the given input. Your answer should contain one or more words."], "Positive Examples": [{"input": "Says the Annies List political group supports third-trimester abortions on demand.", "output": "abortion", "explanation": "It's a correct subject of the statement because it talks about a political group supporting demans of abortions."}, {"input": "In this last election in November, ... 63 percent of the American people chose not to vote, ... 80 percent of young people, (and) 75 percent of low-income workers chose not to vote.", "output": "election", "explanation": "It's a correct subject of the statement because it talks about the percentage of different kinds of people who didn't choose to vote."}, {"input": "The nuclear test conducted in our nation this time is the Earth's 2,054th nuclear test. The five permanent members of the U.N. Security Council have conducted 99.99 percent of the total nuclear tests.", "output": "military", "explanation": "It's a correct subject of the statement because it talks about nuclear test that's been conducted in the nation. Other subjects like \"nuclear weapon\" would also be correct."}], "Negative Examples": [{"input": "We just had the best year for the auto industry in America in history.", "output": "election", "explanation": "It's a wrong subject of the statement. Because the statement talks about the success of an auto industry that year. So, the correct subject would be: economy."}, {"input": "We cut business taxes so today 70 percent of our businesses don't pay a business tax.", "output": "health care", "explanation": "It's a wrong subject of the statement. Because the statement talks about the business not paying taxes. So, the correct subject would be: taxes."}, {"input": "Says a U.S. Supreme Court justice suggested that some U.S. cases will be decided based on South African law.", "output": "military", "explanation": "It's a wrong subject of the statement. Because the statement talks about the suggestion of the U.S. Supreme Court. So, correct subjects would be: legal issues, or supreme court."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Government and Politics"], "Instance": {"id": "task613-3e9538291d264825aa0db5c8017ee40e", "input": "Says Lloyd Doggett voted for the health care, stimulus and cap-and-trade bills.", "output": ["cap-and-trade", "climate-change", "economy", "health-care", "message-machine"]}, "Instance License": ["Unknown"], "prediction": "health care"}
+{"id": "task613-91329fbb87d24ce9a57445bc1ee9870b", "Task": "task613_politifact_text_generation", "Contributors": "['Ishan Purohit']", "Source": ["liar"], "URL": ["https://huggingface.co/datasets/liar"], "Categories": ["Keyword Tagging"], "Reasoning": ["Reasoning on Social Interactions"], "Definition": ["In this task, you are given a statement spoken by a politician in natural language. Your task is to generate the subject of the discussion for the given statement. The subject generated is not necessarily a part of the given input. Your answer should contain one or more words."], "Positive Examples": [{"input": "Says the Annies List political group supports third-trimester abortions on demand.", "output": "abortion", "explanation": "It's a correct subject of the statement because it talks about a political group supporting demans of abortions."}, {"input": "In this last election in November, ... 63 percent of the American people chose not to vote, ... 80 percent of young people, (and) 75 percent of low-income workers chose not to vote.", "output": "election", "explanation": "It's a correct subject of the statement because it talks about the percentage of different kinds of people who didn't choose to vote."}, {"input": "The nuclear test conducted in our nation this time is the Earth's 2,054th nuclear test. The five permanent members of the U.N. Security Council have conducted 99.99 percent of the total nuclear tests.", "output": "military", "explanation": "It's a correct subject of the statement because it talks about nuclear test that's been conducted in the nation. Other subjects like \"nuclear weapon\" would also be correct."}], "Negative Examples": [{"input": "We just had the best year for the auto industry in America in history.", "output": "election", "explanation": "It's a wrong subject of the statement. Because the statement talks about the success of an auto industry that year. So, the correct subject would be: economy."}, {"input": "We cut business taxes so today 70 percent of our businesses don't pay a business tax.", "output": "health care", "explanation": "It's a wrong subject of the statement. Because the statement talks about the business not paying taxes. So, the correct subject would be: taxes."}, {"input": "Says a U.S. Supreme Court justice suggested that some U.S. cases will be decided based on South African law.", "output": "military", "explanation": "It's a wrong subject of the statement. Because the statement talks about the suggestion of the U.S. Supreme Court. So, correct subjects would be: legal issues, or supreme court."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Government and Politics"], "Instance": {"id": "task613-91329fbb87d24ce9a57445bc1ee9870b", "input": "Have the suburbs been inundated with former residents of Atlanta housing projects? Absolutely not.", "output": ["housing"]}, "Instance License": ["Unknown"], "prediction": "Atlanta housing projects"}
+{"id": "task613-f267b7443dca412fabd7c49c7357ea87", "Task": "task613_politifact_text_generation", "Contributors": "['Ishan Purohit']", "Source": ["liar"], "URL": ["https://huggingface.co/datasets/liar"], "Categories": ["Keyword Tagging"], "Reasoning": ["Reasoning on Social Interactions"], "Definition": ["In this task, you are given a statement spoken by a politician in natural language. Your task is to generate the subject of the discussion for the given statement. The subject generated is not necessarily a part of the given input. Your answer should contain one or more words."], "Positive Examples": [{"input": "Says the Annies List political group supports third-trimester abortions on demand.", "output": "abortion", "explanation": "It's a correct subject of the statement because it talks about a political group supporting demans of abortions."}, {"input": "In this last election in November, ... 63 percent of the American people chose not to vote, ... 80 percent of young people, (and) 75 percent of low-income workers chose not to vote.", "output": "election", "explanation": "It's a correct subject of the statement because it talks about the percentage of different kinds of people who didn't choose to vote."}, {"input": "The nuclear test conducted in our nation this time is the Earth's 2,054th nuclear test. The five permanent members of the U.N. Security Council have conducted 99.99 percent of the total nuclear tests.", "output": "military", "explanation": "It's a correct subject of the statement because it talks about nuclear test that's been conducted in the nation. Other subjects like \"nuclear weapon\" would also be correct."}], "Negative Examples": [{"input": "We just had the best year for the auto industry in America in history.", "output": "election", "explanation": "It's a wrong subject of the statement. Because the statement talks about the success of an auto industry that year. So, the correct subject would be: economy."}, {"input": "We cut business taxes so today 70 percent of our businesses don't pay a business tax.", "output": "health care", "explanation": "It's a wrong subject of the statement. Because the statement talks about the business not paying taxes. So, the correct subject would be: taxes."}, {"input": "Says a U.S. Supreme Court justice suggested that some U.S. cases will be decided based on South African law.", "output": "military", "explanation": "It's a wrong subject of the statement. Because the statement talks about the suggestion of the U.S. Supreme Court. So, correct subjects would be: legal issues, or supreme court."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Government and Politics"], "Instance": {"id": "task613-f267b7443dca412fabd7c49c7357ea87", "input": "My opponent was on both the city of Chicago payroll and the state of Illinois payroll simultaneously, taking full salary, funding her full pension benefits both as a city worker and as a state worker for 10 years.", "output": ["pensions"]}, "Instance License": ["Unknown"], "prediction": "state"}
+{"id": "task613-8526e765ec894a1da9e61503ee679abc", "Task": "task613_politifact_text_generation", "Contributors": "['Ishan Purohit']", "Source": ["liar"], "URL": ["https://huggingface.co/datasets/liar"], "Categories": ["Keyword Tagging"], "Reasoning": ["Reasoning on Social Interactions"], "Definition": ["In this task, you are given a statement spoken by a politician in natural language. Your task is to generate the subject of the discussion for the given statement. The subject generated is not necessarily a part of the given input. Your answer should contain one or more words."], "Positive Examples": [{"input": "Says the Annies List political group supports third-trimester abortions on demand.", "output": "abortion", "explanation": "It's a correct subject of the statement because it talks about a political group supporting demans of abortions."}, {"input": "In this last election in November, ... 63 percent of the American people chose not to vote, ... 80 percent of young people, (and) 75 percent of low-income workers chose not to vote.", "output": "election", "explanation": "It's a correct subject of the statement because it talks about the percentage of different kinds of people who didn't choose to vote."}, {"input": "The nuclear test conducted in our nation this time is the Earth's 2,054th nuclear test. The five permanent members of the U.N. Security Council have conducted 99.99 percent of the total nuclear tests.", "output": "military", "explanation": "It's a correct subject of the statement because it talks about nuclear test that's been conducted in the nation. Other subjects like \"nuclear weapon\" would also be correct."}], "Negative Examples": [{"input": "We just had the best year for the auto industry in America in history.", "output": "election", "explanation": "It's a wrong subject of the statement. Because the statement talks about the success of an auto industry that year. So, the correct subject would be: economy."}, {"input": "We cut business taxes so today 70 percent of our businesses don't pay a business tax.", "output": "health care", "explanation": "It's a wrong subject of the statement. Because the statement talks about the business not paying taxes. So, the correct subject would be: taxes."}, {"input": "Says a U.S. Supreme Court justice suggested that some U.S. cases will be decided based on South African law.", "output": "military", "explanation": "It's a wrong subject of the statement. Because the statement talks about the suggestion of the U.S. Supreme Court. So, correct subjects would be: legal issues, or supreme court."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Government and Politics"], "Instance": {"id": "task613-8526e765ec894a1da9e61503ee679abc", "input": "Last year the (Medicaid Fraud Control Unit) in Virginia alone recovered over $200 million!", "output": ["medicaid"]}, "Instance License": ["Unknown"], "prediction": "recovery"}
+{"id": "task219-fa90cf0657994c75a1464694f71a938f", "Task": "task219_rocstories_title_answer_generation", "Contributors": "['Anjana Arunkumar']", "Source": ["rocstories"], "URL": ["https://arxiv.org/pdf/1604.01696.pdf"], "Categories": ["Title Generation"], "Reasoning": ["Deductive Reasoning"], "Definition": ["In this task, you're given five sentences, numbered 1 through 5. Your job is to generate a title for the story that makes complete sense. The title must be short, with less than three words, use simple language, and include the main topic of the story."], "Positive Examples": [{"input": "Sentence 1: Marcus needed clothing for a business casual event. Sentence 2: All of his clothes were either too formal or too casual. Sentence 3: He decided to buy a pair of khakis. Sentence 4: The pair he bought fit him perfectly. Sentence 5: Marcus was happy to have the right clothes for the event.", "output": "Marcus Buys Khakis", "explanation": "Marcus's reasons for buying khakis is established, followed by his purchase of them and reaction."}, {"input": "Sentence 1: Laura loved corn. Sentence 2: So she decided to grow some in her backyard. Sentence 3: The whole process of growing them made her very excited. Sentence 4: But she realized that they required too much water. Sentence 5: So Laura quickly abandoned her corn garden idea.", "output": "Corn", "explanation": "Laura was planning to plant corn, realized the infeasibility of the idea, and then decided against it."}, {"input": "Sentence 1: Larry worked at an accounting firm. Sentence 2: It was a boring job but it paid the bills. Sentence 3: Larry grew tired of doing the same thing every day. Sentence 4: He had the idea to have an office party. Sentence 5: By lunch the whole office had passed out and nothing got done.", "output": "Office Party", "explanation": "Larry's workplace and need for an office party are established, followed by the events of the office party."}, {"input": "Sentence 1: Ben found a frog in the creek. Sentence 2: It was green and slimy. Sentence 3: He took it home and put it in a bucket. Sentence 4: The next day, the frog was gone. Sentence 5: He'd jumped out and escaped!", "output": "The Frog", "explanation": "Ben caught a frog, could not find it the next day and realized it had escaped."}], "Negative Examples": [{"input": "Sentence 1: My grandparents and I were going for a walk. Sentence 2: Suddenly, right in front of us, was a huge moose. Sentence 3: We were walking near some pine trees and turned a corner. Sentence 4: It was so close that it scared us, but they told me not to run. Sentence 5: We all stood still and soon the moose walked away without harm.", "output": "Eggplant Parmesan", "explanation": "The people saw a moose, stopped walking, and allowed it to pass. The title is therefore incorrect."}, {"input": "Sentence 1: Mary sliced the purple eggplant. Sentence 2: Then she breaded each slice carefully before frying them. Sentence 3: She layered each breaded slice into her casserole dish. Sentence 4: Finally, she sprinkled parmesan cheese on top and baked it. Sentence 5: She poured homemade marinara sauce in the dish.", "output": "Up Close", "explanation": "The story describes how eggplant parmesan is made step by step. The title is therefore incorrect."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Narrative", "Story"], "Instance": {"id": "task219-fa90cf0657994c75a1464694f71a938f", "input": "Sentence 1: Jim went fishing in a boat. Sentence 2: Jim caught a catfish. Sentence 3: He dropped the catfish trying to remove the hook. Sentence 4: The the catfish's spine went into Joe's foot. Sentence 5: Joe had to get a tetanus shot.", "output": ["A fish story"]}, "Instance License": ["Unknown"], "prediction": "Jim Drops Catfish"}
+{"id": "task219-dbac7bf821aa4c74bab0d208f19d35f3", "Task": "task219_rocstories_title_answer_generation", "Contributors": "['Anjana Arunkumar']", "Source": ["rocstories"], "URL": ["https://arxiv.org/pdf/1604.01696.pdf"], "Categories": ["Title Generation"], "Reasoning": ["Deductive Reasoning"], "Definition": ["In this task, you're given five sentences, numbered 1 through 5. Your job is to generate a title for the story that makes complete sense. The title must be short, with less than three words, use simple language, and include the main topic of the story."], "Positive Examples": [{"input": "Sentence 1: Marcus needed clothing for a business casual event. Sentence 2: All of his clothes were either too formal or too casual. Sentence 3: He decided to buy a pair of khakis. Sentence 4: The pair he bought fit him perfectly. Sentence 5: Marcus was happy to have the right clothes for the event.", "output": "Marcus Buys Khakis", "explanation": "Marcus's reasons for buying khakis is established, followed by his purchase of them and reaction."}, {"input": "Sentence 1: Laura loved corn. Sentence 2: So she decided to grow some in her backyard. Sentence 3: The whole process of growing them made her very excited. Sentence 4: But she realized that they required too much water. Sentence 5: So Laura quickly abandoned her corn garden idea.", "output": "Corn", "explanation": "Laura was planning to plant corn, realized the infeasibility of the idea, and then decided against it."}, {"input": "Sentence 1: Larry worked at an accounting firm. Sentence 2: It was a boring job but it paid the bills. Sentence 3: Larry grew tired of doing the same thing every day. Sentence 4: He had the idea to have an office party. Sentence 5: By lunch the whole office had passed out and nothing got done.", "output": "Office Party", "explanation": "Larry's workplace and need for an office party are established, followed by the events of the office party."}, {"input": "Sentence 1: Ben found a frog in the creek. Sentence 2: It was green and slimy. Sentence 3: He took it home and put it in a bucket. Sentence 4: The next day, the frog was gone. Sentence 5: He'd jumped out and escaped!", "output": "The Frog", "explanation": "Ben caught a frog, could not find it the next day and realized it had escaped."}], "Negative Examples": [{"input": "Sentence 1: My grandparents and I were going for a walk. Sentence 2: Suddenly, right in front of us, was a huge moose. Sentence 3: We were walking near some pine trees and turned a corner. Sentence 4: It was so close that it scared us, but they told me not to run. Sentence 5: We all stood still and soon the moose walked away without harm.", "output": "Eggplant Parmesan", "explanation": "The people saw a moose, stopped walking, and allowed it to pass. The title is therefore incorrect."}, {"input": "Sentence 1: Mary sliced the purple eggplant. Sentence 2: Then she breaded each slice carefully before frying them. Sentence 3: She layered each breaded slice into her casserole dish. Sentence 4: Finally, she sprinkled parmesan cheese on top and baked it. Sentence 5: She poured homemade marinara sauce in the dish.", "output": "Up Close", "explanation": "The story describes how eggplant parmesan is made step by step. The title is therefore incorrect."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Narrative", "Story"], "Instance": {"id": "task219-dbac7bf821aa4c74bab0d208f19d35f3", "input": "Sentence 1: I went to my cousins house for a party. Sentence 2: Her dog tried to rest on me. Sentence 3: After I tried to moved it away, I started to cough. Sentence 4: The coughing continued until the end of the night. Sentence 5: I had to take pills in order to heal the coughing.", "output": ["Allergies"]}, "Instance License": ["Unknown"], "prediction": "Dog Coughs"}
+{"id": "task219-57a777e9a2f246a38bd41928f4897fa6", "Task": "task219_rocstories_title_answer_generation", "Contributors": "['Anjana Arunkumar']", "Source": ["rocstories"], "URL": ["https://arxiv.org/pdf/1604.01696.pdf"], "Categories": ["Title Generation"], "Reasoning": ["Deductive Reasoning"], "Definition": ["In this task, you're given five sentences, numbered 1 through 5. Your job is to generate a title for the story that makes complete sense. The title must be short, with less than three words, use simple language, and include the main topic of the story."], "Positive Examples": [{"input": "Sentence 1: Marcus needed clothing for a business casual event. Sentence 2: All of his clothes were either too formal or too casual. Sentence 3: He decided to buy a pair of khakis. Sentence 4: The pair he bought fit him perfectly. Sentence 5: Marcus was happy to have the right clothes for the event.", "output": "Marcus Buys Khakis", "explanation": "Marcus's reasons for buying khakis is established, followed by his purchase of them and reaction."}, {"input": "Sentence 1: Laura loved corn. Sentence 2: So she decided to grow some in her backyard. Sentence 3: The whole process of growing them made her very excited. Sentence 4: But she realized that they required too much water. Sentence 5: So Laura quickly abandoned her corn garden idea.", "output": "Corn", "explanation": "Laura was planning to plant corn, realized the infeasibility of the idea, and then decided against it."}, {"input": "Sentence 1: Larry worked at an accounting firm. Sentence 2: It was a boring job but it paid the bills. Sentence 3: Larry grew tired of doing the same thing every day. Sentence 4: He had the idea to have an office party. Sentence 5: By lunch the whole office had passed out and nothing got done.", "output": "Office Party", "explanation": "Larry's workplace and need for an office party are established, followed by the events of the office party."}, {"input": "Sentence 1: Ben found a frog in the creek. Sentence 2: It was green and slimy. Sentence 3: He took it home and put it in a bucket. Sentence 4: The next day, the frog was gone. Sentence 5: He'd jumped out and escaped!", "output": "The Frog", "explanation": "Ben caught a frog, could not find it the next day and realized it had escaped."}], "Negative Examples": [{"input": "Sentence 1: My grandparents and I were going for a walk. Sentence 2: Suddenly, right in front of us, was a huge moose. Sentence 3: We were walking near some pine trees and turned a corner. Sentence 4: It was so close that it scared us, but they told me not to run. Sentence 5: We all stood still and soon the moose walked away without harm.", "output": "Eggplant Parmesan", "explanation": "The people saw a moose, stopped walking, and allowed it to pass. The title is therefore incorrect."}, {"input": "Sentence 1: Mary sliced the purple eggplant. Sentence 2: Then she breaded each slice carefully before frying them. Sentence 3: She layered each breaded slice into her casserole dish. Sentence 4: Finally, she sprinkled parmesan cheese on top and baked it. Sentence 5: She poured homemade marinara sauce in the dish.", "output": "Up Close", "explanation": "The story describes how eggplant parmesan is made step by step. The title is therefore incorrect."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Narrative", "Story"], "Instance": {"id": "task219-57a777e9a2f246a38bd41928f4897fa6", "input": "Sentence 1: Will wasn't sure who he liked in the US presidential election. Sentence 2: Will talked with his friends, who were all undecided as well. Sentence 3: Will watched a debate where the two candidates sparred. Sentence 4: Will decided he liked one candidate's answers over the other's. Sentence 5: Will cast his vote for that candidate.", "output": ["Election Choices"]}, "Instance License": ["Unknown"], "prediction": "Will Votes for the candidate he liked"}
+{"id": "task219-7b20cf02872a4198a27e0d6d38af1c74", "Task": "task219_rocstories_title_answer_generation", "Contributors": "['Anjana Arunkumar']", "Source": ["rocstories"], "URL": ["https://arxiv.org/pdf/1604.01696.pdf"], "Categories": ["Title Generation"], "Reasoning": ["Deductive Reasoning"], "Definition": ["In this task, you're given five sentences, numbered 1 through 5. Your job is to generate a title for the story that makes complete sense. The title must be short, with less than three words, use simple language, and include the main topic of the story."], "Positive Examples": [{"input": "Sentence 1: Marcus needed clothing for a business casual event. Sentence 2: All of his clothes were either too formal or too casual. Sentence 3: He decided to buy a pair of khakis. Sentence 4: The pair he bought fit him perfectly. Sentence 5: Marcus was happy to have the right clothes for the event.", "output": "Marcus Buys Khakis", "explanation": "Marcus's reasons for buying khakis is established, followed by his purchase of them and reaction."}, {"input": "Sentence 1: Laura loved corn. Sentence 2: So she decided to grow some in her backyard. Sentence 3: The whole process of growing them made her very excited. Sentence 4: But she realized that they required too much water. Sentence 5: So Laura quickly abandoned her corn garden idea.", "output": "Corn", "explanation": "Laura was planning to plant corn, realized the infeasibility of the idea, and then decided against it."}, {"input": "Sentence 1: Larry worked at an accounting firm. Sentence 2: It was a boring job but it paid the bills. Sentence 3: Larry grew tired of doing the same thing every day. Sentence 4: He had the idea to have an office party. Sentence 5: By lunch the whole office had passed out and nothing got done.", "output": "Office Party", "explanation": "Larry's workplace and need for an office party are established, followed by the events of the office party."}, {"input": "Sentence 1: Ben found a frog in the creek. Sentence 2: It was green and slimy. Sentence 3: He took it home and put it in a bucket. Sentence 4: The next day, the frog was gone. Sentence 5: He'd jumped out and escaped!", "output": "The Frog", "explanation": "Ben caught a frog, could not find it the next day and realized it had escaped."}], "Negative Examples": [{"input": "Sentence 1: My grandparents and I were going for a walk. Sentence 2: Suddenly, right in front of us, was a huge moose. Sentence 3: We were walking near some pine trees and turned a corner. Sentence 4: It was so close that it scared us, but they told me not to run. Sentence 5: We all stood still and soon the moose walked away without harm.", "output": "Eggplant Parmesan", "explanation": "The people saw a moose, stopped walking, and allowed it to pass. The title is therefore incorrect."}, {"input": "Sentence 1: Mary sliced the purple eggplant. Sentence 2: Then she breaded each slice carefully before frying them. Sentence 3: She layered each breaded slice into her casserole dish. Sentence 4: Finally, she sprinkled parmesan cheese on top and baked it. Sentence 5: She poured homemade marinara sauce in the dish.", "output": "Up Close", "explanation": "The story describes how eggplant parmesan is made step by step. The title is therefore incorrect."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Narrative", "Story"], "Instance": {"id": "task219-7b20cf02872a4198a27e0d6d38af1c74", "input": "Sentence 1: A student ran around the classroom. Sentence 2: He yelled at the other students. Sentence 3: The teacher spoke to him calmly. Sentence 4: He began to calm down. Sentence 5: The student learned a lot.", "output": ["Calm Words"]}, "Instance License": ["Unknown"], "prediction": "Student calms down"}
+{"id": "task219-641314edac624e00ab0b92cfa09d1555", "Task": "task219_rocstories_title_answer_generation", "Contributors": "['Anjana Arunkumar']", "Source": ["rocstories"], "URL": ["https://arxiv.org/pdf/1604.01696.pdf"], "Categories": ["Title Generation"], "Reasoning": ["Deductive Reasoning"], "Definition": ["In this task, you're given five sentences, numbered 1 through 5. Your job is to generate a title for the story that makes complete sense. The title must be short, with less than three words, use simple language, and include the main topic of the story."], "Positive Examples": [{"input": "Sentence 1: Marcus needed clothing for a business casual event. Sentence 2: All of his clothes were either too formal or too casual. Sentence 3: He decided to buy a pair of khakis. Sentence 4: The pair he bought fit him perfectly. Sentence 5: Marcus was happy to have the right clothes for the event.", "output": "Marcus Buys Khakis", "explanation": "Marcus's reasons for buying khakis is established, followed by his purchase of them and reaction."}, {"input": "Sentence 1: Laura loved corn. Sentence 2: So she decided to grow some in her backyard. Sentence 3: The whole process of growing them made her very excited. Sentence 4: But she realized that they required too much water. Sentence 5: So Laura quickly abandoned her corn garden idea.", "output": "Corn", "explanation": "Laura was planning to plant corn, realized the infeasibility of the idea, and then decided against it."}, {"input": "Sentence 1: Larry worked at an accounting firm. Sentence 2: It was a boring job but it paid the bills. Sentence 3: Larry grew tired of doing the same thing every day. Sentence 4: He had the idea to have an office party. Sentence 5: By lunch the whole office had passed out and nothing got done.", "output": "Office Party", "explanation": "Larry's workplace and need for an office party are established, followed by the events of the office party."}, {"input": "Sentence 1: Ben found a frog in the creek. Sentence 2: It was green and slimy. Sentence 3: He took it home and put it in a bucket. Sentence 4: The next day, the frog was gone. Sentence 5: He'd jumped out and escaped!", "output": "The Frog", "explanation": "Ben caught a frog, could not find it the next day and realized it had escaped."}], "Negative Examples": [{"input": "Sentence 1: My grandparents and I were going for a walk. Sentence 2: Suddenly, right in front of us, was a huge moose. Sentence 3: We were walking near some pine trees and turned a corner. Sentence 4: It was so close that it scared us, but they told me not to run. Sentence 5: We all stood still and soon the moose walked away without harm.", "output": "Eggplant Parmesan", "explanation": "The people saw a moose, stopped walking, and allowed it to pass. The title is therefore incorrect."}, {"input": "Sentence 1: Mary sliced the purple eggplant. Sentence 2: Then she breaded each slice carefully before frying them. Sentence 3: She layered each breaded slice into her casserole dish. Sentence 4: Finally, she sprinkled parmesan cheese on top and baked it. Sentence 5: She poured homemade marinara sauce in the dish.", "output": "Up Close", "explanation": "The story describes how eggplant parmesan is made step by step. The title is therefore incorrect."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Narrative", "Story"], "Instance": {"id": "task219-641314edac624e00ab0b92cfa09d1555", "input": "Sentence 1: Grady had a big aquarium. Sentence 2: He filled it with tropical fish. Sentence 3: He loved looking at the tank while he drifted off to sleep. Sentence 4: He had big plans for adding more fish. Sentence 5: The fish had become his favorite entertainment.", "output": ["The Fish"]}, "Instance License": ["Unknown"], "prediction": "Fish"}
+{"id": "task190-ffef5c37fd37460e8e4a60fd53758299", "Task": "task190_snli_classification", "Contributors": "['Anjana Arunkumar']", "Source": ["snli"], "URL": ["https://nlp.stanford.edu/pubs/snli_paper.pdf"], "Categories": ["Textual Entailment"], "Reasoning": ["Textual Entailment"], "Definition": ["In this task, you're given a pair of sentences, sentence 1 and sentence 2. Your job is to choose whether the two sentences clearly agree (entailment)/disagree (contradiction) with each other, or if this cannot be determined (neutral). Your answer must be in the form of the letters E, C, and N respectively."], "Positive Examples": [{"input": "Sentence 1: Jon saw his friend Tom coming out of the grocery store with a bag of fruit. Sentence 2: Tom had been shopping for fruit to give Jon.", "output": "N", "explanation": "Tom's reason for buying the fruit is not known."}, {"input": "Sentence 1: The girl transferred all the flowers from the boquet to a vase. Sentence 2: The flowers will soon wither.", "output": "N", "explanation": "The flowers could be real or plastic."}, {"input": "Sentence 1: The skier was on the edge of the ramp. Sentence 2: The skier was dressed in winter clothes.", "output": "E", "explanation": "Skiing is done in the snow and requires cold climates"}, {"input": "Sentence 1: Joyce likes to eat fruit salad as often as possible. Sentence 2: Joyce loves eating healthy.", "output": "E", "explanation": "Fruit salad is healthy food."}, {"input": "Sentence 1: The boy skated down the staircase railing. Sentence 2: The boy is a newbie skater.", "output": "C", "explanation": "Skating on a railng requires a lot of practice"}, {"input": "Sentence 1: Bertha was selected as captain of her basketball team. Sentence 2: Bertha was not atheletically inclined.", "output": "C", "explanation": "Basketball players are athletic."}], "Negative Examples": [{"input": "Sentence 1: There was an earthquake in San Fransisco. Sentence 2: The earthquake caused a lot of road damage.", "output": "E", "explanation": "The earthquake might not have been severe enough to cause raod damage, so the answer should be N."}, {"input": "Sentence 1: Anna went to the school picnic. Sentence 2: Anna ate with her classmates at the picnic.", "output": "N", "explanation": "Anna's classmates are in her school, and a picnic involves food, so the answer should be E."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Captions -> Image Captions"], "Instance": {"id": "task190-ffef5c37fd37460e8e4a60fd53758299", "input": "Sentence 1: An orchestra practicing their composition. Sentence 2: The orchestra is practicing a very difficult composition.", "output": ["N"]}, "Instance License": ["CC BY-SA 4.0"], "prediction": "N"}
+{"id": "task190-213105a8a3a04fd4bae412d23849d411", "Task": "task190_snli_classification", "Contributors": "['Anjana Arunkumar']", "Source": ["snli"], "URL": ["https://nlp.stanford.edu/pubs/snli_paper.pdf"], "Categories": ["Textual Entailment"], "Reasoning": ["Textual Entailment"], "Definition": ["In this task, you're given a pair of sentences, sentence 1 and sentence 2. Your job is to choose whether the two sentences clearly agree (entailment)/disagree (contradiction) with each other, or if this cannot be determined (neutral). Your answer must be in the form of the letters E, C, and N respectively."], "Positive Examples": [{"input": "Sentence 1: Jon saw his friend Tom coming out of the grocery store with a bag of fruit. Sentence 2: Tom had been shopping for fruit to give Jon.", "output": "N", "explanation": "Tom's reason for buying the fruit is not known."}, {"input": "Sentence 1: The girl transferred all the flowers from the boquet to a vase. Sentence 2: The flowers will soon wither.", "output": "N", "explanation": "The flowers could be real or plastic."}, {"input": "Sentence 1: The skier was on the edge of the ramp. Sentence 2: The skier was dressed in winter clothes.", "output": "E", "explanation": "Skiing is done in the snow and requires cold climates"}, {"input": "Sentence 1: Joyce likes to eat fruit salad as often as possible. Sentence 2: Joyce loves eating healthy.", "output": "E", "explanation": "Fruit salad is healthy food."}, {"input": "Sentence 1: The boy skated down the staircase railing. Sentence 2: The boy is a newbie skater.", "output": "C", "explanation": "Skating on a railng requires a lot of practice"}, {"input": "Sentence 1: Bertha was selected as captain of her basketball team. Sentence 2: Bertha was not atheletically inclined.", "output": "C", "explanation": "Basketball players are athletic."}], "Negative Examples": [{"input": "Sentence 1: There was an earthquake in San Fransisco. Sentence 2: The earthquake caused a lot of road damage.", "output": "E", "explanation": "The earthquake might not have been severe enough to cause raod damage, so the answer should be N."}, {"input": "Sentence 1: Anna went to the school picnic. Sentence 2: Anna ate with her classmates at the picnic.", "output": "N", "explanation": "Anna's classmates are in her school, and a picnic involves food, so the answer should be E."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Captions -> Image Captions"], "Instance": {"id": "task190-213105a8a3a04fd4bae412d23849d411", "input": "Sentence 1: A man crossing a natural stone bridge jumps while in the middle of it. Sentence 2: A Girl was running in the bridge.", "output": ["C"]}, "Instance License": ["CC BY-SA 4.0"], "prediction": "N"}
+{"id": "task190-af92249823164197b3e6a38124a7d7a9", "Task": "task190_snli_classification", "Contributors": "['Anjana Arunkumar']", "Source": ["snli"], "URL": ["https://nlp.stanford.edu/pubs/snli_paper.pdf"], "Categories": ["Textual Entailment"], "Reasoning": ["Textual Entailment"], "Definition": ["In this task, you're given a pair of sentences, sentence 1 and sentence 2. Your job is to choose whether the two sentences clearly agree (entailment)/disagree (contradiction) with each other, or if this cannot be determined (neutral). Your answer must be in the form of the letters E, C, and N respectively."], "Positive Examples": [{"input": "Sentence 1: Jon saw his friend Tom coming out of the grocery store with a bag of fruit. Sentence 2: Tom had been shopping for fruit to give Jon.", "output": "N", "explanation": "Tom's reason for buying the fruit is not known."}, {"input": "Sentence 1: The girl transferred all the flowers from the boquet to a vase. Sentence 2: The flowers will soon wither.", "output": "N", "explanation": "The flowers could be real or plastic."}, {"input": "Sentence 1: The skier was on the edge of the ramp. Sentence 2: The skier was dressed in winter clothes.", "output": "E", "explanation": "Skiing is done in the snow and requires cold climates"}, {"input": "Sentence 1: Joyce likes to eat fruit salad as often as possible. Sentence 2: Joyce loves eating healthy.", "output": "E", "explanation": "Fruit salad is healthy food."}, {"input": "Sentence 1: The boy skated down the staircase railing. Sentence 2: The boy is a newbie skater.", "output": "C", "explanation": "Skating on a railng requires a lot of practice"}, {"input": "Sentence 1: Bertha was selected as captain of her basketball team. Sentence 2: Bertha was not atheletically inclined.", "output": "C", "explanation": "Basketball players are athletic."}], "Negative Examples": [{"input": "Sentence 1: There was an earthquake in San Fransisco. Sentence 2: The earthquake caused a lot of road damage.", "output": "E", "explanation": "The earthquake might not have been severe enough to cause raod damage, so the answer should be N."}, {"input": "Sentence 1: Anna went to the school picnic. Sentence 2: Anna ate with her classmates at the picnic.", "output": "N", "explanation": "Anna's classmates are in her school, and a picnic involves food, so the answer should be E."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Captions -> Image Captions"], "Instance": {"id": "task190-af92249823164197b3e6a38124a7d7a9", "input": "Sentence 1: An older woman sits next to a small girl who is wearing a striped dress. Sentence 2: People on the train can't help but stare-down an homeless man at the end of the coach of the train", "output": ["C"]}, "Instance License": ["CC BY-SA 4.0"], "prediction": "N"}
+{"id": "task190-3197d39a439d4753bb3e1a7427b3c79f", "Task": "task190_snli_classification", "Contributors": "['Anjana Arunkumar']", "Source": ["snli"], "URL": ["https://nlp.stanford.edu/pubs/snli_paper.pdf"], "Categories": ["Textual Entailment"], "Reasoning": ["Textual Entailment"], "Definition": ["In this task, you're given a pair of sentences, sentence 1 and sentence 2. Your job is to choose whether the two sentences clearly agree (entailment)/disagree (contradiction) with each other, or if this cannot be determined (neutral). Your answer must be in the form of the letters E, C, and N respectively."], "Positive Examples": [{"input": "Sentence 1: Jon saw his friend Tom coming out of the grocery store with a bag of fruit. Sentence 2: Tom had been shopping for fruit to give Jon.", "output": "N", "explanation": "Tom's reason for buying the fruit is not known."}, {"input": "Sentence 1: The girl transferred all the flowers from the boquet to a vase. Sentence 2: The flowers will soon wither.", "output": "N", "explanation": "The flowers could be real or plastic."}, {"input": "Sentence 1: The skier was on the edge of the ramp. Sentence 2: The skier was dressed in winter clothes.", "output": "E", "explanation": "Skiing is done in the snow and requires cold climates"}, {"input": "Sentence 1: Joyce likes to eat fruit salad as often as possible. Sentence 2: Joyce loves eating healthy.", "output": "E", "explanation": "Fruit salad is healthy food."}, {"input": "Sentence 1: The boy skated down the staircase railing. Sentence 2: The boy is a newbie skater.", "output": "C", "explanation": "Skating on a railng requires a lot of practice"}, {"input": "Sentence 1: Bertha was selected as captain of her basketball team. Sentence 2: Bertha was not atheletically inclined.", "output": "C", "explanation": "Basketball players are athletic."}], "Negative Examples": [{"input": "Sentence 1: There was an earthquake in San Fransisco. Sentence 2: The earthquake caused a lot of road damage.", "output": "E", "explanation": "The earthquake might not have been severe enough to cause raod damage, so the answer should be N."}, {"input": "Sentence 1: Anna went to the school picnic. Sentence 2: Anna ate with her classmates at the picnic.", "output": "N", "explanation": "Anna's classmates are in her school, and a picnic involves food, so the answer should be E."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Captions -> Image Captions"], "Instance": {"id": "task190-3197d39a439d4753bb3e1a7427b3c79f", "input": "Sentence 1: A hostess in a restaurant, wearing a uniform and a black hat is cleaning one of the tables. Sentence 2: One of the waitresses did not show up so the restaurant hostess is bussing tables.", "output": ["N"]}, "Instance License": ["CC BY-SA 4.0"], "prediction": "N"}
+{"id": "task190-d8c5cce3f8924a2f946ca44bcc875d96", "Task": "task190_snli_classification", "Contributors": "['Anjana Arunkumar']", "Source": ["snli"], "URL": ["https://nlp.stanford.edu/pubs/snli_paper.pdf"], "Categories": ["Textual Entailment"], "Reasoning": ["Textual Entailment"], "Definition": ["In this task, you're given a pair of sentences, sentence 1 and sentence 2. Your job is to choose whether the two sentences clearly agree (entailment)/disagree (contradiction) with each other, or if this cannot be determined (neutral). Your answer must be in the form of the letters E, C, and N respectively."], "Positive Examples": [{"input": "Sentence 1: Jon saw his friend Tom coming out of the grocery store with a bag of fruit. Sentence 2: Tom had been shopping for fruit to give Jon.", "output": "N", "explanation": "Tom's reason for buying the fruit is not known."}, {"input": "Sentence 1: The girl transferred all the flowers from the boquet to a vase. Sentence 2: The flowers will soon wither.", "output": "N", "explanation": "The flowers could be real or plastic."}, {"input": "Sentence 1: The skier was on the edge of the ramp. Sentence 2: The skier was dressed in winter clothes.", "output": "E", "explanation": "Skiing is done in the snow and requires cold climates"}, {"input": "Sentence 1: Joyce likes to eat fruit salad as often as possible. Sentence 2: Joyce loves eating healthy.", "output": "E", "explanation": "Fruit salad is healthy food."}, {"input": "Sentence 1: The boy skated down the staircase railing. Sentence 2: The boy is a newbie skater.", "output": "C", "explanation": "Skating on a railng requires a lot of practice"}, {"input": "Sentence 1: Bertha was selected as captain of her basketball team. Sentence 2: Bertha was not atheletically inclined.", "output": "C", "explanation": "Basketball players are athletic."}], "Negative Examples": [{"input": "Sentence 1: There was an earthquake in San Fransisco. Sentence 2: The earthquake caused a lot of road damage.", "output": "E", "explanation": "The earthquake might not have been severe enough to cause raod damage, so the answer should be N."}, {"input": "Sentence 1: Anna went to the school picnic. Sentence 2: Anna ate with her classmates at the picnic.", "output": "N", "explanation": "Anna's classmates are in her school, and a picnic involves food, so the answer should be E."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Captions -> Image Captions"], "Instance": {"id": "task190-d8c5cce3f8924a2f946ca44bcc875d96", "input": "Sentence 1: A young woman in an \"I Heart Bill Clinton\" T-Shirt cooks meat on a grill in a public picnic area, while two young men converse behind her and a bicyclist and motorcyclist ride by on a nearby road in the background. Sentence 2: a woman heats up a frozen dinner in a microwave", "output": ["C"]}, "Instance License": ["CC BY-SA 4.0"], "prediction": "C"}
+{"id": "task200-acfa05af5c97427dbf7967cbd9e95952", "Task": "task200_mnli_entailment_classification", "Contributors": "['Anjana Arunkumar']", "Source": ["multinli"], "URL": ["https://cims.nyu.edu/~sbowman/multinli/paper.pdf"], "Categories": ["Textual Entailment"], "Reasoning": ["Commonsense Reasoning", "Textual Entailment -> Deductive Reasoning"], "Definition": ["In this task, you're given a statement and three sentences as choices. Your job is to determine which sentence can be inferred from the statement. Incorrect choices change the meaning in important ways or have details that are not mentioned in the statement. Indicate your answer as 1,2, or 3 corresponding to the choice number of the selected sentence."], "Positive Examples": [{"input": "Statement: Next to the MGM Grand you will find M and M World, four stories of merchandise and memorabilia dedicated to the candy that doesn't melt in your hand. Choices: 1. The candy has many fans who love its attractions. 2. There's four stories of memorabilia dedicated to a candy. 3. That particular candy melts and becomes difficult to eat.", "output": "2", "explanation": "The candy may or may not be popular, and does not melt and become difficult to eat. Hence the second choice is the only one that fully agrees with the statement."}, {"input": "Statment: I've forgotten his name now, confessed Tuppence. Choices: 1. Tuppence forgot his name. 2.Tuppence remembered his name later. 3. Tuppence never could forget his name.", "output": "1", "explanation": "Tuppence may or may not have later remembered the name, and has definitely forgotten it. Hence the first choice is the only one that fully agrees with the statement."}, {"input": "Statement: One of the first organizational realignments taking place is in the Office of the Taxpayer Advocate. Choices: 1. The office of the taxpayer advocate is the last to be realigned. 2. The realignment is taking place over a few weeks. 3. The office of the taxpayer advocate is having an organizational realignment.", "output": "3", "explanation": "The office is one of the first to be reorganized, and the duration of this is not know. Hence, the third choice is the only one that fully agrees with the statement."}, {"input": "Statement: yeah i tell you what though if you go price some of those tennis shoes i can see why now you know they're getting up in the hundred dollar range. Choices: 1. The tennis shoes have a range of prices. 2. The tennis shoes can be in the hundred dollar range. 3. The tennis shoes are not over hundred dollars.", "output": "2", "explanation": "The shoes' price range is not known, and they definitely cost more than a hundred dollars. Hence, the second choice is the only one that fully agrees with the statement."}], "Negative Examples": [{"input": "Statement: In 1994, fraction of households owning a personal computer is 0.25. Choices: 1. In 1994, 0.25 of households owned a PC, which was a high sum at the time. 2. In 1984, 0.8 of households owned a PC. In 1994, 0.25 of households owned a PC.", "output": "1", "explanation": "It is not known whether 0.25 is considered a high fraction of the households, so the first choice is incorrect."}, {"input": "Statement: You could say you were in an auto accident, and the ambulance driver took you straight to Dr. Famous' office. Choices: 1. Ambulance drivers knew Dr Famous was great for treating famous people. 2. Ambulance drivers just took you to the hospital. 3. Ambulance drivers knew Dr Famous.", "output": "2", "explanation": "The ambulance took the person to Dr. Famous, and not a hospital, so the second choice is incorrect."}, {"input": "Statement: The union has about 4000 members in Canada. Choices: 1. There's around 4000 Canadians in the union. 2. Toronto has Canada's biggest concentration of union members. 3. There are 100 members in the union that live in Canada.", "output": "3", "explanation": "Based on the statement the union has about 4000 members in canada, so the third choice is incorrect."}, {"input": "Statement: First to arrive was the Tang clan, which established a number of walled villages in the New Territories that still exist today. Choices: 1. The clan was not known for building. 2. Before the arrival of the Tang clan, the area was not inhabited by anyone. 3. Thanks to the Tang clan, there are a lot of walled villages that exist today.", "output": "1", "explanation": "This statement doesn't mention whether clan is known for building or not. Hence, the first choice is incorrect."}, {"input": "Statement: isn't it awful Choices: 1. This isn't too bad. 2. It's not as bad as past situations. 3. That is horrific.", "output": "2", "explanation": "In this example, the statement implies that it's awful. Also, we don't know about the past situations. So, the second choice is incorrect."}, {"input": "Statement: Construction of the offices obliterated much of the archaeological dig which had unearthed the original layout of the ninth-century quay, but the Viking artifacts that were found are on view in the National Museum  and in the Viking Adventure exhibit. Choices:  1. The Viking Adventure exhibit displays Thor's hammer. 2. The National museum has Viking artifacts on display. 3. Construction of the offices was permanently halted when Viking artifacts were found.", "output": "The Viking Adventure exhibit displays Thor's hammer.", "explanation": "You should only answer with the choice number. Here the acceptable answer is \"1\"."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["History", "Fiction", "Dialogue", "Law", "Government and Politics"], "Instance": {"id": "task200-acfa05af5c97427dbf7967cbd9e95952", "input": "Statement: Formal and informal areas are landscaped with pools and fountains, while terraces tumble down the hillsides. Choices:  1. Pools and fountains were used in the landscaping of formal areas. 2. There were no pools or fountains in the informal areas. 3. The architect of the pools and fountains drew inspiration from the gardens of Versailles.", "output": ["1"]}, "Instance License": ["OANC"], "prediction": "1"}
+{"id": "task200-e8fc9c64be3d410d8bed16e131ac3dd9", "Task": "task200_mnli_entailment_classification", "Contributors": "['Anjana Arunkumar']", "Source": ["multinli"], "URL": ["https://cims.nyu.edu/~sbowman/multinli/paper.pdf"], "Categories": ["Textual Entailment"], "Reasoning": ["Commonsense Reasoning", "Textual Entailment -> Deductive Reasoning"], "Definition": ["In this task, you're given a statement and three sentences as choices. Your job is to determine which sentence can be inferred from the statement. Incorrect choices change the meaning in important ways or have details that are not mentioned in the statement. Indicate your answer as 1,2, or 3 corresponding to the choice number of the selected sentence."], "Positive Examples": [{"input": "Statement: Next to the MGM Grand you will find M and M World, four stories of merchandise and memorabilia dedicated to the candy that doesn't melt in your hand. Choices: 1. The candy has many fans who love its attractions. 2. There's four stories of memorabilia dedicated to a candy. 3. That particular candy melts and becomes difficult to eat.", "output": "2", "explanation": "The candy may or may not be popular, and does not melt and become difficult to eat. Hence the second choice is the only one that fully agrees with the statement."}, {"input": "Statment: I've forgotten his name now, confessed Tuppence. Choices: 1. Tuppence forgot his name. 2.Tuppence remembered his name later. 3. Tuppence never could forget his name.", "output": "1", "explanation": "Tuppence may or may not have later remembered the name, and has definitely forgotten it. Hence the first choice is the only one that fully agrees with the statement."}, {"input": "Statement: One of the first organizational realignments taking place is in the Office of the Taxpayer Advocate. Choices: 1. The office of the taxpayer advocate is the last to be realigned. 2. The realignment is taking place over a few weeks. 3. The office of the taxpayer advocate is having an organizational realignment.", "output": "3", "explanation": "The office is one of the first to be reorganized, and the duration of this is not know. Hence, the third choice is the only one that fully agrees with the statement."}, {"input": "Statement: yeah i tell you what though if you go price some of those tennis shoes i can see why now you know they're getting up in the hundred dollar range. Choices: 1. The tennis shoes have a range of prices. 2. The tennis shoes can be in the hundred dollar range. 3. The tennis shoes are not over hundred dollars.", "output": "2", "explanation": "The shoes' price range is not known, and they definitely cost more than a hundred dollars. Hence, the second choice is the only one that fully agrees with the statement."}], "Negative Examples": [{"input": "Statement: In 1994, fraction of households owning a personal computer is 0.25. Choices: 1. In 1994, 0.25 of households owned a PC, which was a high sum at the time. 2. In 1984, 0.8 of households owned a PC. In 1994, 0.25 of households owned a PC.", "output": "1", "explanation": "It is not known whether 0.25 is considered a high fraction of the households, so the first choice is incorrect."}, {"input": "Statement: You could say you were in an auto accident, and the ambulance driver took you straight to Dr. Famous' office. Choices: 1. Ambulance drivers knew Dr Famous was great for treating famous people. 2. Ambulance drivers just took you to the hospital. 3. Ambulance drivers knew Dr Famous.", "output": "2", "explanation": "The ambulance took the person to Dr. Famous, and not a hospital, so the second choice is incorrect."}, {"input": "Statement: The union has about 4000 members in Canada. Choices: 1. There's around 4000 Canadians in the union. 2. Toronto has Canada's biggest concentration of union members. 3. There are 100 members in the union that live in Canada.", "output": "3", "explanation": "Based on the statement the union has about 4000 members in canada, so the third choice is incorrect."}, {"input": "Statement: First to arrive was the Tang clan, which established a number of walled villages in the New Territories that still exist today. Choices: 1. The clan was not known for building. 2. Before the arrival of the Tang clan, the area was not inhabited by anyone. 3. Thanks to the Tang clan, there are a lot of walled villages that exist today.", "output": "1", "explanation": "This statement doesn't mention whether clan is known for building or not. Hence, the first choice is incorrect."}, {"input": "Statement: isn't it awful Choices: 1. This isn't too bad. 2. It's not as bad as past situations. 3. That is horrific.", "output": "2", "explanation": "In this example, the statement implies that it's awful. Also, we don't know about the past situations. So, the second choice is incorrect."}, {"input": "Statement: Construction of the offices obliterated much of the archaeological dig which had unearthed the original layout of the ninth-century quay, but the Viking artifacts that were found are on view in the National Museum  and in the Viking Adventure exhibit. Choices:  1. The Viking Adventure exhibit displays Thor's hammer. 2. The National museum has Viking artifacts on display. 3. Construction of the offices was permanently halted when Viking artifacts were found.", "output": "The Viking Adventure exhibit displays Thor's hammer.", "explanation": "You should only answer with the choice number. Here the acceptable answer is \"1\"."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["History", "Fiction", "Dialogue", "Law", "Government and Politics"], "Instance": {"id": "task200-e8fc9c64be3d410d8bed16e131ac3dd9", "input": "Statement: You there Rennie! Drew saw the involuntary spasm of Don Cazar's lips, the shadow of an expression which might mean he anticipated a distasteful scene to come. Choices:  1. Drew knew Don Cazar's expression well because he has known him for a long time. 2. Drew knew Don Quixote. 3. Drew knew Don Cazar's expression well.", "output": ["3"]}, "Instance License": ["OANC"], "prediction": "3"}
+{"id": "task200-38ed987f6dcd4f66bc6b9f20fc291cbc", "Task": "task200_mnli_entailment_classification", "Contributors": "['Anjana Arunkumar']", "Source": ["multinli"], "URL": ["https://cims.nyu.edu/~sbowman/multinli/paper.pdf"], "Categories": ["Textual Entailment"], "Reasoning": ["Commonsense Reasoning", "Textual Entailment -> Deductive Reasoning"], "Definition": ["In this task, you're given a statement and three sentences as choices. Your job is to determine which sentence can be inferred from the statement. Incorrect choices change the meaning in important ways or have details that are not mentioned in the statement. Indicate your answer as 1,2, or 3 corresponding to the choice number of the selected sentence."], "Positive Examples": [{"input": "Statement: Next to the MGM Grand you will find M and M World, four stories of merchandise and memorabilia dedicated to the candy that doesn't melt in your hand. Choices: 1. The candy has many fans who love its attractions. 2. There's four stories of memorabilia dedicated to a candy. 3. That particular candy melts and becomes difficult to eat.", "output": "2", "explanation": "The candy may or may not be popular, and does not melt and become difficult to eat. Hence the second choice is the only one that fully agrees with the statement."}, {"input": "Statment: I've forgotten his name now, confessed Tuppence. Choices: 1. Tuppence forgot his name. 2.Tuppence remembered his name later. 3. Tuppence never could forget his name.", "output": "1", "explanation": "Tuppence may or may not have later remembered the name, and has definitely forgotten it. Hence the first choice is the only one that fully agrees with the statement."}, {"input": "Statement: One of the first organizational realignments taking place is in the Office of the Taxpayer Advocate. Choices: 1. The office of the taxpayer advocate is the last to be realigned. 2. The realignment is taking place over a few weeks. 3. The office of the taxpayer advocate is having an organizational realignment.", "output": "3", "explanation": "The office is one of the first to be reorganized, and the duration of this is not know. Hence, the third choice is the only one that fully agrees with the statement."}, {"input": "Statement: yeah i tell you what though if you go price some of those tennis shoes i can see why now you know they're getting up in the hundred dollar range. Choices: 1. The tennis shoes have a range of prices. 2. The tennis shoes can be in the hundred dollar range. 3. The tennis shoes are not over hundred dollars.", "output": "2", "explanation": "The shoes' price range is not known, and they definitely cost more than a hundred dollars. Hence, the second choice is the only one that fully agrees with the statement."}], "Negative Examples": [{"input": "Statement: In 1994, fraction of households owning a personal computer is 0.25. Choices: 1. In 1994, 0.25 of households owned a PC, which was a high sum at the time. 2. In 1984, 0.8 of households owned a PC. In 1994, 0.25 of households owned a PC.", "output": "1", "explanation": "It is not known whether 0.25 is considered a high fraction of the households, so the first choice is incorrect."}, {"input": "Statement: You could say you were in an auto accident, and the ambulance driver took you straight to Dr. Famous' office. Choices: 1. Ambulance drivers knew Dr Famous was great for treating famous people. 2. Ambulance drivers just took you to the hospital. 3. Ambulance drivers knew Dr Famous.", "output": "2", "explanation": "The ambulance took the person to Dr. Famous, and not a hospital, so the second choice is incorrect."}, {"input": "Statement: The union has about 4000 members in Canada. Choices: 1. There's around 4000 Canadians in the union. 2. Toronto has Canada's biggest concentration of union members. 3. There are 100 members in the union that live in Canada.", "output": "3", "explanation": "Based on the statement the union has about 4000 members in canada, so the third choice is incorrect."}, {"input": "Statement: First to arrive was the Tang clan, which established a number of walled villages in the New Territories that still exist today. Choices: 1. The clan was not known for building. 2. Before the arrival of the Tang clan, the area was not inhabited by anyone. 3. Thanks to the Tang clan, there are a lot of walled villages that exist today.", "output": "1", "explanation": "This statement doesn't mention whether clan is known for building or not. Hence, the first choice is incorrect."}, {"input": "Statement: isn't it awful Choices: 1. This isn't too bad. 2. It's not as bad as past situations. 3. That is horrific.", "output": "2", "explanation": "In this example, the statement implies that it's awful. Also, we don't know about the past situations. So, the second choice is incorrect."}, {"input": "Statement: Construction of the offices obliterated much of the archaeological dig which had unearthed the original layout of the ninth-century quay, but the Viking artifacts that were found are on view in the National Museum  and in the Viking Adventure exhibit. Choices:  1. The Viking Adventure exhibit displays Thor's hammer. 2. The National museum has Viking artifacts on display. 3. Construction of the offices was permanently halted when Viking artifacts were found.", "output": "The Viking Adventure exhibit displays Thor's hammer.", "explanation": "You should only answer with the choice number. Here the acceptable answer is \"1\"."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["History", "Fiction", "Dialogue", "Law", "Government and Politics"], "Instance": {"id": "task200-38ed987f6dcd4f66bc6b9f20fc291cbc", "input": "Statement: Each June, the Malaysian Nature Society supports an international bird race, where teams compete to identify the largest number of birds. Choices:  1. There is an international bird race every year. 2. There is a special prize for one of the rarest birds. 3. Each June, the Malaysian Nature Society has shunned the international bird race.", "output": ["1"]}, "Instance License": ["OANC"], "prediction": "1"}
+{"id": "task200-c3ddc482101443c7be8d01622ac9e7c0", "Task": "task200_mnli_entailment_classification", "Contributors": "['Anjana Arunkumar']", "Source": ["multinli"], "URL": ["https://cims.nyu.edu/~sbowman/multinli/paper.pdf"], "Categories": ["Textual Entailment"], "Reasoning": ["Commonsense Reasoning", "Textual Entailment -> Deductive Reasoning"], "Definition": ["In this task, you're given a statement and three sentences as choices. Your job is to determine which sentence can be inferred from the statement. Incorrect choices change the meaning in important ways or have details that are not mentioned in the statement. Indicate your answer as 1,2, or 3 corresponding to the choice number of the selected sentence."], "Positive Examples": [{"input": "Statement: Next to the MGM Grand you will find M and M World, four stories of merchandise and memorabilia dedicated to the candy that doesn't melt in your hand. Choices: 1. The candy has many fans who love its attractions. 2. There's four stories of memorabilia dedicated to a candy. 3. That particular candy melts and becomes difficult to eat.", "output": "2", "explanation": "The candy may or may not be popular, and does not melt and become difficult to eat. Hence the second choice is the only one that fully agrees with the statement."}, {"input": "Statment: I've forgotten his name now, confessed Tuppence. Choices: 1. Tuppence forgot his name. 2.Tuppence remembered his name later. 3. Tuppence never could forget his name.", "output": "1", "explanation": "Tuppence may or may not have later remembered the name, and has definitely forgotten it. Hence the first choice is the only one that fully agrees with the statement."}, {"input": "Statement: One of the first organizational realignments taking place is in the Office of the Taxpayer Advocate. Choices: 1. The office of the taxpayer advocate is the last to be realigned. 2. The realignment is taking place over a few weeks. 3. The office of the taxpayer advocate is having an organizational realignment.", "output": "3", "explanation": "The office is one of the first to be reorganized, and the duration of this is not know. Hence, the third choice is the only one that fully agrees with the statement."}, {"input": "Statement: yeah i tell you what though if you go price some of those tennis shoes i can see why now you know they're getting up in the hundred dollar range. Choices: 1. The tennis shoes have a range of prices. 2. The tennis shoes can be in the hundred dollar range. 3. The tennis shoes are not over hundred dollars.", "output": "2", "explanation": "The shoes' price range is not known, and they definitely cost more than a hundred dollars. Hence, the second choice is the only one that fully agrees with the statement."}], "Negative Examples": [{"input": "Statement: In 1994, fraction of households owning a personal computer is 0.25. Choices: 1. In 1994, 0.25 of households owned a PC, which was a high sum at the time. 2. In 1984, 0.8 of households owned a PC. In 1994, 0.25 of households owned a PC.", "output": "1", "explanation": "It is not known whether 0.25 is considered a high fraction of the households, so the first choice is incorrect."}, {"input": "Statement: You could say you were in an auto accident, and the ambulance driver took you straight to Dr. Famous' office. Choices: 1. Ambulance drivers knew Dr Famous was great for treating famous people. 2. Ambulance drivers just took you to the hospital. 3. Ambulance drivers knew Dr Famous.", "output": "2", "explanation": "The ambulance took the person to Dr. Famous, and not a hospital, so the second choice is incorrect."}, {"input": "Statement: The union has about 4000 members in Canada. Choices: 1. There's around 4000 Canadians in the union. 2. Toronto has Canada's biggest concentration of union members. 3. There are 100 members in the union that live in Canada.", "output": "3", "explanation": "Based on the statement the union has about 4000 members in canada, so the third choice is incorrect."}, {"input": "Statement: First to arrive was the Tang clan, which established a number of walled villages in the New Territories that still exist today. Choices: 1. The clan was not known for building. 2. Before the arrival of the Tang clan, the area was not inhabited by anyone. 3. Thanks to the Tang clan, there are a lot of walled villages that exist today.", "output": "1", "explanation": "This statement doesn't mention whether clan is known for building or not. Hence, the first choice is incorrect."}, {"input": "Statement: isn't it awful Choices: 1. This isn't too bad. 2. It's not as bad as past situations. 3. That is horrific.", "output": "2", "explanation": "In this example, the statement implies that it's awful. Also, we don't know about the past situations. So, the second choice is incorrect."}, {"input": "Statement: Construction of the offices obliterated much of the archaeological dig which had unearthed the original layout of the ninth-century quay, but the Viking artifacts that were found are on view in the National Museum  and in the Viking Adventure exhibit. Choices:  1. The Viking Adventure exhibit displays Thor's hammer. 2. The National museum has Viking artifacts on display. 3. Construction of the offices was permanently halted when Viking artifacts were found.", "output": "The Viking Adventure exhibit displays Thor's hammer.", "explanation": "You should only answer with the choice number. Here the acceptable answer is \"1\"."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["History", "Fiction", "Dialogue", "Law", "Government and Politics"], "Instance": {"id": "task200-c3ddc482101443c7be8d01622ac9e7c0", "input": "Statement: Some states have established insurance-buying groups that employers can join. Choices:  1. Employers will not be able to join state established insurance-buying groups. 2. Employers can join state established insurance-buying groups. 3. Almost all of the states have established at least one insurance-buying group.", "output": ["2"]}, "Instance License": ["OANC"], "prediction": "2"}
+{"id": "task200-1f564ea3a8124b09a28ec1198ed2e483", "Task": "task200_mnli_entailment_classification", "Contributors": "['Anjana Arunkumar']", "Source": ["multinli"], "URL": ["https://cims.nyu.edu/~sbowman/multinli/paper.pdf"], "Categories": ["Textual Entailment"], "Reasoning": ["Commonsense Reasoning", "Textual Entailment -> Deductive Reasoning"], "Definition": ["In this task, you're given a statement and three sentences as choices. Your job is to determine which sentence can be inferred from the statement. Incorrect choices change the meaning in important ways or have details that are not mentioned in the statement. Indicate your answer as 1,2, or 3 corresponding to the choice number of the selected sentence."], "Positive Examples": [{"input": "Statement: Next to the MGM Grand you will find M and M World, four stories of merchandise and memorabilia dedicated to the candy that doesn't melt in your hand. Choices: 1. The candy has many fans who love its attractions. 2. There's four stories of memorabilia dedicated to a candy. 3. That particular candy melts and becomes difficult to eat.", "output": "2", "explanation": "The candy may or may not be popular, and does not melt and become difficult to eat. Hence the second choice is the only one that fully agrees with the statement."}, {"input": "Statment: I've forgotten his name now, confessed Tuppence. Choices: 1. Tuppence forgot his name. 2.Tuppence remembered his name later. 3. Tuppence never could forget his name.", "output": "1", "explanation": "Tuppence may or may not have later remembered the name, and has definitely forgotten it. Hence the first choice is the only one that fully agrees with the statement."}, {"input": "Statement: One of the first organizational realignments taking place is in the Office of the Taxpayer Advocate. Choices: 1. The office of the taxpayer advocate is the last to be realigned. 2. The realignment is taking place over a few weeks. 3. The office of the taxpayer advocate is having an organizational realignment.", "output": "3", "explanation": "The office is one of the first to be reorganized, and the duration of this is not know. Hence, the third choice is the only one that fully agrees with the statement."}, {"input": "Statement: yeah i tell you what though if you go price some of those tennis shoes i can see why now you know they're getting up in the hundred dollar range. Choices: 1. The tennis shoes have a range of prices. 2. The tennis shoes can be in the hundred dollar range. 3. The tennis shoes are not over hundred dollars.", "output": "2", "explanation": "The shoes' price range is not known, and they definitely cost more than a hundred dollars. Hence, the second choice is the only one that fully agrees with the statement."}], "Negative Examples": [{"input": "Statement: In 1994, fraction of households owning a personal computer is 0.25. Choices: 1. In 1994, 0.25 of households owned a PC, which was a high sum at the time. 2. In 1984, 0.8 of households owned a PC. In 1994, 0.25 of households owned a PC.", "output": "1", "explanation": "It is not known whether 0.25 is considered a high fraction of the households, so the first choice is incorrect."}, {"input": "Statement: You could say you were in an auto accident, and the ambulance driver took you straight to Dr. Famous' office. Choices: 1. Ambulance drivers knew Dr Famous was great for treating famous people. 2. Ambulance drivers just took you to the hospital. 3. Ambulance drivers knew Dr Famous.", "output": "2", "explanation": "The ambulance took the person to Dr. Famous, and not a hospital, so the second choice is incorrect."}, {"input": "Statement: The union has about 4000 members in Canada. Choices: 1. There's around 4000 Canadians in the union. 2. Toronto has Canada's biggest concentration of union members. 3. There are 100 members in the union that live in Canada.", "output": "3", "explanation": "Based on the statement the union has about 4000 members in canada, so the third choice is incorrect."}, {"input": "Statement: First to arrive was the Tang clan, which established a number of walled villages in the New Territories that still exist today. Choices: 1. The clan was not known for building. 2. Before the arrival of the Tang clan, the area was not inhabited by anyone. 3. Thanks to the Tang clan, there are a lot of walled villages that exist today.", "output": "1", "explanation": "This statement doesn't mention whether clan is known for building or not. Hence, the first choice is incorrect."}, {"input": "Statement: isn't it awful Choices: 1. This isn't too bad. 2. It's not as bad as past situations. 3. That is horrific.", "output": "2", "explanation": "In this example, the statement implies that it's awful. Also, we don't know about the past situations. So, the second choice is incorrect."}, {"input": "Statement: Construction of the offices obliterated much of the archaeological dig which had unearthed the original layout of the ninth-century quay, but the Viking artifacts that were found are on view in the National Museum  and in the Viking Adventure exhibit. Choices:  1. The Viking Adventure exhibit displays Thor's hammer. 2. The National museum has Viking artifacts on display. 3. Construction of the offices was permanently halted when Viking artifacts were found.", "output": "The Viking Adventure exhibit displays Thor's hammer.", "explanation": "You should only answer with the choice number. Here the acceptable answer is \"1\"."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["History", "Fiction", "Dialogue", "Law", "Government and Politics"], "Instance": {"id": "task200-1f564ea3a8124b09a28ec1198ed2e483", "input": "Statement: However, young and old, stranger and Dubliner rub shoulders quite happily. Choices:  1. Dubliners hate outsiders, with a particular contempt for the old.  2. Dubliners and strangers get along well regardless of age.  3. Young and old, stranger and Dubliner give one another shoulder massages. ", "output": ["2"]}, "Instance License": ["OANC"], "prediction": "2"}
+{"id": "task1534-8db6b97dafaa44de88dc3a1ea901d3ab", "Task": "task1534_daily_dialog_question_classification", "Contributors": "['Krishna Sriharsha Gundu']", "Source": ["dailydialog"], "URL": ["https://huggingface.co/datasets/daily_dialog"], "Categories": ["Dialogue Act Recognition"], "Reasoning": [], "Definition": ["You are given a conversation between two people. 'Person1:' and 'Person2:' are used to separate their respective dialogues. If the conversation begins with a question, label it '1' otherwise '0'."], "Positive Examples": [{"input": "Person1:     Passport , please , madam . \n Person2: Just a minute , please . It's in my bag . Here it is . \n Person1:     Thank you . Please fill out the Baggage Declaration Form . \n Person2: All right . Shall I enter all my belongings ? \n Person1:     No , only the articles listed on the Declaration . ", "output": "0", "explanation": "The first sentence in the conversation begins with a request, therefore there is no presence of a question."}, {"input": " Person1:     Hi ! What are you watching ?  \n Person2:  It \u2019 s a program about islam . It \u2019 s very interesting .  \n Person1:      Wow ! So many people ! Where are they and what are they doing ?  \n Person2:  They are muslims on a pilgrimage to mecca . Muslims call this pilgrimage \u201c haj \u201d .  \n Person1:      Why do they go there ?  \n Person2:  Muslims believe that every man who is able should go on a haj at least once in his life . Mecca is the spiritual centre of the muslim faith .  \n Person1:      When muslims pray , they face towards mecca .  \n Person2:  That \u2019 s right . Unfortunately , so many people go on the haj each year that there are often stamped and people get killed .  \n Person1:      I heard about that . The pilgrims must walk around a large , sacred black stone .  \n Person2:  That \u2019 s right . That \u2019 s when accidents often happen . The Saudi government tries to limit the number of pilgrims , to reduce the chances of accidents .  \n Person1:      Pilgrimages are common in many faiths .  \n Person2:  Yes . In England , Christian pilgrims might go to Canterbury and many Christians go to the Vatican on pilgrimages .  \n Person1:      Isn \u2019 t there a place in france where people go to get healed ?  \n Person2:  I think that place is Lourdes . There are many stories of people being healed after visiting there .  \n Person1:      Do you think that there is something magical about that place ?  \n Person2:  Personally . I think that people believe they will be healed and that faith causes a change in their mind that cures them . I don \u2019 t think place is magical in any way . ", "output": "1", "explanation": "The first sentence contains a question, therefore the output is correctly mentioned as 1 "}, {"input": "Person1:     You look terrific and in good shape .  \n Person2: Thank you .  \n Person1:     How do you keep fit ?  \n Person2:  I do yoga twice a weeks  \n Person1:     Yoga ? It sounds interesting .  \n Person2: It was hard at the beginning , but now feel it's really relaxing . It makes me flexible .  \n Person1:     Anything else ?  \n Person2: Yes , I often go swimming .  \n Person1:     Are you interested in swimming ?  \n Person2: Yes , I like it very much . ", "output": "0", "explanation": "The first sentence is not a question, therefore the output is correct."}], "Negative Examples": [{"input": "Person1:     Can I borrow five bucks ? \n Person2:  No ! \n Person1:     Come on ! I'll pay you back on Tuesday . \n Person2: Last time I lent you money , you never paid me back . \n Person1:     I promise if you lend me five dollars today , I will repay you in full next week .  \n Person2: Ok , but I'm taking your skateboard as collateral .  \n Person1:     Fine ! I can't believe you don't trust me . \n Person2: It's nothing personal , just business . ", "output": "0", "explanation": "The first question does begin with a question, therefore the classification result must be 1 instead of 0."}, {"input": "Person1:     I \u2019 m so surprised to meet you in this remote village . Long time no see . \n Person2: Yeah . How are you these days ? ", "output": "1", "explanation": "The first sentence contains a statement about the remote village, since it is not a question the output should be 0 instead of 1."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Dialogue"], "Instance": {"id": "task1534-8db6b97dafaa44de88dc3a1ea901d3ab", "input": " Person1:     Guess what ? Paul and Susan are engaged .  \n Person2:  Really ? When did that happen ?  \n Person1:      A week ago ? They met last summer and now just sink . They will be married soon .  \n Person2:  Have they set a date for the wedding ?  \n Person1:      No , not yet . But Susan says they \u2019 d like to get married in November or December . Then they \u2019 ll go to Hawaii for their honeymoon . ", "output": ["1"]}, "Instance License": ["CC BY-NC-SA 4.0"], "prediction": "0"}
+{"id": "task1534-178dd0f3c885466cb5afbd675ee1c3e3", "Task": "task1534_daily_dialog_question_classification", "Contributors": "['Krishna Sriharsha Gundu']", "Source": ["dailydialog"], "URL": ["https://huggingface.co/datasets/daily_dialog"], "Categories": ["Dialogue Act Recognition"], "Reasoning": [], "Definition": ["You are given a conversation between two people. 'Person1:' and 'Person2:' are used to separate their respective dialogues. If the conversation begins with a question, label it '1' otherwise '0'."], "Positive Examples": [{"input": "Person1:     Passport , please , madam . \n Person2: Just a minute , please . It's in my bag . Here it is . \n Person1:     Thank you . Please fill out the Baggage Declaration Form . \n Person2: All right . Shall I enter all my belongings ? \n Person1:     No , only the articles listed on the Declaration . ", "output": "0", "explanation": "The first sentence in the conversation begins with a request, therefore there is no presence of a question."}, {"input": " Person1:     Hi ! What are you watching ?  \n Person2:  It \u2019 s a program about islam . It \u2019 s very interesting .  \n Person1:      Wow ! So many people ! Where are they and what are they doing ?  \n Person2:  They are muslims on a pilgrimage to mecca . Muslims call this pilgrimage \u201c haj \u201d .  \n Person1:      Why do they go there ?  \n Person2:  Muslims believe that every man who is able should go on a haj at least once in his life . Mecca is the spiritual centre of the muslim faith .  \n Person1:      When muslims pray , they face towards mecca .  \n Person2:  That \u2019 s right . Unfortunately , so many people go on the haj each year that there are often stamped and people get killed .  \n Person1:      I heard about that . The pilgrims must walk around a large , sacred black stone .  \n Person2:  That \u2019 s right . That \u2019 s when accidents often happen . The Saudi government tries to limit the number of pilgrims , to reduce the chances of accidents .  \n Person1:      Pilgrimages are common in many faiths .  \n Person2:  Yes . In England , Christian pilgrims might go to Canterbury and many Christians go to the Vatican on pilgrimages .  \n Person1:      Isn \u2019 t there a place in france where people go to get healed ?  \n Person2:  I think that place is Lourdes . There are many stories of people being healed after visiting there .  \n Person1:      Do you think that there is something magical about that place ?  \n Person2:  Personally . I think that people believe they will be healed and that faith causes a change in their mind that cures them . I don \u2019 t think place is magical in any way . ", "output": "1", "explanation": "The first sentence contains a question, therefore the output is correctly mentioned as 1 "}, {"input": "Person1:     You look terrific and in good shape .  \n Person2: Thank you .  \n Person1:     How do you keep fit ?  \n Person2:  I do yoga twice a weeks  \n Person1:     Yoga ? It sounds interesting .  \n Person2: It was hard at the beginning , but now feel it's really relaxing . It makes me flexible .  \n Person1:     Anything else ?  \n Person2: Yes , I often go swimming .  \n Person1:     Are you interested in swimming ?  \n Person2: Yes , I like it very much . ", "output": "0", "explanation": "The first sentence is not a question, therefore the output is correct."}], "Negative Examples": [{"input": "Person1:     Can I borrow five bucks ? \n Person2:  No ! \n Person1:     Come on ! I'll pay you back on Tuesday . \n Person2: Last time I lent you money , you never paid me back . \n Person1:     I promise if you lend me five dollars today , I will repay you in full next week .  \n Person2: Ok , but I'm taking your skateboard as collateral .  \n Person1:     Fine ! I can't believe you don't trust me . \n Person2: It's nothing personal , just business . ", "output": "0", "explanation": "The first question does begin with a question, therefore the classification result must be 1 instead of 0."}, {"input": "Person1:     I \u2019 m so surprised to meet you in this remote village . Long time no see . \n Person2: Yeah . How are you these days ? ", "output": "1", "explanation": "The first sentence contains a statement about the remote village, since it is not a question the output should be 0 instead of 1."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Dialogue"], "Instance": {"id": "task1534-178dd0f3c885466cb5afbd675ee1c3e3", "input": " Person1:     Awful ! My cell phone is out of service again . Fred , can you lend me some money ?  \n Person2:  How much do you want ?  \n Person1:      200yuan . I bought a computer online , so I have to pay the mortgage .  \n Person2:  I am so sorry to hear that . Is that enough ?  \n Person1:      It's so nice of you . You really make my day .  \n Person2:  Forget it ! We seemingly need to gather money little by little .  \n Person1:      What you said is absolutely right . I will pay you back as soon as I get back on my feet .  \n Person2:  No rush . You can give it back whenever you have it . ", "output": ["0"]}, "Instance License": ["CC BY-NC-SA 4.0"], "prediction": "0"}
+{"id": "task1534-b9b2c6d8ea9247bb9d53494fa91ca442", "Task": "task1534_daily_dialog_question_classification", "Contributors": "['Krishna Sriharsha Gundu']", "Source": ["dailydialog"], "URL": ["https://huggingface.co/datasets/daily_dialog"], "Categories": ["Dialogue Act Recognition"], "Reasoning": [], "Definition": ["You are given a conversation between two people. 'Person1:' and 'Person2:' are used to separate their respective dialogues. If the conversation begins with a question, label it '1' otherwise '0'."], "Positive Examples": [{"input": "Person1:     Passport , please , madam . \n Person2: Just a minute , please . It's in my bag . Here it is . \n Person1:     Thank you . Please fill out the Baggage Declaration Form . \n Person2: All right . Shall I enter all my belongings ? \n Person1:     No , only the articles listed on the Declaration . ", "output": "0", "explanation": "The first sentence in the conversation begins with a request, therefore there is no presence of a question."}, {"input": " Person1:     Hi ! What are you watching ?  \n Person2:  It \u2019 s a program about islam . It \u2019 s very interesting .  \n Person1:      Wow ! So many people ! Where are they and what are they doing ?  \n Person2:  They are muslims on a pilgrimage to mecca . Muslims call this pilgrimage \u201c haj \u201d .  \n Person1:      Why do they go there ?  \n Person2:  Muslims believe that every man who is able should go on a haj at least once in his life . Mecca is the spiritual centre of the muslim faith .  \n Person1:      When muslims pray , they face towards mecca .  \n Person2:  That \u2019 s right . Unfortunately , so many people go on the haj each year that there are often stamped and people get killed .  \n Person1:      I heard about that . The pilgrims must walk around a large , sacred black stone .  \n Person2:  That \u2019 s right . That \u2019 s when accidents often happen . The Saudi government tries to limit the number of pilgrims , to reduce the chances of accidents .  \n Person1:      Pilgrimages are common in many faiths .  \n Person2:  Yes . In England , Christian pilgrims might go to Canterbury and many Christians go to the Vatican on pilgrimages .  \n Person1:      Isn \u2019 t there a place in france where people go to get healed ?  \n Person2:  I think that place is Lourdes . There are many stories of people being healed after visiting there .  \n Person1:      Do you think that there is something magical about that place ?  \n Person2:  Personally . I think that people believe they will be healed and that faith causes a change in their mind that cures them . I don \u2019 t think place is magical in any way . ", "output": "1", "explanation": "The first sentence contains a question, therefore the output is correctly mentioned as 1 "}, {"input": "Person1:     You look terrific and in good shape .  \n Person2: Thank you .  \n Person1:     How do you keep fit ?  \n Person2:  I do yoga twice a weeks  \n Person1:     Yoga ? It sounds interesting .  \n Person2: It was hard at the beginning , but now feel it's really relaxing . It makes me flexible .  \n Person1:     Anything else ?  \n Person2: Yes , I often go swimming .  \n Person1:     Are you interested in swimming ?  \n Person2: Yes , I like it very much . ", "output": "0", "explanation": "The first sentence is not a question, therefore the output is correct."}], "Negative Examples": [{"input": "Person1:     Can I borrow five bucks ? \n Person2:  No ! \n Person1:     Come on ! I'll pay you back on Tuesday . \n Person2: Last time I lent you money , you never paid me back . \n Person1:     I promise if you lend me five dollars today , I will repay you in full next week .  \n Person2: Ok , but I'm taking your skateboard as collateral .  \n Person1:     Fine ! I can't believe you don't trust me . \n Person2: It's nothing personal , just business . ", "output": "0", "explanation": "The first question does begin with a question, therefore the classification result must be 1 instead of 0."}, {"input": "Person1:     I \u2019 m so surprised to meet you in this remote village . Long time no see . \n Person2: Yeah . How are you these days ? ", "output": "1", "explanation": "The first sentence contains a statement about the remote village, since it is not a question the output should be 0 instead of 1."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Dialogue"], "Instance": {"id": "task1534-b9b2c6d8ea9247bb9d53494fa91ca442", "input": " Person1:     I'll never ever work together with him !  \n Person2:  What happened ? Quarrel again ?  \n Person1:      Will you take my materials back from him for me ? Please !  \n Person2:  Don't ask me . I don't wanna be involved in your quarrel . ", "output": ["0"]}, "Instance License": ["CC BY-NC-SA 4.0"], "prediction": "0"}
+{"id": "task1534-862fcc20654748a398aca06143c68d0a", "Task": "task1534_daily_dialog_question_classification", "Contributors": "['Krishna Sriharsha Gundu']", "Source": ["dailydialog"], "URL": ["https://huggingface.co/datasets/daily_dialog"], "Categories": ["Dialogue Act Recognition"], "Reasoning": [], "Definition": ["You are given a conversation between two people. 'Person1:' and 'Person2:' are used to separate their respective dialogues. If the conversation begins with a question, label it '1' otherwise '0'."], "Positive Examples": [{"input": "Person1:     Passport , please , madam . \n Person2: Just a minute , please . It's in my bag . Here it is . \n Person1:     Thank you . Please fill out the Baggage Declaration Form . \n Person2: All right . Shall I enter all my belongings ? \n Person1:     No , only the articles listed on the Declaration . ", "output": "0", "explanation": "The first sentence in the conversation begins with a request, therefore there is no presence of a question."}, {"input": " Person1:     Hi ! What are you watching ?  \n Person2:  It \u2019 s a program about islam . It \u2019 s very interesting .  \n Person1:      Wow ! So many people ! Where are they and what are they doing ?  \n Person2:  They are muslims on a pilgrimage to mecca . Muslims call this pilgrimage \u201c haj \u201d .  \n Person1:      Why do they go there ?  \n Person2:  Muslims believe that every man who is able should go on a haj at least once in his life . Mecca is the spiritual centre of the muslim faith .  \n Person1:      When muslims pray , they face towards mecca .  \n Person2:  That \u2019 s right . Unfortunately , so many people go on the haj each year that there are often stamped and people get killed .  \n Person1:      I heard about that . The pilgrims must walk around a large , sacred black stone .  \n Person2:  That \u2019 s right . That \u2019 s when accidents often happen . The Saudi government tries to limit the number of pilgrims , to reduce the chances of accidents .  \n Person1:      Pilgrimages are common in many faiths .  \n Person2:  Yes . In England , Christian pilgrims might go to Canterbury and many Christians go to the Vatican on pilgrimages .  \n Person1:      Isn \u2019 t there a place in france where people go to get healed ?  \n Person2:  I think that place is Lourdes . There are many stories of people being healed after visiting there .  \n Person1:      Do you think that there is something magical about that place ?  \n Person2:  Personally . I think that people believe they will be healed and that faith causes a change in their mind that cures them . I don \u2019 t think place is magical in any way . ", "output": "1", "explanation": "The first sentence contains a question, therefore the output is correctly mentioned as 1 "}, {"input": "Person1:     You look terrific and in good shape .  \n Person2: Thank you .  \n Person1:     How do you keep fit ?  \n Person2:  I do yoga twice a weeks  \n Person1:     Yoga ? It sounds interesting .  \n Person2: It was hard at the beginning , but now feel it's really relaxing . It makes me flexible .  \n Person1:     Anything else ?  \n Person2: Yes , I often go swimming .  \n Person1:     Are you interested in swimming ?  \n Person2: Yes , I like it very much . ", "output": "0", "explanation": "The first sentence is not a question, therefore the output is correct."}], "Negative Examples": [{"input": "Person1:     Can I borrow five bucks ? \n Person2:  No ! \n Person1:     Come on ! I'll pay you back on Tuesday . \n Person2: Last time I lent you money , you never paid me back . \n Person1:     I promise if you lend me five dollars today , I will repay you in full next week .  \n Person2: Ok , but I'm taking your skateboard as collateral .  \n Person1:     Fine ! I can't believe you don't trust me . \n Person2: It's nothing personal , just business . ", "output": "0", "explanation": "The first question does begin with a question, therefore the classification result must be 1 instead of 0."}, {"input": "Person1:     I \u2019 m so surprised to meet you in this remote village . Long time no see . \n Person2: Yeah . How are you these days ? ", "output": "1", "explanation": "The first sentence contains a statement about the remote village, since it is not a question the output should be 0 instead of 1."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Dialogue"], "Instance": {"id": "task1534-862fcc20654748a398aca06143c68d0a", "input": " Person1:     Where do you want to go ?  \n Person2:  I am going to the Capital Hotel .  \n Person1:      Get in . I will take you there .  \n Person2:  About how much it will cost ?  \n Person1:      $ 50 .  \n Person2:  On the meter ?  \n Person1:      Ye , of course .  \n Person2:  OK.let ' s go . ", "output": ["1"]}, "Instance License": ["CC BY-NC-SA 4.0"], "prediction": "0"}
+{"id": "task1534-de63cca1efad41ffa32a0ed7e55f7cfe", "Task": "task1534_daily_dialog_question_classification", "Contributors": "['Krishna Sriharsha Gundu']", "Source": ["dailydialog"], "URL": ["https://huggingface.co/datasets/daily_dialog"], "Categories": ["Dialogue Act Recognition"], "Reasoning": [], "Definition": ["You are given a conversation between two people. 'Person1:' and 'Person2:' are used to separate their respective dialogues. If the conversation begins with a question, label it '1' otherwise '0'."], "Positive Examples": [{"input": "Person1:     Passport , please , madam . \n Person2: Just a minute , please . It's in my bag . Here it is . \n Person1:     Thank you . Please fill out the Baggage Declaration Form . \n Person2: All right . Shall I enter all my belongings ? \n Person1:     No , only the articles listed on the Declaration . ", "output": "0", "explanation": "The first sentence in the conversation begins with a request, therefore there is no presence of a question."}, {"input": " Person1:     Hi ! What are you watching ?  \n Person2:  It \u2019 s a program about islam . It \u2019 s very interesting .  \n Person1:      Wow ! So many people ! Where are they and what are they doing ?  \n Person2:  They are muslims on a pilgrimage to mecca . Muslims call this pilgrimage \u201c haj \u201d .  \n Person1:      Why do they go there ?  \n Person2:  Muslims believe that every man who is able should go on a haj at least once in his life . Mecca is the spiritual centre of the muslim faith .  \n Person1:      When muslims pray , they face towards mecca .  \n Person2:  That \u2019 s right . Unfortunately , so many people go on the haj each year that there are often stamped and people get killed .  \n Person1:      I heard about that . The pilgrims must walk around a large , sacred black stone .  \n Person2:  That \u2019 s right . That \u2019 s when accidents often happen . The Saudi government tries to limit the number of pilgrims , to reduce the chances of accidents .  \n Person1:      Pilgrimages are common in many faiths .  \n Person2:  Yes . In England , Christian pilgrims might go to Canterbury and many Christians go to the Vatican on pilgrimages .  \n Person1:      Isn \u2019 t there a place in france where people go to get healed ?  \n Person2:  I think that place is Lourdes . There are many stories of people being healed after visiting there .  \n Person1:      Do you think that there is something magical about that place ?  \n Person2:  Personally . I think that people believe they will be healed and that faith causes a change in their mind that cures them . I don \u2019 t think place is magical in any way . ", "output": "1", "explanation": "The first sentence contains a question, therefore the output is correctly mentioned as 1 "}, {"input": "Person1:     You look terrific and in good shape .  \n Person2: Thank you .  \n Person1:     How do you keep fit ?  \n Person2:  I do yoga twice a weeks  \n Person1:     Yoga ? It sounds interesting .  \n Person2: It was hard at the beginning , but now feel it's really relaxing . It makes me flexible .  \n Person1:     Anything else ?  \n Person2: Yes , I often go swimming .  \n Person1:     Are you interested in swimming ?  \n Person2: Yes , I like it very much . ", "output": "0", "explanation": "The first sentence is not a question, therefore the output is correct."}], "Negative Examples": [{"input": "Person1:     Can I borrow five bucks ? \n Person2:  No ! \n Person1:     Come on ! I'll pay you back on Tuesday . \n Person2: Last time I lent you money , you never paid me back . \n Person1:     I promise if you lend me five dollars today , I will repay you in full next week .  \n Person2: Ok , but I'm taking your skateboard as collateral .  \n Person1:     Fine ! I can't believe you don't trust me . \n Person2: It's nothing personal , just business . ", "output": "0", "explanation": "The first question does begin with a question, therefore the classification result must be 1 instead of 0."}, {"input": "Person1:     I \u2019 m so surprised to meet you in this remote village . Long time no see . \n Person2: Yeah . How are you these days ? ", "output": "1", "explanation": "The first sentence contains a statement about the remote village, since it is not a question the output should be 0 instead of 1."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Dialogue"], "Instance": {"id": "task1534-de63cca1efad41ffa32a0ed7e55f7cfe", "input": " Person1:     The stepmother was very wicked . She couldn't stand a happy smile on the boy's face .  \n Person2:  And ?  \n Person1:      And she did her best to pull out the thorn in her flesh and the boy lost whatever made him happy .  \n Person2:  Poor child ! ", "output": ["0"]}, "Instance License": ["CC BY-NC-SA 4.0"], "prediction": "0"}
+{"id": "task1540-add3e88a4a504e17956f0e8511c56a2d", "Task": "task1540_parsed_pdfs_summarization", "Contributors": "['Mamatha Juluru']", "Source": ["peer_read"], "URL": ["https://huggingface.co/datasets/peer_read"], "Categories": ["Title Generation"], "Reasoning": [], "Definition": ["In this task, you are given a part of an article. Your task is to generate headline (title) for this text. Preferred headlines are under fifteen words."], "Positive Examples": [{"input": "We propose a local coherence model based on a convolutional neural network that operates over the entity grid representation of a text. The model captures long range entity transitions along with entity-specific features without loosing generalization, thanks to the power of distributed representation. We present a pairwise ranking method to train the model in an end-to-end fashion on a task and learn task-specific high level features. Our evaluation on three different coherence assessment tasks demonstrates that our model achieves state of the art results outperforming existing models by a good margin.", "output": "A Neural Local Coherence Model", "explanation": "This statement \"A Neural Local Coherence Model\" is taken from the subtext \"convolutional neural network\" and its explanation in the passage. This is a positive example because the title belongs to the mentions in the passage"}, {"input": "We present four methods for recovering the epipolar geometry from images of smooth surfaces. In the existing methods for recovering epipolar geometry corresponding feature points are used that cannot be found in such images. The first method is based on finding corresponding characteristic points created by illumination (ICPM illumination characteristic points method). The second method is based on correspondent tangency points created by tangents from epipoles to outline of smooth bodies (OTPM outline tangent points method). These two methods are exact and give correct results for real images, because positions of the corresponding illumination characteristic points and corresponding outline are known with small errors. But the second method is limited either to special type of scenes or to restricted camera motion. We also consider two more methods which are termed CCPM (curve characteristic points method, green curves are used for this method on Figures) and CTPM (curve tangent points method, red curves are used for this method on Figures), for searching epipolar geometry for images of smooth bodies based on a set of level curves (isophoto curves) with a constant illumination intensity. The CCPM method is based on searching correspondent points on isophoto curves with the help of correlation of curvatures between these lines. The CTPM method is based on property of the tangential to isophoto curve epipolar line to map into the tangential to correspondent isophoto curves epipolar line. The standard method termed SM (standard method, blue curves are used for this method on Figures) and based on knowledge of pairs of the almost exact correspondent points, has been used for testing of these two methods. The main technical contributions of our CCPM method are following. The first of them consists of bounding the search space for epipole locations. On the face of it, this space is infinite and unbounded. We suggest a method to partition the infinite plane into a finite number of regions. This partition is based on the desired accuracy and maintains properties that yield an efficient search over the infinite plane. The second is an efficient method for finding correspondence between points of two closed isophoto curves and finding homography, mapping between these two isophoto curves. Then this homography is corrected for all possible epipole positions with the help of evaluation function. A finite subset of solution is chosen from the full set given by all possible epipole positions. This subset includes fundamental matrices giving local minimums of evaluating function close to global minimum. Epipoles of this subset lie almost on straight line directed parallel to parallax shift. CTPM method was used to find the best solution from this subset. Our method is applicable to any pair of images of smooth objects taken under perspective projection models, as long as assumption of the constant brightness is taken for granted. The methods have", "output": "Recovering Epipolar Geometry from Images of Smooth Surfaces", "explanation": "This statement \"Recovering Epipolar Geometry from Images of Smooth Surfaces\" is taken from the part of the passage \"recovering the epipolar geometry\" and its process description in the passage. This is a positive example because the title indicates the description mentioned in the passage."}, {"input": "Word sense disambiguation (WSD) is a problem in the field of computational linguistics given as finding the intended sense of a word (or a set of words) when it is activated within a certain context. WSD was recently addressed as a combinatorial optimization problem in which the goal is to find a sequence of senses that maximize the semantic relatedness among the target words. In this article, a novel algorithm for solving the WSD problem called D-Bees is proposed which is inspired by bee colony optimization (BCO) where artificial bee agents collaborate to solve the problem. The D-Bees algorithm is evaluated on a standard dataset (SemEval 2007 coarse-grained English all-words task corpus) and is compared to simulated annealing, genetic algorithms, and two ant colony optimization techniques (ACO). It will be observed that the BCO and ACO approaches are on par. 1 ar X iv :1 40 5. 14 06 v1 [ cs .C L ] 6 M ay 2 01 4", "output": "D-Bees: A Novel Method Inspired by Bee Colony Optimization for Solving Word Sense Disambiguation", "explanation": "This statement \"D-Bees: A Novel Method Inspired by Bee Colony Optimization for Solving Word Sense Disambiguation\" is an inference from the part of the passage \" a novel algorithm for solving the WSD problem called D-Bees is proposed which is inspired by bee colony optimization (BCO)\" and its description in the passage. This is a positive example because the title references to the explanation mentioned in the passage."}], "Negative Examples": [{"input": "Semantic role labelling (SRL) is a task in natural language processing which detects and classifies the semantic arguments associated with the predicates of a sentence. It is an important step towards understanding the meaning of a natural language. There exists SRL systems for well-studied languages like English, Chinese or Japanese but there is not any such system for the Vietnamese language. In this paper, we present the first SRL system for Vietnamese with encouraging accuracy. We first demonstrate that a simple application of SRL techniques developed for English could not give a good accuracy for Vietnamese. We then introduce a new algorithm for extracting candidate syntactic constituents, which is much more accurate than the common node-mapping algorithm usually used in the identification step. Finally, in the classification step, in addition to the common linguistic features, we propose novel and useful features for use in SRL. Our SRL system achieves an F1 score of 73.53% on the Vietnamese PropBank corpus. This system, including software and corpus, is available as an open source project and we believe that it is a good baseline for the development of future Vietnamese SRL systems.", "output": "History of Vietnamese language", "explanation": "The statement \"History of Vietnamese language\" is a negative example because it does not infer from the passage. It indicates that the passage is about the history of Vietnamese language but is infact about Semantic role labelling and its importance. "}, {"input": "This article presents the top-level of an ontology categorizing and generalizing best practices and quality criteria or measures for Linked Data. It permits to compare these techniques and have a synthetic organized view of what can or should be done for knowledge sharing purposes. This ontology is part of a general knowledge base that can be accessed and complemented by any Web user. Thus, it can be seen as a cooperatively built library for the above cited elements. Since they permit to evaluate information objects and create better ones, these elements also permit knowledgebased tools and techniques \u2013 as well as knowledge providers \u2013 to be evaluated and categorized based on their input/output information objects. One top-level distinction permitting to organize this ontology is the one between content, medium and containers of descriptions. Various structural, ontological, syntactical and lexical distinctions are then used.", "output": "Organization of Data", "explanation": "This statement \"Organization of Lined Data\" indicates that the passage is about ways to organize data. This is a negative example because the passage informs about ontology categrizing and generalizing and not about organization of data."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Computer Science"], "Instance": {"id": "task1540-add3e88a4a504e17956f0e8511c56a2d", "input": "Although traditionally used in the machine translation field, the encoder-decoder framework has been recently applied for the generation of video and image descriptions. The combination of Convolutional and Recurrent Neural Networks in these models has proven to outperform the previous state of the art, obtaining more accurate video descriptions. In this work we propose pushing further this model by introducing two contributions into the encoding stage. First, producing richer image representations by combining object and location information from Convolutional Neural Networks and second, introducing Bidirectional Recurrent Neural Networks for capturing both forward and backward temporal relationships in the input frames.", "output": ["Video Description using Bidirectional Recurrent Neural Networks"]}, "Instance License": ["CC BY 4.0"], "prediction": "Highlighting the contributions of Convolutional Neural Networks in Encoder-Decoder"}
+{"id": "task1540-8b56d0a230964ae9a29a4913fcfc0723", "Task": "task1540_parsed_pdfs_summarization", "Contributors": "['Mamatha Juluru']", "Source": ["peer_read"], "URL": ["https://huggingface.co/datasets/peer_read"], "Categories": ["Title Generation"], "Reasoning": [], "Definition": ["In this task, you are given a part of an article. Your task is to generate headline (title) for this text. Preferred headlines are under fifteen words."], "Positive Examples": [{"input": "We propose a local coherence model based on a convolutional neural network that operates over the entity grid representation of a text. The model captures long range entity transitions along with entity-specific features without loosing generalization, thanks to the power of distributed representation. We present a pairwise ranking method to train the model in an end-to-end fashion on a task and learn task-specific high level features. Our evaluation on three different coherence assessment tasks demonstrates that our model achieves state of the art results outperforming existing models by a good margin.", "output": "A Neural Local Coherence Model", "explanation": "This statement \"A Neural Local Coherence Model\" is taken from the subtext \"convolutional neural network\" and its explanation in the passage. This is a positive example because the title belongs to the mentions in the passage"}, {"input": "We present four methods for recovering the epipolar geometry from images of smooth surfaces. In the existing methods for recovering epipolar geometry corresponding feature points are used that cannot be found in such images. The first method is based on finding corresponding characteristic points created by illumination (ICPM illumination characteristic points method). The second method is based on correspondent tangency points created by tangents from epipoles to outline of smooth bodies (OTPM outline tangent points method). These two methods are exact and give correct results for real images, because positions of the corresponding illumination characteristic points and corresponding outline are known with small errors. But the second method is limited either to special type of scenes or to restricted camera motion. We also consider two more methods which are termed CCPM (curve characteristic points method, green curves are used for this method on Figures) and CTPM (curve tangent points method, red curves are used for this method on Figures), for searching epipolar geometry for images of smooth bodies based on a set of level curves (isophoto curves) with a constant illumination intensity. The CCPM method is based on searching correspondent points on isophoto curves with the help of correlation of curvatures between these lines. The CTPM method is based on property of the tangential to isophoto curve epipolar line to map into the tangential to correspondent isophoto curves epipolar line. The standard method termed SM (standard method, blue curves are used for this method on Figures) and based on knowledge of pairs of the almost exact correspondent points, has been used for testing of these two methods. The main technical contributions of our CCPM method are following. The first of them consists of bounding the search space for epipole locations. On the face of it, this space is infinite and unbounded. We suggest a method to partition the infinite plane into a finite number of regions. This partition is based on the desired accuracy and maintains properties that yield an efficient search over the infinite plane. The second is an efficient method for finding correspondence between points of two closed isophoto curves and finding homography, mapping between these two isophoto curves. Then this homography is corrected for all possible epipole positions with the help of evaluation function. A finite subset of solution is chosen from the full set given by all possible epipole positions. This subset includes fundamental matrices giving local minimums of evaluating function close to global minimum. Epipoles of this subset lie almost on straight line directed parallel to parallax shift. CTPM method was used to find the best solution from this subset. Our method is applicable to any pair of images of smooth objects taken under perspective projection models, as long as assumption of the constant brightness is taken for granted. The methods have", "output": "Recovering Epipolar Geometry from Images of Smooth Surfaces", "explanation": "This statement \"Recovering Epipolar Geometry from Images of Smooth Surfaces\" is taken from the part of the passage \"recovering the epipolar geometry\" and its process description in the passage. This is a positive example because the title indicates the description mentioned in the passage."}, {"input": "Word sense disambiguation (WSD) is a problem in the field of computational linguistics given as finding the intended sense of a word (or a set of words) when it is activated within a certain context. WSD was recently addressed as a combinatorial optimization problem in which the goal is to find a sequence of senses that maximize the semantic relatedness among the target words. In this article, a novel algorithm for solving the WSD problem called D-Bees is proposed which is inspired by bee colony optimization (BCO) where artificial bee agents collaborate to solve the problem. The D-Bees algorithm is evaluated on a standard dataset (SemEval 2007 coarse-grained English all-words task corpus) and is compared to simulated annealing, genetic algorithms, and two ant colony optimization techniques (ACO). It will be observed that the BCO and ACO approaches are on par. 1 ar X iv :1 40 5. 14 06 v1 [ cs .C L ] 6 M ay 2 01 4", "output": "D-Bees: A Novel Method Inspired by Bee Colony Optimization for Solving Word Sense Disambiguation", "explanation": "This statement \"D-Bees: A Novel Method Inspired by Bee Colony Optimization for Solving Word Sense Disambiguation\" is an inference from the part of the passage \" a novel algorithm for solving the WSD problem called D-Bees is proposed which is inspired by bee colony optimization (BCO)\" and its description in the passage. This is a positive example because the title references to the explanation mentioned in the passage."}], "Negative Examples": [{"input": "Semantic role labelling (SRL) is a task in natural language processing which detects and classifies the semantic arguments associated with the predicates of a sentence. It is an important step towards understanding the meaning of a natural language. There exists SRL systems for well-studied languages like English, Chinese or Japanese but there is not any such system for the Vietnamese language. In this paper, we present the first SRL system for Vietnamese with encouraging accuracy. We first demonstrate that a simple application of SRL techniques developed for English could not give a good accuracy for Vietnamese. We then introduce a new algorithm for extracting candidate syntactic constituents, which is much more accurate than the common node-mapping algorithm usually used in the identification step. Finally, in the classification step, in addition to the common linguistic features, we propose novel and useful features for use in SRL. Our SRL system achieves an F1 score of 73.53% on the Vietnamese PropBank corpus. This system, including software and corpus, is available as an open source project and we believe that it is a good baseline for the development of future Vietnamese SRL systems.", "output": "History of Vietnamese language", "explanation": "The statement \"History of Vietnamese language\" is a negative example because it does not infer from the passage. It indicates that the passage is about the history of Vietnamese language but is infact about Semantic role labelling and its importance. "}, {"input": "This article presents the top-level of an ontology categorizing and generalizing best practices and quality criteria or measures for Linked Data. It permits to compare these techniques and have a synthetic organized view of what can or should be done for knowledge sharing purposes. This ontology is part of a general knowledge base that can be accessed and complemented by any Web user. Thus, it can be seen as a cooperatively built library for the above cited elements. Since they permit to evaluate information objects and create better ones, these elements also permit knowledgebased tools and techniques \u2013 as well as knowledge providers \u2013 to be evaluated and categorized based on their input/output information objects. One top-level distinction permitting to organize this ontology is the one between content, medium and containers of descriptions. Various structural, ontological, syntactical and lexical distinctions are then used.", "output": "Organization of Data", "explanation": "This statement \"Organization of Lined Data\" indicates that the passage is about ways to organize data. This is a negative example because the passage informs about ontology categrizing and generalizing and not about organization of data."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Computer Science"], "Instance": {"id": "task1540-8b56d0a230964ae9a29a4913fcfc0723", "input": "Conventional dependency parsers rely on a statistical model and a transition system or graph algorithm to enforce tree-structured outputs during training and inference. In this work we formalize dependency parsing as the problem of selecting the head (a.k.a. parent) of each word in a sentence. Our model which we call DENSE (as shorthand for Dependency Neural Selection) employs bidirectional recurrent neural networks for the head selection task. Without enforcing any structural constraints during training, DENSE generates (at inference time) trees for the overwhelming majority of sentences (95% on an English dataset), while remaining non-tree outputs can be adjusted with a maximum spanning tree algorithm. We evaluate DENSE on four languages (English, Chinese, Czech, and German) with varying degrees of non-projectivity. Despite the simplicity of our approach, experiments show that the resulting parsers are on par with or outperform the state of the art.", "output": ["Dependency Parsing as Head Selection"]}, "Instance License": ["CC BY 4.0"], "prediction": "Dependency Neural Selection"}
+{"id": "task1540-001094e72c21467c9854e5d83b7cb8a9", "Task": "task1540_parsed_pdfs_summarization", "Contributors": "['Mamatha Juluru']", "Source": ["peer_read"], "URL": ["https://huggingface.co/datasets/peer_read"], "Categories": ["Title Generation"], "Reasoning": [], "Definition": ["In this task, you are given a part of an article. Your task is to generate headline (title) for this text. Preferred headlines are under fifteen words."], "Positive Examples": [{"input": "We propose a local coherence model based on a convolutional neural network that operates over the entity grid representation of a text. The model captures long range entity transitions along with entity-specific features without loosing generalization, thanks to the power of distributed representation. We present a pairwise ranking method to train the model in an end-to-end fashion on a task and learn task-specific high level features. Our evaluation on three different coherence assessment tasks demonstrates that our model achieves state of the art results outperforming existing models by a good margin.", "output": "A Neural Local Coherence Model", "explanation": "This statement \"A Neural Local Coherence Model\" is taken from the subtext \"convolutional neural network\" and its explanation in the passage. This is a positive example because the title belongs to the mentions in the passage"}, {"input": "We present four methods for recovering the epipolar geometry from images of smooth surfaces. In the existing methods for recovering epipolar geometry corresponding feature points are used that cannot be found in such images. The first method is based on finding corresponding characteristic points created by illumination (ICPM illumination characteristic points method). The second method is based on correspondent tangency points created by tangents from epipoles to outline of smooth bodies (OTPM outline tangent points method). These two methods are exact and give correct results for real images, because positions of the corresponding illumination characteristic points and corresponding outline are known with small errors. But the second method is limited either to special type of scenes or to restricted camera motion. We also consider two more methods which are termed CCPM (curve characteristic points method, green curves are used for this method on Figures) and CTPM (curve tangent points method, red curves are used for this method on Figures), for searching epipolar geometry for images of smooth bodies based on a set of level curves (isophoto curves) with a constant illumination intensity. The CCPM method is based on searching correspondent points on isophoto curves with the help of correlation of curvatures between these lines. The CTPM method is based on property of the tangential to isophoto curve epipolar line to map into the tangential to correspondent isophoto curves epipolar line. The standard method termed SM (standard method, blue curves are used for this method on Figures) and based on knowledge of pairs of the almost exact correspondent points, has been used for testing of these two methods. The main technical contributions of our CCPM method are following. The first of them consists of bounding the search space for epipole locations. On the face of it, this space is infinite and unbounded. We suggest a method to partition the infinite plane into a finite number of regions. This partition is based on the desired accuracy and maintains properties that yield an efficient search over the infinite plane. The second is an efficient method for finding correspondence between points of two closed isophoto curves and finding homography, mapping between these two isophoto curves. Then this homography is corrected for all possible epipole positions with the help of evaluation function. A finite subset of solution is chosen from the full set given by all possible epipole positions. This subset includes fundamental matrices giving local minimums of evaluating function close to global minimum. Epipoles of this subset lie almost on straight line directed parallel to parallax shift. CTPM method was used to find the best solution from this subset. Our method is applicable to any pair of images of smooth objects taken under perspective projection models, as long as assumption of the constant brightness is taken for granted. The methods have", "output": "Recovering Epipolar Geometry from Images of Smooth Surfaces", "explanation": "This statement \"Recovering Epipolar Geometry from Images of Smooth Surfaces\" is taken from the part of the passage \"recovering the epipolar geometry\" and its process description in the passage. This is a positive example because the title indicates the description mentioned in the passage."}, {"input": "Word sense disambiguation (WSD) is a problem in the field of computational linguistics given as finding the intended sense of a word (or a set of words) when it is activated within a certain context. WSD was recently addressed as a combinatorial optimization problem in which the goal is to find a sequence of senses that maximize the semantic relatedness among the target words. In this article, a novel algorithm for solving the WSD problem called D-Bees is proposed which is inspired by bee colony optimization (BCO) where artificial bee agents collaborate to solve the problem. The D-Bees algorithm is evaluated on a standard dataset (SemEval 2007 coarse-grained English all-words task corpus) and is compared to simulated annealing, genetic algorithms, and two ant colony optimization techniques (ACO). It will be observed that the BCO and ACO approaches are on par. 1 ar X iv :1 40 5. 14 06 v1 [ cs .C L ] 6 M ay 2 01 4", "output": "D-Bees: A Novel Method Inspired by Bee Colony Optimization for Solving Word Sense Disambiguation", "explanation": "This statement \"D-Bees: A Novel Method Inspired by Bee Colony Optimization for Solving Word Sense Disambiguation\" is an inference from the part of the passage \" a novel algorithm for solving the WSD problem called D-Bees is proposed which is inspired by bee colony optimization (BCO)\" and its description in the passage. This is a positive example because the title references to the explanation mentioned in the passage."}], "Negative Examples": [{"input": "Semantic role labelling (SRL) is a task in natural language processing which detects and classifies the semantic arguments associated with the predicates of a sentence. It is an important step towards understanding the meaning of a natural language. There exists SRL systems for well-studied languages like English, Chinese or Japanese but there is not any such system for the Vietnamese language. In this paper, we present the first SRL system for Vietnamese with encouraging accuracy. We first demonstrate that a simple application of SRL techniques developed for English could not give a good accuracy for Vietnamese. We then introduce a new algorithm for extracting candidate syntactic constituents, which is much more accurate than the common node-mapping algorithm usually used in the identification step. Finally, in the classification step, in addition to the common linguistic features, we propose novel and useful features for use in SRL. Our SRL system achieves an F1 score of 73.53% on the Vietnamese PropBank corpus. This system, including software and corpus, is available as an open source project and we believe that it is a good baseline for the development of future Vietnamese SRL systems.", "output": "History of Vietnamese language", "explanation": "The statement \"History of Vietnamese language\" is a negative example because it does not infer from the passage. It indicates that the passage is about the history of Vietnamese language but is infact about Semantic role labelling and its importance. "}, {"input": "This article presents the top-level of an ontology categorizing and generalizing best practices and quality criteria or measures for Linked Data. It permits to compare these techniques and have a synthetic organized view of what can or should be done for knowledge sharing purposes. This ontology is part of a general knowledge base that can be accessed and complemented by any Web user. Thus, it can be seen as a cooperatively built library for the above cited elements. Since they permit to evaluate information objects and create better ones, these elements also permit knowledgebased tools and techniques \u2013 as well as knowledge providers \u2013 to be evaluated and categorized based on their input/output information objects. One top-level distinction permitting to organize this ontology is the one between content, medium and containers of descriptions. Various structural, ontological, syntactical and lexical distinctions are then used.", "output": "Organization of Data", "explanation": "This statement \"Organization of Lined Data\" indicates that the passage is about ways to organize data. This is a negative example because the passage informs about ontology categrizing and generalizing and not about organization of data."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Computer Science"], "Instance": {"id": "task1540-001094e72c21467c9854e5d83b7cb8a9", "input": "We propose zoneout, a novel method for regularizing RNNs. At each timestep, zoneout stochastically forces some hidden units to maintain their previous values. Like dropout, zoneout uses random noise to train a pseudo-ensemble, improving generalization. But by preserving instead of dropping hidden units, gradient information and state information are more readily propagated through time, as in feedforward stochastic depth networks. We perform an empirical investigation of various RNN regularizers, and find encouraging results: zoneout gives significant performance improvements across tasks, yielding state-ofthe-art results in character-level language modeling on the Penn Treebank dataset and competitive results on word-level Penn Treebank and permuted sequential MNIST classification tasks.", "output": ["Zoneout: Regularizing RNNs by Randomly Preserving Hidden Activations"]}, "Instance License": ["CC BY 4.0"], "prediction": "Zoneout, a Novel Method for Regularizing RNNs"}
+{"id": "task1540-bd5de377b5ef404faf3704e08cb98acc", "Task": "task1540_parsed_pdfs_summarization", "Contributors": "['Mamatha Juluru']", "Source": ["peer_read"], "URL": ["https://huggingface.co/datasets/peer_read"], "Categories": ["Title Generation"], "Reasoning": [], "Definition": ["In this task, you are given a part of an article. Your task is to generate headline (title) for this text. Preferred headlines are under fifteen words."], "Positive Examples": [{"input": "We propose a local coherence model based on a convolutional neural network that operates over the entity grid representation of a text. The model captures long range entity transitions along with entity-specific features without loosing generalization, thanks to the power of distributed representation. We present a pairwise ranking method to train the model in an end-to-end fashion on a task and learn task-specific high level features. Our evaluation on three different coherence assessment tasks demonstrates that our model achieves state of the art results outperforming existing models by a good margin.", "output": "A Neural Local Coherence Model", "explanation": "This statement \"A Neural Local Coherence Model\" is taken from the subtext \"convolutional neural network\" and its explanation in the passage. This is a positive example because the title belongs to the mentions in the passage"}, {"input": "We present four methods for recovering the epipolar geometry from images of smooth surfaces. In the existing methods for recovering epipolar geometry corresponding feature points are used that cannot be found in such images. The first method is based on finding corresponding characteristic points created by illumination (ICPM illumination characteristic points method). The second method is based on correspondent tangency points created by tangents from epipoles to outline of smooth bodies (OTPM outline tangent points method). These two methods are exact and give correct results for real images, because positions of the corresponding illumination characteristic points and corresponding outline are known with small errors. But the second method is limited either to special type of scenes or to restricted camera motion. We also consider two more methods which are termed CCPM (curve characteristic points method, green curves are used for this method on Figures) and CTPM (curve tangent points method, red curves are used for this method on Figures), for searching epipolar geometry for images of smooth bodies based on a set of level curves (isophoto curves) with a constant illumination intensity. The CCPM method is based on searching correspondent points on isophoto curves with the help of correlation of curvatures between these lines. The CTPM method is based on property of the tangential to isophoto curve epipolar line to map into the tangential to correspondent isophoto curves epipolar line. The standard method termed SM (standard method, blue curves are used for this method on Figures) and based on knowledge of pairs of the almost exact correspondent points, has been used for testing of these two methods. The main technical contributions of our CCPM method are following. The first of them consists of bounding the search space for epipole locations. On the face of it, this space is infinite and unbounded. We suggest a method to partition the infinite plane into a finite number of regions. This partition is based on the desired accuracy and maintains properties that yield an efficient search over the infinite plane. The second is an efficient method for finding correspondence between points of two closed isophoto curves and finding homography, mapping between these two isophoto curves. Then this homography is corrected for all possible epipole positions with the help of evaluation function. A finite subset of solution is chosen from the full set given by all possible epipole positions. This subset includes fundamental matrices giving local minimums of evaluating function close to global minimum. Epipoles of this subset lie almost on straight line directed parallel to parallax shift. CTPM method was used to find the best solution from this subset. Our method is applicable to any pair of images of smooth objects taken under perspective projection models, as long as assumption of the constant brightness is taken for granted. The methods have", "output": "Recovering Epipolar Geometry from Images of Smooth Surfaces", "explanation": "This statement \"Recovering Epipolar Geometry from Images of Smooth Surfaces\" is taken from the part of the passage \"recovering the epipolar geometry\" and its process description in the passage. This is a positive example because the title indicates the description mentioned in the passage."}, {"input": "Word sense disambiguation (WSD) is a problem in the field of computational linguistics given as finding the intended sense of a word (or a set of words) when it is activated within a certain context. WSD was recently addressed as a combinatorial optimization problem in which the goal is to find a sequence of senses that maximize the semantic relatedness among the target words. In this article, a novel algorithm for solving the WSD problem called D-Bees is proposed which is inspired by bee colony optimization (BCO) where artificial bee agents collaborate to solve the problem. The D-Bees algorithm is evaluated on a standard dataset (SemEval 2007 coarse-grained English all-words task corpus) and is compared to simulated annealing, genetic algorithms, and two ant colony optimization techniques (ACO). It will be observed that the BCO and ACO approaches are on par. 1 ar X iv :1 40 5. 14 06 v1 [ cs .C L ] 6 M ay 2 01 4", "output": "D-Bees: A Novel Method Inspired by Bee Colony Optimization for Solving Word Sense Disambiguation", "explanation": "This statement \"D-Bees: A Novel Method Inspired by Bee Colony Optimization for Solving Word Sense Disambiguation\" is an inference from the part of the passage \" a novel algorithm for solving the WSD problem called D-Bees is proposed which is inspired by bee colony optimization (BCO)\" and its description in the passage. This is a positive example because the title references to the explanation mentioned in the passage."}], "Negative Examples": [{"input": "Semantic role labelling (SRL) is a task in natural language processing which detects and classifies the semantic arguments associated with the predicates of a sentence. It is an important step towards understanding the meaning of a natural language. There exists SRL systems for well-studied languages like English, Chinese or Japanese but there is not any such system for the Vietnamese language. In this paper, we present the first SRL system for Vietnamese with encouraging accuracy. We first demonstrate that a simple application of SRL techniques developed for English could not give a good accuracy for Vietnamese. We then introduce a new algorithm for extracting candidate syntactic constituents, which is much more accurate than the common node-mapping algorithm usually used in the identification step. Finally, in the classification step, in addition to the common linguistic features, we propose novel and useful features for use in SRL. Our SRL system achieves an F1 score of 73.53% on the Vietnamese PropBank corpus. This system, including software and corpus, is available as an open source project and we believe that it is a good baseline for the development of future Vietnamese SRL systems.", "output": "History of Vietnamese language", "explanation": "The statement \"History of Vietnamese language\" is a negative example because it does not infer from the passage. It indicates that the passage is about the history of Vietnamese language but is infact about Semantic role labelling and its importance. "}, {"input": "This article presents the top-level of an ontology categorizing and generalizing best practices and quality criteria or measures for Linked Data. It permits to compare these techniques and have a synthetic organized view of what can or should be done for knowledge sharing purposes. This ontology is part of a general knowledge base that can be accessed and complemented by any Web user. Thus, it can be seen as a cooperatively built library for the above cited elements. Since they permit to evaluate information objects and create better ones, these elements also permit knowledgebased tools and techniques \u2013 as well as knowledge providers \u2013 to be evaluated and categorized based on their input/output information objects. One top-level distinction permitting to organize this ontology is the one between content, medium and containers of descriptions. Various structural, ontological, syntactical and lexical distinctions are then used.", "output": "Organization of Data", "explanation": "This statement \"Organization of Lined Data\" indicates that the passage is about ways to organize data. This is a negative example because the passage informs about ontology categrizing and generalizing and not about organization of data."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Computer Science"], "Instance": {"id": "task1540-bd5de377b5ef404faf3704e08cb98acc", "input": "The field of Distributed Constraint Optimization has gained momentum in recent years, thanks to its ability to address various applications related to multi-agent cooperation. Nevertheless, solving Distributed Constraint Optimization Problems (DCOPs) optimally is NP-hard. Therefore, in large-scale, complex applications, incomplete DCOP algorithms are necessary. Current incomplete DCOP algorithms suffer of one or more of the following limitations: they (a) find local minima without providing quality guarantees; (b) provide loose quality assessment; or (c) are unable to benefit from the structure of the problem, such as domain-dependent knowledge and hard constraints. Therefore, capitalizing on strategies from the centralized constraint solving community, we propose a Distributed Large Neighborhood Search (D-LNS) framework to solve DCOPs. The proposed framework (with its novel repair phase) provides guarantees on solution quality, refining upper and lower bounds during the iterative process, and can exploit domain-dependent structures. Our experimental results show that D-LNS outperforms other incomplete DCOP algorithms on both structured and unstructured problem instances.", "output": ["Solving DCOPs with Distributed Large Neighborhood Search"]}, "Instance License": ["CC BY 4.0"], "prediction": "Distributed Large Neighborhood Search (D-LNS) framework for Distributed Constraint Optimization"}
+{"id": "task1540-8c934a14c1034bcc90fbfefdee44ac47", "Task": "task1540_parsed_pdfs_summarization", "Contributors": "['Mamatha Juluru']", "Source": ["peer_read"], "URL": ["https://huggingface.co/datasets/peer_read"], "Categories": ["Title Generation"], "Reasoning": [], "Definition": ["In this task, you are given a part of an article. Your task is to generate headline (title) for this text. Preferred headlines are under fifteen words."], "Positive Examples": [{"input": "We propose a local coherence model based on a convolutional neural network that operates over the entity grid representation of a text. The model captures long range entity transitions along with entity-specific features without loosing generalization, thanks to the power of distributed representation. We present a pairwise ranking method to train the model in an end-to-end fashion on a task and learn task-specific high level features. Our evaluation on three different coherence assessment tasks demonstrates that our model achieves state of the art results outperforming existing models by a good margin.", "output": "A Neural Local Coherence Model", "explanation": "This statement \"A Neural Local Coherence Model\" is taken from the subtext \"convolutional neural network\" and its explanation in the passage. This is a positive example because the title belongs to the mentions in the passage"}, {"input": "We present four methods for recovering the epipolar geometry from images of smooth surfaces. In the existing methods for recovering epipolar geometry corresponding feature points are used that cannot be found in such images. The first method is based on finding corresponding characteristic points created by illumination (ICPM illumination characteristic points method). The second method is based on correspondent tangency points created by tangents from epipoles to outline of smooth bodies (OTPM outline tangent points method). These two methods are exact and give correct results for real images, because positions of the corresponding illumination characteristic points and corresponding outline are known with small errors. But the second method is limited either to special type of scenes or to restricted camera motion. We also consider two more methods which are termed CCPM (curve characteristic points method, green curves are used for this method on Figures) and CTPM (curve tangent points method, red curves are used for this method on Figures), for searching epipolar geometry for images of smooth bodies based on a set of level curves (isophoto curves) with a constant illumination intensity. The CCPM method is based on searching correspondent points on isophoto curves with the help of correlation of curvatures between these lines. The CTPM method is based on property of the tangential to isophoto curve epipolar line to map into the tangential to correspondent isophoto curves epipolar line. The standard method termed SM (standard method, blue curves are used for this method on Figures) and based on knowledge of pairs of the almost exact correspondent points, has been used for testing of these two methods. The main technical contributions of our CCPM method are following. The first of them consists of bounding the search space for epipole locations. On the face of it, this space is infinite and unbounded. We suggest a method to partition the infinite plane into a finite number of regions. This partition is based on the desired accuracy and maintains properties that yield an efficient search over the infinite plane. The second is an efficient method for finding correspondence between points of two closed isophoto curves and finding homography, mapping between these two isophoto curves. Then this homography is corrected for all possible epipole positions with the help of evaluation function. A finite subset of solution is chosen from the full set given by all possible epipole positions. This subset includes fundamental matrices giving local minimums of evaluating function close to global minimum. Epipoles of this subset lie almost on straight line directed parallel to parallax shift. CTPM method was used to find the best solution from this subset. Our method is applicable to any pair of images of smooth objects taken under perspective projection models, as long as assumption of the constant brightness is taken for granted. The methods have", "output": "Recovering Epipolar Geometry from Images of Smooth Surfaces", "explanation": "This statement \"Recovering Epipolar Geometry from Images of Smooth Surfaces\" is taken from the part of the passage \"recovering the epipolar geometry\" and its process description in the passage. This is a positive example because the title indicates the description mentioned in the passage."}, {"input": "Word sense disambiguation (WSD) is a problem in the field of computational linguistics given as finding the intended sense of a word (or a set of words) when it is activated within a certain context. WSD was recently addressed as a combinatorial optimization problem in which the goal is to find a sequence of senses that maximize the semantic relatedness among the target words. In this article, a novel algorithm for solving the WSD problem called D-Bees is proposed which is inspired by bee colony optimization (BCO) where artificial bee agents collaborate to solve the problem. The D-Bees algorithm is evaluated on a standard dataset (SemEval 2007 coarse-grained English all-words task corpus) and is compared to simulated annealing, genetic algorithms, and two ant colony optimization techniques (ACO). It will be observed that the BCO and ACO approaches are on par. 1 ar X iv :1 40 5. 14 06 v1 [ cs .C L ] 6 M ay 2 01 4", "output": "D-Bees: A Novel Method Inspired by Bee Colony Optimization for Solving Word Sense Disambiguation", "explanation": "This statement \"D-Bees: A Novel Method Inspired by Bee Colony Optimization for Solving Word Sense Disambiguation\" is an inference from the part of the passage \" a novel algorithm for solving the WSD problem called D-Bees is proposed which is inspired by bee colony optimization (BCO)\" and its description in the passage. This is a positive example because the title references to the explanation mentioned in the passage."}], "Negative Examples": [{"input": "Semantic role labelling (SRL) is a task in natural language processing which detects and classifies the semantic arguments associated with the predicates of a sentence. It is an important step towards understanding the meaning of a natural language. There exists SRL systems for well-studied languages like English, Chinese or Japanese but there is not any such system for the Vietnamese language. In this paper, we present the first SRL system for Vietnamese with encouraging accuracy. We first demonstrate that a simple application of SRL techniques developed for English could not give a good accuracy for Vietnamese. We then introduce a new algorithm for extracting candidate syntactic constituents, which is much more accurate than the common node-mapping algorithm usually used in the identification step. Finally, in the classification step, in addition to the common linguistic features, we propose novel and useful features for use in SRL. Our SRL system achieves an F1 score of 73.53% on the Vietnamese PropBank corpus. This system, including software and corpus, is available as an open source project and we believe that it is a good baseline for the development of future Vietnamese SRL systems.", "output": "History of Vietnamese language", "explanation": "The statement \"History of Vietnamese language\" is a negative example because it does not infer from the passage. It indicates that the passage is about the history of Vietnamese language but is infact about Semantic role labelling and its importance. "}, {"input": "This article presents the top-level of an ontology categorizing and generalizing best practices and quality criteria or measures for Linked Data. It permits to compare these techniques and have a synthetic organized view of what can or should be done for knowledge sharing purposes. This ontology is part of a general knowledge base that can be accessed and complemented by any Web user. Thus, it can be seen as a cooperatively built library for the above cited elements. Since they permit to evaluate information objects and create better ones, these elements also permit knowledgebased tools and techniques \u2013 as well as knowledge providers \u2013 to be evaluated and categorized based on their input/output information objects. One top-level distinction permitting to organize this ontology is the one between content, medium and containers of descriptions. Various structural, ontological, syntactical and lexical distinctions are then used.", "output": "Organization of Data", "explanation": "This statement \"Organization of Lined Data\" indicates that the passage is about ways to organize data. This is a negative example because the passage informs about ontology categrizing and generalizing and not about organization of data."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Computer Science"], "Instance": {"id": "task1540-8c934a14c1034bcc90fbfefdee44ac47", "input": "We describe here a methodology to identify a list of ambiguous Malay words that are commonly being used in Malay documentations such as Requirement Specification. We compiled several relevant and appropriate requirement quality attributes and sentence rules from previous literatures and adopt it to come out with a set of ambiguity attributes that most suit Malay words. The extracted Malay ambiguous words (potential) are then being mapped onto the constructed ambiguity attributes to confirm their vagueness. The list is then verified by Malay linguist experts. This paper aims to identify a list of potential ambiguous words in Malay as an attempt to assist writers to avoid using the vague words while documenting Malay Requirement Specification as well as to any other related Malay documentation. The result of this study is a list of 120 potential ambiguous Malay words that could act as guidelines in writing Malay sentences.", "output": ["MAPPING: AN EXPLORATORY STUDY"]}, "Instance License": ["CC BY 4.0"], "prediction": "Identifies ambiguous words in Malay"}
+{"id": "task442-4bd839b4a05e400ebdb885561ae7d1d2", "Task": "task442_com_qa_paraphrase_question_generation", "Contributors": "['Arut Selvan Dhanasekaran']", "Source": ["com_qa"], "URL": ["https://huggingface.co/datasets/com_qa"], "Categories": ["Question Rewriting"], "Reasoning": [], "Definition": ["Given a question, generate a paraphrase of that question wihout changing the meaning of it. Your answer should reword the given sentence, but not add information to it or remove information from it. The answer to your question should be the same as the answer to the original question."], "Positive Examples": [{"input": "Question: what places in Africa do people speak french?", "output": "where in africa do people speak french?", "explanation": "The generated question means the same as the input question and the answer is the same, so this is a good answer."}, {"input": "Question: Hitler became chancellor of Germany in what year?", "output": "In which year did Hitler become the chancellor of Germany?", "explanation": "The answer for the generated question and the given question can be given by a single date, and it is a good rewording."}, {"input": "Question: mandeville Lousiana zip code?", "output": "what is the zip code for mandeville Louisiana?", "explanation": "The rephrased question exactly means the same as the given question."}], "Negative Examples": [{"input": "Question: How long is the Nile river?", "output": "Is Nile the longest river?", "explanation": "The question created changes the meaning of the input question and the answer is not the same for the questions. This is not a good answer."}, {"input": "Question: Who is the first football player to win seven balon d'ors?", "output": "Who won the first balon dor?", "explanation": "The generated question don't mean the same as the original question and the answers are different for each question. This is not a good answer."}, {"input": "Question: How Vitamin C helps the human body?", "output": "Does Vitamin C help the human body?", "explanation": "The generated question changed the meaning of the given question. This is not a good answer."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Web"], "Instance": {"id": "task442-4bd839b4a05e400ebdb885561ae7d1d2", "input": "Question: what is the highest point of puerto rico?", "output": ["what is the highest point in puerto rico?", "highest point in puerto rico?", "what is the tallest point in puerto rico?", "what is puerto rico's highest point?"]}, "Instance License": ["Unknown"], "prediction": "what is the highest point of puerto rico?"}
+{"id": "task442-6478eae566314cadb1eb134cce3661de", "Task": "task442_com_qa_paraphrase_question_generation", "Contributors": "['Arut Selvan Dhanasekaran']", "Source": ["com_qa"], "URL": ["https://huggingface.co/datasets/com_qa"], "Categories": ["Question Rewriting"], "Reasoning": [], "Definition": ["Given a question, generate a paraphrase of that question wihout changing the meaning of it. Your answer should reword the given sentence, but not add information to it or remove information from it. The answer to your question should be the same as the answer to the original question."], "Positive Examples": [{"input": "Question: what places in Africa do people speak french?", "output": "where in africa do people speak french?", "explanation": "The generated question means the same as the input question and the answer is the same, so this is a good answer."}, {"input": "Question: Hitler became chancellor of Germany in what year?", "output": "In which year did Hitler become the chancellor of Germany?", "explanation": "The answer for the generated question and the given question can be given by a single date, and it is a good rewording."}, {"input": "Question: mandeville Lousiana zip code?", "output": "what is the zip code for mandeville Louisiana?", "explanation": "The rephrased question exactly means the same as the given question."}], "Negative Examples": [{"input": "Question: How long is the Nile river?", "output": "Is Nile the longest river?", "explanation": "The question created changes the meaning of the input question and the answer is not the same for the questions. This is not a good answer."}, {"input": "Question: Who is the first football player to win seven balon d'ors?", "output": "Who won the first balon dor?", "explanation": "The generated question don't mean the same as the original question and the answers are different for each question. This is not a good answer."}, {"input": "Question: How Vitamin C helps the human body?", "output": "Does Vitamin C help the human body?", "explanation": "The generated question changed the meaning of the given question. This is not a good answer."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Web"], "Instance": {"id": "task442-6478eae566314cadb1eb134cce3661de", "input": "Question: what date did hernando de soto die?", "output": ["what month did hernando de soto die?", "when did hernando de soto die?", "what is hernando de soto date of death?"]}, "Instance License": ["Unknown"], "prediction": "when did hernando de soto die?"}
+{"id": "task442-75804b8de01c48a2acba8cf60b10f0cf", "Task": "task442_com_qa_paraphrase_question_generation", "Contributors": "['Arut Selvan Dhanasekaran']", "Source": ["com_qa"], "URL": ["https://huggingface.co/datasets/com_qa"], "Categories": ["Question Rewriting"], "Reasoning": [], "Definition": ["Given a question, generate a paraphrase of that question wihout changing the meaning of it. Your answer should reword the given sentence, but not add information to it or remove information from it. The answer to your question should be the same as the answer to the original question."], "Positive Examples": [{"input": "Question: what places in Africa do people speak french?", "output": "where in africa do people speak french?", "explanation": "The generated question means the same as the input question and the answer is the same, so this is a good answer."}, {"input": "Question: Hitler became chancellor of Germany in what year?", "output": "In which year did Hitler become the chancellor of Germany?", "explanation": "The answer for the generated question and the given question can be given by a single date, and it is a good rewording."}, {"input": "Question: mandeville Lousiana zip code?", "output": "what is the zip code for mandeville Louisiana?", "explanation": "The rephrased question exactly means the same as the given question."}], "Negative Examples": [{"input": "Question: How long is the Nile river?", "output": "Is Nile the longest river?", "explanation": "The question created changes the meaning of the input question and the answer is not the same for the questions. This is not a good answer."}, {"input": "Question: Who is the first football player to win seven balon d'ors?", "output": "Who won the first balon dor?", "explanation": "The generated question don't mean the same as the original question and the answers are different for each question. This is not a good answer."}, {"input": "Question: How Vitamin C helps the human body?", "output": "Does Vitamin C help the human body?", "explanation": "The generated question changed the meaning of the given question. This is not a good answer."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Web"], "Instance": {"id": "task442-75804b8de01c48a2acba8cf60b10f0cf", "input": "Question: what sea divides denmark and sweden?", "output": ["what sea borders southern sweden and denmark?", "which sea lies beside sweeden and denmark?", "what sea separates denmark and sweden?", "what sea is between denmark and sweden?"]}, "Instance License": ["Unknown"], "prediction": "what sea divides denmark and sweden?"}
+{"id": "task442-89dea81db93a45d19a6311f6661be75c", "Task": "task442_com_qa_paraphrase_question_generation", "Contributors": "['Arut Selvan Dhanasekaran']", "Source": ["com_qa"], "URL": ["https://huggingface.co/datasets/com_qa"], "Categories": ["Question Rewriting"], "Reasoning": [], "Definition": ["Given a question, generate a paraphrase of that question wihout changing the meaning of it. Your answer should reword the given sentence, but not add information to it or remove information from it. The answer to your question should be the same as the answer to the original question."], "Positive Examples": [{"input": "Question: what places in Africa do people speak french?", "output": "where in africa do people speak french?", "explanation": "The generated question means the same as the input question and the answer is the same, so this is a good answer."}, {"input": "Question: Hitler became chancellor of Germany in what year?", "output": "In which year did Hitler become the chancellor of Germany?", "explanation": "The answer for the generated question and the given question can be given by a single date, and it is a good rewording."}, {"input": "Question: mandeville Lousiana zip code?", "output": "what is the zip code for mandeville Louisiana?", "explanation": "The rephrased question exactly means the same as the given question."}], "Negative Examples": [{"input": "Question: How long is the Nile river?", "output": "Is Nile the longest river?", "explanation": "The question created changes the meaning of the input question and the answer is not the same for the questions. This is not a good answer."}, {"input": "Question: Who is the first football player to win seven balon d'ors?", "output": "Who won the first balon dor?", "explanation": "The generated question don't mean the same as the original question and the answers are different for each question. This is not a good answer."}, {"input": "Question: How Vitamin C helps the human body?", "output": "Does Vitamin C help the human body?", "explanation": "The generated question changed the meaning of the given question. This is not a good answer."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Web"], "Instance": {"id": "task442-89dea81db93a45d19a6311f6661be75c", "input": "Question: president nixon children's names?", "output": ["what where the names president children?", "who was ricahard m nixon children names?", "who are nixons children?", "names of nixons children?", "what was the names of president nixons children?", "what is president nixons childrens names?"]}, "Instance License": ["Unknown"], "prediction": "president nixon children's names?"}
+{"id": "task442-49ca971a2b964785a121866db6b113e0", "Task": "task442_com_qa_paraphrase_question_generation", "Contributors": "['Arut Selvan Dhanasekaran']", "Source": ["com_qa"], "URL": ["https://huggingface.co/datasets/com_qa"], "Categories": ["Question Rewriting"], "Reasoning": [], "Definition": ["Given a question, generate a paraphrase of that question wihout changing the meaning of it. Your answer should reword the given sentence, but not add information to it or remove information from it. The answer to your question should be the same as the answer to the original question."], "Positive Examples": [{"input": "Question: what places in Africa do people speak french?", "output": "where in africa do people speak french?", "explanation": "The generated question means the same as the input question and the answer is the same, so this is a good answer."}, {"input": "Question: Hitler became chancellor of Germany in what year?", "output": "In which year did Hitler become the chancellor of Germany?", "explanation": "The answer for the generated question and the given question can be given by a single date, and it is a good rewording."}, {"input": "Question: mandeville Lousiana zip code?", "output": "what is the zip code for mandeville Louisiana?", "explanation": "The rephrased question exactly means the same as the given question."}], "Negative Examples": [{"input": "Question: How long is the Nile river?", "output": "Is Nile the longest river?", "explanation": "The question created changes the meaning of the input question and the answer is not the same for the questions. This is not a good answer."}, {"input": "Question: Who is the first football player to win seven balon d'ors?", "output": "Who won the first balon dor?", "explanation": "The generated question don't mean the same as the original question and the answers are different for each question. This is not a good answer."}, {"input": "Question: How Vitamin C helps the human body?", "output": "Does Vitamin C help the human body?", "explanation": "The generated question changed the meaning of the given question. This is not a good answer."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Web"], "Instance": {"id": "task442-49ca971a2b964785a121866db6b113e0", "input": "Question: what was the title of bob dylans first album?", "output": ["what was bob dylans first album?", "what was bob dylan's first album called?"]}, "Instance License": ["Unknown"], "prediction": "What was the title of Bob Dylans first album?"}
+{"id": "task392-bc9eda364c92499e8802a9814fd159e5", "Task": "task392_inverse_causal_relationship", "Contributors": "['Pegah Alipoormolabashi']", "Source": ["cod3s"], "URL": ["https://aclanthology.org/2020.emnlp-main.421.pdf"], "Categories": ["Cause Effect Classification"], "Reasoning": ["Causal Reasoning", "Textual Entailment"], "Definition": ["In this task, you will be given two sentences separated by \"because\". You should decide whether the first sentence can be the result of the second sentence. If you can see a possible cause and effect relationship, answer with \"plausible\", otherwise answer with \"not plausible\"."], "Positive Examples": [{"input": "The woman went to the bank because pigs can fly.", "output": "not plausible", "explanation": "Clearly, there can't be a causation relationship between someone going to the bank and pigs flying."}, {"input": "The women went to the bank because she didn't have enough cash on hand", "output": "plausible", "explanation": "The second sentence can be cause of the first sentence, so the correct answer here is plausible."}, {"input": "the boy felt homesick because he had died", "output": "not plausible", "explanation": "Someone can not feel homesick after they are dead."}], "Negative Examples": [{"input": "The woman went to see a lawyer because she was getting a divorce.", "output": "not plausible", "explanation": "Willing to get a divorce can be a valid cause to see a lawyer, so the correct answer is plausible."}, {"input": "a crater formed on the moon because it had to be", "output": "plausible", "explanation": "In the vague and meaningless cases like this, answer with \"not plausible\"."}, {"input": "the customer filed a complaint with the store manager because the service was poor", "output": "true", "explanation": "This is a plausible causal relationship, but you should only answer with \"plausible\" and \"not plausible\"."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Commonsense"], "Instance": {"id": "task392-bc9eda364c92499e8802a9814fd159e5", "input": "the hospital sent the patient home because he was coughing too much", "output": ["not plausible"]}, "Instance License": ["MIT"], "prediction": "plausible"}
+{"id": "task392-31ac77be6fce47099eb09d5cc0ff60d6", "Task": "task392_inverse_causal_relationship", "Contributors": "['Pegah Alipoormolabashi']", "Source": ["cod3s"], "URL": ["https://aclanthology.org/2020.emnlp-main.421.pdf"], "Categories": ["Cause Effect Classification"], "Reasoning": ["Causal Reasoning", "Textual Entailment"], "Definition": ["In this task, you will be given two sentences separated by \"because\". You should decide whether the first sentence can be the result of the second sentence. If you can see a possible cause and effect relationship, answer with \"plausible\", otherwise answer with \"not plausible\"."], "Positive Examples": [{"input": "The woman went to the bank because pigs can fly.", "output": "not plausible", "explanation": "Clearly, there can't be a causation relationship between someone going to the bank and pigs flying."}, {"input": "The women went to the bank because she didn't have enough cash on hand", "output": "plausible", "explanation": "The second sentence can be cause of the first sentence, so the correct answer here is plausible."}, {"input": "the boy felt homesick because he had died", "output": "not plausible", "explanation": "Someone can not feel homesick after they are dead."}], "Negative Examples": [{"input": "The woman went to see a lawyer because she was getting a divorce.", "output": "not plausible", "explanation": "Willing to get a divorce can be a valid cause to see a lawyer, so the correct answer is plausible."}, {"input": "a crater formed on the moon because it had to be", "output": "plausible", "explanation": "In the vague and meaningless cases like this, answer with \"not plausible\"."}, {"input": "the customer filed a complaint with the store manager because the service was poor", "output": "true", "explanation": "This is a plausible causal relationship, but you should only answer with \"plausible\" and \"not plausible\"."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Commonsense"], "Instance": {"id": "task392-31ac77be6fce47099eb09d5cc0ff60d6", "input": "the man went away for the weekend because he wanted to relax", "output": ["plausible"]}, "Instance License": ["MIT"], "prediction": "plausible"}
+{"id": "task392-f5877013ceed4594839d987b0bb011d2", "Task": "task392_inverse_causal_relationship", "Contributors": "['Pegah Alipoormolabashi']", "Source": ["cod3s"], "URL": ["https://aclanthology.org/2020.emnlp-main.421.pdf"], "Categories": ["Cause Effect Classification"], "Reasoning": ["Causal Reasoning", "Textual Entailment"], "Definition": ["In this task, you will be given two sentences separated by \"because\". You should decide whether the first sentence can be the result of the second sentence. If you can see a possible cause and effect relationship, answer with \"plausible\", otherwise answer with \"not plausible\"."], "Positive Examples": [{"input": "The woman went to the bank because pigs can fly.", "output": "not plausible", "explanation": "Clearly, there can't be a causation relationship between someone going to the bank and pigs flying."}, {"input": "The women went to the bank because she didn't have enough cash on hand", "output": "plausible", "explanation": "The second sentence can be cause of the first sentence, so the correct answer here is plausible."}, {"input": "the boy felt homesick because he had died", "output": "not plausible", "explanation": "Someone can not feel homesick after they are dead."}], "Negative Examples": [{"input": "The woman went to see a lawyer because she was getting a divorce.", "output": "not plausible", "explanation": "Willing to get a divorce can be a valid cause to see a lawyer, so the correct answer is plausible."}, {"input": "a crater formed on the moon because it had to be", "output": "plausible", "explanation": "In the vague and meaningless cases like this, answer with \"not plausible\"."}, {"input": "the customer filed a complaint with the store manager because the service was poor", "output": "true", "explanation": "This is a plausible causal relationship, but you should only answer with \"plausible\" and \"not plausible\"."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Commonsense"], "Instance": {"id": "task392-f5877013ceed4594839d987b0bb011d2", "input": "the benefactor requested to stay anonymous because he didn't want to lose his job", "output": ["plausible"]}, "Instance License": ["MIT"], "prediction": "plausible"}
+{"id": "task392-42c55f2f8b9f4ac8acc61f1e96d9b1d1", "Task": "task392_inverse_causal_relationship", "Contributors": "['Pegah Alipoormolabashi']", "Source": ["cod3s"], "URL": ["https://aclanthology.org/2020.emnlp-main.421.pdf"], "Categories": ["Cause Effect Classification"], "Reasoning": ["Causal Reasoning", "Textual Entailment"], "Definition": ["In this task, you will be given two sentences separated by \"because\". You should decide whether the first sentence can be the result of the second sentence. If you can see a possible cause and effect relationship, answer with \"plausible\", otherwise answer with \"not plausible\"."], "Positive Examples": [{"input": "The woman went to the bank because pigs can fly.", "output": "not plausible", "explanation": "Clearly, there can't be a causation relationship between someone going to the bank and pigs flying."}, {"input": "The women went to the bank because she didn't have enough cash on hand", "output": "plausible", "explanation": "The second sentence can be cause of the first sentence, so the correct answer here is plausible."}, {"input": "the boy felt homesick because he had died", "output": "not plausible", "explanation": "Someone can not feel homesick after they are dead."}], "Negative Examples": [{"input": "The woman went to see a lawyer because she was getting a divorce.", "output": "not plausible", "explanation": "Willing to get a divorce can be a valid cause to see a lawyer, so the correct answer is plausible."}, {"input": "a crater formed on the moon because it had to be", "output": "plausible", "explanation": "In the vague and meaningless cases like this, answer with \"not plausible\"."}, {"input": "the customer filed a complaint with the store manager because the service was poor", "output": "true", "explanation": "This is a plausible causal relationship, but you should only answer with \"plausible\" and \"not plausible\"."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Commonsense"], "Instance": {"id": "task392-42c55f2f8b9f4ac8acc61f1e96d9b1d1", "input": "my flight got delayed because I didn't have a driver's license", "output": ["not plausible"]}, "Instance License": ["MIT"], "prediction": "plausible"}
+{"id": "task392-48e0c21d0cd54365b7467d14f1926d43", "Task": "task392_inverse_causal_relationship", "Contributors": "['Pegah Alipoormolabashi']", "Source": ["cod3s"], "URL": ["https://aclanthology.org/2020.emnlp-main.421.pdf"], "Categories": ["Cause Effect Classification"], "Reasoning": ["Causal Reasoning", "Textual Entailment"], "Definition": ["In this task, you will be given two sentences separated by \"because\". You should decide whether the first sentence can be the result of the second sentence. If you can see a possible cause and effect relationship, answer with \"plausible\", otherwise answer with \"not plausible\"."], "Positive Examples": [{"input": "The woman went to the bank because pigs can fly.", "output": "not plausible", "explanation": "Clearly, there can't be a causation relationship between someone going to the bank and pigs flying."}, {"input": "The women went to the bank because she didn't have enough cash on hand", "output": "plausible", "explanation": "The second sentence can be cause of the first sentence, so the correct answer here is plausible."}, {"input": "the boy felt homesick because he had died", "output": "not plausible", "explanation": "Someone can not feel homesick after they are dead."}], "Negative Examples": [{"input": "The woman went to see a lawyer because she was getting a divorce.", "output": "not plausible", "explanation": "Willing to get a divorce can be a valid cause to see a lawyer, so the correct answer is plausible."}, {"input": "a crater formed on the moon because it had to be", "output": "plausible", "explanation": "In the vague and meaningless cases like this, answer with \"not plausible\"."}, {"input": "the customer filed a complaint with the store manager because the service was poor", "output": "true", "explanation": "This is a plausible causal relationship, but you should only answer with \"plausible\" and \"not plausible\"."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Commonsense"], "Instance": {"id": "task392-48e0c21d0cd54365b7467d14f1926d43", "input": "the trip took a long time because the weather was so bad", "output": ["plausible"]}, "Instance License": ["MIT"], "prediction": "plausible"}
+{"id": "task1562-7bcf62c5e1a7428f8918c0f04e26b6b9", "Task": "task1562_zest_text_modification", "Contributors": "['Yeganeh Kordi']", "Source": ["zest"], "URL": ["https://github.com/allenai/zest"], "Categories": ["Question Rewriting"], "Reasoning": [], "Definition": ["Paraphrase the given questions to have different wording. Your paraphrased questions should have the same answer as the original question. Try to change the sentence as much as possible using synonyms and/or rearranging the structure of the sentence. The questions are in three domains: presidents, national parks, and dogs. Each question has a keyword indicating its domain. Keywords are \"this national park\", \"this dog breed\", and \"this president\", which will be replaced with the name of an actual president, a national park, or a breed of dog. Hence, in paraphrasing, this keyword should also be used the same way. Do not write questions that compare or involve multiple domains. Do not write open-ended or subjective questions (e.g., questions that can be answered differently by different people.) Make your questions specific and concrete. Your question should have the same type of answer as the original question(e.g., if the question is extractive, the paraphrased question should be extractive as well.)"], "Positive Examples": [{"input": "Does this dog breed have short legs compared to the rest of its body?", "output": "Is the body of this dog breed large compared to its legs?", "explanation": "The output has the same meaning and same answer as the original sentence. We changed the first sentence by rearranging the structure of the sentence. "}, {"input": "Does this dog breed have short legs compared to the rest of its body?", "output": "Are the legs of this dog breed proportionally shorter than its body?", "explanation": "The original sentence is changed by using synonyms and rearranging the structure of the sentence. Also, it keeps the meaning and answer."}, {"input": "Does this dog breed have an average life expectancy range that can be more than 12 years?", "output": "Does this dog breed have a lifespan of more than 12 years?", "explanation": "The \"average life expectancy range\" is replaced with \"lifespan\" and it keeps the original meaning. "}], "Negative Examples": [{"input": "Does this dog breed get taller than 2 feet?", "output": "Is this dog breed tall?", "explanation": "This question is vague because it didn't specify tallness. Make your questions specific and concrete rather than open-ended or subjective."}, {"input": "Is this dog breed bigger than 12 inches?", "output": "Is this dog breed the biggest?", "explanation": "Do not write questions that compare domains."}, {"input": "Does this dog breed have short legs compared to the rest of its body?", "output": "What size legs does this dog breed have?", "explanation": "The question should have the same type of answer as the original."}, {"input": "Does this dog breed have short legs compared to the rest of its body?", "output": "Does this dog breed have a large muzzle?", "explanation": "This is a bad question because the question should have the same meaning as the given sentence."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Government and Politics"], "Instance": {"id": "task1562-7bcf62c5e1a7428f8918c0f04e26b6b9", "input": "Do any endangered animals live inside this national park?", "output": ["Are there endangered species at this national park?"]}, "Instance License": ["Apache 2.0"], "prediction": "Are any endangered animals living in this national park?"}
+{"id": "task1562-9e378fb1c6874f769baf4600db8a341f", "Task": "task1562_zest_text_modification", "Contributors": "['Yeganeh Kordi']", "Source": ["zest"], "URL": ["https://github.com/allenai/zest"], "Categories": ["Question Rewriting"], "Reasoning": [], "Definition": ["Paraphrase the given questions to have different wording. Your paraphrased questions should have the same answer as the original question. Try to change the sentence as much as possible using synonyms and/or rearranging the structure of the sentence. The questions are in three domains: presidents, national parks, and dogs. Each question has a keyword indicating its domain. Keywords are \"this national park\", \"this dog breed\", and \"this president\", which will be replaced with the name of an actual president, a national park, or a breed of dog. Hence, in paraphrasing, this keyword should also be used the same way. Do not write questions that compare or involve multiple domains. Do not write open-ended or subjective questions (e.g., questions that can be answered differently by different people.) Make your questions specific and concrete. Your question should have the same type of answer as the original question(e.g., if the question is extractive, the paraphrased question should be extractive as well.)"], "Positive Examples": [{"input": "Does this dog breed have short legs compared to the rest of its body?", "output": "Is the body of this dog breed large compared to its legs?", "explanation": "The output has the same meaning and same answer as the original sentence. We changed the first sentence by rearranging the structure of the sentence. "}, {"input": "Does this dog breed have short legs compared to the rest of its body?", "output": "Are the legs of this dog breed proportionally shorter than its body?", "explanation": "The original sentence is changed by using synonyms and rearranging the structure of the sentence. Also, it keeps the meaning and answer."}, {"input": "Does this dog breed have an average life expectancy range that can be more than 12 years?", "output": "Does this dog breed have a lifespan of more than 12 years?", "explanation": "The \"average life expectancy range\" is replaced with \"lifespan\" and it keeps the original meaning. "}], "Negative Examples": [{"input": "Does this dog breed get taller than 2 feet?", "output": "Is this dog breed tall?", "explanation": "This question is vague because it didn't specify tallness. Make your questions specific and concrete rather than open-ended or subjective."}, {"input": "Is this dog breed bigger than 12 inches?", "output": "Is this dog breed the biggest?", "explanation": "Do not write questions that compare domains."}, {"input": "Does this dog breed have short legs compared to the rest of its body?", "output": "What size legs does this dog breed have?", "explanation": "The question should have the same type of answer as the original."}, {"input": "Does this dog breed have short legs compared to the rest of its body?", "output": "Does this dog breed have a large muzzle?", "explanation": "This is a bad question because the question should have the same meaning as the given sentence."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Government and Politics"], "Instance": {"id": "task1562-9e378fb1c6874f769baf4600db8a341f", "input": "Is this president usually ranked as one of the better half of all presidents?", "output": ["Does this president usually get ranked in the top half of all presidents?"]}, "Instance License": ["Apache 2.0"], "prediction": "Are the ratings for this president generally good?"}
+{"id": "task1562-63f92fb0aade44d8a30f7f2f649ba4a5", "Task": "task1562_zest_text_modification", "Contributors": "['Yeganeh Kordi']", "Source": ["zest"], "URL": ["https://github.com/allenai/zest"], "Categories": ["Question Rewriting"], "Reasoning": [], "Definition": ["Paraphrase the given questions to have different wording. Your paraphrased questions should have the same answer as the original question. Try to change the sentence as much as possible using synonyms and/or rearranging the structure of the sentence. The questions are in three domains: presidents, national parks, and dogs. Each question has a keyword indicating its domain. Keywords are \"this national park\", \"this dog breed\", and \"this president\", which will be replaced with the name of an actual president, a national park, or a breed of dog. Hence, in paraphrasing, this keyword should also be used the same way. Do not write questions that compare or involve multiple domains. Do not write open-ended or subjective questions (e.g., questions that can be answered differently by different people.) Make your questions specific and concrete. Your question should have the same type of answer as the original question(e.g., if the question is extractive, the paraphrased question should be extractive as well.)"], "Positive Examples": [{"input": "Does this dog breed have short legs compared to the rest of its body?", "output": "Is the body of this dog breed large compared to its legs?", "explanation": "The output has the same meaning and same answer as the original sentence. We changed the first sentence by rearranging the structure of the sentence. "}, {"input": "Does this dog breed have short legs compared to the rest of its body?", "output": "Are the legs of this dog breed proportionally shorter than its body?", "explanation": "The original sentence is changed by using synonyms and rearranging the structure of the sentence. Also, it keeps the meaning and answer."}, {"input": "Does this dog breed have an average life expectancy range that can be more than 12 years?", "output": "Does this dog breed have a lifespan of more than 12 years?", "explanation": "The \"average life expectancy range\" is replaced with \"lifespan\" and it keeps the original meaning. "}], "Negative Examples": [{"input": "Does this dog breed get taller than 2 feet?", "output": "Is this dog breed tall?", "explanation": "This question is vague because it didn't specify tallness. Make your questions specific and concrete rather than open-ended or subjective."}, {"input": "Is this dog breed bigger than 12 inches?", "output": "Is this dog breed the biggest?", "explanation": "Do not write questions that compare domains."}, {"input": "Does this dog breed have short legs compared to the rest of its body?", "output": "What size legs does this dog breed have?", "explanation": "The question should have the same type of answer as the original."}, {"input": "Does this dog breed have short legs compared to the rest of its body?", "output": "Does this dog breed have a large muzzle?", "explanation": "This is a bad question because the question should have the same meaning as the given sentence."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Government and Politics"], "Instance": {"id": "task1562-63f92fb0aade44d8a30f7f2f649ba4a5", "input": "Did this president have a pet while in office?", "output": ["Was there a pet in the white house while this president was there?"]}, "Instance License": ["Apache 2.0"], "prediction": "Are there any similarities between this president and a dog?"}
+{"id": "task1562-c89ece351451415586acfac87d6fbac2", "Task": "task1562_zest_text_modification", "Contributors": "['Yeganeh Kordi']", "Source": ["zest"], "URL": ["https://github.com/allenai/zest"], "Categories": ["Question Rewriting"], "Reasoning": [], "Definition": ["Paraphrase the given questions to have different wording. Your paraphrased questions should have the same answer as the original question. Try to change the sentence as much as possible using synonyms and/or rearranging the structure of the sentence. The questions are in three domains: presidents, national parks, and dogs. Each question has a keyword indicating its domain. Keywords are \"this national park\", \"this dog breed\", and \"this president\", which will be replaced with the name of an actual president, a national park, or a breed of dog. Hence, in paraphrasing, this keyword should also be used the same way. Do not write questions that compare or involve multiple domains. Do not write open-ended or subjective questions (e.g., questions that can be answered differently by different people.) Make your questions specific and concrete. Your question should have the same type of answer as the original question(e.g., if the question is extractive, the paraphrased question should be extractive as well.)"], "Positive Examples": [{"input": "Does this dog breed have short legs compared to the rest of its body?", "output": "Is the body of this dog breed large compared to its legs?", "explanation": "The output has the same meaning and same answer as the original sentence. We changed the first sentence by rearranging the structure of the sentence. "}, {"input": "Does this dog breed have short legs compared to the rest of its body?", "output": "Are the legs of this dog breed proportionally shorter than its body?", "explanation": "The original sentence is changed by using synonyms and rearranging the structure of the sentence. Also, it keeps the meaning and answer."}, {"input": "Does this dog breed have an average life expectancy range that can be more than 12 years?", "output": "Does this dog breed have a lifespan of more than 12 years?", "explanation": "The \"average life expectancy range\" is replaced with \"lifespan\" and it keeps the original meaning. "}], "Negative Examples": [{"input": "Does this dog breed get taller than 2 feet?", "output": "Is this dog breed tall?", "explanation": "This question is vague because it didn't specify tallness. Make your questions specific and concrete rather than open-ended or subjective."}, {"input": "Is this dog breed bigger than 12 inches?", "output": "Is this dog breed the biggest?", "explanation": "Do not write questions that compare domains."}, {"input": "Does this dog breed have short legs compared to the rest of its body?", "output": "What size legs does this dog breed have?", "explanation": "The question should have the same type of answer as the original."}, {"input": "Does this dog breed have short legs compared to the rest of its body?", "output": "Does this dog breed have a large muzzle?", "explanation": "This is a bad question because the question should have the same meaning as the given sentence."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Government and Politics"], "Instance": {"id": "task1562-c89ece351451415586acfac87d6fbac2", "input": "Was this president ever shot at?", "output": ["Did anyone try to shoot this president?"]}, "Instance License": ["Apache 2.0"], "prediction": "Are there any other presidents that were shot at?"}
+{"id": "task1562-9d2b7a064ae34e45829779236ff12a28", "Task": "task1562_zest_text_modification", "Contributors": "['Yeganeh Kordi']", "Source": ["zest"], "URL": ["https://github.com/allenai/zest"], "Categories": ["Question Rewriting"], "Reasoning": [], "Definition": ["Paraphrase the given questions to have different wording. Your paraphrased questions should have the same answer as the original question. Try to change the sentence as much as possible using synonyms and/or rearranging the structure of the sentence. The questions are in three domains: presidents, national parks, and dogs. Each question has a keyword indicating its domain. Keywords are \"this national park\", \"this dog breed\", and \"this president\", which will be replaced with the name of an actual president, a national park, or a breed of dog. Hence, in paraphrasing, this keyword should also be used the same way. Do not write questions that compare or involve multiple domains. Do not write open-ended or subjective questions (e.g., questions that can be answered differently by different people.) Make your questions specific and concrete. Your question should have the same type of answer as the original question(e.g., if the question is extractive, the paraphrased question should be extractive as well.)"], "Positive Examples": [{"input": "Does this dog breed have short legs compared to the rest of its body?", "output": "Is the body of this dog breed large compared to its legs?", "explanation": "The output has the same meaning and same answer as the original sentence. We changed the first sentence by rearranging the structure of the sentence. "}, {"input": "Does this dog breed have short legs compared to the rest of its body?", "output": "Are the legs of this dog breed proportionally shorter than its body?", "explanation": "The original sentence is changed by using synonyms and rearranging the structure of the sentence. Also, it keeps the meaning and answer."}, {"input": "Does this dog breed have an average life expectancy range that can be more than 12 years?", "output": "Does this dog breed have a lifespan of more than 12 years?", "explanation": "The \"average life expectancy range\" is replaced with \"lifespan\" and it keeps the original meaning. "}], "Negative Examples": [{"input": "Does this dog breed get taller than 2 feet?", "output": "Is this dog breed tall?", "explanation": "This question is vague because it didn't specify tallness. Make your questions specific and concrete rather than open-ended or subjective."}, {"input": "Is this dog breed bigger than 12 inches?", "output": "Is this dog breed the biggest?", "explanation": "Do not write questions that compare domains."}, {"input": "Does this dog breed have short legs compared to the rest of its body?", "output": "What size legs does this dog breed have?", "explanation": "The question should have the same type of answer as the original."}, {"input": "Does this dog breed have short legs compared to the rest of its body?", "output": "Does this dog breed have a large muzzle?", "explanation": "This is a bad question because the question should have the same meaning as the given sentence."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Government and Politics"], "Instance": {"id": "task1562-9d2b7a064ae34e45829779236ff12a28", "input": "Are there any natural lakes at this national park?", "output": ["Does this national park have natural lakes?"]}, "Instance License": ["Apache 2.0"], "prediction": "Are there any lakes at this national park?"}
+{"id": "task640-42c40110c188424cabf5c5d4d323995e", "Task": "task640_esnli_classification", "Contributors": "['Ian Lobo']", "Source": ["e_snli"], "URL": ["https://github.com/OanaMariaCamburu/e-SNLI/"], "Categories": ["Textual Entailment"], "Reasoning": ["Textual Entailment"], "Definition": ["Given a premise and a hypothesis, determine if the hypothesis (second sentence) can be concluded from the premise and assigning it a label among entailment, neutral, or contradiction. Entailment means thats the hypothesis makes sense/follows after the premise. Neutral means that the hypothesis does not follow the premise but also does not contradict the premise. Contradiction means that the hypothesis clearly contradicts the premise."], "Positive Examples": [{"input": "This church choir sings to the masses as they sing joyous songs from the book at a church. <sep> The church has cracks in the ceiling.", "output": "neutral", "explanation": "Not all churches have cracks in the ceiling."}, {"input": "This church choir sings to the masses as they sing joyous songs from the book at a church. <sep> The church is filled with song.", "output": "entailment", "explanation": "\"Filled with song\" is a rephrasing of the \"choir sings to the masses.\""}, {"input": "This church choir sings to the masses as they sing joyous songs from the book at a church. <sep> A choir singing at a baseball game.", "output": "contradiction", "explanation": "A choir sing some other songs other than book at church during the base play. they cannot see book and play base ball same time."}], "Negative Examples": [{"input": "A land rover is being driven across a river. <sep> A sedan is stuck in the middle of a river.", "output": "entailment", "explanation": "This is false. A land rover and a sedan are different cars, so these sentences cannot be describing the same event. This is a contradiction statement."}, {"input": "A man playing an electric guitar on stage. <sep> A man is performing for cash.", "output": "contradiction", "explanation": "This is false. There is no indication that the man is performing for cash. This is a neutral statement."}, {"input": "A blond-haired doctor and her African american assistant looking threw new medical manuals. <sep> A man is eating pb and j.", "output": "neutral", "explanation": "This is false. A doctor and assistant are two people looking through manuals is different than a man is eating a sandwich. This is a contradiction statement."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Miscellaneous"], "Instance": {"id": "task640-42c40110c188424cabf5c5d4d323995e", "input": "A young family enjoys feeling ocean waves lap at their feet. <sep> A young man and woman take their child to the beach for the first time.", "output": ["neutral"]}, "Instance License": ["MIT"], "prediction": "entailment"}
+{"id": "task640-b62b70caa746472b8bbfb8126641856a", "Task": "task640_esnli_classification", "Contributors": "['Ian Lobo']", "Source": ["e_snli"], "URL": ["https://github.com/OanaMariaCamburu/e-SNLI/"], "Categories": ["Textual Entailment"], "Reasoning": ["Textual Entailment"], "Definition": ["Given a premise and a hypothesis, determine if the hypothesis (second sentence) can be concluded from the premise and assigning it a label among entailment, neutral, or contradiction. Entailment means thats the hypothesis makes sense/follows after the premise. Neutral means that the hypothesis does not follow the premise but also does not contradict the premise. Contradiction means that the hypothesis clearly contradicts the premise."], "Positive Examples": [{"input": "This church choir sings to the masses as they sing joyous songs from the book at a church. <sep> The church has cracks in the ceiling.", "output": "neutral", "explanation": "Not all churches have cracks in the ceiling."}, {"input": "This church choir sings to the masses as they sing joyous songs from the book at a church. <sep> The church is filled with song.", "output": "entailment", "explanation": "\"Filled with song\" is a rephrasing of the \"choir sings to the masses.\""}, {"input": "This church choir sings to the masses as they sing joyous songs from the book at a church. <sep> A choir singing at a baseball game.", "output": "contradiction", "explanation": "A choir sing some other songs other than book at church during the base play. they cannot see book and play base ball same time."}], "Negative Examples": [{"input": "A land rover is being driven across a river. <sep> A sedan is stuck in the middle of a river.", "output": "entailment", "explanation": "This is false. A land rover and a sedan are different cars, so these sentences cannot be describing the same event. This is a contradiction statement."}, {"input": "A man playing an electric guitar on stage. <sep> A man is performing for cash.", "output": "contradiction", "explanation": "This is false. There is no indication that the man is performing for cash. This is a neutral statement."}, {"input": "A blond-haired doctor and her African american assistant looking threw new medical manuals. <sep> A man is eating pb and j.", "output": "neutral", "explanation": "This is false. A doctor and assistant are two people looking through manuals is different than a man is eating a sandwich. This is a contradiction statement."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Miscellaneous"], "Instance": {"id": "task640-b62b70caa746472b8bbfb8126641856a", "input": "A woman with a green headscarf, blue shirt and a very big grin. <sep> The woman has been shot.", "output": ["contradiction"]}, "Instance License": ["MIT"], "prediction": "neutral"}
+{"id": "task640-55a15a77e7d340f1b80829400beaa121", "Task": "task640_esnli_classification", "Contributors": "['Ian Lobo']", "Source": ["e_snli"], "URL": ["https://github.com/OanaMariaCamburu/e-SNLI/"], "Categories": ["Textual Entailment"], "Reasoning": ["Textual Entailment"], "Definition": ["Given a premise and a hypothesis, determine if the hypothesis (second sentence) can be concluded from the premise and assigning it a label among entailment, neutral, or contradiction. Entailment means thats the hypothesis makes sense/follows after the premise. Neutral means that the hypothesis does not follow the premise but also does not contradict the premise. Contradiction means that the hypothesis clearly contradicts the premise."], "Positive Examples": [{"input": "This church choir sings to the masses as they sing joyous songs from the book at a church. <sep> The church has cracks in the ceiling.", "output": "neutral", "explanation": "Not all churches have cracks in the ceiling."}, {"input": "This church choir sings to the masses as they sing joyous songs from the book at a church. <sep> The church is filled with song.", "output": "entailment", "explanation": "\"Filled with song\" is a rephrasing of the \"choir sings to the masses.\""}, {"input": "This church choir sings to the masses as they sing joyous songs from the book at a church. <sep> A choir singing at a baseball game.", "output": "contradiction", "explanation": "A choir sing some other songs other than book at church during the base play. they cannot see book and play base ball same time."}], "Negative Examples": [{"input": "A land rover is being driven across a river. <sep> A sedan is stuck in the middle of a river.", "output": "entailment", "explanation": "This is false. A land rover and a sedan are different cars, so these sentences cannot be describing the same event. This is a contradiction statement."}, {"input": "A man playing an electric guitar on stage. <sep> A man is performing for cash.", "output": "contradiction", "explanation": "This is false. There is no indication that the man is performing for cash. This is a neutral statement."}, {"input": "A blond-haired doctor and her African american assistant looking threw new medical manuals. <sep> A man is eating pb and j.", "output": "neutral", "explanation": "This is false. A doctor and assistant are two people looking through manuals is different than a man is eating a sandwich. This is a contradiction statement."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Miscellaneous"], "Instance": {"id": "task640-55a15a77e7d340f1b80829400beaa121", "input": "A man standing in front of a building on the phone as two men to the side pain on the side. <sep> a busy man stands with bodyguards", "output": ["neutral"]}, "Instance License": ["MIT"], "prediction": "neutral"}
+{"id": "task640-05d2f029284f4bd7815e05dee9709230", "Task": "task640_esnli_classification", "Contributors": "['Ian Lobo']", "Source": ["e_snli"], "URL": ["https://github.com/OanaMariaCamburu/e-SNLI/"], "Categories": ["Textual Entailment"], "Reasoning": ["Textual Entailment"], "Definition": ["Given a premise and a hypothesis, determine if the hypothesis (second sentence) can be concluded from the premise and assigning it a label among entailment, neutral, or contradiction. Entailment means thats the hypothesis makes sense/follows after the premise. Neutral means that the hypothesis does not follow the premise but also does not contradict the premise. Contradiction means that the hypothesis clearly contradicts the premise."], "Positive Examples": [{"input": "This church choir sings to the masses as they sing joyous songs from the book at a church. <sep> The church has cracks in the ceiling.", "output": "neutral", "explanation": "Not all churches have cracks in the ceiling."}, {"input": "This church choir sings to the masses as they sing joyous songs from the book at a church. <sep> The church is filled with song.", "output": "entailment", "explanation": "\"Filled with song\" is a rephrasing of the \"choir sings to the masses.\""}, {"input": "This church choir sings to the masses as they sing joyous songs from the book at a church. <sep> A choir singing at a baseball game.", "output": "contradiction", "explanation": "A choir sing some other songs other than book at church during the base play. they cannot see book and play base ball same time."}], "Negative Examples": [{"input": "A land rover is being driven across a river. <sep> A sedan is stuck in the middle of a river.", "output": "entailment", "explanation": "This is false. A land rover and a sedan are different cars, so these sentences cannot be describing the same event. This is a contradiction statement."}, {"input": "A man playing an electric guitar on stage. <sep> A man is performing for cash.", "output": "contradiction", "explanation": "This is false. There is no indication that the man is performing for cash. This is a neutral statement."}, {"input": "A blond-haired doctor and her African american assistant looking threw new medical manuals. <sep> A man is eating pb and j.", "output": "neutral", "explanation": "This is false. A doctor and assistant are two people looking through manuals is different than a man is eating a sandwich. This is a contradiction statement."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Miscellaneous"], "Instance": {"id": "task640-05d2f029284f4bd7815e05dee9709230", "input": "A land rover is being driven across a river. <sep> A vehicle is crossing a river.", "output": ["entailment"]}, "Instance License": ["MIT"], "prediction": "entailment"}
+{"id": "task640-c987b38a07a8406b8d8537b410f696de", "Task": "task640_esnli_classification", "Contributors": "['Ian Lobo']", "Source": ["e_snli"], "URL": ["https://github.com/OanaMariaCamburu/e-SNLI/"], "Categories": ["Textual Entailment"], "Reasoning": ["Textual Entailment"], "Definition": ["Given a premise and a hypothesis, determine if the hypothesis (second sentence) can be concluded from the premise and assigning it a label among entailment, neutral, or contradiction. Entailment means thats the hypothesis makes sense/follows after the premise. Neutral means that the hypothesis does not follow the premise but also does not contradict the premise. Contradiction means that the hypothesis clearly contradicts the premise."], "Positive Examples": [{"input": "This church choir sings to the masses as they sing joyous songs from the book at a church. <sep> The church has cracks in the ceiling.", "output": "neutral", "explanation": "Not all churches have cracks in the ceiling."}, {"input": "This church choir sings to the masses as they sing joyous songs from the book at a church. <sep> The church is filled with song.", "output": "entailment", "explanation": "\"Filled with song\" is a rephrasing of the \"choir sings to the masses.\""}, {"input": "This church choir sings to the masses as they sing joyous songs from the book at a church. <sep> A choir singing at a baseball game.", "output": "contradiction", "explanation": "A choir sing some other songs other than book at church during the base play. they cannot see book and play base ball same time."}], "Negative Examples": [{"input": "A land rover is being driven across a river. <sep> A sedan is stuck in the middle of a river.", "output": "entailment", "explanation": "This is false. A land rover and a sedan are different cars, so these sentences cannot be describing the same event. This is a contradiction statement."}, {"input": "A man playing an electric guitar on stage. <sep> A man is performing for cash.", "output": "contradiction", "explanation": "This is false. There is no indication that the man is performing for cash. This is a neutral statement."}, {"input": "A blond-haired doctor and her African american assistant looking threw new medical manuals. <sep> A man is eating pb and j.", "output": "neutral", "explanation": "This is false. A doctor and assistant are two people looking through manuals is different than a man is eating a sandwich. This is a contradiction statement."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Miscellaneous"], "Instance": {"id": "task640-c987b38a07a8406b8d8537b410f696de", "input": "A man in a black shirt is looking at a bike in a workshop. <sep> A man is in a black shirt", "output": ["entailment"]}, "Instance License": ["MIT"], "prediction": "entailment"}
+{"id": "task1622-b2434f72637f440baa255af865c5900c", "Task": "task1622_disfl_qa_text_modication", "Contributors": "['Krishna Kesani']", "Source": ["disfl_qa"], "URL": ["https://huggingface.co/datasets/disfl_qa"], "Categories": ["Question Rewriting"], "Reasoning": [], "Definition": ["Convert a disfluent question to a proper question. A disfluent question is a question that has some interruptions in it while framing. A proper question is the correct form of the question without any disfluency."], "Positive Examples": [{"input": "Why was uh where was the Rhine regulated with an upper canal?", "output": "Where was the Rhine regulated with an upper canal?", "explanation": "The above disfluent question is correctly converted to a proper question. The 'uh' and the 'why' before the correction should be removed to make it fluent."}, {"input": "What kind of committee considered legislation on the development of the Scottish or no make that the Edinburgh Tram Network?", "output": "What kind of committee considered legislation on the development of the Edinburgh Tram Network?", "explanation": "The above disfluent question is correctly converted to a proper question. It includes the corrected version, and doesn't include the unnecessary parts."}, {"input": "When degradation no economic inequality is smaller, more waste and pollution is?", "output": "When economic inequality is smaller, more waste and pollution is?", "explanation": "The above disfluent question is correctly converted to a proper question by removing the incorrect part, and replacing it with the correction."}], "Negative Examples": [{"input": "When did Maududi exert the least impact no where did he exert?", "output": "When did Maududi exert the least impact?", "explanation": "The above disfluent question is not correctly converted to a proper question since the original meaning in the disfluent question is where did Maudidi exert the least impact but the output asks when did Maudidi exert the least impact."}, {"input": "What Chinese or no make that Khitan leader rejected the Mongols?", "output": "What Chinese leader rejected the Mongols?", "explanation": "The above disfluent question is not correctly converted to a proper question since the original meaning in the disfluent question is what Khitan leader rejected the Mongols but the output asks what Chinese leader rejected the Mongols."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Wikipedia"], "Instance": {"id": "task1622-b2434f72637f440baa255af865c5900c", "input": "Which idea or uh like theory states that slow geological processes are still occurring today, and have occurred throughout Earth's history?", "output": ["Which theory states that slow geological processes are still occurring today, and have occurred throughout Earth's history?"]}, "Instance License": ["CC BY 4.0"], "prediction": "Which idea or theory states that slow geological processes are still occurring today, and have occurred throughout Earth's history?"}
+{"id": "task1622-248ea6a27e074264a916fe0a9985324f", "Task": "task1622_disfl_qa_text_modication", "Contributors": "['Krishna Kesani']", "Source": ["disfl_qa"], "URL": ["https://huggingface.co/datasets/disfl_qa"], "Categories": ["Question Rewriting"], "Reasoning": [], "Definition": ["Convert a disfluent question to a proper question. A disfluent question is a question that has some interruptions in it while framing. A proper question is the correct form of the question without any disfluency."], "Positive Examples": [{"input": "Why was uh where was the Rhine regulated with an upper canal?", "output": "Where was the Rhine regulated with an upper canal?", "explanation": "The above disfluent question is correctly converted to a proper question. The 'uh' and the 'why' before the correction should be removed to make it fluent."}, {"input": "What kind of committee considered legislation on the development of the Scottish or no make that the Edinburgh Tram Network?", "output": "What kind of committee considered legislation on the development of the Edinburgh Tram Network?", "explanation": "The above disfluent question is correctly converted to a proper question. It includes the corrected version, and doesn't include the unnecessary parts."}, {"input": "When degradation no economic inequality is smaller, more waste and pollution is?", "output": "When economic inequality is smaller, more waste and pollution is?", "explanation": "The above disfluent question is correctly converted to a proper question by removing the incorrect part, and replacing it with the correction."}], "Negative Examples": [{"input": "When did Maududi exert the least impact no where did he exert?", "output": "When did Maududi exert the least impact?", "explanation": "The above disfluent question is not correctly converted to a proper question since the original meaning in the disfluent question is where did Maudidi exert the least impact but the output asks when did Maudidi exert the least impact."}, {"input": "What Chinese or no make that Khitan leader rejected the Mongols?", "output": "What Chinese leader rejected the Mongols?", "explanation": "The above disfluent question is not correctly converted to a proper question since the original meaning in the disfluent question is what Khitan leader rejected the Mongols but the output asks what Chinese leader rejected the Mongols."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Wikipedia"], "Instance": {"id": "task1622-248ea6a27e074264a916fe0a9985324f", "input": "Who refused to act until Loudoun approved, no, instead disapproved plans?", "output": ["Who refused to act until Loudoun disapproved plans?"]}, "Instance License": ["CC BY 4.0"], "prediction": "Who refused to act until Loudoun approved, no, instead disapproved plans?"}
+{"id": "task1622-a3379971a6b3452fb686719108f40b4a", "Task": "task1622_disfl_qa_text_modication", "Contributors": "['Krishna Kesani']", "Source": ["disfl_qa"], "URL": ["https://huggingface.co/datasets/disfl_qa"], "Categories": ["Question Rewriting"], "Reasoning": [], "Definition": ["Convert a disfluent question to a proper question. A disfluent question is a question that has some interruptions in it while framing. A proper question is the correct form of the question without any disfluency."], "Positive Examples": [{"input": "Why was uh where was the Rhine regulated with an upper canal?", "output": "Where was the Rhine regulated with an upper canal?", "explanation": "The above disfluent question is correctly converted to a proper question. The 'uh' and the 'why' before the correction should be removed to make it fluent."}, {"input": "What kind of committee considered legislation on the development of the Scottish or no make that the Edinburgh Tram Network?", "output": "What kind of committee considered legislation on the development of the Edinburgh Tram Network?", "explanation": "The above disfluent question is correctly converted to a proper question. It includes the corrected version, and doesn't include the unnecessary parts."}, {"input": "When degradation no economic inequality is smaller, more waste and pollution is?", "output": "When economic inequality is smaller, more waste and pollution is?", "explanation": "The above disfluent question is correctly converted to a proper question by removing the incorrect part, and replacing it with the correction."}], "Negative Examples": [{"input": "When did Maududi exert the least impact no where did he exert?", "output": "When did Maududi exert the least impact?", "explanation": "The above disfluent question is not correctly converted to a proper question since the original meaning in the disfluent question is where did Maudidi exert the least impact but the output asks when did Maudidi exert the least impact."}, {"input": "What Chinese or no make that Khitan leader rejected the Mongols?", "output": "What Chinese leader rejected the Mongols?", "explanation": "The above disfluent question is not correctly converted to a proper question since the original meaning in the disfluent question is what Khitan leader rejected the Mongols but the output asks what Chinese leader rejected the Mongols."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Wikipedia"], "Instance": {"id": "task1622-a3379971a6b3452fb686719108f40b4a", "input": "The movements of the Cydippids combs are controlled by what no no I meant movements of the lobates combs not Cydippids?", "output": ["The movements of the lobates combs are controlled by what?"]}, "Instance License": ["CC BY 4.0"], "prediction": "The movements of the Cydippids combs are controlled by what?"}
+{"id": "task1622-8ae91718a18541219702b65e41dba8b8", "Task": "task1622_disfl_qa_text_modication", "Contributors": "['Krishna Kesani']", "Source": ["disfl_qa"], "URL": ["https://huggingface.co/datasets/disfl_qa"], "Categories": ["Question Rewriting"], "Reasoning": [], "Definition": ["Convert a disfluent question to a proper question. A disfluent question is a question that has some interruptions in it while framing. A proper question is the correct form of the question without any disfluency."], "Positive Examples": [{"input": "Why was uh where was the Rhine regulated with an upper canal?", "output": "Where was the Rhine regulated with an upper canal?", "explanation": "The above disfluent question is correctly converted to a proper question. The 'uh' and the 'why' before the correction should be removed to make it fluent."}, {"input": "What kind of committee considered legislation on the development of the Scottish or no make that the Edinburgh Tram Network?", "output": "What kind of committee considered legislation on the development of the Edinburgh Tram Network?", "explanation": "The above disfluent question is correctly converted to a proper question. It includes the corrected version, and doesn't include the unnecessary parts."}, {"input": "When degradation no economic inequality is smaller, more waste and pollution is?", "output": "When economic inequality is smaller, more waste and pollution is?", "explanation": "The above disfluent question is correctly converted to a proper question by removing the incorrect part, and replacing it with the correction."}], "Negative Examples": [{"input": "When did Maududi exert the least impact no where did he exert?", "output": "When did Maududi exert the least impact?", "explanation": "The above disfluent question is not correctly converted to a proper question since the original meaning in the disfluent question is where did Maudidi exert the least impact but the output asks when did Maudidi exert the least impact."}, {"input": "What Chinese or no make that Khitan leader rejected the Mongols?", "output": "What Chinese leader rejected the Mongols?", "explanation": "The above disfluent question is not correctly converted to a proper question since the original meaning in the disfluent question is what Khitan leader rejected the Mongols but the output asks what Chinese leader rejected the Mongols."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Wikipedia"], "Instance": {"id": "task1622-8ae91718a18541219702b65e41dba8b8", "input": "Ideal strings transmit multiple no what delayed forces?", "output": ["Ideal strings transmit what delayed forces?"]}, "Instance License": ["CC BY 4.0"], "prediction": "Ideal strings transmit multiple delayed forces?"}
+{"id": "task1622-6a23cc8e02de4a46bfccec7d13a8cf5e", "Task": "task1622_disfl_qa_text_modication", "Contributors": "['Krishna Kesani']", "Source": ["disfl_qa"], "URL": ["https://huggingface.co/datasets/disfl_qa"], "Categories": ["Question Rewriting"], "Reasoning": [], "Definition": ["Convert a disfluent question to a proper question. A disfluent question is a question that has some interruptions in it while framing. A proper question is the correct form of the question without any disfluency."], "Positive Examples": [{"input": "Why was uh where was the Rhine regulated with an upper canal?", "output": "Where was the Rhine regulated with an upper canal?", "explanation": "The above disfluent question is correctly converted to a proper question. The 'uh' and the 'why' before the correction should be removed to make it fluent."}, {"input": "What kind of committee considered legislation on the development of the Scottish or no make that the Edinburgh Tram Network?", "output": "What kind of committee considered legislation on the development of the Edinburgh Tram Network?", "explanation": "The above disfluent question is correctly converted to a proper question. It includes the corrected version, and doesn't include the unnecessary parts."}, {"input": "When degradation no economic inequality is smaller, more waste and pollution is?", "output": "When economic inequality is smaller, more waste and pollution is?", "explanation": "The above disfluent question is correctly converted to a proper question by removing the incorrect part, and replacing it with the correction."}], "Negative Examples": [{"input": "When did Maududi exert the least impact no where did he exert?", "output": "When did Maududi exert the least impact?", "explanation": "The above disfluent question is not correctly converted to a proper question since the original meaning in the disfluent question is where did Maudidi exert the least impact but the output asks when did Maudidi exert the least impact."}, {"input": "What Chinese or no make that Khitan leader rejected the Mongols?", "output": "What Chinese leader rejected the Mongols?", "explanation": "The above disfluent question is not correctly converted to a proper question since the original meaning in the disfluent question is what Khitan leader rejected the Mongols but the output asks what Chinese leader rejected the Mongols."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Wikipedia"], "Instance": {"id": "task1622-6a23cc8e02de4a46bfccec7d13a8cf5e", "input": "Where did French fur trappers travel no wait I want to know where French South Americans settled?", "output": ["Where were French South Americans settled?"]}, "Instance License": ["CC BY 4.0"], "prediction": "Where did French fur trappers travel?"}
+{"id": "task623-c8aa26b2aa844d5faf1b3f2b3c1365d5", "Task": "task623_ohsumed_yes_no_answer_generation", "Contributors": "['Saicharan Papani']", "Source": ["ohsumed"], "URL": ["https://huggingface.co/datasets/ohsumed"], "Categories": ["Keyword Tagging"], "Reasoning": [], "Definition": ["Given an abstract, and a few options, indicate if any of the given options appropriately describe the given abstract. If any of them is a proper keyword, answer 'Yes', otherwise answer 'No'."], "Positive Examples": [{"input": "Abstract: Some patients converted from ventricular fibrillation to organized rhythms by defibrillation-trained ambulance technicians (EMT-Ds) will refibrillate before hospital arrival. The authors analyzed 271 cases of ventricular fibrillation managed by EMT-Ds working without paramedic back-up. Of 111 patients initially converted to organized rhythms, 19 (17%) refibrillated, 11 (58%) of whom were reconverted to perfusing rhythms, including nine of 11 (82%) who had spontaneous pulses prior to refibrillation. Among patients initially converted to organized rhythms, hospital admission rates were lower for patients who refibrillated than for patients who did not(53% versus 76%, P = NS), although discharge rates were virtually identical (37% and 35%, respectively). Scene-to-hospital transport times were not predictively associated with either the frequency of refibrillation or patient outcome. Defibrillation-trained EMTs can effectively manage refibrillation with additional shocks and are not at a significant disadvantage when paramedic back-up is not available. \nQuestion Does the following mesh terms have a suitable mesh term for the abstract? 1)Ventricular Fibrillation 2)Transportation of Patients 3)Allied Health Personnel", "output": "Yes", "explanation": "Ventricular Fibrillation term is directly present in the abstract and it is one of the main topic in it. So can be chosen as the medical subject heading."}, {"input": "Abstract: The course of a pregnant patient at term who was acutely exposed to carbon monoxide is described. A review of the fetal-maternal carboxyhemoglobin relationships and the differences in fetal oxyhemoglobin physiology are used to explain the recommendation that pregnant women with carbon monoxide poisoning should receive 100% oxygen therapy for up to five times longer than is otherwise necessary. The role of hyperbaric oxygen therapy is considered. \nQuestion Does the following mesh terms have a suitable mesh term for the abstract? 1)Carbon Monoxide Poisoning 2)Transportation of Patients 3)Allied Health Personnel", "output": "Yes", "explanation": "The Carbon Monoxide Poisoning is directly given in the abstract so can be considered as mesh term."}, {"input": "Abstract: In the critically ill child, administration of fluids and medications via the intraosseous route often proves life-saving. The authors describe the case of a child with status epilepticus in whom phenytoin was administered via the intraosseous route, and seizure resolution and therapeutic serum levels were achieved. Intraosseous drug administration should be reserved for the rare critically ill child in whom vascular access proves impossible. \nQuestion Does the following mesh terms have a suitable mesh term for the abstract? 1)Carbon Monoxide Poisoning 2)Transportation of Patients 3)Allied Health Personnel", "output": "No", "explanation": "None of the given options are present in the abstract or related to the abstract."}], "Negative Examples": [{"input": "Abstract: Intraosseous infusions were widely used in pediatric patients during the 1930s and 1940s. Recent reports have re-introduced this concept and confirmed its safety and ready accessability for fluid and drug administration. However, these reports have not addressed the difficulties encountered during insertion of the intraosseous needle. Spinal needles, standard metal intravenous (IV) needles, and bone marrow biopsy needles have been suggested for intraosseous infusion. These needles were tested for ease of insertion on a pediatric cadaver leg. The site for needle placement was also evaluated during the study. It was found that the 13-gauge Kormed/Jamshidi disposable bone marrow/aspiration needle was the easiest to insert and did not plug with bone or tissue during insertion. An area proximal to the medial malleolus was found to provide a stable, relatively flat, and easily penetrable location for needle placement. This method was successfully utilized in ten pediatric and five adult patients. Intraosseous needle placement is a safe, rapid method to gain access to the venous circulation. By utilizing these techniques, a stable, usable fluid line can be established in even the most dehydrated pediatric patients. \nQuestion Does the following mesh terms have a suitable mesh term for the abstract? 1)Carbon Monoxide Poisoning 2)Transportation 3) Allied Health Personnel", "output": "Yes", "explanation": "None of the given options are present in the abstract or relatable to abstract but answered as yes, which is a wrong answer"}, {"input": "Abstract: As the use of helicopters for air transport of critically ill patients increases, the availability of monitoring devices for physiological parameters during flight becomes important. It has long been known that arterial PO2 (PaO2) decreases during unsupplemented, non- pressurized flight. In this study, the authors examined the use of the transconjunctival oxygen (cjO2) monitor for assessing the adequacy of arterial oxygenation during helicopter flight in four healthy volunteers. Arterial PaO2 as measured by conventional blood gas analysis was compared with cjO2 at ground level, 5,000 feet, and 10,000 feet altitude. Mean PaO2 dropped significantly from 93.5 to 81.5 to 58.5 mm Hg, respectively (P less than 0.001, analysis of variance with repeated measures). Mean cjO2 also decreased significantly from 63.8 to 52.0 to 34.8 mm Hg, respectively (P less than 0.001, analysis of variance with repeated measures). Within individual subjects, cjO2 was an accurate predictor of PaO2 (P less than 0.001, multiple regression analysis). The relationship between cjO2 and PaO2 was linear with a regression coefficient of 1.147. The authors conclude that the transconjunctival O2 monitor may be useful for monitoring the adequacy of arterial oxygenation during helicopter flight in hemodynamically stable patients. The results of study also support the use of supplemental oxygen in all patients subjected to helicopter transport. \nQuestion Does the following mesh terms have a suitable mesh term for the abstract? 1)Transportation of Patients 2)Aircraft 3) Blood Gas Monitoring", "output": "No", "explanation": "Even though Blood gas and aircraft are directly present in abstract, it answered as no. So the correct answer is yes"}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Scientific Research Papers"], "Instance": {"id": "task623-c8aa26b2aa844d5faf1b3f2b3c1365d5", "input": "Abstract: This article describes the circumstances of the diagnosis of three of a group of 12 high-functioning multiple personality disorder patients. All had performed major social and professional activities with consistent competence, and all appeared to be neurotic patients suitable for classical psychoanalysis. All 12 had been misdiagnosed on at least three occasions before the correct diagnosis was made. Aspects of the difficulties encountered in assessing these patients are discussed and guidelines for the preservation of their high level of function during the treatment process are offered. \nQuestion Does the following mesh terms have a suitable mesh term for the abstract? 1)Animal 2)Antibodies, Monoclonal 3)Antigen-Antibody Complex", "output": ["No"]}, "Instance License": ["CC BY-NC 4.0"], "prediction": "No"}
+{"id": "task623-7c3536eb121442eb8c2bcc80b542c113", "Task": "task623_ohsumed_yes_no_answer_generation", "Contributors": "['Saicharan Papani']", "Source": ["ohsumed"], "URL": ["https://huggingface.co/datasets/ohsumed"], "Categories": ["Keyword Tagging"], "Reasoning": [], "Definition": ["Given an abstract, and a few options, indicate if any of the given options appropriately describe the given abstract. If any of them is a proper keyword, answer 'Yes', otherwise answer 'No'."], "Positive Examples": [{"input": "Abstract: Some patients converted from ventricular fibrillation to organized rhythms by defibrillation-trained ambulance technicians (EMT-Ds) will refibrillate before hospital arrival. The authors analyzed 271 cases of ventricular fibrillation managed by EMT-Ds working without paramedic back-up. Of 111 patients initially converted to organized rhythms, 19 (17%) refibrillated, 11 (58%) of whom were reconverted to perfusing rhythms, including nine of 11 (82%) who had spontaneous pulses prior to refibrillation. Among patients initially converted to organized rhythms, hospital admission rates were lower for patients who refibrillated than for patients who did not(53% versus 76%, P = NS), although discharge rates were virtually identical (37% and 35%, respectively). Scene-to-hospital transport times were not predictively associated with either the frequency of refibrillation or patient outcome. Defibrillation-trained EMTs can effectively manage refibrillation with additional shocks and are not at a significant disadvantage when paramedic back-up is not available. \nQuestion Does the following mesh terms have a suitable mesh term for the abstract? 1)Ventricular Fibrillation 2)Transportation of Patients 3)Allied Health Personnel", "output": "Yes", "explanation": "Ventricular Fibrillation term is directly present in the abstract and it is one of the main topic in it. So can be chosen as the medical subject heading."}, {"input": "Abstract: The course of a pregnant patient at term who was acutely exposed to carbon monoxide is described. A review of the fetal-maternal carboxyhemoglobin relationships and the differences in fetal oxyhemoglobin physiology are used to explain the recommendation that pregnant women with carbon monoxide poisoning should receive 100% oxygen therapy for up to five times longer than is otherwise necessary. The role of hyperbaric oxygen therapy is considered. \nQuestion Does the following mesh terms have a suitable mesh term for the abstract? 1)Carbon Monoxide Poisoning 2)Transportation of Patients 3)Allied Health Personnel", "output": "Yes", "explanation": "The Carbon Monoxide Poisoning is directly given in the abstract so can be considered as mesh term."}, {"input": "Abstract: In the critically ill child, administration of fluids and medications via the intraosseous route often proves life-saving. The authors describe the case of a child with status epilepticus in whom phenytoin was administered via the intraosseous route, and seizure resolution and therapeutic serum levels were achieved. Intraosseous drug administration should be reserved for the rare critically ill child in whom vascular access proves impossible. \nQuestion Does the following mesh terms have a suitable mesh term for the abstract? 1)Carbon Monoxide Poisoning 2)Transportation of Patients 3)Allied Health Personnel", "output": "No", "explanation": "None of the given options are present in the abstract or related to the abstract."}], "Negative Examples": [{"input": "Abstract: Intraosseous infusions were widely used in pediatric patients during the 1930s and 1940s. Recent reports have re-introduced this concept and confirmed its safety and ready accessability for fluid and drug administration. However, these reports have not addressed the difficulties encountered during insertion of the intraosseous needle. Spinal needles, standard metal intravenous (IV) needles, and bone marrow biopsy needles have been suggested for intraosseous infusion. These needles were tested for ease of insertion on a pediatric cadaver leg. The site for needle placement was also evaluated during the study. It was found that the 13-gauge Kormed/Jamshidi disposable bone marrow/aspiration needle was the easiest to insert and did not plug with bone or tissue during insertion. An area proximal to the medial malleolus was found to provide a stable, relatively flat, and easily penetrable location for needle placement. This method was successfully utilized in ten pediatric and five adult patients. Intraosseous needle placement is a safe, rapid method to gain access to the venous circulation. By utilizing these techniques, a stable, usable fluid line can be established in even the most dehydrated pediatric patients. \nQuestion Does the following mesh terms have a suitable mesh term for the abstract? 1)Carbon Monoxide Poisoning 2)Transportation 3) Allied Health Personnel", "output": "Yes", "explanation": "None of the given options are present in the abstract or relatable to abstract but answered as yes, which is a wrong answer"}, {"input": "Abstract: As the use of helicopters for air transport of critically ill patients increases, the availability of monitoring devices for physiological parameters during flight becomes important. It has long been known that arterial PO2 (PaO2) decreases during unsupplemented, non- pressurized flight. In this study, the authors examined the use of the transconjunctival oxygen (cjO2) monitor for assessing the adequacy of arterial oxygenation during helicopter flight in four healthy volunteers. Arterial PaO2 as measured by conventional blood gas analysis was compared with cjO2 at ground level, 5,000 feet, and 10,000 feet altitude. Mean PaO2 dropped significantly from 93.5 to 81.5 to 58.5 mm Hg, respectively (P less than 0.001, analysis of variance with repeated measures). Mean cjO2 also decreased significantly from 63.8 to 52.0 to 34.8 mm Hg, respectively (P less than 0.001, analysis of variance with repeated measures). Within individual subjects, cjO2 was an accurate predictor of PaO2 (P less than 0.001, multiple regression analysis). The relationship between cjO2 and PaO2 was linear with a regression coefficient of 1.147. The authors conclude that the transconjunctival O2 monitor may be useful for monitoring the adequacy of arterial oxygenation during helicopter flight in hemodynamically stable patients. The results of study also support the use of supplemental oxygen in all patients subjected to helicopter transport. \nQuestion Does the following mesh terms have a suitable mesh term for the abstract? 1)Transportation of Patients 2)Aircraft 3) Blood Gas Monitoring", "output": "No", "explanation": "Even though Blood gas and aircraft are directly present in abstract, it answered as no. So the correct answer is yes"}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Scientific Research Papers"], "Instance": {"id": "task623-7c3536eb121442eb8c2bcc80b542c113", "input": "Abstract: To assess the prevalence of sports eye injuries in our area a register was kept over the 18 months from October 1982 to March 1984. Squash, association football, badminton, and tennis were the main offenders. The severest injury was from a golf ball, involving a fractured zygoma. There was one retinal dialysis, and one lens dislocation requiring extraction. Spectacles were broken in six cases and a contact lens in one. Glass fragments needed operative removal in one case, but there were no penetrating injuries. The value of eye protection, not worn by any of our patients, is emphasised. \nQuestion Does the following mesh terms have a suitable mesh term for the abstract? 1)Adolescence 2)Adult 3)Athletic Injuries 4)England 5)Eye Injuries 6)Eye Protective Devices 7)Female 8)Human 9)Male 10)Soccer 11)Tennis.", "output": ["Yes"]}, "Instance License": ["CC BY-NC 4.0"], "prediction": "Yes"}
+{"id": "task623-e34509e987024d71880846da4914551b", "Task": "task623_ohsumed_yes_no_answer_generation", "Contributors": "['Saicharan Papani']", "Source": ["ohsumed"], "URL": ["https://huggingface.co/datasets/ohsumed"], "Categories": ["Keyword Tagging"], "Reasoning": [], "Definition": ["Given an abstract, and a few options, indicate if any of the given options appropriately describe the given abstract. If any of them is a proper keyword, answer 'Yes', otherwise answer 'No'."], "Positive Examples": [{"input": "Abstract: Some patients converted from ventricular fibrillation to organized rhythms by defibrillation-trained ambulance technicians (EMT-Ds) will refibrillate before hospital arrival. The authors analyzed 271 cases of ventricular fibrillation managed by EMT-Ds working without paramedic back-up. Of 111 patients initially converted to organized rhythms, 19 (17%) refibrillated, 11 (58%) of whom were reconverted to perfusing rhythms, including nine of 11 (82%) who had spontaneous pulses prior to refibrillation. Among patients initially converted to organized rhythms, hospital admission rates were lower for patients who refibrillated than for patients who did not(53% versus 76%, P = NS), although discharge rates were virtually identical (37% and 35%, respectively). Scene-to-hospital transport times were not predictively associated with either the frequency of refibrillation or patient outcome. Defibrillation-trained EMTs can effectively manage refibrillation with additional shocks and are not at a significant disadvantage when paramedic back-up is not available. \nQuestion Does the following mesh terms have a suitable mesh term for the abstract? 1)Ventricular Fibrillation 2)Transportation of Patients 3)Allied Health Personnel", "output": "Yes", "explanation": "Ventricular Fibrillation term is directly present in the abstract and it is one of the main topic in it. So can be chosen as the medical subject heading."}, {"input": "Abstract: The course of a pregnant patient at term who was acutely exposed to carbon monoxide is described. A review of the fetal-maternal carboxyhemoglobin relationships and the differences in fetal oxyhemoglobin physiology are used to explain the recommendation that pregnant women with carbon monoxide poisoning should receive 100% oxygen therapy for up to five times longer than is otherwise necessary. The role of hyperbaric oxygen therapy is considered. \nQuestion Does the following mesh terms have a suitable mesh term for the abstract? 1)Carbon Monoxide Poisoning 2)Transportation of Patients 3)Allied Health Personnel", "output": "Yes", "explanation": "The Carbon Monoxide Poisoning is directly given in the abstract so can be considered as mesh term."}, {"input": "Abstract: In the critically ill child, administration of fluids and medications via the intraosseous route often proves life-saving. The authors describe the case of a child with status epilepticus in whom phenytoin was administered via the intraosseous route, and seizure resolution and therapeutic serum levels were achieved. Intraosseous drug administration should be reserved for the rare critically ill child in whom vascular access proves impossible. \nQuestion Does the following mesh terms have a suitable mesh term for the abstract? 1)Carbon Monoxide Poisoning 2)Transportation of Patients 3)Allied Health Personnel", "output": "No", "explanation": "None of the given options are present in the abstract or related to the abstract."}], "Negative Examples": [{"input": "Abstract: Intraosseous infusions were widely used in pediatric patients during the 1930s and 1940s. Recent reports have re-introduced this concept and confirmed its safety and ready accessability for fluid and drug administration. However, these reports have not addressed the difficulties encountered during insertion of the intraosseous needle. Spinal needles, standard metal intravenous (IV) needles, and bone marrow biopsy needles have been suggested for intraosseous infusion. These needles were tested for ease of insertion on a pediatric cadaver leg. The site for needle placement was also evaluated during the study. It was found that the 13-gauge Kormed/Jamshidi disposable bone marrow/aspiration needle was the easiest to insert and did not plug with bone or tissue during insertion. An area proximal to the medial malleolus was found to provide a stable, relatively flat, and easily penetrable location for needle placement. This method was successfully utilized in ten pediatric and five adult patients. Intraosseous needle placement is a safe, rapid method to gain access to the venous circulation. By utilizing these techniques, a stable, usable fluid line can be established in even the most dehydrated pediatric patients. \nQuestion Does the following mesh terms have a suitable mesh term for the abstract? 1)Carbon Monoxide Poisoning 2)Transportation 3) Allied Health Personnel", "output": "Yes", "explanation": "None of the given options are present in the abstract or relatable to abstract but answered as yes, which is a wrong answer"}, {"input": "Abstract: As the use of helicopters for air transport of critically ill patients increases, the availability of monitoring devices for physiological parameters during flight becomes important. It has long been known that arterial PO2 (PaO2) decreases during unsupplemented, non- pressurized flight. In this study, the authors examined the use of the transconjunctival oxygen (cjO2) monitor for assessing the adequacy of arterial oxygenation during helicopter flight in four healthy volunteers. Arterial PaO2 as measured by conventional blood gas analysis was compared with cjO2 at ground level, 5,000 feet, and 10,000 feet altitude. Mean PaO2 dropped significantly from 93.5 to 81.5 to 58.5 mm Hg, respectively (P less than 0.001, analysis of variance with repeated measures). Mean cjO2 also decreased significantly from 63.8 to 52.0 to 34.8 mm Hg, respectively (P less than 0.001, analysis of variance with repeated measures). Within individual subjects, cjO2 was an accurate predictor of PaO2 (P less than 0.001, multiple regression analysis). The relationship between cjO2 and PaO2 was linear with a regression coefficient of 1.147. The authors conclude that the transconjunctival O2 monitor may be useful for monitoring the adequacy of arterial oxygenation during helicopter flight in hemodynamically stable patients. The results of study also support the use of supplemental oxygen in all patients subjected to helicopter transport. \nQuestion Does the following mesh terms have a suitable mesh term for the abstract? 1)Transportation of Patients 2)Aircraft 3) Blood Gas Monitoring", "output": "No", "explanation": "Even though Blood gas and aircraft are directly present in abstract, it answered as no. So the correct answer is yes"}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Scientific Research Papers"], "Instance": {"id": "task623-e34509e987024d71880846da4914551b", "input": "Abstract: Twenty-two patients with recurrent nose bleeds and varicose vessels on the nasal septum were subjected to transection of the vessels and followed-up for 2 years. One month after the operation, it was not possible to identify the original vessels. In other locations new varicose vessels began to appear after 1 month, and at the end of the follow-up period were observed on 9 out of 10 operated sides. The transection resulted in an immediate decrease in the frequency of nose bleeds and at the end of the control period 12 (55%) of the patients had had less than 4 bleeds during the previous year in spite of the observed rapid formation of new vessels. Mucosal atrophy with symptoms of increased nasal crusting occurred in 3 patients. Transection of varicose vessels in patients with nose bleeds leads to a decrease in the number of bleeds. \nQuestion Does the following mesh terms have a suitable mesh term for the abstract? 1)Adult 2)Epistaxis 3)Female 4)Follow-Up Studies 5)Human 6)Male 7)Nasal Mucosa 8)Recurrence 9)Support, Non-U.S. Gov't 10)Varicose Veins", "output": ["Yes"]}, "Instance License": ["CC BY-NC 4.0"], "prediction": "Yes"}
+{"id": "task623-d6aadcf0dbcd43a586f1bf530101b65c", "Task": "task623_ohsumed_yes_no_answer_generation", "Contributors": "['Saicharan Papani']", "Source": ["ohsumed"], "URL": ["https://huggingface.co/datasets/ohsumed"], "Categories": ["Keyword Tagging"], "Reasoning": [], "Definition": ["Given an abstract, and a few options, indicate if any of the given options appropriately describe the given abstract. If any of them is a proper keyword, answer 'Yes', otherwise answer 'No'."], "Positive Examples": [{"input": "Abstract: Some patients converted from ventricular fibrillation to organized rhythms by defibrillation-trained ambulance technicians (EMT-Ds) will refibrillate before hospital arrival. The authors analyzed 271 cases of ventricular fibrillation managed by EMT-Ds working without paramedic back-up. Of 111 patients initially converted to organized rhythms, 19 (17%) refibrillated, 11 (58%) of whom were reconverted to perfusing rhythms, including nine of 11 (82%) who had spontaneous pulses prior to refibrillation. Among patients initially converted to organized rhythms, hospital admission rates were lower for patients who refibrillated than for patients who did not(53% versus 76%, P = NS), although discharge rates were virtually identical (37% and 35%, respectively). Scene-to-hospital transport times were not predictively associated with either the frequency of refibrillation or patient outcome. Defibrillation-trained EMTs can effectively manage refibrillation with additional shocks and are not at a significant disadvantage when paramedic back-up is not available. \nQuestion Does the following mesh terms have a suitable mesh term for the abstract? 1)Ventricular Fibrillation 2)Transportation of Patients 3)Allied Health Personnel", "output": "Yes", "explanation": "Ventricular Fibrillation term is directly present in the abstract and it is one of the main topic in it. So can be chosen as the medical subject heading."}, {"input": "Abstract: The course of a pregnant patient at term who was acutely exposed to carbon monoxide is described. A review of the fetal-maternal carboxyhemoglobin relationships and the differences in fetal oxyhemoglobin physiology are used to explain the recommendation that pregnant women with carbon monoxide poisoning should receive 100% oxygen therapy for up to five times longer than is otherwise necessary. The role of hyperbaric oxygen therapy is considered. \nQuestion Does the following mesh terms have a suitable mesh term for the abstract? 1)Carbon Monoxide Poisoning 2)Transportation of Patients 3)Allied Health Personnel", "output": "Yes", "explanation": "The Carbon Monoxide Poisoning is directly given in the abstract so can be considered as mesh term."}, {"input": "Abstract: In the critically ill child, administration of fluids and medications via the intraosseous route often proves life-saving. The authors describe the case of a child with status epilepticus in whom phenytoin was administered via the intraosseous route, and seizure resolution and therapeutic serum levels were achieved. Intraosseous drug administration should be reserved for the rare critically ill child in whom vascular access proves impossible. \nQuestion Does the following mesh terms have a suitable mesh term for the abstract? 1)Carbon Monoxide Poisoning 2)Transportation of Patients 3)Allied Health Personnel", "output": "No", "explanation": "None of the given options are present in the abstract or related to the abstract."}], "Negative Examples": [{"input": "Abstract: Intraosseous infusions were widely used in pediatric patients during the 1930s and 1940s. Recent reports have re-introduced this concept and confirmed its safety and ready accessability for fluid and drug administration. However, these reports have not addressed the difficulties encountered during insertion of the intraosseous needle. Spinal needles, standard metal intravenous (IV) needles, and bone marrow biopsy needles have been suggested for intraosseous infusion. These needles were tested for ease of insertion on a pediatric cadaver leg. The site for needle placement was also evaluated during the study. It was found that the 13-gauge Kormed/Jamshidi disposable bone marrow/aspiration needle was the easiest to insert and did not plug with bone or tissue during insertion. An area proximal to the medial malleolus was found to provide a stable, relatively flat, and easily penetrable location for needle placement. This method was successfully utilized in ten pediatric and five adult patients. Intraosseous needle placement is a safe, rapid method to gain access to the venous circulation. By utilizing these techniques, a stable, usable fluid line can be established in even the most dehydrated pediatric patients. \nQuestion Does the following mesh terms have a suitable mesh term for the abstract? 1)Carbon Monoxide Poisoning 2)Transportation 3) Allied Health Personnel", "output": "Yes", "explanation": "None of the given options are present in the abstract or relatable to abstract but answered as yes, which is a wrong answer"}, {"input": "Abstract: As the use of helicopters for air transport of critically ill patients increases, the availability of monitoring devices for physiological parameters during flight becomes important. It has long been known that arterial PO2 (PaO2) decreases during unsupplemented, non- pressurized flight. In this study, the authors examined the use of the transconjunctival oxygen (cjO2) monitor for assessing the adequacy of arterial oxygenation during helicopter flight in four healthy volunteers. Arterial PaO2 as measured by conventional blood gas analysis was compared with cjO2 at ground level, 5,000 feet, and 10,000 feet altitude. Mean PaO2 dropped significantly from 93.5 to 81.5 to 58.5 mm Hg, respectively (P less than 0.001, analysis of variance with repeated measures). Mean cjO2 also decreased significantly from 63.8 to 52.0 to 34.8 mm Hg, respectively (P less than 0.001, analysis of variance with repeated measures). Within individual subjects, cjO2 was an accurate predictor of PaO2 (P less than 0.001, multiple regression analysis). The relationship between cjO2 and PaO2 was linear with a regression coefficient of 1.147. The authors conclude that the transconjunctival O2 monitor may be useful for monitoring the adequacy of arterial oxygenation during helicopter flight in hemodynamically stable patients. The results of study also support the use of supplemental oxygen in all patients subjected to helicopter transport. \nQuestion Does the following mesh terms have a suitable mesh term for the abstract? 1)Transportation of Patients 2)Aircraft 3) Blood Gas Monitoring", "output": "No", "explanation": "Even though Blood gas and aircraft are directly present in abstract, it answered as no. So the correct answer is yes"}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Scientific Research Papers"], "Instance": {"id": "task623-d6aadcf0dbcd43a586f1bf530101b65c", "input": "Abstract: Using a series of graded destabilizing forces, we have developed a simple quantitative test of the postural response: the Postural Stress Test (PST). Suitable for widespread testing of elderly subjects, the test evaluates the subject's ability to avoid a fall as well as the appropriateness of the response. We have determined that by comparison with young subjects, the elderly controls have compromised although functionally effective balance. On the other hand, the balance response was severely compromised in half of the individuals with a history of falls. Experience with the Postural Stress Test suggests it will predict those elderly individuals with a tendency to fall as well as provide a simple mechanism for studying the balance response in the elderly. \nQuestion Does the following mesh terms have a suitable mesh term for the abstract? 1)Adult 2)Age Factors 3)Education, Premedical", "output": ["No"]}, "Instance License": ["CC BY-NC 4.0"], "prediction": "Yes"}
+{"id": "task623-3e5d5e84bceb4f659edf857c6b0bef4e", "Task": "task623_ohsumed_yes_no_answer_generation", "Contributors": "['Saicharan Papani']", "Source": ["ohsumed"], "URL": ["https://huggingface.co/datasets/ohsumed"], "Categories": ["Keyword Tagging"], "Reasoning": [], "Definition": ["Given an abstract, and a few options, indicate if any of the given options appropriately describe the given abstract. If any of them is a proper keyword, answer 'Yes', otherwise answer 'No'."], "Positive Examples": [{"input": "Abstract: Some patients converted from ventricular fibrillation to organized rhythms by defibrillation-trained ambulance technicians (EMT-Ds) will refibrillate before hospital arrival. The authors analyzed 271 cases of ventricular fibrillation managed by EMT-Ds working without paramedic back-up. Of 111 patients initially converted to organized rhythms, 19 (17%) refibrillated, 11 (58%) of whom were reconverted to perfusing rhythms, including nine of 11 (82%) who had spontaneous pulses prior to refibrillation. Among patients initially converted to organized rhythms, hospital admission rates were lower for patients who refibrillated than for patients who did not(53% versus 76%, P = NS), although discharge rates were virtually identical (37% and 35%, respectively). Scene-to-hospital transport times were not predictively associated with either the frequency of refibrillation or patient outcome. Defibrillation-trained EMTs can effectively manage refibrillation with additional shocks and are not at a significant disadvantage when paramedic back-up is not available. \nQuestion Does the following mesh terms have a suitable mesh term for the abstract? 1)Ventricular Fibrillation 2)Transportation of Patients 3)Allied Health Personnel", "output": "Yes", "explanation": "Ventricular Fibrillation term is directly present in the abstract and it is one of the main topic in it. So can be chosen as the medical subject heading."}, {"input": "Abstract: The course of a pregnant patient at term who was acutely exposed to carbon monoxide is described. A review of the fetal-maternal carboxyhemoglobin relationships and the differences in fetal oxyhemoglobin physiology are used to explain the recommendation that pregnant women with carbon monoxide poisoning should receive 100% oxygen therapy for up to five times longer than is otherwise necessary. The role of hyperbaric oxygen therapy is considered. \nQuestion Does the following mesh terms have a suitable mesh term for the abstract? 1)Carbon Monoxide Poisoning 2)Transportation of Patients 3)Allied Health Personnel", "output": "Yes", "explanation": "The Carbon Monoxide Poisoning is directly given in the abstract so can be considered as mesh term."}, {"input": "Abstract: In the critically ill child, administration of fluids and medications via the intraosseous route often proves life-saving. The authors describe the case of a child with status epilepticus in whom phenytoin was administered via the intraosseous route, and seizure resolution and therapeutic serum levels were achieved. Intraosseous drug administration should be reserved for the rare critically ill child in whom vascular access proves impossible. \nQuestion Does the following mesh terms have a suitable mesh term for the abstract? 1)Carbon Monoxide Poisoning 2)Transportation of Patients 3)Allied Health Personnel", "output": "No", "explanation": "None of the given options are present in the abstract or related to the abstract."}], "Negative Examples": [{"input": "Abstract: Intraosseous infusions were widely used in pediatric patients during the 1930s and 1940s. Recent reports have re-introduced this concept and confirmed its safety and ready accessability for fluid and drug administration. However, these reports have not addressed the difficulties encountered during insertion of the intraosseous needle. Spinal needles, standard metal intravenous (IV) needles, and bone marrow biopsy needles have been suggested for intraosseous infusion. These needles were tested for ease of insertion on a pediatric cadaver leg. The site for needle placement was also evaluated during the study. It was found that the 13-gauge Kormed/Jamshidi disposable bone marrow/aspiration needle was the easiest to insert and did not plug with bone or tissue during insertion. An area proximal to the medial malleolus was found to provide a stable, relatively flat, and easily penetrable location for needle placement. This method was successfully utilized in ten pediatric and five adult patients. Intraosseous needle placement is a safe, rapid method to gain access to the venous circulation. By utilizing these techniques, a stable, usable fluid line can be established in even the most dehydrated pediatric patients. \nQuestion Does the following mesh terms have a suitable mesh term for the abstract? 1)Carbon Monoxide Poisoning 2)Transportation 3) Allied Health Personnel", "output": "Yes", "explanation": "None of the given options are present in the abstract or relatable to abstract but answered as yes, which is a wrong answer"}, {"input": "Abstract: As the use of helicopters for air transport of critically ill patients increases, the availability of monitoring devices for physiological parameters during flight becomes important. It has long been known that arterial PO2 (PaO2) decreases during unsupplemented, non- pressurized flight. In this study, the authors examined the use of the transconjunctival oxygen (cjO2) monitor for assessing the adequacy of arterial oxygenation during helicopter flight in four healthy volunteers. Arterial PaO2 as measured by conventional blood gas analysis was compared with cjO2 at ground level, 5,000 feet, and 10,000 feet altitude. Mean PaO2 dropped significantly from 93.5 to 81.5 to 58.5 mm Hg, respectively (P less than 0.001, analysis of variance with repeated measures). Mean cjO2 also decreased significantly from 63.8 to 52.0 to 34.8 mm Hg, respectively (P less than 0.001, analysis of variance with repeated measures). Within individual subjects, cjO2 was an accurate predictor of PaO2 (P less than 0.001, multiple regression analysis). The relationship between cjO2 and PaO2 was linear with a regression coefficient of 1.147. The authors conclude that the transconjunctival O2 monitor may be useful for monitoring the adequacy of arterial oxygenation during helicopter flight in hemodynamically stable patients. The results of study also support the use of supplemental oxygen in all patients subjected to helicopter transport. \nQuestion Does the following mesh terms have a suitable mesh term for the abstract? 1)Transportation of Patients 2)Aircraft 3) Blood Gas Monitoring", "output": "No", "explanation": "Even though Blood gas and aircraft are directly present in abstract, it answered as no. So the correct answer is yes"}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Scientific Research Papers"], "Instance": {"id": "task623-3e5d5e84bceb4f659edf857c6b0bef4e", "input": "Abstract: Twelve patients with intractable rheumatoid arthritis were treated with antilymphocyte globulin (ALG), prednisolone and a cytotoxic agent, usually azathioprine, and were followed for 1 year. There was a significant (p less than 0.05) improvement in the mean score for early-morning stiffness, grip strength and the severity of nodules and vasculitis at 6 weeks and 3 months when compared to the initial visit. However, in most patients, this benefit was not sustained despite continued cytotoxic and steroid therapy. A rise in the haemoglobin and fall in ESR was maintained throughout the study period. \nQuestion Does the following mesh terms have a suitable mesh term for the abstract? 1)Antilymphocyte Serum 2)Arthritis, Rheumatoid 3)Combined Modality Therapy 4)Hemoglobins 5)Human 6)Immunosuppressive Agents 7)Leukocyte Count.", "output": ["Yes"]}, "Instance License": ["CC BY-NC 4.0"], "prediction": "Yes"}
+{"id": "task020-11a0b598025c4afe84fcfb6db8522d71", "Task": "task020_mctaco_span_based_question", "Contributors": "['Swaroop Mishra', 'Daniel Khashabi']", "Source": ["mctaco"], "URL": ["https://github.com/CogComp/MCTACO"], "Categories": ["Answerability Classification"], "Reasoning": ["Temporal Reasoning", "Commonsense Reasoning"], "Definition": ["The answer will be 'yes' if the provided sentence contains an explicit mention that answers the given question. Otherwise, the answer should be 'no'. Instances where the answer is implied from the sentence using \"instinct\" or \"common sense\" (as opposed to being written explicitly in the sentence) should be labeled as 'no'."], "Positive Examples": [{"input": "Sentence: Jack played basketball for an hour after school, after which he was very tired. \nQuestion: How long did Jack play basketball?", "output": "Yes.", "explanation": "The answer to this question (an hour)  lies in its text."}, {"input": "Sentence: He was born in China, so he went to the Embassy at 1 pm to apply for a U.S. Visa. \nQuestion: When did he go to Embassy?", "output": "Yes.", "explanation": "The answer to this question (1 pm)  lies in its text."}], "Negative Examples": [{"input": "Sentence: Jack played basketball after school, after which he was very tired. \nQuestion: How long did Jack play basketball?", "output": "No.", "explanation": "The answer to this question is not present in its text and it requires commonsense to answer."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["News", "Wikipedia", "Law", "Justice", "History", "History -> 9/11 Reports", "Anthropology", "School Science Textbooks", "Fiction"], "Instance": {"id": "task020-11a0b598025c4afe84fcfb6db8522d71", "input": "Sentence: Those in the shelter wondered if the aircraft had been shot down pursuant to this authorization. \nQuestion: Are they still in the shelter?", "output": ["Yes."]}, "Instance License": ["Unknown"], "prediction": "Yes"}
+{"id": "task020-96341c5425204c009e621055ec722ff1", "Task": "task020_mctaco_span_based_question", "Contributors": "['Swaroop Mishra', 'Daniel Khashabi']", "Source": ["mctaco"], "URL": ["https://github.com/CogComp/MCTACO"], "Categories": ["Answerability Classification"], "Reasoning": ["Temporal Reasoning", "Commonsense Reasoning"], "Definition": ["The answer will be 'yes' if the provided sentence contains an explicit mention that answers the given question. Otherwise, the answer should be 'no'. Instances where the answer is implied from the sentence using \"instinct\" or \"common sense\" (as opposed to being written explicitly in the sentence) should be labeled as 'no'."], "Positive Examples": [{"input": "Sentence: Jack played basketball for an hour after school, after which he was very tired. \nQuestion: How long did Jack play basketball?", "output": "Yes.", "explanation": "The answer to this question (an hour)  lies in its text."}, {"input": "Sentence: He was born in China, so he went to the Embassy at 1 pm to apply for a U.S. Visa. \nQuestion: When did he go to Embassy?", "output": "Yes.", "explanation": "The answer to this question (1 pm)  lies in its text."}], "Negative Examples": [{"input": "Sentence: Jack played basketball after school, after which he was very tired. \nQuestion: How long did Jack play basketball?", "output": "No.", "explanation": "The answer to this question is not present in its text and it requires commonsense to answer."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["News", "Wikipedia", "Law", "Justice", "History", "History -> 9/11 Reports", "Anthropology", "School Science Textbooks", "Fiction"], "Instance": {"id": "task020-96341c5425204c009e621055ec722ff1", "input": "Sentence: Delighted , Preetam goes in search of her watch and brings it back . \nQuestion: How often does Preetam lose her things and gets them back?", "output": ["No."]}, "Instance License": ["Unknown"], "prediction": "Yes"}
+{"id": "task020-0ddf2915172f4904b60566a79e1e55ac", "Task": "task020_mctaco_span_based_question", "Contributors": "['Swaroop Mishra', 'Daniel Khashabi']", "Source": ["mctaco"], "URL": ["https://github.com/CogComp/MCTACO"], "Categories": ["Answerability Classification"], "Reasoning": ["Temporal Reasoning", "Commonsense Reasoning"], "Definition": ["The answer will be 'yes' if the provided sentence contains an explicit mention that answers the given question. Otherwise, the answer should be 'no'. Instances where the answer is implied from the sentence using \"instinct\" or \"common sense\" (as opposed to being written explicitly in the sentence) should be labeled as 'no'."], "Positive Examples": [{"input": "Sentence: Jack played basketball for an hour after school, after which he was very tired. \nQuestion: How long did Jack play basketball?", "output": "Yes.", "explanation": "The answer to this question (an hour)  lies in its text."}, {"input": "Sentence: He was born in China, so he went to the Embassy at 1 pm to apply for a U.S. Visa. \nQuestion: When did he go to Embassy?", "output": "Yes.", "explanation": "The answer to this question (1 pm)  lies in its text."}], "Negative Examples": [{"input": "Sentence: Jack played basketball after school, after which he was very tired. \nQuestion: How long did Jack play basketball?", "output": "No.", "explanation": "The answer to this question is not present in its text and it requires commonsense to answer."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["News", "Wikipedia", "Law", "Justice", "History", "History -> 9/11 Reports", "Anthropology", "School Science Textbooks", "Fiction"], "Instance": {"id": "task020-0ddf2915172f4904b60566a79e1e55ac", "input": "Sentence: She told them that she would help take care of the puppy, if she could have one. \nQuestion: How often did she ask for a puppy?", "output": ["No."]}, "Instance License": ["Unknown"], "prediction": "Yes"}
+{"id": "task020-b97b4e60e1d64a88886251f4f048f373", "Task": "task020_mctaco_span_based_question", "Contributors": "['Swaroop Mishra', 'Daniel Khashabi']", "Source": ["mctaco"], "URL": ["https://github.com/CogComp/MCTACO"], "Categories": ["Answerability Classification"], "Reasoning": ["Temporal Reasoning", "Commonsense Reasoning"], "Definition": ["The answer will be 'yes' if the provided sentence contains an explicit mention that answers the given question. Otherwise, the answer should be 'no'. Instances where the answer is implied from the sentence using \"instinct\" or \"common sense\" (as opposed to being written explicitly in the sentence) should be labeled as 'no'."], "Positive Examples": [{"input": "Sentence: Jack played basketball for an hour after school, after which he was very tired. \nQuestion: How long did Jack play basketball?", "output": "Yes.", "explanation": "The answer to this question (an hour)  lies in its text."}, {"input": "Sentence: He was born in China, so he went to the Embassy at 1 pm to apply for a U.S. Visa. \nQuestion: When did he go to Embassy?", "output": "Yes.", "explanation": "The answer to this question (1 pm)  lies in its text."}], "Negative Examples": [{"input": "Sentence: Jack played basketball after school, after which he was very tired. \nQuestion: How long did Jack play basketball?", "output": "No.", "explanation": "The answer to this question is not present in its text and it requires commonsense to answer."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["News", "Wikipedia", "Law", "Justice", "History", "History -> 9/11 Reports", "Anthropology", "School Science Textbooks", "Fiction"], "Instance": {"id": "task020-b97b4e60e1d64a88886251f4f048f373", "input": "Sentence: Radio Televizioni Shqiptar (RTSH) is the public radio and TV broadcaster of Albania, founded by King Zog in 1938. \nQuestion: How long has RTSH been established?", "output": ["Yes."]}, "Instance License": ["Unknown"], "prediction": "Yes"}
+{"id": "task020-45805df0fe054d5d888a5a14751391f0", "Task": "task020_mctaco_span_based_question", "Contributors": "['Swaroop Mishra', 'Daniel Khashabi']", "Source": ["mctaco"], "URL": ["https://github.com/CogComp/MCTACO"], "Categories": ["Answerability Classification"], "Reasoning": ["Temporal Reasoning", "Commonsense Reasoning"], "Definition": ["The answer will be 'yes' if the provided sentence contains an explicit mention that answers the given question. Otherwise, the answer should be 'no'. Instances where the answer is implied from the sentence using \"instinct\" or \"common sense\" (as opposed to being written explicitly in the sentence) should be labeled as 'no'."], "Positive Examples": [{"input": "Sentence: Jack played basketball for an hour after school, after which he was very tired. \nQuestion: How long did Jack play basketball?", "output": "Yes.", "explanation": "The answer to this question (an hour)  lies in its text."}, {"input": "Sentence: He was born in China, so he went to the Embassy at 1 pm to apply for a U.S. Visa. \nQuestion: When did he go to Embassy?", "output": "Yes.", "explanation": "The answer to this question (1 pm)  lies in its text."}], "Negative Examples": [{"input": "Sentence: Jack played basketball after school, after which he was very tired. \nQuestion: How long did Jack play basketball?", "output": "No.", "explanation": "The answer to this question is not present in its text and it requires commonsense to answer."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["News", "Wikipedia", "Law", "Justice", "History", "History -> 9/11 Reports", "Anthropology", "School Science Textbooks", "Fiction"], "Instance": {"id": "task020-45805df0fe054d5d888a5a14751391f0", "input": "Sentence: The Persian Gulf War destroyed much of the country's medical infrastructure, according to a report by the World Health Organization. \nQuestion: How long did it take the Persian Gulf War to destroy the country's medical infrastructure?", "output": ["No."]}, "Instance License": ["Unknown"], "prediction": "Yes"}
+{"id": "task642-f1b932e6b989465287341a1d1772cc99", "Task": "task642_esnli_classification", "Contributors": "['Ian Lobo']", "Source": ["e_snli"], "URL": ["https://github.com/OanaMariaCamburu/e-SNLI/"], "Categories": ["Textual Entailment"], "Reasoning": ["Textual Entailment"], "Definition": ["Given Sentence 1 and Sentence 2, indicate your answer as yes when the two sentences clearly agree or clearly disagree with each other. If the relationship cannot be determined, answer with 'no'."], "Positive Examples": [{"input": "A boy in a blue jacket rides a skateboard down the street. <sep> A blue jacketed boy is standing in football field.", "output": "yes", "explanation": "This answer is yes because the boy can either be riding or standing but not both. Since the statements disagree, the answer is yes."}, {"input": "A large group of people gather at a piano bar. <sep> A group of men at a piano bar", "output": "no", "explanation": "This answer is no because we can't assume the gender of people and assume them to be men. Since we can't determine clearly, the answer is no."}], "Negative Examples": [{"input": "There are two young ladies jogging, by the ocean side. <sep> Two women are running late for a meeting.", "output": "yes", "explanation": "The answer should be no. Just because the ladies are jogging doesn't mean they are running late for something."}, {"input": "A man and a woman are on a seesaw. <sep> Two adults on a seesaw.", "output": "no", "explanation": "The answer should be yes. A man and woman can also be called two adults."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Miscellaneous"], "Instance": {"id": "task642-f1b932e6b989465287341a1d1772cc99", "input": "A brown dog sniffing at the fence of a brown bull. <sep> The brown dog was looking intently at the bull on the other side.", "output": ["no"]}, "Instance License": ["MIT"], "prediction": "yes"}
+{"id": "task642-b21062e724e94915abde9d8856088194", "Task": "task642_esnli_classification", "Contributors": "['Ian Lobo']", "Source": ["e_snli"], "URL": ["https://github.com/OanaMariaCamburu/e-SNLI/"], "Categories": ["Textual Entailment"], "Reasoning": ["Textual Entailment"], "Definition": ["Given Sentence 1 and Sentence 2, indicate your answer as yes when the two sentences clearly agree or clearly disagree with each other. If the relationship cannot be determined, answer with 'no'."], "Positive Examples": [{"input": "A boy in a blue jacket rides a skateboard down the street. <sep> A blue jacketed boy is standing in football field.", "output": "yes", "explanation": "This answer is yes because the boy can either be riding or standing but not both. Since the statements disagree, the answer is yes."}, {"input": "A large group of people gather at a piano bar. <sep> A group of men at a piano bar", "output": "no", "explanation": "This answer is no because we can't assume the gender of people and assume them to be men. Since we can't determine clearly, the answer is no."}], "Negative Examples": [{"input": "There are two young ladies jogging, by the ocean side. <sep> Two women are running late for a meeting.", "output": "yes", "explanation": "The answer should be no. Just because the ladies are jogging doesn't mean they are running late for something."}, {"input": "A man and a woman are on a seesaw. <sep> Two adults on a seesaw.", "output": "no", "explanation": "The answer should be yes. A man and woman can also be called two adults."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Miscellaneous"], "Instance": {"id": "task642-b21062e724e94915abde9d8856088194", "input": "Cityscape with four men on bikes serving as the focal point of picture. <sep> Local robbers escape after stealing an otter", "output": ["yes"]}, "Instance License": ["MIT"], "prediction": "no"}
+{"id": "task642-17adb551766a4b60a639ea76ae7a55ce", "Task": "task642_esnli_classification", "Contributors": "['Ian Lobo']", "Source": ["e_snli"], "URL": ["https://github.com/OanaMariaCamburu/e-SNLI/"], "Categories": ["Textual Entailment"], "Reasoning": ["Textual Entailment"], "Definition": ["Given Sentence 1 and Sentence 2, indicate your answer as yes when the two sentences clearly agree or clearly disagree with each other. If the relationship cannot be determined, answer with 'no'."], "Positive Examples": [{"input": "A boy in a blue jacket rides a skateboard down the street. <sep> A blue jacketed boy is standing in football field.", "output": "yes", "explanation": "This answer is yes because the boy can either be riding or standing but not both. Since the statements disagree, the answer is yes."}, {"input": "A large group of people gather at a piano bar. <sep> A group of men at a piano bar", "output": "no", "explanation": "This answer is no because we can't assume the gender of people and assume them to be men. Since we can't determine clearly, the answer is no."}], "Negative Examples": [{"input": "There are two young ladies jogging, by the ocean side. <sep> Two women are running late for a meeting.", "output": "yes", "explanation": "The answer should be no. Just because the ladies are jogging doesn't mean they are running late for something."}, {"input": "A man and a woman are on a seesaw. <sep> Two adults on a seesaw.", "output": "no", "explanation": "The answer should be yes. A man and woman can also be called two adults."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Miscellaneous"], "Instance": {"id": "task642-17adb551766a4b60a639ea76ae7a55ce", "input": "The young lady is giving the old man a hug. <sep> The lady is giving the old man a hug.", "output": ["yes"]}, "Instance License": ["MIT"], "prediction": "yes"}
+{"id": "task642-11613bf6084d45da9859f099b3b719ac", "Task": "task642_esnli_classification", "Contributors": "['Ian Lobo']", "Source": ["e_snli"], "URL": ["https://github.com/OanaMariaCamburu/e-SNLI/"], "Categories": ["Textual Entailment"], "Reasoning": ["Textual Entailment"], "Definition": ["Given Sentence 1 and Sentence 2, indicate your answer as yes when the two sentences clearly agree or clearly disagree with each other. If the relationship cannot be determined, answer with 'no'."], "Positive Examples": [{"input": "A boy in a blue jacket rides a skateboard down the street. <sep> A blue jacketed boy is standing in football field.", "output": "yes", "explanation": "This answer is yes because the boy can either be riding or standing but not both. Since the statements disagree, the answer is yes."}, {"input": "A large group of people gather at a piano bar. <sep> A group of men at a piano bar", "output": "no", "explanation": "This answer is no because we can't assume the gender of people and assume them to be men. Since we can't determine clearly, the answer is no."}], "Negative Examples": [{"input": "There are two young ladies jogging, by the ocean side. <sep> Two women are running late for a meeting.", "output": "yes", "explanation": "The answer should be no. Just because the ladies are jogging doesn't mean they are running late for something."}, {"input": "A man and a woman are on a seesaw. <sep> Two adults on a seesaw.", "output": "no", "explanation": "The answer should be yes. A man and woman can also be called two adults."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Miscellaneous"], "Instance": {"id": "task642-11613bf6084d45da9859f099b3b719ac", "input": "A skateboarding youth does a trick on a rail. <sep> A young boy showing his new skateboard tricks to his friends.", "output": ["no"]}, "Instance License": ["MIT"], "prediction": "yes"}
+{"id": "task642-f95c440d81784a8ca581278fef25139b", "Task": "task642_esnli_classification", "Contributors": "['Ian Lobo']", "Source": ["e_snli"], "URL": ["https://github.com/OanaMariaCamburu/e-SNLI/"], "Categories": ["Textual Entailment"], "Reasoning": ["Textual Entailment"], "Definition": ["Given Sentence 1 and Sentence 2, indicate your answer as yes when the two sentences clearly agree or clearly disagree with each other. If the relationship cannot be determined, answer with 'no'."], "Positive Examples": [{"input": "A boy in a blue jacket rides a skateboard down the street. <sep> A blue jacketed boy is standing in football field.", "output": "yes", "explanation": "This answer is yes because the boy can either be riding or standing but not both. Since the statements disagree, the answer is yes."}, {"input": "A large group of people gather at a piano bar. <sep> A group of men at a piano bar", "output": "no", "explanation": "This answer is no because we can't assume the gender of people and assume them to be men. Since we can't determine clearly, the answer is no."}], "Negative Examples": [{"input": "There are two young ladies jogging, by the ocean side. <sep> Two women are running late for a meeting.", "output": "yes", "explanation": "The answer should be no. Just because the ladies are jogging doesn't mean they are running late for something."}, {"input": "A man and a woman are on a seesaw. <sep> Two adults on a seesaw.", "output": "no", "explanation": "The answer should be yes. A man and woman can also be called two adults."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Miscellaneous"], "Instance": {"id": "task642-f95c440d81784a8ca581278fef25139b", "input": "A man and woman are taking a picture of themselves while a woman in a scarf walks by them. <sep> A man and woman take selfies of themselves.", "output": ["yes"]}, "Instance License": ["MIT"], "prediction": "yes"}
+{"id": "task102-1b5f269cf9a94e62986c9dc8bd367bbc", "Task": "task102_commongen_sentence_generation", "Contributors": "['Mihir Parmar']", "Source": ["commongen"], "URL": ["https://inklab.usc.edu/CommonGen/"], "Categories": ["Data to Text"], "Reasoning": ["Relational Reasoning", "Analogical Reasoning", "Commonsense Reasoning"], "Definition": ["In this task, you are given concept set (with 3 to 5 concepts) that contain mentions of names of people, places, activities, or things. These concept sets reflect reasonable concept co-occurrences in everyday situations. All concepts given as input are separated by \"#\". Your job is to generate a sentence describing a day-to-day scene using all concepts from a given concept set."], "Positive Examples": [{"input": "mountain#ski#skier", "output": "Skier skis down the mountain", "explanation": "Generated sentence as output is based on all three concepts \"mountain\", \"ski\", and \"skier\" given in the concept set."}, {"input": "call#character#contain#wallpaper", "output": "queen of wallpaper containing a portrait called film character .", "explanation": "Generated sentence as output is based on all four concepts \"call\", \"character\", \"contain\", and \"wallpaper\" given in the concept set."}, {"input": "artwork#element#place#temple#worship", "output": "type of place of worship of artwork featuring a temple or place of worship and religious elements", "explanation": "Generated sentence as output is based on all five concepts \"artwork\", \"element\", \"place\", \"temple\", and \"worship\" given in the concept set."}], "Negative Examples": [{"input": "monarch#present#trophy#win", "output": "A huge commercial airplane comes down the runway.", "explanation": "No concepts from given concept set are present in the output sentence."}, {"input": "hang#stall#wall", "output": "military commander entering into a city on the railway", "explanation": "No concepts from given concept set are present in the output sentence."}, {"input": "eat#hay#horse", "output": "A horse is eating grass.", "explanation": "Only two concepts, i.e., 'eat' and 'horse' are used in generating sentence, but cencept 'hay' is not used."}, {"input": "fan#match#watch", "output": "play a match with friends", "explanation": "Only one concept, i.e., 'match' is used, but cencepts 'watch' and 'friends' are missing from generated sentence."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Captions -> Image Captions"], "Instance": {"id": "task102-1b5f269cf9a94e62986c9dc8bd367bbc", "input": "sit#station#train", "output": ["a train sits at the station", "A train that is sitting in a station.", "A red train sitting at an empty station."]}, "Instance License": ["MIT"], "prediction": "Train travels along the station."}
+{"id": "task102-f9b3232975f9477aa443c8270e8bad45", "Task": "task102_commongen_sentence_generation", "Contributors": "['Mihir Parmar']", "Source": ["commongen"], "URL": ["https://inklab.usc.edu/CommonGen/"], "Categories": ["Data to Text"], "Reasoning": ["Relational Reasoning", "Analogical Reasoning", "Commonsense Reasoning"], "Definition": ["In this task, you are given concept set (with 3 to 5 concepts) that contain mentions of names of people, places, activities, or things. These concept sets reflect reasonable concept co-occurrences in everyday situations. All concepts given as input are separated by \"#\". Your job is to generate a sentence describing a day-to-day scene using all concepts from a given concept set."], "Positive Examples": [{"input": "mountain#ski#skier", "output": "Skier skis down the mountain", "explanation": "Generated sentence as output is based on all three concepts \"mountain\", \"ski\", and \"skier\" given in the concept set."}, {"input": "call#character#contain#wallpaper", "output": "queen of wallpaper containing a portrait called film character .", "explanation": "Generated sentence as output is based on all four concepts \"call\", \"character\", \"contain\", and \"wallpaper\" given in the concept set."}, {"input": "artwork#element#place#temple#worship", "output": "type of place of worship of artwork featuring a temple or place of worship and religious elements", "explanation": "Generated sentence as output is based on all five concepts \"artwork\", \"element\", \"place\", \"temple\", and \"worship\" given in the concept set."}], "Negative Examples": [{"input": "monarch#present#trophy#win", "output": "A huge commercial airplane comes down the runway.", "explanation": "No concepts from given concept set are present in the output sentence."}, {"input": "hang#stall#wall", "output": "military commander entering into a city on the railway", "explanation": "No concepts from given concept set are present in the output sentence."}, {"input": "eat#hay#horse", "output": "A horse is eating grass.", "explanation": "Only two concepts, i.e., 'eat' and 'horse' are used in generating sentence, but cencept 'hay' is not used."}, {"input": "fan#match#watch", "output": "play a match with friends", "explanation": "Only one concept, i.e., 'match' is used, but cencepts 'watch' and 'friends' are missing from generated sentence."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Captions -> Image Captions"], "Instance": {"id": "task102-f9b3232975f9477aa443c8270e8bad45", "input": "farmer#field#plow", "output": ["A farmer plows his field.", "The farmer is plowing his field.", "A couple of farmers plowing a field"]}, "Instance License": ["MIT"], "prediction": "Farmer plowing the field."}
+{"id": "task102-36b4e3a3ae66461fae8e2231a5304a37", "Task": "task102_commongen_sentence_generation", "Contributors": "['Mihir Parmar']", "Source": ["commongen"], "URL": ["https://inklab.usc.edu/CommonGen/"], "Categories": ["Data to Text"], "Reasoning": ["Relational Reasoning", "Analogical Reasoning", "Commonsense Reasoning"], "Definition": ["In this task, you are given concept set (with 3 to 5 concepts) that contain mentions of names of people, places, activities, or things. These concept sets reflect reasonable concept co-occurrences in everyday situations. All concepts given as input are separated by \"#\". Your job is to generate a sentence describing a day-to-day scene using all concepts from a given concept set."], "Positive Examples": [{"input": "mountain#ski#skier", "output": "Skier skis down the mountain", "explanation": "Generated sentence as output is based on all three concepts \"mountain\", \"ski\", and \"skier\" given in the concept set."}, {"input": "call#character#contain#wallpaper", "output": "queen of wallpaper containing a portrait called film character .", "explanation": "Generated sentence as output is based on all four concepts \"call\", \"character\", \"contain\", and \"wallpaper\" given in the concept set."}, {"input": "artwork#element#place#temple#worship", "output": "type of place of worship of artwork featuring a temple or place of worship and religious elements", "explanation": "Generated sentence as output is based on all five concepts \"artwork\", \"element\", \"place\", \"temple\", and \"worship\" given in the concept set."}], "Negative Examples": [{"input": "monarch#present#trophy#win", "output": "A huge commercial airplane comes down the runway.", "explanation": "No concepts from given concept set are present in the output sentence."}, {"input": "hang#stall#wall", "output": "military commander entering into a city on the railway", "explanation": "No concepts from given concept set are present in the output sentence."}, {"input": "eat#hay#horse", "output": "A horse is eating grass.", "explanation": "Only two concepts, i.e., 'eat' and 'horse' are used in generating sentence, but cencept 'hay' is not used."}, {"input": "fan#match#watch", "output": "play a match with friends", "explanation": "Only one concept, i.e., 'match' is used, but cencepts 'watch' and 'friends' are missing from generated sentence."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Captions -> Image Captions"], "Instance": {"id": "task102-36b4e3a3ae66461fae8e2231a5304a37", "input": "family#park#picnic", "output": ["family on the picnic in park", "A family has a picnic at the park.", "young family having picnic in a park"]}, "Instance License": ["MIT"], "prediction": "The family picnics in the park."}
+{"id": "task102-ea0ac1126ac448aca10e4ea421791b98", "Task": "task102_commongen_sentence_generation", "Contributors": "['Mihir Parmar']", "Source": ["commongen"], "URL": ["https://inklab.usc.edu/CommonGen/"], "Categories": ["Data to Text"], "Reasoning": ["Relational Reasoning", "Analogical Reasoning", "Commonsense Reasoning"], "Definition": ["In this task, you are given concept set (with 3 to 5 concepts) that contain mentions of names of people, places, activities, or things. These concept sets reflect reasonable concept co-occurrences in everyday situations. All concepts given as input are separated by \"#\". Your job is to generate a sentence describing a day-to-day scene using all concepts from a given concept set."], "Positive Examples": [{"input": "mountain#ski#skier", "output": "Skier skis down the mountain", "explanation": "Generated sentence as output is based on all three concepts \"mountain\", \"ski\", and \"skier\" given in the concept set."}, {"input": "call#character#contain#wallpaper", "output": "queen of wallpaper containing a portrait called film character .", "explanation": "Generated sentence as output is based on all four concepts \"call\", \"character\", \"contain\", and \"wallpaper\" given in the concept set."}, {"input": "artwork#element#place#temple#worship", "output": "type of place of worship of artwork featuring a temple or place of worship and religious elements", "explanation": "Generated sentence as output is based on all five concepts \"artwork\", \"element\", \"place\", \"temple\", and \"worship\" given in the concept set."}], "Negative Examples": [{"input": "monarch#present#trophy#win", "output": "A huge commercial airplane comes down the runway.", "explanation": "No concepts from given concept set are present in the output sentence."}, {"input": "hang#stall#wall", "output": "military commander entering into a city on the railway", "explanation": "No concepts from given concept set are present in the output sentence."}, {"input": "eat#hay#horse", "output": "A horse is eating grass.", "explanation": "Only two concepts, i.e., 'eat' and 'horse' are used in generating sentence, but cencept 'hay' is not used."}, {"input": "fan#match#watch", "output": "play a match with friends", "explanation": "Only one concept, i.e., 'match' is used, but cencepts 'watch' and 'friends' are missing from generated sentence."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Captions -> Image Captions"], "Instance": {"id": "task102-ea0ac1126ac448aca10e4ea421791b98", "input": "airport#luggage#wait", "output": ["People wait for their luggage at an airport.", "Man waiting next to his luggage at an airport.", "Several men waiting on their luggage at the airport."]}, "Instance License": ["MIT"], "prediction": "wait for luggage to arrive at the airport."}
+{"id": "task102-793cd08ac45043748060b051f3da2abe", "Task": "task102_commongen_sentence_generation", "Contributors": "['Mihir Parmar']", "Source": ["commongen"], "URL": ["https://inklab.usc.edu/CommonGen/"], "Categories": ["Data to Text"], "Reasoning": ["Relational Reasoning", "Analogical Reasoning", "Commonsense Reasoning"], "Definition": ["In this task, you are given concept set (with 3 to 5 concepts) that contain mentions of names of people, places, activities, or things. These concept sets reflect reasonable concept co-occurrences in everyday situations. All concepts given as input are separated by \"#\". Your job is to generate a sentence describing a day-to-day scene using all concepts from a given concept set."], "Positive Examples": [{"input": "mountain#ski#skier", "output": "Skier skis down the mountain", "explanation": "Generated sentence as output is based on all three concepts \"mountain\", \"ski\", and \"skier\" given in the concept set."}, {"input": "call#character#contain#wallpaper", "output": "queen of wallpaper containing a portrait called film character .", "explanation": "Generated sentence as output is based on all four concepts \"call\", \"character\", \"contain\", and \"wallpaper\" given in the concept set."}, {"input": "artwork#element#place#temple#worship", "output": "type of place of worship of artwork featuring a temple or place of worship and religious elements", "explanation": "Generated sentence as output is based on all five concepts \"artwork\", \"element\", \"place\", \"temple\", and \"worship\" given in the concept set."}], "Negative Examples": [{"input": "monarch#present#trophy#win", "output": "A huge commercial airplane comes down the runway.", "explanation": "No concepts from given concept set are present in the output sentence."}, {"input": "hang#stall#wall", "output": "military commander entering into a city on the railway", "explanation": "No concepts from given concept set are present in the output sentence."}, {"input": "eat#hay#horse", "output": "A horse is eating grass.", "explanation": "Only two concepts, i.e., 'eat' and 'horse' are used in generating sentence, but cencept 'hay' is not used."}, {"input": "fan#match#watch", "output": "play a match with friends", "explanation": "Only one concept, i.e., 'match' is used, but cencepts 'watch' and 'friends' are missing from generated sentence."}], "Input_language": ["English"], "Output_language": ["English"], "Instruction_language": ["English"], "Domains": ["Captions -> Image Captions"], "Instance": {"id": "task102-793cd08ac45043748060b051f3da2abe", "input": "come#track#train", "output": ["train coming down the track", "A train is coming along on a track.", "a long train in coming down some tracks"]}, "Instance License": ["MIT"], "prediction": "Train arrives at the station."}