{"GEM/web_nlg_en": {"0": {"PALM_prompt": {"bleu": 0.4274462846584994, "bleu_stderr": 0.026506045585829644, "rouge1_fmeasure": 0.11401591584123742, "rouge1_fmeasure_stderr": 0.0020018749467427548, "rouge1_precision": 0.0743940764798566, "rouge1_precision_stderr": 0.0014865309649260369, "rouge1_recall": 0.32181178468311483, "rouge1_recall_stderr": 0.0046779793640138664, "rouge2_fmeasure": 0.05433244012190525, "rouge2_fmeasure_stderr": 0.0012833100172831976, "rouge2_precision": 0.035398271042759596, "rouge2_precision_stderr": 0.0009285365780968767, "rouge2_recall": 0.15703798625688678, "rouge2_recall_stderr": 0.0033071200278070876, "rougeL_fmeasure": 0.10946929754745122, "rougeL_fmeasure_stderr": 0.0018607174533106234, "rougeL_precision": 0.07120802247039631, "rougeL_precision_stderr": 0.001362906540968755, "rougeL_recall": 0.31125592253868395, "rougeL_recall_stderr": 0.004548153090547622, "rougeLsum_fmeasure": 0.10881188996025698, "rougeLsum_fmeasure_stderr": 0.0018835358686024326, "rougeLsum_precision": 0.07100637180754554, "rougeLsum_precision_stderr": 0.001398755345483045, "rougeLsum_recall": 0.3067417251277733, "rougeLsum_recall_stderr": 0.004374950039871412}}, "1": {"PALM_prompt": {"bleu": 0.5086086062549235, "bleu_stderr": 0.024148152161397957, "rouge1_fmeasure": 0.11613651882382699, "rouge1_fmeasure_stderr": 0.0017869903586088247, "rouge1_precision": 0.07420670646576108, "rouge1_precision_stderr": 0.0012994585087623457, "rouge1_recall": 0.3699833502592873, "rouge1_recall_stderr": 0.005221535560959868, "rouge2_fmeasure": 0.05556040217298211, "rouge2_fmeasure_stderr": 0.0011573526331625286, "rouge2_precision": 0.03528298594442465, "rouge2_precision_stderr": 0.0008131219269542471, "rouge2_recall": 0.18919504627943293, "rouge2_recall_stderr": 0.003948470106675628, "rougeL_fmeasure": 0.11069330166344538, "rougeL_fmeasure_stderr": 0.0016501808624972724, "rougeL_precision": 0.07064592165677544, "rougeL_precision_stderr": 0.0011911523984872805, "rougeL_recall": 0.3529817507096153, "rougeL_recall_stderr": 0.00491517289541728, "rougeLsum_fmeasure": 0.11048988644232176, "rougeLsum_fmeasure_stderr": 0.001670545364215763, "rougeLsum_precision": 0.07063890112491973, "rougeLsum_precision_stderr": 0.0012189437083937394, "rougeLsum_recall": 0.35151452415262047, "rougeLsum_recall_stderr": 0.004837998006757547}}, "2": {"PALM_prompt": {"bleu": 0.6056899396941058, "bleu_stderr": 0.031095911436243143, "rouge1_fmeasure": 0.11269434916911006, "rouge1_fmeasure_stderr": 0.0016709087363002723, "rouge1_precision": 0.07171720323593823, "rouge1_precision_stderr": 0.0013407577731600893, "rouge1_recall": 0.3940444073904271, "rouge1_recall_stderr": 0.005453929450001824, "rouge2_fmeasure": 0.05325348987984883, "rouge2_fmeasure_stderr": 0.0010824823620329564, "rouge2_precision": 0.03342565708524102, "rouge2_precision_stderr": 0.0007679332484666479, "rouge2_recall": 0.20366528828334413, "rouge2_recall_stderr": 0.004145286907818467, "rougeL_fmeasure": 0.10449422734114891, "rougeL_fmeasure_stderr": 0.0014912988107590758, "rougeL_precision": 0.06654587012077771, "rougeL_precision_stderr": 0.0012126902994658729, "rougeL_recall": 0.3626163032278441, "rougeL_recall_stderr": 0.004808677935098044, "rougeLsum_fmeasure": 0.1068591227441311, "rougeLsum_fmeasure_stderr": 0.0015708609058507584, "rougeLsum_precision": 0.06809528741035778, "rougeLsum_precision_stderr": 0.0012705443708076406, "rougeLsum_recall": 0.3717881435944756, "rougeLsum_recall_stderr": 0.005017031823311842}}, "3": {"PALM_prompt": {"bleu": 0.7043691445234566, "bleu_stderr": 0.033436352647492236, "rouge1_fmeasure": 0.11118267231139893, "rouge1_fmeasure_stderr": 0.0016217396109271171, "rouge1_precision": 0.06945197089001147, "rouge1_precision_stderr": 0.0011528009544658436, "rouge1_recall": 0.40339819978438163, "rouge1_recall_stderr": 0.005565480395978604, "rouge2_fmeasure": 0.05211591902402141, "rouge2_fmeasure_stderr": 0.0010331141960554706, "rouge2_precision": 0.03230783770657853, "rouge2_precision_stderr": 0.0007067527472951313, "rouge2_recall": 0.20764571809595184, "rouge2_recall_stderr": 0.004196897185127135, "rougeL_fmeasure": 0.10117012026750102, "rougeL_fmeasure_stderr": 0.0014209168284038964, "rougeL_precision": 0.0633620924773605, "rougeL_precision_stderr": 0.0010232470500386361, "rougeL_recall": 0.3638284378001932, "rougeL_recall_stderr": 0.004793212255287554, "rougeLsum_fmeasure": 0.1053138951283582, "rougeLsum_fmeasure_stderr": 0.001529640334300114, "rougeLsum_precision": 0.06592327408520764, "rougeLsum_precision_stderr": 0.0010958929866110073, "rougeLsum_recall": 0.37984454029428794, "rougeLsum_recall_stderr": 0.005122585721030877}}, "4": {"PALM_prompt": {"bleu": 0.7237940725363642, "bleu_stderr": 0.05068347700106321, "rouge1_fmeasure": 0.10982478834712758, "rouge1_fmeasure_stderr": 0.0015663207694755273, "rouge1_precision": 0.06842641677261545, "rouge1_precision_stderr": 0.0011165170819324747, "rouge1_recall": 0.406375539617853, "rouge1_recall_stderr": 0.00550424978526618, "rouge2_fmeasure": 0.05155868190087433, "rouge2_fmeasure_stderr": 0.0009911919774912529, "rouge2_precision": 0.031843816337460154, "rouge2_precision_stderr": 0.0006802306529242348, "rouge2_recall": 0.2101465380791208, "rouge2_recall_stderr": 0.004148287013449519, "rougeL_fmeasure": 0.09912881209100917, "rougeL_fmeasure_stderr": 0.001366723974954788, "rougeL_precision": 0.06196757937456414, "rougeL_precision_stderr": 0.0009925820821838872, "rougeL_recall": 0.36309144001642407, "rougeL_recall_stderr": 0.004660726913536042, "rougeLsum_fmeasure": 0.10396329790700495, "rougeLsum_fmeasure_stderr": 0.0014800754096392262, "rougeLsum_precision": 0.06489771066521006, "rougeLsum_precision_stderr": 0.0010636680077013658, "rougeLsum_recall": 0.3825474992320362, "rougeLsum_recall_stderr": 0.005083374729929655}}, "5": {"PALM_prompt": {"bleu": 0.8235132351061684, "bleu_stderr": 0.03673652426206423, "rouge1_fmeasure": 0.11000005624917578, "rouge1_fmeasure_stderr": 0.001511602784285709, "rouge1_precision": 0.06807661053530396, "rouge1_precision_stderr": 0.0010608834381468243, "rouge1_recall": 0.41555132879030265, "rouge1_recall_stderr": 0.005712806441867834, "rouge2_fmeasure": 0.05209703492451165, "rouge2_fmeasure_stderr": 0.000966760303297213, "rouge2_precision": 0.03190049650831127, "rouge2_precision_stderr": 0.0006496066520260159, "rouge2_recall": 0.21868118098088812, "rouge2_recall_stderr": 0.004351358375129378, "rougeL_fmeasure": 0.09833778576062344, "rougeL_fmeasure_stderr": 0.0013130705666902862, "rougeL_precision": 0.061096978042372, "rougeL_precision_stderr": 0.0009419140672594094, "rougeL_recall": 0.3679922650615108, "rougeL_recall_stderr": 0.004831134262904494, "rougeLsum_fmeasure": 0.10329798028758783, "rougeLsum_fmeasure_stderr": 0.0014185087292018597, "rougeLsum_precision": 0.06407881465692666, "rougeLsum_precision_stderr": 0.0010057526623759078, "rougeLsum_recall": 0.38744747681119496, "rougeLsum_recall_stderr": 0.00519938044209454}}}, "GEM/wiki_lingua_en": {"0": {"tldr_en": {"bleu": 1.607743073760489, "bleu_stderr": 0.0505448817544192, "rouge1_fmeasure": 0.16789045871402775, "rouge1_fmeasure_stderr": 0.001899331826630772, "rouge1_precision": 0.141621308728508, "rouge1_precision_stderr": 0.001852197455721959, "rouge1_recall": 0.2487835153814821, "rouge1_recall_stderr": 0.002883968433439267, "rouge2_fmeasure": 0.033980155567562176, "rouge2_fmeasure_stderr": 0.0008772611553649017, "rouge2_precision": 0.028274308481376006, "rouge2_precision_stderr": 0.0007638689773747983, "rouge2_recall": 0.05312688704536566, "rouge2_recall_stderr": 0.001543560570845198, "rougeL_fmeasure": 0.12866222215650755, "rougeL_fmeasure_stderr": 0.0013553903517883699, "rougeL_precision": 0.10723271379275104, "rougeL_precision_stderr": 0.0012832871011880624, "rougeL_recall": 0.19569867076577613, "rougeL_recall_stderr": 0.002336256705578366, "rougeLsum_fmeasure": 0.15551623162738257, "rougeLsum_fmeasure_stderr": 0.0017397466278372554, "rougeLsum_precision": 0.1310312538372522, "rougeLsum_precision_stderr": 0.0016949440714634507, "rougeLsum_recall": 0.2313303827432569, "rougeLsum_recall_stderr": 0.0026938189641655444}}, "1": {"tldr_en": {"bleu": 3.247891638911873, "bleu_stderr": 0.08372328781084526, "rouge1_fmeasure": 0.22971432102282577, "rouge1_fmeasure_stderr": 0.002024992641113895, "rouge1_precision": 0.20162081804133491, "rouge1_precision_stderr": 0.0023006404028398596, "rouge1_recall": 0.3302113914143275, "rouge1_recall_stderr": 0.0029253291213495436, "rouge2_fmeasure": 0.06075703698527234, "rouge2_fmeasure_stderr": 0.0011280888351149878, "rouge2_precision": 0.05353641148052063, "rouge2_precision_stderr": 0.0011596978277920967, "rouge2_recall": 0.0901699660110981, "rouge2_recall_stderr": 0.0018295391165180175, "rougeL_fmeasure": 0.16594057607108714, "rougeL_fmeasure_stderr": 0.0014257612958005858, "rougeL_precision": 0.14458374147535075, "rougeL_precision_stderr": 0.001635799675433344, "rougeL_recall": 0.24465580855285374, "rougeL_recall_stderr": 0.0024107233856668618, "rougeLsum_fmeasure": 0.21655317006571786, "rougeLsum_fmeasure_stderr": 0.001899322620870555, "rougeLsum_precision": 0.18996108622649027, "rougeLsum_precision_stderr": 0.002170230659407399, "rougeLsum_recall": 0.31222699454801467, "rougeLsum_recall_stderr": 0.0027814459127952855}}, "2": {"tldr_en": {"bleu": 3.7546658955082104, "bleu_stderr": 0.05106004200886398, "rouge1_fmeasure": 0.24066179288126918, "rouge1_fmeasure_stderr": 0.0020250503611946593, "rouge1_precision": 0.22464896032753767, "rouge1_precision_stderr": 0.00267471320719044, "rouge1_recall": 0.3334397692148636, "rouge1_recall_stderr": 0.0029039999435442228, "rouge2_fmeasure": 0.0672929256474048, "rouge2_fmeasure_stderr": 0.0011920824100654986, "rouge2_precision": 0.06367029131472855, "rouge2_precision_stderr": 0.0013893020454497178, "rouge2_recall": 0.09620481258465774, "rouge2_recall_stderr": 0.0019131250126952382, "rougeL_fmeasure": 0.17657109086645734, "rougeL_fmeasure_stderr": 0.001468075623241685, "rougeL_precision": 0.16413395555652943, "rougeL_precision_stderr": 0.0019891543999868556, "rougeL_recall": 0.250622872215609, "rougeL_recall_stderr": 0.0024435750314427333, "rougeLsum_fmeasure": 0.2268588669501038, "rougeLsum_fmeasure_stderr": 0.0019039387353264705, "rougeLsum_precision": 0.21176073950316202, "rougeLsum_precision_stderr": 0.0025334766675070507, "rougeLsum_recall": 0.31521561952071925, "rougeLsum_recall_stderr": 0.0027809099107783215}}, "3": {"tldr_en": {"bleu": 3.693352277729935, "bleu_stderr": 0.09530601369536958, "rouge1_fmeasure": 0.1999944588590951, "rouge1_fmeasure_stderr": 0.0024431054075354647, "rouge1_precision": 0.19547574181004312, "rouge1_precision_stderr": 0.003050688739798117, "rouge1_recall": 0.27599613346113083, "rouge1_recall_stderr": 0.003547296490903856, "rouge2_fmeasure": 0.055502076840201975, "rouge2_fmeasure_stderr": 0.0012165658097950253, "rouge2_precision": 0.05556100650606968, "rouge2_precision_stderr": 0.0015316523441232619, "rouge2_recall": 0.07900668123150884, "rouge2_recall_stderr": 0.001936538574501469, "rougeL_fmeasure": 0.14698550688574344, "rougeL_fmeasure_stderr": 0.0018099945049349275, "rougeL_precision": 0.14441472671608785, "rougeL_precision_stderr": 0.0023810920879014986, "rougeL_recall": 0.20695094754990062, "rougeL_recall_stderr": 0.0028534088606798126, "rougeLsum_fmeasure": 0.1893838880235665, "rougeLsum_fmeasure_stderr": 0.0023154515872413177, "rougeLsum_precision": 0.18528466682755065, "rougeLsum_precision_stderr": 0.002913994201194578, "rougeLsum_recall": 0.2616826664782059, "rougeLsum_recall_stderr": 0.0033798208398086076}}, "4": {"tldr_en": {"bleu": 0.7011252343751181, "bleu_stderr": 0.054776720182795745, "rouge1_fmeasure": 0.06295072251821578, "rouge1_fmeasure_stderr": 0.0021227903441220584, "rouge1_precision": 0.063039334135716, "rouge1_precision_stderr": 0.00237217321150148, "rouge1_recall": 0.09017328403874066, "rouge1_recall_stderr": 0.003175334226857727, "rouge2_fmeasure": 0.01740325470887385, "rouge2_fmeasure_stderr": 0.0008413142438273321, "rouge2_precision": 0.01726942511454547, "rouge2_precision_stderr": 0.001004417819364943, "rouge2_recall": 0.026632929529636855, "rouge2_recall_stderr": 0.0014520619320699361, "rougeL_fmeasure": 0.04720899567270062, "rougeL_fmeasure_stderr": 0.0015949102808424699, "rougeL_precision": 0.048037538244205064, "rougeL_precision_stderr": 0.0018761060154017623, "rougeL_recall": 0.06863572497099125, "rougeL_recall_stderr": 0.002484143953625902, "rougeLsum_fmeasure": 0.05941144209472935, "rougeLsum_fmeasure_stderr": 0.0020085067689640797, "rougeLsum_precision": 0.059620692839723696, "rougeLsum_precision_stderr": 0.0022577542164374776, "rougeLsum_recall": 0.08531399766560527, "rougeLsum_recall_stderr": 0.00302563434718094}}, "5": {"tldr_en": {"bleu": 6.442668131454499e-07, "bleu_stderr": 1.6780002001919048e-06, "rouge1_fmeasure": 0.010948945347352195, "rouge1_fmeasure_stderr": 0.0010303712513734353, "rouge1_precision": 0.011023013045319767, "rouge1_precision_stderr": 0.0011239191554005244, "rouge1_recall": 0.01576861876664237, "rouge1_recall_stderr": 0.001514110135289748, "rouge2_fmeasure": 0.003081959728364898, "rouge2_fmeasure_stderr": 0.0003958924398148921, "rouge2_precision": 0.0030642982687765735, "rouge2_precision_stderr": 0.00043761754647970557, "rouge2_recall": 0.0048436181769985496, "rouge2_recall_stderr": 0.0007069513940476318, "rougeL_fmeasure": 0.008113230483687816, "rougeL_fmeasure_stderr": 0.000757965684491531, "rougeL_precision": 0.008303485879920013, "rougeL_precision_stderr": 0.000873077615735369, "rougeL_recall": 0.011933114229936235, "rougeL_recall_stderr": 0.0011773390443061134, "rougeLsum_fmeasure": 0.010379882751860353, "rougeLsum_fmeasure_stderr": 0.0009814470061507048, "rougeLsum_precision": 0.010476549059782741, "rougeLsum_precision_stderr": 0.0010807405840856448, "rougeLsum_recall": 0.015045032229734936, "rougeLsum_recall_stderr": 0.0014570036926186405}}}, "e2e_nlg_cleaned": {"0": {"generate_text_restaurant": {"bleu": 1.2617835680167517, "bleu_stderr": 0.10635778923661202, "rouge1_fmeasure": 0.14934980508808265, "rouge1_fmeasure_stderr": 0.0016043096357849695, "rouge1_precision": 0.11745138823891885, "rouge1_precision_stderr": 0.0015011277238236715, "rouge1_recall": 0.22985234642531047, "rouge1_recall_stderr": 0.002121425510390003, "rouge2_fmeasure": 0.027899167959252163, "rouge2_fmeasure_stderr": 0.0009510765177625647, "rouge2_precision": 0.022449491334163164, "rouge2_precision_stderr": 0.0007873950105451982, "rouge2_recall": 0.041963515173589365, "rouge2_recall_stderr": 0.0013675959887181714, "rougeL_fmeasure": 0.13395735123983762, "rougeL_fmeasure_stderr": 0.00119951498857243, "rougeL_precision": 0.1035383301816468, "rougeL_precision_stderr": 0.0010714123610581939, "rougeL_recall": 0.21015803872628752, "rougeL_recall_stderr": 0.0017418540261349958, "rougeLsum_fmeasure": 0.13550871061320946, "rougeLsum_fmeasure_stderr": 0.001452232590175344, "rougeLsum_precision": 0.10678429826736537, "rougeLsum_precision_stderr": 0.0013783155650794233, "rougeLsum_recall": 0.20841519216554769, "rougeLsum_recall_stderr": 0.0019094622189363957}}, "1": {"generate_text_restaurant": {"bleu": 8.028465709884875, "bleu_stderr": 0.10414333335862284, "rouge1_fmeasure": 0.39099089747429966, "rouge1_fmeasure_stderr": 0.0019423224150055892, "rouge1_precision": 0.33860487694185304, "rouge1_precision_stderr": 0.002059676862058819, "rouge1_recall": 0.5051950548626472, "rouge1_recall_stderr": 0.00294388539222501, "rouge2_fmeasure": 0.17313651053671014, "rouge2_fmeasure_stderr": 0.0015844557666629471, "rouge2_precision": 0.14891190026236875, "rouge2_precision_stderr": 0.0014722962919980933, "rouge2_recall": 0.2273413357531751, "rouge2_recall_stderr": 0.002240835952327236, "rougeL_fmeasure": 0.2875433639233825, "rougeL_fmeasure_stderr": 0.0015221333146636332, "rougeL_precision": 0.24778622071466067, "rougeL_precision_stderr": 0.001542767658539951, "rougeL_recall": 0.3751611447552265, "rougeL_recall_stderr": 0.0024874116332485865, "rougeLsum_fmeasure": 0.3214385233916606, "rougeLsum_fmeasure_stderr": 0.001926585809990621, "rougeLsum_precision": 0.2789653525284207, "rougeLsum_precision_stderr": 0.001973666047446342, "rougeLsum_recall": 0.4143210047809657, "rougeLsum_recall_stderr": 0.002765128231116627}}, "2": {"generate_text_restaurant": {"bleu": 10.118135078197039, "bleu_stderr": 0.09810052501619766, "rouge1_fmeasure": 0.42448550544175645, "rouge1_fmeasure_stderr": 0.001825472888691242, "rouge1_precision": 0.37391944585631076, "rouge1_precision_stderr": 0.0019127935246138258, "rouge1_recall": 0.5276735152486758, "rouge1_recall_stderr": 0.0028083305880520666, "rouge2_fmeasure": 0.20250984831545202, "rouge2_fmeasure_stderr": 0.0016721804731251128, "rouge2_precision": 0.17745705101705952, "rouge2_precision_stderr": 0.0015612598687988076, "rouge2_recall": 0.25548983218564925, "rouge2_recall_stderr": 0.0023268496099242975, "rougeL_fmeasure": 0.3085528535031243, "rougeL_fmeasure_stderr": 0.0015558243556986532, "rougeL_precision": 0.2708392675295398, "rougeL_precision_stderr": 0.0015293358001324147, "rougeL_recall": 0.3866756916075708, "rougeL_recall_stderr": 0.0024884834616842755, "rougeLsum_fmeasure": 0.35353842822798887, "rougeLsum_fmeasure_stderr": 0.001886743880999753, "rougeLsum_precision": 0.31184277536230626, "rougeLsum_precision_stderr": 0.0018957620411070345, "rougeLsum_recall": 0.43875485442059636, "rougeLsum_recall_stderr": 0.002710851391374029}}, "3": {"generate_text_restaurant": {"bleu": 10.189563951094414, "bleu_stderr": 0.09427499367940084, "rouge1_fmeasure": 0.42389949583381237, "rouge1_fmeasure_stderr": 0.0018605488068051588, "rouge1_precision": 0.36817190833860697, "rouge1_precision_stderr": 0.0019656678844549645, "rouge1_recall": 0.5363504766997446, "rouge1_recall_stderr": 0.0027352574830906383, "rouge2_fmeasure": 0.20474913748031123, "rouge2_fmeasure_stderr": 0.0016798602044551796, "rouge2_precision": 0.17677690202821514, "rouge2_precision_stderr": 0.0015500577175042321, "rouge2_recall": 0.2630023508064778, "rouge2_recall_stderr": 0.0023343418511276868, "rougeL_fmeasure": 0.3118160024380036, "rougeL_fmeasure_stderr": 0.0015347599766876738, "rougeL_precision": 0.26924224328922214, "rougeL_precision_stderr": 0.0014968175338731645, "rougeL_recall": 0.3991179057569062, "rougeL_recall_stderr": 0.002484404009518406, "rougeLsum_fmeasure": 0.3544946381824597, "rougeLsum_fmeasure_stderr": 0.0019027110628313127, "rougeLsum_precision": 0.30800886875805217, "rougeLsum_precision_stderr": 0.0019097659829946047, "rougeLsum_recall": 0.4483937574374488, "rougeLsum_recall_stderr": 0.0026777107579305293}}, "4": {"generate_text_restaurant": {"bleu": 10.087905126304989, "bleu_stderr": 0.12083096625574397, "rouge1_fmeasure": 0.4212315759756044, "rouge1_fmeasure_stderr": 0.0018415320213085158, "rouge1_precision": 0.363770828222443, "rouge1_precision_stderr": 0.0020036630555845163, "rouge1_recall": 0.5387177659214019, "rouge1_recall_stderr": 0.002646963846141895, "rouge2_fmeasure": 0.20471927374375903, "rouge2_fmeasure_stderr": 0.0016719159604382972, "rouge2_precision": 0.17597560551882171, "rouge2_precision_stderr": 0.001571481262205388, "rouge2_recall": 0.2657691623220242, "rouge2_recall_stderr": 0.002333604850349637, "rougeL_fmeasure": 0.3130529200481379, "rougeL_fmeasure_stderr": 0.0015386652999892186, "rougeL_precision": 0.26877802100515913, "rougeL_precision_stderr": 0.0015442331987074057, "rougeL_recall": 0.4052364760809525, "rougeL_recall_stderr": 0.0024774430086498, "rougeLsum_fmeasure": 0.3523313968378458, "rougeLsum_fmeasure_stderr": 0.001878784755073219, "rougeLsum_precision": 0.3043335333487051, "rougeLsum_precision_stderr": 0.0019221279858750424, "rougeLsum_recall": 0.45057659617077206, "rougeLsum_recall_stderr": 0.0026276807170486868}}, "5": {"generate_text_restaurant": {"bleu": 9.819773449865215, "bleu_stderr": 0.11548211534367327, "rouge1_fmeasure": 0.4171512639820159, "rouge1_fmeasure_stderr": 0.0018457472467404608, "rouge1_precision": 0.35770393515726967, "rouge1_precision_stderr": 0.0020171246319611895, "rouge1_recall": 0.539688571960094, "rouge1_recall_stderr": 0.002611808763994368, "rouge2_fmeasure": 0.20263412608550646, "rouge2_fmeasure_stderr": 0.0016590004976459545, "rouge2_precision": 0.1728779412674664, "rouge2_precision_stderr": 0.001552564907957209, "rouge2_recall": 0.26604296450461634, "rouge2_recall_stderr": 0.002299997324816336, "rougeL_fmeasure": 0.3113829743853015, "rougeL_fmeasure_stderr": 0.001519582979021018, "rougeL_precision": 0.2650100444015115, "rougeL_precision_stderr": 0.0015203204596296734, "rougeL_recall": 0.4087745798701937, "rougeL_recall_stderr": 0.0024798181425658206, "rougeLsum_fmeasure": 0.34979542583413165, "rougeLsum_fmeasure_stderr": 0.0018887263526221952, "rougeLsum_precision": 0.3001431880229394, "rougeLsum_precision_stderr": 0.0019447092940593606, "rougeLsum_recall": 0.4521649916174878, "rougeLsum_recall_stderr": 0.0025893467916896255}}}, "gem_xsum": {"0": {"article_DOC_summary": {"bleu": 2.660236171533595, "bleu_stderr": 0.13058979906246349, "rouge1_fmeasure": 0.22742139033510708, "rouge1_fmeasure_stderr": 0.0026114290632041296, "rouge1_precision": 0.1640429927941635, "rouge1_precision_stderr": 0.002015041956665472, "rouge1_recall": 0.39341008253163384, "rouge1_recall_stderr": 0.004636047629579328, "rouge2_fmeasure": 0.060906753315850805, "rouge2_fmeasure_stderr": 0.0018640421740763493, "rouge2_precision": 0.043275784885704716, "rouge2_precision_stderr": 0.001336391186147405, "rouge2_recall": 0.10866533118072726, "rouge2_recall_stderr": 0.003402923147178015, "rougeL_fmeasure": 0.17023515816181556, "rougeL_fmeasure_stderr": 0.002061842004493983, "rougeL_precision": 0.12259957209931875, "rougeL_precision_stderr": 0.0015710911079803718, "rougeL_recall": 0.2958746933623946, "rougeL_recall_stderr": 0.0037695130327974375, "rougeLsum_fmeasure": 0.1796488354953124, "rougeLsum_fmeasure_stderr": 0.00228884690406039, "rougeLsum_precision": 0.12928277474166358, "rougeLsum_precision_stderr": 0.0017231366356998507, "rougeLsum_recall": 0.31266179796436216, "rougeLsum_recall_stderr": 0.004192600769757827}}, "1": {"article_DOC_summary": {"bleu": 1.8314489114971673, "bleu_stderr": 0.05409360756715158, "rouge1_fmeasure": 0.19173204586716094, "rouge1_fmeasure_stderr": 0.002639692576988235, "rouge1_precision": 0.13655953349875768, "rouge1_precision_stderr": 0.0019656757175551577, "rouge1_recall": 0.3351266289452704, "rouge1_recall_stderr": 0.0045506786659058425, "rouge2_fmeasure": 0.043509124193048414, "rouge2_fmeasure_stderr": 0.0016166226125424621, "rouge2_precision": 0.030642922658876727, "rouge2_precision_stderr": 0.001142930640307047, "rouge2_recall": 0.07840904303144859, "rouge2_recall_stderr": 0.003007597927500564, "rougeL_fmeasure": 0.1479712469429257, "rougeL_fmeasure_stderr": 0.002021808544636796, "rougeL_precision": 0.10515008122500365, "rougeL_precision_stderr": 0.0014878667949867396, "rougeL_recall": 0.2603291047174206, "rougeL_recall_stderr": 0.0036304258303670577, "rougeLsum_fmeasure": 0.15295586712265904, "rougeLsum_fmeasure_stderr": 0.0022389650188625095, "rougeLsum_precision": 0.10864088340556836, "rougeLsum_precision_stderr": 0.0016392672849460208, "rougeLsum_recall": 0.26926885885160073, "rougeLsum_recall_stderr": 0.004010439316574938}}, "2": {"article_DOC_summary": {"bleu": 2.3328395887156255, "bleu_stderr": 0.10816864533274577, "rouge1_fmeasure": 0.20690402045254036, "rouge1_fmeasure_stderr": 0.0027232531224059726, "rouge1_precision": 0.14713632905683816, "rouge1_precision_stderr": 0.0020215279085607075, "rouge1_recall": 0.3625697155906082, "rouge1_recall_stderr": 0.004676136272316295, "rouge2_fmeasure": 0.05427974421404337, "rouge2_fmeasure_stderr": 0.0017696178332732388, "rouge2_precision": 0.03817870519938818, "rouge2_precision_stderr": 0.0012523560434755418, "rouge2_recall": 0.09803539445968558, "rouge2_recall_stderr": 0.003268351761516068, "rougeL_fmeasure": 0.16250269839239403, "rougeL_fmeasure_stderr": 0.0021208807462068965, "rougeL_precision": 0.11527249431509622, "rougeL_precision_stderr": 0.0015525999339183435, "rougeL_recall": 0.28699007838315493, "rougeL_recall_stderr": 0.003846678173723021, "rougeLsum_fmeasure": 0.16643954154187726, "rougeLsum_fmeasure_stderr": 0.0023327546790871127, "rougeLsum_precision": 0.11807937715144022, "rougeLsum_precision_stderr": 0.0017041758270634855, "rougeLsum_recall": 0.2936525618807245, "rougeLsum_recall_stderr": 0.004161272394841371}}, "3": {"article_DOC_summary": {"bleu": 2.4415835212159744, "bleu_stderr": 0.09205861798425756, "rouge1_fmeasure": 0.20790416673134823, "rouge1_fmeasure_stderr": 0.0027904145464295793, "rouge1_precision": 0.15050477129545162, "rouge1_precision_stderr": 0.0021650717494144725, "rouge1_recall": 0.35833402440286477, "rouge1_recall_stderr": 0.004875928275119348, "rouge2_fmeasure": 0.05578255582904122, "rouge2_fmeasure_stderr": 0.0017532403099110591, "rouge2_precision": 0.03967555502420575, "rouge2_precision_stderr": 0.001257612569171145, "rouge2_recall": 0.0995195510617509, "rouge2_recall_stderr": 0.0032409089175577817, "rougeL_fmeasure": 0.1588561646225248, "rougeL_fmeasure_stderr": 0.00218993426182156, "rougeL_precision": 0.11465132801092887, "rougeL_precision_stderr": 0.001666726965584784, "rougeL_recall": 0.27592762804713344, "rougeL_recall_stderr": 0.004014306258609167, "rougeLsum_fmeasure": 0.1652197759476937, "rougeLsum_fmeasure_stderr": 0.002376223870136714, "rougeLsum_precision": 0.11933090671402025, "rougeLsum_precision_stderr": 0.0018043535233345025, "rougeLsum_recall": 0.28657490925873824, "rougeLsum_recall_stderr": 0.004297538545009866}}, "4": {"article_DOC_summary": {"bleu": 1.0886930800027617, "bleu_stderr": 0.13685163756146332, "rouge1_fmeasure": 0.05651233636898341, "rouge1_fmeasure_stderr": 0.0030905378199610973, "rouge1_precision": 0.04479833541552641, "rouge1_precision_stderr": 0.0024920338028095244, "rouge1_recall": 0.09115873549013587, "rouge1_recall_stderr": 0.0051576903382473185, "rouge2_fmeasure": 0.014022544687027934, "rouge2_fmeasure_stderr": 0.0011421600358457382, "rouge2_precision": 0.010549200347804146, "rouge2_precision_stderr": 0.0008786327894641382, "rouge2_recall": 0.024034279053592206, "rouge2_recall_stderr": 0.0020028495235980617, "rougeL_fmeasure": 0.04286140894694921, "rougeL_fmeasure_stderr": 0.002370447391151435, "rougeL_precision": 0.03426844067651488, "rougeL_precision_stderr": 0.0019596209525071014, "rougeL_recall": 0.06925411151199752, "rougeL_recall_stderr": 0.003988959935482703, "rougeLsum_fmeasure": 0.045863687869416005, "rougeLsum_fmeasure_stderr": 0.0025272572767658435, "rougeLsum_precision": 0.036540645050964785, "rougeLsum_precision_stderr": 0.0020678075006755215, "rougeLsum_recall": 0.07413354565538481, "rougeLsum_recall_stderr": 0.004252794848785553}}, "5": {"article_DOC_summary": {"bleu": 2.170644306962683e-19, "bleu_stderr": 5.499005165072242e-15, "rouge1_fmeasure": 0.0030531767218957887, "rouge1_fmeasure_stderr": 0.0008235812485186412, "rouge1_precision": 0.0027738518451789936, "rouge1_precision_stderr": 0.0007772852422880741, "rouge1_recall": 0.004449774503151586, "rouge1_recall_stderr": 0.0013000230402188415, "rouge2_fmeasure": 0.000461932013569787, "rouge2_fmeasure_stderr": 0.00019747062019636368, "rouge2_precision": 0.0004318387593770127, "rouge2_precision_stderr": 0.0002096018140886139, "rouge2_recall": 0.0006493854199619724, "rouge2_recall_stderr": 0.0002769463291779765, "rougeL_fmeasure": 0.00206141715660179, "rougeL_fmeasure_stderr": 0.0005827251790517291, "rougeL_precision": 0.0018680723098669894, "rougeL_precision_stderr": 0.0005358076043197855, "rougeL_recall": 0.0029818697516115103, "rougeL_recall_stderr": 0.0008929801630497813, "rougeLsum_fmeasure": 0.002323102977881885, "rougeLsum_fmeasure_stderr": 0.0006354398848530671, "rougeLsum_precision": 0.002156304889205613, "rougeLsum_precision_stderr": 0.0006383957765946712, "rougeLsum_recall": 0.003337441465976244, "rougeLsum_recall_stderr": 0.0009699711366361862}}}}