File size: 28,013 Bytes
5f1fb3a |
1 |
{"GEM/web_nlg_en": {"0": {"PALM_prompt": {"bleu": 0.332418164076265, "bleu_stderr": 0.03696058294042095, "rouge1_fmeasure": 0.1095978356180801, "rouge1_fmeasure_stderr": 0.0019564248982681257, "rouge1_precision": 0.07190940889482068, "rouge1_precision_stderr": 0.001455025906136879, "rouge1_recall": 0.301390732870209, "rouge1_recall_stderr": 0.004402601720305443, "rouge2_fmeasure": 0.05171405582224464, "rouge2_fmeasure_stderr": 0.0012435373590367134, "rouge2_precision": 0.03366735249156069, "rouge2_precision_stderr": 0.0008858326464608315, "rouge2_recall": 0.1465983694875745, "rouge2_recall_stderr": 0.003074755705857914, "rougeL_fmeasure": 0.10587809310127003, "rougeL_fmeasure_stderr": 0.001838006623068389, "rougeL_precision": 0.06928463832111945, "rougeL_precision_stderr": 0.001354402286433117, "rougeL_recall": 0.29343421778124684, "rougeL_recall_stderr": 0.004302109252038838, "rougeLsum_fmeasure": 0.10516308015267403, "rougeLsum_fmeasure_stderr": 0.0018547700987810625, "rougeLsum_precision": 0.06900976089065335, "rougeLsum_precision_stderr": 0.0013821359592628988, "rougeLsum_recall": 0.28936351476019084, "rougeLsum_recall_stderr": 0.004198483169030062}}, "1": {"PALM_prompt": {"bleu": 0.4396246502267527, "bleu_stderr": 0.03794273972678262, "rouge1_fmeasure": 0.11510858435008614, "rouge1_fmeasure_stderr": 0.001829941745508391, "rouge1_precision": 0.0739181124020759, "rouge1_precision_stderr": 0.0013418349953620108, "rouge1_recall": 0.35963891837485074, "rouge1_recall_stderr": 0.004935335446807934, "rouge2_fmeasure": 0.054655222423642985, "rouge2_fmeasure_stderr": 0.0011574253411672022, "rouge2_precision": 0.034943394233011765, "rouge2_precision_stderr": 0.0008228677576697449, "rouge2_recall": 0.17989319170126253, "rouge2_recall_stderr": 0.003650522605621509, "rougeL_fmeasure": 0.10946339983990763, "rougeL_fmeasure_stderr": 0.0016790473876574434, "rougeL_precision": 0.07022432800426698, "rougeL_precision_stderr": 0.0012223544306487109, "rougeL_recall": 0.3398876745824502, "rougeL_recall_stderr": 0.004493731176695288, "rougeLsum_fmeasure": 0.11046019470928523, "rougeLsum_fmeasure_stderr": 0.00173280705768612, "rougeLsum_precision": 0.07093990858477271, "rougeLsum_precision_stderr": 0.0012725781012108558, "rougeLsum_recall": 0.34408662950943764, "rougeLsum_recall_stderr": 0.004619974377582772}}, "2": {"PALM_prompt": {"bleu": 0.47929145559638225, "bleu_stderr": 0.013932123962412855, "rouge1_fmeasure": 0.11266051583386952, "rouge1_fmeasure_stderr": 0.0016388264831012904, "rouge1_precision": 0.07137936932112236, "rouge1_precision_stderr": 0.0011784730418670042, "rouge1_recall": 0.3699801668532645, "rouge1_recall_stderr": 0.004983372147117968, "rouge2_fmeasure": 0.05259910261699664, "rouge2_fmeasure_stderr": 0.0010491604565333935, "rouge2_precision": 0.03309847277281182, "rouge2_precision_stderr": 0.0007256900997219835, "rouge2_recall": 0.18647973916218474, "rouge2_recall_stderr": 0.0037435312434141257, "rougeL_fmeasure": 0.10644239169147508, "rougeL_fmeasure_stderr": 0.0015316327496444973, "rougeL_precision": 0.06751660699477897, "rougeL_precision_stderr": 0.0011071302423418996, "rougeL_recall": 0.3460463516284548, "rougeL_recall_stderr": 0.0044526867532594374, "rougeLsum_fmeasure": 0.10811495254365688, "rougeLsum_fmeasure_stderr": 0.0015702834219670347, "rougeLsum_precision": 0.06854436178289768, "rougeLsum_precision_stderr": 0.001132855557018181, "rougeLsum_recall": 0.35357532668740393, "rougeLsum_recall_stderr": 0.004680159458874175}}, "3": {"PALM_prompt": {"bleu": 0.5254091236383978, "bleu_stderr": 0.0272707184705863, "rouge1_fmeasure": 0.1137800918874328, "rouge1_fmeasure_stderr": 0.0015623641314802495, "rouge1_precision": 0.07190916345114307, "rouge1_precision_stderr": 0.0011342056239523493, "rouge1_recall": 0.3796797864121142, "rouge1_recall_stderr": 0.0049211015597907335, "rouge2_fmeasure": 0.053524415343767374, "rouge2_fmeasure_stderr": 0.0010377150477586447, "rouge2_precision": 0.03359440011812607, "rouge2_precision_stderr": 0.000717267417649812, "rouge2_recall": 0.19204855728023304, "rouge2_recall_stderr": 0.003700810575997827, "rougeL_fmeasure": 0.10739509357535582, "rougeL_fmeasure_stderr": 0.0014688768045950926, "rougeL_precision": 0.06797419059481667, "rougeL_precision_stderr": 0.0010722591518842702, "rougeL_recall": 0.3549241769775831, "rougeL_recall_stderr": 0.0044079173685938056, "rougeLsum_fmeasure": 0.10880190459995145, "rougeLsum_fmeasure_stderr": 0.0014957717696141243, "rougeLsum_precision": 0.06883524450761919, "rougeLsum_precision_stderr": 0.0010904375559758742, "rougeLsum_recall": 0.36157753989860286, "rougeLsum_recall_stderr": 0.00458238890896547}}, "4": {"PALM_prompt": {"bleu": 0.5896016424303352, "bleu_stderr": 0.04348163762184696, "rouge1_fmeasure": 0.1152098647187527, "rouge1_fmeasure_stderr": 0.0015875085813414037, "rouge1_precision": 0.07280177888449052, "rouge1_precision_stderr": 0.001167476102151522, "rouge1_recall": 0.38454519285609656, "rouge1_recall_stderr": 0.004901871012575138, "rouge2_fmeasure": 0.05404038379134397, "rouge2_fmeasure_stderr": 0.001047558823714542, "rouge2_precision": 0.03384968429202272, "rouge2_precision_stderr": 0.0007316072980959663, "rouge2_recall": 0.19690825980706886, "rouge2_recall_stderr": 0.003822922236606215, "rougeL_fmeasure": 0.10796621981670128, "rougeL_fmeasure_stderr": 0.0014415066070786182, "rougeL_precision": 0.06829385238072445, "rougeL_precision_stderr": 0.0010696413261370567, "rougeL_recall": 0.3593088405468019, "rougeL_recall_stderr": 0.004380347845482903, "rougeLsum_fmeasure": 0.11042781164659983, "rougeLsum_fmeasure_stderr": 0.0015072405756468101, "rougeLsum_precision": 0.06983214496239268, "rougeLsum_precision_stderr": 0.0011145751003995281, "rougeLsum_recall": 0.3684081584518333, "rougeLsum_recall_stderr": 0.0046181910041404525}}, "5": {"PALM_prompt": {"bleu": 0.5579849887702564, "bleu_stderr": 0.02566777731605262, "rouge1_fmeasure": 0.11496348733004745, "rouge1_fmeasure_stderr": 0.0014986246232008803, "rouge1_precision": 0.0722244811765284, "rouge1_precision_stderr": 0.0010883491004439172, "rouge1_recall": 0.39225252025509727, "rouge1_recall_stderr": 0.00500239708089686, "rouge2_fmeasure": 0.05406065553629826, "rouge2_fmeasure_stderr": 0.001009602112409382, "rouge2_precision": 0.033751098133716816, "rouge2_precision_stderr": 0.0007017585569903578, "rouge2_recall": 0.20045030871386427, "rouge2_recall_stderr": 0.0038136378057587856, "rougeL_fmeasure": 0.10724709950776415, "rougeL_fmeasure_stderr": 0.001385394861578905, "rougeL_precision": 0.06750750522157839, "rougeL_precision_stderr": 0.0010132953538675234, "rougeL_recall": 0.3629468989772955, "rougeL_recall_stderr": 0.004411901125085533, "rougeLsum_fmeasure": 0.10981073422881693, "rougeLsum_fmeasure_stderr": 0.0014263114503938255, "rougeLsum_precision": 0.06905880474217613, "rougeLsum_precision_stderr": 0.001041674323116577, "rougeLsum_recall": 0.37377123464513246, "rougeLsum_recall_stderr": 0.004666454165917922}}}, "GEM/wiki_lingua_en": {"0": {"tldr_en": {"bleu": 1.831310525161332, "bleu_stderr": 0.08457373503805206, "rouge1_fmeasure": 0.1862365342289606, "rouge1_fmeasure_stderr": 0.0019333176047893425, "rouge1_precision": 0.15972274079475446, "rouge1_precision_stderr": 0.0019865559238896858, "rouge1_recall": 0.2700593421670508, "rouge1_recall_stderr": 0.0027737951668886907, "rouge2_fmeasure": 0.04032054400755849, "rouge2_fmeasure_stderr": 0.0009252920084472916, "rouge2_precision": 0.034556806570887444, "rouge2_precision_stderr": 0.0008425423478960415, "rouge2_recall": 0.05978905462791134, "rouge2_recall_stderr": 0.0014708640693064097, "rougeL_fmeasure": 0.14210549237770434, "rougeL_fmeasure_stderr": 0.001352102962568602, "rougeL_precision": 0.12038536558218806, "rougeL_precision_stderr": 0.0013551069603724947, "rougeL_recall": 0.21115022540563333, "rougeL_recall_stderr": 0.0022023323083645396, "rougeLsum_fmeasure": 0.17172494748072423, "rougeLsum_fmeasure_stderr": 0.0017652741846676486, "rougeLsum_precision": 0.1471563634835902, "rougeLsum_precision_stderr": 0.001816380499537014, "rougeLsum_recall": 0.24955829066428167, "rougeLsum_recall_stderr": 0.0025549018069577077}}, "1": {"tldr_en": {"bleu": 3.1946229115600104, "bleu_stderr": 0.0902528894135031, "rouge1_fmeasure": 0.22713731519119962, "rouge1_fmeasure_stderr": 0.0020303856541629157, "rouge1_precision": 0.20084840762025002, "rouge1_precision_stderr": 0.002375570727890994, "rouge1_recall": 0.3279331840452314, "rouge1_recall_stderr": 0.0029166900556576378, "rouge2_fmeasure": 0.05813673529140247, "rouge2_fmeasure_stderr": 0.0010858552857269058, "rouge2_precision": 0.05192805744789268, "rouge2_precision_stderr": 0.0011904825748754472, "rouge2_recall": 0.08693391944333162, "rouge2_recall_stderr": 0.0017928197332860247, "rougeL_fmeasure": 0.16290527667884375, "rougeL_fmeasure_stderr": 0.0013800590148163698, "rougeL_precision": 0.1432641278979817, "rougeL_precision_stderr": 0.0016838668333439412, "rougeL_recall": 0.24141036590043435, "rougeL_recall_stderr": 0.002321080600691811, "rougeLsum_fmeasure": 0.21344783101010534, "rougeLsum_fmeasure_stderr": 0.0019004009451698382, "rougeLsum_precision": 0.1885894929526097, "rougeLsum_precision_stderr": 0.0022300914877422806, "rougeLsum_recall": 0.3090983774717522, "rougeLsum_recall_stderr": 0.0027802990042071363}}, "2": {"tldr_en": {"bleu": 4.089342922787345, "bleu_stderr": 0.09294377977855839, "rouge1_fmeasure": 0.24178148334371152, "rouge1_fmeasure_stderr": 0.002084865329415859, "rouge1_precision": 0.2656984608711839, "rouge1_precision_stderr": 0.003475974826636605, "rouge1_recall": 0.3139253119933751, "rouge1_recall_stderr": 0.003012955655711283, "rouge2_fmeasure": 0.06887382606726644, "rouge2_fmeasure_stderr": 0.0012807228279060876, "rouge2_precision": 0.08136466928288727, "rouge2_precision_stderr": 0.0021586497346161937, "rouge2_recall": 0.09042739130647694, "rouge2_recall_stderr": 0.0018404609298964, "rougeL_fmeasure": 0.17903750582234018, "rougeL_fmeasure_stderr": 0.0015877517832273015, "rougeL_precision": 0.20056631932614633, "rougeL_precision_stderr": 0.0029240196408032576, "rougeL_recall": 0.23442772665220632, "rougeL_recall_stderr": 0.002412584818753376, "rougeLsum_fmeasure": 0.22871976277916323, "rougeLsum_fmeasure_stderr": 0.0019660579351207536, "rougeLsum_precision": 0.2521499144307301, "rougeLsum_precision_stderr": 0.0033481985589333117, "rougeLsum_recall": 0.29706441266630634, "rougeLsum_recall_stderr": 0.0028655519018383232}}, "3": {"tldr_en": {"bleu": 4.072610754323664, "bleu_stderr": 0.07525164017980863, "rouge1_fmeasure": 0.19590336767483915, "rouge1_fmeasure_stderr": 0.002603449114946719, "rouge1_precision": 0.25558962697073145, "rouge1_precision_stderr": 0.004282279704468573, "rouge1_recall": 0.23153110943427863, "rouge1_recall_stderr": 0.003438107905334785, "rouge2_fmeasure": 0.05767822682063389, "rouge2_fmeasure_stderr": 0.0013980794793852763, "rouge2_precision": 0.08146818659563723, "rouge2_precision_stderr": 0.002448660534108266, "rouge2_recall": 0.06743455850825143, "rouge2_recall_stderr": 0.0017452087926378838, "rougeL_fmeasure": 0.14912723506935083, "rougeL_fmeasure_stderr": 0.0020363514995009485, "rougeL_precision": 0.19917268042172423, "rougeL_precision_stderr": 0.00359110440185509, "rougeL_recall": 0.17626539265723254, "rougeL_recall_stderr": 0.0027059496141968596, "rougeLsum_fmeasure": 0.18563647374529954, "rougeLsum_fmeasure_stderr": 0.0024816986882333276, "rougeLsum_precision": 0.24272073863797083, "rougeLsum_precision_stderr": 0.004109190949161484, "rougeLsum_recall": 0.2194427111114507, "rougeLsum_recall_stderr": 0.003281194179793178}}, "4": {"tldr_en": {"bleu": 0.30672054851921343, "bleu_stderr": 0.027801502217640873, "rouge1_fmeasure": 0.060859438120474105, "rouge1_fmeasure_stderr": 0.002186962487867776, "rouge1_precision": 0.08272085590013521, "rouge1_precision_stderr": 0.003328470018227569, "rouge1_recall": 0.073607896755553, "rouge1_recall_stderr": 0.002786595724689709, "rouge2_fmeasure": 0.018259934336381307, "rouge2_fmeasure_stderr": 0.0009369665663167178, "rouge2_precision": 0.027384557827759736, "rouge2_precision_stderr": 0.0017208392028580295, "rouge2_recall": 0.021828735652406926, "rouge2_recall_stderr": 0.0011755690210094216, "rougeL_fmeasure": 0.047327721198656594, "rougeL_fmeasure_stderr": 0.001720788977327356, "rougeL_precision": 0.0663593638177798, "rougeL_precision_stderr": 0.002792690105843212, "rougeL_recall": 0.056938933254415285, "rougeL_recall_stderr": 0.0021770204347710985, "rougeLsum_fmeasure": 0.05738648078691023, "rougeLsum_fmeasure_stderr": 0.0020702191744425805, "rougeLsum_precision": 0.0784447476522085, "rougeLsum_precision_stderr": 0.003187161977557443, "rougeLsum_recall": 0.06936769106400163, "rougeLsum_recall_stderr": 0.0026401376140555047}}, "5": {"tldr_en": {"bleu": 1.0767109875104664e-10, "bleu_stderr": 2.7041266760972117e-09, "rouge1_fmeasure": 0.009545168655738663, "rouge1_fmeasure_stderr": 0.0009833205973525279, "rouge1_precision": 0.013957270253644866, "rouge1_precision_stderr": 0.0015489152693527737, "rouge1_recall": 0.010948829734039874, "rouge1_recall_stderr": 0.001189429950745709, "rouge2_fmeasure": 0.003194781805527316, "rouge2_fmeasure_stderr": 0.00046191164979125494, "rouge2_precision": 0.005346599799374829, "rouge2_precision_stderr": 0.000922536579868288, "rouge2_recall": 0.003447960863177172, "rouge2_recall_stderr": 0.0005097345293134105, "rougeL_fmeasure": 0.00771353363185855, "rougeL_fmeasure_stderr": 0.0008078330599179273, "rougeL_precision": 0.011558443617862643, "rougeL_precision_stderr": 0.0013357028661274022, "rougeL_recall": 0.00878713432773727, "rougeL_recall_stderr": 0.0009510460692818358, "rougeLsum_fmeasure": 0.009095278752494966, "rougeLsum_fmeasure_stderr": 0.0009411593635337467, "rougeLsum_precision": 0.013380501718320581, "rougeLsum_precision_stderr": 0.0014992977277420356, "rougeLsum_recall": 0.010421509428125204, "rougeLsum_recall_stderr": 0.0011325542079141924}}}, "e2e_nlg_cleaned": {"0": {"generate_text_restaurant": {"bleu": 2.1637748729872377, "bleu_stderr": 0.04708061810035152, "rouge1_fmeasure": 0.1857729182904806, "rouge1_fmeasure_stderr": 0.0015977758615005752, "rouge1_precision": 0.17571114021612258, "rouge1_precision_stderr": 0.00234001350004936, "rouge1_recall": 0.2403810966028036, "rouge1_recall_stderr": 0.001917930986446359, "rouge2_fmeasure": 0.038846854218182576, "rouge2_fmeasure_stderr": 0.0008031687884467253, "rouge2_precision": 0.03853560508356721, "rouge2_precision_stderr": 0.0008749576393956302, "rouge2_recall": 0.04848364378645718, "rouge2_recall_stderr": 0.001080661761475741, "rougeL_fmeasure": 0.14517349755186024, "rougeL_fmeasure_stderr": 0.00122530969799679, "rougeL_precision": 0.13673433720639006, "rougeL_precision_stderr": 0.0018383470645185228, "rougeL_recall": 0.19020915483344014, "rougeL_recall_stderr": 0.0015344656813421698, "rougeLsum_fmeasure": 0.17477219266422644, "rougeLsum_fmeasure_stderr": 0.0015733449442962115, "rougeLsum_precision": 0.16441038855158038, "rougeLsum_precision_stderr": 0.00216945133305093, "rougeLsum_recall": 0.22661830578107306, "rougeLsum_recall_stderr": 0.0019584009970905515}}, "1": {"generate_text_restaurant": {"bleu": 12.699076129183206, "bleu_stderr": 0.10399531996709636, "rouge1_fmeasure": 0.46200013120745637, "rouge1_fmeasure_stderr": 0.0023848096470577393, "rouge1_precision": 0.5458616254773436, "rouge1_precision_stderr": 0.0034897518863656377, "rouge1_recall": 0.44911695528747547, "rouge1_recall_stderr": 0.003049432231004983, "rouge2_fmeasure": 0.21840214637971003, "rouge2_fmeasure_stderr": 0.0020520500269639213, "rouge2_precision": 0.2625771628656913, "rouge2_precision_stderr": 0.002777565484439754, "rouge2_recall": 0.21189977549122158, "rouge2_recall_stderr": 0.0022330452298268692, "rougeL_fmeasure": 0.3377881512152975, "rougeL_fmeasure_stderr": 0.0020544234738392457, "rougeL_precision": 0.4020226840139383, "rougeL_precision_stderr": 0.003079117739342717, "rougeL_recall": 0.3281876590745158, "rougeL_recall_stderr": 0.002505390281354571, "rougeLsum_fmeasure": 0.3799905020241611, "rougeLsum_fmeasure_stderr": 0.0023491152850802477, "rougeLsum_precision": 0.45027802951118134, "rougeLsum_precision_stderr": 0.0033307854923309735, "rougeLsum_recall": 0.3687964450646062, "rougeLsum_recall_stderr": 0.002811107425715743}}, "2": {"generate_text_restaurant": {"bleu": 15.349320073567956, "bleu_stderr": 0.20065362471122622, "rouge1_fmeasure": 0.5062690903947293, "rouge1_fmeasure_stderr": 0.0022184418781909503, "rouge1_precision": 0.5641138089260663, "rouge1_precision_stderr": 0.003122162389799746, "rouge1_recall": 0.4993081674056431, "rouge1_recall_stderr": 0.0029190169239720776, "rouge2_fmeasure": 0.25323692889972166, "rouge2_fmeasure_stderr": 0.002116475114261491, "rouge2_precision": 0.28480233937098404, "rouge2_precision_stderr": 0.0026558013765171293, "rouge2_recall": 0.2505303415532217, "rouge2_recall_stderr": 0.002363227578711657, "rougeL_fmeasure": 0.3699075196394537, "rougeL_fmeasure_stderr": 0.002038510745722095, "rougeL_precision": 0.4134223803505085, "rougeL_precision_stderr": 0.0027884299786810726, "rougeL_recall": 0.364967373581058, "rougeL_recall_stderr": 0.0025050008227674118, "rougeLsum_fmeasure": 0.42153114614795945, "rougeLsum_fmeasure_stderr": 0.0022965855563879564, "rougeLsum_precision": 0.4701745407770204, "rougeLsum_precision_stderr": 0.0030588655833951616, "rougeLsum_recall": 0.415665042099645, "rougeLsum_recall_stderr": 0.0027902197560574714}}, "3": {"generate_text_restaurant": {"bleu": 14.321380888062812, "bleu_stderr": 0.13332556788591748, "rouge1_fmeasure": 0.4942167403659075, "rouge1_fmeasure_stderr": 0.0021128256597481797, "rouge1_precision": 0.5163006609255177, "rouge1_precision_stderr": 0.002848705467042193, "rouge1_recall": 0.5103725325478746, "rouge1_recall_stderr": 0.002812023353115975, "rouge2_fmeasure": 0.24523127893147686, "rouge2_fmeasure_stderr": 0.0020480988327082963, "rouge2_precision": 0.2568516782752942, "rouge2_precision_stderr": 0.0023590125409771855, "rouge2_recall": 0.2546224310607835, "rouge2_recall_stderr": 0.0023818244395298806, "rougeL_fmeasure": 0.36209783653768146, "rougeL_fmeasure_stderr": 0.001959264414079404, "rougeL_precision": 0.3787196100484137, "rougeL_precision_stderr": 0.0024985656409790852, "rougeL_recall": 0.3741605928354789, "rougeL_recall_stderr": 0.002454556248255368, "rougeLsum_fmeasure": 0.41228039547049994, "rougeLsum_fmeasure_stderr": 0.002190141578787795, "rougeLsum_precision": 0.4306732810674897, "rougeLsum_precision_stderr": 0.002754882401260447, "rougeLsum_recall": 0.42590630743564917, "rougeLsum_recall_stderr": 0.0027265425997138994}}, "4": {"generate_text_restaurant": {"bleu": 13.722841928196777, "bleu_stderr": 0.13804846172826613, "rouge1_fmeasure": 0.48393429045188835, "rouge1_fmeasure_stderr": 0.0019859645893939115, "rouge1_precision": 0.48828386592969264, "rouge1_precision_stderr": 0.0024858404633992743, "rouge1_recall": 0.5114305264974095, "rouge1_recall_stderr": 0.002697661923152199, "rouge2_fmeasure": 0.23840855028747443, "rouge2_fmeasure_stderr": 0.0019573193912396634, "rouge2_precision": 0.24059108499141613, "rouge2_precision_stderr": 0.00210840059224509, "rouge2_recall": 0.25365084544842664, "rouge2_recall_stderr": 0.0023384488190548417, "rougeL_fmeasure": 0.3537873295650889, "rougeL_fmeasure_stderr": 0.0018387088951343877, "rougeL_precision": 0.3566021510402825, "rougeL_precision_stderr": 0.002136311576118472, "rougeL_recall": 0.3747086531915837, "rougeL_recall_stderr": 0.0023926470384127776, "rougeLsum_fmeasure": 0.4043059323351792, "rougeLsum_fmeasure_stderr": 0.002080752243862837, "rougeLsum_precision": 0.4075869423080161, "rougeLsum_precision_stderr": 0.0024174778601222056, "rougeLsum_recall": 0.4276935666531386, "rougeLsum_recall_stderr": 0.002665628883634715}}, "5": {"generate_text_restaurant": {"bleu": 13.372484418259432, "bleu_stderr": 0.12631428400851766, "rouge1_fmeasure": 0.47859053217432174, "rouge1_fmeasure_stderr": 0.0019398187941902603, "rouge1_precision": 0.47557867752442456, "rouge1_precision_stderr": 0.0023360428027170664, "rouge1_recall": 0.5107946193055894, "rouge1_recall_stderr": 0.002625085316285608, "rouge2_fmeasure": 0.23444687287756075, "rouge2_fmeasure_stderr": 0.001962765988186735, "rouge2_precision": 0.23277405462932813, "rouge2_precision_stderr": 0.00205201253568292, "rouge2_recall": 0.2519154898433275, "rouge2_recall_stderr": 0.0023288239477406566, "rougeL_fmeasure": 0.35043527019394044, "rougeL_fmeasure_stderr": 0.0018309395599414636, "rougeL_precision": 0.3476553000546008, "rougeL_precision_stderr": 0.0020361706787158022, "rougeL_recall": 0.3751201703103127, "rougeL_recall_stderr": 0.002384327433554856, "rougeLsum_fmeasure": 0.4022665348493678, "rougeLsum_fmeasure_stderr": 0.002066528906487744, "rougeLsum_precision": 0.39968395508657584, "rougeLsum_precision_stderr": 0.0023326315704367095, "rougeLsum_recall": 0.42940604077002287, "rougeLsum_recall_stderr": 0.002605951608709431}}}, "gem_xsum": {"0": {"article_DOC_summary": {"bleu": 2.381704327009844, "bleu_stderr": 0.11413286241675519, "rouge1_fmeasure": 0.2252785173179299, "rouge1_fmeasure_stderr": 0.0025302839963541515, "rouge1_precision": 0.16652504564117318, "rouge1_precision_stderr": 0.0020480225617605856, "rouge1_recall": 0.37848923564363685, "rouge1_recall_stderr": 0.0045711110875955915, "rouge2_fmeasure": 0.05560640356600142, "rouge2_fmeasure_stderr": 0.0017257721593849657, "rouge2_precision": 0.04023090834156273, "rouge2_precision_stderr": 0.0012912806060900344, "rouge2_recall": 0.09751455692123925, "rouge2_recall_stderr": 0.003144590481436754, "rougeL_fmeasure": 0.1678662401695973, "rougeL_fmeasure_stderr": 0.0019429705177302374, "rougeL_precision": 0.12391529652302673, "rougeL_precision_stderr": 0.0015698267806295476, "rougeL_recall": 0.28383434867259993, "rougeL_recall_stderr": 0.003658695564054696, "rougeLsum_fmeasure": 0.17781888968117063, "rougeLsum_fmeasure_stderr": 0.0021578317596841075, "rougeLsum_precision": 0.1310543700695647, "rougeLsum_precision_stderr": 0.0017000651189640957, "rougeLsum_recall": 0.30107876434344966, "rougeLsum_recall_stderr": 0.004054884960237835}}, "1": {"article_DOC_summary": {"bleu": 1.9568092253132736, "bleu_stderr": 0.08743638623038145, "rouge1_fmeasure": 0.1938089585188387, "rouge1_fmeasure_stderr": 0.002822597453009016, "rouge1_precision": 0.13823526560660052, "rouge1_precision_stderr": 0.0020944863718590696, "rouge1_recall": 0.33753001607653804, "rouge1_recall_stderr": 0.004807587398146579, "rouge2_fmeasure": 0.04477392420959174, "rouge2_fmeasure_stderr": 0.001637714965321643, "rouge2_precision": 0.03166938333546749, "rouge2_precision_stderr": 0.0011689549810166263, "rouge2_recall": 0.07993218887659431, "rouge2_recall_stderr": 0.0029743255309706987, "rougeL_fmeasure": 0.1491400353009075, "rougeL_fmeasure_stderr": 0.002089252796225244, "rougeL_precision": 0.10613937916799303, "rougeL_precision_stderr": 0.001538610633349276, "rougeL_recall": 0.2616251241654161, "rougeL_recall_stderr": 0.0037053413551593833, "rougeLsum_fmeasure": 0.15494229567861334, "rougeLsum_fmeasure_stderr": 0.002347654380789924, "rougeLsum_precision": 0.11026653419842858, "rougeLsum_precision_stderr": 0.001720420262105802, "rougeLsum_recall": 0.27172748877390046, "rougeLsum_recall_stderr": 0.004162646884513488}}, "2": {"article_DOC_summary": {"bleu": 2.1208498600162966, "bleu_stderr": 0.08489840925537316, "rouge1_fmeasure": 0.20197965634555684, "rouge1_fmeasure_stderr": 0.002690267282815034, "rouge1_precision": 0.14402898776642667, "rouge1_precision_stderr": 0.001998944393289479, "rouge1_recall": 0.351517404045027, "rouge1_recall_stderr": 0.004610583100015181, "rouge2_fmeasure": 0.050742990668066985, "rouge2_fmeasure_stderr": 0.0016773265894277122, "rouge2_precision": 0.035886973035083945, "rouge2_precision_stderr": 0.001190491610976737, "rouge2_recall": 0.09015312700835054, "rouge2_recall_stderr": 0.003061506688050075, "rougeL_fmeasure": 0.15939919631832364, "rougeL_fmeasure_stderr": 0.002118290262084322, "rougeL_precision": 0.11355508618202974, "rougeL_precision_stderr": 0.0015669742839297053, "rougeL_recall": 0.27829233445848645, "rougeL_recall_stderr": 0.0036956919869857914, "rougeLsum_fmeasure": 0.15895119262920798, "rougeLsum_fmeasure_stderr": 0.002273913023033009, "rougeLsum_precision": 0.11304178539172682, "rougeLsum_precision_stderr": 0.0016600760618328486, "rougeLsum_recall": 0.27844833955215303, "rougeLsum_recall_stderr": 0.004022259545774517}}, "3": {"article_DOC_summary": {"bleu": 2.1488883346464993, "bleu_stderr": 0.10061894207225484, "rouge1_fmeasure": 0.19449648740464862, "rouge1_fmeasure_stderr": 0.002859916967955778, "rouge1_precision": 0.14192323740566237, "rouge1_precision_stderr": 0.002270573664293402, "rouge1_recall": 0.3317122838307692, "rouge1_recall_stderr": 0.0048796302898910975, "rouge2_fmeasure": 0.049958285647633605, "rouge2_fmeasure_stderr": 0.0017043147625524138, "rouge2_precision": 0.03602126113927686, "rouge2_precision_stderr": 0.0012539266263007617, "rouge2_recall": 0.0878057273475559, "rouge2_recall_stderr": 0.0030959059452337553, "rougeL_fmeasure": 0.15536673840207987, "rougeL_fmeasure_stderr": 0.0022317734298045364, "rougeL_precision": 0.11305477995205825, "rougeL_precision_stderr": 0.0017434930500077924, "rougeL_recall": 0.2663468354538728, "rougeL_recall_stderr": 0.0039010875469112365, "rougeLsum_fmeasure": 0.15242546645043564, "rougeLsum_fmeasure_stderr": 0.002411210173116271, "rougeLsum_precision": 0.11102920371579805, "rougeLsum_precision_stderr": 0.001876855631693002, "rougeLsum_recall": 0.2613081764654086, "rougeLsum_recall_stderr": 0.004217382008118568}}, "4": {"article_DOC_summary": {"bleu": 1.030072955735859, "bleu_stderr": 0.1448131273948289, "rouge1_fmeasure": 0.053859811302847754, "rouge1_fmeasure_stderr": 0.0029259257948128737, "rouge1_precision": 0.04622581157969239, "rouge1_precision_stderr": 0.002758425516324379, "rouge1_recall": 0.0843663512427161, "rouge1_recall_stderr": 0.004754251649959729, "rouge2_fmeasure": 0.012848562232113562, "rouge2_fmeasure_stderr": 0.0010859365945209303, "rouge2_precision": 0.009725911780399114, "rouge2_precision_stderr": 0.0008407639061619823, "rouge2_recall": 0.021588809000409173, "rouge2_recall_stderr": 0.0018787516143550758, "rougeL_fmeasure": 0.042690265385557376, "rougeL_fmeasure_stderr": 0.0023298094610187006, "rougeL_precision": 0.03656500907804365, "rougeL_precision_stderr": 0.002224872922024987, "rougeL_recall": 0.06728556626210627, "rougeL_recall_stderr": 0.003838297011101563, "rougeLsum_fmeasure": 0.04238885022609439, "rougeLsum_fmeasure_stderr": 0.002344653333666526, "rougeLsum_precision": 0.03647468832987227, "rougeLsum_precision_stderr": 0.0022537297464633585, "rougeLsum_recall": 0.06688889415336839, "rougeLsum_recall_stderr": 0.0038935277003977983}}, "5": {"article_DOC_summary": {"bleu": 1.5116856439856716e-16, "bleu_stderr": 7.251120818898454e-14, "rouge1_fmeasure": 0.0028858004896843946, "rouge1_fmeasure_stderr": 0.0008256676759201416, "rouge1_precision": 0.002521194639962509, "rouge1_precision_stderr": 0.0007796352087425173, "rouge1_recall": 0.004189678674165279, "rouge1_recall_stderr": 0.0012085716148740944, "rouge2_fmeasure": 0.0007107345703701913, "rouge2_fmeasure_stderr": 0.00031220919556434665, "rouge2_precision": 0.0006208832859776256, "rouge2_precision_stderr": 0.00029409209860814094, "rouge2_recall": 0.001041831827070451, "rouge2_recall_stderr": 0.0004529249135232237, "rougeL_fmeasure": 0.0023094434195131235, "rougeL_fmeasure_stderr": 0.0006631782952940002, "rougeL_precision": 0.001959124935014627, "rougeL_precision_stderr": 0.0005749051558534733, "rougeL_recall": 0.003422811625192831, "rougeL_recall_stderr": 0.0010061472311316847, "rougeLsum_fmeasure": 0.0023727145860087903, "rougeLsum_fmeasure_stderr": 0.0006800010549959292, "rougeLsum_precision": 0.0021015099772572314, "rougeLsum_precision_stderr": 0.00067865052077321, "rougeLsum_recall": 0.0034125788706789104, "rougeLsum_recall_stderr": 0.000959892406042587}}}} |