{"GEM/web_nlg_en": {"0": {"PALM_prompt": {"bleu": 0.3423886062648571, "bleu_stderr": 0.03277534172219839, "rouge1_fmeasure": 0.1078155721409226, "rouge1_fmeasure_stderr": 0.0020097112571708245, "rouge1_precision": 0.07116912691303, "rouge1_precision_stderr": 0.0015925050224480028, "rouge1_recall": 0.2998523601292701, "rouge1_recall_stderr": 0.004615423133559915, "rouge2_fmeasure": 0.04998894903569846, "rouge2_fmeasure_stderr": 0.001254978454654862, "rouge2_precision": 0.03290155614985229, "rouge2_precision_stderr": 0.0009635800950074162, "rouge2_recall": 0.1430151870039024, "rouge2_recall_stderr": 0.003133828558045969, "rougeL_fmeasure": 0.10384529013890176, "rougeL_fmeasure_stderr": 0.0018689379304153127, "rougeL_precision": 0.06817638471397719, "rougeL_precision_stderr": 0.001440134234671522, "rougeL_recall": 0.2915042735714293, "rougeL_recall_stderr": 0.004516752469805975, "rougeLsum_fmeasure": 0.10254842199703165, "rougeLsum_fmeasure_stderr": 0.0018748895711891628, "rougeLsum_precision": 0.06758374630355668, "rougeLsum_precision_stderr": 0.0014755310584898722, "rougeLsum_recall": 0.2855613282697172, "rougeLsum_recall_stderr": 0.004322222242728911}}, "1": {"PALM_prompt": {"bleu": 0.43549317288896894, "bleu_stderr": 0.029438186163177924, "rouge1_fmeasure": 0.11204264924342298, "rouge1_fmeasure_stderr": 0.0018816879797699437, "rouge1_precision": 0.07179524471867899, "rouge1_precision_stderr": 0.0013752072779383184, "rouge1_recall": 0.35855038856048876, "rouge1_recall_stderr": 0.005049635846993475, "rouge2_fmeasure": 0.051345397484036256, "rouge2_fmeasure_stderr": 0.0011584347174914676, "rouge2_precision": 0.032801419147362856, "rouge2_precision_stderr": 0.0008197872630256377, "rouge2_recall": 0.1723852958712864, "rouge2_recall_stderr": 0.0035877516735487143, "rougeL_fmeasure": 0.10481665765175784, "rougeL_fmeasure_stderr": 0.0016825296642133658, "rougeL_precision": 0.06711558592890904, "rougeL_precision_stderr": 0.00122163800184802, "rougeL_recall": 0.33387823961526397, "rougeL_recall_stderr": 0.004537882130758048, "rougeLsum_fmeasure": 0.10653343348961458, "rougeLsum_fmeasure_stderr": 0.0017665097203702323, "rougeLsum_precision": 0.06830552553162243, "rougeLsum_precision_stderr": 0.001292240550330291, "rougeLsum_recall": 0.33957294457499176, "rougeLsum_recall_stderr": 0.004661961230072316}}, "2": {"PALM_prompt": {"bleu": 0.4731158648079456, "bleu_stderr": 0.019398006063203924, "rouge1_fmeasure": 0.11565039220118124, "rouge1_fmeasure_stderr": 0.0017909510986326618, "rouge1_precision": 0.07373712610103833, "rouge1_precision_stderr": 0.0013232763617533117, "rouge1_recall": 0.3838400605745808, "rouge1_recall_stderr": 0.004971353366559517, "rouge2_fmeasure": 0.053828506115298144, "rouge2_fmeasure_stderr": 0.0011299593484305154, "rouge2_precision": 0.03418002818557043, "rouge2_precision_stderr": 0.0007999127016124942, "rouge2_recall": 0.18966804432678097, "rouge2_recall_stderr": 0.0037070132910163134, "rougeL_fmeasure": 0.10799852330681028, "rougeL_fmeasure_stderr": 0.0016342464145243179, "rougeL_precision": 0.0688866789263329, "rougeL_precision_stderr": 0.001197716696827759, "rougeL_recall": 0.35416301817745277, "rougeL_recall_stderr": 0.004408869173242153, "rougeLsum_fmeasure": 0.11029915615802689, "rougeLsum_fmeasure_stderr": 0.0017015090669507955, "rougeLsum_precision": 0.07036220911566307, "rougeLsum_precision_stderr": 0.0012542262936579098, "rougeLsum_recall": 0.3642675981143951, "rougeLsum_recall_stderr": 0.004634298128673839}}, "3": {"PALM_prompt": {"bleu": 0.511033492138013, "bleu_stderr": 0.016836817368392938, "rouge1_fmeasure": 0.11234455309812195, "rouge1_fmeasure_stderr": 0.001658068318944836, "rouge1_precision": 0.0711394556954671, "rouge1_precision_stderr": 0.0012159991412829965, "rouge1_recall": 0.3852018338546001, "rouge1_recall_stderr": 0.005067790324136812, "rouge2_fmeasure": 0.051724489676439236, "rouge2_fmeasure_stderr": 0.0010463045011873814, "rouge2_precision": 0.03260081169248259, "rouge2_precision_stderr": 0.0007319564987104789, "rouge2_recall": 0.18947442868920766, "rouge2_recall_stderr": 0.0037625536404537635, "rougeL_fmeasure": 0.10462160106353212, "rougeL_fmeasure_stderr": 0.0015374663592284314, "rougeL_precision": 0.06636573472304302, "rougeL_precision_stderr": 0.0011254814997386617, "rougeL_recall": 0.3527863813991901, "rougeL_recall_stderr": 0.004403124502538447, "rougeLsum_fmeasure": 0.10692341362108594, "rougeLsum_fmeasure_stderr": 0.001592257988435529, "rougeLsum_precision": 0.0678291021786637, "rougeLsum_precision_stderr": 0.0011705423632374366, "rougeLsum_recall": 0.36350690371493805, "rougeLsum_recall_stderr": 0.004671323997080324}}, "4": {"PALM_prompt": {"bleu": 0.5255384435057461, "bleu_stderr": 0.03418580070894041, "rouge1_fmeasure": 0.11520145885524227, "rouge1_fmeasure_stderr": 0.0016544612830049232, "rouge1_precision": 0.07289393265058683, "rouge1_precision_stderr": 0.001221203882596679, "rouge1_recall": 0.39210555607501246, "rouge1_recall_stderr": 0.004907654599821545, "rouge2_fmeasure": 0.052942763106877684, "rouge2_fmeasure_stderr": 0.0010297898091120672, "rouge2_precision": 0.03333523314795858, "rouge2_precision_stderr": 0.0007290358506575526, "rouge2_recall": 0.19457648128168623, "rouge2_recall_stderr": 0.003616303249775819, "rougeL_fmeasure": 0.10655328646588215, "rougeL_fmeasure_stderr": 0.0014999277772535491, "rougeL_precision": 0.06752250125401707, "rougeL_precision_stderr": 0.0011086146136256522, "rougeL_recall": 0.35896707400416245, "rougeL_recall_stderr": 0.004279012704408649, "rougeLsum_fmeasure": 0.10971668045319283, "rougeLsum_fmeasure_stderr": 0.001577124609883823, "rougeLsum_precision": 0.06949836967046885, "rougeLsum_precision_stderr": 0.0011669918564828742, "rougeLsum_recall": 0.3713609435685992, "rougeLsum_recall_stderr": 0.004540169352829801}}, "5": {"PALM_prompt": {"bleu": 0.5823615010118224, "bleu_stderr": 0.037398869921054644, "rouge1_fmeasure": 0.11639260450950206, "rouge1_fmeasure_stderr": 0.0016495247557604747, "rouge1_precision": 0.07346269739111895, "rouge1_precision_stderr": 0.0012187681049390564, "rouge1_recall": 0.4042470714837263, "rouge1_recall_stderr": 0.005065518163952181, "rouge2_fmeasure": 0.054089458597439195, "rouge2_fmeasure_stderr": 0.0010444166935940533, "rouge2_precision": 0.033940599163428696, "rouge2_precision_stderr": 0.0007391477550345831, "rouge2_recall": 0.20304234761076909, "rouge2_recall_stderr": 0.003764961452207978, "rougeL_fmeasure": 0.10741878654019481, "rougeL_fmeasure_stderr": 0.0015017472778460627, "rougeL_precision": 0.06792933252591714, "rougeL_precision_stderr": 0.0011100797550413972, "rougeL_recall": 0.3687266029366595, "rougeL_recall_stderr": 0.004388331338140494, "rougeLsum_fmeasure": 0.11057542829413115, "rougeLsum_fmeasure_stderr": 0.0015808583588389114, "rougeLsum_precision": 0.06991029736225668, "rougeLsum_precision_stderr": 0.001173008019162227, "rougeLsum_recall": 0.38168151833425595, "rougeLsum_recall_stderr": 0.00467124723267976}}}, "GEM/wiki_lingua_en": {"0": {"tldr_en": {"bleu": 1.4552750330972206, "bleu_stderr": 0.05646997136025405, "rouge1_fmeasure": 0.17104966216653122, "rouge1_fmeasure_stderr": 0.0018388410541572498, "rouge1_precision": 0.1463073350919793, "rouge1_precision_stderr": 0.001849976731473478, "rouge1_recall": 0.24687692205659445, "rouge1_recall_stderr": 0.0026245416604448834, "rouge2_fmeasure": 0.03393757157227001, "rouge2_fmeasure_stderr": 0.0008395819605445009, "rouge2_precision": 0.02868070817665277, "rouge2_precision_stderr": 0.0007455100631059865, "rouge2_recall": 0.050970339370236116, "rouge2_recall_stderr": 0.0013773850589296726, "rougeL_fmeasure": 0.13431002294362815, "rougeL_fmeasure_stderr": 0.001329252784566218, "rougeL_precision": 0.1134975332744349, "rougeL_precision_stderr": 0.0013046086784248739, "rougeL_recall": 0.19882847469371265, "rougeL_recall_stderr": 0.002160779528818444, "rougeLsum_fmeasure": 0.1570085078363825, "rougeLsum_fmeasure_stderr": 0.0016723834304551517, "rougeLsum_precision": 0.1341572569615249, "rougeLsum_precision_stderr": 0.001680913399139742, "rougeLsum_recall": 0.22735010800139077, "rougeLsum_recall_stderr": 0.002429214690741554}}, "1": {"tldr_en": {"bleu": 2.807870663958701, "bleu_stderr": 0.08388649431195123, "rouge1_fmeasure": 0.21883314563862602, "rouge1_fmeasure_stderr": 0.001968035833203396, "rouge1_precision": 0.19104818364291273, "rouge1_precision_stderr": 0.0022212767005973058, "rouge1_recall": 0.3165545579856358, "rouge1_recall_stderr": 0.002818835296854103, "rouge2_fmeasure": 0.05423182118294372, "rouge2_fmeasure_stderr": 0.0010465141353409224, "rouge2_precision": 0.04737338234449901, "rouge2_precision_stderr": 0.0010449765003741809, "rouge2_recall": 0.081573363995006, "rouge2_recall_stderr": 0.0017297723073854117, "rougeL_fmeasure": 0.15600647601501733, "rougeL_fmeasure_stderr": 0.0013358035921943341, "rougeL_precision": 0.1352656471757331, "rougeL_precision_stderr": 0.0015360042939327185, "rougeL_recall": 0.23168675674466935, "rougeL_recall_stderr": 0.0022572191515858007, "rougeLsum_fmeasure": 0.20602296990458846, "rougeLsum_fmeasure_stderr": 0.0018407304080033926, "rougeLsum_precision": 0.17973117727215357, "rougeLsum_precision_stderr": 0.0020830282164021902, "rougeLsum_recall": 0.29889898054403574, "rougeLsum_recall_stderr": 0.0026791790500151685}}, "2": {"tldr_en": {"bleu": 3.0758182963274967, "bleu_stderr": 0.07269865886048295, "rouge1_fmeasure": 0.213319730404769, "rouge1_fmeasure_stderr": 0.001947942927707738, "rouge1_precision": 0.22091940935835946, "rouge1_precision_stderr": 0.003036544780507811, "rouge1_recall": 0.28592540020450335, "rouge1_recall_stderr": 0.0028268458929152375, "rouge2_fmeasure": 0.05619324678157442, "rouge2_fmeasure_stderr": 0.0011378174233996204, "rouge2_precision": 0.0625668775391695, "rouge2_precision_stderr": 0.001863481800778566, "rouge2_recall": 0.07636442527094099, "rouge2_recall_stderr": 0.0016705370533154184, "rougeL_fmeasure": 0.15707830961714367, "rougeL_fmeasure_stderr": 0.001424704542577375, "rougeL_precision": 0.16524622277086715, "rougeL_precision_stderr": 0.002504977446892061, "rougeL_recall": 0.21312172953880804, "rougeL_recall_stderr": 0.002230572391304009, "rougeLsum_fmeasure": 0.20133540483239756, "rougeLsum_fmeasure_stderr": 0.0018432855451969799, "rougeLsum_precision": 0.2088533869488438, "rougeLsum_precision_stderr": 0.0029209986594073956, "rougeLsum_recall": 0.27031759901723496, "rougeLsum_recall_stderr": 0.00269091513844755}}, "3": {"tldr_en": {"bleu": 3.2676357062273516, "bleu_stderr": 0.12290136548273946, "rouge1_fmeasure": 0.17690311487463797, "rouge1_fmeasure_stderr": 0.0023173541475324253, "rouge1_precision": 0.21388175415191102, "rouge1_precision_stderr": 0.0037807201763198858, "rouge1_recall": 0.22109179833036308, "rouge1_recall_stderr": 0.00317048229219639, "rouge2_fmeasure": 0.04775424867054453, "rouge2_fmeasure_stderr": 0.0011657814934947282, "rouge2_precision": 0.06310561248802647, "rouge2_precision_stderr": 0.0021350241076741575, "rouge2_recall": 0.05983363177094545, "rouge2_recall_stderr": 0.0015915281660158853, "rougeL_fmeasure": 0.13377606619329538, "rougeL_fmeasure_stderr": 0.0017521905460361976, "rougeL_precision": 0.16656647324261953, "rougeL_precision_stderr": 0.0032154715784240336, "rougeL_recall": 0.16788106886771248, "rougeL_recall_stderr": 0.0024768275501905303, "rougeLsum_fmeasure": 0.16765421945999662, "rougeLsum_fmeasure_stderr": 0.002202375233222233, "rougeLsum_precision": 0.2032660883469589, "rougeLsum_precision_stderr": 0.003645991164048245, "rougeLsum_recall": 0.20988404520976878, "rougeLsum_recall_stderr": 0.003033569663633178}}, "4": {"tldr_en": {"bleu": 0.3207302415446247, "bleu_stderr": 0.03951812995159553, "rouge1_fmeasure": 0.05381265634572307, "rouge1_fmeasure_stderr": 0.0019615926895963105, "rouge1_precision": 0.07217489085431607, "rouge1_precision_stderr": 0.003030440715398035, "rouge1_recall": 0.06719640775054124, "rouge1_recall_stderr": 0.0025953918642397556, "rouge2_fmeasure": 0.014607128479951145, "rouge2_fmeasure_stderr": 0.0007893617726734669, "rouge2_precision": 0.021665967083708774, "rouge2_precision_stderr": 0.0015098116987345535, "rouge2_recall": 0.01860172806438717, "rouge2_recall_stderr": 0.0011134284906677621, "rougeL_fmeasure": 0.041897511040161206, "rougeL_fmeasure_stderr": 0.0015198623386063986, "rougeL_precision": 0.057955761496930415, "rougeL_precision_stderr": 0.002549676328226009, "rougeL_recall": 0.05288705994275681, "rougeL_recall_stderr": 0.0020802147270799964, "rougeLsum_fmeasure": 0.05091825334557307, "rougeLsum_fmeasure_stderr": 0.001857333758746474, "rougeLsum_precision": 0.06845672227370601, "rougeLsum_precision_stderr": 0.0028945029688266562, "rougeLsum_recall": 0.06371644081837961, "rougeLsum_recall_stderr": 0.0024692144864177654}}, "5": {"tldr_en": {"bleu": 2.2490869778774144e-09, "bleu_stderr": 4.579875964652809e-08, "rouge1_fmeasure": 0.008600982975105755, "rouge1_fmeasure_stderr": 0.000871586481245996, "rouge1_precision": 0.012746310259293975, "rouge1_precision_stderr": 0.001498370110228753, "rouge1_recall": 0.01036719903184163, "rouge1_recall_stderr": 0.0011041663951146658, "rouge2_fmeasure": 0.0027143726441978717, "rouge2_fmeasure_stderr": 0.0004021894165602589, "rouge2_precision": 0.0046837043167768724, "rouge2_precision_stderr": 0.000851048694914921, "rouge2_recall": 0.0032041325852383415, "rouge2_recall_stderr": 0.00048168285623642387, "rougeL_fmeasure": 0.006953217638177468, "rougeL_fmeasure_stderr": 0.0007188116843350712, "rougeL_precision": 0.010658331542732118, "rougeL_precision_stderr": 0.0013171585867806077, "rougeL_recall": 0.008285275201527513, "rougeL_recall_stderr": 0.0008892336234217646, "rougeLsum_fmeasure": 0.008236010332581721, "rougeLsum_fmeasure_stderr": 0.0008379564793264335, "rougeLsum_precision": 0.01225616498642844, "rougeLsum_precision_stderr": 0.0014511703007000516, "rougeLsum_recall": 0.009942438567258063, "rougeLsum_recall_stderr": 0.0010638347073576458}}}, "e2e_nlg_cleaned": {"0": {"generate_text_restaurant": {"bleu": 3.3868925634521596, "bleu_stderr": 0.07415023515490869, "rouge1_fmeasure": 0.16968795558812888, "rouge1_fmeasure_stderr": 0.0020520636735140885, "rouge1_precision": 0.12781588961197554, "rouge1_precision_stderr": 0.0016392738386146906, "rouge1_recall": 0.26686211195039367, "rouge1_recall_stderr": 0.0030010672113457175, "rouge2_fmeasure": 0.06289750165250287, "rouge2_fmeasure_stderr": 0.0013193385142581298, "rouge2_precision": 0.04754240795799523, "rouge2_precision_stderr": 0.001014281868832704, "rouge2_recall": 0.09732440743600192, "rouge2_recall_stderr": 0.002035877095135508, "rougeL_fmeasure": 0.15745602394794062, "rougeL_fmeasure_stderr": 0.0017868944105710683, "rougeL_precision": 0.11843660338175163, "rougeL_precision_stderr": 0.0014270824435811313, "rougeL_recall": 0.24837983245494402, "rougeL_recall_stderr": 0.0026307193382184542, "rougeLsum_fmeasure": 0.14802696104042146, "rougeLsum_fmeasure_stderr": 0.0018361037263776232, "rougeLsum_precision": 0.11138415788379845, "rougeLsum_precision_stderr": 0.0014602010171592388, "rougeLsum_recall": 0.23362654109870873, "rougeLsum_recall_stderr": 0.0027185132812130603}}, "1": {"generate_text_restaurant": {"bleu": 5.656637998489558, "bleu_stderr": 0.06138640019754124, "rouge1_fmeasure": 0.29857293628895076, "rouge1_fmeasure_stderr": 0.0017883517178428313, "rouge1_precision": 0.22448431958439818, "rouge1_precision_stderr": 0.0015774519438982097, "rouge1_recall": 0.475937695786901, "rouge1_recall_stderr": 0.002823854240730373, "rouge2_fmeasure": 0.12449829406834531, "rouge2_fmeasure_stderr": 0.0012625501065363337, "rouge2_precision": 0.09278798103068853, "rouge2_precision_stderr": 0.0010182785337770847, "rouge2_recall": 0.2039364568886483, "rouge2_recall_stderr": 0.0021426616098330804, "rougeL_fmeasure": 0.2478615356783164, "rougeL_fmeasure_stderr": 0.0013407338809586194, "rougeL_precision": 0.18571244490415678, "rougeL_precision_stderr": 0.0011675141052374309, "rougeL_recall": 0.3980265502028155, "rougeL_recall_stderr": 0.0023515010622215645, "rougeLsum_fmeasure": 0.24278851384210426, "rougeLsum_fmeasure_stderr": 0.0016843478489220692, "rougeLsum_precision": 0.18244634491896064, "rougeLsum_precision_stderr": 0.001437571751990845, "rougeLsum_recall": 0.3876575760439037, "rougeLsum_recall_stderr": 0.002699802672015727}}, "2": {"generate_text_restaurant": {"bleu": 6.856901680068561, "bleu_stderr": 0.08124041054587171, "rouge1_fmeasure": 0.32161895837988735, "rouge1_fmeasure_stderr": 0.00168146427395452, "rouge1_precision": 0.2401800477102809, "rouge1_precision_stderr": 0.0014473576335462571, "rouge1_recall": 0.5163816757468545, "rouge1_recall_stderr": 0.0027490552702758896, "rouge2_fmeasure": 0.14591205568832014, "rouge2_fmeasure_stderr": 0.001294685527449689, "rouge2_precision": 0.10780300493629737, "rouge2_precision_stderr": 0.0010069472486850257, "rouge2_recall": 0.2413921319510364, "rouge2_recall_stderr": 0.002257493837016372, "rougeL_fmeasure": 0.2704562548681343, "rougeL_fmeasure_stderr": 0.0013038206676934103, "rougeL_precision": 0.20140298531801745, "rougeL_precision_stderr": 0.0011006514010170898, "rougeL_recall": 0.43694912141494435, "rougeL_recall_stderr": 0.002368493512084033, "rougeLsum_fmeasure": 0.2651360409168281, "rougeLsum_fmeasure_stderr": 0.00165326573625161, "rougeLsum_precision": 0.19780238487026972, "rougeLsum_precision_stderr": 0.0013643352859564666, "rougeLsum_recall": 0.42666941865224894, "rougeLsum_recall_stderr": 0.0027363306527661384}}, "3": {"generate_text_restaurant": {"bleu": 7.067980420028392, "bleu_stderr": 0.07674666618798165, "rouge1_fmeasure": 0.3234918087831591, "rouge1_fmeasure_stderr": 0.0016866852215600267, "rouge1_precision": 0.24119330473410452, "rouge1_precision_stderr": 0.001436265091489619, "rouge1_recall": 0.520447176584629, "rouge1_recall_stderr": 0.0027841731171524635, "rouge2_fmeasure": 0.14908085018598377, "rouge2_fmeasure_stderr": 0.001325863965517803, "rouge2_precision": 0.1098856604345649, "rouge2_precision_stderr": 0.0010230282133462645, "rouge2_recall": 0.24765707981063853, "rouge2_recall_stderr": 0.002344687079258296, "rougeL_fmeasure": 0.2728226991547497, "rougeL_fmeasure_stderr": 0.001319038570084664, "rougeL_precision": 0.2028877822846739, "rougeL_precision_stderr": 0.00110597560698619, "rougeL_recall": 0.44168375010036015, "rougeL_recall_stderr": 0.0024210245845319865, "rougeLsum_fmeasure": 0.2684669151387224, "rougeLsum_fmeasure_stderr": 0.0016553181450139245, "rougeLsum_precision": 0.19995751457276323, "rougeLsum_precision_stderr": 0.0013597786817193271, "rougeLsum_recall": 0.4331317668864426, "rougeLsum_recall_stderr": 0.002771288232621466}}, "4": {"generate_text_restaurant": {"bleu": 7.301331414189049, "bleu_stderr": 0.07282835065460666, "rouge1_fmeasure": 0.3281997540286874, "rouge1_fmeasure_stderr": 0.0016842914784987548, "rouge1_precision": 0.24454894011699824, "rouge1_precision_stderr": 0.0014458985189821688, "rouge1_recall": 0.5282893998840518, "rouge1_recall_stderr": 0.0027239476703194553, "rouge2_fmeasure": 0.15250785714191883, "rouge2_fmeasure_stderr": 0.0013289295083122636, "rouge2_precision": 0.11241096101927037, "rouge2_precision_stderr": 0.0010296837842975505, "rouge2_recall": 0.25292679532334217, "rouge2_recall_stderr": 0.0023135968641909677, "rougeL_fmeasure": 0.27576809325399554, "rougeL_fmeasure_stderr": 0.001332292317195587, "rougeL_precision": 0.20493346554385022, "rougeL_precision_stderr": 0.0011217276272122712, "rougeL_recall": 0.44669665680269593, "rougeL_recall_stderr": 0.0023872195322647088, "rougeLsum_fmeasure": 0.2720277049182356, "rougeLsum_fmeasure_stderr": 0.0016797663432208906, "rougeLsum_precision": 0.20253099841039804, "rougeLsum_precision_stderr": 0.0013836573195200987, "rougeLsum_recall": 0.4389119231936933, "rougeLsum_recall_stderr": 0.0027715255759945875}}, "5": {"generate_text_restaurant": {"bleu": 7.391640493190723, "bleu_stderr": 0.07696132388022625, "rouge1_fmeasure": 0.33316361794611193, "rouge1_fmeasure_stderr": 0.0016721318654132375, "rouge1_precision": 0.248561550528162, "rouge1_precision_stderr": 0.0014842009296995168, "rouge1_recall": 0.5361907676530253, "rouge1_recall_stderr": 0.0026923692664488426, "rouge2_fmeasure": 0.15567663749325128, "rouge2_fmeasure_stderr": 0.001316099001704392, "rouge2_precision": 0.11498051543992278, "rouge2_precision_stderr": 0.0010486619107346665, "rouge2_recall": 0.2578870983510302, "rouge2_recall_stderr": 0.0022815014259324113, "rougeL_fmeasure": 0.27881193769275936, "rougeL_fmeasure_stderr": 0.0013297414200118412, "rougeL_precision": 0.2074081838133947, "rougeL_precision_stderr": 0.0011575590389617165, "rougeL_recall": 0.45169489347455444, "rougeL_recall_stderr": 0.0023905395426844995, "rougeLsum_fmeasure": 0.27704641367351746, "rougeLsum_fmeasure_stderr": 0.001654188879883823, "rougeLsum_precision": 0.20657408552804282, "rougeLsum_precision_stderr": 0.0014132706167399262, "rougeLsum_recall": 0.4467577031168348, "rougeLsum_recall_stderr": 0.0027053770792765386}}}, "gem_xsum": {"0": {"article_DOC_summary": {"bleu": 1.8973746751821576, "bleu_stderr": 0.07374608873039461, "rouge1_fmeasure": 0.20448305051370513, "rouge1_fmeasure_stderr": 0.0024499517599214865, "rouge1_precision": 0.14714404834539455, "rouge1_precision_stderr": 0.0018923895784899547, "rouge1_recall": 0.35332808198249066, "rouge1_recall_stderr": 0.004277854613117222, "rouge2_fmeasure": 0.04639360161894793, "rouge2_fmeasure_stderr": 0.0015361212037212923, "rouge2_precision": 0.03290270141635618, "rouge2_precision_stderr": 0.0010989269503369368, "rouge2_recall": 0.08287973270989689, "rouge2_recall_stderr": 0.002833032880998302, "rougeL_fmeasure": 0.1522143356903949, "rougeL_fmeasure_stderr": 0.0018364801701113477, "rougeL_precision": 0.10929554255441323, "rougeL_precision_stderr": 0.001387362394565063, "rougeL_recall": 0.26469649902339626, "rougeL_recall_stderr": 0.0033616815736178403, "rougeLsum_fmeasure": 0.1627172387554665, "rougeLsum_fmeasure_stderr": 0.0020740152357133783, "rougeLsum_precision": 0.11672705515751206, "rougeLsum_precision_stderr": 0.001546854617689576, "rougeLsum_recall": 0.28315180080173324, "rougeLsum_recall_stderr": 0.0037966298013545237}}, "1": {"article_DOC_summary": {"bleu": 1.6712614198546765, "bleu_stderr": 0.08029090892350033, "rouge1_fmeasure": 0.18885391905418497, "rouge1_fmeasure_stderr": 0.0025584792794476653, "rouge1_precision": 0.1344416388362992, "rouge1_precision_stderr": 0.0019127327308320389, "rouge1_recall": 0.33053933219336484, "rouge1_recall_stderr": 0.00435936977132835, "rouge2_fmeasure": 0.041352212313184845, "rouge2_fmeasure_stderr": 0.0015256985849036882, "rouge2_precision": 0.02919021495874484, "rouge2_precision_stderr": 0.001083579043412117, "rouge2_recall": 0.07395642387380598, "rouge2_recall_stderr": 0.0027833547930418757, "rougeL_fmeasure": 0.1447818747001178, "rougeL_fmeasure_stderr": 0.001931305342910804, "rougeL_precision": 0.10283551822207533, "rougeL_precision_stderr": 0.0014281321188522025, "rougeL_recall": 0.25511273674645885, "rougeL_recall_stderr": 0.0034307162021354593, "rougeLsum_fmeasure": 0.14973596762001254, "rougeLsum_fmeasure_stderr": 0.002121716066142779, "rougeLsum_precision": 0.10637101855903888, "rougeLsum_precision_stderr": 0.0015675521812090556, "rougeLsum_recall": 0.26365396988763345, "rougeLsum_recall_stderr": 0.003725007857599503}}, "2": {"article_DOC_summary": {"bleu": 1.7895958187086474, "bleu_stderr": 0.04787428909067152, "rouge1_fmeasure": 0.19729124660372196, "rouge1_fmeasure_stderr": 0.0024865996635105967, "rouge1_precision": 0.14045160525988198, "rouge1_precision_stderr": 0.0018675726895835078, "rouge1_recall": 0.3448073202698317, "rouge1_recall_stderr": 0.004206053313996407, "rouge2_fmeasure": 0.04614704751240165, "rouge2_fmeasure_stderr": 0.001558612721206191, "rouge2_precision": 0.03250319865239163, "rouge2_precision_stderr": 0.001104582027493848, "rouge2_recall": 0.08285013633430294, "rouge2_recall_stderr": 0.0028679116547561338, "rougeL_fmeasure": 0.15159285154298055, "rougeL_fmeasure_stderr": 0.0018751369925771642, "rougeL_precision": 0.1076421486644076, "rougeL_precision_stderr": 0.00138815532226034, "rougeL_recall": 0.2669756747819945, "rougeL_recall_stderr": 0.0033509483772327935, "rougeLsum_fmeasure": 0.1571758204423751, "rougeLsum_fmeasure_stderr": 0.002082270276853359, "rougeLsum_precision": 0.11165266260752228, "rougeLsum_precision_stderr": 0.0015420215686911798, "rougeLsum_recall": 0.2762348157117063, "rougeLsum_recall_stderr": 0.0036302813408504828}}, "3": {"article_DOC_summary": {"bleu": 1.799886255448494, "bleu_stderr": 0.06241605343512123, "rouge1_fmeasure": 0.19247676178691825, "rouge1_fmeasure_stderr": 0.0027783344646224338, "rouge1_precision": 0.1397482550494329, "rouge1_precision_stderr": 0.0021614980521941947, "rouge1_recall": 0.3314206756572503, "rouge1_recall_stderr": 0.0048258842534713575, "rouge2_fmeasure": 0.04492583126972709, "rouge2_fmeasure_stderr": 0.0015630404482977962, "rouge2_precision": 0.032034815897723355, "rouge2_precision_stderr": 0.0011234176352706835, "rouge2_recall": 0.08021224571691461, "rouge2_recall_stderr": 0.00290937059770342, "rougeL_fmeasure": 0.14710040508558128, "rougeL_fmeasure_stderr": 0.0020844906061187624, "rougeL_precision": 0.10664386827077653, "rougeL_precision_stderr": 0.0016219261205998713, "rougeL_recall": 0.25469242016766824, "rougeL_recall_stderr": 0.003747468811937111, "rougeLsum_fmeasure": 0.1523907734490472, "rougeLsum_fmeasure_stderr": 0.0023066662456799336, "rougeLsum_precision": 0.11038994072863482, "rougeLsum_precision_stderr": 0.001775109847716677, "rougeLsum_recall": 0.2637144833686383, "rougeLsum_recall_stderr": 0.004087246305150146}}, "4": {"article_DOC_summary": {"bleu": 0.912241430159217, "bleu_stderr": 0.1508779538575514, "rouge1_fmeasure": 0.052109895215743926, "rouge1_fmeasure_stderr": 0.0029325961974541494, "rouge1_precision": 0.04293551268263482, "rouge1_precision_stderr": 0.0025300915700631186, "rouge1_recall": 0.08251909123638941, "rouge1_recall_stderr": 0.0047552295627311435, "rouge2_fmeasure": 0.01203821663060757, "rouge2_fmeasure_stderr": 0.001058756941479336, "rouge2_precision": 0.008902116582691397, "rouge2_precision_stderr": 0.0007882814434287245, "rouge2_recall": 0.020355209333257882, "rouge2_recall_stderr": 0.0018399757489791825, "rougeL_fmeasure": 0.039428572953528446, "rougeL_fmeasure_stderr": 0.002210624192813922, "rougeL_precision": 0.03291018535700006, "rougeL_precision_stderr": 0.001988611171780747, "rougeL_recall": 0.06245660895956642, "rougeL_recall_stderr": 0.0036021201516783473, "rougeLsum_fmeasure": 0.0423468971865807, "rougeLsum_fmeasure_stderr": 0.002398760878941016, "rougeLsum_precision": 0.03518063964656488, "rougeLsum_precision_stderr": 0.0021155739741956746, "rougeLsum_recall": 0.0671088243853192, "rougeLsum_recall_stderr": 0.003920638757312349}}, "5": {"article_DOC_summary": {"bleu": 3.097815638153428e-39, "bleu_stderr": 5.018895149426352e-34, "rouge1_fmeasure": 0.0023684978392920267, "rouge1_fmeasure_stderr": 0.000684399718764436, "rouge1_precision": 0.002739968547331711, "rouge1_precision_stderr": 0.0008278012212952025, "rouge1_recall": 0.0022134599272398445, "rouge1_recall_stderr": 0.0006273422111807437, "rouge2_fmeasure": 0.0003256051958251534, "rouge2_fmeasure_stderr": 0.00013752393773970521, "rouge2_precision": 0.000376696230153845, "rouge2_precision_stderr": 0.00016337393027254123, "rouge2_recall": 0.00030314025597044463, "rouge2_recall_stderr": 0.00012776302473939982, "rougeL_fmeasure": 0.0019272015023736237, "rougeL_fmeasure_stderr": 0.0005653230599258551, "rougeL_precision": 0.0021741866307845633, "rougeL_precision_stderr": 0.0006503820290684123, "rougeL_recall": 0.0018275205470825698, "rougeL_recall_stderr": 0.0005304151694392347, "rougeLsum_fmeasure": 0.0020216316744952494, "rougeLsum_fmeasure_stderr": 0.0005921597049542807, "rougeLsum_precision": 0.002299258100195655, "rougeLsum_precision_stderr": 0.0006916877058747434, "rougeLsum_recall": 0.0019069310038515171, "rougeLsum_recall_stderr": 0.0005514157386454834}}}}