{"GEM/web_nlg_en": {"0": {"PALM_prompt": {"bleu": 0.4561902687825146, "bleu_stderr": 0.045631246828587047, "rouge1_fmeasure": 0.11679844154672582, "rouge1_fmeasure_stderr": 0.0019568915949739994, "rouge1_precision": 0.07625749807589129, "rouge1_precision_stderr": 0.0015146545254109735, "rouge1_recall": 0.3307426476163128, "rouge1_recall_stderr": 0.00456779888031621, "rouge2_fmeasure": 0.0554093381893294, "rouge2_fmeasure_stderr": 0.0012327294395014525, "rouge2_precision": 0.03608151986203413, "rouge2_precision_stderr": 0.0009254470422146193, "rouge2_recall": 0.16229717802554836, "rouge2_recall_stderr": 0.0032223185692842058, "rougeL_fmeasure": 0.11311445429105703, "rougeL_fmeasure_stderr": 0.0018346474985473178, "rougeL_precision": 0.07353494344552397, "rougeL_precision_stderr": 0.0013741278529976802, "rougeL_recall": 0.3230730872507571, "rougeL_recall_stderr": 0.004482961394584532, "rougeLsum_fmeasure": 0.11188332112192871, "rougeLsum_fmeasure_stderr": 0.0018465577738166203, "rougeLsum_precision": 0.07303744482119352, "rougeLsum_precision_stderr": 0.0014379306638165714, "rougeLsum_recall": 0.31705954495780236, "rougeLsum_recall_stderr": 0.004318803443289957}}, "1": {"PALM_prompt": {"bleu": 0.5886516458334025, "bleu_stderr": 0.03717726878870121, "rouge1_fmeasure": 0.12548839335267944, "rouge1_fmeasure_stderr": 0.001928881826547231, "rouge1_precision": 0.08026566053193719, "rouge1_precision_stderr": 0.0014159639116614112, "rouge1_recall": 0.3942157437513017, "rouge1_recall_stderr": 0.005461079688404384, "rouge2_fmeasure": 0.059755176813484405, "rouge2_fmeasure_stderr": 0.0012347079912433854, "rouge2_precision": 0.038000879190334146, "rouge2_precision_stderr": 0.0008787103935280456, "rouge2_recall": 0.19923195745941746, "rouge2_recall_stderr": 0.003907735021234661, "rougeL_fmeasure": 0.1183744839063624, "rougeL_fmeasure_stderr": 0.0016906391136317978, "rougeL_precision": 0.07552316506586856, "rougeL_precision_stderr": 0.00123012987736281, "rougeL_recall": 0.3738994305484677, "rougeL_recall_stderr": 0.005048426209720286, "rougeLsum_fmeasure": 0.11887135903817798, "rougeLsum_fmeasure_stderr": 0.0017838888979302661, "rougeLsum_precision": 0.07603490019116672, "rougeLsum_precision_stderr": 0.001311880863082997, "rougeLsum_recall": 0.37313363669466976, "rougeLsum_recall_stderr": 0.004995079076932912}}, "2": {"PALM_prompt": {"bleu": 0.6600722092729007, "bleu_stderr": 0.03519197756328506, "rouge1_fmeasure": 0.1228359376509253, "rouge1_fmeasure_stderr": 0.0017091878261403075, "rouge1_precision": 0.07745497341270637, "rouge1_precision_stderr": 0.0012346921599162308, "rouge1_recall": 0.41190076505770906, "rouge1_recall_stderr": 0.005377825981214025, "rouge2_fmeasure": 0.05732608605259917, "rouge2_fmeasure_stderr": 0.0011019893164004922, "rouge2_precision": 0.035903159669296886, "rouge2_precision_stderr": 0.0007708405381290396, "rouge2_recall": 0.20783156644312073, "rouge2_recall_stderr": 0.0039023098470249125, "rougeL_fmeasure": 0.11414361148332351, "rougeL_fmeasure_stderr": 0.0015117695102111128, "rougeL_precision": 0.07197458828228794, "rougeL_precision_stderr": 0.001092373974273461, "rougeL_recall": 0.3823575589838747, "rougeL_recall_stderr": 0.004836437439878737, "rougeLsum_fmeasure": 0.11649612591713067, "rougeLsum_fmeasure_stderr": 0.0016039234092463776, "rougeLsum_precision": 0.07349628109207673, "rougeLsum_precision_stderr": 0.0011632716540392056, "rougeLsum_recall": 0.3899929430530594, "rougeLsum_recall_stderr": 0.004966781612279243}}, "3": {"PALM_prompt": {"bleu": 0.7938690838487434, "bleu_stderr": 0.031249006432413233, "rouge1_fmeasure": 0.12765986861457063, "rouge1_fmeasure_stderr": 0.0017842279285890702, "rouge1_precision": 0.0802242746933909, "rouge1_precision_stderr": 0.0012915264518391, "rouge1_recall": 0.432425410033066, "rouge1_recall_stderr": 0.005388624217576616, "rouge2_fmeasure": 0.060003612710909315, "rouge2_fmeasure_stderr": 0.001146664477215343, "rouge2_precision": 0.03742102127943016, "rouge2_precision_stderr": 0.0007953067755003365, "rouge2_recall": 0.22000051519312314, "rouge2_recall_stderr": 0.00404703168782795, "rougeL_fmeasure": 0.11660022195969111, "rougeL_fmeasure_stderr": 0.0015332520691398934, "rougeL_precision": 0.07327312156062743, "rougeL_precision_stderr": 0.0011113752501149396, "rougeL_recall": 0.39487814553889183, "rougeL_recall_stderr": 0.004737789640173793, "rougeLsum_fmeasure": 0.12088469182871771, "rougeLsum_fmeasure_stderr": 0.001661523804555607, "rougeLsum_precision": 0.07598267078545315, "rougeLsum_precision_stderr": 0.001204590796246913, "rougeLsum_recall": 0.4089805013247068, "rougeLsum_recall_stderr": 0.004967802237281888}}, "4": {"PALM_prompt": {"bleu": 0.8218123055098046, "bleu_stderr": 0.044246313732840256, "rouge1_fmeasure": 0.12410661735510435, "rouge1_fmeasure_stderr": 0.001658918514736671, "rouge1_precision": 0.07753724548278816, "rouge1_precision_stderr": 0.0011900746777565759, "rouge1_recall": 0.4341910857165979, "rouge1_recall_stderr": 0.005446504875155181, "rouge2_fmeasure": 0.058623697481614896, "rouge2_fmeasure_stderr": 0.0010716614020870505, "rouge2_precision": 0.03630893474019336, "rouge2_precision_stderr": 0.0007351259548705939, "rouge2_recall": 0.2243388369397611, "rouge2_recall_stderr": 0.004106316366094987, "rougeL_fmeasure": 0.11289953851936033, "rougeL_fmeasure_stderr": 0.0014402500630831217, "rougeL_precision": 0.07062282112602274, "rougeL_precision_stderr": 0.0010428980489891116, "rougeL_recall": 0.3935550435860648, "rougeL_recall_stderr": 0.004760493217032566, "rougeLsum_fmeasure": 0.1172028966984663, "rougeLsum_fmeasure_stderr": 0.001554404781749481, "rougeLsum_precision": 0.07330274436223451, "rougeLsum_precision_stderr": 0.0011220316964088218, "rougeLsum_recall": 0.4085243199495146, "rougeLsum_recall_stderr": 0.0049771427706643894}}, "5": {"PALM_prompt": {"bleu": 0.913925260231582, "bleu_stderr": 0.051763978663194966, "rouge1_fmeasure": 0.12641834793897835, "rouge1_fmeasure_stderr": 0.0016320788274985598, "rouge1_precision": 0.07874146764038398, "rouge1_precision_stderr": 0.0012134560937164121, "rouge1_recall": 0.45109520601285813, "rouge1_recall_stderr": 0.005553088446218645, "rouge2_fmeasure": 0.05915409533137278, "rouge2_fmeasure_stderr": 0.0010512753815705362, "rouge2_precision": 0.03656608773889105, "rouge2_precision_stderr": 0.000760846094550187, "rouge2_recall": 0.23230496648757598, "rouge2_recall_stderr": 0.004227400481066823, "rougeL_fmeasure": 0.11387146771889235, "rougeL_fmeasure_stderr": 0.0013950097533787038, "rougeL_precision": 0.07104014696908037, "rougeL_precision_stderr": 0.0010444495191682013, "rougeL_recall": 0.40599373509139014, "rougeL_recall_stderr": 0.00482831666482983, "rougeLsum_fmeasure": 0.11913823061282955, "rougeLsum_fmeasure_stderr": 0.0015199756969136377, "rougeLsum_precision": 0.07423831821118593, "rougeLsum_precision_stderr": 0.0011248214939780865, "rougeLsum_recall": 0.424873549364599, "rougeLsum_recall_stderr": 0.005112245054065837}}}, "GEM/wiki_lingua_en": {"0": {"tldr_en": {"bleu": 1.6235229126061184, "bleu_stderr": 0.07158856142385593, "rouge1_fmeasure": 0.1745670903777373, "rouge1_fmeasure_stderr": 0.0019234371005345781, "rouge1_precision": 0.1490543596959789, "rouge1_precision_stderr": 0.0019546229536216812, "rouge1_recall": 0.25389546448233424, "rouge1_recall_stderr": 0.002741124482183061, "rouge2_fmeasure": 0.03547451018256482, "rouge2_fmeasure_stderr": 0.0008627729378350705, "rouge2_precision": 0.03016441545474279, "rouge2_precision_stderr": 0.0007719528814370501, "rouge2_recall": 0.053419440384246994, "rouge2_recall_stderr": 0.0014288658559341756, "rougeL_fmeasure": 0.13785667531218, "rougeL_fmeasure_stderr": 0.0013936984378312576, "rougeL_precision": 0.11627822506127969, "rougeL_precision_stderr": 0.0013862347099417346, "rougeL_recall": 0.2054884045718469, "rougeL_recall_stderr": 0.002244877757105672, "rougeLsum_fmeasure": 0.16028302243607997, "rougeLsum_fmeasure_stderr": 0.0017474929334903653, "rougeLsum_precision": 0.13663769110467477, "rougeLsum_precision_stderr": 0.0017798375104242446, "rougeLsum_recall": 0.23440517613484713, "rougeLsum_recall_stderr": 0.0025460475763855804}}, "1": {"tldr_en": {"bleu": 3.148014517976192, "bleu_stderr": 0.08632853762954663, "rouge1_fmeasure": 0.22808328022499394, "rouge1_fmeasure_stderr": 0.0020320515676967767, "rouge1_precision": 0.22331912988940492, "rouge1_precision_stderr": 0.0027687942933625823, "rouge1_recall": 0.3105879084943194, "rouge1_recall_stderr": 0.0029250201802578303, "rouge2_fmeasure": 0.05894457560206053, "rouge2_fmeasure_stderr": 0.001148762569744268, "rouge2_precision": 0.06014163619235408, "rouge2_precision_stderr": 0.001549861456149217, "rouge2_recall": 0.08133586965727622, "rouge2_recall_stderr": 0.0017304100412085226, "rougeL_fmeasure": 0.16440728290895265, "rougeL_fmeasure_stderr": 0.001417667346489937, "rougeL_precision": 0.16233563631626566, "rougeL_precision_stderr": 0.0021600975326785993, "rougeL_recall": 0.22817247618168887, "rougeL_recall_stderr": 0.0023092419967920526, "rougeLsum_fmeasure": 0.2138081154409409, "rougeLsum_fmeasure_stderr": 0.0019073843040340796, "rougeLsum_precision": 0.2095322539144404, "rougeLsum_precision_stderr": 0.002623522761491815, "rougeLsum_recall": 0.29186247430489015, "rougeLsum_recall_stderr": 0.0027828596792989963}}, "2": {"tldr_en": {"bleu": 3.648405351452855, "bleu_stderr": 0.12713119304572523, "rouge1_fmeasure": 0.23269927040845031, "rouge1_fmeasure_stderr": 0.0020394436744448855, "rouge1_precision": 0.25284242615549224, "rouge1_precision_stderr": 0.003346416305554945, "rouge1_recall": 0.2985206799819407, "rouge1_recall_stderr": 0.002872417745008737, "rouge2_fmeasure": 0.06308783765355935, "rouge2_fmeasure_stderr": 0.0012452038663643937, "rouge2_precision": 0.07352861081692932, "rouge2_precision_stderr": 0.001975577012025009, "rouge2_recall": 0.08045188272326337, "rouge2_recall_stderr": 0.001687564851802267, "rougeL_fmeasure": 0.1711468063140619, "rougeL_fmeasure_stderr": 0.0015216107571068406, "rougeL_precision": 0.18896530779163317, "rougeL_precision_stderr": 0.0027402813839447243, "rougeL_recall": 0.22165381331302203, "rougeL_recall_stderr": 0.0022793478208025125, "rougeLsum_fmeasure": 0.2196667775453629, "rougeLsum_fmeasure_stderr": 0.0019303318209296886, "rougeLsum_precision": 0.23906918273035027, "rougeLsum_precision_stderr": 0.003206715750850772, "rougeLsum_recall": 0.2821026125213223, "rougeLsum_recall_stderr": 0.0027371552638994733}}, "3": {"tldr_en": {"bleu": 3.6829199554261502, "bleu_stderr": 0.08848427999980182, "rouge1_fmeasure": 0.18860588124930222, "rouge1_fmeasure_stderr": 0.002411594336470169, "rouge1_precision": 0.21412240705416308, "rouge1_precision_stderr": 0.003573906850229763, "rouge1_recall": 0.2363591035613763, "rouge1_recall_stderr": 0.0032427476384113535, "rouge2_fmeasure": 0.051285956226699604, "rouge2_fmeasure_stderr": 0.0012327125521204533, "rouge2_precision": 0.0620187002238152, "rouge2_precision_stderr": 0.001908345830156357, "rouge2_recall": 0.0644931653305227, "rouge2_recall_stderr": 0.001637056221909264, "rougeL_fmeasure": 0.14052920532911936, "rougeL_fmeasure_stderr": 0.0018198320452371584, "rougeL_precision": 0.1623855639995828, "rougeL_precision_stderr": 0.002892414171534976, "rougeL_recall": 0.17796581661301386, "rougeL_recall_stderr": 0.0025623361467453773, "rougeLsum_fmeasure": 0.17844826504839648, "rougeLsum_fmeasure_stderr": 0.0022785596409348953, "rougeLsum_precision": 0.20310628745671855, "rougeLsum_precision_stderr": 0.0034230022998127862, "rougeLsum_recall": 0.22379283876686262, "rougeLsum_recall_stderr": 0.0030762140186834028}}, "4": {"tldr_en": {"bleu": 0.4977010788321425, "bleu_stderr": 0.029197504340406147, "rouge1_fmeasure": 0.058680633472697495, "rouge1_fmeasure_stderr": 0.0020527112852523396, "rouge1_precision": 0.06596988964164227, "rouge1_precision_stderr": 0.0026452643433214004, "rouge1_recall": 0.07786694962495821, "rouge1_recall_stderr": 0.002793778795842796, "rouge2_fmeasure": 0.015912520231271727, "rouge2_fmeasure_stderr": 0.0008257625671288616, "rouge2_precision": 0.018662630886825272, "rouge2_precision_stderr": 0.0011852493101770921, "rouge2_recall": 0.021659652341736273, "rouge2_recall_stderr": 0.0011776028400838929, "rougeL_fmeasure": 0.04448068031172814, "rougeL_fmeasure_stderr": 0.0015668077231183733, "rougeL_precision": 0.05090308576277237, "rougeL_precision_stderr": 0.002121767282678217, "rougeL_recall": 0.05971715204113024, "rougeL_recall_stderr": 0.002201135080103992, "rougeLsum_fmeasure": 0.055493537558428035, "rougeLsum_fmeasure_stderr": 0.001944192579335498, "rougeLsum_precision": 0.06266723632734954, "rougeLsum_precision_stderr": 0.002537275263785622, "rougeLsum_recall": 0.07362961134314913, "rougeLsum_recall_stderr": 0.0026439669964067034}}, "5": {"tldr_en": {"bleu": 8.62147070684518e-08, "bleu_stderr": 2.4998412186774315e-07, "rouge1_fmeasure": 0.009019405424799239, "rouge1_fmeasure_stderr": 0.0008796953070286968, "rouge1_precision": 0.009347302370204104, "rouge1_precision_stderr": 0.0009939432842913038, "rouge1_recall": 0.012675375103590819, "rouge1_recall_stderr": 0.0012741296212300682, "rouge2_fmeasure": 0.002459973367560091, "rouge2_fmeasure_stderr": 0.0003520874137724776, "rouge2_precision": 0.002520125545331128, "rouge2_precision_stderr": 0.00043890835709493897, "rouge2_recall": 0.0034745962063106794, "rouge2_recall_stderr": 0.0004926837590871648, "rougeL_fmeasure": 0.006955043299953472, "rougeL_fmeasure_stderr": 0.0006891726751168752, "rougeL_precision": 0.007379431863883617, "rougeL_precision_stderr": 0.0008249510021821957, "rougeL_recall": 0.009772980431375072, "rougeL_recall_stderr": 0.0009978936334822926, "rougeLsum_fmeasure": 0.008527269899079934, "rougeLsum_fmeasure_stderr": 0.0008337482953004597, "rougeLsum_precision": 0.008880786469979814, "rougeLsum_precision_stderr": 0.0009541098770127502, "rougeLsum_recall": 0.011981285756158963, "rougeLsum_recall_stderr": 0.0012073677632838248}}}, "e2e_nlg_cleaned": {"0": {"generate_text_restaurant": {"bleu": 2.5190605487649087, "bleu_stderr": 0.14578061564278902, "rouge1_fmeasure": 0.08785204369989494, "rouge1_fmeasure_stderr": 0.001909841985405621, "rouge1_precision": 0.12015610790826121, "rouge1_precision_stderr": 0.0026013907575401264, "rouge1_recall": 0.1007142822326354, "rouge1_recall_stderr": 0.0025699976738232087, "rouge2_fmeasure": 0.020631873410295806, "rouge2_fmeasure_stderr": 0.0008986868448192905, "rouge2_precision": 0.021978597704618782, "rouge2_precision_stderr": 0.0011061787510217053, "rouge2_recall": 0.026856846878022297, "rouge2_recall_stderr": 0.0012249926502431994, "rougeL_fmeasure": 0.083870708743602, "rougeL_fmeasure_stderr": 0.0017764834490443292, "rougeL_precision": 0.11432207717597319, "rougeL_precision_stderr": 0.002375152014750786, "rougeL_recall": 0.09673002538661275, "rougeL_recall_stderr": 0.0024476967854968764, "rougeLsum_fmeasure": 0.0771386142988915, "rougeLsum_fmeasure_stderr": 0.0016644247241633418, "rougeLsum_precision": 0.10920558363229785, "rougeLsum_precision_stderr": 0.0023563322630614446, "rougeLsum_recall": 0.08646567425286227, "rougeLsum_recall_stderr": 0.0022239273238183668}}, "1": {"generate_text_restaurant": {"bleu": 11.471305506037798, "bleu_stderr": 0.07875003513092577, "rouge1_fmeasure": 0.43708472576518986, "rouge1_fmeasure_stderr": 0.00224171007536442, "rouge1_precision": 0.5170379371586666, "rouge1_precision_stderr": 0.0033287522955400954, "rouge1_recall": 0.4239211672299534, "rouge1_recall_stderr": 0.002947218737469124, "rouge2_fmeasure": 0.19998119743920914, "rouge2_fmeasure_stderr": 0.0019048339787913725, "rouge2_precision": 0.24177763061210847, "rouge2_precision_stderr": 0.0026337382842525014, "rouge2_recall": 0.1931046855790191, "rouge2_recall_stderr": 0.0020767023449716755, "rougeL_fmeasure": 0.31725506977900303, "rougeL_fmeasure_stderr": 0.0019449957706219145, "rougeL_precision": 0.3792838934227107, "rougeL_precision_stderr": 0.002982844793468976, "rougeL_recall": 0.3062355213393646, "rougeL_recall_stderr": 0.0023427585826778815, "rougeLsum_fmeasure": 0.3599294935860651, "rougeLsum_fmeasure_stderr": 0.0021823306634720274, "rougeLsum_precision": 0.42712804511272506, "rougeLsum_precision_stderr": 0.003164747958067866, "rougeLsum_recall": 0.3486090540172501, "rougeLsum_recall_stderr": 0.002679539945997737}}, "2": {"generate_text_restaurant": {"bleu": 13.980968022690044, "bleu_stderr": 0.21821573679070036, "rouge1_fmeasure": 0.47004796009089583, "rouge1_fmeasure_stderr": 0.0022258968023120985, "rouge1_precision": 0.5445902709342957, "rouge1_precision_stderr": 0.00337974740434529, "rouge1_recall": 0.458944313155064, "rouge1_recall_stderr": 0.0029017981497803163, "rouge2_fmeasure": 0.23012493273504447, "rouge2_fmeasure_stderr": 0.002033859795223151, "rouge2_precision": 0.2713453392654981, "rouge2_precision_stderr": 0.002780199873202826, "rouge2_recall": 0.2245350505416365, "rouge2_recall_stderr": 0.0022393722057462194, "rougeL_fmeasure": 0.34524196268248847, "rougeL_fmeasure_stderr": 0.0020571216808165926, "rougeL_precision": 0.4018381948627221, "rougeL_precision_stderr": 0.0030321901639654486, "rougeL_recall": 0.33679603771757866, "rougeL_recall_stderr": 0.002478135715528108, "rougeLsum_fmeasure": 0.39203827558400783, "rougeLsum_fmeasure_stderr": 0.0022732280818521912, "rougeLsum_precision": 0.45423494017342136, "rougeLsum_precision_stderr": 0.003233814196249404, "rougeLsum_recall": 0.3829304393507027, "rougeLsum_recall_stderr": 0.0027623882797974796}}, "3": {"generate_text_restaurant": {"bleu": 14.154980307761505, "bleu_stderr": 0.1448658074579454, "rouge1_fmeasure": 0.4705643512917158, "rouge1_fmeasure_stderr": 0.00214940659696796, "rouge1_precision": 0.5290233700279933, "rouge1_precision_stderr": 0.003286733532241089, "rouge1_recall": 0.4695155836113227, "rouge1_recall_stderr": 0.0028589858065198362, "rouge2_fmeasure": 0.23283631982568367, "rouge2_fmeasure_stderr": 0.0019771157251113228, "rouge2_precision": 0.265538771393177, "rouge2_precision_stderr": 0.0026553555632510255, "rouge2_recall": 0.23270443394551238, "rouge2_recall_stderr": 0.0022448787273333173, "rougeL_fmeasure": 0.3471376353301056, "rougeL_fmeasure_stderr": 0.0020102129845005895, "rougeL_precision": 0.39229315419704086, "rougeL_precision_stderr": 0.0029631232557498915, "rougeL_recall": 0.3458978765243631, "rougeL_recall_stderr": 0.0024472277771961978, "rougeLsum_fmeasure": 0.3954525442177938, "rougeLsum_fmeasure_stderr": 0.0022179179708118656, "rougeLsum_precision": 0.44487893090959907, "rougeLsum_precision_stderr": 0.003164337474810978, "rougeLsum_recall": 0.39451585686809876, "rougeLsum_recall_stderr": 0.002730627600611841}}, "4": {"generate_text_restaurant": {"bleu": 13.721038666752582, "bleu_stderr": 0.17683442815246456, "rouge1_fmeasure": 0.4691628743032071, "rouge1_fmeasure_stderr": 0.002144459294602491, "rouge1_precision": 0.5089881039212353, "rouge1_precision_stderr": 0.0031941598167466606, "rouge1_recall": 0.479032657967036, "rouge1_recall_stderr": 0.002765675705775823, "rouge2_fmeasure": 0.23219088772710936, "rouge2_fmeasure_stderr": 0.001982880603357365, "rouge2_precision": 0.2551097554402564, "rouge2_precision_stderr": 0.002576496565725004, "rouge2_recall": 0.23713242535420967, "rouge2_recall_stderr": 0.00222316717149407, "rougeL_fmeasure": 0.3437342989792434, "rougeL_fmeasure_stderr": 0.0019737589675455874, "rougeL_precision": 0.37390882033029804, "rougeL_precision_stderr": 0.0028070940255931595, "rougeL_recall": 0.3512215949214737, "rougeL_recall_stderr": 0.0024022657027433863, "rougeLsum_fmeasure": 0.39438992601573425, "rougeLsum_fmeasure_stderr": 0.0022083897072610196, "rougeLsum_precision": 0.4277340821604659, "rougeLsum_precision_stderr": 0.003042188683426346, "rougeLsum_recall": 0.40285522466618634, "rougeLsum_recall_stderr": 0.0026869688850980986}}, "5": {"generate_text_restaurant": {"bleu": 13.685692148533645, "bleu_stderr": 0.18475778017537345, "rouge1_fmeasure": 0.4719066444266488, "rouge1_fmeasure_stderr": 0.0021232213144874593, "rouge1_precision": 0.508438587476658, "rouge1_precision_stderr": 0.0030967236462497586, "rouge1_recall": 0.4814718095446795, "rouge1_recall_stderr": 0.002740769966051787, "rouge2_fmeasure": 0.2335596273503415, "rouge2_fmeasure_stderr": 0.0019811310308482434, "rouge2_precision": 0.2543070392775442, "rouge2_precision_stderr": 0.0025002270899075695, "rouge2_recall": 0.2386513703857796, "rouge2_recall_stderr": 0.0022344362770068673, "rougeL_fmeasure": 0.34320081095568616, "rougeL_fmeasure_stderr": 0.001977144393265691, "rougeL_precision": 0.3699950720656377, "rougeL_precision_stderr": 0.0026651187832523664, "rougeL_recall": 0.35074320852708746, "rougeL_recall_stderr": 0.002429104142195895, "rougeLsum_fmeasure": 0.3963766746924401, "rougeLsum_fmeasure_stderr": 0.00219952367965179, "rougeLsum_precision": 0.427080652482253, "rougeLsum_precision_stderr": 0.002971111279966823, "rougeLsum_recall": 0.40443782365098674, "rougeLsum_recall_stderr": 0.0026631012930175323}}}, "gem_xsum": {"0": {"article_DOC_summary": {"bleu": 2.160170846637464, "bleu_stderr": 0.09889873775096984, "rouge1_fmeasure": 0.2155668468544653, "rouge1_fmeasure_stderr": 0.0026646559073492822, "rouge1_precision": 0.1675664806545814, "rouge1_precision_stderr": 0.002452603521749886, "rouge1_recall": 0.34303659164580813, "rouge1_recall_stderr": 0.00451220621305511, "rouge2_fmeasure": 0.05045080374949566, "rouge2_fmeasure_stderr": 0.0017576960885745984, "rouge2_precision": 0.03864946281782141, "rouge2_precision_stderr": 0.0014769194957715624, "rouge2_recall": 0.08335808413265051, "rouge2_recall_stderr": 0.002908314864654091, "rougeL_fmeasure": 0.1635478469839484, "rougeL_fmeasure_stderr": 0.0021077578920492917, "rougeL_precision": 0.12702750275933555, "rougeL_precision_stderr": 0.001968823066408308, "rougeL_recall": 0.26154017483908965, "rougeL_recall_stderr": 0.003585895961808971, "rougeLsum_fmeasure": 0.16836751227813998, "rougeLsum_fmeasure_stderr": 0.0022998758409405514, "rougeLsum_precision": 0.13051144332858214, "rougeLsum_precision_stderr": 0.0020713501923767027, "rougeLsum_recall": 0.26981706823174656, "rougeLsum_recall_stderr": 0.003957679243103724}}, "1": {"article_DOC_summary": {"bleu": 1.8701953699144762, "bleu_stderr": 0.05457096063405516, "rouge1_fmeasure": 0.1898050764365515, "rouge1_fmeasure_stderr": 0.0025895313777244354, "rouge1_precision": 0.13520973640137626, "rouge1_precision_stderr": 0.001930299351096568, "rouge1_recall": 0.3323577264719374, "rouge1_recall_stderr": 0.004491568598510519, "rouge2_fmeasure": 0.04465858992847766, "rouge2_fmeasure_stderr": 0.0015759770915751918, "rouge2_precision": 0.03140636068492149, "rouge2_precision_stderr": 0.001113870373266841, "rouge2_recall": 0.08109440867971819, "rouge2_recall_stderr": 0.0029471809124174825, "rougeL_fmeasure": 0.14968873061397606, "rougeL_fmeasure_stderr": 0.001933469116399493, "rougeL_precision": 0.10636283963297354, "rougeL_precision_stderr": 0.0014233454751993193, "rougeL_recall": 0.26423746064810627, "rougeL_recall_stderr": 0.003579439421960654, "rougeLsum_fmeasure": 0.14993016736293346, "rougeLsum_fmeasure_stderr": 0.0021358853384488446, "rougeLsum_precision": 0.10653719114272985, "rougeLsum_precision_stderr": 0.0015634601753452939, "rougeLsum_recall": 0.26451619174803076, "rougeLsum_recall_stderr": 0.003902068769045215}}, "2": {"article_DOC_summary": {"bleu": 1.8292996100546781, "bleu_stderr": 0.08163094513619551, "rouge1_fmeasure": 0.1913140581117672, "rouge1_fmeasure_stderr": 0.0025051242733995895, "rouge1_precision": 0.1369596940677527, "rouge1_precision_stderr": 0.0018924121735394107, "rouge1_recall": 0.33267847518896543, "rouge1_recall_stderr": 0.004382896639279902, "rouge2_fmeasure": 0.046514407795467595, "rouge2_fmeasure_stderr": 0.0015752063358252097, "rouge2_precision": 0.03283865595587313, "rouge2_precision_stderr": 0.0011141105617716379, "rouge2_recall": 0.08404626501275646, "rouge2_recall_stderr": 0.0029766014928721417, "rougeL_fmeasure": 0.1555172607724421, "rougeL_fmeasure_stderr": 0.0019665304832963766, "rougeL_precision": 0.11105944816976555, "rougeL_precision_stderr": 0.0014582290975397828, "rougeL_recall": 0.27226184993618935, "rougeL_recall_stderr": 0.003638521351468343, "rougeLsum_fmeasure": 0.148021529852108, "rougeLsum_fmeasure_stderr": 0.0021093930620772303, "rougeLsum_precision": 0.10559932998246374, "rougeLsum_precision_stderr": 0.0015493840715498106, "rougeLsum_recall": 0.2597115453851503, "rougeLsum_recall_stderr": 0.003887704936356228}}, "3": {"article_DOC_summary": {"bleu": 1.729714249041032, "bleu_stderr": 0.09968587223572584, "rouge1_fmeasure": 0.1828325966117306, "rouge1_fmeasure_stderr": 0.0026884744365811403, "rouge1_precision": 0.13421303891622097, "rouge1_precision_stderr": 0.0021412802231387967, "rouge1_recall": 0.310980261970668, "rouge1_recall_stderr": 0.004684135200277263, "rouge2_fmeasure": 0.043981143624385655, "rouge2_fmeasure_stderr": 0.0015389553455476062, "rouge2_precision": 0.03176375904264973, "rouge2_precision_stderr": 0.0011285744197009628, "rouge2_recall": 0.0771291588842163, "rouge2_recall_stderr": 0.0028009360577460445, "rougeL_fmeasure": 0.15042887440453737, "rougeL_fmeasure_stderr": 0.002182144987791837, "rougeL_precision": 0.11010971775440595, "rougeL_precision_stderr": 0.0017060839433245796, "rougeL_recall": 0.257265478142769, "rougeL_recall_stderr": 0.003940518987777604, "rougeLsum_fmeasure": 0.14143730410765654, "rougeLsum_fmeasure_stderr": 0.0022370123860963476, "rougeLsum_precision": 0.10364375570761218, "rougeLsum_precision_stderr": 0.0017533516458810485, "rougeLsum_recall": 0.24201646695848927, "rougeLsum_recall_stderr": 0.004005217279812412}}, "4": {"article_DOC_summary": {"bleu": 0.9890184534659001, "bleu_stderr": 0.14163039170125274, "rouge1_fmeasure": 0.0521003876015691, "rouge1_fmeasure_stderr": 0.002910995728301919, "rouge1_precision": 0.04440086644350133, "rouge1_precision_stderr": 0.0028076146832161425, "rouge1_recall": 0.0803342918035357, "rouge1_recall_stderr": 0.004572536216376621, "rouge2_fmeasure": 0.01307647569779615, "rouge2_fmeasure_stderr": 0.0011218803952754701, "rouge2_precision": 0.011721386490746217, "rouge2_precision_stderr": 0.001394908515617324, "rouge2_recall": 0.020621720002167342, "rouge2_recall_stderr": 0.0017793611110912008, "rougeL_fmeasure": 0.04296796327738306, "rougeL_fmeasure_stderr": 0.002392166194141485, "rougeL_precision": 0.03669834695042482, "rougeL_precision_stderr": 0.0023530729136330853, "rougeL_recall": 0.06682107529885967, "rougeL_recall_stderr": 0.0038307757001802474, "rougeLsum_fmeasure": 0.042028608773829565, "rougeLsum_fmeasure_stderr": 0.0023859608992589927, "rougeLsum_precision": 0.03617640134116618, "rougeLsum_precision_stderr": 0.0023748208613590294, "rougeLsum_recall": 0.06502829732266231, "rougeLsum_recall_stderr": 0.003786163884263381}}, "5": {"article_DOC_summary": {"bleu": 1.3300633595706627e-37, "bleu_stderr": 2.704529748702706e-32, "rouge1_fmeasure": 0.002975946933660433, "rouge1_fmeasure_stderr": 0.0008325096950346747, "rouge1_precision": 0.003536517824005411, "rouge1_precision_stderr": 0.0010348361693354221, "rouge1_recall": 0.0026502867716370814, "rouge1_recall_stderr": 0.0007219200372674768, "rouge2_fmeasure": 0.0005678964868499288, "rouge2_fmeasure_stderr": 0.00022071683514847003, "rouge2_precision": 0.0007216185282223018, "rouge2_precision_stderr": 0.00028726019405366274, "rouge2_recall": 0.00047841047841047846, "rouge2_recall_stderr": 0.00018648358251820024, "rougeL_fmeasure": 0.002335136000302258, "rougeL_fmeasure_stderr": 0.000650477644840957, "rougeL_precision": 0.0027483075773717747, "rougeL_precision_stderr": 0.0008030756319798513, "rougeL_recall": 0.0021047616766507017, "rougeL_recall_stderr": 0.0005731278953348982, "rougeLsum_fmeasure": 0.0024473347701190456, "rougeLsum_fmeasure_stderr": 0.0006984333555662036, "rougeLsum_precision": 0.0029063810983753734, "rougeLsum_precision_stderr": 0.0008739925650642316, "rougeLsum_recall": 0.0021888663476128875, "rougeLsum_recall_stderr": 0.0006063079941836999}}}}