{"GEM/web_nlg_en": {"0": {"PALM_prompt": {"bleu": 0.4070835356827751, "bleu_stderr": 0.03514958095848397, "rouge1_fmeasure": 0.11509298027342854, "rouge1_fmeasure_stderr": 0.002040147114373331, "rouge1_precision": 0.0758536616906455, "rouge1_precision_stderr": 0.0015747064380670645, "rouge1_recall": 0.3264375465319237, "rouge1_recall_stderr": 0.004888854445231445, "rouge2_fmeasure": 0.0532813862747049, "rouge2_fmeasure_stderr": 0.0012579627803205211, "rouge2_precision": 0.03493638633069714, "rouge2_precision_stderr": 0.0009342574915112234, "rouge2_recall": 0.15766160622381195, "rouge2_recall_stderr": 0.0033114573324024405, "rougeL_fmeasure": 0.1105412242108245, "rougeL_fmeasure_stderr": 0.0019072286738988954, "rougeL_precision": 0.07257604824526195, "rougeL_precision_stderr": 0.0014483785678009685, "rougeL_recall": 0.31637706878833355, "rougeL_recall_stderr": 0.004769735504597033, "rougeLsum_fmeasure": 0.10843545057843905, "rougeLsum_fmeasure_stderr": 0.0019083088150967664, "rougeLsum_precision": 0.0714774644843108, "rougeLsum_precision_stderr": 0.0014699104009543759, "rougeLsum_recall": 0.307939556685913, "rougeLsum_recall_stderr": 0.004520814685280998}}, "1": {"PALM_prompt": {"bleu": 0.41914858834195134, "bleu_stderr": 0.030279335876129, "rouge1_fmeasure": 0.11424698089656772, "rouge1_fmeasure_stderr": 0.001973221738343803, "rouge1_precision": 0.07536633674836868, "rouge1_precision_stderr": 0.001620641410096321, "rouge1_recall": 0.3290768382699901, "rouge1_recall_stderr": 0.00481767508183653, "rouge2_fmeasure": 0.05368591058094131, "rouge2_fmeasure_stderr": 0.0012551880063213156, "rouge2_precision": 0.03540467062379218, "rouge2_precision_stderr": 0.001074817084017668, "rouge2_recall": 0.16089821041540717, "rouge2_recall_stderr": 0.0033011630774406127, "rougeL_fmeasure": 0.10991123942051419, "rougeL_fmeasure_stderr": 0.0018557651460448018, "rougeL_precision": 0.07231503158237214, "rougeL_precision_stderr": 0.0015163361416883465, "rougeL_recall": 0.3189205930522712, "rougeL_recall_stderr": 0.004694857387684187, "rougeLsum_fmeasure": 0.1082043807305256, "rougeLsum_fmeasure_stderr": 0.0018480349337665876, "rougeLsum_precision": 0.07148579673935408, "rougeLsum_precision_stderr": 0.0015357817111525064, "rougeLsum_recall": 0.3110112645350247, "rougeLsum_recall_stderr": 0.00441643475943137}}, "2": {"PALM_prompt": {"bleu": 0.4241874936612034, "bleu_stderr": 0.03699728854949305, "rouge1_fmeasure": 0.11375522621692136, "rouge1_fmeasure_stderr": 0.0019642936162507533, "rouge1_precision": 0.07469786641233617, "rouge1_precision_stderr": 0.0015771153206732972, "rouge1_recall": 0.32891693541469197, "rouge1_recall_stderr": 0.004751520151482175, "rouge2_fmeasure": 0.05344291957030947, "rouge2_fmeasure_stderr": 0.001233885317072834, "rouge2_precision": 0.03462695918297652, "rouge2_precision_stderr": 0.0009079391487918842, "rouge2_recall": 0.16210166248343671, "rouge2_recall_stderr": 0.003411098262587952, "rougeL_fmeasure": 0.10934081987838024, "rougeL_fmeasure_stderr": 0.0018415550723111455, "rougeL_precision": 0.07161852924412807, "rougeL_precision_stderr": 0.0014761860684115284, "rougeL_recall": 0.31797917629392425, "rougeL_recall_stderr": 0.004598849198704314, "rougeLsum_fmeasure": 0.10823991385374933, "rougeLsum_fmeasure_stderr": 0.0018380668821100924, "rougeLsum_precision": 0.0711214967812572, "rougeLsum_precision_stderr": 0.00149377360051449, "rougeLsum_recall": 0.3130870814045286, "rougeLsum_recall_stderr": 0.004421211065212564}}, "3": {"PALM_prompt": {"bleu": 0.3916994292697065, "bleu_stderr": 0.02655023153261868, "rouge1_fmeasure": 0.11443103117633296, "rouge1_fmeasure_stderr": 0.0019845366723218495, "rouge1_precision": 0.07713695315738618, "rouge1_precision_stderr": 0.0018521617901133295, "rouge1_recall": 0.32641437991318506, "rouge1_recall_stderr": 0.004583689746653368, "rouge2_fmeasure": 0.05368996382308088, "rouge2_fmeasure_stderr": 0.0012403567348119643, "rouge2_precision": 0.036319480745632425, "rouge2_precision_stderr": 0.0012079439649413412, "rouge2_recall": 0.15985213856119682, "rouge2_recall_stderr": 0.003223582265695079, "rougeL_fmeasure": 0.10920281437234497, "rougeL_fmeasure_stderr": 0.0018472429946517301, "rougeL_precision": 0.07333561421491072, "rougeL_precision_stderr": 0.0017170202297610163, "rougeL_recall": 0.3129899723170166, "rougeL_recall_stderr": 0.004403504671395443, "rougeLsum_fmeasure": 0.10882089385505, "rougeLsum_fmeasure_stderr": 0.0018674885337082484, "rougeLsum_precision": 0.07332584684616669, "rougeLsum_precision_stderr": 0.0017553031622823821, "rougeLsum_recall": 0.31070372160179327, "rougeLsum_recall_stderr": 0.004314602758278112}}, "4": {"PALM_prompt": {"bleu": 0.37875018794247045, "bleu_stderr": 0.024296780304434905, "rouge1_fmeasure": 0.1102139471634063, "rouge1_fmeasure_stderr": 0.0019620155943445507, "rouge1_precision": 0.07231813177556075, "rouge1_precision_stderr": 0.0015118246585830762, "rouge1_recall": 0.31870699434574523, "rouge1_recall_stderr": 0.0046463072458484975, "rouge2_fmeasure": 0.0515680827205002, "rouge2_fmeasure_stderr": 0.001213141047008391, "rouge2_precision": 0.033695317164630666, "rouge2_precision_stderr": 0.0009163247572691914, "rouge2_recall": 0.15554105747469235, "rouge2_recall_stderr": 0.003236397171744527, "rougeL_fmeasure": 0.1054595308766645, "rougeL_fmeasure_stderr": 0.0018290764447497754, "rougeL_precision": 0.06901574750871842, "rougeL_precision_stderr": 0.0013947803448898716, "rougeL_recall": 0.30638147232578594, "rougeL_recall_stderr": 0.004472401624140904, "rougeLsum_fmeasure": 0.10492767242713451, "rougeLsum_fmeasure_stderr": 0.001836832016012516, "rougeLsum_precision": 0.06885871876103705, "rougeLsum_precision_stderr": 0.001420315845279487, "rougeLsum_recall": 0.30338100654345734, "rougeLsum_recall_stderr": 0.0043561963135752306}}, "5": {"PALM_prompt": {"bleu": 0.3689406693649318, "bleu_stderr": 0.01833284872989782, "rouge1_fmeasure": 0.10942321553706275, "rouge1_fmeasure_stderr": 0.001960578009336271, "rouge1_precision": 0.0725733890131515, "rouge1_precision_stderr": 0.0016541722828599028, "rouge1_recall": 0.31647681542290346, "rouge1_recall_stderr": 0.004649887369574888, "rouge2_fmeasure": 0.05107734688924233, "rouge2_fmeasure_stderr": 0.00122669666906548, "rouge2_precision": 0.0340511038621137, "rouge2_precision_stderr": 0.001109810266658632, "rouge2_recall": 0.1539259113242296, "rouge2_recall_stderr": 0.003295678214536681, "rougeL_fmeasure": 0.10453686352175766, "rougeL_fmeasure_stderr": 0.0018279045748061345, "rougeL_precision": 0.06920155517233274, "rougeL_precision_stderr": 0.0015510532870385023, "rougeL_recall": 0.30372126675172995, "rougeL_recall_stderr": 0.004472388579309833, "rougeLsum_fmeasure": 0.1036182486745027, "rougeLsum_fmeasure_stderr": 0.0018321897232056268, "rougeLsum_precision": 0.0688242602910231, "rougeLsum_precision_stderr": 0.0015744817424633028, "rougeLsum_recall": 0.3000075619025587, "rougeLsum_recall_stderr": 0.004328528641012373}}}, "GEM/wiki_lingua_en": {"0": {"tldr_en": {"bleu": 0.14859459498800928, "bleu_stderr": 0.019538924284114197, "rouge1_fmeasure": 0.05739499438745971, "rouge1_fmeasure_stderr": 0.000959404112224303, "rouge1_precision": 0.0505257980847339, "rouge1_precision_stderr": 0.0009316535384306269, "rouge1_recall": 0.07944574030730557, "rouge1_recall_stderr": 0.0013436416711421135, "rouge2_fmeasure": 0.002874313185982406, "rouge2_fmeasure_stderr": 0.00022791640812011725, "rouge2_precision": 0.0025522430280765624, "rouge2_precision_stderr": 0.00019188137819214202, "rouge2_recall": 0.003889530091650386, "rouge2_recall_stderr": 0.0003502492712853139, "rougeL_fmeasure": 0.053008425140295905, "rougeL_fmeasure_stderr": 0.0008201296289562219, "rougeL_precision": 0.04641940622808299, "rougeL_precision_stderr": 0.0007892141876172595, "rougeL_recall": 0.07403750267734954, "rougeL_recall_stderr": 0.0011941764542527037, "rougeLsum_fmeasure": 0.05476968826480647, "rougeLsum_fmeasure_stderr": 0.0008953065390907387, "rougeLsum_precision": 0.04816018092226108, "rougeLsum_precision_stderr": 0.0008696938078640268, "rougeLsum_recall": 0.07599978162074517, "rougeLsum_recall_stderr": 0.0012632037879506343}}, "1": {"tldr_en": {"bleu": 1.346869321685321, "bleu_stderr": 0.06607443264134674, "rouge1_fmeasure": 0.15836293018887368, "rouge1_fmeasure_stderr": 0.001891640433790272, "rouge1_precision": 0.13584035826185337, "rouge1_precision_stderr": 0.001883003830967405, "rouge1_recall": 0.2300655738827389, "rouge1_recall_stderr": 0.002771815067524841, "rouge2_fmeasure": 0.028190707681194575, "rouge2_fmeasure_stderr": 0.0008118715649523407, "rouge2_precision": 0.02400583408187123, "rouge2_precision_stderr": 0.0007285343955308211, "rouge2_recall": 0.04289680599794199, "rouge2_recall_stderr": 0.001353605133009988, "rougeL_fmeasure": 0.12130392597137107, "rougeL_fmeasure_stderr": 0.0012906736654645788, "rougeL_precision": 0.10298984208878467, "rougeL_precision_stderr": 0.0012746961770117027, "rougeL_recall": 0.18009351587124983, "rougeL_recall_stderr": 0.002104050870387258, "rougeLsum_fmeasure": 0.14788907195330203, "rougeLsum_fmeasure_stderr": 0.0017520956258023405, "rougeLsum_precision": 0.12668865175777289, "rougeLsum_precision_stderr": 0.0017429813042225584, "rougeLsum_recall": 0.21558088869876474, "rougeLsum_recall_stderr": 0.0026000978058887433}}, "2": {"tldr_en": {"bleu": 2.247794388992107, "bleu_stderr": 0.09928029909737168, "rouge1_fmeasure": 0.1979943409707515, "rouge1_fmeasure_stderr": 0.0019701979235594003, "rouge1_precision": 0.1708173947979992, "rouge1_precision_stderr": 0.002081500885534108, "rouge1_recall": 0.2857546859749413, "rouge1_recall_stderr": 0.002766073063501205, "rouge2_fmeasure": 0.04456119604899187, "rouge2_fmeasure_stderr": 0.0009779372383836055, "rouge2_precision": 0.03867526801746755, "rouge2_precision_stderr": 0.0009249837176721441, "rouge2_recall": 0.06488659439579164, "rouge2_recall_stderr": 0.0015151297174771778, "rougeL_fmeasure": 0.14561448339286645, "rougeL_fmeasure_stderr": 0.0013308339769298708, "rougeL_precision": 0.12436000788073821, "rougeL_precision_stderr": 0.0013936495773448447, "rougeL_recall": 0.21512580022359384, "rougeL_recall_stderr": 0.0021392819398317084, "rougeLsum_fmeasure": 0.18443888049277404, "rougeLsum_fmeasure_stderr": 0.0018323545176278458, "rougeLsum_precision": 0.15896932268065497, "rougeLsum_precision_stderr": 0.0019322450604166179, "rougeLsum_recall": 0.2668532631896298, "rougeLsum_recall_stderr": 0.00261075911429361}}, "3": {"tldr_en": {"bleu": 2.212268753332442, "bleu_stderr": 0.09749124513916169, "rouge1_fmeasure": 0.17165885454358776, "rouge1_fmeasure_stderr": 0.002266523062316873, "rouge1_precision": 0.15395480397824707, "rouge1_precision_stderr": 0.002402542953049042, "rouge1_recall": 0.24557521515724243, "rouge1_recall_stderr": 0.0032199609208037362, "rouge2_fmeasure": 0.03887583188926559, "rouge2_fmeasure_stderr": 0.0009318869486006191, "rouge2_precision": 0.0345849314932535, "rouge2_precision_stderr": 0.000925086814362582, "rouge2_recall": 0.05685215254790676, "rouge2_recall_stderr": 0.0014741611375388177, "rougeL_fmeasure": 0.12611107179368627, "rougeL_fmeasure_stderr": 0.0015753873989903184, "rougeL_precision": 0.11262382269704937, "rougeL_precision_stderr": 0.001735467609168603, "rougeL_recall": 0.1853949845751863, "rougeL_recall_stderr": 0.002495030067359919, "rougeLsum_fmeasure": 0.15920866146470747, "rougeLsum_fmeasure_stderr": 0.0021025779963518188, "rougeLsum_precision": 0.1426484686620457, "rougeLsum_precision_stderr": 0.0022377962576445335, "rougeLsum_recall": 0.22876101619014125, "rougeLsum_recall_stderr": 0.0030299996388814796}}, "4": {"tldr_en": {"bleu": 0.5159665881377578, "bleu_stderr": 0.0355848354666848, "rouge1_fmeasure": 0.057194516095400834, "rouge1_fmeasure_stderr": 0.0019532780600384314, "rouge1_precision": 0.05323367871163294, "rouge1_precision_stderr": 0.002019764759552398, "rouge1_recall": 0.08477832633294664, "rouge1_recall_stderr": 0.0029256767843087337, "rouge2_fmeasure": 0.013407675922368708, "rouge2_fmeasure_stderr": 0.0006687476239191229, "rouge2_precision": 0.011892613439611567, "rouge2_precision_stderr": 0.0006525291351364055, "rouge2_recall": 0.021014952711012305, "rouge2_recall_stderr": 0.0011420293722952714, "rougeL_fmeasure": 0.0429641799328658, "rougeL_fmeasure_stderr": 0.0014362645716637073, "rougeL_precision": 0.03994947969161068, "rougeL_precision_stderr": 0.0015323136750776513, "rougeL_recall": 0.0654114763710059, "rougeL_recall_stderr": 0.0022890377474177525, "rougeLsum_fmeasure": 0.052823275351703086, "rougeLsum_fmeasure_stderr": 0.0018085153746161442, "rougeLsum_precision": 0.049203521589357486, "rougeLsum_precision_stderr": 0.0018745212624263795, "rougeLsum_recall": 0.07828616324493042, "rougeLsum_recall_stderr": 0.00270998239625019}}, "5": {"tldr_en": {"bleu": 5.133528491740168e-07, "bleu_stderr": 9.288876136024227e-07, "rouge1_fmeasure": 0.00885537771521418, "rouge1_fmeasure_stderr": 0.0008474145806800235, "rouge1_precision": 0.008397509125114434, "rouge1_precision_stderr": 0.0008676037544483993, "rouge1_recall": 0.013182384245950918, "rouge1_recall_stderr": 0.0012488579545023588, "rouge2_fmeasure": 0.0020845828252393957, "rouge2_fmeasure_stderr": 0.0002776449859686965, "rouge2_precision": 0.0018519121687661717, "rouge2_precision_stderr": 0.0002652232008037664, "rouge2_recall": 0.003201546871291623, "rouge2_recall_stderr": 0.00042951400653203656, "rougeL_fmeasure": 0.006795329450745382, "rougeL_fmeasure_stderr": 0.0006430172034977336, "rougeL_precision": 0.006312806712827651, "rougeL_precision_stderr": 0.0006339300731280119, "rougeL_recall": 0.010466170637582555, "rougeL_recall_stderr": 0.0010119772330203227, "rougeLsum_fmeasure": 0.008112137370163754, "rougeLsum_fmeasure_stderr": 0.0007719985459243486, "rougeLsum_precision": 0.0076894646083944945, "rougeLsum_precision_stderr": 0.000786099271409283, "rougeLsum_recall": 0.012227793486074013, "rougeLsum_recall_stderr": 0.0011695312324965957}}}, "e2e_nlg_cleaned": {"0": {"generate_text_restaurant": {"bleu": 0.02601889547824242, "bleu_stderr": 0.008845990174481217, "rouge1_fmeasure": 0.016342850382717815, "rouge1_fmeasure_stderr": 0.00034912236129064063, "rouge1_precision": 0.013188289488289925, "rouge1_precision_stderr": 0.0003020110162685144, "rouge1_recall": 0.02331912229418711, "rouge1_recall_stderr": 0.0005487407492538043, "rouge2_fmeasure": 0.00024104025657346095, "rouge2_fmeasure_stderr": 5.3010616942847675e-05, "rouge2_precision": 0.00018882696164487857, "rouge2_precision_stderr": 4.0143613745290394e-05, "rouge2_recall": 0.0003925072247489244, "rouge2_recall_stderr": 9.925690772584578e-05, "rougeL_fmeasure": 0.016342850382717815, "rougeL_fmeasure_stderr": 0.00034912236129064063, "rougeL_precision": 0.013188289488289925, "rougeL_precision_stderr": 0.0003020110162685144, "rougeL_recall": 0.02331912229418711, "rougeL_recall_stderr": 0.0005487407492538043, "rougeLsum_fmeasure": 0.015820908294670494, "rougeLsum_fmeasure_stderr": 0.00033227991604236137, "rougeLsum_precision": 0.012772945572946016, "rougeLsum_precision_stderr": 0.000289959796992291, "rougeLsum_recall": 0.022577540598345845, "rougeLsum_recall_stderr": 0.0005237847970514886}}, "1": {"generate_text_restaurant": {"bleu": 10.11194167971178, "bleu_stderr": 0.11325409958385195, "rouge1_fmeasure": 0.396708212066539, "rouge1_fmeasure_stderr": 0.0023271634805327288, "rouge1_precision": 0.44662580344767955, "rouge1_precision_stderr": 0.0029145470980427935, "rouge1_recall": 0.403325138761631, "rouge1_recall_stderr": 0.0029812540605776657, "rouge2_fmeasure": 0.1714205638298909, "rouge2_fmeasure_stderr": 0.0017391694364972787, "rouge2_precision": 0.19849995481108837, "rouge2_precision_stderr": 0.0023301034372897886, "rouge2_recall": 0.17476709268624893, "rouge2_recall_stderr": 0.0019834376005625296, "rougeL_fmeasure": 0.28469304359904984, "rougeL_fmeasure_stderr": 0.0018043411811584805, "rougeL_precision": 0.3259862976774872, "rougeL_precision_stderr": 0.0025491424613272398, "rougeL_recall": 0.28928330619087117, "rougeL_recall_stderr": 0.002329063084463768, "rougeLsum_fmeasure": 0.3323030796627126, "rougeLsum_fmeasure_stderr": 0.002111384569072981, "rougeLsum_precision": 0.37806486217321694, "rougeLsum_precision_stderr": 0.002787004218176944, "rougeLsum_recall": 0.3367501905387613, "rougeLsum_recall_stderr": 0.002641205675752919}}, "2": {"generate_text_restaurant": {"bleu": 10.765851233592166, "bleu_stderr": 0.1147637687545087, "rouge1_fmeasure": 0.4194853660757534, "rouge1_fmeasure_stderr": 0.002222220598248002, "rouge1_precision": 0.5029109698404333, "rouge1_precision_stderr": 0.0032326251122724503, "rouge1_recall": 0.399072749631299, "rouge1_recall_stderr": 0.002770754484292409, "rouge2_fmeasure": 0.19259169221915515, "rouge2_fmeasure_stderr": 0.0018423181170468268, "rouge2_precision": 0.23608052397188775, "rouge2_precision_stderr": 0.002567411684370418, "rouge2_recall": 0.18324767332759007, "rouge2_recall_stderr": 0.001989894281113984, "rougeL_fmeasure": 0.3027130154416743, "rougeL_fmeasure_stderr": 0.001900798692043736, "rougeL_precision": 0.3660346353864222, "rougeL_precision_stderr": 0.0028533265797324394, "rougeL_recall": 0.28763635547225785, "rougeL_recall_stderr": 0.002249079446710024, "rougeLsum_fmeasure": 0.34512069878778673, "rougeLsum_fmeasure_stderr": 0.00213278119755698, "rougeLsum_precision": 0.4152150772992765, "rougeLsum_precision_stderr": 0.0030631524445173153, "rougeLsum_recall": 0.32804484742896467, "rougeLsum_recall_stderr": 0.002520109021821381}}, "3": {"generate_text_restaurant": {"bleu": 10.504414399066166, "bleu_stderr": 0.14144404460789148, "rouge1_fmeasure": 0.42179412730593185, "rouge1_fmeasure_stderr": 0.0021527795098671134, "rouge1_precision": 0.509958754752616, "rouge1_precision_stderr": 0.003154730928607417, "rouge1_recall": 0.3954899202585752, "rouge1_recall_stderr": 0.002608601302312822, "rouge2_fmeasure": 0.19636018570824587, "rouge2_fmeasure_stderr": 0.0018014064871279597, "rouge2_precision": 0.24242098353513022, "rouge2_precision_stderr": 0.002484157206893866, "rouge2_recall": 0.18360253637850166, "rouge2_recall_stderr": 0.001904297402323581, "rougeL_fmeasure": 0.30275824983777616, "rougeL_fmeasure_stderr": 0.0018031245552577217, "rougeL_precision": 0.36777401786978037, "rougeL_precision_stderr": 0.002648283289980144, "rougeL_recall": 0.28409076327843025, "rougeL_recall_stderr": 0.002115488452238855, "rougeLsum_fmeasure": 0.3452111361624014, "rougeLsum_fmeasure_stderr": 0.0020448977561221436, "rougeLsum_precision": 0.4185549498251625, "rougeLsum_precision_stderr": 0.0029283489596877298, "rougeLsum_recall": 0.32342169868683124, "rougeLsum_recall_stderr": 0.0023588979812351725}}, "4": {"generate_text_restaurant": {"bleu": 10.453461006006084, "bleu_stderr": 0.20323399299325623, "rouge1_fmeasure": 0.4184745538314975, "rouge1_fmeasure_stderr": 0.002152424221911221, "rouge1_precision": 0.5152975398825912, "rouge1_precision_stderr": 0.0032876121566522126, "rouge1_recall": 0.3875757012647283, "rouge1_recall_stderr": 0.002563136912882847, "rouge2_fmeasure": 0.19590832872090894, "rouge2_fmeasure_stderr": 0.0017695553874619732, "rouge2_precision": 0.24767323400172267, "rouge2_precision_stderr": 0.002578983235298861, "rouge2_recall": 0.1802765312255684, "rouge2_recall_stderr": 0.0018268424519338505, "rougeL_fmeasure": 0.30013711995116676, "rougeL_fmeasure_stderr": 0.001799774395616833, "rougeL_precision": 0.37129359217610464, "rougeL_precision_stderr": 0.0027272181980460375, "rougeL_recall": 0.2780682094337028, "rougeL_recall_stderr": 0.0020775510109816452, "rougeLsum_fmeasure": 0.34206938848652774, "rougeLsum_fmeasure_stderr": 0.0020120604230570572, "rougeLsum_precision": 0.4223690533102043, "rougeLsum_precision_stderr": 0.003005111083307187, "rougeLsum_recall": 0.3169024351381635, "rougeLsum_recall_stderr": 0.0023241001320442878}}, "5": {"generate_text_restaurant": {"bleu": 10.336987597938899, "bleu_stderr": 0.20513507856533955, "rouge1_fmeasure": 0.4170315564856164, "rouge1_fmeasure_stderr": 0.002124259039598598, "rouge1_precision": 0.5143545157562858, "rouge1_precision_stderr": 0.003337934175013788, "rouge1_recall": 0.3857868235592206, "rouge1_recall_stderr": 0.0024923995035469678, "rouge2_fmeasure": 0.19402158147865167, "rouge2_fmeasure_stderr": 0.0017876994973534497, "rouge2_precision": 0.24631251817723201, "rouge2_precision_stderr": 0.002657555991369566, "rouge2_recall": 0.17787346956272435, "rouge2_recall_stderr": 0.001792217462473695, "rougeL_fmeasure": 0.3009842944910936, "rougeL_fmeasure_stderr": 0.0018055725861154817, "rougeL_precision": 0.37299125515052484, "rougeL_precision_stderr": 0.002815154394732632, "rougeL_recall": 0.27850203471081203, "rougeL_recall_stderr": 0.002038628599689064, "rougeLsum_fmeasure": 0.3425854571657328, "rougeLsum_fmeasure_stderr": 0.0020124639191903327, "rougeLsum_precision": 0.42379837225389067, "rougeLsum_precision_stderr": 0.0031034115053880863, "rougeLsum_recall": 0.31679500554979756, "rougeLsum_recall_stderr": 0.002259000761426462}}}, "gem_xsum": {"0": {"article_DOC_summary": {"bleu": 0.711911214189282, "bleu_stderr": 0.062271095680873176, "rouge1_fmeasure": 0.11144536072130062, "rouge1_fmeasure_stderr": 0.002449613618907836, "rouge1_precision": 0.08057623396604993, "rouge1_precision_stderr": 0.0018427190672612415, "rouge1_recall": 0.1903611222785915, "rouge1_recall_stderr": 0.004119319495363413, "rouge2_fmeasure": 0.01730052045113504, "rouge2_fmeasure_stderr": 0.0010550283614850532, "rouge2_precision": 0.012439638488265747, "rouge2_precision_stderr": 0.0007674450472725088, "rouge2_recall": 0.029923546174765742, "rouge2_recall_stderr": 0.0018325311907880977, "rougeL_fmeasure": 0.09482469984719238, "rougeL_fmeasure_stderr": 0.001891115330305303, "rougeL_precision": 0.06836163772266587, "rougeL_precision_stderr": 0.001418824283099982, "rougeL_recall": 0.16290273051352785, "rougeL_recall_stderr": 0.0032456160924942976, "rougeLsum_fmeasure": 0.09329416183941738, "rougeLsum_fmeasure_stderr": 0.0019565438808381327, "rougeLsum_precision": 0.06720724706425169, "rougeLsum_precision_stderr": 0.001458820899362241, "rougeLsum_recall": 0.16056752379802697, "rougeLsum_recall_stderr": 0.003380030301216589}}, "1": {"article_DOC_summary": {"bleu": 0.7485653629026496, "bleu_stderr": 0.10161315249240252, "rouge1_fmeasure": 0.12151658666281231, "rouge1_fmeasure_stderr": 0.0025542911124592704, "rouge1_precision": 0.08658830544513134, "rouge1_precision_stderr": 0.0018612611645494558, "rouge1_recall": 0.21204874097915127, "rouge1_recall_stderr": 0.004437751832600217, "rouge2_fmeasure": 0.019132118327200527, "rouge2_fmeasure_stderr": 0.0010395559026960023, "rouge2_precision": 0.013510304634606875, "rouge2_precision_stderr": 0.0007312649740318255, "rouge2_recall": 0.03415295300257043, "rouge2_recall_stderr": 0.0019425669982816587, "rougeL_fmeasure": 0.09875044840716671, "rougeL_fmeasure_stderr": 0.0018572603815356456, "rougeL_precision": 0.0702987343925042, "rougeL_precision_stderr": 0.0013468612933160927, "rougeL_recall": 0.17295883718094748, "rougeL_recall_stderr": 0.0033149082764143117, "rougeLsum_fmeasure": 0.10073542075586238, "rougeLsum_fmeasure_stderr": 0.002008424522536892, "rougeLsum_precision": 0.07169769773353042, "rougeLsum_precision_stderr": 0.001454220219767976, "rougeLsum_recall": 0.17642520944692217, "rougeLsum_recall_stderr": 0.0035711244979865823}}, "2": {"article_DOC_summary": {"bleu": 1.0047358326681721, "bleu_stderr": 0.07696741647689843, "rouge1_fmeasure": 0.15372555310846955, "rouge1_fmeasure_stderr": 0.0024917036123975646, "rouge1_precision": 0.10919972863971208, "rouge1_precision_stderr": 0.0018326070695569962, "rouge1_recall": 0.27085077984418787, "rouge1_recall_stderr": 0.004340987074007443, "rouge2_fmeasure": 0.026545543337132424, "rouge2_fmeasure_stderr": 0.001202505861016018, "rouge2_precision": 0.018660104842681158, "rouge2_precision_stderr": 0.0008521301906071727, "rouge2_recall": 0.048121178106264206, "rouge2_recall_stderr": 0.002236763054096929, "rougeL_fmeasure": 0.12124448179130719, "rougeL_fmeasure_stderr": 0.0018406701231741705, "rougeL_precision": 0.08598679476507894, "rougeL_precision_stderr": 0.001347479595633704, "rougeL_recall": 0.21491972476150967, "rougeL_recall_stderr": 0.0033319697703370205, "rougeLsum_fmeasure": 0.12600811759241443, "rougeLsum_fmeasure_stderr": 0.002023272430841333, "rougeLsum_precision": 0.08936454412712036, "rougeLsum_precision_stderr": 0.00147707143314301, "rougeLsum_recall": 0.22313932236999878, "rougeLsum_recall_stderr": 0.003637762226705496}}, "3": {"article_DOC_summary": {"bleu": 1.3876528749760366, "bleu_stderr": 0.09352517366139018, "rouge1_fmeasure": 0.16788870363340208, "rouge1_fmeasure_stderr": 0.0026015869149755492, "rouge1_precision": 0.12156176985300436, "rouge1_precision_stderr": 0.0019916743006548566, "rouge1_recall": 0.2919486745230574, "rouge1_recall_stderr": 0.004594202930152972, "rouge2_fmeasure": 0.03291830334125208, "rouge2_fmeasure_stderr": 0.0013348595001679636, "rouge2_precision": 0.023390561110934703, "rouge2_precision_stderr": 0.0009482124699139898, "rouge2_recall": 0.05931283277905219, "rouge2_recall_stderr": 0.00253961685376344, "rougeL_fmeasure": 0.12998891345659275, "rougeL_fmeasure_stderr": 0.00194502365003499, "rougeL_precision": 0.09410425031338661, "rougeL_precision_stderr": 0.001505615984367887, "rougeL_recall": 0.22729829891507616, "rougeL_recall_stderr": 0.0035793671647219765, "rougeLsum_fmeasure": 0.13536430596241408, "rougeLsum_fmeasure_stderr": 0.0020963457328233175, "rougeLsum_precision": 0.09794367331761664, "rougeLsum_precision_stderr": 0.0016077634502078913, "rougeLsum_recall": 0.23679450093245694, "rougeLsum_recall_stderr": 0.003856459984346274}}, "4": {"article_DOC_summary": {"bleu": 0.8091606018729823, "bleu_stderr": 0.13365493953263705, "rouge1_fmeasure": 0.04817132624367883, "rouge1_fmeasure_stderr": 0.002710318861619294, "rouge1_precision": 0.04061391536633297, "rouge1_precision_stderr": 0.0025885117246031656, "rouge1_recall": 0.0774019664424454, "rouge1_recall_stderr": 0.004501264779451914, "rouge2_fmeasure": 0.010104068388385765, "rouge2_fmeasure_stderr": 0.0009810253225945517, "rouge2_precision": 0.007571424737600509, "rouge2_precision_stderr": 0.000774569805719568, "rouge2_recall": 0.017306355810365114, "rouge2_recall_stderr": 0.0017078169253319931, "rougeL_fmeasure": 0.03758941214391744, "rougeL_fmeasure_stderr": 0.002107269506833207, "rougeL_precision": 0.03226926320041072, "rougeL_precision_stderr": 0.0021853447839680425, "rougeL_recall": 0.0606544963878778, "rougeL_recall_stderr": 0.0035695265285015203, "rougeLsum_fmeasure": 0.03925168824333697, "rougeLsum_fmeasure_stderr": 0.0022220799806552142, "rougeLsum_precision": 0.03361123521194327, "rougeLsum_precision_stderr": 0.002255713167385482, "rougeLsum_recall": 0.063038545340123, "rougeLsum_recall_stderr": 0.003730201727070476}}, "5": {"article_DOC_summary": {"bleu": 2.9417748605436574e-39, "bleu_stderr": 1.644365126953672e-33, "rouge1_fmeasure": 0.002218415772902317, "rouge1_fmeasure_stderr": 0.0005977307451849004, "rouge1_precision": 0.0025292500918997793, "rouge1_precision_stderr": 0.0006843948420078455, "rouge1_recall": 0.0020532297175197265, "rouge1_recall_stderr": 0.0005556296741534733, "rouge2_fmeasure": 0.00041371259854665804, "rouge2_fmeasure_stderr": 0.0002415623180229552, "rouge2_precision": 0.0004376650603065697, "rouge2_precision_stderr": 0.00024169751059179606, "rouge2_recall": 0.00040004436924525715, "rouge2_recall_stderr": 0.0002447488200268485, "rougeL_fmeasure": 0.0018828340816919485, "rougeL_fmeasure_stderr": 0.0005121954193145257, "rougeL_precision": 0.0021231909904583543, "rougeL_precision_stderr": 0.0005742362353931501, "rougeL_recall": 0.0017609197535564964, "rougeL_recall_stderr": 0.0004851127145778472, "rougeLsum_fmeasure": 0.0019227239855572795, "rougeLsum_fmeasure_stderr": 0.0005197852399034371, "rougeLsum_precision": 0.002170837264519722, "rougeLsum_precision_stderr": 0.0005838940116621144, "rougeLsum_recall": 0.0017952250708806817, "rougeLsum_recall_stderr": 0.0004910386484249093}}}}