Muennighoff's picture
Add
29393c3
{"GEM/web_nlg_en": {"0": {"PALM_prompt": {"bleu": 0.38932054005592026, "bleu_stderr": 0.033555755060432874, "rouge1_fmeasure": 0.11567054917865605, "rouge1_fmeasure_stderr": 0.0020244917898064024, "rouge1_precision": 0.07700762746532616, "rouge1_precision_stderr": 0.0017574979074395903, "rouge1_recall": 0.32659511083930237, "rouge1_recall_stderr": 0.004731650619590043, "rouge2_fmeasure": 0.05486406523084765, "rouge2_fmeasure_stderr": 0.001296868906653324, "rouge2_precision": 0.03638446401446654, "rouge2_precision_stderr": 0.0010787709184703832, "rouge2_recall": 0.16083759865432445, "rouge2_recall_stderr": 0.003301779480848987, "rougeL_fmeasure": 0.1109504406851204, "rougeL_fmeasure_stderr": 0.0018678472410080015, "rougeL_precision": 0.07349742960861025, "rougeL_precision_stderr": 0.0015742317195240577, "rougeL_recall": 0.3166189013286804, "rougeL_recall_stderr": 0.004624777728623184, "rougeLsum_fmeasure": 0.10923439857735848, "rougeLsum_fmeasure_stderr": 0.0018915212851263181, "rougeLsum_precision": 0.07279482633328832, "rougeLsum_precision_stderr": 0.0016761377220670234, "rougeLsum_recall": 0.3093845485351636, "rougeLsum_recall_stderr": 0.0044227058124167145}}, "1": {"PALM_prompt": {"bleu": 0.4010897789440996, "bleu_stderr": 0.035896717451801716, "rouge1_fmeasure": 0.11699641676828608, "rouge1_fmeasure_stderr": 0.0019738238820560176, "rouge1_precision": 0.07680237479305678, "rouge1_precision_stderr": 0.0015098564819853281, "rouge1_recall": 0.33534169873311565, "rouge1_recall_stderr": 0.004781931847971189, "rouge2_fmeasure": 0.055756584513908414, "rouge2_fmeasure_stderr": 0.001272076817653578, "rouge2_precision": 0.03628266659322727, "rouge2_precision_stderr": 0.000933027012126572, "rouge2_recall": 0.16628641951511963, "rouge2_recall_stderr": 0.0033828151468031586, "rougeL_fmeasure": 0.11218413128284264, "rougeL_fmeasure_stderr": 0.0018370252279043208, "rougeL_precision": 0.07343722417982688, "rougeL_precision_stderr": 0.0013890074049552911, "rougeL_recall": 0.3242524897206685, "rougeL_recall_stderr": 0.004652592170560419, "rougeLsum_fmeasure": 0.11118263806943471, "rougeLsum_fmeasure_stderr": 0.00186587403392927, "rougeLsum_precision": 0.07304381756570862, "rougeLsum_precision_stderr": 0.0014318516789194186, "rougeLsum_recall": 0.31848926688825263, "rougeLsum_recall_stderr": 0.004464167390774732}}, "2": {"PALM_prompt": {"bleu": 0.42050495009420186, "bleu_stderr": 0.032401125485335705, "rouge1_fmeasure": 0.11702064522926466, "rouge1_fmeasure_stderr": 0.0019445019569898875, "rouge1_precision": 0.07641858629031524, "rouge1_precision_stderr": 0.001512634713162659, "rouge1_recall": 0.33877843978124605, "rouge1_recall_stderr": 0.004754821881470426, "rouge2_fmeasure": 0.05594462621018749, "rouge2_fmeasure_stderr": 0.0012491415665991895, "rouge2_precision": 0.036264403146498855, "rouge2_precision_stderr": 0.0009035954944938369, "rouge2_recall": 0.1690812614534248, "rouge2_recall_stderr": 0.003434599850442417, "rougeL_fmeasure": 0.11189801577003984, "rougeL_fmeasure_stderr": 0.0018101065557781222, "rougeL_precision": 0.07283896117332733, "rougeL_precision_stderr": 0.0013782370339395086, "rougeL_recall": 0.3264281887874627, "rougeL_recall_stderr": 0.004614214472784931, "rougeLsum_fmeasure": 0.11116640622510127, "rougeLsum_fmeasure_stderr": 0.0018282586995381895, "rougeLsum_precision": 0.07258450279456244, "rougeLsum_precision_stderr": 0.001408393730596637, "rougeLsum_recall": 0.3215563384939613, "rougeLsum_recall_stderr": 0.004418413263595925}}, "3": {"PALM_prompt": {"bleu": 0.4159282397373365, "bleu_stderr": 0.028655242365073413, "rouge1_fmeasure": 0.11669978392247876, "rouge1_fmeasure_stderr": 0.001947629137421236, "rouge1_precision": 0.07708995134838893, "rouge1_precision_stderr": 0.0016510440818257972, "rouge1_recall": 0.3354474085870324, "rouge1_recall_stderr": 0.00468185355577616, "rouge2_fmeasure": 0.05573726170555429, "rouge2_fmeasure_stderr": 0.001260032003769061, "rouge2_precision": 0.036292243594643316, "rouge2_precision_stderr": 0.0009640743250760637, "rouge2_recall": 0.1671806366343255, "rouge2_recall_stderr": 0.0033800199116181236, "rougeL_fmeasure": 0.11124128735569962, "rougeL_fmeasure_stderr": 0.0018188725421961862, "rougeL_precision": 0.07334583374730402, "rougeL_precision_stderr": 0.0015569789464435146, "rougeL_recall": 0.3219883012710275, "rougeL_recall_stderr": 0.004531388461994007, "rougeLsum_fmeasure": 0.1105408760944851, "rougeLsum_fmeasure_stderr": 0.0018355827239676303, "rougeLsum_precision": 0.0731288278640945, "rougeLsum_precision_stderr": 0.001584414887403581, "rougeLsum_recall": 0.3175376346502283, "rougeLsum_recall_stderr": 0.004360960463880489}}, "4": {"PALM_prompt": {"bleu": 0.45977953222907975, "bleu_stderr": 0.040383389212127606, "rouge1_fmeasure": 0.12037862744280613, "rouge1_fmeasure_stderr": 0.0019934979793417573, "rouge1_precision": 0.07912418599977926, "rouge1_precision_stderr": 0.0016198563555509216, "rouge1_recall": 0.3469232249585729, "rouge1_recall_stderr": 0.004748846708374396, "rouge2_fmeasure": 0.057885613023243146, "rouge2_fmeasure_stderr": 0.0012856906291534122, "rouge2_precision": 0.03786394920640546, "rouge2_precision_stderr": 0.0009914452911534558, "rouge2_recall": 0.1738267805541333, "rouge2_recall_stderr": 0.0034485131641693997, "rougeL_fmeasure": 0.11423756257112685, "rougeL_fmeasure_stderr": 0.001835936651182981, "rougeL_precision": 0.07493423869370922, "rougeL_precision_stderr": 0.001498740213643017, "rougeL_recall": 0.3315897347595549, "rougeL_recall_stderr": 0.004565989220241603, "rougeLsum_fmeasure": 0.11380829873927818, "rougeLsum_fmeasure_stderr": 0.001868863082530539, "rougeLsum_precision": 0.07489164236007877, "rougeLsum_precision_stderr": 0.0015400968477694266, "rougeLsum_recall": 0.32772172422348506, "rougeLsum_recall_stderr": 0.0044015503137291995}}, "5": {"PALM_prompt": {"bleu": 0.4100101691229707, "bleu_stderr": 0.038169326985519704, "rouge1_fmeasure": 0.11616969508673808, "rouge1_fmeasure_stderr": 0.001954781890870284, "rouge1_precision": 0.0761749476924903, "rouge1_precision_stderr": 0.0015866409368917428, "rouge1_recall": 0.33694404520159127, "rouge1_recall_stderr": 0.004725880718920406, "rouge2_fmeasure": 0.055555746394993916, "rouge2_fmeasure_stderr": 0.0012524254498175414, "rouge2_precision": 0.03627352196162682, "rouge2_precision_stderr": 0.000977188491579374, "rouge2_recall": 0.167813784642509, "rouge2_recall_stderr": 0.0033985471522842725, "rougeL_fmeasure": 0.11092231794095461, "rougeL_fmeasure_stderr": 0.0018208627331043194, "rougeL_precision": 0.07259356194973668, "rougeL_precision_stderr": 0.0014842070922326297, "rougeL_recall": 0.3238850222294547, "rougeL_recall_stderr": 0.00455273082293743, "rougeLsum_fmeasure": 0.11030205012975042, "rougeLsum_fmeasure_stderr": 0.0018300168280422182, "rougeLsum_precision": 0.07239284886715931, "rougeLsum_precision_stderr": 0.0015076194366894973, "rougeLsum_recall": 0.3201817418126636, "rougeLsum_recall_stderr": 0.004401296672435449}}}, "GEM/wiki_lingua_en": {"0": {"tldr_en": {"bleu": 0.06823499187294975, "bleu_stderr": 0.02672839530839174, "rouge1_fmeasure": 0.09998460503837092, "rouge1_fmeasure_stderr": 0.0010700519248261517, "rouge1_precision": 0.09250196886098348, "rouge1_precision_stderr": 0.0012387826019604092, "rouge1_recall": 0.12905376314562253, "rouge1_recall_stderr": 0.0013091825113428792, "rouge2_fmeasure": 0.004548025347793951, "rouge2_fmeasure_stderr": 0.00021301188784611375, "rouge2_precision": 0.004542792640061134, "rouge2_precision_stderr": 0.00021902406054084622, "rouge2_recall": 0.005267988260289562, "rouge2_recall_stderr": 0.0002641606109254951, "rougeL_fmeasure": 0.0884294786747584, "rougeL_fmeasure_stderr": 0.0008862698881090451, "rougeL_precision": 0.0806751359892451, "rougeL_precision_stderr": 0.000988255429146176, "rougeL_recall": 0.11638678461084004, "rougeL_recall_stderr": 0.0011920958367752498, "rougeLsum_fmeasure": 0.09653806771590727, "rougeLsum_fmeasure_stderr": 0.0010284292205864202, "rougeLsum_precision": 0.08931760733909207, "rougeLsum_precision_stderr": 0.0011977856331501172, "rougeLsum_recall": 0.12471118748837833, "rougeLsum_recall_stderr": 0.0012621097866983477}}, "1": {"tldr_en": {"bleu": 0.627587943269457, "bleu_stderr": 0.03752664558072816, "rouge1_fmeasure": 0.1176727050001766, "rouge1_fmeasure_stderr": 0.0015061256733290465, "rouge1_precision": 0.10227535255850072, "rouge1_precision_stderr": 0.0015211441148919019, "rouge1_recall": 0.1666238343075504, "rouge1_recall_stderr": 0.002113191459192441, "rouge2_fmeasure": 0.011758190082089873, "rouge2_fmeasure_stderr": 0.0005161253570713452, "rouge2_precision": 0.010133390687879478, "rouge2_precision_stderr": 0.00045221775358988313, "rouge2_recall": 0.017278009943298343, "rouge2_recall_stderr": 0.0008307221313804175, "rougeL_fmeasure": 0.0977465022371193, "rougeL_fmeasure_stderr": 0.0010778296010975216, "rougeL_precision": 0.0840035133484757, "rougeL_precision_stderr": 0.00108582843746046, "rougeL_recall": 0.1409822252220471, "rougeL_recall_stderr": 0.0016244906370306395, "rougeLsum_fmeasure": 0.11014610167130383, "rougeLsum_fmeasure_stderr": 0.0014009647264510289, "rougeLsum_precision": 0.09563245107317732, "rougeLsum_precision_stderr": 0.0014144569423562025, "rougeLsum_recall": 0.15636027194288163, "rougeLsum_recall_stderr": 0.001975628206486446}}, "2": {"tldr_en": {"bleu": 1.3448790104080863, "bleu_stderr": 0.06809231563626762, "rouge1_fmeasure": 0.15805650713785413, "rouge1_fmeasure_stderr": 0.0019004938271445784, "rouge1_precision": 0.13533522102182108, "rouge1_precision_stderr": 0.0018951373520473378, "rouge1_recall": 0.22856932435608124, "rouge1_recall_stderr": 0.0027080432167508025, "rouge2_fmeasure": 0.02760738077834664, "rouge2_fmeasure_stderr": 0.0008049340257416579, "rouge2_precision": 0.023543013388107385, "rouge2_precision_stderr": 0.000717310361867752, "rouge2_recall": 0.040832806012490945, "rouge2_recall_stderr": 0.001298377746871254, "rougeL_fmeasure": 0.12169470238796481, "rougeL_fmeasure_stderr": 0.0012563483854001994, "rougeL_precision": 0.10293794994726356, "rougeL_precision_stderr": 0.0012437549972814086, "rougeL_recall": 0.1802214254693049, "rougeL_recall_stderr": 0.0020107380760737443, "rougeLsum_fmeasure": 0.14735538469349385, "rougeLsum_fmeasure_stderr": 0.0017649380102418163, "rougeLsum_precision": 0.12611401083224677, "rougeLsum_precision_stderr": 0.0017609062395669717, "rougeLsum_recall": 0.21348564535890185, "rougeLsum_recall_stderr": 0.0025299144255695695}}, "3": {"tldr_en": {"bleu": 1.528039320029562, "bleu_stderr": 0.036905573594762583, "rouge1_fmeasure": 0.14320563335091396, "rouge1_fmeasure_stderr": 0.0020698343768995294, "rouge1_precision": 0.12776173884849967, "rouge1_precision_stderr": 0.002166703255999288, "rouge1_recall": 0.2075725639546676, "rouge1_recall_stderr": 0.0030329813736934214, "rouge2_fmeasure": 0.026283043574202986, "rouge2_fmeasure_stderr": 0.0008159202511212215, "rouge2_precision": 0.022636857885145915, "rouge2_precision_stderr": 0.0007440116219601286, "rouge2_recall": 0.0397256121665061, "rouge2_recall_stderr": 0.001322773196274425, "rougeL_fmeasure": 0.10883270044311108, "rougeL_fmeasure_stderr": 0.0014339155970440763, "rougeL_precision": 0.09657179764839124, "rougeL_precision_stderr": 0.0015732121770481863, "rougeL_recall": 0.16159908811630536, "rougeL_recall_stderr": 0.0023213429955332913, "rougeLsum_fmeasure": 0.13283753381327199, "rougeLsum_fmeasure_stderr": 0.0019146305178959213, "rougeLsum_precision": 0.11866324620879036, "rougeLsum_precision_stderr": 0.0020254088359404664, "rougeLsum_recall": 0.19292621911672542, "rougeLsum_recall_stderr": 0.002834333227053115}}, "4": {"tldr_en": {"bleu": 0.37223171728306426, "bleu_stderr": 0.03014516594133762, "rouge1_fmeasure": 0.04899842107573778, "rouge1_fmeasure_stderr": 0.0017104674234628445, "rouge1_precision": 0.04598706351137218, "rouge1_precision_stderr": 0.0018221188645625001, "rouge1_recall": 0.0739807986804339, "rouge1_recall_stderr": 0.002646171903509083, "rouge2_fmeasure": 0.009690319746932921, "rouge2_fmeasure_stderr": 0.0005414022669991509, "rouge2_precision": 0.008841756168682364, "rouge2_precision_stderr": 0.0006116495968030462, "rouge2_recall": 0.015468257674774097, "rouge2_recall_stderr": 0.0009624564354622926, "rougeL_fmeasure": 0.03836996592095654, "rougeL_fmeasure_stderr": 0.0012956784650356502, "rougeL_precision": 0.03612427764892416, "rougeL_precision_stderr": 0.0014536883711277432, "rougeL_recall": 0.05940229969748619, "rougeL_recall_stderr": 0.002132196101860115, "rougeLsum_fmeasure": 0.04519059371598313, "rougeLsum_fmeasure_stderr": 0.001579759147906247, "rougeLsum_precision": 0.04261326941140918, "rougeLsum_precision_stderr": 0.0017129168307166089, "rougeLsum_recall": 0.06810975113263097, "rougeLsum_recall_stderr": 0.0024407540230673218}}, "5": {"tldr_en": {"bleu": 5.013143696035085e-07, "bleu_stderr": 9.50150744136576e-07, "rouge1_fmeasure": 0.007820849054110231, "rouge1_fmeasure_stderr": 0.0007600843285544493, "rouge1_precision": 0.007551294746242374, "rouge1_precision_stderr": 0.0008016066090893644, "rouge1_recall": 0.01175212455089267, "rouge1_recall_stderr": 0.0011644529839797179, "rouge2_fmeasure": 0.001550055750323692, "rouge2_fmeasure_stderr": 0.0002154946138593672, "rouge2_precision": 0.0014154766947717414, "rouge2_precision_stderr": 0.00021722050245300052, "rouge2_recall": 0.002696191748609163, "rouge2_recall_stderr": 0.0004898145017501464, "rougeL_fmeasure": 0.006164411990577186, "rougeL_fmeasure_stderr": 0.0005772505558321714, "rougeL_precision": 0.005847845224705761, "rougeL_precision_stderr": 0.000595323185000189, "rougeL_recall": 0.009647797063887112, "rougeL_recall_stderr": 0.0009660140204759589, "rougeLsum_fmeasure": 0.007179693639002067, "rougeLsum_fmeasure_stderr": 0.0006977167152892271, "rougeLsum_precision": 0.006936670272296256, "rougeLsum_precision_stderr": 0.0007360722546012934, "rougeLsum_recall": 0.010824451468983412, "rougeLsum_recall_stderr": 0.0010820316072561469}}}, "e2e_nlg_cleaned": {"0": {"generate_text_restaurant": {"bleu": 0.09084719792363964, "bleu_stderr": 0.023524182784253476, "rouge1_fmeasure": 0.016457051237123384, "rouge1_fmeasure_stderr": 0.0003925090249226089, "rouge1_precision": 0.013115055244320387, "rouge1_precision_stderr": 0.0003168780725030529, "rouge1_recall": 0.023423577684344953, "rouge1_recall_stderr": 0.0005821108276955901, "rouge2_fmeasure": 0.0003989196235540006, "rouge2_fmeasure_stderr": 0.00010791151592722659, "rouge2_precision": 0.0003338211382113822, "rouge2_precision_stderr": 8.920509387302503e-05, "rouge2_recall": 0.0005083527300182993, "rouge2_recall_stderr": 0.00013811375079865392, "rougeL_fmeasure": 0.016457051237123384, "rougeL_fmeasure_stderr": 0.0003925090249226089, "rougeL_precision": 0.013115055244320387, "rougeL_precision_stderr": 0.0003168780725030529, "rougeL_recall": 0.023423577684344953, "rougeL_recall_stderr": 0.0005821108276955901, "rougeLsum_fmeasure": 0.015885414699151633, "rougeLsum_fmeasure_stderr": 0.00036971385737970014, "rougeLsum_precision": 0.012659903516962778, "rougeLsum_precision_stderr": 0.00029850433041728446, "rougeLsum_recall": 0.0226118934358276, "rougeLsum_recall_stderr": 0.0005511022657739085}}, "1": {"generate_text_restaurant": {"bleu": 8.493656512933155, "bleu_stderr": 0.06507341585485718, "rouge1_fmeasure": 0.38211667792792864, "rouge1_fmeasure_stderr": 0.002042530024715172, "rouge1_precision": 0.3973818846475776, "rouge1_precision_stderr": 0.0026976072721873632, "rouge1_recall": 0.4223117985183209, "rouge1_recall_stderr": 0.002783358808801643, "rouge2_fmeasure": 0.16014559457551358, "rouge2_fmeasure_stderr": 0.0014918368862659674, "rouge2_precision": 0.16992657792281268, "rouge2_precision_stderr": 0.0019145879314252548, "rouge2_recall": 0.178124519625553, "rouge2_recall_stderr": 0.0018587557359939306, "rougeL_fmeasure": 0.2656366947575347, "rougeL_fmeasure_stderr": 0.00154921779515304, "rougeL_precision": 0.2784440754511285, "rougeL_precision_stderr": 0.002173881277475784, "rougeL_recall": 0.2960008580013917, "rougeL_recall_stderr": 0.00223721376663644, "rougeLsum_fmeasure": 0.3191928781032716, "rougeLsum_fmeasure_stderr": 0.0018752599773732524, "rougeLsum_precision": 0.33386523672528523, "rougeLsum_precision_stderr": 0.002495920334450439, "rougeLsum_recall": 0.3524456027280379, "rougeLsum_recall_stderr": 0.00250316491749807}}, "2": {"generate_text_restaurant": {"bleu": 9.70861649242996, "bleu_stderr": 0.180728212256743, "rouge1_fmeasure": 0.4028985936075782, "rouge1_fmeasure_stderr": 0.0019913008996638617, "rouge1_precision": 0.4246829342811345, "rouge1_precision_stderr": 0.002766857681080391, "rouge1_recall": 0.42902360153249547, "rouge1_recall_stderr": 0.0026637334370122148, "rouge2_fmeasure": 0.17685301250165733, "rouge2_fmeasure_stderr": 0.0015810873135005685, "rouge2_precision": 0.188091439420101, "rouge2_precision_stderr": 0.0019527339746865022, "rouge2_recall": 0.18884241914729302, "rouge2_recall_stderr": 0.001866659004782858, "rougeL_fmeasure": 0.28212495177649627, "rougeL_fmeasure_stderr": 0.0016022344134082288, "rougeL_precision": 0.2982294118028583, "rougeL_precision_stderr": 0.0022177478762698505, "rougeL_recall": 0.3014772250776991, "rougeL_recall_stderr": 0.0021343172062020443, "rougeLsum_fmeasure": 0.33457230441540664, "rougeLsum_fmeasure_stderr": 0.0018977411692316212, "rougeLsum_precision": 0.3532941586993858, "rougeLsum_precision_stderr": 0.002547817337684264, "rougeLsum_recall": 0.3559974321347138, "rougeLsum_recall_stderr": 0.0024336261264831867}}, "3": {"generate_text_restaurant": {"bleu": 9.966588735110538, "bleu_stderr": 0.12599090386040324, "rouge1_fmeasure": 0.4068505832141505, "rouge1_fmeasure_stderr": 0.0019329494846097367, "rouge1_precision": 0.42159026565077223, "rouge1_precision_stderr": 0.002651117861201503, "rouge1_recall": 0.436277297035412, "rouge1_recall_stderr": 0.0026416756972084655, "rouge2_fmeasure": 0.17997150688916153, "rouge2_fmeasure_stderr": 0.001592406273022251, "rouge2_precision": 0.18776315928969667, "rouge2_precision_stderr": 0.0018907826120837835, "rouge2_recall": 0.19380136137444595, "rouge2_recall_stderr": 0.0019180421049331063, "rougeL_fmeasure": 0.28424346982191884, "rougeL_fmeasure_stderr": 0.0016109414932517093, "rougeL_precision": 0.2954653149171501, "rougeL_precision_stderr": 0.002167984706061261, "rougeL_recall": 0.30557723457112207, "rougeL_recall_stderr": 0.0021619718205346107, "rougeLsum_fmeasure": 0.3401366732280647, "rougeLsum_fmeasure_stderr": 0.0018580545934390128, "rougeLsum_precision": 0.3525432765457679, "rougeLsum_precision_stderr": 0.0024285145519395723, "rougeLsum_recall": 0.3651612369599634, "rougeLsum_recall_stderr": 0.0024667743399167472}}, "4": {"generate_text_restaurant": {"bleu": 9.251162519243813, "bleu_stderr": 0.16043314004667306, "rouge1_fmeasure": 0.3969692723001995, "rouge1_fmeasure_stderr": 0.0019731818045355485, "rouge1_precision": 0.40242023070868665, "rouge1_precision_stderr": 0.0027480602148687965, "rouge1_recall": 0.436755013677424, "rouge1_recall_stderr": 0.002566467851228464, "rouge2_fmeasure": 0.17289054467515227, "rouge2_fmeasure_stderr": 0.00158925330122968, "rouge2_precision": 0.176937710453779, "rouge2_precision_stderr": 0.0019212015420408378, "rouge2_recall": 0.19058682088957968, "rouge2_recall_stderr": 0.0018838368515368652, "rougeL_fmeasure": 0.2734957726548441, "rougeL_fmeasure_stderr": 0.0016372934907566048, "rougeL_precision": 0.2782288135889908, "rougeL_precision_stderr": 0.002208420858744797, "rougeL_recall": 0.30117513507531163, "rougeL_recall_stderr": 0.002108417735667974, "rougeLsum_fmeasure": 0.33022165481719784, "rougeLsum_fmeasure_stderr": 0.001911613908677662, "rougeLsum_precision": 0.3343952904639146, "rougeLsum_precision_stderr": 0.0024871514512787504, "rougeLsum_recall": 0.36379303588555467, "rougeLsum_recall_stderr": 0.0024348682831782293}}, "5": {"generate_text_restaurant": {"bleu": 8.324834183472209, "bleu_stderr": 0.12201022191511865, "rouge1_fmeasure": 0.3826658470581734, "rouge1_fmeasure_stderr": 0.0019397433080247473, "rouge1_precision": 0.3770667876954104, "rouge1_precision_stderr": 0.002761667549229222, "rouge1_recall": 0.4384978042745568, "rouge1_recall_stderr": 0.002504170522982392, "rouge2_fmeasure": 0.1633047480034024, "rouge2_fmeasure_stderr": 0.0015591168107894247, "rouge2_precision": 0.16298069992158787, "rouge2_precision_stderr": 0.001917959278145272, "rouge2_recall": 0.18727836348007232, "rouge2_recall_stderr": 0.0018506477395530997, "rougeL_fmeasure": 0.2662588358520316, "rougeL_fmeasure_stderr": 0.0016519997409068458, "rougeL_precision": 0.263196349500877, "rougeL_precision_stderr": 0.002234840925291514, "rougeL_recall": 0.30529924132930725, "rougeL_recall_stderr": 0.0021085926401520298, "rougeLsum_fmeasure": 0.3210382724978914, "rougeLsum_fmeasure_stderr": 0.0018713242691196597, "rougeLsum_precision": 0.3161706099613126, "rougeLsum_precision_stderr": 0.002502426291497884, "rougeLsum_recall": 0.36828376734500556, "rougeLsum_recall_stderr": 0.002374793122680808}}}, "gem_xsum": {"0": {"article_DOC_summary": {"bleu": 0.050773439614255005, "bleu_stderr": 0.009607935815050534, "rouge1_fmeasure": 0.10525034871077296, "rouge1_fmeasure_stderr": 0.0014205929613240243, "rouge1_precision": 0.07457722326961545, "rouge1_precision_stderr": 0.0010813149665918967, "rouge1_recall": 0.18616767062678954, "rouge1_recall_stderr": 0.0023262601944921035, "rouge2_fmeasure": 0.005853296742054689, "rouge2_fmeasure_stderr": 0.0003595212542050643, "rouge2_precision": 0.004128841009305119, "rouge2_precision_stderr": 0.00025477847907952686, "rouge2_recall": 0.01051230796440712, "rouge2_recall_stderr": 0.0006602646260890872, "rougeL_fmeasure": 0.0912182400057594, "rougeL_fmeasure_stderr": 0.001142160193884147, "rougeL_precision": 0.06451608999455927, "rougeL_precision_stderr": 0.0008702064411682341, "rougeL_recall": 0.1622598214643354, "rougeL_recall_stderr": 0.0019407556202309798, "rougeLsum_fmeasure": 0.08935271982090909, "rougeLsum_fmeasure_stderr": 0.001186659250809151, "rougeLsum_precision": 0.06318245796876595, "rougeLsum_precision_stderr": 0.0008975507843696847, "rougeLsum_recall": 0.15913828904970537, "rougeLsum_recall_stderr": 0.002044934654600564}}, "1": {"article_DOC_summary": {"bleu": 0.37658580921002954, "bleu_stderr": 0.03383903342773015, "rouge1_fmeasure": 0.11065247004530705, "rouge1_fmeasure_stderr": 0.0017812843994385369, "rouge1_precision": 0.07879837485772763, "rouge1_precision_stderr": 0.0013599444284337506, "rouge1_recall": 0.19465714656847785, "rouge1_recall_stderr": 0.0029003189713371035, "rouge2_fmeasure": 0.009780488414863557, "rouge2_fmeasure_stderr": 0.0006426504271738838, "rouge2_precision": 0.006994168819790609, "rouge2_precision_stderr": 0.0004648272193447288, "rouge2_recall": 0.017050685879784068, "rouge2_recall_stderr": 0.0011197895634276233, "rougeL_fmeasure": 0.0932686816822836, "rougeL_fmeasure_stderr": 0.001351090628116566, "rougeL_precision": 0.06626180423614893, "rougeL_precision_stderr": 0.00103152044172589, "rougeL_recall": 0.16506949443493862, "rougeL_recall_stderr": 0.002243999574785469, "rougeLsum_fmeasure": 0.09068800328595211, "rougeLsum_fmeasure_stderr": 0.0014406209430729104, "rougeLsum_precision": 0.06443833252424745, "rougeLsum_precision_stderr": 0.0010900785870787669, "rougeLsum_recall": 0.1605294884501161, "rougeLsum_recall_stderr": 0.0024099921996914896}}, "2": {"article_DOC_summary": {"bleu": 0.5613289650024746, "bleu_stderr": 0.06954224370193056, "rouge1_fmeasure": 0.12480432119777549, "rouge1_fmeasure_stderr": 0.0021054789997765754, "rouge1_precision": 0.0889047742823774, "rouge1_precision_stderr": 0.0015736385663893536, "rouge1_recall": 0.21871321971864371, "rouge1_recall_stderr": 0.003489898707290529, "rouge2_fmeasure": 0.013892927856252131, "rouge2_fmeasure_stderr": 0.0009041385431726432, "rouge2_precision": 0.009892665457522843, "rouge2_precision_stderr": 0.0006521664121306877, "rouge2_recall": 0.02437366955189581, "rouge2_recall_stderr": 0.0015659961501778526, "rougeL_fmeasure": 0.1015360359782745, "rougeL_fmeasure_stderr": 0.0015523847061620607, "rougeL_precision": 0.07214973246105617, "rougeL_precision_stderr": 0.00116007366829089, "rougeL_recall": 0.1791872648503229, "rougeL_recall_stderr": 0.002631093758225792, "rougeLsum_fmeasure": 0.10235719035547435, "rougeLsum_fmeasure_stderr": 0.0017287630454853157, "rougeLsum_precision": 0.07278538171522661, "rougeLsum_precision_stderr": 0.001284146511191204, "rougeLsum_recall": 0.18033245428711908, "rougeLsum_recall_stderr": 0.0029284834426938845}}, "3": {"article_DOC_summary": {"bleu": 0.7079488064244481, "bleu_stderr": 0.07074366573560065, "rouge1_fmeasure": 0.12920118195381422, "rouge1_fmeasure_stderr": 0.002284952127981043, "rouge1_precision": 0.09397556603911704, "rouge1_precision_stderr": 0.0017994169570713602, "rouge1_recall": 0.22313205728599414, "rouge1_recall_stderr": 0.0039035927988892247, "rouge2_fmeasure": 0.017334182525631046, "rouge2_fmeasure_stderr": 0.0010127873838950666, "rouge2_precision": 0.01255758062915019, "rouge2_precision_stderr": 0.0007553728961037906, "rouge2_recall": 0.030710887496420355, "rouge2_recall_stderr": 0.0018415895742210585, "rougeL_fmeasure": 0.1039819933524293, "rougeL_fmeasure_stderr": 0.0017400868646152738, "rougeL_precision": 0.07567512644757472, "rougeL_precision_stderr": 0.0013958572399353046, "rougeL_recall": 0.18027261644595613, "rougeL_recall_stderr": 0.003034050646720842, "rougeLsum_fmeasure": 0.10658308430361232, "rougeLsum_fmeasure_stderr": 0.0018787907354694993, "rougeLsum_precision": 0.0775560956207995, "rougeLsum_precision_stderr": 0.0015015791755260772, "rougeLsum_recall": 0.1849635012704667, "rougeLsum_recall_stderr": 0.003277420997428528}}, "4": {"article_DOC_summary": {"bleu": 0.4082429912701259, "bleu_stderr": 0.0779765946109533, "rouge1_fmeasure": 0.03895580700792708, "rouge1_fmeasure_stderr": 0.002269413843476501, "rouge1_precision": 0.03264760362151805, "rouge1_precision_stderr": 0.0020833568971290787, "rouge1_recall": 0.061777608876693486, "rouge1_recall_stderr": 0.0037289394788052755, "rouge2_fmeasure": 0.0051666306699138615, "rouge2_fmeasure_stderr": 0.0005905785787950259, "rouge2_precision": 0.0038550154412843093, "rouge2_precision_stderr": 0.0004446008638460962, "rouge2_recall": 0.009089864083505584, "rouge2_recall_stderr": 0.0010911425483655028, "rougeL_fmeasure": 0.030269389323315635, "rougeL_fmeasure_stderr": 0.0017191936988352017, "rougeL_precision": 0.025565238785773294, "rougeL_precision_stderr": 0.0016418229878507925, "rougeL_recall": 0.04842391895975862, "rougeL_recall_stderr": 0.002904785956254577, "rougeLsum_fmeasure": 0.03182638094199837, "rougeLsum_fmeasure_stderr": 0.001849989660796298, "rougeLsum_precision": 0.026709322906345055, "rougeLsum_precision_stderr": 0.0017170791129193154, "rougeLsum_recall": 0.050929122969953576, "rougeLsum_recall_stderr": 0.0031086814353982915}}, "5": {"article_DOC_summary": {"bleu": 2.3068185785066287e-38, "bleu_stderr": 6.496274000069576e-33, "rouge1_fmeasure": 0.0021817427772383405, "rouge1_fmeasure_stderr": 0.0006550320885850304, "rouge1_precision": 0.002487457924399334, "rouge1_precision_stderr": 0.0007733944656593977, "rouge1_recall": 0.0019894770885392197, "rouge1_recall_stderr": 0.000580222680643798, "rouge2_fmeasure": 0.00026626492060156015, "rouge2_fmeasure_stderr": 0.00019473030694105065, "rouge2_precision": 0.0003335239184295789, "rouge2_precision_stderr": 0.0002474907080024258, "rouge2_recall": 0.00022186932564291056, "rouge2_recall_stderr": 0.00016062217222749233, "rougeL_fmeasure": 0.00163204036870977, "rougeL_fmeasure_stderr": 0.00048037762637480547, "rougeL_precision": 0.0018641694287175915, "rougeL_precision_stderr": 0.0005696317403990395, "rougeL_recall": 0.001490936334422112, "rougeL_recall_stderr": 0.0004262092207690586, "rougeLsum_fmeasure": 0.0016483540386329559, "rougeLsum_fmeasure_stderr": 0.0004762553014171529, "rougeLsum_precision": 0.0018726329116100717, "rougeLsum_precision_stderr": 0.0005610053066563542, "rougeLsum_recall": 0.0015127742100335723, "rougeLsum_recall_stderr": 0.00042560130622958597}}}}