{"GEM/web_nlg_en": {"0": {"PALM_prompt": {"bleu": 0.4358876645741479, "bleu_stderr": 0.04475556276641748, "rouge1_fmeasure": 0.11084365567127677, "rouge1_fmeasure_stderr": 0.0022963454664604076, "rouge1_precision": 0.08601617848273047, "rouge1_precision_stderr": 0.003027222218230607, "rouge1_recall": 0.29226306498620885, "rouge1_recall_stderr": 0.005344776046578116, "rouge2_fmeasure": 0.05146498360167007, "rouge2_fmeasure_stderr": 0.0014277295107541841, "rouge2_precision": 0.04041394987853437, "rouge2_precision_stderr": 0.002132583963194437, "rouge2_recall": 0.1415225530229299, "rouge2_recall_stderr": 0.0034803378779995004, "rougeL_fmeasure": 0.10611300272902285, "rougeL_fmeasure_stderr": 0.002132214334314073, "rougeL_precision": 0.08239970522779808, "rougeL_precision_stderr": 0.0029176133842350504, "rougeL_recall": 0.2827601971319833, "rougeL_recall_stderr": 0.00519215142624447, "rougeLsum_fmeasure": 0.10445493190549919, "rougeLsum_fmeasure_stderr": 0.00215267434014802, "rougeLsum_precision": 0.0815748628057772, "rougeLsum_precision_stderr": 0.002939098844173709, "rougeLsum_recall": 0.2756279858381666, "rougeLsum_recall_stderr": 0.0049864009961195395}}, "1": {"PALM_prompt": {"bleu": 0.6458190048668558, "bleu_stderr": 0.03274318464461181, "rouge1_fmeasure": 0.16170102806244036, "rouge1_fmeasure_stderr": 0.0036142070180597507, "rouge1_precision": 0.13985160542322855, "rouge1_precision_stderr": 0.004374312136397895, "rouge1_recall": 0.32007070778063884, "rouge1_recall_stderr": 0.004962532451445636, "rouge2_fmeasure": 0.07885240324677927, "rouge2_fmeasure_stderr": 0.0023523131620574156, "rouge2_precision": 0.0694179465016437, "rouge2_precision_stderr": 0.002921286815952664, "rouge2_recall": 0.15883761787677303, "rouge2_recall_stderr": 0.003480119679954502, "rougeL_fmeasure": 0.14742576479874345, "rougeL_fmeasure_stderr": 0.0031238502419319854, "rougeL_precision": 0.12591553956133228, "rougeL_precision_stderr": 0.003854734977633317, "rougeL_recall": 0.30061625652088586, "rougeL_recall_stderr": 0.004630766957074663, "rougeLsum_fmeasure": 0.1497000837635611, "rougeLsum_fmeasure_stderr": 0.0032201737172114866, "rougeLsum_precision": 0.1283694931084644, "rougeLsum_precision_stderr": 0.003947705918972332, "rougeLsum_recall": 0.3021994113995889, "rougeLsum_recall_stderr": 0.004647780404212457}}, "2": {"PALM_prompt": {"bleu": 0.7970016196921748, "bleu_stderr": 0.04581096081746233, "rouge1_fmeasure": 0.19703997895188197, "rouge1_fmeasure_stderr": 0.0042195368281687335, "rouge1_precision": 0.18059337363344904, "rouge1_precision_stderr": 0.005339355314623877, "rouge1_recall": 0.3595991748021704, "rouge1_recall_stderr": 0.004980869877485108, "rouge2_fmeasure": 0.10271084479951895, "rouge2_fmeasure_stderr": 0.0029196673345892295, "rouge2_precision": 0.09688101950971822, "rouge2_precision_stderr": 0.0036313101633365223, "rouge2_recall": 0.18755499121707667, "rouge2_recall_stderr": 0.00376908816872013, "rougeL_fmeasure": 0.1772530360597836, "rougeL_fmeasure_stderr": 0.0035959119026034024, "rougeL_precision": 0.15982668252407492, "rougeL_precision_stderr": 0.004603772659928646, "rougeL_recall": 0.3351391580099154, "rougeL_recall_stderr": 0.004585332134390738, "rougeLsum_fmeasure": 0.18084941775566396, "rougeLsum_fmeasure_stderr": 0.0037099919587234576, "rougeLsum_precision": 0.16383301190827276, "rougeLsum_precision_stderr": 0.004742860098171715, "rougeLsum_recall": 0.33868792774850437, "rougeLsum_recall_stderr": 0.004634428210263519}}, "3": {"PALM_prompt": {"bleu": 0.9098079216712224, "bleu_stderr": 0.049900879662925314, "rouge1_fmeasure": 0.20522389412159425, "rouge1_fmeasure_stderr": 0.0043615630325957435, "rouge1_precision": 0.19212508744736018, "rouge1_precision_stderr": 0.005617174437077427, "rouge1_recall": 0.3703600547581712, "rouge1_recall_stderr": 0.004938819064876214, "rouge2_fmeasure": 0.10810375284373198, "rouge2_fmeasure_stderr": 0.003075123686799679, "rouge2_precision": 0.10484577205978293, "rouge2_precision_stderr": 0.003926715523602227, "rouge2_recall": 0.19383710059664028, "rouge2_recall_stderr": 0.003742953011901514, "rougeL_fmeasure": 0.18478247984025434, "rougeL_fmeasure_stderr": 0.003743746721954891, "rougeL_precision": 0.17083343128882605, "rougeL_precision_stderr": 0.004911086258050898, "rougeL_recall": 0.34476103034505623, "rougeL_recall_stderr": 0.004533133149997157, "rougeLsum_fmeasure": 0.18830268691133512, "rougeLsum_fmeasure_stderr": 0.003857827801954891, "rougeLsum_precision": 0.17532235438945584, "rougeLsum_precision_stderr": 0.005084911003429309, "rougeLsum_recall": 0.3483193020595072, "rougeLsum_recall_stderr": 0.0045873162051077825}}, "4": {"PALM_prompt": {"bleu": 1.052600188336286, "bleu_stderr": 0.06665675598684426, "rouge1_fmeasure": 0.21317352472996992, "rouge1_fmeasure_stderr": 0.004401402126159575, "rouge1_precision": 0.20108020030540724, "rouge1_precision_stderr": 0.005644545699403245, "rouge1_recall": 0.3818834779332785, "rouge1_recall_stderr": 0.004965307876320074, "rouge2_fmeasure": 0.1144786865204847, "rouge2_fmeasure_stderr": 0.003126094675218737, "rouge2_precision": 0.11098039808305214, "rouge2_precision_stderr": 0.003927637491564618, "rouge2_recall": 0.204923577311545, "rouge2_recall_stderr": 0.003948475544315969, "rougeL_fmeasure": 0.19087293738824496, "rougeL_fmeasure_stderr": 0.0037489593597534975, "rougeL_precision": 0.1772302061036221, "rougeL_precision_stderr": 0.0048597986989461165, "rougeL_recall": 0.35524087803093607, "rougeL_recall_stderr": 0.004631433081108199, "rougeLsum_fmeasure": 0.19652423173229852, "rougeLsum_fmeasure_stderr": 0.003927577783905062, "rougeLsum_precision": 0.183821519223083, "rougeLsum_precision_stderr": 0.005085692199041701, "rougeLsum_recall": 0.36063124635272004, "rougeLsum_recall_stderr": 0.004673788271599251}}, "5": {"PALM_prompt": {"bleu": 1.0960931080747824, "bleu_stderr": 0.06344656593457922, "rouge1_fmeasure": 0.22442306072164447, "rouge1_fmeasure_stderr": 0.004490024810310396, "rouge1_precision": 0.21325470731107665, "rouge1_precision_stderr": 0.005803174587983953, "rouge1_recall": 0.3950162351216541, "rouge1_recall_stderr": 0.004977496708782323, "rouge2_fmeasure": 0.11914106590715341, "rouge2_fmeasure_stderr": 0.003087212545803013, "rouge2_precision": 0.11715823165872309, "rouge2_precision_stderr": 0.004000375023616823, "rouge2_recall": 0.2112966644324947, "rouge2_recall_stderr": 0.003874637116812206, "rougeL_fmeasure": 0.19921393354497344, "rougeL_fmeasure_stderr": 0.0037728930475513494, "rougeL_precision": 0.1866801247482292, "rougeL_precision_stderr": 0.004986038924327078, "rougeL_recall": 0.36529275376302506, "rougeL_recall_stderr": 0.0045911093135183, "rougeLsum_fmeasure": 0.20449901465956502, "rougeLsum_fmeasure_stderr": 0.003922872033805495, "rougeLsum_precision": 0.1931918251374917, "rougeLsum_precision_stderr": 0.00519492169870331, "rougeLsum_recall": 0.3699764207220656, "rougeLsum_recall_stderr": 0.004618932928096925}}}, "GEM/wiki_lingua_en": {"0": {"tldr_en": {"bleu": 2.278917009551764, "bleu_stderr": 0.09140957868815724, "rouge1_fmeasure": 0.12988512607981967, "rouge1_fmeasure_stderr": 0.0024439343174664525, "rouge1_precision": 0.122915905754568, "rouge1_precision_stderr": 0.0027293510115185423, "rouge1_recall": 0.1767818917839268, "rouge1_recall_stderr": 0.0033841479310980638, "rouge2_fmeasure": 0.03000716115226249, "rouge2_fmeasure_stderr": 0.0009354733970545372, "rouge2_precision": 0.026806616635118036, "rouge2_precision_stderr": 0.0008667140586963389, "rouge2_recall": 0.04199675102883295, "rouge2_recall_stderr": 0.0014222033630357748, "rougeL_fmeasure": 0.09879731353636668, "rougeL_fmeasure_stderr": 0.001799103726263371, "rougeL_precision": 0.0938740707460975, "rougeL_precision_stderr": 0.002177005796825213, "rougeL_recall": 0.1374323483251746, "rougeL_recall_stderr": 0.00266526479478189, "rougeLsum_fmeasure": 0.12094018141973355, "rougeLsum_fmeasure_stderr": 0.002284523760450248, "rougeLsum_precision": 0.11485464277414363, "rougeLsum_precision_stderr": 0.002596139008897079, "rougeLsum_recall": 0.16449395724493923, "rougeLsum_recall_stderr": 0.0031654167638919778}}, "1": {"tldr_en": {"bleu": 2.707464673902901, "bleu_stderr": 0.1122035248088363, "rouge1_fmeasure": 0.18879633772816867, "rouge1_fmeasure_stderr": 0.002216973861149929, "rouge1_precision": 0.2321033086693269, "rouge1_precision_stderr": 0.003444990523939608, "rouge1_recall": 0.21218959051209052, "rouge1_recall_stderr": 0.0028780222957239345, "rouge2_fmeasure": 0.04395688090556475, "rouge2_fmeasure_stderr": 0.0012580561387008646, "rouge2_precision": 0.05986007346081548, "rouge2_precision_stderr": 0.0021311948977268975, "rouge2_recall": 0.048915032760613236, "rouge2_recall_stderr": 0.0014864819960528294, "rougeL_fmeasure": 0.14456965085181128, "rougeL_fmeasure_stderr": 0.0017115993134306947, "rougeL_precision": 0.18107984090374726, "rougeL_precision_stderr": 0.0028960619334779066, "rougeL_recall": 0.162566462675585, "rougeL_recall_stderr": 0.002220609266556534, "rougeLsum_fmeasure": 0.1776723900847922, "rougeLsum_fmeasure_stderr": 0.0020872816698884362, "rougeLsum_precision": 0.2192803166896013, "rougeLsum_precision_stderr": 0.0033059632616290542, "rougeLsum_recall": 0.19959677205987747, "rougeLsum_recall_stderr": 0.002694200019026103}}, "2": {"tldr_en": {"bleu": 3.7904798767943335, "bleu_stderr": 0.11122294896753164, "rouge1_fmeasure": 0.23558432539564403, "rouge1_fmeasure_stderr": 0.0021996425715538554, "rouge1_precision": 0.3147030364809968, "rouge1_precision_stderr": 0.0037689305738243476, "rouge1_recall": 0.25097433153568405, "rouge1_recall_stderr": 0.0028925947424101703, "rouge2_fmeasure": 0.06557325455887651, "rouge2_fmeasure_stderr": 0.0013735424734152642, "rouge2_precision": 0.09338720402263002, "rouge2_precision_stderr": 0.002368756352904399, "rouge2_recall": 0.06942686553346078, "rouge2_recall_stderr": 0.0016202813479301297, "rougeL_fmeasure": 0.17976921379978278, "rougeL_fmeasure_stderr": 0.001722115310366516, "rougeL_precision": 0.244935161158131, "rougeL_precision_stderr": 0.003198495702253031, "rougeL_recall": 0.1911576784626261, "rougeL_recall_stderr": 0.002276055119508395, "rougeLsum_fmeasure": 0.22099937310878076, "rougeLsum_fmeasure_stderr": 0.002075646266476727, "rougeLsum_precision": 0.2958662208042827, "rougeLsum_precision_stderr": 0.003600934016250172, "rougeLsum_recall": 0.23572659332760645, "rougeLsum_recall_stderr": 0.002741901482334439}}, "3": {"tldr_en": {"bleu": 2.8632324313744557, "bleu_stderr": 0.09299178906804655, "rouge1_fmeasure": 0.19838663921126778, "rouge1_fmeasure_stderr": 0.002621759128746396, "rouge1_precision": 0.2754936136179268, "rouge1_precision_stderr": 0.004157379347035767, "rouge1_recall": 0.20528413095627832, "rouge1_recall_stderr": 0.003149288824376793, "rouge2_fmeasure": 0.055968236855402816, "rouge2_fmeasure_stderr": 0.0014034751658766104, "rouge2_precision": 0.08256853694746276, "rouge2_precision_stderr": 0.0024364087557486665, "rouge2_recall": 0.05727334409426975, "rouge2_recall_stderr": 0.0015675844642289158, "rougeL_fmeasure": 0.15243563853997083, "rougeL_fmeasure_stderr": 0.0020406692721428466, "rougeL_precision": 0.21625894747073696, "rougeL_precision_stderr": 0.0034653747339702624, "rougeL_recall": 0.15717871923447801, "rougeL_recall_stderr": 0.00246051792291125, "rougeLsum_fmeasure": 0.18589041350629654, "rougeLsum_fmeasure_stderr": 0.0024658633555113495, "rougeLsum_precision": 0.2591405389486435, "rougeLsum_precision_stderr": 0.003962509253114959, "rougeLsum_recall": 0.19231398442318168, "rougeLsum_recall_stderr": 0.0029662256128315167}}, "4": {"tldr_en": {"bleu": 0.08259030504562871, "bleu_stderr": 0.0071288759428394894, "rouge1_fmeasure": 0.06581475266895565, "rouge1_fmeasure_stderr": 0.002308785748398076, "rouge1_precision": 0.09597320792153687, "rouge1_precision_stderr": 0.003523744199921863, "rouge1_recall": 0.06743171611131621, "rouge1_recall_stderr": 0.0025672971207144984, "rouge2_fmeasure": 0.019691124849550927, "rouge2_fmeasure_stderr": 0.001032704031652877, "rouge2_precision": 0.03073553158490422, "rouge2_precision_stderr": 0.0018205157024659981, "rouge2_recall": 0.02032186815564804, "rouge2_recall_stderr": 0.0011741990653970874, "rougeL_fmeasure": 0.05209993435974213, "rougeL_fmeasure_stderr": 0.0018508808521006768, "rougeL_precision": 0.07767834454496185, "rougeL_precision_stderr": 0.002968257043282438, "rougeL_recall": 0.05327838136711029, "rougeL_recall_stderr": 0.0020669018184854763, "rougeLsum_fmeasure": 0.06145306117564354, "rougeLsum_fmeasure_stderr": 0.0021697142437582524, "rougeLsum_precision": 0.09035808108893525, "rougeLsum_precision_stderr": 0.0033673742748827878, "rougeLsum_recall": 0.06286918923105832, "rougeLsum_recall_stderr": 0.002407780221261254}}, "5": {"tldr_en": {"bleu": 3.0184106792465108e-15, "bleu_stderr": 1.78802158675685e-13, "rouge1_fmeasure": 0.00991335048881209, "rouge1_fmeasure_stderr": 0.0009630926105753386, "rouge1_precision": 0.015768279475199848, "rouge1_precision_stderr": 0.0015994817709509021, "rouge1_recall": 0.010208407683374372, "rouge1_recall_stderr": 0.0011101868759327263, "rouge2_fmeasure": 0.0029524028339129186, "rouge2_fmeasure_stderr": 0.00041005985526957695, "rouge2_precision": 0.005050282757985984, "rouge2_precision_stderr": 0.0007965820847066382, "rouge2_recall": 0.003233565984990156, "rouge2_recall_stderr": 0.0005539676407167323, "rougeL_fmeasure": 0.008248037341762705, "rougeL_fmeasure_stderr": 0.000807006653030911, "rougeL_precision": 0.013277476442981736, "rougeL_precision_stderr": 0.0013881298634661826, "rougeL_recall": 0.008616852733661218, "rougeL_recall_stderr": 0.0009635704353861369, "rougeLsum_fmeasure": 0.009376779842315807, "rougeLsum_fmeasure_stderr": 0.0009193911532830411, "rougeLsum_precision": 0.014923565167243124, "rougeLsum_precision_stderr": 0.0015288899364523146, "rougeLsum_recall": 0.009697966584991889, "rougeLsum_recall_stderr": 0.001073756967121187}}}, "e2e_nlg_cleaned": {"0": {"generate_text_restaurant": {"bleu": 3.205452750701432, "bleu_stderr": 0.029369723752371055, "rouge1_fmeasure": 0.2026666683966741, "rouge1_fmeasure_stderr": 0.001854044988549804, "rouge1_precision": 0.18794203900806028, "rouge1_precision_stderr": 0.002509182484953893, "rouge1_recall": 0.27563499652889517, "rouge1_recall_stderr": 0.002522516313059265, "rouge2_fmeasure": 0.054594037237788585, "rouge2_fmeasure_stderr": 0.0010529893200416562, "rouge2_precision": 0.04736777911623166, "rouge2_precision_stderr": 0.0009912253924337147, "rouge2_recall": 0.07529125273517918, "rouge2_recall_stderr": 0.0015129136922472945, "rougeL_fmeasure": 0.17465641737008017, "rougeL_fmeasure_stderr": 0.0014217853180858962, "rougeL_precision": 0.16091347621914998, "rougeL_precision_stderr": 0.0020468972719200795, "rougeL_recall": 0.24052353002182375, "rougeL_recall_stderr": 0.002110543832931725, "rougeLsum_fmeasure": 0.1754467264102351, "rougeLsum_fmeasure_stderr": 0.001775758147384932, "rougeLsum_precision": 0.162408167198493, "rougeLsum_precision_stderr": 0.0022254242193644625, "rougeLsum_recall": 0.23809586470877792, "rougeLsum_recall_stderr": 0.0024056082119999767}}, "1": {"generate_text_restaurant": {"bleu": 11.314986164630461, "bleu_stderr": 0.09886007247543747, "rouge1_fmeasure": 0.45168976701280994, "rouge1_fmeasure_stderr": 0.0023803410292144262, "rouge1_precision": 0.5405367881450536, "rouge1_precision_stderr": 0.0031944831139177473, "rouge1_recall": 0.4265799747472657, "rouge1_recall_stderr": 0.0030051178365182673, "rouge2_fmeasure": 0.2086255432248638, "rouge2_fmeasure_stderr": 0.002005283814444169, "rouge2_precision": 0.2530645509899577, "rouge2_precision_stderr": 0.0025820188553003945, "rouge2_recall": 0.19690559018039472, "rouge2_recall_stderr": 0.0021546256249304957, "rougeL_fmeasure": 0.32671702545878634, "rougeL_fmeasure_stderr": 0.0020575751841782584, "rougeL_precision": 0.3941062713485247, "rougeL_precision_stderr": 0.0028671074248121063, "rougeL_recall": 0.307687838606323, "rougeL_recall_stderr": 0.0024236181103855607, "rougeLsum_fmeasure": 0.3682903569907333, "rougeLsum_fmeasure_stderr": 0.0023311514221899116, "rougeLsum_precision": 0.44239922810973775, "rougeLsum_precision_stderr": 0.0031220549443630044, "rougeLsum_recall": 0.3472525108890491, "rougeLsum_recall_stderr": 0.00274280048405182}}, "2": {"generate_text_restaurant": {"bleu": 13.825382196007423, "bleu_stderr": 0.14341892864265515, "rouge1_fmeasure": 0.47949895116223057, "rouge1_fmeasure_stderr": 0.002274496687632488, "rouge1_precision": 0.5584732398385521, "rouge1_precision_stderr": 0.0031726923154704037, "rouge1_recall": 0.45947280161409504, "rouge1_recall_stderr": 0.002947956873468934, "rouge2_fmeasure": 0.234132554236615, "rouge2_fmeasure_stderr": 0.002050727643013208, "rouge2_precision": 0.27533931731718275, "rouge2_precision_stderr": 0.0026239982120668894, "rouge2_recall": 0.2249642538757707, "rouge2_recall_stderr": 0.002262594422709972, "rougeL_fmeasure": 0.35427830623229684, "rougeL_fmeasure_stderr": 0.0020644801949430084, "rougeL_precision": 0.4144330916795227, "rougeL_precision_stderr": 0.002865466880028744, "rougeL_recall": 0.3391232820910882, "rougeL_recall_stderr": 0.002487675496155266, "rougeLsum_fmeasure": 0.39980527255607845, "rougeLsum_fmeasure_stderr": 0.002302036382207211, "rougeLsum_precision": 0.46586823562780794, "rougeLsum_precision_stderr": 0.0030764860572737814, "rougeLsum_recall": 0.38321253954384926, "rougeLsum_recall_stderr": 0.002786697010998289}}, "3": {"generate_text_restaurant": {"bleu": 14.734710333150248, "bleu_stderr": 0.13327591335822025, "rouge1_fmeasure": 0.49284383237521995, "rouge1_fmeasure_stderr": 0.0022741384691834527, "rouge1_precision": 0.566363810944366, "rouge1_precision_stderr": 0.0031329176207456266, "rouge1_recall": 0.4738543349642313, "rouge1_recall_stderr": 0.002916750104399688, "rouge2_fmeasure": 0.24473795777586516, "rouge2_fmeasure_stderr": 0.0021021762412204888, "rouge2_precision": 0.2835262882274797, "rouge2_precision_stderr": 0.002620037892529304, "rouge2_recall": 0.23582515668443185, "rouge2_recall_stderr": 0.002307150627998116, "rougeL_fmeasure": 0.364532741901036, "rougeL_fmeasure_stderr": 0.002119688594264684, "rougeL_precision": 0.4201683174467468, "rougeL_precision_stderr": 0.0028464798891116223, "rougeL_recall": 0.3504188695034407, "rougeL_recall_stderr": 0.0025288933574772144, "rougeLsum_fmeasure": 0.4121332244451046, "rougeLsum_fmeasure_stderr": 0.0023416760964820984, "rougeLsum_precision": 0.4736089581434219, "rougeLsum_precision_stderr": 0.00306065010387841, "rougeLsum_recall": 0.396405785185109, "rougeLsum_recall_stderr": 0.002794473833800316}}, "4": {"generate_text_restaurant": {"bleu": 15.080804791535655, "bleu_stderr": 0.14821971591156646, "rouge1_fmeasure": 0.4935313098839454, "rouge1_fmeasure_stderr": 0.002271845302152271, "rouge1_precision": 0.5624928789321237, "rouge1_precision_stderr": 0.0031294366446319713, "rouge1_recall": 0.47592863926028084, "rouge1_recall_stderr": 0.0028908116130151665, "rouge2_fmeasure": 0.2467411297660491, "rouge2_fmeasure_stderr": 0.002101346812765226, "rouge2_precision": 0.2834307304449863, "rouge2_precision_stderr": 0.0026187903085809257, "rouge2_recall": 0.2386118604584549, "rouge2_recall_stderr": 0.0023078935639056814, "rougeL_fmeasure": 0.36587999086871936, "rougeL_fmeasure_stderr": 0.0021050945906898252, "rougeL_precision": 0.4178299399327378, "rougeL_precision_stderr": 0.0028182273866756095, "rougeL_recall": 0.35288616277467044, "rougeL_recall_stderr": 0.002503800280122615, "rougeLsum_fmeasure": 0.4149830902149149, "rougeLsum_fmeasure_stderr": 0.0023565846719075163, "rougeLsum_precision": 0.4726074434579816, "rougeLsum_precision_stderr": 0.0030529008210380413, "rougeLsum_recall": 0.40030956626841174, "rougeLsum_recall_stderr": 0.002788731746840601}}, "5": {"generate_text_restaurant": {"bleu": 15.265600470980436, "bleu_stderr": 0.20285527803005138, "rouge1_fmeasure": 0.49535698221178465, "rouge1_fmeasure_stderr": 0.0022639532726268564, "rouge1_precision": 0.5617758997558588, "rouge1_precision_stderr": 0.0031160645760995214, "rouge1_recall": 0.477780058424707, "rouge1_recall_stderr": 0.0028609800200870505, "rouge2_fmeasure": 0.24925086960246148, "rouge2_fmeasure_stderr": 0.002125288231383812, "rouge2_precision": 0.2848892339570606, "rouge2_precision_stderr": 0.0026387395366262536, "rouge2_recall": 0.24077912408729735, "rouge2_recall_stderr": 0.0023046951728657333, "rougeL_fmeasure": 0.3687908505277805, "rougeL_fmeasure_stderr": 0.0021558916218128877, "rougeL_precision": 0.4192693573282302, "rougeL_precision_stderr": 0.002855212675860218, "rougeL_recall": 0.35537258514643544, "rougeL_recall_stderr": 0.0025017841926330076, "rougeLsum_fmeasure": 0.4181866743293669, "rougeLsum_fmeasure_stderr": 0.002368198674279566, "rougeLsum_precision": 0.4743649010098781, "rougeLsum_precision_stderr": 0.003080316334291657, "rougeLsum_recall": 0.40318795066110624, "rougeLsum_recall_stderr": 0.0027745110069664625}}}, "gem_xsum": {"0": {"article_DOC_summary": {"bleu": 1.7911957794729954, "bleu_stderr": 0.1028992752886963, "rouge1_fmeasure": 0.2132476859870225, "rouge1_fmeasure_stderr": 0.002596728123368581, "rouge1_precision": 0.1544803647320562, "rouge1_precision_stderr": 0.001998179323003808, "rouge1_recall": 0.3617501123052072, "rouge1_recall_stderr": 0.004401350843198141, "rouge2_fmeasure": 0.04756359555453488, "rouge2_fmeasure_stderr": 0.0015388801074832958, "rouge2_precision": 0.034104422429782094, "rouge2_precision_stderr": 0.0011296363295058075, "rouge2_recall": 0.08341719921119035, "rouge2_recall_stderr": 0.0027753920629418876, "rougeL_fmeasure": 0.15260364524737308, "rougeL_fmeasure_stderr": 0.0018980795169799797, "rougeL_precision": 0.11047768692113931, "rougeL_precision_stderr": 0.0014728181415206798, "rougeL_recall": 0.26038442217264174, "rougeL_recall_stderr": 0.003368032246087583, "rougeLsum_fmeasure": 0.17085907541578757, "rougeLsum_fmeasure_stderr": 0.00219601338601483, "rougeLsum_precision": 0.1235706334215309, "rougeLsum_precision_stderr": 0.0016790133111005653, "rougeLsum_recall": 0.29156249557144304, "rougeLsum_recall_stderr": 0.003855753079955984}}, "1": {"article_DOC_summary": {"bleu": 1.9369867872208306, "bleu_stderr": 0.13301743127426643, "rouge1_fmeasure": 0.21212307020665455, "rouge1_fmeasure_stderr": 0.002805971174994527, "rouge1_precision": 0.18210955050574165, "rouge1_precision_stderr": 0.0030336588185256538, "rouge1_recall": 0.30765438008746904, "rouge1_recall_stderr": 0.0045764351815007235, "rouge2_fmeasure": 0.04293890964191621, "rouge2_fmeasure_stderr": 0.0016754133257735123, "rouge2_precision": 0.03608017605336464, "rouge2_precision_stderr": 0.0015351821810233588, "rouge2_recall": 0.06530630731492977, "rouge2_recall_stderr": 0.0026678483835833266, "rougeL_fmeasure": 0.15522658921799362, "rougeL_fmeasure_stderr": 0.0020874537466411373, "rougeL_precision": 0.133576425244387, "rougeL_precision_stderr": 0.0022712598584840454, "rougeL_recall": 0.2257975651465562, "rougeL_recall_stderr": 0.0035054216942714362, "rougeLsum_fmeasure": 0.16565749532885793, "rougeLsum_fmeasure_stderr": 0.002253857246658309, "rougeLsum_precision": 0.14117554206112032, "rougeLsum_precision_stderr": 0.0023065404958774274, "rougeLsum_recall": 0.24343402256399355, "rougeLsum_recall_stderr": 0.003941092857511189}}, "2": {"article_DOC_summary": {"bleu": 2.133141577656285, "bleu_stderr": 0.12965820672946443, "rouge1_fmeasure": 0.2277383324826566, "rouge1_fmeasure_stderr": 0.0030573712743888364, "rouge1_precision": 0.2105718627026518, "rouge1_precision_stderr": 0.0035778413560214016, "rouge1_recall": 0.2986830414520048, "rouge1_recall_stderr": 0.004329540379099283, "rouge2_fmeasure": 0.051547066687828734, "rouge2_fmeasure_stderr": 0.0019622251118453704, "rouge2_precision": 0.04843737420278684, "rouge2_precision_stderr": 0.002078874124454135, "rouge2_recall": 0.06777424154476913, "rouge2_recall_stderr": 0.002554380728108249, "rougeL_fmeasure": 0.17058950590239796, "rougeL_fmeasure_stderr": 0.00245256877334995, "rougeL_precision": 0.15888578947684742, "rougeL_precision_stderr": 0.002954896445415003, "rougeL_recall": 0.22275234069768626, "rougeL_recall_stderr": 0.003313554078249958, "rougeLsum_fmeasure": 0.17778653214796106, "rougeLsum_fmeasure_stderr": 0.0025471887620010904, "rougeLsum_precision": 0.16407328548937136, "rougeLsum_precision_stderr": 0.0029472894981933152, "rougeLsum_recall": 0.23520189891677276, "rougeLsum_recall_stderr": 0.0037453526896800695}}, "3": {"article_DOC_summary": {"bleu": 2.2845962769932853, "bleu_stderr": 0.1118763427251602, "rouge1_fmeasure": 0.22352993200471194, "rouge1_fmeasure_stderr": 0.0034158533172611158, "rouge1_precision": 0.21408207074509233, "rouge1_precision_stderr": 0.003911771705487585, "rouge1_recall": 0.27616262040256995, "rouge1_recall_stderr": 0.00445926401302726, "rouge2_fmeasure": 0.0505319645754636, "rouge2_fmeasure_stderr": 0.0019929881863291095, "rouge2_precision": 0.04872713712902665, "rouge2_precision_stderr": 0.0021207481086453045, "rouge2_recall": 0.06294658987847104, "rouge2_recall_stderr": 0.002453274077945568, "rougeL_fmeasure": 0.16637492784414312, "rougeL_fmeasure_stderr": 0.0027123155106531316, "rougeL_precision": 0.159438518303562, "rougeL_precision_stderr": 0.003102061741719361, "rougeL_recall": 0.20607630574913904, "rougeL_recall_stderr": 0.0035265999447064503, "rougeLsum_fmeasure": 0.17215854927610266, "rougeLsum_fmeasure_stderr": 0.00276757297974389, "rougeLsum_precision": 0.16373162683207845, "rougeLsum_precision_stderr": 0.0030891132218923796, "rougeLsum_recall": 0.2156279714811016, "rougeLsum_recall_stderr": 0.003810201919065186}}, "4": {"article_DOC_summary": {"bleu": 0.3124946765538571, "bleu_stderr": 0.07230250867579978, "rouge1_fmeasure": 0.05885821408809552, "rouge1_fmeasure_stderr": 0.0033400021306721392, "rouge1_precision": 0.06392907254960759, "rouge1_precision_stderr": 0.003876201158464289, "rouge1_recall": 0.06750288591690386, "rouge1_recall_stderr": 0.0039913615182408215, "rouge2_fmeasure": 0.012855134170914497, "rouge2_fmeasure_stderr": 0.0011864715171664183, "rouge2_precision": 0.014573840849595909, "rouge2_precision_stderr": 0.0016332201756935874, "rouge2_recall": 0.01510184445883284, "rouge2_recall_stderr": 0.0014126505769374265, "rougeL_fmeasure": 0.04407299444650032, "rougeL_fmeasure_stderr": 0.0025320491349861813, "rougeL_precision": 0.04895381713163094, "rougeL_precision_stderr": 0.0030882253843767114, "rougeL_recall": 0.0501669133523796, "rougeL_recall_stderr": 0.002985189039759907, "rougeLsum_fmeasure": 0.04628126164174725, "rougeLsum_fmeasure_stderr": 0.002645018363815525, "rougeLsum_precision": 0.05093801249895102, "rougeLsum_precision_stderr": 0.0031687581333617715, "rougeLsum_recall": 0.05318442494362772, "rougeLsum_recall_stderr": 0.00319392235102553}}, "5": {"article_DOC_summary": {"bleu": 1.0828965147492013e-39, "bleu_stderr": 2.1508906223493296e-34, "rouge1_fmeasure": 0.0020718557755462, "rouge1_fmeasure_stderr": 0.0005803475030367974, "rouge1_precision": 0.002395128003303927, "rouge1_precision_stderr": 0.000695243693352885, "rouge1_recall": 0.00195574424379908, "rouge1_recall_stderr": 0.0005505695407964535, "rouge2_fmeasure": 0.0001226302404615478, "rouge2_fmeasure_stderr": 7.106807371334149e-05, "rouge2_precision": 0.00013792342491448747, "rouge2_precision_stderr": 7.95881099815707e-05, "rouge2_recall": 0.00011258133899643333, "rouge2_recall_stderr": 6.616712432800021e-05, "rougeL_fmeasure": 0.0014461673142424087, "rougeL_fmeasure_stderr": 0.0003992063154628714, "rougeL_precision": 0.0016797182212470382, "rougeL_precision_stderr": 0.00047877790197405523, "rougeL_recall": 0.0013438433718934864, "rougeL_recall_stderr": 0.00036757969239639373, "rougeLsum_fmeasure": 0.0015096956796575665, "rougeLsum_fmeasure_stderr": 0.00041391116095822775, "rougeLsum_precision": 0.0017248567966735974, "rougeLsum_precision_stderr": 0.0004849887493451295, "rougeLsum_recall": 0.0014510474885315653, "rougeLsum_recall_stderr": 0.0004115402839485218}}}}