| {"GEM/web_nlg_en": {"0": {"PALM_prompt": {"bleu": 0.22883262521963457, "bleu_stderr": 0.027812784355662805, "rouge1_fmeasure": 0.08597342838383007, "rouge1_fmeasure_stderr": 0.0016706133404280645, "rouge1_precision": 0.05586003903362003, "rouge1_precision_stderr": 0.001210122174269387, "rouge1_recall": 0.24242206204772987, "rouge1_recall_stderr": 0.00406311577145891, "rouge2_fmeasure": 0.04138231986575359, "rouge2_fmeasure_stderr": 0.0010877957797931874, "rouge2_precision": 0.02681915167649114, "rouge2_precision_stderr": 0.0007667503131708552, "rouge2_recall": 0.1198429847566052, "rouge2_recall_stderr": 0.002900245290872093, "rougeL_fmeasure": 0.08417220195877628, "rougeL_fmeasure_stderr": 0.0016113500400264057, "rougeL_precision": 0.054558298468825164, "rougeL_precision_stderr": 0.0011547348959483191, "rougeL_recall": 0.23869961861095434, "rougeL_recall_stderr": 0.004019678329876834, "rougeLsum_fmeasure": 0.08303053627222617, "rougeLsum_fmeasure_stderr": 0.0015828450619681193, "rougeLsum_precision": 0.053912329140769884, "rougeLsum_precision_stderr": 0.0011465126361564196, "rougeLsum_recall": 0.23448028224096124, "rougeLsum_recall_stderr": 0.0038290152808916687}}, "1": {"PALM_prompt": {"bleu": 0.15575574742170292, "bleu_stderr": 0.017955848150539994, "rouge1_fmeasure": 0.07979284621488447, "rouge1_fmeasure_stderr": 0.0014891690285340458, "rouge1_precision": 0.05111535113081184, "rouge1_precision_stderr": 0.0010569639568656138, "rouge1_recall": 0.24170102692127848, "rouge1_recall_stderr": 0.003887710100922636, "rouge2_fmeasure": 0.03623174370339374, "rouge2_fmeasure_stderr": 0.0009530237429355749, "rouge2_precision": 0.02319539268897493, "rouge2_precision_stderr": 0.0006528037703471886, "rouge2_recall": 0.10947015615742409, "rouge2_recall_stderr": 0.0027377316691087903, "rougeL_fmeasure": 0.0784179897604357, "rougeL_fmeasure_stderr": 0.0014562658859192477, "rougeL_precision": 0.050193570501271496, "rougeL_precision_stderr": 0.001028472018467999, "rougeL_recall": 0.23749645057907356, "rougeL_recall_stderr": 0.0038081908356859396, "rougeLsum_fmeasure": 0.07704351061583765, "rougeLsum_fmeasure_stderr": 0.001426638202203612, "rougeLsum_precision": 0.049369870759019566, "rougeLsum_precision_stderr": 0.0010133278968197307, "rougeLsum_recall": 0.2327791385209823, "rougeLsum_recall_stderr": 0.003684550808421332}}, "2": {"PALM_prompt": {"bleu": 0.11268067835710893, "bleu_stderr": 0.016117537835788783, "rouge1_fmeasure": 0.07825326885860989, "rouge1_fmeasure_stderr": 0.001440978853110425, "rouge1_precision": 0.05051442816287885, "rouge1_precision_stderr": 0.0011508877054317382, "rouge1_recall": 0.23644760012414331, "rouge1_recall_stderr": 0.003674644463876482, "rouge2_fmeasure": 0.035231660164805785, "rouge2_fmeasure_stderr": 0.0009297500296840882, "rouge2_precision": 0.022522751858263527, "rouge2_precision_stderr": 0.0006351580301931131, "rouge2_recall": 0.10704237700401503, "rouge2_recall_stderr": 0.0026405410434178767, "rougeL_fmeasure": 0.07721547440153723, "rougeL_fmeasure_stderr": 0.0014241275115813303, "rougeL_precision": 0.04983511890393805, "rougeL_precision_stderr": 0.0011358261496601876, "rougeL_recall": 0.23226685909234288, "rougeL_recall_stderr": 0.0035796541421674885, "rougeLsum_fmeasure": 0.07603991744725928, "rougeLsum_fmeasure_stderr": 0.0013988704181332936, "rougeLsum_precision": 0.04910718457688571, "rougeLsum_precision_stderr": 0.0011242886510810662, "rougeLsum_recall": 0.22930984617447991, "rougeLsum_recall_stderr": 0.003533204831294875}}, "3": {"PALM_prompt": {"bleu": 0.10023958520271987, "bleu_stderr": 0.00971716873348663, "rouge1_fmeasure": 0.07829031027709862, "rouge1_fmeasure_stderr": 0.001430784109255991, "rouge1_precision": 0.05067153957719335, "rouge1_precision_stderr": 0.001191666778337723, "rouge1_recall": 0.23959949696648097, "rouge1_recall_stderr": 0.003667056307063945, "rouge2_fmeasure": 0.03498308879465038, "rouge2_fmeasure_stderr": 0.0009183882717060898, "rouge2_precision": 0.02236115249874777, "rouge2_precision_stderr": 0.0006367547266607817, "rouge2_recall": 0.10826670979300317, "rouge2_recall_stderr": 0.002634480071726296, "rougeL_fmeasure": 0.07694344069935595, "rougeL_fmeasure_stderr": 0.0013971914265873296, "rougeL_precision": 0.049726423469511824, "rougeL_precision_stderr": 0.0011482147824323167, "rougeL_recall": 0.235074424902374, "rougeL_recall_stderr": 0.003581208119051607, "rougeLsum_fmeasure": 0.07585440271342676, "rougeLsum_fmeasure_stderr": 0.0013846552471020674, "rougeLsum_precision": 0.04906977784065461, "rougeLsum_precision_stderr": 0.0011457059871568674, "rougeLsum_recall": 0.23202608921361742, "rougeLsum_recall_stderr": 0.0035573781836356197}}, "4": {"PALM_prompt": {"bleu": 0.1250569767383199, "bleu_stderr": 0.021628601699908004, "rouge1_fmeasure": 0.07994546949564424, "rouge1_fmeasure_stderr": 0.0014211193648653705, "rouge1_precision": 0.051227713247576225, "rouge1_precision_stderr": 0.0010795326291589034, "rouge1_recall": 0.24913049586114253, "rouge1_recall_stderr": 0.0037758792838945734, "rouge2_fmeasure": 0.03616407362539412, "rouge2_fmeasure_stderr": 0.0009414194120798864, "rouge2_precision": 0.023147509973142556, "rouge2_precision_stderr": 0.0007025722449267816, "rouge2_recall": 0.11505322393998348, "rouge2_recall_stderr": 0.002750803567815038, "rougeL_fmeasure": 0.07875849123282895, "rougeL_fmeasure_stderr": 0.0013979148156232973, "rougeL_precision": 0.050449943064731946, "rougeL_precision_stderr": 0.0010510818215242375, "rougeL_recall": 0.24470086974952332, "rougeL_recall_stderr": 0.0036741476280504953, "rougeLsum_fmeasure": 0.07780048005428908, "rougeLsum_fmeasure_stderr": 0.0013878222359377333, "rougeLsum_precision": 0.04987064991309479, "rougeLsum_precision_stderr": 0.0010470276141344049, "rougeLsum_recall": 0.2417182789397841, "rougeLsum_recall_stderr": 0.0036483215475860884}}, "5": {"PALM_prompt": {"bleu": 0.13005434642499197, "bleu_stderr": 0.010305698888010667, "rouge1_fmeasure": 0.08007155614694793, "rouge1_fmeasure_stderr": 0.0013739824517440447, "rouge1_precision": 0.05083504737121614, "rouge1_precision_stderr": 0.0009791389486581562, "rouge1_recall": 0.2513764601791396, "rouge1_recall_stderr": 0.0038227866407648994, "rouge2_fmeasure": 0.03554619045223363, "rouge2_fmeasure_stderr": 0.0009074930456849103, "rouge2_precision": 0.022503923501631235, "rouge2_precision_stderr": 0.0006219870748423658, "rouge2_recall": 0.11458449377422993, "rouge2_recall_stderr": 0.00275472174018853, "rougeL_fmeasure": 0.07854454523551002, "rougeL_fmeasure_stderr": 0.0013506756461914645, "rougeL_precision": 0.049876244862291454, "rougeL_precision_stderr": 0.0009596753537288436, "rougeL_recall": 0.2453692869402309, "rougeL_recall_stderr": 0.003667684923694637, "rougeLsum_fmeasure": 0.07777039763023255, "rougeLsum_fmeasure_stderr": 0.0013383824495560735, "rougeLsum_precision": 0.04940531544011753, "rougeLsum_precision_stderr": 0.0009556461222745182, "rougeLsum_recall": 0.24369845054346978, "rougeLsum_recall_stderr": 0.0036791477193529676}}}, "GEM/wiki_lingua_en": {"0": {"tldr_en": {"bleu": 0.49687897813178417, "bleu_stderr": 0.028753272849352945, "rouge1_fmeasure": 0.09912682070533965, "rouge1_fmeasure_stderr": 0.001568429644016599, "rouge1_precision": 0.08918754448453994, "rouge1_precision_stderr": 0.0015932292071292517, "rouge1_recall": 0.13575112269881404, "rouge1_recall_stderr": 0.0021807035000954386, "rouge2_fmeasure": 0.012242312744229137, "rouge2_fmeasure_stderr": 0.0005067795444742174, "rouge2_precision": 0.010880211822211733, "rouge2_precision_stderr": 0.0004652941571441064, "rouge2_recall": 0.017760638377981565, "rouge2_recall_stderr": 0.0008339736615674986, "rougeL_fmeasure": 0.08904469475289996, "rougeL_fmeasure_stderr": 0.0013408271016179848, "rougeL_precision": 0.07960812665447552, "rougeL_precision_stderr": 0.0013419368478906097, "rougeL_recall": 0.12335393646166343, "rougeL_recall_stderr": 0.001962960490931355, "rougeLsum_fmeasure": 0.09217605866260052, "rougeLsum_fmeasure_stderr": 0.0014433103845410448, "rougeLsum_precision": 0.08286720839573229, "rougeLsum_precision_stderr": 0.0014710250802756778, "rougeLsum_recall": 0.1265759930387205, "rougeLsum_recall_stderr": 0.0020220996079844036}}, "1": {"tldr_en": {"bleu": 0.4209954239393304, "bleu_stderr": 0.03176221976327906, "rouge1_fmeasure": 0.10341097418229313, "rouge1_fmeasure_stderr": 0.0013506246569402033, "rouge1_precision": 0.09108345639125676, "rouge1_precision_stderr": 0.0013414051332403126, "rouge1_recall": 0.14374521382155062, "rouge1_recall_stderr": 0.0019373235502897549, "rouge2_fmeasure": 0.0073507199277508825, "rouge2_fmeasure_stderr": 0.00038900605048980045, "rouge2_precision": 0.006366424495184133, "rouge2_precision_stderr": 0.00033879797030736587, "rouge2_recall": 0.011055391527813261, "rouge2_recall_stderr": 0.000720932463146685, "rougeL_fmeasure": 0.08213432595813003, "rougeL_fmeasure_stderr": 0.0009442571910773332, "rougeL_precision": 0.07176268588179166, "rougeL_precision_stderr": 0.0009370468184145725, "rougeL_recall": 0.11646644523105884, "rougeL_recall_stderr": 0.0014990807345932596, "rougeLsum_fmeasure": 0.09789009627397521, "rougeLsum_fmeasure_stderr": 0.0012554566404861117, "rougeLsum_precision": 0.0861238381653085, "rougeLsum_precision_stderr": 0.0012500535942948073, "rougeLsum_recall": 0.13658818770137882, "rougeLsum_recall_stderr": 0.0018342040331144193}}, "2": {"tldr_en": {"bleu": 0.3662014163092573, "bleu_stderr": 0.03512932309274555, "rouge1_fmeasure": 0.09759598981071996, "rouge1_fmeasure_stderr": 0.0013580795670625858, "rouge1_precision": 0.08962886049037526, "rouge1_precision_stderr": 0.0014557995887673056, "rouge1_recall": 0.13142388510558053, "rouge1_recall_stderr": 0.0018322115687655425, "rouge2_fmeasure": 0.007001951186011981, "rouge2_fmeasure_stderr": 0.0003928300541809073, "rouge2_precision": 0.006459794912288849, "rouge2_precision_stderr": 0.00039736825277010513, "rouge2_recall": 0.009646265425710393, "rouge2_recall_stderr": 0.0005575014671908036, "rougeL_fmeasure": 0.08154716868365836, "rougeL_fmeasure_stderr": 0.0010323345748373103, "rougeL_precision": 0.07428847306130615, "rougeL_precision_stderr": 0.0011113706498795289, "rougeL_recall": 0.1117787565135024, "rougeL_recall_stderr": 0.001507759191681407, "rougeLsum_fmeasure": 0.0915845046326089, "rougeLsum_fmeasure_stderr": 0.001250008944008003, "rougeLsum_precision": 0.08399764483535616, "rougeLsum_precision_stderr": 0.0013459142554786106, "rougeLsum_recall": 0.12372819672301809, "rougeLsum_recall_stderr": 0.001704125865736863}}, "3": {"tldr_en": {"bleu": 0.558567693535546, "bleu_stderr": 0.059328676012531334, "rouge1_fmeasure": 0.087537415147445, "rouge1_fmeasure_stderr": 0.0015354531166868524, "rouge1_precision": 0.08885799809368973, "rouge1_precision_stderr": 0.0019348327165460144, "rouge1_recall": 0.11654077328550566, "rouge1_recall_stderr": 0.0021991705748568326, "rouge2_fmeasure": 0.009383113142976338, "rouge2_fmeasure_stderr": 0.0004958980836726872, "rouge2_precision": 0.009914622438569649, "rouge2_precision_stderr": 0.0006522325398007237, "rouge2_recall": 0.013569391618498709, "rouge2_recall_stderr": 0.0008559625787159471, "rougeL_fmeasure": 0.07425320055271334, "rougeL_fmeasure_stderr": 0.0012438089865080164, "rougeL_precision": 0.07476162220353817, "rougeL_precision_stderr": 0.0015778653051055946, "rougeL_recall": 0.1005389837409404, "rougeL_recall_stderr": 0.0018902936583710462, "rougeLsum_fmeasure": 0.08158571031468127, "rougeLsum_fmeasure_stderr": 0.0014179098384736939, "rougeLsum_precision": 0.08282976799475586, "rougeLsum_precision_stderr": 0.0018070176003999415, "rougeLsum_recall": 0.10903150651704524, "rougeLsum_recall_stderr": 0.0020555713704425685}}, "4": {"tldr_en": {"bleu": 0.2666315699216447, "bleu_stderr": 0.04602526809695048, "rouge1_fmeasure": 0.03122194580188561, "rouge1_fmeasure_stderr": 0.0012441428977843587, "rouge1_precision": 0.03600497009970023, "rouge1_precision_stderr": 0.0017041914474905083, "rouge1_recall": 0.0405939531186821, "rouge1_recall_stderr": 0.0016845502061290764, "rouge2_fmeasure": 0.003984021707078218, "rouge2_fmeasure_stderr": 0.0003464773884452124, "rouge2_precision": 0.00501859392689466, "rouge2_precision_stderr": 0.000548209402419891, "rouge2_recall": 0.005490853123571033, "rouge2_recall_stderr": 0.0006056703124515839, "rougeL_fmeasure": 0.027162299961073107, "rougeL_fmeasure_stderr": 0.0010492438955382582, "rougeL_precision": 0.03120550445864107, "rougeL_precision_stderr": 0.0014566603437604745, "rougeL_recall": 0.03575355085817033, "rougeL_recall_stderr": 0.0014586794204117094, "rougeLsum_fmeasure": 0.028997162012914524, "rougeLsum_fmeasure_stderr": 0.001157930832064929, "rougeLsum_precision": 0.03366739502631602, "rougeLsum_precision_stderr": 0.0016160090202211065, "rougeLsum_recall": 0.037710615384056095, "rougeLsum_recall_stderr": 0.0015687838454172922}}, "5": {"tldr_en": {"bleu": 7.886206328273586e-06, "bleu_stderr": 1.221361669315733e-05, "rouge1_fmeasure": 0.00535516413631097, "rouge1_fmeasure_stderr": 0.0005989788021678713, "rouge1_precision": 0.006709044851699656, "rouge1_precision_stderr": 0.0008832342566561942, "rouge1_recall": 0.006512638750272697, "rouge1_recall_stderr": 0.0007563435499462167, "rouge2_fmeasure": 0.0009343759708146302, "rouge2_fmeasure_stderr": 0.00019124522298799218, "rouge2_precision": 0.001281837491890342, "rouge2_precision_stderr": 0.000304608742717695, "rouge2_recall": 0.0011010851742601637, "rouge2_recall_stderr": 0.0002253109954852027, "rougeL_fmeasure": 0.004672160110494701, "rougeL_fmeasure_stderr": 0.0005068592712515271, "rougeL_precision": 0.005724582318965228, "rougeL_precision_stderr": 0.0007159612442775775, "rougeL_recall": 0.00580938066432881, "rougeL_recall_stderr": 0.0006776468535233207, "rougeLsum_fmeasure": 0.0050875569393090715, "rougeLsum_fmeasure_stderr": 0.00057132173191095, "rougeLsum_precision": 0.006363502163931598, "rougeLsum_precision_stderr": 0.0008361966843529074, "rougeLsum_recall": 0.00622891484597148, "rougeLsum_recall_stderr": 0.0007333253589288016}}}, "e2e_nlg_cleaned": {"0": {"generate_text_restaurant": {"bleu": 0.8343403861560295, "bleu_stderr": 0.08848890438051935, "rouge1_fmeasure": 0.04331398539056834, "rouge1_fmeasure_stderr": 0.0015510481823475862, "rouge1_precision": 0.04482003180956012, "rouge1_precision_stderr": 0.001997077263135176, "rouge1_recall": 0.05496626728471005, "rouge1_recall_stderr": 0.0019739634808670177, "rouge2_fmeasure": 0.010736674908829128, "rouge2_fmeasure_stderr": 0.0005134871607341201, "rouge2_precision": 0.010968928668382354, "rouge2_precision_stderr": 0.0006660784749433778, "rouge2_recall": 0.013837637563125265, "rouge2_recall_stderr": 0.0006656353732837446, "rougeL_fmeasure": 0.04135106793261327, "rougeL_fmeasure_stderr": 0.0014779152643788263, "rougeL_precision": 0.04082014014811183, "rougeL_precision_stderr": 0.0017013420099803993, "rougeL_recall": 0.05346730136724671, "rougeL_recall_stderr": 0.0019401768471861783, "rougeLsum_fmeasure": 0.03267655491671789, "rougeLsum_fmeasure_stderr": 0.0011867994802981648, "rougeLsum_precision": 0.03393512996088468, "rougeLsum_precision_stderr": 0.001554141532768072, "rougeLsum_recall": 0.041493274650743935, "rougeLsum_recall_stderr": 0.0015131168604173573}}, "1": {"generate_text_restaurant": {"bleu": 2.9406196061775116, "bleu_stderr": 0.10258259522175316, "rouge1_fmeasure": 0.18693446462920227, "rouge1_fmeasure_stderr": 0.002787464540486619, "rouge1_precision": 0.2787618289181687, "rouge1_precision_stderr": 0.005384508455643661, "rouge1_recall": 0.19799693389239711, "rouge1_recall_stderr": 0.003182542201890721, "rouge2_fmeasure": 0.05706123212585479, "rouge2_fmeasure_stderr": 0.0013015405321589112, "rouge2_precision": 0.1437328248773931, "rouge2_precision_stderr": 0.005092642043712837, "rouge2_recall": 0.05733865153595204, "rouge2_recall_stderr": 0.001383897371483806, "rougeL_fmeasure": 0.14444789684107232, "rougeL_fmeasure_stderr": 0.0021086022369478444, "rougeL_precision": 0.2302703496004102, "rougeL_precision_stderr": 0.005102072689082256, "rougeL_recall": 0.15449193654318977, "rougeL_recall_stderr": 0.002518846268029969, "rougeLsum_fmeasure": 0.1553009809575637, "rougeLsum_fmeasure_stderr": 0.0023739934749666684, "rougeLsum_precision": 0.24427645994280608, "rougeLsum_precision_stderr": 0.005221824942580713, "rougeLsum_recall": 0.1627325478139627, "rougeLsum_recall_stderr": 0.0026692987289094598}}, "2": {"generate_text_restaurant": {"bleu": 3.0869989165891227, "bleu_stderr": 0.16013219623315433, "rouge1_fmeasure": 0.21814903833369859, "rouge1_fmeasure_stderr": 0.0031866040091908464, "rouge1_precision": 0.3978056637157276, "rouge1_precision_stderr": 0.006383333506870748, "rouge1_recall": 0.19769999489666457, "rouge1_recall_stderr": 0.003338189945298019, "rouge2_fmeasure": 0.08456553732934603, "rouge2_fmeasure_stderr": 0.0016022980395205303, "rouge2_precision": 0.24931076985350456, "rouge2_precision_stderr": 0.006415148520407114, "rouge2_recall": 0.07401280693073875, "rouge2_recall_stderr": 0.0016105308975029838, "rougeL_fmeasure": 0.1673148071155831, "rougeL_fmeasure_stderr": 0.002388385786508644, "rougeL_precision": 0.33763473031412045, "rougeL_precision_stderr": 0.006269179792430952, "rougeL_recall": 0.14877296254487207, "rougeL_recall_stderr": 0.0024783679014017384, "rougeLsum_fmeasure": 0.18463628783286154, "rougeLsum_fmeasure_stderr": 0.002693460028052387, "rougeLsum_precision": 0.357819032438701, "rougeLsum_precision_stderr": 0.006300016081780083, "rougeLsum_recall": 0.16548809371217418, "rougeLsum_recall_stderr": 0.0028048620055066233}}, "3": {"generate_text_restaurant": {"bleu": 3.7011916246059053, "bleu_stderr": 0.14593162958819425, "rouge1_fmeasure": 0.23033091532940253, "rouge1_fmeasure_stderr": 0.0032924392197765163, "rouge1_precision": 0.41822296870814335, "rouge1_precision_stderr": 0.006460520453011632, "rouge1_recall": 0.2071298534116268, "rouge1_recall_stderr": 0.0034383519555611984, "rouge2_fmeasure": 0.09792307241998234, "rouge2_fmeasure_stderr": 0.0017582063387383436, "rouge2_precision": 0.2702971908568115, "rouge2_precision_stderr": 0.00643370737283098, "rouge2_recall": 0.08487129021823478, "rouge2_recall_stderr": 0.00173547236263484, "rougeL_fmeasure": 0.17881874820814597, "rougeL_fmeasure_stderr": 0.0024988437464002213, "rougeL_precision": 0.3572174834274431, "rougeL_precision_stderr": 0.006354476895716739, "rougeL_recall": 0.1574631215849211, "rougeL_recall_stderr": 0.002552084505977488, "rougeLsum_fmeasure": 0.19693757021044234, "rougeLsum_fmeasure_stderr": 0.002816228141853166, "rougeLsum_precision": 0.37863570607432673, "rougeLsum_precision_stderr": 0.006392889923077396, "rougeLsum_recall": 0.17478692469025933, "rougeLsum_recall_stderr": 0.002894063899840589}}, "4": {"generate_text_restaurant": {"bleu": 4.378358579277868, "bleu_stderr": 0.15272962158453546, "rouge1_fmeasure": 0.25232175927064066, "rouge1_fmeasure_stderr": 0.003252006309486809, "rouge1_precision": 0.45882713034371453, "rouge1_precision_stderr": 0.006415593061369954, "rouge1_recall": 0.2255093763170198, "rouge1_recall_stderr": 0.003436954476710523, "rouge2_fmeasure": 0.11225233292150326, "rouge2_fmeasure_stderr": 0.0018233487430859975, "rouge2_precision": 0.299477006298075, "rouge2_precision_stderr": 0.0065384661124707425, "rouge2_recall": 0.09678212220073933, "rouge2_recall_stderr": 0.0018066974497821132, "rougeL_fmeasure": 0.19796718724270523, "rougeL_fmeasure_stderr": 0.002503553099442586, "rougeL_precision": 0.39417067582169574, "rougeL_precision_stderr": 0.006410266792021505, "rougeL_recall": 0.17324797729857383, "rougeL_recall_stderr": 0.002580532804445032, "rougeLsum_fmeasure": 0.2170954167942643, "rougeLsum_fmeasure_stderr": 0.002802720816613775, "rougeLsum_precision": 0.41668133719539296, "rougeLsum_precision_stderr": 0.006408889836300579, "rougeLsum_recall": 0.19157341143212034, "rougeLsum_recall_stderr": 0.002922660612765926}}, "5": {"generate_text_restaurant": {"bleu": 4.890257220178811, "bleu_stderr": 0.13420785403183202, "rouge1_fmeasure": 0.2681436632992601, "rouge1_fmeasure_stderr": 0.003258641900873387, "rouge1_precision": 0.475398003113497, "rouge1_precision_stderr": 0.006327908810294356, "rouge1_recall": 0.24024724261621913, "rouge1_recall_stderr": 0.0034704603090637783, "rouge2_fmeasure": 0.12437458519230632, "rouge2_fmeasure_stderr": 0.0018508476727143834, "rouge2_precision": 0.31255952474835047, "rouge2_precision_stderr": 0.006463307595299056, "rouge2_recall": 0.10772173878741007, "rouge2_recall_stderr": 0.0018408748834838522, "rougeL_fmeasure": 0.21086184259770677, "rougeL_fmeasure_stderr": 0.002497969164716478, "rougeL_precision": 0.40683490044030046, "rougeL_precision_stderr": 0.006313377793533003, "rougeL_recall": 0.18544055623635025, "rougeL_recall_stderr": 0.0026168715932805803, "rougeLsum_fmeasure": 0.23024299776500148, "rougeLsum_fmeasure_stderr": 0.0027826284448924806, "rougeLsum_precision": 0.4295272827032871, "rougeLsum_precision_stderr": 0.006304887170894177, "rougeLsum_recall": 0.20394125936151544, "rougeLsum_recall_stderr": 0.0029282150904557346}}}, "gem_xsum": {"0": {"article_DOC_summary": {"bleu": 0.9016790167616279, "bleu_stderr": 0.08554255656260222, "rouge1_fmeasure": 0.14196393966710072, "rouge1_fmeasure_stderr": 0.002104608543541609, "rouge1_precision": 0.1022798973400133, "rouge1_precision_stderr": 0.0016195028484036645, "rouge1_recall": 0.2472257110564639, "rouge1_recall_stderr": 0.0036244015531403696, "rouge2_fmeasure": 0.02440112287257367, "rouge2_fmeasure_stderr": 0.0010880062384939326, "rouge2_precision": 0.01730961638211292, "rouge2_precision_stderr": 0.0007982969706574101, "rouge2_recall": 0.043897826329439435, "rouge2_recall_stderr": 0.0019301619560314596, "rougeL_fmeasure": 0.12383517753988749, "rougeL_fmeasure_stderr": 0.0017149719617583993, "rougeL_precision": 0.08904777578480996, "rougeL_precision_stderr": 0.0013272362515087367, "rougeL_recall": 0.2169745636685914, "rougeL_recall_stderr": 0.003060682824750885, "rougeLsum_fmeasure": 0.10898759142531142, "rougeLsum_fmeasure_stderr": 0.001653332454666073, "rougeLsum_precision": 0.0783856177341214, "rougeLsum_precision_stderr": 0.0012799850206698408, "rougeLsum_recall": 0.1915896888630931, "rougeLsum_recall_stderr": 0.0029773166596938527}}, "1": {"article_DOC_summary": {"bleu": 0.6174225365598259, "bleu_stderr": 0.05127643687143349, "rouge1_fmeasure": 0.12680695998689423, "rouge1_fmeasure_stderr": 0.001991458093221162, "rouge1_precision": 0.08983663259289545, "rouge1_precision_stderr": 0.0014656640724220792, "rouge1_recall": 0.22526078131503421, "rouge1_recall_stderr": 0.0034677534855223576, "rouge2_fmeasure": 0.018226182677564602, "rouge2_fmeasure_stderr": 0.0008914321799827453, "rouge2_precision": 0.012790758078394766, "rouge2_precision_stderr": 0.0006274060760347892, "rouge2_recall": 0.03314630221773423, "rouge2_recall_stderr": 0.0016600656887166795, "rougeL_fmeasure": 0.11108456989593447, "rougeL_fmeasure_stderr": 0.0016654771979817452, "rougeL_precision": 0.07859662487412902, "rougeL_precision_stderr": 0.0012275599440022234, "rougeL_recall": 0.19823099261868493, "rougeL_recall_stderr": 0.002945509989290099, "rougeLsum_fmeasure": 0.09809900796895703, "rougeLsum_fmeasure_stderr": 0.0015505955006710195, "rougeLsum_precision": 0.06928351933199965, "rougeLsum_precision_stderr": 0.0011286042016073875, "rougeLsum_recall": 0.1759900951750178, "rougeLsum_recall_stderr": 0.002828460597285845}}, "2": {"article_DOC_summary": {"bleu": 0.6922674508727583, "bleu_stderr": 0.09204471088454393, "rouge1_fmeasure": 0.12387534340787068, "rouge1_fmeasure_stderr": 0.002014018603012206, "rouge1_precision": 0.08766778881774849, "rouge1_precision_stderr": 0.0014891572798897187, "rouge1_recall": 0.22075516476448948, "rouge1_recall_stderr": 0.00347829704174308, "rouge2_fmeasure": 0.018525660614874147, "rouge2_fmeasure_stderr": 0.0010059837278380754, "rouge2_precision": 0.013027956332330589, "rouge2_precision_stderr": 0.000726229100756286, "rouge2_recall": 0.03360633434332384, "rouge2_recall_stderr": 0.0017823718475256693, "rougeL_fmeasure": 0.11034857045454226, "rougeL_fmeasure_stderr": 0.001695778207988071, "rougeL_precision": 0.077990231219861, "rougeL_precision_stderr": 0.0012548203942130344, "rougeL_recall": 0.19754633749547196, "rougeL_recall_stderr": 0.0029825381740120733, "rougeLsum_fmeasure": 0.09519799112177334, "rougeLsum_fmeasure_stderr": 0.0015659285260077656, "rougeLsum_precision": 0.06719420386174171, "rougeLsum_precision_stderr": 0.0011491767128342227, "rougeLsum_recall": 0.17095111398494645, "rougeLsum_recall_stderr": 0.002777030573630023}}, "3": {"article_DOC_summary": {"bleu": 0.6181747520447193, "bleu_stderr": 0.049332282488453325, "rouge1_fmeasure": 0.11970202642407167, "rouge1_fmeasure_stderr": 0.0021197440846560966, "rouge1_precision": 0.08698815906142213, "rouge1_precision_stderr": 0.0017345476005806628, "rouge1_recall": 0.210024658038518, "rouge1_recall_stderr": 0.003645324207351596, "rouge2_fmeasure": 0.017445968725527953, "rouge2_fmeasure_stderr": 0.0009133145642922374, "rouge2_precision": 0.012464843327563693, "rouge2_precision_stderr": 0.0006606924610361004, "rouge2_recall": 0.03149526320515733, "rouge2_recall_stderr": 0.0016746812407298752, "rougeL_fmeasure": 0.10682732750074307, "rougeL_fmeasure_stderr": 0.0017831957682131314, "rougeL_precision": 0.07749990811103293, "rougeL_precision_stderr": 0.0014590057257022838, "rougeL_recall": 0.18830492688774997, "rougeL_recall_stderr": 0.0031305358996651976, "rougeLsum_fmeasure": 0.09289835920150129, "rougeLsum_fmeasure_stderr": 0.001624619431174144, "rougeLsum_precision": 0.06755902721539477, "rougeLsum_precision_stderr": 0.0013628857922879717, "rougeLsum_recall": 0.16409288081988832, "rougeLsum_recall_stderr": 0.002865541107683648}}, "4": {"article_DOC_summary": {"bleu": 0.450056497825642, "bleu_stderr": 0.14846722588344094, "rouge1_fmeasure": 0.03470890743725083, "rouge1_fmeasure_stderr": 0.0020520465159130927, "rouge1_precision": 0.030544594130750835, "rouge1_precision_stderr": 0.0021330267604427484, "rouge1_recall": 0.054628538366303006, "rouge1_recall_stderr": 0.0032412927121272896, "rouge2_fmeasure": 0.005129090360707225, "rouge2_fmeasure_stderr": 0.0006597787970364636, "rouge2_precision": 0.004045481859690613, "rouge2_precision_stderr": 0.0005769901773501374, "rouge2_recall": 0.008512380598717688, "rouge2_recall_stderr": 0.0010089042236144311, "rougeL_fmeasure": 0.030241620839919433, "rougeL_fmeasure_stderr": 0.0017471531374678303, "rougeL_precision": 0.026676015773228576, "rougeL_precision_stderr": 0.001870277821695184, "rougeL_recall": 0.04805945027625291, "rougeL_recall_stderr": 0.002827982846252903, "rougeLsum_fmeasure": 0.027168700375590663, "rougeLsum_fmeasure_stderr": 0.0016300199179532333, "rougeLsum_precision": 0.024493166051240776, "rougeLsum_precision_stderr": 0.0018426049402895288, "rougeLsum_recall": 0.042743950057792045, "rougeLsum_recall_stderr": 0.0025687027564754382}}, "5": {"article_DOC_summary": {"bleu": 4.701645545451422e-39, "bleu_stderr": 4.423933320700958e-33, "rouge1_fmeasure": 0.002541504826499715, "rouge1_fmeasure_stderr": 0.0007284967864016516, "rouge1_precision": 0.002880347249708247, "rouge1_precision_stderr": 0.0008552363057144186, "rouge1_recall": 0.0023662681113285227, "rouge1_recall_stderr": 0.0006671844202651334, "rouge2_fmeasure": 0.0003192230499539746, "rouge2_fmeasure_stderr": 0.0001551634211277905, "rouge2_precision": 0.0003609205260148656, "rouge2_precision_stderr": 0.00016999661105349456, "rouge2_recall": 0.00029366489965824033, "rouge2_recall_stderr": 0.00014802866526663323, "rougeL_fmeasure": 0.002078487848546464, "rougeL_fmeasure_stderr": 0.00058210203581558, "rougeL_precision": 0.002324954694563953, "rougeL_precision_stderr": 0.000660753735821071, "rougeL_recall": 0.0019645608817565226, "rougeL_recall_stderr": 0.0005537267229057413, "rougeLsum_fmeasure": 0.002192963200921734, "rougeLsum_fmeasure_stderr": 0.0006172749787154629, "rougeLsum_precision": 0.0024628781194784405, "rougeLsum_precision_stderr": 0.0007073962748883953, "rougeLsum_recall": 0.002062973958092467, "rougeLsum_recall_stderr": 0.0005804863416586463}}}} |