File size: 27,951 Bytes
9defb95 |
1 |
{"GEM/web_nlg_en": {"0": {"PALM_prompt": {"bleu": 0.3018678413532531, "bleu_stderr": 0.02844023781425127, "rouge1_fmeasure": 0.10892691674779821, "rouge1_fmeasure_stderr": 0.0019071235551653418, "rouge1_precision": 0.07529613947856881, "rouge1_precision_stderr": 0.001982838396838402, "rouge1_recall": 0.3128650370000908, "rouge1_recall_stderr": 0.0050801382033981305, "rouge2_fmeasure": 0.049040742381146675, "rouge2_fmeasure_stderr": 0.0011519113898695909, "rouge2_precision": 0.03417694669369951, "rouge2_precision_stderr": 0.001313368572681446, "rouge2_recall": 0.14493621807358514, "rouge2_recall_stderr": 0.0032191726931486194, "rougeL_fmeasure": 0.10396046493580034, "rougeL_fmeasure_stderr": 0.001778756221046735, "rougeL_precision": 0.07180450626627975, "rougeL_precision_stderr": 0.001883124040127771, "rougeL_recall": 0.30107392723259574, "rougeL_recall_stderr": 0.004911398619361963, "rougeLsum_fmeasure": 0.10404327940071008, "rougeLsum_fmeasure_stderr": 0.001820581250965178, "rougeLsum_precision": 0.0720836832710309, "rougeLsum_precision_stderr": 0.001909971490636727, "rougeLsum_recall": 0.29709085493162957, "rougeLsum_recall_stderr": 0.004719450806012623}}, "1": {"PALM_prompt": {"bleu": 0.5232740840707778, "bleu_stderr": 0.020854898797383486, "rouge1_fmeasure": 0.1654988415912321, "rouge1_fmeasure_stderr": 0.003746858529251122, "rouge1_precision": 0.14535656258632043, "rouge1_precision_stderr": 0.00467037788995567, "rouge1_recall": 0.32467105717536826, "rouge1_recall_stderr": 0.004844586825107793, "rouge2_fmeasure": 0.08445836822356238, "rouge2_fmeasure_stderr": 0.0026512482133539865, "rouge2_precision": 0.07725516531902364, "rouge2_precision_stderr": 0.0033727094011323654, "rouge2_recall": 0.16618004223187002, "rouge2_recall_stderr": 0.003573100663317745, "rougeL_fmeasure": 0.1515457985267535, "rougeL_fmeasure_stderr": 0.003242282817029173, "rougeL_precision": 0.1318447100821655, "rougeL_precision_stderr": 0.004146806578291652, "rougeL_recall": 0.30561460626596343, "rougeL_recall_stderr": 0.004514632290906585, "rougeLsum_fmeasure": 0.15355200233921673, "rougeLsum_fmeasure_stderr": 0.0032933307640919023, "rougeLsum_precision": 0.1339783021316465, "rougeLsum_precision_stderr": 0.004209899048276762, "rougeLsum_recall": 0.3075713065076715, "rougeLsum_recall_stderr": 0.004515232151240997}}, "2": {"PALM_prompt": {"bleu": 0.8216652782232776, "bleu_stderr": 0.04062910442416713, "rouge1_fmeasure": 0.2027123169825771, "rouge1_fmeasure_stderr": 0.004395624756947157, "rouge1_precision": 0.18008691481284958, "rouge1_precision_stderr": 0.0052757038925836395, "rouge1_recall": 0.3711673998047281, "rouge1_recall_stderr": 0.00487879034297811, "rouge2_fmeasure": 0.10928693373297448, "rouge2_fmeasure_stderr": 0.003154986876758784, "rouge2_precision": 0.10008962637316307, "rouge2_precision_stderr": 0.0037529405438827225, "rouge2_recall": 0.20016469360773192, "rouge2_recall_stderr": 0.003813720451519567, "rougeL_fmeasure": 0.18244327655886838, "rougeL_fmeasure_stderr": 0.003749619328233065, "rougeL_precision": 0.15996735275766777, "rougeL_precision_stderr": 0.004577626944141576, "rougeL_recall": 0.3460684822761284, "rougeL_recall_stderr": 0.004492766954524856, "rougeLsum_fmeasure": 0.18698187602734404, "rougeLsum_fmeasure_stderr": 0.0038921774054845996, "rougeLsum_precision": 0.1650914247834489, "rougeLsum_precision_stderr": 0.00477544492053463, "rougeLsum_recall": 0.3505702667663343, "rougeLsum_recall_stderr": 0.004548048493270462}}, "3": {"PALM_prompt": {"bleu": 0.8830672069742221, "bleu_stderr": 0.028000457075678158, "rouge1_fmeasure": 0.21071007543003908, "rouge1_fmeasure_stderr": 0.004463218149424481, "rouge1_precision": 0.188815921549058, "rouge1_precision_stderr": 0.005405782039170827, "rouge1_recall": 0.38372152833073453, "rouge1_recall_stderr": 0.004859603610175178, "rouge2_fmeasure": 0.11292635699291721, "rouge2_fmeasure_stderr": 0.0031281095189860052, "rouge2_precision": 0.10432859230180822, "rouge2_precision_stderr": 0.003707124967324291, "rouge2_recall": 0.2043813472297843, "rouge2_recall_stderr": 0.003801503662629156, "rougeL_fmeasure": 0.18796910977796713, "rougeL_fmeasure_stderr": 0.003750496425693158, "rougeL_precision": 0.16609714125737446, "rougeL_precision_stderr": 0.004603337178258819, "rougeL_recall": 0.3553325064502732, "rougeL_recall_stderr": 0.0044309664783451575, "rougeLsum_fmeasure": 0.1924829285681012, "rougeLsum_fmeasure_stderr": 0.0038880601940687624, "rougeLsum_precision": 0.17111254219249275, "rougeLsum_precision_stderr": 0.004780700019520514, "rougeLsum_recall": 0.36026081429848233, "rougeLsum_recall_stderr": 0.004488184055350965}}, "4": {"PALM_prompt": {"bleu": 1.0358671081792514, "bleu_stderr": 0.04263566752630496, "rouge1_fmeasure": 0.22245843694786877, "rouge1_fmeasure_stderr": 0.0045583402573195686, "rouge1_precision": 0.19989615669545296, "rouge1_precision_stderr": 0.005599957130646531, "rouge1_recall": 0.40336166710123866, "rouge1_recall_stderr": 0.004818721124125534, "rouge2_fmeasure": 0.12100972003049645, "rouge2_fmeasure_stderr": 0.0032743404066677153, "rouge2_precision": 0.1124336236373582, "rouge2_precision_stderr": 0.003935741095779227, "rouge2_recall": 0.21819990615637125, "rouge2_recall_stderr": 0.00385618079142143, "rougeL_fmeasure": 0.19760963957512798, "rougeL_fmeasure_stderr": 0.00383542084139647, "rougeL_precision": 0.17492321519899293, "rougeL_precision_stderr": 0.004773378480561351, "rougeL_recall": 0.37224158952457587, "rougeL_recall_stderr": 0.004377948019839408, "rougeLsum_fmeasure": 0.20440757227679296, "rougeLsum_fmeasure_stderr": 0.004022054785395138, "rougeLsum_precision": 0.18235385466161755, "rougeLsum_precision_stderr": 0.005021694344891093, "rougeLsum_recall": 0.3793687467005697, "rougeLsum_recall_stderr": 0.004423507289060084}}, "5": {"PALM_prompt": {"bleu": 1.204171361933669, "bleu_stderr": 0.07613961296168276, "rouge1_fmeasure": 0.2366466068769033, "rouge1_fmeasure_stderr": 0.0048055385839361016, "rouge1_precision": 0.21975255516712816, "rouge1_precision_stderr": 0.0060000476488098085, "rouge1_recall": 0.4066635344523642, "rouge1_recall_stderr": 0.0048262902071662655, "rouge2_fmeasure": 0.13171103508163604, "rouge2_fmeasure_stderr": 0.0034923443640983974, "rouge2_precision": 0.1275911476917841, "rouge2_precision_stderr": 0.004309205748397978, "rouge2_recall": 0.2235792080539432, "rouge2_recall_stderr": 0.003950954664759423, "rougeL_fmeasure": 0.2088535130444153, "rougeL_fmeasure_stderr": 0.004052842030593682, "rougeL_precision": 0.19131328031391062, "rougeL_precision_stderr": 0.005134255771123987, "rougeL_recall": 0.37336352525066424, "rougeL_recall_stderr": 0.0044216260882892515, "rougeLsum_fmeasure": 0.21625717477809833, "rougeLsum_fmeasure_stderr": 0.004260506456488727, "rougeLsum_precision": 0.1997593788485136, "rougeLsum_precision_stderr": 0.005406525039653976, "rougeLsum_recall": 0.3803285154915348, "rougeLsum_recall_stderr": 0.004488995109880062}}}, "GEM/wiki_lingua_en": {"0": {"tldr_en": {"bleu": 2.7397274944771954, "bleu_stderr": 0.10039261451919343, "rouge1_fmeasure": 0.1238366627407439, "rouge1_fmeasure_stderr": 0.0026637547390690967, "rouge1_precision": 0.12462462729719587, "rouge1_precision_stderr": 0.0031826046662497306, "rouge1_recall": 0.16449607884346923, "rouge1_recall_stderr": 0.003588981148112544, "rouge2_fmeasure": 0.03307271090107231, "rouge2_fmeasure_stderr": 0.0010639050828558138, "rouge2_precision": 0.030579818116461738, "rouge2_precision_stderr": 0.001114447996676589, "rouge2_recall": 0.045348988871228374, "rouge2_recall_stderr": 0.0015776302264520795, "rougeL_fmeasure": 0.0940193069900903, "rougeL_fmeasure_stderr": 0.001985212421750187, "rougeL_precision": 0.09689369540491309, "rougeL_precision_stderr": 0.0026833442642966994, "rougeL_recall": 0.1273558135465041, "rougeL_recall_stderr": 0.002838117953205465, "rougeLsum_fmeasure": 0.11606269945283079, "rougeLsum_fmeasure_stderr": 0.0025094061265404873, "rougeLsum_precision": 0.11762669226995941, "rougeLsum_precision_stderr": 0.0030721629727453585, "rougeLsum_recall": 0.15435308236518808, "rougeLsum_recall_stderr": 0.003394722386908597}}, "1": {"tldr_en": {"bleu": 2.980212171285624, "bleu_stderr": 0.08986977717018042, "rouge1_fmeasure": 0.18706368194466189, "rouge1_fmeasure_stderr": 0.0023760001514770367, "rouge1_precision": 0.2303358349811005, "rouge1_precision_stderr": 0.003690727542733754, "rouge1_recall": 0.2154464843014795, "rouge1_recall_stderr": 0.00312287409246033, "rouge2_fmeasure": 0.04664136277906473, "rouge2_fmeasure_stderr": 0.0012607234019787598, "rouge2_precision": 0.0623131824874716, "rouge2_precision_stderr": 0.0021997319954224622, "rouge2_recall": 0.05366477872164223, "rouge2_recall_stderr": 0.0015294014686067932, "rougeL_fmeasure": 0.14101873450061833, "rougeL_fmeasure_stderr": 0.0017902413086473704, "rougeL_precision": 0.1774352175816246, "rougeL_precision_stderr": 0.003056714448069494, "rougeL_recall": 0.16262682837459477, "rougeL_recall_stderr": 0.00239676054267987, "rougeLsum_fmeasure": 0.175474051697367, "rougeLsum_fmeasure_stderr": 0.0022207055448280263, "rougeLsum_precision": 0.21694264697187762, "rougeLsum_precision_stderr": 0.0035242626334641026, "rougeLsum_recall": 0.2020549195476134, "rougeLsum_recall_stderr": 0.0029196969560855153}}, "2": {"tldr_en": {"bleu": 4.611723071615721, "bleu_stderr": 0.09604703447972755, "rouge1_fmeasure": 0.2502603578204361, "rouge1_fmeasure_stderr": 0.002293574688170618, "rouge1_precision": 0.31402819280145294, "rouge1_precision_stderr": 0.00372043085747532, "rouge1_recall": 0.27476531134514864, "rouge1_recall_stderr": 0.003004834706287235, "rouge2_fmeasure": 0.07312196156858046, "rouge2_fmeasure_stderr": 0.0015175238657054205, "rouge2_precision": 0.0964374050617497, "rouge2_precision_stderr": 0.0023942829869708893, "rouge2_recall": 0.07950609744170317, "rouge2_recall_stderr": 0.0017736713632069314, "rougeL_fmeasure": 0.18837114117652573, "rougeL_fmeasure_stderr": 0.0018392223420105429, "rougeL_precision": 0.23993957539542324, "rougeL_precision_stderr": 0.0031070932808128005, "rougeL_recall": 0.20656602583791495, "rougeL_recall_stderr": 0.0024047364648286966, "rougeLsum_fmeasure": 0.23530722744582147, "rougeLsum_fmeasure_stderr": 0.0021867085010560715, "rougeLsum_precision": 0.29611740779831397, "rougeLsum_precision_stderr": 0.0035725589380756783, "rougeLsum_recall": 0.2582729289090492, "rougeLsum_recall_stderr": 0.002859502904870282}}, "3": {"tldr_en": {"bleu": 3.6534705242416563, "bleu_stderr": 0.0881203300496025, "rouge1_fmeasure": 0.2137655552336782, "rouge1_fmeasure_stderr": 0.002714393421558324, "rouge1_precision": 0.27636674426156177, "rouge1_precision_stderr": 0.004101651110307418, "rouge1_recall": 0.22930947512843322, "rouge1_recall_stderr": 0.003338024591740698, "rouge2_fmeasure": 0.06389847418480928, "rouge2_fmeasure_stderr": 0.001481197293938296, "rouge2_precision": 0.08702087298573732, "rouge2_precision_stderr": 0.0023613075212299754, "rouge2_recall": 0.06834799049896098, "rouge2_recall_stderr": 0.0017608046858656524, "rougeL_fmeasure": 0.162300378297079, "rougeL_fmeasure_stderr": 0.002115846911993043, "rougeL_precision": 0.2135610881070536, "rougeL_precision_stderr": 0.0033828812360183476, "rougeL_recall": 0.1743188444814511, "rougeL_recall_stderr": 0.002648347151651851, "rougeLsum_fmeasure": 0.2007815371334278, "rougeLsum_fmeasure_stderr": 0.002564977939596769, "rougeLsum_precision": 0.260193792903579, "rougeLsum_precision_stderr": 0.003915057196799965, "rougeLsum_recall": 0.2155361794060783, "rougeLsum_recall_stderr": 0.003167125886789834}}, "4": {"tldr_en": {"bleu": 0.14336768966011842, "bleu_stderr": 0.01664751835367322, "rouge1_fmeasure": 0.06966991898451057, "rouge1_fmeasure_stderr": 0.0024061665565282536, "rouge1_precision": 0.09318115237631248, "rouge1_precision_stderr": 0.0034313497448162753, "rouge1_recall": 0.07510657766582833, "rouge1_recall_stderr": 0.0027823499468141023, "rouge2_fmeasure": 0.021410981626472696, "rouge2_fmeasure_stderr": 0.0010806600066785071, "rouge2_precision": 0.0306990992199194, "rouge2_precision_stderr": 0.001732779147193654, "rouge2_recall": 0.023135462034409776, "rouge2_recall_stderr": 0.0012681089305181597, "rougeL_fmeasure": 0.05441308852467703, "rougeL_fmeasure_stderr": 0.0019026572440828432, "rougeL_precision": 0.07441428298557279, "rougeL_precision_stderr": 0.0028438647198895358, "rougeL_recall": 0.05853529439287516, "rougeL_recall_stderr": 0.0022113797700769144, "rougeLsum_fmeasure": 0.06515832990606861, "rougeLsum_fmeasure_stderr": 0.0022584661554748706, "rougeLsum_precision": 0.08804803757911164, "rougeLsum_precision_stderr": 0.003292180554603894, "rougeLsum_recall": 0.06984747732679251, "rougeLsum_recall_stderr": 0.0025861205751654633}}, "5": {"tldr_en": {"bleu": 1.5519142183400993e-12, "bleu_stderr": 6.955628631620419e-11, "rouge1_fmeasure": 0.011789826148853048, "rouge1_fmeasure_stderr": 0.0011310450894670711, "rouge1_precision": 0.016751606857569483, "rouge1_precision_stderr": 0.0016597025910088947, "rouge1_recall": 0.012874957063334068, "rouge1_recall_stderr": 0.001320598626607211, "rouge2_fmeasure": 0.0035301672488990635, "rouge2_fmeasure_stderr": 0.00046931341477467973, "rouge2_precision": 0.004789908933072763, "rouge2_precision_stderr": 0.0006572780023821424, "rouge2_recall": 0.003932891692847358, "rouge2_recall_stderr": 0.0005535394810295029, "rougeL_fmeasure": 0.009092320709271332, "rougeL_fmeasure_stderr": 0.000875179657864614, "rougeL_precision": 0.013288040221462351, "rougeL_precision_stderr": 0.0013727762159921608, "rougeL_recall": 0.00989469802053577, "rougeL_recall_stderr": 0.0010241634280214566, "rougeLsum_fmeasure": 0.010891546354591043, "rougeLsum_fmeasure_stderr": 0.001040987925967451, "rougeLsum_precision": 0.015518838953812768, "rougeLsum_precision_stderr": 0.001554235047112553, "rougeLsum_recall": 0.01190208294502919, "rougeLsum_recall_stderr": 0.001221212576212141}}}, "e2e_nlg_cleaned": {"0": {"generate_text_restaurant": {"bleu": 7.805428848697077, "bleu_stderr": 0.12760294204588482, "rouge1_fmeasure": 0.3241138419996619, "rouge1_fmeasure_stderr": 0.0023488121086233404, "rouge1_precision": 0.27630659363671284, "rouge1_precision_stderr": 0.0026635424916828915, "rouge1_recall": 0.4517766787964781, "rouge1_recall_stderr": 0.003086695070399088, "rouge2_fmeasure": 0.14611347950675788, "rouge2_fmeasure_stderr": 0.001555781159556189, "rouge2_precision": 0.1264233869651961, "rouge2_precision_stderr": 0.0021472423489400424, "rouge2_recall": 0.21006531093284228, "rouge2_recall_stderr": 0.002273053133823739, "rougeL_fmeasure": 0.2782112735172708, "rougeL_fmeasure_stderr": 0.0017379173406301361, "rougeL_precision": 0.23647123285513574, "rougeL_precision_stderr": 0.0021694427334222896, "rougeL_recall": 0.39302733892651276, "rougeL_recall_stderr": 0.0026453773863021526, "rougeLsum_fmeasure": 0.2838669853732326, "rougeLsum_fmeasure_stderr": 0.0022710804975857187, "rougeLsum_precision": 0.24330576145803912, "rougeLsum_precision_stderr": 0.0025941508735257053, "rougeLsum_recall": 0.3957393841813685, "rougeLsum_recall_stderr": 0.0030500827793352625}}, "1": {"generate_text_restaurant": {"bleu": 12.182758345079787, "bleu_stderr": 0.16518841123830086, "rouge1_fmeasure": 0.4813086962286221, "rouge1_fmeasure_stderr": 0.0023626326089443398, "rouge1_precision": 0.6058724528221369, "rouge1_precision_stderr": 0.0033311930729353, "rouge1_recall": 0.4375685096869626, "rouge1_recall_stderr": 0.003004503828354488, "rouge2_fmeasure": 0.23028289344422687, "rouge2_fmeasure_stderr": 0.0021131218145040835, "rouge2_precision": 0.29572879977984745, "rouge2_precision_stderr": 0.0029383694383037506, "rouge2_recall": 0.20878267638207582, "rouge2_recall_stderr": 0.002207007421280634, "rougeL_fmeasure": 0.3505103154607651, "rougeL_fmeasure_stderr": 0.002138758436636428, "rougeL_precision": 0.4452525524920764, "rougeL_precision_stderr": 0.003155514665754343, "rougeL_recall": 0.31741659640932457, "rougeL_recall_stderr": 0.0024579048629975297, "rougeLsum_fmeasure": 0.39279988924924625, "rougeLsum_fmeasure_stderr": 0.002377886979824964, "rougeLsum_precision": 0.4958740637334028, "rougeLsum_precision_stderr": 0.0033266551400865404, "rougeLsum_recall": 0.356592637216114, "rougeLsum_recall_stderr": 0.0027567285724463706}}, "2": {"generate_text_restaurant": {"bleu": 14.77827774961412, "bleu_stderr": 0.17074445414549996, "rouge1_fmeasure": 0.5169724859470212, "rouge1_fmeasure_stderr": 0.0022847828063681107, "rouge1_precision": 0.6222132815532128, "rouge1_precision_stderr": 0.0032116680629870925, "rouge1_recall": 0.4773787870946972, "rouge1_recall_stderr": 0.002880300695039262, "rouge2_fmeasure": 0.2598408586362927, "rouge2_fmeasure_stderr": 0.002199049529931736, "rouge2_precision": 0.31734278580959246, "rouge2_precision_stderr": 0.002901203617815359, "rouge2_recall": 0.23934523412335545, "rouge2_recall_stderr": 0.0022881777132200292, "rougeL_fmeasure": 0.37830224304770604, "rougeL_fmeasure_stderr": 0.0021704191814246308, "rougeL_precision": 0.45801859712166865, "rougeL_precision_stderr": 0.0030651884383412443, "rougeL_recall": 0.3483543845938943, "rougeL_recall_stderr": 0.002450753947224449, "rougeLsum_fmeasure": 0.42874770680726115, "rougeLsum_fmeasure_stderr": 0.00239536120318971, "rougeLsum_precision": 0.5166167827562745, "rougeLsum_precision_stderr": 0.003243801734266107, "rougeLsum_recall": 0.3956919145577125, "rougeLsum_recall_stderr": 0.002759335166433648}}, "3": {"generate_text_restaurant": {"bleu": 15.660507663936528, "bleu_stderr": 0.14749957372060007, "rouge1_fmeasure": 0.5280713486662109, "rouge1_fmeasure_stderr": 0.0022869985346214445, "rouge1_precision": 0.6220372006914571, "rouge1_precision_stderr": 0.0031139706058727593, "rouge1_recall": 0.4921683601168692, "rouge1_recall_stderr": 0.0029083346931655855, "rouge2_fmeasure": 0.26903286770558915, "rouge2_fmeasure_stderr": 0.0022307748577894758, "rouge2_precision": 0.31964099722948836, "rouge2_precision_stderr": 0.002777708595069122, "rouge2_recall": 0.2509916858334456, "rouge2_recall_stderr": 0.0023901154240661446, "rougeL_fmeasure": 0.38565827502841116, "rougeL_fmeasure_stderr": 0.0022144421481799675, "rougeL_precision": 0.455321793928234, "rougeL_precision_stderr": 0.0029321326061168074, "rougeL_recall": 0.35903739623304465, "rougeL_recall_stderr": 0.0025252866229682975, "rougeLsum_fmeasure": 0.4394144928671385, "rougeLsum_fmeasure_stderr": 0.002446885490860059, "rougeLsum_precision": 0.5172893895354551, "rougeLsum_precision_stderr": 0.003153574847912617, "rougeLsum_recall": 0.40954269048002123, "rougeLsum_recall_stderr": 0.002825679167152443}}, "4": {"generate_text_restaurant": {"bleu": 16.046714521986758, "bleu_stderr": 0.20143548468737246, "rouge1_fmeasure": 0.5343300631658281, "rouge1_fmeasure_stderr": 0.002276059193634907, "rouge1_precision": 0.6240126615936337, "rouge1_precision_stderr": 0.00312720979038774, "rouge1_recall": 0.4989840309368499, "rouge1_recall_stderr": 0.0028177351641601373, "rouge2_fmeasure": 0.2724112279454815, "rouge2_fmeasure_stderr": 0.0022911561617215254, "rouge2_precision": 0.3206493529913017, "rouge2_precision_stderr": 0.0028268414398358497, "rouge2_recall": 0.2544472343665272, "rouge2_recall_stderr": 0.0024038250271984246, "rougeL_fmeasure": 0.38733097602553734, "rougeL_fmeasure_stderr": 0.0022465126119210273, "rougeL_precision": 0.4530934873979934, "rougeL_precision_stderr": 0.0029431217749683455, "rougeL_recall": 0.3614836535348617, "rougeL_recall_stderr": 0.0025050776663639207, "rougeLsum_fmeasure": 0.4465935641244627, "rougeLsum_fmeasure_stderr": 0.0024867305930155463, "rougeLsum_precision": 0.5210977780903223, "rougeLsum_precision_stderr": 0.003193746615616614, "rougeLsum_recall": 0.41707944621670306, "rougeLsum_recall_stderr": 0.002802635738849298}}, "5": {"generate_text_restaurant": {"bleu": 16.068878582309953, "bleu_stderr": 0.16081121483163321, "rouge1_fmeasure": 0.5355837269029773, "rouge1_fmeasure_stderr": 0.002256980681599985, "rouge1_precision": 0.6224102862193265, "rouge1_precision_stderr": 0.003110234568961701, "rouge1_recall": 0.500933748593845, "rouge1_recall_stderr": 0.0027924958992030795, "rouge2_fmeasure": 0.27475970807249195, "rouge2_fmeasure_stderr": 0.0022615182075459324, "rouge2_precision": 0.32190257045006593, "rouge2_precision_stderr": 0.0027959933340407817, "rouge2_recall": 0.2569886621162686, "rouge2_recall_stderr": 0.002381426382114005, "rougeL_fmeasure": 0.3914922502865105, "rougeL_fmeasure_stderr": 0.0022467536238069325, "rougeL_precision": 0.45606984360921154, "rougeL_precision_stderr": 0.002956375747033492, "rougeL_recall": 0.3657446339488385, "rougeL_recall_stderr": 0.002509353106433301, "rougeLsum_fmeasure": 0.4482824729485371, "rougeLsum_fmeasure_stderr": 0.002444818682804833, "rougeLsum_precision": 0.5210361752122326, "rougeLsum_precision_stderr": 0.003175466781222956, "rougeLsum_recall": 0.4190489396414274, "rougeLsum_recall_stderr": 0.0027531052100554392}}}, "gem_xsum": {"0": {"article_DOC_summary": {"bleu": 1.9818055644823127, "bleu_stderr": 0.13978823814879407, "rouge1_fmeasure": 0.16636180556058044, "rouge1_fmeasure_stderr": 0.003516551179676636, "rouge1_precision": 0.12872236323811218, "rouge1_precision_stderr": 0.0032462823876021106, "rouge1_recall": 0.2715393984942335, "rouge1_recall_stderr": 0.005900736678094209, "rouge2_fmeasure": 0.03841432091372367, "rouge2_fmeasure_stderr": 0.001586981058162795, "rouge2_precision": 0.028024322491153688, "rouge2_precision_stderr": 0.0011655819703985627, "rouge2_recall": 0.06517448572813263, "rouge2_recall_stderr": 0.002766560068276156, "rougeL_fmeasure": 0.1211817583352299, "rougeL_fmeasure_stderr": 0.0025835665514872593, "rougeL_precision": 0.09534495061706572, "rougeL_precision_stderr": 0.0027658531338571454, "rougeL_recall": 0.19816999370668548, "rougeL_recall_stderr": 0.004414878706261276, "rougeLsum_fmeasure": 0.13466615178498392, "rougeLsum_fmeasure_stderr": 0.002869955857600535, "rougeLsum_precision": 0.10514740754117864, "rougeLsum_precision_stderr": 0.0028961374555318475, "rougeLsum_recall": 0.22067225131355028, "rougeLsum_recall_stderr": 0.004901108311721729}}, "1": {"article_DOC_summary": {"bleu": 2.718621562424974, "bleu_stderr": 0.25634902183378955, "rouge1_fmeasure": 0.2252201544517192, "rouge1_fmeasure_stderr": 0.003572521220076497, "rouge1_precision": 0.23797749292717868, "rouge1_precision_stderr": 0.0044248829684158586, "rouge1_recall": 0.23607563998039394, "rouge1_recall_stderr": 0.0037207865629804763, "rouge2_fmeasure": 0.05054236360888691, "rouge2_fmeasure_stderr": 0.0023023749748183903, "rouge2_precision": 0.05608458865614393, "rouge2_precision_stderr": 0.0026939326656790527, "rouge2_recall": 0.0508692034245319, "rouge2_recall_stderr": 0.0022931658802725287, "rougeL_fmeasure": 0.1713099421580951, "rougeL_fmeasure_stderr": 0.0029320038478532935, "rougeL_precision": 0.18150902719333478, "rougeL_precision_stderr": 0.0036305277559064066, "rougeL_recall": 0.179561582857957, "rougeL_recall_stderr": 0.003045132003822578, "rougeLsum_fmeasure": 0.17382401249824367, "rougeLsum_fmeasure_stderr": 0.0029535439613312367, "rougeLsum_precision": 0.18366739499452403, "rougeLsum_precision_stderr": 0.003629882854081677, "rougeLsum_recall": 0.18297857106589824, "rougeLsum_recall_stderr": 0.003137997544172217}}, "2": {"article_DOC_summary": {"bleu": 3.6613673832300515, "bleu_stderr": 0.29305939325429936, "rouge1_fmeasure": 0.2516525371976862, "rouge1_fmeasure_stderr": 0.0037511199505683374, "rouge1_precision": 0.26927175770553385, "rouge1_precision_stderr": 0.004455761662742256, "rouge1_recall": 0.25342716562216744, "rouge1_recall_stderr": 0.0038549474849294127, "rouge2_fmeasure": 0.06264124531231369, "rouge2_fmeasure_stderr": 0.0025022071058794777, "rouge2_precision": 0.06831364960977458, "rouge2_precision_stderr": 0.0028257306475568847, "rouge2_recall": 0.06217985063286193, "rouge2_recall_stderr": 0.0025187198385362495, "rougeL_fmeasure": 0.19077644710608424, "rougeL_fmeasure_stderr": 0.003126557023491442, "rougeL_precision": 0.20401963131847098, "rougeL_precision_stderr": 0.0036937944194900436, "rougeL_recall": 0.19255452445504442, "rougeL_recall_stderr": 0.0032146416769602863, "rougeLsum_fmeasure": 0.19254279514804024, "rougeLsum_fmeasure_stderr": 0.00313403184014492, "rougeLsum_precision": 0.20564280351844771, "rougeLsum_precision_stderr": 0.003691582561213757, "rougeLsum_recall": 0.1946786446186705, "rougeLsum_recall_stderr": 0.0032424612854966943}}, "3": {"article_DOC_summary": {"bleu": 3.406816013953246, "bleu_stderr": 0.24161861472249982, "rouge1_fmeasure": 0.24229133087381188, "rouge1_fmeasure_stderr": 0.004031858321395662, "rouge1_precision": 0.262476289887743, "rouge1_precision_stderr": 0.004621204276158766, "rouge1_recall": 0.2404612136480006, "rouge1_recall_stderr": 0.004125414843698027, "rouge2_fmeasure": 0.06268337272766085, "rouge2_fmeasure_stderr": 0.0024567035789010046, "rouge2_precision": 0.06842316364282378, "rouge2_precision_stderr": 0.0027647383711749615, "rouge2_recall": 0.061651170011214104, "rouge2_recall_stderr": 0.002429297519350672, "rougeL_fmeasure": 0.18567208218878792, "rougeL_fmeasure_stderr": 0.0033333790452062923, "rougeL_precision": 0.20156202346447022, "rougeL_precision_stderr": 0.003847300881262445, "rougeL_recall": 0.18433196409317407, "rougeL_recall_stderr": 0.0033927670396723853, "rougeLsum_fmeasure": 0.18654971088104422, "rougeLsum_fmeasure_stderr": 0.003345098888199193, "rougeLsum_precision": 0.20245862347934387, "rougeLsum_precision_stderr": 0.003853570083238628, "rougeLsum_recall": 0.18518636196696317, "rougeLsum_recall_stderr": 0.0034107354023354916}}, "4": {"article_DOC_summary": {"bleu": 0.07621103585426778, "bleu_stderr": 0.02328218785956861, "rouge1_fmeasure": 0.06037720875233413, "rouge1_fmeasure_stderr": 0.003756291069253472, "rouge1_precision": 0.069527922152048, "rouge1_precision_stderr": 0.004415548165696612, "rouge1_recall": 0.058255960572026616, "rouge1_recall_stderr": 0.0036893676818933246, "rouge2_fmeasure": 0.016076749046209322, "rouge2_fmeasure_stderr": 0.00155018273945325, "rouge2_precision": 0.01884212610032935, "rouge2_precision_stderr": 0.001864365662358469, "rouge2_recall": 0.01541077730496209, "rouge2_recall_stderr": 0.0015005237179700724, "rougeL_fmeasure": 0.04601022042911696, "rougeL_fmeasure_stderr": 0.002972538395939391, "rougeL_precision": 0.05366548982395334, "rougeL_precision_stderr": 0.003589390411326478, "rougeL_recall": 0.04435979503971948, "rougeL_recall_stderr": 0.0029246377632095007, "rougeLsum_fmeasure": 0.046274903650287996, "rougeLsum_fmeasure_stderr": 0.0029855052852481925, "rougeLsum_precision": 0.05393140916782405, "rougeLsum_precision_stderr": 0.003600323595663311, "rougeLsum_recall": 0.04463374272617106, "rougeLsum_recall_stderr": 0.0029386715942067774}}, "5": {"article_DOC_summary": {"bleu": 1.2907915607447047e-48, "bleu_stderr": 8.181410959491275e-33, "rouge1_fmeasure": 0.0024677589985080198, "rouge1_fmeasure_stderr": 0.0008512467369069438, "rouge1_precision": 0.002519205393633051, "rouge1_precision_stderr": 0.0009010685681674164, "rouge1_recall": 0.002553406526725967, "rouge1_recall_stderr": 0.0008674535432962121, "rouge2_fmeasure": 0.0005053609550867747, "rouge2_fmeasure_stderr": 0.00027556435520113126, "rouge2_precision": 0.0005748785133997738, "rouge2_precision_stderr": 0.00032234854700264514, "rouge2_recall": 0.00047620248785620596, "rouge2_recall_stderr": 0.0002558552981869991, "rougeL_fmeasure": 0.0016858136591016738, "rougeL_fmeasure_stderr": 0.0006017432419253131, "rougeL_precision": 0.001782337656185266, "rougeL_precision_stderr": 0.0006875286151113505, "rougeL_recall": 0.0016948473649144099, "rougeL_recall_stderr": 0.0005810537809262554, "rougeLsum_fmeasure": 0.0017257035629670058, "rougeLsum_fmeasure_stderr": 0.000608227728173233, "rougeLsum_precision": 0.0018196260445811194, "rougeLsum_precision_stderr": 0.0006924871080774834, "rougeLsum_recall": 0.0017377290115696417, "rougeLsum_recall_stderr": 0.0005888117009644554}}}} |