File size: 28,036 Bytes
8263782 |
1 |
{"GEM/web_nlg_en": {"0": {"PALM_prompt": {"bleu": 0.3677810394757023, "bleu_stderr": 0.03281723526619896, "rouge1_fmeasure": 0.11606407601489055, "rouge1_fmeasure_stderr": 0.001969146758246114, "rouge1_precision": 0.07551756953809975, "rouge1_precision_stderr": 0.0014428401024288566, "rouge1_recall": 0.32667793832637043, "rouge1_recall_stderr": 0.0045432759692835755, "rouge2_fmeasure": 0.05525608727734654, "rouge2_fmeasure_stderr": 0.0012506172623425777, "rouge2_precision": 0.0358576440999003, "rouge2_precision_stderr": 0.0009026300665133467, "rouge2_recall": 0.16122516666992529, "rouge2_recall_stderr": 0.003267212716096976, "rougeL_fmeasure": 0.11192452656660684, "rougeL_fmeasure_stderr": 0.00184821865839915, "rougeL_precision": 0.07265841861456275, "rougeL_precision_stderr": 0.0013478808767448548, "rougeL_recall": 0.3173688843344159, "rougeL_recall_stderr": 0.004415574211500117, "rougeLsum_fmeasure": 0.11130422275494882, "rougeLsum_fmeasure_stderr": 0.0018686028478286372, "rougeLsum_precision": 0.07243892580671336, "rougeLsum_precision_stderr": 0.0013760467900819921, "rougeLsum_recall": 0.3134569235593474, "rougeLsum_recall_stderr": 0.004287283373230945}}, "1": {"PALM_prompt": {"bleu": 0.5497938903834476, "bleu_stderr": 0.030329648907717416, "rouge1_fmeasure": 0.12377098272865582, "rouge1_fmeasure_stderr": 0.0018005918585052136, "rouge1_precision": 0.07921341676188258, "rouge1_precision_stderr": 0.0013409822377619385, "rouge1_recall": 0.39870747987203026, "rouge1_recall_stderr": 0.005183434021587761, "rouge2_fmeasure": 0.059610216940881165, "rouge2_fmeasure_stderr": 0.0011877157461269233, "rouge2_precision": 0.037977631085495546, "rouge2_precision_stderr": 0.0008537095990628626, "rouge2_recall": 0.20482620328537757, "rouge2_recall_stderr": 0.003925783970259362, "rougeL_fmeasure": 0.11717642785021219, "rougeL_fmeasure_stderr": 0.001674344616420258, "rougeL_precision": 0.07494409148525415, "rougeL_precision_stderr": 0.0012339020353945417, "rougeL_recall": 0.3749296897875364, "rougeL_recall_stderr": 0.004746737866261382, "rougeLsum_fmeasure": 0.1180104667449292, "rougeLsum_fmeasure_stderr": 0.0017037357470238706, "rougeLsum_precision": 0.07561615649375214, "rougeLsum_precision_stderr": 0.001274630336916664, "rougeLsum_recall": 0.3781401543982665, "rougeLsum_recall_stderr": 0.004772450320283416}}, "2": {"PALM_prompt": {"bleu": 0.6345753558723145, "bleu_stderr": 0.022376664491002615, "rouge1_fmeasure": 0.12360575844131859, "rouge1_fmeasure_stderr": 0.0016749434032436248, "rouge1_precision": 0.07795669324486854, "rouge1_precision_stderr": 0.00119684640928671, "rouge1_recall": 0.41803228663523345, "rouge1_recall_stderr": 0.0053864905798921125, "rouge2_fmeasure": 0.059094553406324295, "rouge2_fmeasure_stderr": 0.0010986707292730262, "rouge2_precision": 0.03697168943889819, "rouge2_precision_stderr": 0.0007524504443837138, "rouge2_recall": 0.21717607459640267, "rouge2_recall_stderr": 0.004101036268432045, "rougeL_fmeasure": 0.1151080347627734, "rougeL_fmeasure_stderr": 0.0015232281204089519, "rougeL_precision": 0.07270569406411607, "rougeL_precision_stderr": 0.0010983482762338668, "rougeL_recall": 0.38609502456284567, "rougeL_recall_stderr": 0.004797386037833962, "rougeLsum_fmeasure": 0.11783674396217436, "rougeLsum_fmeasure_stderr": 0.0015879949279193565, "rougeLsum_precision": 0.07442415306126304, "rougeLsum_precision_stderr": 0.0011448850348819214, "rougeLsum_recall": 0.396883636105679, "rougeLsum_recall_stderr": 0.0049884922683259055}}, "3": {"PALM_prompt": {"bleu": 0.6611202603466564, "bleu_stderr": 0.026292760196011896, "rouge1_fmeasure": 0.12270682587650009, "rouge1_fmeasure_stderr": 0.001689827532535868, "rouge1_precision": 0.07720993388700956, "rouge1_precision_stderr": 0.0012101497257156794, "rouge1_recall": 0.4133639192496906, "rouge1_recall_stderr": 0.005411628648726416, "rouge2_fmeasure": 0.05861591086080908, "rouge2_fmeasure_stderr": 0.0010907460831452867, "rouge2_precision": 0.03655832324841317, "rouge2_precision_stderr": 0.0007506453443122757, "rouge2_recall": 0.21585685095591742, "rouge2_recall_stderr": 0.004093725567157412, "rougeL_fmeasure": 0.11361332097070079, "rougeL_fmeasure_stderr": 0.0015022331310385422, "rougeL_precision": 0.07151482183987531, "rougeL_precision_stderr": 0.001086199341044554, "rougeL_recall": 0.3823649104455851, "rougeL_recall_stderr": 0.004813722726129101, "rougeLsum_fmeasure": 0.11674347677370367, "rougeLsum_fmeasure_stderr": 0.0015911049077229342, "rougeLsum_precision": 0.07350481492884033, "rougeLsum_precision_stderr": 0.0011485603851221294, "rougeLsum_recall": 0.39303289732256513, "rougeLsum_recall_stderr": 0.005032921309423209}}, "4": {"PALM_prompt": {"bleu": 0.7128978831232388, "bleu_stderr": 0.03892571091725707, "rouge1_fmeasure": 0.12369444007480314, "rouge1_fmeasure_stderr": 0.0016461113907076013, "rouge1_precision": 0.07777752463393256, "rouge1_precision_stderr": 0.0011834566593491008, "rouge1_recall": 0.4222346728535934, "rouge1_recall_stderr": 0.005371874334785877, "rouge2_fmeasure": 0.05896624699685776, "rouge2_fmeasure_stderr": 0.0010852712903198752, "rouge2_precision": 0.03670980373588488, "rouge2_precision_stderr": 0.0007435896517793837, "rouge2_recall": 0.2212321108756897, "rouge2_recall_stderr": 0.004139207390440789, "rougeL_fmeasure": 0.11384905074014122, "rougeL_fmeasure_stderr": 0.00146289053656463, "rougeL_precision": 0.07163006841296378, "rougeL_precision_stderr": 0.001061488881603934, "rougeL_recall": 0.3878434903814413, "rougeL_recall_stderr": 0.004773394354686469, "rougeLsum_fmeasure": 0.11795118372977331, "rougeLsum_fmeasure_stderr": 0.001557940253935983, "rougeLsum_precision": 0.07421506767947293, "rougeLsum_precision_stderr": 0.001124685544226384, "rougeLsum_recall": 0.40133513783035873, "rougeLsum_recall_stderr": 0.005016786537745759}}, "5": {"PALM_prompt": {"bleu": 0.7296500968020738, "bleu_stderr": 0.03986679058747073, "rouge1_fmeasure": 0.12440202385333685, "rouge1_fmeasure_stderr": 0.0016439820305072118, "rouge1_precision": 0.07793578273286862, "rouge1_precision_stderr": 0.001170086916396576, "rouge1_recall": 0.4293926231707037, "rouge1_recall_stderr": 0.005544216357063792, "rouge2_fmeasure": 0.059676320234352584, "rouge2_fmeasure_stderr": 0.0010914957404078694, "rouge2_precision": 0.03706679304975263, "rouge2_precision_stderr": 0.0007461793226765045, "rouge2_recall": 0.22614254310251874, "rouge2_recall_stderr": 0.004258603721661164, "rougeL_fmeasure": 0.11426293462896298, "rougeL_fmeasure_stderr": 0.001470255169191014, "rougeL_precision": 0.07171154548923617, "rougeL_precision_stderr": 0.001063717283795246, "rougeL_recall": 0.39264622495319934, "rougeL_recall_stderr": 0.004853098099750933, "rougeLsum_fmeasure": 0.11846322387156706, "rougeLsum_fmeasure_stderr": 0.0015476540324461025, "rougeLsum_precision": 0.07430376688251292, "rougeLsum_precision_stderr": 0.0011115454477617379, "rougeLsum_recall": 0.40784183583085276, "rougeLsum_recall_stderr": 0.005148423771775361}}}, "GEM/wiki_lingua_en": {"0": {"tldr_en": {"bleu": 1.6588537886073913, "bleu_stderr": 0.0443627487585664, "rouge1_fmeasure": 0.1771116987872097, "rouge1_fmeasure_stderr": 0.0019001225147585595, "rouge1_precision": 0.15071008120560497, "rouge1_precision_stderr": 0.0019169944124831117, "rouge1_recall": 0.2615215631789747, "rouge1_recall_stderr": 0.0028587647553713004, "rouge2_fmeasure": 0.037350220833466265, "rouge2_fmeasure_stderr": 0.0009013013631899656, "rouge2_precision": 0.03154759752710423, "rouge2_precision_stderr": 0.0007938342962238314, "rouge2_recall": 0.05718093036037643, "rouge2_recall_stderr": 0.0015126905612736802, "rougeL_fmeasure": 0.1360411096046868, "rougeL_fmeasure_stderr": 0.0013491547776702593, "rougeL_precision": 0.11439573579669693, "rougeL_precision_stderr": 0.0013313396769038728, "rougeL_recall": 0.2058353141373366, "rougeL_recall_stderr": 0.0022855149086852887, "rougeLsum_fmeasure": 0.16367916861611936, "rougeLsum_fmeasure_stderr": 0.0017419145199993307, "rougeLsum_precision": 0.13909515224541577, "rougeLsum_precision_stderr": 0.0017556231845242017, "rougeLsum_recall": 0.24244042499581767, "rougeLsum_recall_stderr": 0.0026519653366143562}}, "1": {"tldr_en": {"bleu": 3.5656470388016652, "bleu_stderr": 0.08197311523066556, "rouge1_fmeasure": 0.24342094967396746, "rouge1_fmeasure_stderr": 0.002061008293601447, "rouge1_precision": 0.2174735691686053, "rouge1_precision_stderr": 0.0024727115624900444, "rouge1_recall": 0.3460178647953164, "rouge1_recall_stderr": 0.0029105441665587413, "rouge2_fmeasure": 0.06579562483959114, "rouge2_fmeasure_stderr": 0.0012229149405673168, "rouge2_precision": 0.05974334784565509, "rouge2_precision_stderr": 0.0013520311423251665, "rouge2_recall": 0.09579105477293766, "rouge2_recall_stderr": 0.0019333447701627138, "rougeL_fmeasure": 0.1715894965219696, "rougeL_fmeasure_stderr": 0.0014647407258985053, "rougeL_precision": 0.15264641094715217, "rougeL_precision_stderr": 0.0017989249509303383, "rougeL_recall": 0.24988397509922583, "rougeL_recall_stderr": 0.0023954858097757943, "rougeLsum_fmeasure": 0.2293964977081046, "rougeLsum_fmeasure_stderr": 0.0019478558777254497, "rougeLsum_precision": 0.20485722652733274, "rougeLsum_precision_stderr": 0.002345428003149735, "rougeLsum_recall": 0.32704916730419714, "rougeLsum_recall_stderr": 0.0027965860033602368}}, "2": {"tldr_en": {"bleu": 4.105745383260244, "bleu_stderr": 0.08432146375641045, "rouge1_fmeasure": 0.24748860335539324, "rouge1_fmeasure_stderr": 0.0020650327174219227, "rouge1_precision": 0.23457091267008237, "rouge1_precision_stderr": 0.0027679657131044456, "rouge1_recall": 0.34134267442562116, "rouge1_recall_stderr": 0.0029201119619592353, "rouge2_fmeasure": 0.07016193751579543, "rouge2_fmeasure_stderr": 0.0012709364243235631, "rouge2_precision": 0.06809717111480851, "rouge2_precision_stderr": 0.0015408937269110604, "rouge2_recall": 0.09908181073861143, "rouge2_recall_stderr": 0.001996906692665077, "rougeL_fmeasure": 0.17762855895363824, "rougeL_fmeasure_stderr": 0.0015104607154289617, "rougeL_precision": 0.16899767873052451, "rougeL_precision_stderr": 0.0021331406852508664, "rougeL_recall": 0.24978190911695647, "rougeL_recall_stderr": 0.0024029557797763655, "rougeLsum_fmeasure": 0.23449572227657609, "rougeLsum_fmeasure_stderr": 0.001955519333700258, "rougeLsum_precision": 0.22219258646455792, "rougeLsum_precision_stderr": 0.0026321839454086595, "rougeLsum_recall": 0.32435218510070457, "rougeLsum_recall_stderr": 0.002817151691787598}}, "3": {"tldr_en": {"bleu": 4.150193084650233, "bleu_stderr": 0.11031172513046578, "rouge1_fmeasure": 0.20579755698645813, "rouge1_fmeasure_stderr": 0.0024814106035235444, "rouge1_precision": 0.2018448766253913, "rouge1_precision_stderr": 0.003073161400459354, "rouge1_recall": 0.28172071543272187, "rouge1_recall_stderr": 0.003594746473409513, "rouge2_fmeasure": 0.057766738614790786, "rouge2_fmeasure_stderr": 0.001223860321221621, "rouge2_precision": 0.05693855985307953, "rouge2_precision_stderr": 0.0014354920153072253, "rouge2_recall": 0.08217428533466181, "rouge2_recall_stderr": 0.001967375414041398, "rougeL_fmeasure": 0.14896417876723742, "rougeL_fmeasure_stderr": 0.001816503510484197, "rougeL_precision": 0.14712383510443716, "rougeL_precision_stderr": 0.002367934256298009, "rougeL_recall": 0.2074931184166513, "rougeL_recall_stderr": 0.002842631573610709, "rougeLsum_fmeasure": 0.19498864236687288, "rougeLsum_fmeasure_stderr": 0.0023499776362643178, "rougeLsum_precision": 0.19153153433363726, "rougeLsum_precision_stderr": 0.002934568467456808, "rougeLsum_recall": 0.2671010109221112, "rougeLsum_recall_stderr": 0.003425037370895828}}, "4": {"tldr_en": {"bleu": 0.7482733498786457, "bleu_stderr": 0.04289432927446872, "rouge1_fmeasure": 0.0638872592550199, "rouge1_fmeasure_stderr": 0.0021736088152739283, "rouge1_precision": 0.06276227014065545, "rouge1_precision_stderr": 0.0023884276241260254, "rouge1_recall": 0.09152089229465758, "rouge1_recall_stderr": 0.003170681109109529, "rouge2_fmeasure": 0.017492971654085164, "rouge2_fmeasure_stderr": 0.0008455647267737554, "rouge2_precision": 0.016993816746714407, "rouge2_precision_stderr": 0.0009445450958091424, "rouge2_recall": 0.026516974130858528, "rouge2_recall_stderr": 0.0013633238440930392, "rougeL_fmeasure": 0.04716945018429479, "rougeL_fmeasure_stderr": 0.0016102955217448768, "rougeL_precision": 0.04661295129618777, "rougeL_precision_stderr": 0.0018307969366172505, "rougeL_recall": 0.06895783497739912, "rougeL_recall_stderr": 0.002463509315480347, "rougeLsum_fmeasure": 0.06053208461846568, "rougeLsum_fmeasure_stderr": 0.002064190262965029, "rougeLsum_precision": 0.059550490378451754, "rougeLsum_precision_stderr": 0.0022812820815524093, "rougeLsum_recall": 0.08666480644593474, "rougeLsum_recall_stderr": 0.003010285669141728}}, "5": {"tldr_en": {"bleu": 1.2541436019570651e-06, "bleu_stderr": 3.589754879521194e-06, "rouge1_fmeasure": 0.010963700281898832, "rouge1_fmeasure_stderr": 0.001016356199855156, "rouge1_precision": 0.01062569815388256, "rouge1_precision_stderr": 0.001044931714423556, "rouge1_recall": 0.015829449605584002, "rouge1_recall_stderr": 0.0014988937828031954, "rouge2_fmeasure": 0.0031213037008769227, "rouge2_fmeasure_stderr": 0.00038874767150106574, "rouge2_precision": 0.002965306348837173, "rouge2_precision_stderr": 0.00039542449556901336, "rouge2_recall": 0.004883623633485144, "rouge2_recall_stderr": 0.0006415779749258939, "rougeL_fmeasure": 0.00827136001527878, "rougeL_fmeasure_stderr": 0.0007741743267056739, "rougeL_precision": 0.00810568450656589, "rougeL_precision_stderr": 0.0008158965824147807, "rougeL_recall": 0.012260844933610076, "rougeL_recall_stderr": 0.0012027923697108917, "rougeLsum_fmeasure": 0.010362958827854624, "rougeLsum_fmeasure_stderr": 0.0009617992097751725, "rougeLsum_precision": 0.010057343739525522, "rougeLsum_precision_stderr": 0.0009929081454170272, "rougeLsum_recall": 0.0149839670075284, "rougeLsum_recall_stderr": 0.0014220508785650803}}}, "e2e_nlg_cleaned": {"0": {"generate_text_restaurant": {"bleu": 0.0829790820445851, "bleu_stderr": 0.02197797601631595, "rouge1_fmeasure": 0.10446518863159925, "rouge1_fmeasure_stderr": 0.000777744935734902, "rouge1_precision": 0.07862879559521596, "rouge1_precision_stderr": 0.0006642205609450126, "rouge1_recall": 0.16475897375079807, "rouge1_recall_stderr": 0.0011383196654042192, "rouge2_fmeasure": 0.009544918858239404, "rouge2_fmeasure_stderr": 0.00027235599690889593, "rouge2_precision": 0.007369812030601589, "rouge2_precision_stderr": 0.00021896094396311517, "rouge2_recall": 0.014262052938121144, "rouge2_recall_stderr": 0.0004147127585356459, "rougeL_fmeasure": 0.1010125389757392, "rougeL_fmeasure_stderr": 0.0007159378810539217, "rougeL_precision": 0.07591871687158004, "rougeL_precision_stderr": 0.000610191190689566, "rougeL_recall": 0.1597865992371287, "rougeL_recall_stderr": 0.0010790075675615354, "rougeLsum_fmeasure": 0.08956898548608715, "rougeLsum_fmeasure_stderr": 0.0006418100960192206, "rougeLsum_precision": 0.0673047657702021, "rougeLsum_precision_stderr": 0.0005522793921438968, "rougeLsum_recall": 0.14195098898955258, "rougeLsum_recall_stderr": 0.0009730497278821901}}, "1": {"generate_text_restaurant": {"bleu": 10.908919859430615, "bleu_stderr": 0.16637332277469416, "rouge1_fmeasure": 0.43946652639475914, "rouge1_fmeasure_stderr": 0.0020459488608388305, "rouge1_precision": 0.4456385087012675, "rouge1_precision_stderr": 0.002353995044749726, "rouge1_recall": 0.47020454378467724, "rouge1_recall_stderr": 0.002936861869075764, "rouge2_fmeasure": 0.19809860044914396, "rouge2_fmeasure_stderr": 0.0017761118795827473, "rouge2_precision": 0.20055830506980424, "rouge2_precision_stderr": 0.0018894709575218048, "rouge2_recall": 0.2135715698673984, "rouge2_recall_stderr": 0.002164535077464, "rougeL_fmeasure": 0.31158605078339746, "rougeL_fmeasure_stderr": 0.0017722355642195858, "rougeL_precision": 0.31683119553670347, "rougeL_precision_stderr": 0.00202952794744226, "rougeL_recall": 0.33327675710241655, "rougeL_recall_stderr": 0.0023834364279679216, "rougeLsum_fmeasure": 0.36402615233989766, "rougeLsum_fmeasure_stderr": 0.0020471793436135748, "rougeLsum_precision": 0.36992976009148365, "rougeLsum_precision_stderr": 0.0023186341348778463, "rougeLsum_recall": 0.38880934305270765, "rougeLsum_recall_stderr": 0.0027097894189422028}}, "2": {"generate_text_restaurant": {"bleu": 12.496024480959404, "bleu_stderr": 0.17088930912135533, "rouge1_fmeasure": 0.46766982775713095, "rouge1_fmeasure_stderr": 0.001918126464011959, "rouge1_precision": 0.46513050554651497, "rouge1_precision_stderr": 0.002223586404391749, "rouge1_recall": 0.5044545963797141, "rouge1_recall_stderr": 0.0028151136740913597, "rouge2_fmeasure": 0.22321575010543798, "rouge2_fmeasure_stderr": 0.0018224289381751444, "rouge2_precision": 0.22174324642559978, "rouge2_precision_stderr": 0.0019100067340740226, "rouge2_recall": 0.24291920242568943, "rouge2_recall_stderr": 0.0022611578365930884, "rougeL_fmeasure": 0.3381497040905446, "rougeL_fmeasure_stderr": 0.0017546749447990841, "rougeL_precision": 0.3367051458657208, "rougeL_precision_stderr": 0.001973018443090721, "rougeL_recall": 0.36493130556649644, "rougeL_recall_stderr": 0.002393148715464209, "rougeLsum_fmeasure": 0.3916198529515355, "rougeLsum_fmeasure_stderr": 0.0020225802259552245, "rougeLsum_precision": 0.3898243742937925, "rougeLsum_precision_stderr": 0.002253177427026344, "rougeLsum_recall": 0.421949500869911, "rougeLsum_recall_stderr": 0.002689886396084085}}, "3": {"generate_text_restaurant": {"bleu": 12.876624238007336, "bleu_stderr": 0.13633367748001868, "rouge1_fmeasure": 0.47400023722312934, "rouge1_fmeasure_stderr": 0.001900202291806821, "rouge1_precision": 0.4666088727251901, "rouge1_precision_stderr": 0.0022313332553631853, "rouge1_recall": 0.5154695171919821, "rouge1_recall_stderr": 0.0027754047400933637, "rouge2_fmeasure": 0.2289130980630063, "rouge2_fmeasure_stderr": 0.0018363466703835796, "rouge2_precision": 0.2243865656346707, "rouge2_precision_stderr": 0.0018719494043509864, "rouge2_recall": 0.25156840321883794, "rouge2_recall_stderr": 0.0023063040992685763, "rougeL_fmeasure": 0.34349469052543125, "rougeL_fmeasure_stderr": 0.0017677223953016846, "rougeL_precision": 0.3380898171473523, "rougeL_precision_stderr": 0.0019534178000102315, "rougeL_recall": 0.37434995371411073, "rougeL_recall_stderr": 0.002444470010384392, "rougeLsum_fmeasure": 0.3977755285897407, "rougeLsum_fmeasure_stderr": 0.0020093339319118943, "rougeLsum_precision": 0.39156150543550683, "rougeLsum_precision_stderr": 0.0022264717816469198, "rougeLsum_recall": 0.43267538620734924, "rougeLsum_recall_stderr": 0.0027083330913664685}}, "4": {"generate_text_restaurant": {"bleu": 13.038419795082826, "bleu_stderr": 0.1976428408924392, "rouge1_fmeasure": 0.47584611404695387, "rouge1_fmeasure_stderr": 0.001947074296264647, "rouge1_precision": 0.466899050531228, "rouge1_precision_stderr": 0.0022803800444716094, "rouge1_recall": 0.5180929741571967, "rouge1_recall_stderr": 0.0027666521523327485, "rouge2_fmeasure": 0.2331128191296418, "rouge2_fmeasure_stderr": 0.0018880871361337953, "rouge2_precision": 0.22797984329863402, "rouge2_precision_stderr": 0.0019493427856802211, "rouge2_recall": 0.2562999197032082, "rouge2_recall_stderr": 0.002335812648509201, "rougeL_fmeasure": 0.34478040188814424, "rougeL_fmeasure_stderr": 0.0018168580160894932, "rougeL_precision": 0.33801665068739845, "rougeL_precision_stderr": 0.0019999447186985647, "rougeL_recall": 0.37648151811835306, "rougeL_recall_stderr": 0.0024685261116801542, "rougeLsum_fmeasure": 0.40002040198984967, "rougeLsum_fmeasure_stderr": 0.00209065471547177, "rougeLsum_precision": 0.3924955108326523, "rougeLsum_precision_stderr": 0.0023101764008543304, "rougeLsum_recall": 0.4357423190744161, "rougeLsum_recall_stderr": 0.0027563832782966625}}, "5": {"generate_text_restaurant": {"bleu": 12.732763368074703, "bleu_stderr": 0.17590369930486258, "rouge1_fmeasure": 0.47424433103008173, "rouge1_fmeasure_stderr": 0.0019121232239086051, "rouge1_precision": 0.46421051231524674, "rouge1_precision_stderr": 0.002228291979514538, "rouge1_recall": 0.5154379150999142, "rouge1_recall_stderr": 0.0026933286526690937, "rouge2_fmeasure": 0.22941163204827142, "rouge2_fmeasure_stderr": 0.001863304249033461, "rouge2_precision": 0.2240248553808123, "rouge2_precision_stderr": 0.001895223667089071, "rouge2_recall": 0.2513696885147789, "rouge2_recall_stderr": 0.0022849010356271104, "rougeL_fmeasure": 0.34311455561819293, "rougeL_fmeasure_stderr": 0.001783681336394135, "rougeL_precision": 0.3353528060064174, "rougeL_precision_stderr": 0.0019239210092200653, "rougeL_recall": 0.37390031423496406, "rougeL_recall_stderr": 0.0023965157476151687, "rougeLsum_fmeasure": 0.3973658692506892, "rougeLsum_fmeasure_stderr": 0.0020284980495066177, "rougeLsum_precision": 0.38889217013284716, "rougeLsum_precision_stderr": 0.0022276201914498226, "rougeLsum_recall": 0.43194157222453305, "rougeLsum_recall_stderr": 0.002653041029715851}}}, "gem_xsum": {"0": {"article_DOC_summary": {"bleu": 2.379481370668616, "bleu_stderr": 0.06717438559240217, "rouge1_fmeasure": 0.22307907562150814, "rouge1_fmeasure_stderr": 0.002574919259740255, "rouge1_precision": 0.1641976469365769, "rouge1_precision_stderr": 0.0020666411427313226, "rouge1_recall": 0.3769795179589196, "rouge1_recall_stderr": 0.004557040772745154, "rouge2_fmeasure": 0.05581311382540214, "rouge2_fmeasure_stderr": 0.0017319768283373825, "rouge2_precision": 0.040059412047117826, "rouge2_precision_stderr": 0.0012577854209926665, "rouge2_recall": 0.09876412540351458, "rouge2_recall_stderr": 0.0031994931770752293, "rougeL_fmeasure": 0.16469766371025393, "rougeL_fmeasure_stderr": 0.0019416684869235467, "rougeL_precision": 0.12066732888153141, "rougeL_precision_stderr": 0.001491352270771391, "rougeL_recall": 0.2811429796223486, "rougeL_recall_stderr": 0.0036958208158303246, "rougeLsum_fmeasure": 0.1764735128921134, "rougeLsum_fmeasure_stderr": 0.0022058663139781407, "rougeLsum_precision": 0.12918261249170612, "rougeLsum_precision_stderr": 0.0016727035049342064, "rougeLsum_recall": 0.30129412715173376, "rougeLsum_recall_stderr": 0.0041384700689898295}}, "1": {"article_DOC_summary": {"bleu": 2.0057184143447615, "bleu_stderr": 0.10784776015193966, "rouge1_fmeasure": 0.19977490507493711, "rouge1_fmeasure_stderr": 0.0027304130941086407, "rouge1_precision": 0.14227928785850447, "rouge1_precision_stderr": 0.002038647007352537, "rouge1_recall": 0.3496445389327938, "rouge1_recall_stderr": 0.004687420539003245, "rouge2_fmeasure": 0.04842756093378267, "rouge2_fmeasure_stderr": 0.0016766359525896973, "rouge2_precision": 0.0341741556467082, "rouge2_precision_stderr": 0.0011919230006458453, "rouge2_recall": 0.0868085117734084, "rouge2_recall_stderr": 0.0030751950321611407, "rougeL_fmeasure": 0.15299299492001714, "rougeL_fmeasure_stderr": 0.0020609720286366845, "rougeL_precision": 0.1087255275926617, "rougeL_precision_stderr": 0.0015201339104374042, "rougeL_recall": 0.26941360644447593, "rougeL_recall_stderr": 0.0036873426379033505, "rougeLsum_fmeasure": 0.1598451013344069, "rougeLsum_fmeasure_stderr": 0.0023180038401233254, "rougeLsum_precision": 0.11362838643634136, "rougeLsum_precision_stderr": 0.0017063249170823618, "rougeLsum_recall": 0.28136113073762375, "rougeLsum_recall_stderr": 0.0041294851110808455}}, "2": {"article_DOC_summary": {"bleu": 2.2208813740601956, "bleu_stderr": 0.08894604311937805, "rouge1_fmeasure": 0.208834898706681, "rouge1_fmeasure_stderr": 0.0026978364031301984, "rouge1_precision": 0.14892949469644043, "rouge1_precision_stderr": 0.00200583160476678, "rouge1_recall": 0.3634135497733337, "rouge1_recall_stderr": 0.004671515326255189, "rouge2_fmeasure": 0.05372147678733591, "rouge2_fmeasure_stderr": 0.0017727625629579478, "rouge2_precision": 0.037878856143553255, "rouge2_precision_stderr": 0.0012582826871233468, "rouge2_recall": 0.09625625668090708, "rouge2_recall_stderr": 0.0032497068654648584, "rougeL_fmeasure": 0.1628407034853261, "rougeL_fmeasure_stderr": 0.0020951830521425178, "rougeL_precision": 0.11593507352191997, "rougeL_precision_stderr": 0.0015458134885275524, "rougeL_recall": 0.2849234476380913, "rougeL_recall_stderr": 0.0037398830811592306, "rougeLsum_fmeasure": 0.16488303511797936, "rougeLsum_fmeasure_stderr": 0.0022824435253937184, "rougeLsum_precision": 0.1172906648583005, "rougeLsum_precision_stderr": 0.0016670598084846545, "rougeLsum_recall": 0.2888804067318797, "rougeLsum_recall_stderr": 0.004097916730726731}}, "3": {"article_DOC_summary": {"bleu": 2.2460570125021815, "bleu_stderr": 0.09639536279310482, "rouge1_fmeasure": 0.203288145377478, "rouge1_fmeasure_stderr": 0.002902549912894558, "rouge1_precision": 0.14794374341275107, "rouge1_precision_stderr": 0.0022457907635443767, "rouge1_recall": 0.34719811012821766, "rouge1_recall_stderr": 0.0049938759471077005, "rouge2_fmeasure": 0.05387889032218581, "rouge2_fmeasure_stderr": 0.0017118408282623175, "rouge2_precision": 0.038373258945208606, "rouge2_precision_stderr": 0.0012224763268285, "rouge2_recall": 0.09516942967025471, "rouge2_recall_stderr": 0.0031451684639885744, "rougeL_fmeasure": 0.15948452331329185, "rougeL_fmeasure_stderr": 0.0022439870906278744, "rougeL_precision": 0.11596978873700024, "rougeL_precision_stderr": 0.0017382600731524656, "rougeL_recall": 0.2738718049202109, "rougeL_recall_stderr": 0.00398280173794519, "rougeLsum_fmeasure": 0.16072503506629401, "rougeLsum_fmeasure_stderr": 0.002448676603417113, "rougeLsum_precision": 0.11685891599330396, "rougeLsum_precision_stderr": 0.001878971804961673, "rougeLsum_recall": 0.2761128747693524, "rougeLsum_recall_stderr": 0.004338710723283792}}, "4": {"article_DOC_summary": {"bleu": 1.217900205097583, "bleu_stderr": 0.16547330167199492, "rouge1_fmeasure": 0.05559972270834411, "rouge1_fmeasure_stderr": 0.0030493540636307315, "rouge1_precision": 0.045641403513942344, "rouge1_precision_stderr": 0.0026877928553966255, "rouge1_recall": 0.08792590860532339, "rouge1_recall_stderr": 0.004951100510662503, "rouge2_fmeasure": 0.01431853871406581, "rouge2_fmeasure_stderr": 0.0011857334383597357, "rouge2_precision": 0.011710935455623647, "rouge2_precision_stderr": 0.0012861915474572897, "rouge2_recall": 0.02368119469360542, "rouge2_recall_stderr": 0.001960136241976673, "rougeL_fmeasure": 0.04491432061444308, "rougeL_fmeasure_stderr": 0.0024680842086334605, "rougeL_precision": 0.03727739770750944, "rougeL_precision_stderr": 0.0022705131920867042, "rougeL_recall": 0.07104571554164463, "rougeL_recall_stderr": 0.004021066125324381, "rougeLsum_fmeasure": 0.044904907347443464, "rougeLsum_fmeasure_stderr": 0.002501946586732125, "rougeLsum_precision": 0.03735291149683435, "rougeLsum_precision_stderr": 0.002314584651645963, "rougeLsum_recall": 0.07107549567098383, "rougeLsum_recall_stderr": 0.004070397888407412}}, "5": {"article_DOC_summary": {"bleu": 3.69574011869292e-17, "bleu_stderr": 2.684261446109072e-14, "rouge1_fmeasure": 0.002984428901393074, "rouge1_fmeasure_stderr": 0.0008077475320402855, "rouge1_precision": 0.0025215542744389413, "rouge1_precision_stderr": 0.0007044520139374636, "rouge1_recall": 0.004537012002175192, "rouge1_recall_stderr": 0.0012541613619486166, "rouge2_fmeasure": 0.000431120989446868, "rouge2_fmeasure_stderr": 0.00019695106711284816, "rouge2_precision": 0.0003456350518315212, "rouge2_precision_stderr": 0.00015654732477210276, "rouge2_recall": 0.0006329432975265091, "rouge2_recall_stderr": 0.00028793862001474474, "rougeL_fmeasure": 0.002060124493547919, "rougeL_fmeasure_stderr": 0.0005846305244422877, "rougeL_precision": 0.0017146833815532188, "rougeL_precision_stderr": 0.0004901362650343392, "rougeL_recall": 0.003097704549940136, "rougeL_recall_stderr": 0.000885003553914414, "rougeLsum_fmeasure": 0.0023450606462443726, "rougeLsum_fmeasure_stderr": 0.0006698668342557274, "rougeLsum_precision": 0.0019763029300951048, "rougeLsum_precision_stderr": 0.000583997721778465, "rougeLsum_recall": 0.003481088798128124, "rougeLsum_recall_stderr": 0.0009743709994872758}}}} |