| {"GEM/web_nlg_en": {"0": {"PALM_prompt": {"bleu": 0.30438087878461806, "bleu_stderr": 0.027985398209556842, "rouge1_fmeasure": 0.10072645925520833, "rouge1_fmeasure_stderr": 0.001803334386023207, "rouge1_precision": 0.06571872727613429, "rouge1_precision_stderr": 0.0014178747302171335, "rouge1_recall": 0.28999616131453776, "rouge1_recall_stderr": 0.00434042822819289, "rouge2_fmeasure": 0.046598784604859486, "rouge2_fmeasure_stderr": 0.0011368379760255077, "rouge2_precision": 0.030429296094824455, "rouge2_precision_stderr": 0.0008978277172003451, "rouge2_recall": 0.13772743526874254, "rouge2_recall_stderr": 0.0029713701289473594, "rougeL_fmeasure": 0.09804723740892954, "rougeL_fmeasure_stderr": 0.001738122594593388, "rougeL_precision": 0.06388836453568124, "rougeL_precision_stderr": 0.0013632881297082904, "rougeL_recall": 0.28363499948165843, "rougeL_recall_stderr": 0.004278943131293478, "rougeLsum_fmeasure": 0.09688278752987489, "rougeLsum_fmeasure_stderr": 0.0017265830325622752, "rougeLsum_precision": 0.06323531180120187, "rougeLsum_precision_stderr": 0.0013639142517225444, "rougeLsum_recall": 0.2788262564249966, "rougeLsum_recall_stderr": 0.004155727073631924}}, "1": {"PALM_prompt": {"bleu": 0.3677620101657523, "bleu_stderr": 0.02209751845324868, "rouge1_fmeasure": 0.10743506199331603, "rouge1_fmeasure_stderr": 0.0017479884253783432, "rouge1_precision": 0.06882276794192525, "rouge1_precision_stderr": 0.001269726775890253, "rouge1_recall": 0.3358838633226288, "rouge1_recall_stderr": 0.004944830474767479, "rouge2_fmeasure": 0.050065381446004406, "rouge2_fmeasure_stderr": 0.0011139596034513608, "rouge2_precision": 0.03198910527175372, "rouge2_precision_stderr": 0.0007904311483238523, "rouge2_recall": 0.1639727133230724, "rouge2_recall_stderr": 0.0035115320297904157, "rougeL_fmeasure": 0.10330309525862182, "rougeL_fmeasure_stderr": 0.0016709978496468228, "rougeL_precision": 0.06619223938605175, "rougeL_precision_stderr": 0.001213536084420925, "rougeL_recall": 0.3209215286944476, "rougeL_recall_stderr": 0.004642641539916205, "rougeLsum_fmeasure": 0.102932245838326, "rougeLsum_fmeasure_stderr": 0.0016665533221243655, "rougeLsum_precision": 0.06596557560336991, "rougeLsum_precision_stderr": 0.0012138292029559524, "rougeLsum_recall": 0.32099921969419465, "rougeLsum_recall_stderr": 0.004628086148730377}}, "2": {"PALM_prompt": {"bleu": 0.47923990514244874, "bleu_stderr": 0.03166485764907936, "rouge1_fmeasure": 0.11370260047327577, "rouge1_fmeasure_stderr": 0.0017046442313663663, "rouge1_precision": 0.07204383319731683, "rouge1_precision_stderr": 0.0012155881365152256, "rouge1_recall": 0.36672271781887156, "rouge1_recall_stderr": 0.00504889217499601, "rouge2_fmeasure": 0.05299300887318277, "rouge2_fmeasure_stderr": 0.0010947490193883183, "rouge2_precision": 0.03340955873075625, "rouge2_precision_stderr": 0.0007555261485064188, "rouge2_recall": 0.18177633862979822, "rouge2_recall_stderr": 0.0037021276711014387, "rougeL_fmeasure": 0.1079044075881634, "rougeL_fmeasure_stderr": 0.0015944656814960549, "rougeL_precision": 0.0684099274474328, "rougeL_precision_stderr": 0.00113914940883586, "rougeL_recall": 0.3455577571113544, "rougeL_recall_stderr": 0.004627024307619622, "rougeLsum_fmeasure": 0.10867383319593066, "rougeLsum_fmeasure_stderr": 0.0016268811944244747, "rougeLsum_precision": 0.06889283297975032, "rougeLsum_precision_stderr": 0.0011627655720725584, "rougeLsum_recall": 0.3493606357170359, "rougeLsum_recall_stderr": 0.0047163037850670355}}, "3": {"PALM_prompt": {"bleu": 0.5027920774081681, "bleu_stderr": 0.030462214372567638, "rouge1_fmeasure": 0.1146798040803432, "rouge1_fmeasure_stderr": 0.0016732637014203531, "rouge1_precision": 0.07255116336657369, "rouge1_precision_stderr": 0.0011977538039791803, "rouge1_recall": 0.38345627514615743, "rouge1_recall_stderr": 0.005203246900271579, "rouge2_fmeasure": 0.05346240993388053, "rouge2_fmeasure_stderr": 0.00108055575928216, "rouge2_precision": 0.03363690204181306, "rouge2_precision_stderr": 0.0007452192351280848, "rouge2_recall": 0.1918451527107662, "rouge2_recall_stderr": 0.0038340869615008937, "rougeL_fmeasure": 0.10795694469281018, "rougeL_fmeasure_stderr": 0.0015660316693302382, "rougeL_precision": 0.06838424060537425, "rougeL_precision_stderr": 0.0011261261420472187, "rougeL_recall": 0.35815409259444997, "rougeL_recall_stderr": 0.004736318677371466, "rougeLsum_fmeasure": 0.10928613566777898, "rougeLsum_fmeasure_stderr": 0.0015925978011445418, "rougeLsum_precision": 0.06920483129615293, "rougeLsum_precision_stderr": 0.0011443226072995456, "rougeLsum_recall": 0.36357801556888564, "rougeLsum_recall_stderr": 0.004808733759405405}}, "4": {"PALM_prompt": {"bleu": 0.5831555359984453, "bleu_stderr": 0.032234659529391536, "rouge1_fmeasure": 0.11750008800672353, "rouge1_fmeasure_stderr": 0.0016477505264978866, "rouge1_precision": 0.07392661038451319, "rouge1_precision_stderr": 0.00117243887617427, "rouge1_recall": 0.39335666383917167, "rouge1_recall_stderr": 0.005142725185391461, "rouge2_fmeasure": 0.05523835531458514, "rouge2_fmeasure_stderr": 0.0010698113777651895, "rouge2_precision": 0.03448655846022897, "rouge2_precision_stderr": 0.000729028189759837, "rouge2_recall": 0.20020642249358464, "rouge2_recall_stderr": 0.0038687044782014456, "rougeL_fmeasure": 0.1101991356020512, "rougeL_fmeasure_stderr": 0.0015236328659278776, "rougeL_precision": 0.06941307599352699, "rougeL_precision_stderr": 0.0010899673683375645, "rougeL_recall": 0.3670211800134988, "rougeL_recall_stderr": 0.004700921629116034, "rougeLsum_fmeasure": 0.1117873702364502, "rougeLsum_fmeasure_stderr": 0.0015580968509773768, "rougeLsum_precision": 0.07037653651757456, "rougeLsum_precision_stderr": 0.0011110620728147437, "rougeLsum_recall": 0.3732246975137694, "rougeLsum_recall_stderr": 0.004797544529790582}}, "5": {"PALM_prompt": {"bleu": 0.6365749188582466, "bleu_stderr": 0.039638813172299045, "rouge1_fmeasure": 0.11886210839837029, "rouge1_fmeasure_stderr": 0.001641331021319136, "rouge1_precision": 0.07471557189793104, "rouge1_precision_stderr": 0.001168900413573336, "rouge1_recall": 0.40490074663891484, "rouge1_recall_stderr": 0.005284549026027036, "rouge2_fmeasure": 0.05619659179665226, "rouge2_fmeasure_stderr": 0.0010637830284484662, "rouge2_precision": 0.0350998165096206, "rouge2_precision_stderr": 0.0007323935879922631, "rouge2_recall": 0.20683097072034598, "rouge2_recall_stderr": 0.003912349890143833, "rougeL_fmeasure": 0.10996565063664662, "rougeL_fmeasure_stderr": 0.0015072851492445695, "rougeL_precision": 0.06926051144904892, "rougeL_precision_stderr": 0.0010863629617073184, "rougeL_recall": 0.37213644980404864, "rougeL_recall_stderr": 0.004688196830703624, "rougeLsum_fmeasure": 0.11299990359140699, "rougeLsum_fmeasure_stderr": 0.001561286385930656, "rougeLsum_precision": 0.07111141425693926, "rougeLsum_precision_stderr": 0.0011190880115330949, "rougeLsum_recall": 0.38316893134013263, "rougeLsum_recall_stderr": 0.004892613100508629}}}, "GEM/wiki_lingua_en": {"0": {"tldr_en": {"bleu": 1.5579291268345696, "bleu_stderr": 0.06016300187830401, "rouge1_fmeasure": 0.17406988949643304, "rouge1_fmeasure_stderr": 0.0018339930055680368, "rouge1_precision": 0.14888065220459862, "rouge1_precision_stderr": 0.0018522381431221608, "rouge1_recall": 0.2533502341723187, "rouge1_recall_stderr": 0.002694764028887335, "rouge2_fmeasure": 0.03434823579340285, "rouge2_fmeasure_stderr": 0.0008465750128095288, "rouge2_precision": 0.029169878872080838, "rouge2_precision_stderr": 0.0007679053115951254, "rouge2_recall": 0.05196743771903658, "rouge2_recall_stderr": 0.001421253503809284, "rougeL_fmeasure": 0.13456472416719728, "rougeL_fmeasure_stderr": 0.0013210328093623985, "rougeL_precision": 0.1138889494347587, "rougeL_precision_stderr": 0.0013014428116691651, "rougeL_recall": 0.20025749658243655, "rougeL_recall_stderr": 0.0021830666467128335, "rougeLsum_fmeasure": 0.16115176655656072, "rougeLsum_fmeasure_stderr": 0.0016863623652902142, "rougeLsum_precision": 0.13762861506852897, "rougeLsum_precision_stderr": 0.001700786002748469, "rougeLsum_recall": 0.23544002194089206, "rougeLsum_recall_stderr": 0.002515653712672603}}, "1": {"tldr_en": {"bleu": 2.8504691019972226, "bleu_stderr": 0.07529997127562747, "rouge1_fmeasure": 0.21615787975223222, "rouge1_fmeasure_stderr": 0.001980052888687319, "rouge1_precision": 0.18628138897984436, "rouge1_precision_stderr": 0.0021004152459147747, "rouge1_recall": 0.3129007187114192, "rouge1_recall_stderr": 0.0029032182486249418, "rouge2_fmeasure": 0.05439999185109123, "rouge2_fmeasure_stderr": 0.001031487571403725, "rouge2_precision": 0.046486537780770956, "rouge2_precision_stderr": 0.0009461054630336336, "rouge2_recall": 0.08171808437787392, "rouge2_recall_stderr": 0.001737593596442716, "rougeL_fmeasure": 0.15690618601267947, "rougeL_fmeasure_stderr": 0.0013436606219927435, "rougeL_precision": 0.13401183830304364, "rougeL_precision_stderr": 0.00140969758282127, "rougeL_recall": 0.23246416864486025, "rougeL_recall_stderr": 0.0022971477521400944, "rougeLsum_fmeasure": 0.20269374476846683, "rougeLsum_fmeasure_stderr": 0.0018536229956474099, "rougeLsum_precision": 0.1743604474408626, "rougeLsum_precision_stderr": 0.001958253968449097, "rougeLsum_recall": 0.2946260029722949, "rougeLsum_recall_stderr": 0.0027768807102536105}}, "2": {"tldr_en": {"bleu": 3.127885213179027, "bleu_stderr": 0.05567768230878822, "rouge1_fmeasure": 0.21248721018427344, "rouge1_fmeasure_stderr": 0.002005377613049306, "rouge1_precision": 0.19145535496087807, "rouge1_precision_stderr": 0.002296451033052049, "rouge1_recall": 0.2975680142091921, "rouge1_recall_stderr": 0.002931688880420891, "rouge2_fmeasure": 0.055330208196910265, "rouge2_fmeasure_stderr": 0.0010696008344144292, "rouge2_precision": 0.05003016577994891, "rouge2_precision_stderr": 0.0011239070261388475, "rouge2_recall": 0.08044311392175647, "rouge2_recall_stderr": 0.001763848842609043, "rougeL_fmeasure": 0.1613056472114288, "rougeL_fmeasure_stderr": 0.0014427201039189429, "rougeL_precision": 0.14417467914561882, "rougeL_precision_stderr": 0.0016764997188872376, "rougeL_recall": 0.23103867510190504, "rougeL_recall_stderr": 0.002419663302485, "rougeLsum_fmeasure": 0.19917102006805654, "rougeLsum_fmeasure_stderr": 0.0018806834912790124, "rougeLsum_precision": 0.17923916059988207, "rougeLsum_precision_stderr": 0.002160531408137847, "rougeLsum_recall": 0.27981692016794185, "rougeLsum_recall_stderr": 0.002789997688790343}}, "3": {"tldr_en": {"bleu": 3.0807771429420754, "bleu_stderr": 0.09283762605369977, "rouge1_fmeasure": 0.1775686933392586, "rouge1_fmeasure_stderr": 0.0023132433314061317, "rouge1_precision": 0.17616795901868026, "rouge1_precision_stderr": 0.0029041735231821264, "rouge1_recall": 0.2398365427132762, "rouge1_recall_stderr": 0.003303934643917804, "rouge2_fmeasure": 0.046193370406017856, "rouge2_fmeasure_stderr": 0.0010778055491266162, "rouge2_precision": 0.046939802020617566, "rouge2_precision_stderr": 0.0014687470735497206, "rouge2_recall": 0.06422548105107985, "rouge2_recall_stderr": 0.0016475717099470786, "rougeL_fmeasure": 0.135715301519862, "rougeL_fmeasure_stderr": 0.0017310055665623648, "rougeL_precision": 0.13481464964787096, "rougeL_precision_stderr": 0.0022897360632217266, "rougeL_recall": 0.18678109287740904, "rougeL_recall_stderr": 0.0026738452831759677, "rougeLsum_fmeasure": 0.1672145914904344, "rougeLsum_fmeasure_stderr": 0.0021753093573102073, "rougeLsum_precision": 0.1658688389623912, "rougeLsum_precision_stderr": 0.002743944725824659, "rougeLsum_recall": 0.22654605759305751, "rougeLsum_recall_stderr": 0.0031428598277916196}}, "4": {"tldr_en": {"bleu": 0.5293847081914334, "bleu_stderr": 0.044698835511384254, "rouge1_fmeasure": 0.05573280124002876, "rouge1_fmeasure_stderr": 0.0019136745631413645, "rouge1_precision": 0.0584713690765183, "rouge1_precision_stderr": 0.0023318063534537165, "rouge1_recall": 0.07718352458545524, "rouge1_recall_stderr": 0.002735992768065453, "rouge2_fmeasure": 0.013946881394381343, "rouge2_fmeasure_stderr": 0.0007038540032034839, "rouge2_precision": 0.01500160633710272, "rouge2_precision_stderr": 0.0009825454465574395, "rouge2_recall": 0.02039516990198183, "rouge2_recall_stderr": 0.001139121615096021, "rougeL_fmeasure": 0.04301362739459154, "rougeL_fmeasure_stderr": 0.0014516622611586488, "rougeL_precision": 0.04558030719768415, "rougeL_precision_stderr": 0.0018674171866451237, "rougeL_recall": 0.06093944803992283, "rougeL_recall_stderr": 0.0022091397429612157, "rougeLsum_fmeasure": 0.052282734877528686, "rougeLsum_fmeasure_stderr": 0.0017926957831151907, "rougeLsum_precision": 0.05496664162339461, "rougeLsum_precision_stderr": 0.0022050347910565274, "rougeLsum_recall": 0.0725975299250868, "rougeLsum_recall_stderr": 0.0025818847671325463}}, "5": {"tldr_en": {"bleu": 1.9499255251335006e-07, "bleu_stderr": 3.3145291785030997e-07, "rouge1_fmeasure": 0.008623575125031323, "rouge1_fmeasure_stderr": 0.0008288612961403041, "rouge1_precision": 0.009305181256700445, "rouge1_precision_stderr": 0.0010395448742730087, "rouge1_recall": 0.012223369402839458, "rouge1_recall_stderr": 0.0012274307651446278, "rouge2_fmeasure": 0.002093015608191419, "rouge2_fmeasure_stderr": 0.00027758841441824164, "rouge2_precision": 0.0025435206455146683, "rouge2_precision_stderr": 0.0005383342373842493, "rouge2_recall": 0.0031006973107968873, "rouge2_recall_stderr": 0.0004472222802474402, "rougeL_fmeasure": 0.006710465163509879, "rougeL_fmeasure_stderr": 0.0006498829914466451, "rougeL_precision": 0.007394254420247825, "rougeL_precision_stderr": 0.000882581070383217, "rougeL_recall": 0.009645269299470693, "rougeL_recall_stderr": 0.0009987275588991668, "rougeLsum_fmeasure": 0.008136271016090088, "rougeLsum_fmeasure_stderr": 0.0007837539033952645, "rougeLsum_precision": 0.008824151605454963, "rougeLsum_precision_stderr": 0.0010021873301601862, "rougeLsum_recall": 0.011594578158050393, "rougeLsum_recall_stderr": 0.0011725427133673896}}}, "e2e_nlg_cleaned": {"0": {"generate_text_restaurant": {"bleu": 1.82061032660784, "bleu_stderr": 0.07096469051250175, "rouge1_fmeasure": 0.15825083088882455, "rouge1_fmeasure_stderr": 0.0015057952646897993, "rouge1_precision": 0.222486766832112, "rouge1_precision_stderr": 0.0033842158110189277, "rouge1_recall": 0.1790689833398624, "rouge1_recall_stderr": 0.0018970549220355723, "rouge2_fmeasure": 0.022292985524574444, "rouge2_fmeasure_stderr": 0.0006610427910211585, "rouge2_precision": 0.021935233358876982, "rouge2_precision_stderr": 0.0008022922500453108, "rouge2_recall": 0.031732352695645706, "rouge2_recall_stderr": 0.0009741385489925919, "rougeL_fmeasure": 0.1495036471572004, "rougeL_fmeasure_stderr": 0.0013950962210181237, "rougeL_precision": 0.20561351860512828, "rougeL_precision_stderr": 0.0030700557880713867, "rougeL_recall": 0.17239931551868604, "rougeL_recall_stderr": 0.001867012935877257, "rougeLsum_fmeasure": 0.136862319950687, "rougeLsum_fmeasure_stderr": 0.0014225741473040676, "rougeLsum_precision": 0.19805184360305841, "rougeLsum_precision_stderr": 0.0032227599715627343, "rougeLsum_recall": 0.1509451752386678, "rougeLsum_recall_stderr": 0.0016062725531267121}}, "1": {"generate_text_restaurant": {"bleu": 11.657037239702142, "bleu_stderr": 0.1250980356694754, "rouge1_fmeasure": 0.4389348120897716, "rouge1_fmeasure_stderr": 0.002063579737266741, "rouge1_precision": 0.45968566711122216, "rouge1_precision_stderr": 0.002881285091661702, "rouge1_recall": 0.46542006430779354, "rouge1_recall_stderr": 0.0028779976054145785, "rouge2_fmeasure": 0.1995055031643681, "rouge2_fmeasure_stderr": 0.0017838055449605266, "rouge2_precision": 0.21038656753149504, "rouge2_precision_stderr": 0.002167887993557998, "rouge2_recall": 0.21239637096024527, "rouge2_recall_stderr": 0.0021227522877282565, "rougeL_fmeasure": 0.3114176922977353, "rougeL_fmeasure_stderr": 0.0017952929940337735, "rougeL_precision": 0.3268614579954877, "rougeL_precision_stderr": 0.002404585448478252, "rougeL_recall": 0.3303654420846652, "rougeL_recall_stderr": 0.002362681762163533, "rougeLsum_fmeasure": 0.3620752417019191, "rougeLsum_fmeasure_stderr": 0.002056079671135789, "rougeLsum_precision": 0.3793916638196591, "rougeLsum_precision_stderr": 0.002677199223367296, "rougeLsum_recall": 0.3835618439741999, "rougeLsum_recall_stderr": 0.002671098460743732}}, "2": {"generate_text_restaurant": {"bleu": 14.339702198028428, "bleu_stderr": 0.13350232957464767, "rouge1_fmeasure": 0.4798241859576156, "rouge1_fmeasure_stderr": 0.0022710941605897325, "rouge1_precision": 0.5570264884781344, "rouge1_precision_stderr": 0.0033490944418358374, "rouge1_recall": 0.46432809954638865, "rouge1_recall_stderr": 0.002945932627099228, "rouge2_fmeasure": 0.2403073697075928, "rouge2_fmeasure_stderr": 0.002087685451857004, "rouge2_precision": 0.28313861767317927, "rouge2_precision_stderr": 0.0027952153389596843, "rouge2_recall": 0.2325744710533778, "rouge2_recall_stderr": 0.0022998468012822644, "rougeL_fmeasure": 0.35446236973706474, "rougeL_fmeasure_stderr": 0.0021166068311389095, "rougeL_precision": 0.4135082878473266, "rougeL_precision_stderr": 0.003050078856711996, "rougeL_recall": 0.34252272942973466, "rougeL_recall_stderr": 0.002524272588321217, "rougeLsum_fmeasure": 0.40022368564912997, "rougeLsum_fmeasure_stderr": 0.00229931320451958, "rougeLsum_precision": 0.46552847624479543, "rougeLsum_precision_stderr": 0.0032616657748971998, "rougeLsum_recall": 0.3869495647860439, "rougeLsum_recall_stderr": 0.002764146985697145}}, "3": {"generate_text_restaurant": {"bleu": 14.50537794842067, "bleu_stderr": 0.11584363484363577, "rouge1_fmeasure": 0.4791848298362283, "rouge1_fmeasure_stderr": 0.0022007720607771426, "rouge1_precision": 0.5402112307108176, "rouge1_precision_stderr": 0.003295524595806651, "rouge1_recall": 0.47732917178018114, "rouge1_recall_stderr": 0.00294022910982499, "rouge2_fmeasure": 0.24067531660097596, "rouge2_fmeasure_stderr": 0.002087534005568858, "rouge2_precision": 0.2750068424415456, "rouge2_precision_stderr": 0.002742749101788008, "rouge2_recall": 0.239901278700609, "rouge2_recall_stderr": 0.0023557789869618896, "rougeL_fmeasure": 0.35365228129689674, "rougeL_fmeasure_stderr": 0.00209824048462177, "rougeL_precision": 0.40045561756040954, "rougeL_precision_stderr": 0.002992395353090302, "rougeL_recall": 0.35170929339590973, "rougeL_recall_stderr": 0.0025447548206976338, "rougeLsum_fmeasure": 0.40103023450016195, "rougeLsum_fmeasure_stderr": 0.002275399298911374, "rougeLsum_precision": 0.45223409928062946, "rougeLsum_precision_stderr": 0.0031770144742772127, "rougeLsum_recall": 0.3996467826064061, "rougeLsum_recall_stderr": 0.002820396617171887}}, "4": {"generate_text_restaurant": {"bleu": 13.323972252459379, "bleu_stderr": 0.16742143852884073, "rouge1_fmeasure": 0.46396091436304504, "rouge1_fmeasure_stderr": 0.0021581635430039958, "rouge1_precision": 0.4899803542811925, "rouge1_precision_stderr": 0.003129903470372565, "rouge1_recall": 0.48706786873461216, "rouge1_recall_stderr": 0.002870795532573222, "rouge2_fmeasure": 0.2283664329607444, "rouge2_fmeasure_stderr": 0.0020126317997385106, "rouge2_precision": 0.24359351406261168, "rouge2_precision_stderr": 0.0025312411079664366, "rouge2_recall": 0.24067281188228995, "rouge2_recall_stderr": 0.0023396690126969532, "rougeL_fmeasure": 0.3421085000388542, "rougeL_fmeasure_stderr": 0.002013555794275305, "rougeL_precision": 0.3624069982870762, "rougeL_precision_stderr": 0.0027711033582985124, "rougeL_recall": 0.3591682726211815, "rougeL_recall_stderr": 0.0025140239206322313, "rougeLsum_fmeasure": 0.3900177854874722, "rougeLsum_fmeasure_stderr": 0.0022269574328580566, "rougeLsum_precision": 0.4114748595185199, "rougeLsum_precision_stderr": 0.0029677058156554, "rougeLsum_recall": 0.4100795333879036, "rougeLsum_recall_stderr": 0.002820033316291732}}, "5": {"generate_text_restaurant": {"bleu": 12.462777642040733, "bleu_stderr": 0.13551486783004044, "rouge1_fmeasure": 0.4559772721525502, "rouge1_fmeasure_stderr": 0.0020283797559365376, "rouge1_precision": 0.45865129639331476, "rouge1_precision_stderr": 0.002686570307588201, "rouge1_recall": 0.4938245489163575, "rouge1_recall_stderr": 0.0027958101448835645, "rouge2_fmeasure": 0.22088952705630202, "rouge2_fmeasure_stderr": 0.0018905153937119456, "rouge2_precision": 0.22301236793840634, "rouge2_precision_stderr": 0.002160872250109803, "rouge2_recall": 0.24081053155333462, "rouge2_recall_stderr": 0.0022973862129338496, "rougeL_fmeasure": 0.3335077717084848, "rougeL_fmeasure_stderr": 0.0018782606369312164, "rougeL_precision": 0.3354962184605829, "rougeL_precision_stderr": 0.0023253516829045725, "rougeL_recall": 0.3619962097662624, "rougeL_recall_stderr": 0.002476618191262458, "rougeLsum_fmeasure": 0.38415093197988986, "rougeLsum_fmeasure_stderr": 0.00209136460819391, "rougeLsum_precision": 0.3861502626280554, "rougeLsum_precision_stderr": 0.0025748401786830784, "rougeLsum_recall": 0.416513089237172, "rougeLsum_recall_stderr": 0.002733652456992395}}}, "gem_xsum": {"0": {"article_DOC_summary": {"bleu": 2.282427388603868, "bleu_stderr": 0.12070696540892288, "rouge1_fmeasure": 0.21547497313031236, "rouge1_fmeasure_stderr": 0.002589604938536055, "rouge1_precision": 0.15955334897495682, "rouge1_precision_stderr": 0.002209067557750088, "rouge1_recall": 0.36217161593458225, "rouge1_recall_stderr": 0.004440471846187096, "rouge2_fmeasure": 0.05432411992031246, "rouge2_fmeasure_stderr": 0.0017179496173428985, "rouge2_precision": 0.039876602220101885, "rouge2_precision_stderr": 0.0013408657891869856, "rouge2_recall": 0.09373979355812566, "rouge2_recall_stderr": 0.003020539395998483, "rougeL_fmeasure": 0.16451405093380472, "rougeL_fmeasure_stderr": 0.0019625362254798284, "rougeL_precision": 0.12161602298528985, "rougeL_precision_stderr": 0.0016687848022286617, "rougeL_recall": 0.277756692596081, "rougeL_recall_stderr": 0.003476817201900778, "rougeLsum_fmeasure": 0.1678765700309988, "rougeLsum_fmeasure_stderr": 0.002214619502903411, "rougeLsum_precision": 0.12390275070243846, "rougeLsum_precision_stderr": 0.001821194882097903, "rougeLsum_recall": 0.2841653396002695, "rougeLsum_recall_stderr": 0.003918981158721574}}, "1": {"article_DOC_summary": {"bleu": 1.3775738726107656, "bleu_stderr": 0.08168674122275797, "rouge1_fmeasure": 0.16895420412623663, "rouge1_fmeasure_stderr": 0.002594837744965486, "rouge1_precision": 0.12010749072738239, "rouge1_precision_stderr": 0.0019038452514628232, "rouge1_recall": 0.2963599272578747, "rouge1_recall_stderr": 0.004492167665019704, "rouge2_fmeasure": 0.0333977078622104, "rouge2_fmeasure_stderr": 0.00144862051823388, "rouge2_precision": 0.02342764378945351, "rouge2_precision_stderr": 0.001019840391470285, "rouge2_recall": 0.0606775250012725, "rouge2_recall_stderr": 0.002681867584351387, "rougeL_fmeasure": 0.1329671503634145, "rougeL_fmeasure_stderr": 0.0019756316848368602, "rougeL_precision": 0.09436779371850286, "rougeL_precision_stderr": 0.0014414694335729383, "rougeL_recall": 0.2345277453603614, "rougeL_recall_stderr": 0.003510304651172983, "rougeLsum_fmeasure": 0.1348677191851774, "rougeLsum_fmeasure_stderr": 0.0021296361098744635, "rougeLsum_precision": 0.09564640396609536, "rougeLsum_precision_stderr": 0.0015463429453530608, "rougeLsum_recall": 0.23817260800506607, "rougeLsum_recall_stderr": 0.0037920083635799903}}, "2": {"article_DOC_summary": {"bleu": 1.6436795917006544, "bleu_stderr": 0.07345990657620402, "rouge1_fmeasure": 0.183152447945667, "rouge1_fmeasure_stderr": 0.0026661841419304156, "rouge1_precision": 0.13018508734953355, "rouge1_precision_stderr": 0.0019680938941104625, "rouge1_recall": 0.3210711017407105, "rouge1_recall_stderr": 0.004611340413923777, "rouge2_fmeasure": 0.04006840275451415, "rouge2_fmeasure_stderr": 0.0015228269131846886, "rouge2_precision": 0.028176744941516615, "rouge2_precision_stderr": 0.001075491149082574, "rouge2_recall": 0.07240802386862864, "rouge2_recall_stderr": 0.002820788158486654, "rougeL_fmeasure": 0.14371195073214757, "rougeL_fmeasure_stderr": 0.0019879171616702124, "rougeL_precision": 0.10199545313071355, "rougeL_precision_stderr": 0.0014580281840802887, "rougeL_recall": 0.2531633381335362, "rougeL_recall_stderr": 0.003556665780315997, "rougeLsum_fmeasure": 0.14532030438832994, "rougeLsum_fmeasure_stderr": 0.002206439734918519, "rougeLsum_precision": 0.10303479198876377, "rougeLsum_precision_stderr": 0.0016024271297654439, "rougeLsum_recall": 0.2565576177699366, "rougeLsum_recall_stderr": 0.003974104626273052}}, "3": {"article_DOC_summary": {"bleu": 1.6496742062970557, "bleu_stderr": 0.10044687108522192, "rouge1_fmeasure": 0.17881939665307162, "rouge1_fmeasure_stderr": 0.0027596350151271876, "rouge1_precision": 0.13017675194898692, "rouge1_precision_stderr": 0.002198538499348046, "rouge1_recall": 0.30922236829508537, "rouge1_recall_stderr": 0.004838699494510795, "rouge2_fmeasure": 0.03850524479452543, "rouge2_fmeasure_stderr": 0.0015068733635772717, "rouge2_precision": 0.02760225846524049, "rouge2_precision_stderr": 0.0011161638977048621, "rouge2_recall": 0.06881042595527115, "rouge2_recall_stderr": 0.0028092871690327376, "rougeL_fmeasure": 0.13794374325281775, "rougeL_fmeasure_stderr": 0.0020813614818383725, "rougeL_precision": 0.10014486228665212, "rougeL_precision_stderr": 0.0016329144933538103, "rougeL_recall": 0.2399877011308486, "rougeL_recall_stderr": 0.0037910983726926846, "rougeLsum_fmeasure": 0.1407907014518307, "rougeLsum_fmeasure_stderr": 0.0022509491687602674, "rougeLsum_precision": 0.10223719953083442, "rougeLsum_precision_stderr": 0.001759902279193926, "rougeLsum_recall": 0.24547016572644775, "rougeLsum_recall_stderr": 0.004083522562686188}}, "4": {"article_DOC_summary": {"bleu": 0.8321034229031437, "bleu_stderr": 0.08945851965278599, "rouge1_fmeasure": 0.049656632315842844, "rouge1_fmeasure_stderr": 0.002856336743990567, "rouge1_precision": 0.04149135621677754, "rouge1_precision_stderr": 0.0026386378608042917, "rouge1_recall": 0.07750948792703138, "rouge1_recall_stderr": 0.004477188850582034, "rouge2_fmeasure": 0.010989532389756859, "rouge2_fmeasure_stderr": 0.001029101618129444, "rouge2_precision": 0.008961527810790616, "rouge2_precision_stderr": 0.0009890519095079862, "rouge2_recall": 0.017840955869101484, "rouge2_recall_stderr": 0.0016844183124156535, "rougeL_fmeasure": 0.0375802335882974, "rougeL_fmeasure_stderr": 0.002147921108027172, "rougeL_precision": 0.03154250432068281, "rougeL_precision_stderr": 0.0020252442164337293, "rougeL_recall": 0.05909979811818957, "rougeL_recall_stderr": 0.0034347562251169, "rougeLsum_fmeasure": 0.03944906528704634, "rougeLsum_fmeasure_stderr": 0.0022725008097993537, "rougeLsum_precision": 0.03303780727965199, "rougeLsum_precision_stderr": 0.002118654737857532, "rougeLsum_recall": 0.06214884490779202, "rougeLsum_recall_stderr": 0.003663125602489163}}, "5": {"article_DOC_summary": {"bleu": 3.1493567208404783e-39, "bleu_stderr": 1.4249121699400145e-34, "rouge1_fmeasure": 0.0028022236632419895, "rouge1_fmeasure_stderr": 0.0007863889401033125, "rouge1_precision": 0.003117323860723007, "rouge1_precision_stderr": 0.0008837148810752774, "rouge1_recall": 0.0026242515972514074, "rouge1_recall_stderr": 0.0007336964722264186, "rouge2_fmeasure": 0.0005154358964062439, "rouge2_fmeasure_stderr": 0.00023513093079516412, "rouge2_precision": 0.0005615954214733349, "rouge2_precision_stderr": 0.00024697557291310967, "rouge2_recall": 0.0004889607248097814, "rouge2_recall_stderr": 0.00023161252427707105, "rougeL_fmeasure": 0.002054859718325845, "rougeL_fmeasure_stderr": 0.0005764790804455003, "rougeL_precision": 0.002278284775437062, "rougeL_precision_stderr": 0.0006480855590254838, "rougeL_recall": 0.0019397313262420287, "rougeL_recall_stderr": 0.0005430737577124271, "rougeLsum_fmeasure": 0.002218076936186532, "rougeLsum_fmeasure_stderr": 0.0006333184346671743, "rougeLsum_precision": 0.0024716725936861457, "rougeLsum_precision_stderr": 0.0007191187737619554, "rougeLsum_recall": 0.0020845273284634726, "rougeLsum_recall_stderr": 0.0005920007456566033}}}} |