{"GEM/web_nlg_en": {"0": {"PALM_prompt": {"bleu": 0.4273206525263921, "bleu_stderr": 0.05364575256139351, "rouge1_fmeasure": 0.11230037179769856, "rouge1_fmeasure_stderr": 0.0021352190368007454, "rouge1_precision": 0.07516332695488044, "rouge1_precision_stderr": 0.0017494053619516534, "rouge1_recall": 0.3000002487080154, "rouge1_recall_stderr": 0.004693559983294075, "rouge2_fmeasure": 0.05344453588119793, "rouge2_fmeasure_stderr": 0.0013515518560690634, "rouge2_precision": 0.03590952594711019, "rouge2_precision_stderr": 0.00111479086151588, "rouge2_recall": 0.14620648751654972, "rouge2_recall_stderr": 0.003234756290211622, "rougeL_fmeasure": 0.10771019147913463, "rougeL_fmeasure_stderr": 0.0019671591552995436, "rougeL_precision": 0.07168459834878929, "rougeL_precision_stderr": 0.0015668817269601622, "rougeL_recall": 0.29090649446634975, "rougeL_recall_stderr": 0.004555120095447256, "rougeLsum_fmeasure": 0.10717155022915739, "rougeLsum_fmeasure_stderr": 0.0019927955387855968, "rougeLsum_precision": 0.07152558346509422, "rougeLsum_precision_stderr": 0.001609325107400611, "rougeLsum_recall": 0.28799432197952096, "rougeLsum_recall_stderr": 0.004451937577964067}}, "1": {"PALM_prompt": {"bleu": 0.5663724921835591, "bleu_stderr": 0.03793270967595185, "rouge1_fmeasure": 0.12756709737220784, "rouge1_fmeasure_stderr": 0.002030468381881967, "rouge1_precision": 0.08217512985928499, "rouge1_precision_stderr": 0.0015069260165856669, "rouge1_recall": 0.3920117360421087, "rouge1_recall_stderr": 0.005374085547490371, "rouge2_fmeasure": 0.0604895960614538, "rouge2_fmeasure_stderr": 0.0013006193696080512, "rouge2_precision": 0.03886435424085205, "rouge2_precision_stderr": 0.0009357648884166175, "rouge2_recall": 0.1952944224324245, "rouge2_recall_stderr": 0.003818475633981706, "rougeL_fmeasure": 0.12035361435811785, "rougeL_fmeasure_stderr": 0.00181560137606144, "rougeL_precision": 0.07729829270693146, "rougeL_precision_stderr": 0.0013303444161253287, "rougeL_recall": 0.3723170212800364, "rougeL_recall_stderr": 0.005024550440352146, "rougeLsum_fmeasure": 0.1206781467869011, "rougeLsum_fmeasure_stderr": 0.0018904175388126346, "rougeLsum_precision": 0.07779518642109406, "rougeLsum_precision_stderr": 0.0014090714637609509, "rougeLsum_recall": 0.3702218835789373, "rougeLsum_recall_stderr": 0.004905029541255394}}, "2": {"PALM_prompt": {"bleu": 0.6313130510239234, "bleu_stderr": 0.02727704631142144, "rouge1_fmeasure": 0.12940251519432414, "rouge1_fmeasure_stderr": 0.0018563230360622849, "rouge1_precision": 0.08219107059651697, "rouge1_precision_stderr": 0.0013422258523153536, "rouge1_recall": 0.4151352004015792, "rouge1_recall_stderr": 0.005332508949374494, "rouge2_fmeasure": 0.06086364336249341, "rouge2_fmeasure_stderr": 0.0011655118907789416, "rouge2_precision": 0.03845495568474405, "rouge2_precision_stderr": 0.0008134611533833349, "rouge2_recall": 0.20877882384960775, "rouge2_recall_stderr": 0.003907086651198888, "rougeL_fmeasure": 0.12014889628673367, "rougeL_fmeasure_stderr": 0.0016294871735385334, "rougeL_precision": 0.07626492600480415, "rougeL_precision_stderr": 0.0011790764283155961, "rougeL_recall": 0.38715675983971815, "rougeL_recall_stderr": 0.004836346504741043, "rougeLsum_fmeasure": 0.12261763705509457, "rougeLsum_fmeasure_stderr": 0.0017345722248776798, "rougeLsum_precision": 0.07790995067901116, "rougeLsum_precision_stderr": 0.0012592690527861467, "rougeLsum_recall": 0.3934974316637387, "rougeLsum_recall_stderr": 0.004930425413445172}}, "3": {"PALM_prompt": {"bleu": 0.6636681020720647, "bleu_stderr": 0.03135011211987113, "rouge1_fmeasure": 0.13179598729950448, "rouge1_fmeasure_stderr": 0.0018608653117238654, "rouge1_precision": 0.08335165133186997, "rouge1_precision_stderr": 0.0013566594758271408, "rouge1_recall": 0.4363611958728497, "rouge1_recall_stderr": 0.005466144892220358, "rouge2_fmeasure": 0.06172653863702163, "rouge2_fmeasure_stderr": 0.0011849569250187196, "rouge2_precision": 0.038821951607757095, "rouge2_precision_stderr": 0.0008309945118711307, "rouge2_recall": 0.21925719264824975, "rouge2_recall_stderr": 0.003975211126463013, "rougeL_fmeasure": 0.1203852422828686, "rougeL_fmeasure_stderr": 0.0015949578691764172, "rougeL_precision": 0.07607458853736868, "rougeL_precision_stderr": 0.0011617831771301823, "rougeL_recall": 0.3989579329521947, "rougeL_recall_stderr": 0.004797365715247612, "rougeLsum_fmeasure": 0.12430003630857168, "rougeLsum_fmeasure_stderr": 0.0017268968711559307, "rougeLsum_precision": 0.07866244698502353, "rougeLsum_precision_stderr": 0.0012631336576740743, "rougeLsum_recall": 0.41007264952780736, "rougeLsum_recall_stderr": 0.004984839846868383}}, "4": {"PALM_prompt": {"bleu": 0.7445914925255956, "bleu_stderr": 0.04471373508927592, "rouge1_fmeasure": 0.13191715691415712, "rouge1_fmeasure_stderr": 0.001848451971487058, "rouge1_precision": 0.08335134599012016, "rouge1_precision_stderr": 0.0013601845542222193, "rouge1_recall": 0.4369343435538318, "rouge1_recall_stderr": 0.00545111390697167, "rouge2_fmeasure": 0.061883789388597316, "rouge2_fmeasure_stderr": 0.0011527436830992247, "rouge2_precision": 0.03875848226958462, "rouge2_precision_stderr": 0.0008040225568103941, "rouge2_recall": 0.22226421540491542, "rouge2_recall_stderr": 0.004032909658463521, "rougeL_fmeasure": 0.11940663728897792, "rougeL_fmeasure_stderr": 0.0015860574558582763, "rougeL_precision": 0.0754476375575414, "rougeL_precision_stderr": 0.001174153361661276, "rougeL_recall": 0.3964743307100715, "rougeL_recall_stderr": 0.004828941243739242, "rougeLsum_fmeasure": 0.12423777278329896, "rougeLsum_fmeasure_stderr": 0.0017238674224559544, "rougeLsum_precision": 0.07858636401791905, "rougeLsum_precision_stderr": 0.0012777097204336968, "rougeLsum_recall": 0.41038517941804836, "rougeLsum_recall_stderr": 0.005000143163857465}}, "5": {"PALM_prompt": {"bleu": 0.8005310739494581, "bleu_stderr": 0.033724293174082695, "rouge1_fmeasure": 0.13259315662099147, "rouge1_fmeasure_stderr": 0.0017356987872365276, "rouge1_precision": 0.08338013300594908, "rouge1_precision_stderr": 0.001260130864731573, "rouge1_recall": 0.44613389749037924, "rouge1_recall_stderr": 0.0053462691621041685, "rouge2_fmeasure": 0.06197974009288303, "rouge2_fmeasure_stderr": 0.001091686612001906, "rouge2_precision": 0.03871058510533021, "rouge2_precision_stderr": 0.0007593773025926396, "rouge2_recall": 0.22607554732619956, "rouge2_recall_stderr": 0.004027973657557073, "rougeL_fmeasure": 0.11956303513601427, "rougeL_fmeasure_stderr": 0.001512266881380029, "rougeL_precision": 0.07523239671078998, "rougeL_precision_stderr": 0.0011063220739786807, "rougeL_recall": 0.40282994585844645, "rougeL_recall_stderr": 0.0046937441735825924, "rougeLsum_fmeasure": 0.12469867862475097, "rougeLsum_fmeasure_stderr": 0.0016220089487202947, "rougeLsum_precision": 0.07851137617969797, "rougeLsum_precision_stderr": 0.001188072848467214, "rougeLsum_recall": 0.41817890606333163, "rougeLsum_recall_stderr": 0.004881701441444398}}}, "GEM/wiki_lingua_en": {"0": {"tldr_en": {"bleu": 1.414984862410896, "bleu_stderr": 0.05940234677879655, "rouge1_fmeasure": 0.172029086258773, "rouge1_fmeasure_stderr": 0.0018269882294786313, "rouge1_precision": 0.14692825480864516, "rouge1_precision_stderr": 0.0018425931958625118, "rouge1_recall": 0.2512970070836738, "rouge1_recall_stderr": 0.002648136861575683, "rouge2_fmeasure": 0.03327297097578151, "rouge2_fmeasure_stderr": 0.0008291280040639999, "rouge2_precision": 0.027966624066931015, "rouge2_precision_stderr": 0.0007198127679157396, "rouge2_recall": 0.050572163826476904, "rouge2_recall_stderr": 0.00137135380680017, "rougeL_fmeasure": 0.13597766469494962, "rougeL_fmeasure_stderr": 0.0013133399966305693, "rougeL_precision": 0.11468189898145331, "rougeL_precision_stderr": 0.0012927912945671872, "rougeL_recall": 0.20361426191617446, "rougeL_recall_stderr": 0.002161893564032071, "rougeLsum_fmeasure": 0.15820053127675784, "rougeLsum_fmeasure_stderr": 0.0016635461401018714, "rougeLsum_precision": 0.1348221046642956, "rougeLsum_precision_stderr": 0.0016706708007563362, "rougeLsum_recall": 0.23199038101436165, "rougeLsum_recall_stderr": 0.0024449378448124903}}, "1": {"tldr_en": {"bleu": 2.836407401710481, "bleu_stderr": 0.04043755617370114, "rouge1_fmeasure": 0.2221915237870407, "rouge1_fmeasure_stderr": 0.0019942889407287214, "rouge1_precision": 0.20096070137159358, "rouge1_precision_stderr": 0.0024183404012715405, "rouge1_recall": 0.31553844384377067, "rouge1_recall_stderr": 0.002899492197080727, "rouge2_fmeasure": 0.056766090400891124, "rouge2_fmeasure_stderr": 0.0010805710237233974, "rouge2_precision": 0.05245104495325915, "rouge2_precision_stderr": 0.0012835508781176563, "rouge2_recall": 0.0826631709797398, "rouge2_recall_stderr": 0.0017188300283128646, "rougeL_fmeasure": 0.15912396957362257, "rougeL_fmeasure_stderr": 0.0013601645244304275, "rougeL_precision": 0.14393356016704015, "rougeL_precision_stderr": 0.001799791687854001, "rougeL_recall": 0.23074840768589486, "rougeL_recall_stderr": 0.0022312022411283892, "rougeLsum_fmeasure": 0.20821150035815492, "rougeLsum_fmeasure_stderr": 0.0018771242477053024, "rougeLsum_precision": 0.18819591770649413, "rougeLsum_precision_stderr": 0.002281534419296507, "rougeLsum_recall": 0.2963346702924994, "rougeLsum_recall_stderr": 0.0027562668344971878}}, "2": {"tldr_en": {"bleu": 3.0672692499706633, "bleu_stderr": 0.049106354646547744, "rouge1_fmeasure": 0.22254451379263313, "rouge1_fmeasure_stderr": 0.001915395486050023, "rouge1_precision": 0.20680907589782577, "rouge1_precision_stderr": 0.002488502986523018, "rouge1_recall": 0.30989444650796616, "rouge1_recall_stderr": 0.002753786143548591, "rouge2_fmeasure": 0.057748452491246806, "rouge2_fmeasure_stderr": 0.001071605656207478, "rouge2_precision": 0.05499744970071221, "rouge2_precision_stderr": 0.001313828428933835, "rouge2_recall": 0.08212190745009494, "rouge2_recall_stderr": 0.0016893036964833342, "rougeL_fmeasure": 0.15964814622161871, "rougeL_fmeasure_stderr": 0.0013347717397906025, "rougeL_precision": 0.14843146397136125, "rougeL_precision_stderr": 0.0018718282405222096, "rougeL_recall": 0.22714968032490238, "rougeL_recall_stderr": 0.0022095657686829933, "rougeLsum_fmeasure": 0.20960062484582434, "rougeLsum_fmeasure_stderr": 0.0018046035863626521, "rougeLsum_precision": 0.19471899528471098, "rougeLsum_precision_stderr": 0.002355009451192118, "rougeLsum_recall": 0.292336561157753, "rougeLsum_recall_stderr": 0.0026262120649372398}}, "3": {"tldr_en": {"bleu": 3.0771001660724235, "bleu_stderr": 0.10166627860233955, "rouge1_fmeasure": 0.1820115847047415, "rouge1_fmeasure_stderr": 0.002231556986150065, "rouge1_precision": 0.17474019948410954, "rouge1_precision_stderr": 0.0027474429834987804, "rouge1_recall": 0.25521371457329683, "rouge1_recall_stderr": 0.0033152648455079072, "rouge2_fmeasure": 0.04689779702656875, "rouge2_fmeasure_stderr": 0.001034952296288115, "rouge2_precision": 0.045362687902130126, "rouge2_precision_stderr": 0.0012564421439368422, "rouge2_recall": 0.06804888392817302, "rouge2_recall_stderr": 0.0016992089106080323, "rougeL_fmeasure": 0.13086000378258256, "rougeL_fmeasure_stderr": 0.0015951624748139174, "rougeL_precision": 0.1265226291981258, "rougeL_precision_stderr": 0.002108936479136444, "rougeL_recall": 0.18709591094229805, "rougeL_recall_stderr": 0.002591170589040495, "rougeLsum_fmeasure": 0.17171382413552935, "rougeLsum_fmeasure_stderr": 0.0021029154857551075, "rougeLsum_precision": 0.1650854923795236, "rougeLsum_precision_stderr": 0.0026195222440337307, "rougeLsum_recall": 0.24111486429370707, "rougeLsum_recall_stderr": 0.003150424029915772}}, "4": {"tldr_en": {"bleu": 0.6074700254086013, "bleu_stderr": 0.05423743996990111, "rouge1_fmeasure": 0.05660115935642753, "rouge1_fmeasure_stderr": 0.0019128121580337133, "rouge1_precision": 0.05686654081896349, "rouge1_precision_stderr": 0.002233440497229162, "rouge1_recall": 0.08353923265042008, "rouge1_recall_stderr": 0.0029077074042461065, "rouge2_fmeasure": 0.013741746630537094, "rouge2_fmeasure_stderr": 0.0006742800088300104, "rouge2_precision": 0.012648534117560613, "rouge2_precision_stderr": 0.000714480304383431, "rouge2_recall": 0.02199374005627044, "rouge2_recall_stderr": 0.0012054249033507543, "rougeL_fmeasure": 0.04194122086488744, "rougeL_fmeasure_stderr": 0.0014016615434499398, "rougeL_precision": 0.04243723633575883, "rougeL_precision_stderr": 0.0017020140807939923, "rougeL_recall": 0.0631413785577323, "rougeL_recall_stderr": 0.002247650978929538, "rougeLsum_fmeasure": 0.05334942672891278, "rougeLsum_fmeasure_stderr": 0.0018012620317959791, "rougeLsum_precision": 0.05323619772247561, "rougeLsum_precision_stderr": 0.0020619540523883185, "rougeLsum_recall": 0.07914684184702428, "rougeLsum_recall_stderr": 0.0027725917227984414}}, "5": {"tldr_en": {"bleu": 1.0033020706801269e-06, "bleu_stderr": 1.9077024795694913e-06, "rouge1_fmeasure": 0.009252067005496314, "rouge1_fmeasure_stderr": 0.0008857404763954463, "rouge1_precision": 0.008781294870051274, "rouge1_precision_stderr": 0.0009050499890841822, "rouge1_recall": 0.013677582922976033, "rouge1_recall_stderr": 0.0013193791852402054, "rouge2_fmeasure": 0.0023512305693387013, "rouge2_fmeasure_stderr": 0.0002931024418143357, "rouge2_precision": 0.002216585419720102, "rouge2_precision_stderr": 0.0003047584752236144, "rouge2_recall": 0.0035060227812251585, "rouge2_recall_stderr": 0.0004475043348074056, "rougeL_fmeasure": 0.007007677157867705, "rougeL_fmeasure_stderr": 0.0006708462523675694, "rougeL_precision": 0.00679769925058833, "rougeL_precision_stderr": 0.000718459101307871, "rougeL_recall": 0.010367182111106583, "rougeL_recall_stderr": 0.0010118399277303067, "rougeLsum_fmeasure": 0.008671543071872297, "rougeLsum_fmeasure_stderr": 0.0008282868408056053, "rougeLsum_precision": 0.0082009891177148, "rougeLsum_precision_stderr": 0.0008441371445186326, "rougeLsum_recall": 0.012916195361676434, "rougeLsum_recall_stderr": 0.0012503160451136067}}}, "e2e_nlg_cleaned": {"0": {"generate_text_restaurant": {"bleu": 0.5451634050753023, "bleu_stderr": 0.03476122561593657, "rouge1_fmeasure": 0.04310290552413315, "rouge1_fmeasure_stderr": 0.0013354170612674893, "rouge1_precision": 0.046590041682019065, "rouge1_precision_stderr": 0.0018113877733116784, "rouge1_recall": 0.05509845941495712, "rouge1_recall_stderr": 0.0017154015403554534, "rouge2_fmeasure": 0.0063826724183375155, "rouge2_fmeasure_stderr": 0.0004428905323251431, "rouge2_precision": 0.0061050451406738674, "rouge2_precision_stderr": 0.0004913565515769247, "rouge2_recall": 0.009015504658999519, "rouge2_recall_stderr": 0.0006494884515366231, "rougeL_fmeasure": 0.041469788976882346, "rougeL_fmeasure_stderr": 0.0012468639228984321, "rougeL_precision": 0.04442283664669869, "rougeL_precision_stderr": 0.0016857127584432392, "rougeL_recall": 0.053364978373077035, "rougeL_recall_stderr": 0.0016220526842467798, "rougeLsum_fmeasure": 0.03867299387707548, "rougeLsum_fmeasure_stderr": 0.0011657405780310776, "rougeLsum_precision": 0.04212798093112617, "rougeLsum_precision_stderr": 0.00163957458202675, "rougeLsum_recall": 0.04928251726552432, "rougeLsum_recall_stderr": 0.0014753429112820023}}, "1": {"generate_text_restaurant": {"bleu": 11.396112958955289, "bleu_stderr": 0.12774001717020914, "rouge1_fmeasure": 0.4479642771715969, "rouge1_fmeasure_stderr": 0.0023079960050490524, "rouge1_precision": 0.5339579313432855, "rouge1_precision_stderr": 0.0031227264254700595, "rouge1_recall": 0.42523020862127436, "rouge1_recall_stderr": 0.002981115684302531, "rouge2_fmeasure": 0.2056915755809246, "rouge2_fmeasure_stderr": 0.0019163170514045066, "rouge2_precision": 0.248732624279182, "rouge2_precision_stderr": 0.002509203740513705, "rouge2_recall": 0.1952491238459977, "rouge2_recall_stderr": 0.0020864674211335237, "rougeL_fmeasure": 0.3204968358680575, "rougeL_fmeasure_stderr": 0.001985520070286022, "rougeL_precision": 0.3850344789575973, "rougeL_precision_stderr": 0.00278033592883375, "rougeL_recall": 0.3033612056952134, "rougeL_recall_stderr": 0.002388739694886294, "rougeLsum_fmeasure": 0.36313254630951347, "rougeLsum_fmeasure_stderr": 0.0022360796971689707, "rougeLsum_precision": 0.4342921156865786, "rougeLsum_precision_stderr": 0.003003575710929277, "rougeLsum_recall": 0.34421205733760346, "rougeLsum_recall_stderr": 0.0026942002219059206}}, "2": {"generate_text_restaurant": {"bleu": 12.976405649449786, "bleu_stderr": 0.20113725542092992, "rouge1_fmeasure": 0.47007019927530463, "rouge1_fmeasure_stderr": 0.0022920087841303556, "rouge1_precision": 0.558994227405181, "rouge1_precision_stderr": 0.0032295866736836163, "rouge1_recall": 0.44495262240037453, "rouge1_recall_stderr": 0.0029490508361979437, "rouge2_fmeasure": 0.22591032128288588, "rouge2_fmeasure_stderr": 0.0020560357969047136, "rouge2_precision": 0.27217728286113113, "rouge2_precision_stderr": 0.0026898706377774815, "rouge2_recall": 0.21411207509510502, "rouge2_recall_stderr": 0.002230097528851014, "rougeL_fmeasure": 0.3425232001087342, "rougeL_fmeasure_stderr": 0.0020806737697165846, "rougeL_precision": 0.40975809640656674, "rougeL_precision_stderr": 0.00294221380121017, "rougeL_recall": 0.3236212819558878, "rougeL_recall_stderr": 0.0024673142471829217, "rougeLsum_fmeasure": 0.3859835303051329, "rougeLsum_fmeasure_stderr": 0.0023029475516390383, "rougeLsum_precision": 0.46033224287141866, "rougeLsum_precision_stderr": 0.0031762512099836643, "rougeLsum_recall": 0.3647714098177991, "rougeLsum_recall_stderr": 0.0027210820647532467}}, "3": {"generate_text_restaurant": {"bleu": 13.841780368990428, "bleu_stderr": 0.16004525418920557, "rouge1_fmeasure": 0.4775062117887383, "rouge1_fmeasure_stderr": 0.0022520658159749783, "rouge1_precision": 0.5672114023663154, "rouge1_precision_stderr": 0.0031836037058964135, "rouge1_recall": 0.4506315681499688, "rouge1_recall_stderr": 0.0028976257859202057, "rouge2_fmeasure": 0.23547797340215765, "rouge2_fmeasure_stderr": 0.002080191282609909, "rouge2_precision": 0.2831489435622744, "rouge2_precision_stderr": 0.0026849363746315716, "rouge2_recall": 0.2224359793863677, "rouge2_recall_stderr": 0.0022585552678834257, "rougeL_fmeasure": 0.3522099816274127, "rougeL_fmeasure_stderr": 0.0021360587201332483, "rougeL_precision": 0.42052513955243626, "rougeL_precision_stderr": 0.0029794181672521524, "rougeL_recall": 0.3316609702212396, "rougeL_recall_stderr": 0.002482260811969057, "rougeLsum_fmeasure": 0.39783266320253785, "rougeLsum_fmeasure_stderr": 0.0023487903214587246, "rougeLsum_precision": 0.4731322251491655, "rougeLsum_precision_stderr": 0.0031830112351273762, "rougeLsum_recall": 0.3751305124701987, "rougeLsum_recall_stderr": 0.0027537781991579034}}, "4": {"generate_text_restaurant": {"bleu": 14.347043577937871, "bleu_stderr": 0.13183200117809515, "rouge1_fmeasure": 0.4791803139648653, "rouge1_fmeasure_stderr": 0.0022359999842246512, "rouge1_precision": 0.5657141271378652, "rouge1_precision_stderr": 0.0032494806378829547, "rouge1_recall": 0.4543139798474618, "rouge1_recall_stderr": 0.002865992018425755, "rouge2_fmeasure": 0.23765394178309218, "rouge2_fmeasure_stderr": 0.0021422406093072697, "rouge2_precision": 0.2840374640470508, "rouge2_precision_stderr": 0.0028091760925762137, "rouge2_recall": 0.22548495306647312, "rouge2_recall_stderr": 0.002307333846171272, "rougeL_fmeasure": 0.3551586826634256, "rougeL_fmeasure_stderr": 0.0021591742079548407, "rougeL_precision": 0.4208287732411973, "rougeL_precision_stderr": 0.003031588432467615, "rougeL_recall": 0.33645734099493246, "rougeL_recall_stderr": 0.0025176571940632108, "rougeLsum_fmeasure": 0.40243539061119715, "rougeLsum_fmeasure_stderr": 0.002367520270615011, "rougeLsum_precision": 0.47480321305856177, "rougeLsum_precision_stderr": 0.003220379872286072, "rougeLsum_recall": 0.38184109614706496, "rougeLsum_recall_stderr": 0.002799589796872638}}, "5": {"generate_text_restaurant": {"bleu": 14.305213942543, "bleu_stderr": 0.1483607819215848, "rouge1_fmeasure": 0.4804680058354203, "rouge1_fmeasure_stderr": 0.0021741397703150594, "rouge1_precision": 0.5597772799865962, "rouge1_precision_stderr": 0.0031779357829373007, "rouge1_recall": 0.45931387100423793, "rouge1_recall_stderr": 0.002804556836326018, "rouge2_fmeasure": 0.2366049201616526, "rouge2_fmeasure_stderr": 0.0020482405764989274, "rouge2_precision": 0.27941286210601324, "rouge2_precision_stderr": 0.002685923767684149, "rouge2_recall": 0.2261024234770814, "rouge2_recall_stderr": 0.002220825905817483, "rougeL_fmeasure": 0.3555529772285316, "rougeL_fmeasure_stderr": 0.0020868456031009723, "rougeL_precision": 0.4153388685887487, "rougeL_precision_stderr": 0.002922026669760074, "rougeL_recall": 0.33991925444128, "rougeL_recall_stderr": 0.0024671212347911007, "rougeLsum_fmeasure": 0.403868227449958, "rougeLsum_fmeasure_stderr": 0.0023025847428200684, "rougeLsum_precision": 0.470187398074112, "rougeLsum_precision_stderr": 0.0031325933820836164, "rougeLsum_recall": 0.3864435015330604, "rougeLsum_recall_stderr": 0.0027449279832689228}}}, "gem_xsum": {"0": {"article_DOC_summary": {"bleu": 2.103288067343989, "bleu_stderr": 0.12415880355418442, "rouge1_fmeasure": 0.2135984788737725, "rouge1_fmeasure_stderr": 0.0026714992621488937, "rouge1_precision": 0.1691487054500622, "rouge1_precision_stderr": 0.0024250397934530475, "rouge1_recall": 0.3329424577074328, "rouge1_recall_stderr": 0.004657379753879945, "rouge2_fmeasure": 0.04790575968435739, "rouge2_fmeasure_stderr": 0.0017255007150536288, "rouge2_precision": 0.03660197341061794, "rouge2_precision_stderr": 0.0013876615412254558, "rouge2_recall": 0.07882441796533844, "rouge2_recall_stderr": 0.0029121244310315966, "rougeL_fmeasure": 0.15810158263668517, "rougeL_fmeasure_stderr": 0.0020195259778767218, "rougeL_precision": 0.12480506419752084, "rougeL_precision_stderr": 0.0018165017981600132, "rougeL_recall": 0.24849031836840368, "rougeL_recall_stderr": 0.0036491823702079194, "rougeLsum_fmeasure": 0.16520124922802173, "rougeLsum_fmeasure_stderr": 0.0022185800515451995, "rougeLsum_precision": 0.12993544368406393, "rougeLsum_precision_stderr": 0.0019145615600976785, "rougeLsum_recall": 0.26077607018509813, "rougeLsum_recall_stderr": 0.004054503415661984}}, "1": {"article_DOC_summary": {"bleu": 1.7714825425476433, "bleu_stderr": 0.10905675609895228, "rouge1_fmeasure": 0.19244278875333556, "rouge1_fmeasure_stderr": 0.002639391462026543, "rouge1_precision": 0.1369839651831878, "rouge1_precision_stderr": 0.0019614322408207006, "rouge1_recall": 0.3369949215642884, "rouge1_recall_stderr": 0.004522579510481593, "rouge2_fmeasure": 0.04413377405232099, "rouge2_fmeasure_stderr": 0.0015985481401232032, "rouge2_precision": 0.031094803643512716, "rouge2_precision_stderr": 0.0011365997631264868, "rouge2_recall": 0.07935713496492708, "rouge2_recall_stderr": 0.002884276945599807, "rougeL_fmeasure": 0.1500620628581487, "rougeL_fmeasure_stderr": 0.0020207447957827454, "rougeL_precision": 0.10657563716596334, "rougeL_precision_stderr": 0.0014875062360428326, "rougeL_recall": 0.26467978376956175, "rougeL_recall_stderr": 0.0036163241442920165, "rougeLsum_fmeasure": 0.15187454343375792, "rougeLsum_fmeasure_stderr": 0.0021906040942089064, "rougeLsum_precision": 0.1078060619083588, "rougeLsum_precision_stderr": 0.0016045831813046104, "rougeLsum_recall": 0.2680535986457037, "rougeLsum_recall_stderr": 0.0038953175735036904}}, "2": {"article_DOC_summary": {"bleu": 1.8719539285791582, "bleu_stderr": 0.12363679141275902, "rouge1_fmeasure": 0.19861514735566918, "rouge1_fmeasure_stderr": 0.002536869900552261, "rouge1_precision": 0.1416725332039807, "rouge1_precision_stderr": 0.0019003755973271465, "rouge1_recall": 0.3459660596871756, "rouge1_recall_stderr": 0.004306340084752496, "rouge2_fmeasure": 0.046170973346933354, "rouge2_fmeasure_stderr": 0.0016039666517335285, "rouge2_precision": 0.032589396300244954, "rouge2_precision_stderr": 0.001135411316234186, "rouge2_recall": 0.08273970858446308, "rouge2_recall_stderr": 0.0029435229941216076, "rougeL_fmeasure": 0.1563808799657367, "rougeL_fmeasure_stderr": 0.0019620345863827896, "rougeL_precision": 0.11131065526290164, "rougeL_precision_stderr": 0.0014510877883445626, "rougeL_recall": 0.2741645486545069, "rougeL_recall_stderr": 0.003497544935564585, "rougeLsum_fmeasure": 0.15581654576519338, "rougeLsum_fmeasure_stderr": 0.0021586761800846295, "rougeLsum_precision": 0.11082674371408649, "rougeLsum_precision_stderr": 0.0015845483453646742, "rougeLsum_recall": 0.2737340240682109, "rougeLsum_recall_stderr": 0.003854876130312793}}, "3": {"article_DOC_summary": {"bleu": 2.0369871247788307, "bleu_stderr": 0.11889285675918113, "rouge1_fmeasure": 0.19191359742761793, "rouge1_fmeasure_stderr": 0.00277051626651925, "rouge1_precision": 0.13956778448576387, "rouge1_precision_stderr": 0.0021737270808076243, "rouge1_recall": 0.329102550985314, "rouge1_recall_stderr": 0.004775853265191935, "rouge2_fmeasure": 0.04715930396420784, "rouge2_fmeasure_stderr": 0.001624147693037141, "rouge2_precision": 0.034143138087541, "rouge2_precision_stderr": 0.0012197975952686348, "rouge2_recall": 0.08270285997486158, "rouge2_recall_stderr": 0.0029002084266991856, "rougeL_fmeasure": 0.1528761624914166, "rougeL_fmeasure_stderr": 0.002169630539318251, "rougeL_precision": 0.11089339313344634, "rougeL_precision_stderr": 0.0016751091885532099, "rougeL_recall": 0.26375167528125915, "rougeL_recall_stderr": 0.0038713870137101424, "rougeLsum_fmeasure": 0.15380687866772882, "rougeLsum_fmeasure_stderr": 0.002388364659924707, "rougeLsum_precision": 0.11161318605392968, "rougeLsum_precision_stderr": 0.0018444411300991288, "rougeLsum_recall": 0.26547328847718554, "rougeLsum_recall_stderr": 0.004239107141632789}}, "4": {"article_DOC_summary": {"bleu": 0.9532704572175751, "bleu_stderr": 0.1334974714932564, "rouge1_fmeasure": 0.053658040802239085, "rouge1_fmeasure_stderr": 0.0029774150017601803, "rouge1_precision": 0.045437643598581885, "rouge1_precision_stderr": 0.002731741164998445, "rouge1_recall": 0.0834633850546414, "rouge1_recall_stderr": 0.004709515538170699, "rouge2_fmeasure": 0.012335864733508397, "rouge2_fmeasure_stderr": 0.0010450675751901856, "rouge2_precision": 0.009714659363066126, "rouge2_precision_stderr": 0.0009061043015811388, "rouge2_recall": 0.020204993259341004, "rouge2_recall_stderr": 0.0017173474943290197, "rougeL_fmeasure": 0.041486821630655535, "rougeL_fmeasure_stderr": 0.0022764116642440576, "rougeL_precision": 0.03525079234225019, "rougeL_precision_stderr": 0.0021438053902596605, "rougeL_recall": 0.06521180915166398, "rougeL_recall_stderr": 0.003703751644624955, "rougeLsum_fmeasure": 0.04288192765446807, "rougeLsum_fmeasure_stderr": 0.0023977202282267356, "rougeLsum_precision": 0.03647650806323336, "rougeLsum_precision_stderr": 0.002248078408967042, "rougeLsum_recall": 0.06711329846733026, "rougeLsum_recall_stderr": 0.003863144394106958}}, "5": {"article_DOC_summary": {"bleu": 3.120169018915429e-39, "bleu_stderr": 2.777103521919484e-32, "rouge1_fmeasure": 0.002997767517780879, "rouge1_fmeasure_stderr": 0.0008334506629000642, "rouge1_precision": 0.003263719197769084, "rouge1_precision_stderr": 0.0008887617448902996, "rouge1_recall": 0.0028345456514645845, "rouge1_recall_stderr": 0.0008116977743173961, "rouge2_fmeasure": 0.0004337191943913522, "rouge2_fmeasure_stderr": 0.00021214389566854186, "rouge2_precision": 0.0004590858641913026, "rouge2_precision_stderr": 0.00021377485443811557, "rouge2_recall": 0.00041953329689178745, "rouge2_recall_stderr": 0.00021411305439143847, "rougeL_fmeasure": 0.002106529594577242, "rougeL_fmeasure_stderr": 0.0005845294157065285, "rougeL_precision": 0.0023145025817495005, "rougeL_precision_stderr": 0.0006312757980824667, "rougeL_recall": 0.0019717134578344517, "rougeL_recall_stderr": 0.0005600175515270516, "rougeLsum_fmeasure": 0.0024033045589119204, "rougeLsum_fmeasure_stderr": 0.0006766571604709825, "rougeLsum_precision": 0.0026347083023874887, "rougeLsum_precision_stderr": 0.0007273791404483311, "rougeLsum_recall": 0.00225801889401816, "rougeLsum_recall_stderr": 0.000653191190142516}}}}