{"GEM/web_nlg_en": {"0": {"PALM_prompt": {"bleu": 0.5360651854033321, "bleu_stderr": 0.04256493048481422, "rouge1_fmeasure": 0.11703731094627681, "rouge1_fmeasure_stderr": 0.0023099010503697163, "rouge1_precision": 0.0899710062520438, "rouge1_precision_stderr": 0.002733564353594117, "rouge1_recall": 0.33063321497259557, "rouge1_recall_stderr": 0.005082809158106232, "rouge2_fmeasure": 0.050209876854654424, "rouge2_fmeasure_stderr": 0.00139566067725402, "rouge2_precision": 0.039336196641808305, "rouge2_precision_stderr": 0.001715101531039642, "rouge2_recall": 0.14377777116972676, "rouge2_recall_stderr": 0.003290079655812811, "rougeL_fmeasure": 0.10410690412481492, "rougeL_fmeasure_stderr": 0.001970211495017576, "rougeL_precision": 0.079768875505422, "rougeL_precision_stderr": 0.0024190846876120864, "rougeL_recall": 0.29935042842995513, "rougeL_recall_stderr": 0.004616391395045465, "rougeLsum_fmeasure": 0.10721436888153839, "rougeLsum_fmeasure_stderr": 0.0021127388747576538, "rougeLsum_precision": 0.0826555500749783, "rougeLsum_precision_stderr": 0.002555867928952612, "rougeLsum_recall": 0.30355552506299893, "rougeLsum_recall_stderr": 0.004656831028738861}}, "1": {"PALM_prompt": {"bleu": 0.6802224009591102, "bleu_stderr": 0.04492815625354331, "rouge1_fmeasure": 0.11390823787630369, "rouge1_fmeasure_stderr": 0.002092748719741799, "rouge1_precision": 0.07461313068432787, "rouge1_precision_stderr": 0.0017662222515359694, "rouge1_recall": 0.372595398614972, "rouge1_recall_stderr": 0.005022894768490944, "rouge2_fmeasure": 0.04788274742708309, "rouge2_fmeasure_stderr": 0.001335468400942394, "rouge2_precision": 0.03144260517505359, "rouge2_precision_stderr": 0.0010954007812074113, "rouge2_recall": 0.16216117762517218, "rouge2_recall_stderr": 0.003540557825236836, "rougeL_fmeasure": 0.09862949956148871, "rougeL_fmeasure_stderr": 0.0017348311881018063, "rougeL_precision": 0.06430823474158391, "rougeL_precision_stderr": 0.001450822149093989, "rougeL_recall": 0.32776952027123735, "rougeL_recall_stderr": 0.004463575595509288, "rougeLsum_fmeasure": 0.10371590290401189, "rougeLsum_fmeasure_stderr": 0.001919446152689098, "rougeLsum_precision": 0.06792680129399332, "rougeLsum_precision_stderr": 0.0016204262837167783, "rougeLsum_recall": 0.33968125496997575, "rougeLsum_recall_stderr": 0.0045445995282505924}}, "2": {"PALM_prompt": {"bleu": 0.7421753234818311, "bleu_stderr": 0.058142097599066474, "rouge1_fmeasure": 0.11568167659841286, "rouge1_fmeasure_stderr": 0.0019756616545099706, "rouge1_precision": 0.07467676852089566, "rouge1_precision_stderr": 0.0016365713066735295, "rouge1_recall": 0.39206002680015317, "rouge1_recall_stderr": 0.005060271412913158, "rouge2_fmeasure": 0.049111982430960446, "rouge2_fmeasure_stderr": 0.0012783990550174547, "rouge2_precision": 0.03201968689196959, "rouge2_precision_stderr": 0.0010606073690619061, "rouge2_recall": 0.17433943475684258, "rouge2_recall_stderr": 0.0036664073103424713, "rougeL_fmeasure": 0.10005506236504283, "rougeL_fmeasure_stderr": 0.001651667409449542, "rougeL_precision": 0.06439207073032543, "rougeL_precision_stderr": 0.001373955096716673, "rougeL_recall": 0.34371763245797454, "rougeL_recall_stderr": 0.004505609280479333, "rougeLsum_fmeasure": 0.1050019387672539, "rougeLsum_fmeasure_stderr": 0.0018008044515920333, "rougeLsum_precision": 0.06782658473689997, "rougeLsum_precision_stderr": 0.0015027459055493005, "rougeLsum_recall": 0.35767707252188435, "rougeLsum_recall_stderr": 0.004646683404394275}}, "3": {"PALM_prompt": {"bleu": 0.7188535617714238, "bleu_stderr": 0.03519944556258603, "rouge1_fmeasure": 0.11579215217674567, "rouge1_fmeasure_stderr": 0.0018264739390039843, "rouge1_precision": 0.07388743389054267, "rouge1_precision_stderr": 0.0014922551498186853, "rouge1_recall": 0.40655159407197466, "rouge1_recall_stderr": 0.005087707266532105, "rouge2_fmeasure": 0.04901217699390464, "rouge2_fmeasure_stderr": 0.0011685479931085388, "rouge2_precision": 0.0314899543029952, "rouge2_precision_stderr": 0.0009557711556575558, "rouge2_recall": 0.1826251549753492, "rouge2_recall_stderr": 0.003641907390766911, "rougeL_fmeasure": 0.0983386270641459, "rougeL_fmeasure_stderr": 0.001492600011551131, "rougeL_precision": 0.06252862451464879, "rougeL_precision_stderr": 0.00121227139148576, "rougeL_recall": 0.3504975578791793, "rougeL_recall_stderr": 0.00448181425469438, "rougeLsum_fmeasure": 0.10530117384191293, "rougeLsum_fmeasure_stderr": 0.0016684330187746533, "rougeLsum_precision": 0.06730929990997614, "rougeLsum_precision_stderr": 0.0013838254439389821, "rougeLsum_recall": 0.3708026802911801, "rougeLsum_recall_stderr": 0.004623882247190055}}, "4": {"PALM_prompt": {"bleu": 0.7356439715076686, "bleu_stderr": 0.034000125678247964, "rouge1_fmeasure": 0.1147943522144661, "rouge1_fmeasure_stderr": 0.0018063385532961329, "rouge1_precision": 0.07276465535536372, "rouge1_precision_stderr": 0.001402274340634281, "rouge1_recall": 0.4010732633333032, "rouge1_recall_stderr": 0.005031473102978275, "rouge2_fmeasure": 0.04799828271736168, "rouge2_fmeasure_stderr": 0.0011481297831730717, "rouge2_precision": 0.030441136569863136, "rouge2_precision_stderr": 0.0008680169230332024, "rouge2_recall": 0.17998860942195416, "rouge2_recall_stderr": 0.0035899170058648713, "rougeL_fmeasure": 0.09700958657806398, "rougeL_fmeasure_stderr": 0.0014957916703609423, "rougeL_precision": 0.061409018888316014, "rougeL_precision_stderr": 0.001162871962197699, "rougeL_recall": 0.34312128735122893, "rougeL_recall_stderr": 0.004376699961011487, "rougeLsum_fmeasure": 0.10389368450136928, "rougeLsum_fmeasure_stderr": 0.0016495601390011836, "rougeLsum_precision": 0.06590967070216937, "rougeLsum_precision_stderr": 0.0012895737406364428, "rougeLsum_recall": 0.3647408763184601, "rougeLsum_recall_stderr": 0.004596517842636764}}, "5": {"PALM_prompt": {"bleu": 0.774498674641057, "bleu_stderr": 0.046025666098424615, "rouge1_fmeasure": 0.1145076719006982, "rouge1_fmeasure_stderr": 0.0017986089153009496, "rouge1_precision": 0.07168554541147722, "rouge1_precision_stderr": 0.0013567491666828951, "rouge1_recall": 0.40311382031478993, "rouge1_recall_stderr": 0.005093519815631301, "rouge2_fmeasure": 0.04748834860177524, "rouge2_fmeasure_stderr": 0.0011381885469089572, "rouge2_precision": 0.029640249400459045, "rouge2_precision_stderr": 0.0008248970598907547, "rouge2_recall": 0.17922361100140816, "rouge2_recall_stderr": 0.0036463149274911922, "rougeL_fmeasure": 0.09581522945526423, "rougeL_fmeasure_stderr": 0.0014457046424409396, "rougeL_precision": 0.05979676606804081, "rougeL_precision_stderr": 0.0010829180120786699, "rougeL_recall": 0.3429993601688589, "rougeL_recall_stderr": 0.0044165337458333025, "rougeLsum_fmeasure": 0.10343462084662852, "rougeLsum_fmeasure_stderr": 0.0016190969843153712, "rougeLsum_precision": 0.0647765765675484, "rougeLsum_precision_stderr": 0.0012251354927212512, "rougeLsum_recall": 0.36627971544729243, "rougeLsum_recall_stderr": 0.00466986591996086}}}, "GEM/wiki_lingua_en": {"0": {"tldr_en": {"bleu": 1.5232593023758256, "bleu_stderr": 0.04747265065152494, "rouge1_fmeasure": 0.18849953981212825, "rouge1_fmeasure_stderr": 0.0017651084291359991, "rouge1_precision": 0.16713881881245704, "rouge1_precision_stderr": 0.0019675559614062317, "rouge1_recall": 0.2675635999010821, "rouge1_recall_stderr": 0.002514916375462715, "rouge2_fmeasure": 0.03506973226946951, "rouge2_fmeasure_stderr": 0.000828365798842279, "rouge2_precision": 0.03129812627625643, "rouge2_precision_stderr": 0.0008361148272854467, "rouge2_recall": 0.05071754722622078, "rouge2_recall_stderr": 0.001311834312898096, "rougeL_fmeasure": 0.13822063710515434, "rougeL_fmeasure_stderr": 0.001209603068162531, "rougeL_precision": 0.12151132876190665, "rougeL_precision_stderr": 0.001367091894817583, "rougeL_recall": 0.20104126997571714, "rougeL_recall_stderr": 0.0019684739493456994, "rougeLsum_fmeasure": 0.17552265116019092, "rougeLsum_fmeasure_stderr": 0.001631387985609637, "rougeLsum_precision": 0.15537471654065166, "rougeLsum_precision_stderr": 0.0018202212529241414, "rougeLsum_recall": 0.25004836431590777, "rougeLsum_recall_stderr": 0.0023701023893618026}}, "1": {"tldr_en": {"bleu": 1.8880118627721794, "bleu_stderr": 0.05942943111971925, "rouge1_fmeasure": 0.1984602458949581, "rouge1_fmeasure_stderr": 0.001835524387024883, "rouge1_precision": 0.17053090746783298, "rouge1_precision_stderr": 0.0019872482776833456, "rouge1_recall": 0.2862592054300288, "rouge1_recall_stderr": 0.0025208248871725165, "rouge2_fmeasure": 0.04000846126572821, "rouge2_fmeasure_stderr": 0.0008452030738686245, "rouge2_precision": 0.034781757767719336, "rouge2_precision_stderr": 0.0007914156120289567, "rouge2_recall": 0.05819412473089733, "rouge2_recall_stderr": 0.0013767099922495528, "rougeL_fmeasure": 0.14054619741164162, "rougeL_fmeasure_stderr": 0.0012057251064722665, "rougeL_precision": 0.11920675042988256, "rougeL_precision_stderr": 0.0012760690917858948, "rougeL_recall": 0.2090473969119961, "rougeL_recall_stderr": 0.0019879307284216374, "rougeLsum_fmeasure": 0.18719993560041495, "rougeLsum_fmeasure_stderr": 0.0017213110797211495, "rougeLsum_precision": 0.16072751156146212, "rougeLsum_precision_stderr": 0.0018664748954273353, "rougeLsum_recall": 0.2708352805729064, "rougeLsum_recall_stderr": 0.0023993133135588726}}, "2": {"tldr_en": {"bleu": 2.044058833379777, "bleu_stderr": 0.041953937602340896, "rouge1_fmeasure": 0.20351754507246114, "rouge1_fmeasure_stderr": 0.0017840270190731694, "rouge1_precision": 0.17521114979818148, "rouge1_precision_stderr": 0.0019971191521694237, "rouge1_recall": 0.29505512111856136, "rouge1_recall_stderr": 0.002482377287715188, "rouge2_fmeasure": 0.04133083707035807, "rouge2_fmeasure_stderr": 0.000856187073681672, "rouge2_precision": 0.036078610027588165, "rouge2_precision_stderr": 0.0008246029351859187, "rouge2_recall": 0.06091288234269016, "rouge2_recall_stderr": 0.0014548836676621338, "rougeL_fmeasure": 0.14198764195001126, "rougeL_fmeasure_stderr": 0.0011641554814427809, "rougeL_precision": 0.12068563083479135, "rougeL_precision_stderr": 0.0012692637381675736, "rougeL_recall": 0.21169778984086512, "rougeL_recall_stderr": 0.001937114431082882, "rougeLsum_fmeasure": 0.19139812574716686, "rougeLsum_fmeasure_stderr": 0.00166952084328464, "rougeLsum_precision": 0.16463657951818378, "rougeLsum_precision_stderr": 0.0018721618563475912, "rougeLsum_recall": 0.27817600580901414, "rougeLsum_recall_stderr": 0.0023540319937164467}}, "3": {"tldr_en": {"bleu": 1.9396853588642966, "bleu_stderr": 0.08436045314084763, "rouge1_fmeasure": 0.16866495698431502, "rouge1_fmeasure_stderr": 0.0020804742919056395, "rouge1_precision": 0.14952794366183797, "rouge1_precision_stderr": 0.0022058583212912894, "rouge1_recall": 0.2452665800285056, "rouge1_recall_stderr": 0.0030704239734715643, "rouge2_fmeasure": 0.03416690056560839, "rouge2_fmeasure_stderr": 0.0008143086155271332, "rouge2_precision": 0.03004702509666011, "rouge2_precision_stderr": 0.0008311502047120946, "rouge2_recall": 0.05157913638840345, "rouge2_recall_stderr": 0.001422503519963882, "rougeL_fmeasure": 0.11914034077321806, "rougeL_fmeasure_stderr": 0.001414045100639011, "rougeL_precision": 0.10508212692824712, "rougeL_precision_stderr": 0.0015351142071270904, "rougeL_recall": 0.1780004213567274, "rougeL_recall_stderr": 0.0023476795324690334, "rougeLsum_fmeasure": 0.1589503965996838, "rougeLsum_fmeasure_stderr": 0.0019545618825912202, "rougeLsum_precision": 0.14081324897147796, "rougeLsum_precision_stderr": 0.0020751347908728626, "rougeLsum_recall": 0.23180239636511424, "rougeLsum_recall_stderr": 0.002923128111627586}}, "4": {"tldr_en": {"bleu": 0.3954106592667591, "bleu_stderr": 0.030424148288259543, "rouge1_fmeasure": 0.05506811843559695, "rouge1_fmeasure_stderr": 0.0018376936149103464, "rouge1_precision": 0.04937284041758572, "rouge1_precision_stderr": 0.0017645796727106123, "rouge1_recall": 0.0833503207360656, "rouge1_recall_stderr": 0.00281280262106624, "rouge2_fmeasure": 0.010634499122607565, "rouge2_fmeasure_stderr": 0.0005332176567831833, "rouge2_precision": 0.00925290416351339, "rouge2_precision_stderr": 0.0004935225555037847, "rouge2_recall": 0.01677617349133985, "rouge2_recall_stderr": 0.0009360795342904428, "rougeL_fmeasure": 0.039896533001018496, "rougeL_fmeasure_stderr": 0.0013013251448423227, "rougeL_precision": 0.035847971920994384, "rougeL_precision_stderr": 0.0012693963406449355, "rougeL_recall": 0.06190737436016968, "rougeL_recall_stderr": 0.002117457405307065, "rougeLsum_fmeasure": 0.051825504001507226, "rougeLsum_fmeasure_stderr": 0.0017233734941035895, "rougeLsum_precision": 0.04653344364816083, "rougeLsum_precision_stderr": 0.0016598993555511953, "rougeLsum_recall": 0.07865177981190832, "rougeLsum_recall_stderr": 0.0026624468386525343}}, "5": {"tldr_en": {"bleu": 7.859167635470547e-07, "bleu_stderr": 1.1934142180355652e-06, "rouge1_fmeasure": 0.009101557137028772, "rouge1_fmeasure_stderr": 0.0008140491421946896, "rouge1_precision": 0.008802342511085599, "rouge1_precision_stderr": 0.0008333254171856367, "rouge1_recall": 0.013846594891110736, "rouge1_recall_stderr": 0.001284943993178689, "rouge2_fmeasure": 0.0016982724173124299, "rouge2_fmeasure_stderr": 0.0001951130112550121, "rouge2_precision": 0.001520410895591214, "rouge2_precision_stderr": 0.00019110488537087714, "rouge2_recall": 0.002936659432696735, "rouge2_recall_stderr": 0.0004020275770238017, "rougeL_fmeasure": 0.006814509974228523, "rougeL_fmeasure_stderr": 0.0005978666541117267, "rougeL_precision": 0.006684691255186687, "rougeL_precision_stderr": 0.0006324968238367776, "rougeL_recall": 0.010578259743111997, "rougeL_recall_stderr": 0.0009807869745277378, "rougeLsum_fmeasure": 0.008490392592813478, "rougeLsum_fmeasure_stderr": 0.0007546988490410512, "rougeLsum_precision": 0.008241685827174364, "rougeLsum_precision_stderr": 0.0007767216582054409, "rougeLsum_recall": 0.012939045909680607, "rougeLsum_recall_stderr": 0.001191464823217516}}}, "e2e_nlg_cleaned": {"0": {"generate_text_restaurant": {"bleu": 1.7691179321908588, "bleu_stderr": 0.05199631794487594, "rouge1_fmeasure": 0.1597457244947749, "rouge1_fmeasure_stderr": 0.0015754443648131056, "rouge1_precision": 0.12404388162125599, "rouge1_precision_stderr": 0.0014296085692360062, "rouge1_recall": 0.24113298891528734, "rouge1_recall_stderr": 0.0021195221866358305, "rouge2_fmeasure": 0.035999793072600185, "rouge2_fmeasure_stderr": 0.0009624756735963167, "rouge2_precision": 0.028289803328052695, "rouge2_precision_stderr": 0.0008570729362836853, "rouge2_recall": 0.05442101911192778, "rouge2_recall_stderr": 0.0014043108131977875, "rougeL_fmeasure": 0.14600635284564262, "rougeL_fmeasure_stderr": 0.0013795631395537417, "rougeL_precision": 0.11310129172937744, "rougeL_precision_stderr": 0.0012492394490123515, "rougeL_recall": 0.22135445621870045, "rougeL_recall_stderr": 0.001908698378645529, "rougeLsum_fmeasure": 0.1355872624921452, "rougeLsum_fmeasure_stderr": 0.0014398399847291973, "rougeLsum_precision": 0.10515677540232808, "rougeLsum_precision_stderr": 0.0012984677845430614, "rougeLsum_recall": 0.20544674202250837, "rougeLsum_recall_stderr": 0.001966897239298014}}, "1": {"generate_text_restaurant": {"bleu": 5.651044586681334, "bleu_stderr": 0.07926438990816918, "rouge1_fmeasure": 0.3078278785254422, "rouge1_fmeasure_stderr": 0.001908062705345462, "rouge1_precision": 0.2716212972945311, "rouge1_precision_stderr": 0.0026058040333959537, "rouge1_recall": 0.4236216032222433, "rouge1_recall_stderr": 0.0026180226506166463, "rouge2_fmeasure": 0.12259566762702832, "rouge2_fmeasure_stderr": 0.0013108581526452968, "rouge2_precision": 0.10952561587924448, "rouge2_precision_stderr": 0.0016418857574103474, "rouge2_recall": 0.17185473066549486, "rouge2_recall_stderr": 0.0018971444386739766, "rougeL_fmeasure": 0.23718705321133973, "rougeL_fmeasure_stderr": 0.00138256279237305, "rougeL_precision": 0.20793662314020775, "rougeL_precision_stderr": 0.001966736398197739, "rougeL_recall": 0.3306629249371328, "rougeL_recall_stderr": 0.0021642636770467646, "rougeLsum_fmeasure": 0.2573509246055057, "rougeLsum_fmeasure_stderr": 0.0017483657121627276, "rougeLsum_precision": 0.2271295898568511, "rougeLsum_precision_stderr": 0.0023078665148769063, "rougeLsum_recall": 0.35503755430035955, "rougeLsum_recall_stderr": 0.002474276440762186}}, "2": {"generate_text_restaurant": {"bleu": 5.8424163448955415, "bleu_stderr": 0.08355827344599492, "rouge1_fmeasure": 0.31288302842111376, "rouge1_fmeasure_stderr": 0.0017808501976129172, "rouge1_precision": 0.2566016107317033, "rouge1_precision_stderr": 0.0022067745089076256, "rouge1_recall": 0.461194891770376, "rouge1_recall_stderr": 0.0025273079440682293, "rouge2_fmeasure": 0.12981003854776116, "rouge2_fmeasure_stderr": 0.001232713595041452, "rouge2_precision": 0.10663824144759744, "rouge2_precision_stderr": 0.001372692263793003, "rouge2_recall": 0.1963344119197119, "rouge2_recall_stderr": 0.0019212562311138061, "rougeL_fmeasure": 0.23920101858831294, "rougeL_fmeasure_stderr": 0.0012833315214473093, "rougeL_precision": 0.19466241734213402, "rougeL_precision_stderr": 0.0015883723269025356, "rougeL_recall": 0.35748703923277775, "rougeL_recall_stderr": 0.002135743881465239, "rougeLsum_fmeasure": 0.26382166088143494, "rougeLsum_fmeasure_stderr": 0.0016894009510511382, "rougeLsum_precision": 0.2160451049013204, "rougeLsum_precision_stderr": 0.0019568292320360082, "rougeLsum_recall": 0.38977835292938257, "rougeLsum_recall_stderr": 0.002475205894007756}}, "3": {"generate_text_restaurant": {"bleu": 5.810474759979567, "bleu_stderr": 0.07579006844458654, "rouge1_fmeasure": 0.307699846077658, "rouge1_fmeasure_stderr": 0.0016836798456212607, "rouge1_precision": 0.24309828934304148, "rouge1_precision_stderr": 0.0019005898753670413, "rouge1_recall": 0.4670566019113305, "rouge1_recall_stderr": 0.0023932775436402193, "rouge2_fmeasure": 0.12918070346005242, "rouge2_fmeasure_stderr": 0.0011654611122014701, "rouge2_precision": 0.10168781845908033, "rouge2_precision_stderr": 0.0011883824391395869, "rouge2_recall": 0.20209647607764591, "rouge2_recall_stderr": 0.0019104221912810875, "rougeL_fmeasure": 0.23605748656654202, "rougeL_fmeasure_stderr": 0.0012419184728918431, "rougeL_precision": 0.18580091003866794, "rougeL_precision_stderr": 0.0014382176327432795, "rougeL_recall": 0.36221484092783923, "rougeL_recall_stderr": 0.0020685753646924234, "rougeLsum_fmeasure": 0.25979950139324387, "rougeLsum_fmeasure_stderr": 0.0016108185985968808, "rougeLsum_precision": 0.20525158463645873, "rougeLsum_precision_stderr": 0.0017314120087883877, "rougeLsum_recall": 0.3947742486081849, "rougeLsum_recall_stderr": 0.002360306367469496}}, "4": {"generate_text_restaurant": {"bleu": 5.856583823504068, "bleu_stderr": 0.08590752222075627, "rouge1_fmeasure": 0.3072297336966097, "rouge1_fmeasure_stderr": 0.001677600068476274, "rouge1_precision": 0.24083912701088211, "rouge1_precision_stderr": 0.001891795976143307, "rouge1_recall": 0.46987502312106944, "rouge1_recall_stderr": 0.002373970795855411, "rouge2_fmeasure": 0.13013649575708963, "rouge2_fmeasure_stderr": 0.0011872264816164021, "rouge2_precision": 0.10194079575537923, "rouge2_precision_stderr": 0.0012738284927660533, "rouge2_recall": 0.20486607531207773, "rouge2_recall_stderr": 0.0019180923641256352, "rougeL_fmeasure": 0.23535954148408947, "rougeL_fmeasure_stderr": 0.001235256889547661, "rougeL_precision": 0.18407870093260886, "rougeL_precision_stderr": 0.00147269880081677, "rougeL_recall": 0.3634519313727439, "rougeL_recall_stderr": 0.0020191238189298604, "rougeLsum_fmeasure": 0.2592529609283163, "rougeLsum_fmeasure_stderr": 0.0015947975783409823, "rougeLsum_precision": 0.20324551641227329, "rougeLsum_precision_stderr": 0.001730862935580683, "rougeLsum_recall": 0.3970250584377568, "rougeLsum_recall_stderr": 0.00232405668117713}}, "5": {"generate_text_restaurant": {"bleu": 5.701988223904371, "bleu_stderr": 0.05974327947875344, "rouge1_fmeasure": 0.30342180002404195, "rouge1_fmeasure_stderr": 0.0016429215832907001, "rouge1_precision": 0.2357192890434931, "rouge1_precision_stderr": 0.0017709653279963382, "rouge1_recall": 0.46793875744209246, "rouge1_recall_stderr": 0.0023377619498614883, "rouge2_fmeasure": 0.12711050572770574, "rouge2_fmeasure_stderr": 0.001182240229485702, "rouge2_precision": 0.09834833044152837, "rouge2_precision_stderr": 0.0011541319656096648, "rouge2_recall": 0.2017968785574919, "rouge2_recall_stderr": 0.001929650748227801, "rougeL_fmeasure": 0.2315222472386274, "rougeL_fmeasure_stderr": 0.0011861982598106887, "rougeL_precision": 0.17902630726475285, "rougeL_precision_stderr": 0.0012897932939114531, "rougeL_recall": 0.36086666712927185, "rougeL_recall_stderr": 0.0019704166593789243, "rougeLsum_fmeasure": 0.256915761431013, "rougeLsum_fmeasure_stderr": 0.0015851952901884037, "rougeLsum_precision": 0.19964816084000173, "rougeLsum_precision_stderr": 0.0016311639902271977, "rougeLsum_recall": 0.39633205907689883, "rougeLsum_recall_stderr": 0.0022975718064400996}}}, "gem_xsum": {"0": {"article_DOC_summary": {"bleu": 1.7324193654708817, "bleu_stderr": 0.13416126334094292, "rouge1_fmeasure": 0.2085969207130687, "rouge1_fmeasure_stderr": 0.002677475599144402, "rouge1_precision": 0.1655773024489004, "rouge1_precision_stderr": 0.0028576845139351987, "rouge1_recall": 0.32851562505932314, "rouge1_recall_stderr": 0.0039803284921081, "rouge2_fmeasure": 0.044656791266145565, "rouge2_fmeasure_stderr": 0.0016785808050176795, "rouge2_precision": 0.036089021388490294, "rouge2_precision_stderr": 0.0015969906559037688, "rouge2_recall": 0.07051409622481412, "rouge2_recall_stderr": 0.0025672161932226503, "rougeL_fmeasure": 0.15500054113220843, "rougeL_fmeasure_stderr": 0.002069637277533473, "rougeL_precision": 0.12315934281916667, "rougeL_precision_stderr": 0.0022342850887312926, "rougeL_recall": 0.2450990337124764, "rougeL_recall_stderr": 0.0031721420821518784, "rougeLsum_fmeasure": 0.1648368106728737, "rougeLsum_fmeasure_stderr": 0.0021862489460295126, "rougeLsum_precision": 0.130324877139233, "rougeLsum_precision_stderr": 0.002282842578765438, "rougeLsum_recall": 0.2618161404002937, "rougeLsum_recall_stderr": 0.0034400702646342324}}, "1": {"article_DOC_summary": {"bleu": 0.9718103240280566, "bleu_stderr": 0.0618162240060556, "rouge1_fmeasure": 0.16538496371657396, "rouge1_fmeasure_stderr": 0.0022823923941345326, "rouge1_precision": 0.11802826309532148, "rouge1_precision_stderr": 0.001749157965306058, "rouge1_recall": 0.2892400892348949, "rouge1_recall_stderr": 0.003843967130143464, "rouge2_fmeasure": 0.025192202332776397, "rouge2_fmeasure_stderr": 0.0011296247751961938, "rouge2_precision": 0.017821354334989277, "rouge2_precision_stderr": 0.0008141612570301904, "rouge2_recall": 0.04545518558443322, "rouge2_recall_stderr": 0.00206477086181511, "rougeL_fmeasure": 0.12421960300726272, "rougeL_fmeasure_stderr": 0.0016143054069980196, "rougeL_precision": 0.08829393492717166, "rougeL_precision_stderr": 0.0011978449597419942, "rougeL_recall": 0.219464699636153, "rougeL_recall_stderr": 0.0029458921049705118, "rougeLsum_fmeasure": 0.13238865606315464, "rougeLsum_fmeasure_stderr": 0.0017891980246226586, "rougeLsum_precision": 0.09409421229331506, "rougeLsum_precision_stderr": 0.0013239443870656413, "rougeLsum_recall": 0.23385506502219394, "rougeLsum_recall_stderr": 0.00324955152033377}}, "2": {"article_DOC_summary": {"bleu": 0.8276490187392188, "bleu_stderr": 0.06507121832672531, "rouge1_fmeasure": 0.15944247539707976, "rouge1_fmeasure_stderr": 0.002076895889562475, "rouge1_precision": 0.11300176611968675, "rouge1_precision_stderr": 0.0015556940763036152, "rouge1_recall": 0.28221717850396943, "rouge1_recall_stderr": 0.003575100110282272, "rouge2_fmeasure": 0.023271326997139498, "rouge2_fmeasure_stderr": 0.000998854505955608, "rouge2_precision": 0.016338317353700334, "rouge2_precision_stderr": 0.0007066281144508859, "rouge2_recall": 0.04249427144713084, "rouge2_recall_stderr": 0.0018743700982079647, "rougeL_fmeasure": 0.12070835773462767, "rougeL_fmeasure_stderr": 0.0015063108121480115, "rougeL_precision": 0.08541393540574391, "rougeL_precision_stderr": 0.0011196684087793841, "rougeL_recall": 0.21475231259583918, "rougeL_recall_stderr": 0.0027096441989616395, "rougeLsum_fmeasure": 0.12867240195403112, "rougeLsum_fmeasure_stderr": 0.0016705058332119036, "rougeLsum_precision": 0.0910255058370105, "rougeLsum_precision_stderr": 0.0012384505621305965, "rougeLsum_recall": 0.22901792345741215, "rougeLsum_recall_stderr": 0.0029934117569162446}}, "3": {"article_DOC_summary": {"bleu": 0.7275997003420623, "bleu_stderr": 0.0714354424073514, "rouge1_fmeasure": 0.15238579729436347, "rouge1_fmeasure_stderr": 0.002219643304647064, "rouge1_precision": 0.11018963016474236, "rouge1_precision_stderr": 0.0017609312368803887, "rouge1_recall": 0.26507326260117575, "rouge1_recall_stderr": 0.003880711394203358, "rouge2_fmeasure": 0.021062414069558447, "rouge2_fmeasure_stderr": 0.0009593758217756945, "rouge2_precision": 0.015117606651088168, "rouge2_precision_stderr": 0.0006986418363838183, "rouge2_recall": 0.03773286266192692, "rouge2_recall_stderr": 0.0018152164946043806, "rougeL_fmeasure": 0.11522763416460359, "rougeL_fmeasure_stderr": 0.001618702230193589, "rougeL_precision": 0.08310804850408599, "rougeL_precision_stderr": 0.0012711620194565188, "rougeL_recall": 0.20191066209656278, "rougeL_recall_stderr": 0.0029597555352106446, "rougeLsum_fmeasure": 0.12244041168535194, "rougeLsum_fmeasure_stderr": 0.0017541862256624464, "rougeLsum_precision": 0.08833010081790499, "rougeLsum_precision_stderr": 0.0013694697105856542, "rougeLsum_recall": 0.2141478181293177, "rougeLsum_recall_stderr": 0.0031699460893052926}}, "4": {"article_DOC_summary": {"bleu": 0.4439583603615215, "bleu_stderr": 0.08948187684408024, "rouge1_fmeasure": 0.04307117627455316, "rouge1_fmeasure_stderr": 0.0023598454976796876, "rouge1_precision": 0.03624855696288989, "rouge1_precision_stderr": 0.002154806718675479, "rouge1_recall": 0.0682882112226377, "rouge1_recall_stderr": 0.0038546915936573645, "rouge2_fmeasure": 0.006190654035790546, "rouge2_fmeasure_stderr": 0.0006616893079956838, "rouge2_precision": 0.004753927251604713, "rouge2_precision_stderr": 0.0005422823928753415, "rouge2_recall": 0.0106246331727171, "rouge2_recall_stderr": 0.0011981010783161145, "rougeL_fmeasure": 0.03276313985133739, "rougeL_fmeasure_stderr": 0.0017948172115691448, "rougeL_precision": 0.028106320699876345, "rougeL_precision_stderr": 0.0017520100851387333, "rougeL_recall": 0.052034316243931046, "rougeL_recall_stderr": 0.0029666651577281325, "rougeLsum_fmeasure": 0.035056311907356266, "rougeLsum_fmeasure_stderr": 0.0019249998841907874, "rougeLsum_precision": 0.029946826835674154, "rougeLsum_precision_stderr": 0.0018494008939282194, "rougeLsum_recall": 0.055803585868478424, "rougeLsum_recall_stderr": 0.0031909204737398653}}, "5": {"article_DOC_summary": {"bleu": 2.65655135116426e-20, "bleu_stderr": 4.792898103586736e-16, "rouge1_fmeasure": 0.0022522566068641243, "rouge1_fmeasure_stderr": 0.0006246092526882687, "rouge1_precision": 0.002088044689590363, "rouge1_precision_stderr": 0.0006378388401635087, "rouge1_recall": 0.003108954066790554, "rouge1_recall_stderr": 0.0008691530961624927, "rouge2_fmeasure": 0.0003835367082818429, "rouge2_fmeasure_stderr": 0.0001988715771533667, "rouge2_precision": 0.0003787409297378254, "rouge2_precision_stderr": 0.00021259653675635183, "rouge2_recall": 0.0005089643061341174, "rouge2_recall_stderr": 0.00023434661614044327, "rougeL_fmeasure": 0.001729950940438837, "rougeL_fmeasure_stderr": 0.0004682531759199556, "rougeL_precision": 0.00159544525172581, "rougeL_precision_stderr": 0.0004634439016633172, "rougeL_recall": 0.0024010246985727165, "rougeL_recall_stderr": 0.0006703355161678125, "rougeLsum_fmeasure": 0.001846364966167502, "rougeLsum_fmeasure_stderr": 0.0004949667296463943, "rougeLsum_precision": 0.0016789411481352083, "rougeLsum_precision_stderr": 0.00047783261972336987, "rougeLsum_recall": 0.002599073871515686, "rougeLsum_recall_stderr": 0.0007224347751525072}}}}