{"GEM/web_nlg_en": {"0": {"PALM_prompt": {"bleu": 0.35460578896365613, "bleu_stderr": 0.04127239985505294, "rouge1_fmeasure": 0.11046047475367161, "rouge1_fmeasure_stderr": 0.0022175469970283947, "rouge1_precision": 0.07598634034268477, "rouge1_precision_stderr": 0.0020593257538953696, "rouge1_recall": 0.30331494602005443, "rouge1_recall_stderr": 0.005045821872290179, "rouge2_fmeasure": 0.052467944710660325, "rouge2_fmeasure_stderr": 0.0013579106932935785, "rouge2_precision": 0.03614080750642198, "rouge2_precision_stderr": 0.0013003604067484368, "rouge2_recall": 0.14679475394818947, "rouge2_recall_stderr": 0.0033169349191795395, "rougeL_fmeasure": 0.10587025011107204, "rougeL_fmeasure_stderr": 0.002057999260024394, "rougeL_precision": 0.07261501210208798, "rougeL_precision_stderr": 0.001929042340123457, "rougeL_recall": 0.29378141049090273, "rougeL_recall_stderr": 0.004903476880957363, "rougeLsum_fmeasure": 0.10544926366442316, "rougeLsum_fmeasure_stderr": 0.0020870180908242673, "rougeLsum_precision": 0.07253602455249049, "rougeLsum_precision_stderr": 0.001960212317107411, "rougeLsum_recall": 0.28972075705368405, "rougeLsum_recall_stderr": 0.004765941005197029}}, "1": {"PALM_prompt": {"bleu": 0.43000649556861953, "bleu_stderr": 0.03769296256723733, "rouge1_fmeasure": 0.11423577207775937, "rouge1_fmeasure_stderr": 0.0019694511711788217, "rouge1_precision": 0.07449267528933835, "rouge1_precision_stderr": 0.0015591243035150693, "rouge1_recall": 0.3570734232135794, "rouge1_recall_stderr": 0.005049147159370153, "rouge2_fmeasure": 0.05269993626863907, "rouge2_fmeasure_stderr": 0.0012130143492016113, "rouge2_precision": 0.03447632020892676, "rouge2_precision_stderr": 0.0009515126663085263, "rouge2_recall": 0.16931911049070325, "rouge2_recall_stderr": 0.0034730603938979677, "rougeL_fmeasure": 0.10772696325239679, "rougeL_fmeasure_stderr": 0.0018050301374967716, "rougeL_precision": 0.07024660297627622, "rougeL_precision_stderr": 0.0014320687118875425, "rougeL_recall": 0.33400063927103313, "rougeL_recall_stderr": 0.004557935006444777, "rougeLsum_fmeasure": 0.10853509777552768, "rougeLsum_fmeasure_stderr": 0.001862736778219524, "rougeLsum_precision": 0.07087429190816584, "rougeLsum_precision_stderr": 0.0014847845278820806, "rougeLsum_recall": 0.33807210476530836, "rougeLsum_recall_stderr": 0.004700621881301265}}, "2": {"PALM_prompt": {"bleu": 0.46635237695480414, "bleu_stderr": 0.036668809623062, "rouge1_fmeasure": 0.11557506829814276, "rouge1_fmeasure_stderr": 0.001924033280192195, "rouge1_precision": 0.07418652948466994, "rouge1_precision_stderr": 0.0014193439744244487, "rouge1_recall": 0.36556492135686, "rouge1_recall_stderr": 0.0050312007549606534, "rouge2_fmeasure": 0.05310933897261573, "rouge2_fmeasure_stderr": 0.0011935945329990892, "rouge2_precision": 0.033828374294314886, "rouge2_precision_stderr": 0.0008631483412359538, "rouge2_recall": 0.1755206924620156, "rouge2_recall_stderr": 0.0035430702160321806, "rougeL_fmeasure": 0.10811633325240383, "rougeL_fmeasure_stderr": 0.0017651025504977517, "rougeL_precision": 0.06937350612818097, "rougeL_precision_stderr": 0.001298396116933123, "rougeL_recall": 0.3401896184445853, "rougeL_recall_stderr": 0.004572939700685839, "rougeLsum_fmeasure": 0.10996153625412339, "rougeLsum_fmeasure_stderr": 0.001828648876946442, "rougeLsum_precision": 0.07060788755354988, "rougeLsum_precision_stderr": 0.0013492078636814708, "rougeLsum_recall": 0.3466944175988772, "rougeLsum_recall_stderr": 0.004718601773324721}}, "3": {"PALM_prompt": {"bleu": 0.5318880573063225, "bleu_stderr": 0.03077006985866061, "rouge1_fmeasure": 0.1187681526614185, "rouge1_fmeasure_stderr": 0.0018389245831829989, "rouge1_precision": 0.07572199540644148, "rouge1_precision_stderr": 0.0013725787893078976, "rouge1_recall": 0.386186194255226, "rouge1_recall_stderr": 0.0050631478485505975, "rouge2_fmeasure": 0.0545990877071863, "rouge2_fmeasure_stderr": 0.0011418202566802825, "rouge2_precision": 0.034691337373678494, "rouge2_precision_stderr": 0.0008101010333279721, "rouge2_recall": 0.18672789069562837, "rouge2_recall_stderr": 0.0036362158555646932, "rougeL_fmeasure": 0.11094586486203455, "rougeL_fmeasure_stderr": 0.0016863362576384658, "rougeL_precision": 0.07075495815573636, "rougeL_precision_stderr": 0.0012595872580060065, "rougeL_recall": 0.35859989642125883, "rougeL_recall_stderr": 0.00457458234745712, "rougeLsum_fmeasure": 0.11279487606503577, "rougeLsum_fmeasure_stderr": 0.001740345273722019, "rougeLsum_precision": 0.07195645133988224, "rougeLsum_precision_stderr": 0.0013011441014847468, "rougeLsum_recall": 0.3655473787152986, "rougeLsum_recall_stderr": 0.004697139221840445}}, "4": {"PALM_prompt": {"bleu": 0.5501744822594039, "bleu_stderr": 0.03409130654156849, "rouge1_fmeasure": 0.12205117106283064, "rouge1_fmeasure_stderr": 0.0018267167297263492, "rouge1_precision": 0.0773953741957407, "rouge1_precision_stderr": 0.0013204324907578587, "rouge1_recall": 0.39710159332805806, "rouge1_recall_stderr": 0.00504803274078318, "rouge2_fmeasure": 0.05673629789733436, "rouge2_fmeasure_stderr": 0.001131466888576198, "rouge2_precision": 0.03574892990415424, "rouge2_precision_stderr": 0.0007844605741780433, "rouge2_recall": 0.1966788736461859, "rouge2_recall_stderr": 0.003719036109492947, "rougeL_fmeasure": 0.11359102901387463, "rougeL_fmeasure_stderr": 0.0016628480882232698, "rougeL_precision": 0.07208379137252659, "rougeL_precision_stderr": 0.0012045521412790883, "rougeL_recall": 0.3679102688951241, "rougeL_recall_stderr": 0.004541973385497078, "rougeLsum_fmeasure": 0.1156616432799891, "rougeLsum_fmeasure_stderr": 0.0017252677961420559, "rougeLsum_precision": 0.07340824717593364, "rougeLsum_precision_stderr": 0.0012507702589347408, "rougeLsum_recall": 0.3754732283837251, "rougeLsum_recall_stderr": 0.004681001943001544}}, "5": {"PALM_prompt": {"bleu": 0.6069653948528808, "bleu_stderr": 0.022478797894781258, "rouge1_fmeasure": 0.12361532318566361, "rouge1_fmeasure_stderr": 0.0018017937208595991, "rouge1_precision": 0.07833603783865227, "rouge1_precision_stderr": 0.001352405348891179, "rouge1_recall": 0.41502730709431096, "rouge1_recall_stderr": 0.005094647215628354, "rouge2_fmeasure": 0.05716985509173004, "rouge2_fmeasure_stderr": 0.0011074288762205806, "rouge2_precision": 0.03600950877265579, "rouge2_precision_stderr": 0.0007884596657334906, "rouge2_recall": 0.20573962541606136, "rouge2_recall_stderr": 0.0037497370778539845, "rougeL_fmeasure": 0.11344042224284119, "rougeL_fmeasure_stderr": 0.0016155314972144464, "rougeL_precision": 0.07196876600610892, "rougeL_precision_stderr": 0.001224924971314539, "rougeL_recall": 0.37833069025228927, "rougeL_recall_stderr": 0.004495187818982786, "rougeLsum_fmeasure": 0.1168897795571233, "rougeLsum_fmeasure_stderr": 0.0017011725978752143, "rougeLsum_precision": 0.07417079754442318, "rougeLsum_precision_stderr": 0.0012856883253605687, "rougeLsum_recall": 0.39062928440269434, "rougeLsum_recall_stderr": 0.004704501383036899}}}, "GEM/wiki_lingua_en": {"0": {"tldr_en": {"bleu": 1.390853464486237, "bleu_stderr": 0.059853799172008365, "rouge1_fmeasure": 0.16517157703306565, "rouge1_fmeasure_stderr": 0.0018149558416127082, "rouge1_precision": 0.1430757560611486, "rouge1_precision_stderr": 0.0018512962398626901, "rouge1_recall": 0.23637136153102328, "rouge1_recall_stderr": 0.0025951414839324363, "rouge2_fmeasure": 0.03144881649306534, "rouge2_fmeasure_stderr": 0.0007949045821369007, "rouge2_precision": 0.027253137929797694, "rouge2_precision_stderr": 0.0007565671384632661, "rouge2_recall": 0.046319655637173676, "rouge2_recall_stderr": 0.0013027510329844502, "rougeL_fmeasure": 0.12939552425065465, "rougeL_fmeasure_stderr": 0.0013070901034852402, "rougeL_precision": 0.11076533487865345, "rougeL_precision_stderr": 0.0013126275934646958, "rougeL_recall": 0.18971611018232362, "rougeL_recall_stderr": 0.0020959074049994044, "rougeLsum_fmeasure": 0.151441460006642, "rougeLsum_fmeasure_stderr": 0.0016465261311395824, "rougeLsum_precision": 0.13092618224064537, "rougeLsum_precision_stderr": 0.0016810775282002177, "rougeLsum_recall": 0.21779579893664588, "rougeLsum_recall_stderr": 0.0023948902348789936}}, "1": {"tldr_en": {"bleu": 2.3020814552441036, "bleu_stderr": 0.07124494518745983, "rouge1_fmeasure": 0.20774908941497858, "rouge1_fmeasure_stderr": 0.0019527184699241, "rouge1_precision": 0.17852734604158793, "rouge1_precision_stderr": 0.0020710995740373522, "rouge1_recall": 0.30264596885910944, "rouge1_recall_stderr": 0.00291873292100196, "rouge2_fmeasure": 0.04792367232693977, "rouge2_fmeasure_stderr": 0.000971523171352038, "rouge2_precision": 0.04099710309933377, "rouge2_precision_stderr": 0.000910818770381285, "rouge2_recall": 0.07279917781718397, "rouge2_recall_stderr": 0.0016547259631172991, "rougeL_fmeasure": 0.14759799820832575, "rougeL_fmeasure_stderr": 0.0012896913962158606, "rougeL_precision": 0.12547942347426674, "rougeL_precision_stderr": 0.0013525118104691794, "rougeL_recall": 0.22057999445178014, "rougeL_recall_stderr": 0.0022414540337101223, "rougeLsum_fmeasure": 0.19350686245390553, "rougeLsum_fmeasure_stderr": 0.001814216671457794, "rougeLsum_precision": 0.16603857159214477, "rougeLsum_precision_stderr": 0.001918454683011944, "rougeLsum_recall": 0.2826463785548646, "rougeLsum_recall_stderr": 0.0027435570236691792}}, "2": {"tldr_en": {"bleu": 2.56061946074879, "bleu_stderr": 0.08875901983481134, "rouge1_fmeasure": 0.21298028389245655, "rouge1_fmeasure_stderr": 0.0018566335384653636, "rouge1_precision": 0.1832669676031301, "rouge1_precision_stderr": 0.0020160001989551132, "rouge1_recall": 0.31044482930358086, "rouge1_recall_stderr": 0.002782637370104287, "rouge2_fmeasure": 0.05111590452574008, "rouge2_fmeasure_stderr": 0.000984436891043789, "rouge2_precision": 0.04359936792401392, "rouge2_precision_stderr": 0.0009012688991148481, "rouge2_recall": 0.07746108584334276, "rouge2_recall_stderr": 0.0016970078202864917, "rougeL_fmeasure": 0.1515450545072009, "rougeL_fmeasure_stderr": 0.0012442172141465177, "rougeL_precision": 0.1290928592055247, "rougeL_precision_stderr": 0.0013251005584623103, "rougeL_recall": 0.2265125598092535, "rougeL_recall_stderr": 0.0022015069669254045, "rougeLsum_fmeasure": 0.1997192575381439, "rougeLsum_fmeasure_stderr": 0.0017345981527878763, "rougeLsum_precision": 0.17157223010778608, "rougeLsum_precision_stderr": 0.0018727495126747784, "rougeLsum_recall": 0.29190060671500806, "rougeLsum_recall_stderr": 0.0026378499445263008}}, "3": {"tldr_en": {"bleu": 2.4567620772859544, "bleu_stderr": 0.07804801426146958, "rouge1_fmeasure": 0.1734250515140521, "rouge1_fmeasure_stderr": 0.0021585230764058403, "rouge1_precision": 0.15365556799869134, "rouge1_precision_stderr": 0.0022375644528785585, "rouge1_recall": 0.2520250438413879, "rouge1_recall_stderr": 0.003280462869976282, "rouge2_fmeasure": 0.04046018099620164, "rouge2_fmeasure_stderr": 0.0009368491430766626, "rouge2_precision": 0.035304417807292626, "rouge2_precision_stderr": 0.0008933122056836016, "rouge2_recall": 0.06145996914352228, "rouge2_recall_stderr": 0.0015943752876392376, "rougeL_fmeasure": 0.12482706202216799, "rougeL_fmeasure_stderr": 0.0015071076159934608, "rougeL_precision": 0.11014823619866325, "rougeL_precision_stderr": 0.0015873396520271518, "rougeL_recall": 0.1857322798596749, "rougeL_recall_stderr": 0.002553313928784032, "rougeLsum_fmeasure": 0.16261984079091396, "rougeLsum_fmeasure_stderr": 0.00201669945503749, "rougeLsum_precision": 0.14400230894616803, "rougeLsum_precision_stderr": 0.002097114189887866, "rougeLsum_recall": 0.23691973770859226, "rougeLsum_recall_stderr": 0.003108576444854855}}, "4": {"tldr_en": {"bleu": 0.5686192864139299, "bleu_stderr": 0.05329872239897294, "rouge1_fmeasure": 0.05514449811895782, "rouge1_fmeasure_stderr": 0.0018661361529205558, "rouge1_precision": 0.050446112431908365, "rouge1_precision_stderr": 0.0018621346986588624, "rouge1_recall": 0.08296121662582322, "rouge1_recall_stderr": 0.0028815435632905994, "rouge2_fmeasure": 0.012506081428575835, "rouge2_fmeasure_stderr": 0.000617828942630335, "rouge2_precision": 0.010827044508083692, "rouge2_precision_stderr": 0.000584691320512827, "rouge2_recall": 0.019907513701632813, "rouge2_recall_stderr": 0.0010930514612001662, "rougeL_fmeasure": 0.04114530708158443, "rougeL_fmeasure_stderr": 0.0013718968214232637, "rougeL_precision": 0.0378964094729927, "rougeL_precision_stderr": 0.001419123037289574, "rougeL_recall": 0.06320549575577322, "rougeL_recall_stderr": 0.0022530025801340424, "rougeLsum_fmeasure": 0.05161513337559881, "rougeLsum_fmeasure_stderr": 0.0017417092171012594, "rougeLsum_precision": 0.047261454636276935, "rougeLsum_precision_stderr": 0.001749098938810562, "rougeLsum_recall": 0.07790933996710452, "rougeLsum_recall_stderr": 0.0027202426274044768}}, "5": {"tldr_en": {"bleu": 1.4978632294934352e-06, "bleu_stderr": 2.8426588022690166e-06, "rouge1_fmeasure": 0.008723812047284148, "rouge1_fmeasure_stderr": 0.0008193557654359252, "rouge1_precision": 0.00816218714291048, "rouge1_precision_stderr": 0.0008225175706365002, "rouge1_recall": 0.013376777535733507, "rouge1_recall_stderr": 0.0012945755094527528, "rouge2_fmeasure": 0.001834359089625422, "rouge2_fmeasure_stderr": 0.00023179541880762196, "rouge2_precision": 0.0016392883778666894, "rouge2_precision_stderr": 0.00022497812116211926, "rouge2_recall": 0.0030504312623576067, "rouge2_recall_stderr": 0.0004174116396029455, "rougeL_fmeasure": 0.00647027468483912, "rougeL_fmeasure_stderr": 0.0005992276725051343, "rougeL_precision": 0.006061858268899674, "rougeL_precision_stderr": 0.000608364835519215, "rougeL_recall": 0.01021577852815356, "rougeL_recall_stderr": 0.0010105057014620934, "rougeLsum_fmeasure": 0.00812179216223168, "rougeLsum_fmeasure_stderr": 0.0007615460927384592, "rougeLsum_precision": 0.007575733113414468, "rougeLsum_precision_stderr": 0.0007607557971305472, "rougeLsum_recall": 0.012573851281871638, "rougeLsum_recall_stderr": 0.001225769033813259}}}, "e2e_nlg_cleaned": {"0": {"generate_text_restaurant": {"bleu": 0.5430652885343026, "bleu_stderr": 0.022082484632507872, "rouge1_fmeasure": 0.07741361857983127, "rouge1_fmeasure_stderr": 0.001132924636873198, "rouge1_precision": 0.058690510706937433, "rouge1_precision_stderr": 0.0009708303148239041, "rouge1_recall": 0.12537197958835283, "rouge1_recall_stderr": 0.0018746074102243583, "rouge2_fmeasure": 0.008169134941790867, "rouge2_fmeasure_stderr": 0.00047672897974732135, "rouge2_precision": 0.006081743671322657, "rouge2_precision_stderr": 0.0003657111764040069, "rouge2_recall": 0.013546950620169113, "rouge2_recall_stderr": 0.0007812479279203251, "rougeL_fmeasure": 0.07639604693417318, "rougeL_fmeasure_stderr": 0.0010809118409461501, "rougeL_precision": 0.057686950703333045, "rougeL_precision_stderr": 0.0008896823845173719, "rougeL_recall": 0.12403635392847258, "rougeL_recall_stderr": 0.0018233766742210078, "rougeLsum_fmeasure": 0.06358108342639292, "rougeLsum_fmeasure_stderr": 0.0009407364363846421, "rougeLsum_precision": 0.04821257551275573, "rougeLsum_precision_stderr": 0.000810755418294155, "rougeLsum_recall": 0.10309655754134595, "rougeLsum_recall_stderr": 0.0015536256465239371}}, "1": {"generate_text_restaurant": {"bleu": 9.021355379582062, "bleu_stderr": 0.10623953202209324, "rouge1_fmeasure": 0.4055777436674024, "rouge1_fmeasure_stderr": 0.0020513543480466046, "rouge1_precision": 0.40793804080711205, "rouge1_precision_stderr": 0.0025241462455489836, "rouge1_recall": 0.4447838396302669, "rouge1_recall_stderr": 0.002843720569909992, "rouge2_fmeasure": 0.1723284719323317, "rouge2_fmeasure_stderr": 0.0017077073940088953, "rouge2_precision": 0.17321636216395442, "rouge2_precision_stderr": 0.0018751370046392074, "rouge2_recall": 0.19070657240665465, "rouge2_recall_stderr": 0.0020935532982887437, "rougeL_fmeasure": 0.2881503807490911, "rougeL_fmeasure_stderr": 0.0016750738518425616, "rougeL_precision": 0.2902723436144399, "rougeL_precision_stderr": 0.0020485949228574835, "rougeL_recall": 0.3170307319809301, "rougeL_recall_stderr": 0.0022979256302620267, "rougeLsum_fmeasure": 0.33767965579292886, "rougeLsum_fmeasure_stderr": 0.0019918613599406863, "rougeLsum_precision": 0.3398038056283089, "rougeLsum_precision_stderr": 0.0023494605618611625, "rougeLsum_recall": 0.37004877183005896, "rougeLsum_recall_stderr": 0.0026282083685719676}}, "2": {"generate_text_restaurant": {"bleu": 10.113940674814147, "bleu_stderr": 0.14158653466380353, "rouge1_fmeasure": 0.4192695997412943, "rouge1_fmeasure_stderr": 0.001956593030198661, "rouge1_precision": 0.42169201018178765, "rouge1_precision_stderr": 0.0024591821051573844, "rouge1_recall": 0.4553757907208419, "rouge1_recall_stderr": 0.002762586151947058, "rouge2_fmeasure": 0.1877463274388085, "rouge2_fmeasure_stderr": 0.0017292126115718328, "rouge2_precision": 0.18860533474575017, "rouge2_precision_stderr": 0.0019093113876152922, "rouge2_recall": 0.20618277051281303, "rouge2_recall_stderr": 0.002147489885830656, "rougeL_fmeasure": 0.3031593987471526, "rougeL_fmeasure_stderr": 0.0017185441047347237, "rougeL_precision": 0.3049199738981857, "rougeL_precision_stderr": 0.002060649727261783, "rougeL_recall": 0.3301213216090321, "rougeL_recall_stderr": 0.0023449418849790346, "rougeLsum_fmeasure": 0.34937362258056176, "rougeLsum_fmeasure_stderr": 0.0019377724085507641, "rougeLsum_precision": 0.3508806465899511, "rougeLsum_precision_stderr": 0.0022749935402855376, "rougeLsum_recall": 0.37984919905452064, "rougeLsum_recall_stderr": 0.002603638405911715}}, "3": {"generate_text_restaurant": {"bleu": 10.8201389431134, "bleu_stderr": 0.14308976771282733, "rouge1_fmeasure": 0.42425148245558203, "rouge1_fmeasure_stderr": 0.001970717028195558, "rouge1_precision": 0.4270119331576845, "rouge1_precision_stderr": 0.0024841694273249355, "rouge1_recall": 0.4595201825615637, "rouge1_recall_stderr": 0.0027434642248067836, "rouge2_fmeasure": 0.1965472622348377, "rouge2_fmeasure_stderr": 0.0017674561951196886, "rouge2_precision": 0.1980135179853101, "rouge2_precision_stderr": 0.001958609184896891, "rouge2_recall": 0.21515925688103615, "rouge2_recall_stderr": 0.0021936934119952973, "rougeL_fmeasure": 0.31077211552436274, "rougeL_fmeasure_stderr": 0.0017645823005779276, "rougeL_precision": 0.313027569485227, "rougeL_precision_stderr": 0.002150997784044619, "rougeL_recall": 0.33729693598184624, "rougeL_recall_stderr": 0.002349898786076012, "rougeLsum_fmeasure": 0.35667974526063834, "rougeLsum_fmeasure_stderr": 0.0019855982113182236, "rougeLsum_precision": 0.35862892839542776, "rougeLsum_precision_stderr": 0.0023574734411340495, "rougeLsum_recall": 0.3868880675862601, "rougeLsum_recall_stderr": 0.002629274635035275}}, "4": {"generate_text_restaurant": {"bleu": 10.748006102366846, "bleu_stderr": 0.20587131675493173, "rouge1_fmeasure": 0.4193816174833963, "rouge1_fmeasure_stderr": 0.0019534021605399406, "rouge1_precision": 0.4203153115235523, "rouge1_precision_stderr": 0.0025761947742893496, "rouge1_recall": 0.45817921600162986, "rouge1_recall_stderr": 0.0026979219990255587, "rouge2_fmeasure": 0.19496951545711436, "rouge2_fmeasure_stderr": 0.0017675695646951184, "rouge2_precision": 0.19569900813831625, "rouge2_precision_stderr": 0.0019749036772695933, "rouge2_recall": 0.21498311497796316, "rouge2_recall_stderr": 0.002187842079829162, "rougeL_fmeasure": 0.30944368265364386, "rougeL_fmeasure_stderr": 0.001760799097861244, "rougeL_precision": 0.3098963653292, "rougeL_precision_stderr": 0.002187376726727452, "rougeL_recall": 0.3392067881509787, "rougeL_recall_stderr": 0.002363806042112853, "rougeLsum_fmeasure": 0.35483471453855586, "rougeLsum_fmeasure_stderr": 0.0019769772638384736, "rougeLsum_precision": 0.3548498145433127, "rougeLsum_precision_stderr": 0.002404468701475204, "rougeLsum_recall": 0.3885822037053069, "rougeLsum_recall_stderr": 0.0026339915778194056}}, "5": {"generate_text_restaurant": {"bleu": 10.07029280392025, "bleu_stderr": 0.16820417246403815, "rouge1_fmeasure": 0.4120744202773343, "rouge1_fmeasure_stderr": 0.0019268013859534442, "rouge1_precision": 0.3997424443126998, "rouge1_precision_stderr": 0.002509076491945065, "rouge1_recall": 0.46532662291450666, "rouge1_recall_stderr": 0.00264363774082294, "rouge2_fmeasure": 0.19029346353882015, "rouge2_fmeasure_stderr": 0.0017688208079494707, "rouge2_precision": 0.18469396343654157, "rouge2_precision_stderr": 0.0019364037617764882, "rouge2_recall": 0.21700435263229634, "rouge2_recall_stderr": 0.002190664608271055, "rougeL_fmeasure": 0.30540353731105185, "rougeL_fmeasure_stderr": 0.0017767777362628493, "rougeL_precision": 0.2961306858200834, "rougeL_precision_stderr": 0.0021584129425405406, "rougeL_recall": 0.34594887959254145, "rougeL_recall_stderr": 0.002372231185418221, "rougeLsum_fmeasure": 0.35216926515870645, "rougeLsum_fmeasure_stderr": 0.001966241705609662, "rougeLsum_precision": 0.34111556606843185, "rougeLsum_precision_stderr": 0.0023637597564672504, "rougeLsum_recall": 0.39828555999095006, "rougeLsum_recall_stderr": 0.002611728081083023}}}, "gem_xsum": {"0": {"article_DOC_summary": {"bleu": 2.1262594378676067, "bleu_stderr": 0.095134222030361, "rouge1_fmeasure": 0.2146540097271338, "rouge1_fmeasure_stderr": 0.0026889142432873487, "rouge1_precision": 0.17140703214052655, "rouge1_precision_stderr": 0.002657385766704294, "rouge1_recall": 0.3328727910689603, "rouge1_recall_stderr": 0.004478215733101042, "rouge2_fmeasure": 0.049663336738937365, "rouge2_fmeasure_stderr": 0.0017642714115669107, "rouge2_precision": 0.03900330994819724, "rouge2_precision_stderr": 0.001528495657116988, "rouge2_recall": 0.08030726522172472, "rouge2_recall_stderr": 0.002887852065979978, "rougeL_fmeasure": 0.16038878419096453, "rougeL_fmeasure_stderr": 0.0021363642948066205, "rougeL_precision": 0.12794926942490142, "rougeL_precision_stderr": 0.0021041803528192753, "rougeL_recall": 0.24989761131083427, "rougeL_recall_stderr": 0.00358408703157254, "rougeLsum_fmeasure": 0.16814747869602256, "rougeLsum_fmeasure_stderr": 0.0022974302463237696, "rougeLsum_precision": 0.1335666168529187, "rougeLsum_precision_stderr": 0.0021728880500778438, "rougeLsum_recall": 0.2632275074866455, "rougeLsum_recall_stderr": 0.003953396990275494}}, "1": {"article_DOC_summary": {"bleu": 1.4483377477041561, "bleu_stderr": 0.0840030327291259, "rouge1_fmeasure": 0.1790918098017675, "rouge1_fmeasure_stderr": 0.0025132906259886117, "rouge1_precision": 0.12762495343099467, "rouge1_precision_stderr": 0.0018780124957160557, "rouge1_recall": 0.313413092533033, "rouge1_recall_stderr": 0.004306518419134443, "rouge2_fmeasure": 0.03655839749230803, "rouge2_fmeasure_stderr": 0.0014038700307555834, "rouge2_precision": 0.025830285615912763, "rouge2_precision_stderr": 0.0009915971356563732, "rouge2_recall": 0.06570288742608651, "rouge2_recall_stderr": 0.00264662461319788, "rougeL_fmeasure": 0.1388485940184289, "rougeL_fmeasure_stderr": 0.0018751083682789276, "rougeL_precision": 0.09873873361045128, "rougeL_precision_stderr": 0.0013888491496605799, "rougeL_recall": 0.2446195811573636, "rougeL_recall_stderr": 0.0033615248260746096, "rougeLsum_fmeasure": 0.14333789882498887, "rougeLsum_fmeasure_stderr": 0.002102831086991533, "rougeLsum_precision": 0.10194750437982684, "rougeLsum_precision_stderr": 0.0015522863811899836, "rougeLsum_recall": 0.252360107505834, "rougeLsum_recall_stderr": 0.0037266545345916377}}, "2": {"article_DOC_summary": {"bleu": 1.4098334620416249, "bleu_stderr": 0.10251781578887398, "rouge1_fmeasure": 0.18318008255527174, "rouge1_fmeasure_stderr": 0.0024878335268235297, "rouge1_precision": 0.13039220364032736, "rouge1_precision_stderr": 0.0018489941105405477, "rouge1_recall": 0.3208338991546151, "rouge1_recall_stderr": 0.004297695481110425, "rouge2_fmeasure": 0.037993467492829024, "rouge2_fmeasure_stderr": 0.0013560650853370311, "rouge2_precision": 0.026781308730490817, "rouge2_precision_stderr": 0.0009577167465939763, "rouge2_recall": 0.06824095591764738, "rouge2_recall_stderr": 0.0025179645513505435, "rougeL_fmeasure": 0.1433277343773715, "rougeL_fmeasure_stderr": 0.0018719617109376372, "rougeL_precision": 0.10184190144496406, "rougeL_precision_stderr": 0.001381528660279364, "rougeL_recall": 0.25250694238777793, "rougeL_recall_stderr": 0.003364599776037821, "rougeLsum_fmeasure": 0.1459671345211713, "rougeLsum_fmeasure_stderr": 0.002081513626929764, "rougeLsum_precision": 0.10364570773812086, "rougeLsum_precision_stderr": 0.0015257796013009766, "rougeLsum_recall": 0.25744273875109214, "rougeLsum_recall_stderr": 0.0037263830864618396}}, "3": {"article_DOC_summary": {"bleu": 1.7655055241804707, "bleu_stderr": 0.06477912123560818, "rouge1_fmeasure": 0.1823286909702188, "rouge1_fmeasure_stderr": 0.0027172739032140136, "rouge1_precision": 0.13260082146223712, "rouge1_precision_stderr": 0.0020837715361515315, "rouge1_recall": 0.31417364649267365, "rouge1_recall_stderr": 0.004766326484185003, "rouge2_fmeasure": 0.0418696855155091, "rouge2_fmeasure_stderr": 0.001561764077187165, "rouge2_precision": 0.029860167938620372, "rouge2_precision_stderr": 0.001119618909474985, "rouge2_recall": 0.0744234434951538, "rouge2_recall_stderr": 0.002838973765382053, "rougeL_fmeasure": 0.14378532654364076, "rougeL_fmeasure_stderr": 0.0020641586964029695, "rougeL_precision": 0.1044912013394587, "rougeL_precision_stderr": 0.0015885738089965284, "rougeL_recall": 0.24881332740973316, "rougeL_recall_stderr": 0.00370494003948016, "rougeLsum_fmeasure": 0.145758065422687, "rougeLsum_fmeasure_stderr": 0.0022897023386280607, "rougeLsum_precision": 0.10592669923558432, "rougeLsum_precision_stderr": 0.0017438522893054556, "rougeLsum_recall": 0.2524237548781368, "rougeLsum_recall_stderr": 0.004105527632225445}}, "4": {"article_DOC_summary": {"bleu": 0.7281725414747328, "bleu_stderr": 0.1260106543272375, "rouge1_fmeasure": 0.04910213359418778, "rouge1_fmeasure_stderr": 0.002744537374746729, "rouge1_precision": 0.041688643979342556, "rouge1_precision_stderr": 0.002601042149795104, "rouge1_recall": 0.07735095250848614, "rouge1_recall_stderr": 0.004456764254802236, "rouge2_fmeasure": 0.010389278018093686, "rouge2_fmeasure_stderr": 0.000885603435222816, "rouge2_precision": 0.007962003061308665, "rouge2_precision_stderr": 0.000712056980108108, "rouge2_recall": 0.01755275162918786, "rouge2_recall_stderr": 0.0015467145554586869, "rougeL_fmeasure": 0.03783956544850372, "rougeL_fmeasure_stderr": 0.0021016204447309272, "rougeL_precision": 0.03254096549229946, "rougeL_precision_stderr": 0.002113524713833357, "rougeL_recall": 0.05986377270001221, "rougeL_recall_stderr": 0.0034321169053043903, "rougeLsum_fmeasure": 0.039609121778678015, "rougeLsum_fmeasure_stderr": 0.0022308134808697523, "rougeLsum_precision": 0.0339927160449478, "rougeLsum_precision_stderr": 0.0022040533285906335, "rougeLsum_recall": 0.06260373695298717, "rougeLsum_recall_stderr": 0.003653558913424135}}, "5": {"article_DOC_summary": {"bleu": 1.2076944953786812e-38, "bleu_stderr": 9.41695631660932e-34, "rouge1_fmeasure": 0.002427323172932295, "rouge1_fmeasure_stderr": 0.0006885605705564534, "rouge1_precision": 0.0027081548968779534, "rouge1_precision_stderr": 0.000769629501128022, "rouge1_recall": 0.0022854665614044562, "rouge1_recall_stderr": 0.0006527724974423966, "rouge2_fmeasure": 0.00043206158301881207, "rouge2_fmeasure_stderr": 0.00019988234207854035, "rouge2_precision": 0.00048226606911401585, "rouge2_precision_stderr": 0.00021993176645429774, "rouge2_recall": 0.0003963716930303764, "rouge2_recall_stderr": 0.00018610435903420472, "rougeL_fmeasure": 0.001903925076413495, "rougeL_fmeasure_stderr": 0.0005355714845904816, "rougeL_precision": 0.002098042355577843, "rougeL_precision_stderr": 0.0005877770180975632, "rougeL_recall": 0.001821815264382321, "rougeL_recall_stderr": 0.000523325114699533, "rougeLsum_fmeasure": 0.001994261659228993, "rougeLsum_fmeasure_stderr": 0.0005516448655133461, "rougeLsum_precision": 0.0022069481248609703, "rougeLsum_precision_stderr": 0.0006101246103421121, "rougeLsum_recall": 0.0018999298389345458, "rougeLsum_recall_stderr": 0.0005353725566945594}}}}