| {"GEM/web_nlg_en": {"0": {"PALM_prompt": {"bleu": 0.2975989706476116, "bleu_stderr": 0.04003039263082336, "rouge1_fmeasure": 0.10454253577265941, "rouge1_fmeasure_stderr": 0.0020033273254233754, "rouge1_precision": 0.07036951453310922, "rouge1_precision_stderr": 0.001708454486390292, "rouge1_recall": 0.28391423378552716, "rouge1_recall_stderr": 0.004406605071545494, "rouge2_fmeasure": 0.04887042562262386, "rouge2_fmeasure_stderr": 0.0012367653733248375, "rouge2_precision": 0.03205700906292, "rouge2_precision_stderr": 0.0008904068747417852, "rouge2_recall": 0.1344860970658841, "rouge2_recall_stderr": 0.0029699527724654008, "rougeL_fmeasure": 0.09984712791182629, "rougeL_fmeasure_stderr": 0.001864385700385995, "rougeL_precision": 0.06700444340435573, "rougeL_precision_stderr": 0.001577635401560107, "rougeL_recall": 0.2723165283491304, "rougeL_recall_stderr": 0.00420334764816495, "rougeLsum_fmeasure": 0.09986723049046536, "rougeLsum_fmeasure_stderr": 0.0018921794146755414, "rougeLsum_precision": 0.06714085166592883, "rougeLsum_precision_stderr": 0.0016058922247288731, "rougeLsum_recall": 0.2710598887897389, "rougeLsum_recall_stderr": 0.004143182286682885}}, "1": {"PALM_prompt": {"bleu": 0.5399102183044338, "bleu_stderr": 0.017964459975753112, "rouge1_fmeasure": 0.1179994472699294, "rouge1_fmeasure_stderr": 0.001898574018978891, "rouge1_precision": 0.07582800253640251, "rouge1_precision_stderr": 0.0014775645988873703, "rouge1_recall": 0.3887660352664638, "rouge1_recall_stderr": 0.005510916338178581, "rouge2_fmeasure": 0.05575099241882265, "rouge2_fmeasure_stderr": 0.0011943826599908319, "rouge2_precision": 0.03547782475927522, "rouge2_precision_stderr": 0.000840851630406, "rouge2_recall": 0.19434244564750444, "rouge2_recall_stderr": 0.0039041652957777923, "rougeL_fmeasure": 0.10987367600038657, "rougeL_fmeasure_stderr": 0.0017019944711869266, "rougeL_precision": 0.07062905559753234, "rougeL_precision_stderr": 0.0013389008252074547, "rougeL_recall": 0.3594853678419995, "rougeL_recall_stderr": 0.004899885542632218, "rougeLsum_fmeasure": 0.11246764238131458, "rougeLsum_fmeasure_stderr": 0.001788765887772429, "rougeLsum_precision": 0.07235075590060619, "rougeLsum_precision_stderr": 0.0014035297849105085, "rougeLsum_recall": 0.36849778247126685, "rougeLsum_recall_stderr": 0.005075094016447408}}, "2": {"PALM_prompt": {"bleu": 0.6132285241911561, "bleu_stderr": 0.021744492816193794, "rouge1_fmeasure": 0.11750948362933708, "rouge1_fmeasure_stderr": 0.0017443663495669947, "rouge1_precision": 0.07454923688966983, "rouge1_precision_stderr": 0.0013402782053761812, "rouge1_recall": 0.4060696737056673, "rouge1_recall_stderr": 0.005408951548341353, "rouge2_fmeasure": 0.055072070164922673, "rouge2_fmeasure_stderr": 0.0011249794411084804, "rouge2_precision": 0.034783751809391424, "rouge2_precision_stderr": 0.0008624538099408842, "rouge2_recall": 0.20529500851088617, "rouge2_recall_stderr": 0.004029599291312284, "rougeL_fmeasure": 0.1081453556034095, "rougeL_fmeasure_stderr": 0.0015836947383010406, "rougeL_precision": 0.06870503701115688, "rougeL_precision_stderr": 0.001214108724498691, "rougeL_recall": 0.36958240896722416, "rougeL_recall_stderr": 0.004690608909122334, "rougeLsum_fmeasure": 0.11165202694972098, "rougeLsum_fmeasure_stderr": 0.0016570784342064698, "rougeLsum_precision": 0.07091032443010714, "rougeLsum_precision_stderr": 0.0012648199327180544, "rougeLsum_recall": 0.383427293902694, "rougeLsum_recall_stderr": 0.004986353289044804}}, "3": {"PALM_prompt": {"bleu": 0.6689911149446237, "bleu_stderr": 0.03744306343722813, "rouge1_fmeasure": 0.1180307283191865, "rouge1_fmeasure_stderr": 0.0017866703950125558, "rouge1_precision": 0.07481052377527687, "rouge1_precision_stderr": 0.0013081535798312271, "rouge1_recall": 0.4066681705698085, "rouge1_recall_stderr": 0.0054019768500427, "rouge2_fmeasure": 0.05572250969924929, "rouge2_fmeasure_stderr": 0.0011431197746402597, "rouge2_precision": 0.03499189343685807, "rouge2_precision_stderr": 0.0007904982370484803, "rouge2_recall": 0.20736527087710988, "rouge2_recall_stderr": 0.0040148188536021905, "rougeL_fmeasure": 0.10739194121096401, "rougeL_fmeasure_stderr": 0.0015945105292757362, "rougeL_precision": 0.06809194203501431, "rougeL_precision_stderr": 0.0011605273645199663, "rougeL_recall": 0.36740563590690617, "rougeL_recall_stderr": 0.004685196144542859, "rougeLsum_fmeasure": 0.11166569262354312, "rougeLsum_fmeasure_stderr": 0.001692220078605611, "rougeLsum_precision": 0.07085369656177957, "rougeLsum_precision_stderr": 0.0012407868939625576, "rougeLsum_recall": 0.38310128345463584, "rougeLsum_recall_stderr": 0.004987172857446567}}, "4": {"PALM_prompt": {"bleu": 0.7331295013237835, "bleu_stderr": 0.0376308794527232, "rouge1_fmeasure": 0.12533762675953772, "rouge1_fmeasure_stderr": 0.0018878485389189842, "rouge1_precision": 0.07979502355783509, "rouge1_precision_stderr": 0.0014030109393831616, "rouge1_recall": 0.4235816766130294, "rouge1_recall_stderr": 0.005421570401845218, "rouge2_fmeasure": 0.05965148393261353, "rouge2_fmeasure_stderr": 0.0011811051795035776, "rouge2_precision": 0.037526756160207154, "rouge2_precision_stderr": 0.0008206560892571376, "rouge2_recall": 0.21978995547688931, "rouge2_recall_stderr": 0.004158496007987482, "rougeL_fmeasure": 0.1127973185683369, "rougeL_fmeasure_stderr": 0.0016137599087464715, "rougeL_precision": 0.07173000592003134, "rougeL_precision_stderr": 0.001189659942487538, "rougeL_recall": 0.3800311917113359, "rougeL_recall_stderr": 0.004634022951095827, "rougeLsum_fmeasure": 0.1188731408826614, "rougeLsum_fmeasure_stderr": 0.001769238872468489, "rougeLsum_precision": 0.07571045481706781, "rougeLsum_precision_stderr": 0.0013130071112336225, "rougeLsum_recall": 0.3998599380714254, "rougeLsum_recall_stderr": 0.004996013261269132}}, "5": {"PALM_prompt": {"bleu": 0.7199803964010689, "bleu_stderr": 0.0335341295220522, "rouge1_fmeasure": 0.12957731808842543, "rouge1_fmeasure_stderr": 0.001950385050411022, "rouge1_precision": 0.0831998254284886, "rouge1_precision_stderr": 0.0015598094416264543, "rouge1_recall": 0.43497959954822596, "rouge1_recall_stderr": 0.005519903741092491, "rouge2_fmeasure": 0.061471018231031564, "rouge2_fmeasure_stderr": 0.0011954291401081725, "rouge2_precision": 0.038915148561977614, "rouge2_precision_stderr": 0.0008746684971485049, "rouge2_recall": 0.22682184765709848, "rouge2_recall_stderr": 0.004248572295542693, "rougeL_fmeasure": 0.11444599253148456, "rougeL_fmeasure_stderr": 0.0016146327759809166, "rougeL_precision": 0.07313294781649872, "rougeL_precision_stderr": 0.0012487980616292505, "rougeL_recall": 0.3869620252624607, "rougeL_recall_stderr": 0.00472547888254755, "rougeLsum_fmeasure": 0.12182978494965954, "rougeLsum_fmeasure_stderr": 0.0017943723258623825, "rougeLsum_precision": 0.07806446348136394, "rougeLsum_precision_stderr": 0.0013916456734416912, "rougeLsum_recall": 0.4091496557022353, "rougeLsum_recall_stderr": 0.005082415980961682}}}, "GEM/wiki_lingua_en": {"0": {"tldr_en": {"bleu": 1.953242244453973, "bleu_stderr": 0.05731680211281534, "rouge1_fmeasure": 0.19037826199272892, "rouge1_fmeasure_stderr": 0.0019330255590741413, "rouge1_precision": 0.16219138852188794, "rouge1_precision_stderr": 0.001952170268256085, "rouge1_recall": 0.27855214789998106, "rouge1_recall_stderr": 0.0028661354548397203, "rouge2_fmeasure": 0.04216588190254503, "rouge2_fmeasure_stderr": 0.0009553783013135788, "rouge2_precision": 0.0354263621636146, "rouge2_precision_stderr": 0.0008399737677670994, "rouge2_recall": 0.06484436785581019, "rouge2_recall_stderr": 0.001614050776584332, "rougeL_fmeasure": 0.1448489434443541, "rougeL_fmeasure_stderr": 0.001361425790826035, "rougeL_precision": 0.12175563950858005, "rougeL_precision_stderr": 0.0013221666940557008, "rougeL_recall": 0.21752194752302395, "rougeL_recall_stderr": 0.0023088753932079594, "rougeLsum_fmeasure": 0.1758237056132223, "rougeLsum_fmeasure_stderr": 0.0017714351825610913, "rougeLsum_precision": 0.14956126999475367, "rougeLsum_precision_stderr": 0.0017821025582316077, "rougeLsum_recall": 0.2582733333610139, "rougeLsum_recall_stderr": 0.0026810100132315094}}, "1": {"tldr_en": {"bleu": 3.1938176079049834, "bleu_stderr": 0.06758802228266159, "rouge1_fmeasure": 0.23210095477457815, "rouge1_fmeasure_stderr": 0.0019831122653105916, "rouge1_precision": 0.21449004123956839, "rouge1_precision_stderr": 0.002565225956613692, "rouge1_recall": 0.3240170155957018, "rouge1_recall_stderr": 0.002854256640412515, "rouge2_fmeasure": 0.06178715930121975, "rouge2_fmeasure_stderr": 0.0011277206664131291, "rouge2_precision": 0.05838461705053636, "rouge2_precision_stderr": 0.0014235851964682594, "rouge2_recall": 0.08878615660224992, "rouge2_recall_stderr": 0.0017942884481548583, "rougeL_fmeasure": 0.16714787573615286, "rougeL_fmeasure_stderr": 0.001398161530856219, "rougeL_precision": 0.15474204497973576, "rougeL_precision_stderr": 0.001972497669394072, "rougeL_recall": 0.23823572295131598, "rougeL_recall_stderr": 0.0022819725517357744, "rougeLsum_fmeasure": 0.2194764899179448, "rougeLsum_fmeasure_stderr": 0.0018724396931342306, "rougeLsum_precision": 0.20262040584770197, "rougeLsum_precision_stderr": 0.0024273351077249345, "rougeLsum_recall": 0.3070782317130203, "rougeLsum_recall_stderr": 0.0027244549656214464}}, "2": {"tldr_en": {"bleu": 3.6209568989964964, "bleu_stderr": 0.05693014182524011, "rouge1_fmeasure": 0.23240946839912788, "rouge1_fmeasure_stderr": 0.0020535331913193833, "rouge1_precision": 0.24807700870805302, "rouge1_precision_stderr": 0.0032686331426239274, "rouge1_recall": 0.2993366704587394, "rouge1_recall_stderr": 0.0028897035935155396, "rouge2_fmeasure": 0.06722787106866046, "rouge2_fmeasure_stderr": 0.001306015352926357, "rouge2_precision": 0.07542612135833042, "rouge2_precision_stderr": 0.0019732499800712644, "rouge2_recall": 0.08771578704686069, "rouge2_recall_stderr": 0.001852341009446473, "rougeL_fmeasure": 0.17544324351165277, "rougeL_fmeasure_stderr": 0.001595587702286189, "rougeL_precision": 0.19005839255632967, "rougeL_precision_stderr": 0.002778132688091869, "rougeL_recall": 0.22871074992869012, "rougeL_recall_stderr": 0.002406566174307835, "rougeLsum_fmeasure": 0.2213635199796785, "rougeLsum_fmeasure_stderr": 0.0019597819111732734, "rougeLsum_precision": 0.23648500820691407, "rougeLsum_precision_stderr": 0.0031596714430369476, "rougeLsum_recall": 0.285430067349801, "rougeLsum_recall_stderr": 0.0027751440475442097}}, "3": {"tldr_en": {"bleu": 3.2600101837197197, "bleu_stderr": 0.04841341881147457, "rouge1_fmeasure": 0.18788478661055097, "rouge1_fmeasure_stderr": 0.002472024769674421, "rouge1_precision": 0.23084151108139417, "rouge1_precision_stderr": 0.003999536576630713, "rouge1_recall": 0.22564401884098545, "rouge1_recall_stderr": 0.00322268288462845, "rouge2_fmeasure": 0.0547277065977853, "rouge2_fmeasure_stderr": 0.001316330403077771, "rouge2_precision": 0.07199814947709587, "rouge2_precision_stderr": 0.002257359657010455, "rouge2_recall": 0.0658546131120379, "rouge2_recall_stderr": 0.0016996600071196948, "rougeL_fmeasure": 0.1450771150583464, "rougeL_fmeasure_stderr": 0.0019574386379697857, "rougeL_precision": 0.1812422041327713, "rougeL_precision_stderr": 0.0033598941031452102, "rougeL_recall": 0.17549664105843907, "rougeL_recall_stderr": 0.00262690640098719, "rougeLsum_fmeasure": 0.17866009428807192, "rougeLsum_fmeasure_stderr": 0.0023640874867847488, "rougeLsum_precision": 0.21961824449300582, "rougeLsum_precision_stderr": 0.003836248551627411, "rougeLsum_recall": 0.21459589482318636, "rougeLsum_recall_stderr": 0.003079841928060846}}, "4": {"tldr_en": {"bleu": 0.6197416585249048, "bleu_stderr": 0.050726126214537225, "rouge1_fmeasure": 0.05902884784226779, "rouge1_fmeasure_stderr": 0.0021304994672767174, "rouge1_precision": 0.07762612304263315, "rouge1_precision_stderr": 0.0032117324014510297, "rouge1_recall": 0.07075067661625373, "rouge1_recall_stderr": 0.00266141134016641, "rouge2_fmeasure": 0.01811109085502527, "rouge2_fmeasure_stderr": 0.0009535025790089693, "rouge2_precision": 0.024715265794116245, "rouge2_precision_stderr": 0.0015375396891910912, "rouge2_recall": 0.02194236604474347, "rouge2_recall_stderr": 0.001230091261779581, "rougeL_fmeasure": 0.04687343959092794, "rougeL_fmeasure_stderr": 0.00171937320425508, "rougeL_precision": 0.06261195931905689, "rougeL_precision_stderr": 0.002684073457127978, "rougeL_recall": 0.0564250650958304, "rougeL_recall_stderr": 0.0021744446112801413, "rougeLsum_fmeasure": 0.056127739240012624, "rougeLsum_fmeasure_stderr": 0.002031189471014326, "rougeLsum_precision": 0.07398653730135701, "rougeLsum_precision_stderr": 0.003081234652717845, "rougeLsum_recall": 0.06720084909348248, "rougeLsum_recall_stderr": 0.002527336091137797}}, "5": {"tldr_en": {"bleu": 4.394475685873892e-07, "bleu_stderr": 1.020668525155571e-06, "rouge1_fmeasure": 0.01025088836822709, "rouge1_fmeasure_stderr": 0.0010237064667092625, "rouge1_precision": 0.012749197720849256, "rouge1_precision_stderr": 0.0013678224737624083, "rouge1_recall": 0.011454983373776283, "rouge1_recall_stderr": 0.001152103487332925, "rouge2_fmeasure": 0.003230399473756007, "rouge2_fmeasure_stderr": 0.0004373491168596821, "rouge2_precision": 0.004106263613998532, "rouge2_precision_stderr": 0.0006621811206101381, "rouge2_recall": 0.003568369407358366, "rouge2_recall_stderr": 0.00047406732675066786, "rougeL_fmeasure": 0.008151883997164445, "rougeL_fmeasure_stderr": 0.0008219787823794978, "rougeL_precision": 0.01021272837958567, "rougeL_precision_stderr": 0.001137838670735105, "rougeL_recall": 0.009264383578933708, "rougeL_recall_stderr": 0.0009514107080117658, "rougeLsum_fmeasure": 0.00977974159773322, "rougeLsum_fmeasure_stderr": 0.0009796733551025018, "rougeLsum_precision": 0.012094227953101243, "rougeLsum_precision_stderr": 0.0013067091712138548, "rougeLsum_recall": 0.010971397408480117, "rougeLsum_recall_stderr": 0.0011066936947192276}}}, "e2e_nlg_cleaned": {"0": {"generate_text_restaurant": {"bleu": 5.041894180834452, "bleu_stderr": 0.13033007436218397, "rouge1_fmeasure": 0.2602520157352752, "rouge1_fmeasure_stderr": 0.0019814546233520676, "rouge1_precision": 0.2562147385675977, "rouge1_precision_stderr": 0.0023058315204108905, "rouge1_recall": 0.30315886913634216, "rouge1_recall_stderr": 0.0026139295974695565, "rouge2_fmeasure": 0.08140776012327813, "rouge2_fmeasure_stderr": 0.001311313047394141, "rouge2_precision": 0.07721561798611194, "rouge2_precision_stderr": 0.0012074751318368925, "rouge2_recall": 0.09865589414861335, "rouge2_recall_stderr": 0.0018266381810205243, "rougeL_fmeasure": 0.2348805493930538, "rougeL_fmeasure_stderr": 0.0016535155281064092, "rougeL_precision": 0.23076758584429627, "rougeL_precision_stderr": 0.0019576805274118237, "rougeL_recall": 0.27459675434984065, "rougeL_recall_stderr": 0.002244077056891058, "rougeLsum_fmeasure": 0.2231769159790997, "rougeLsum_fmeasure_stderr": 0.0018450572724071957, "rougeLsum_precision": 0.2179856280727458, "rougeLsum_precision_stderr": 0.0019996113997260653, "rougeLsum_recall": 0.26255348104591614, "rougeLsum_recall_stderr": 0.002535270034294405}}, "1": {"generate_text_restaurant": {"bleu": 11.374090854418796, "bleu_stderr": 0.16642693339608366, "rouge1_fmeasure": 0.44441293942301124, "rouge1_fmeasure_stderr": 0.0019990822428693255, "rouge1_precision": 0.4562660071544534, "rouge1_precision_stderr": 0.0023247072186540372, "rouge1_recall": 0.47023523973208886, "rouge1_recall_stderr": 0.0029204957902967815, "rouge2_fmeasure": 0.19963881437447786, "rouge2_fmeasure_stderr": 0.001763576201025895, "rouge2_precision": 0.20466887595780073, "rouge2_precision_stderr": 0.0018785112726430648, "rouge2_recall": 0.21306332737215863, "rouge2_recall_stderr": 0.0021659970991227857, "rougeL_fmeasure": 0.31715680141114483, "rougeL_fmeasure_stderr": 0.0017221275024008205, "rougeL_precision": 0.32653768131528194, "rougeL_precision_stderr": 0.001990750084311469, "rougeL_recall": 0.3355433404446685, "rougeL_recall_stderr": 0.0023788838500677285, "rougeLsum_fmeasure": 0.37193579102313756, "rougeLsum_fmeasure_stderr": 0.0020241065034827393, "rougeLsum_precision": 0.3824555027115406, "rougeLsum_precision_stderr": 0.0023079179899071546, "rougeLsum_recall": 0.39314046484640197, "rougeLsum_recall_stderr": 0.0027333955271206228}}, "2": {"generate_text_restaurant": {"bleu": 12.560644285364408, "bleu_stderr": 0.16815632193227215, "rouge1_fmeasure": 0.471505067248124, "rouge1_fmeasure_stderr": 0.0019357830388836816, "rouge1_precision": 0.4693114735453705, "rouge1_precision_stderr": 0.002281004588256248, "rouge1_recall": 0.5083374783023907, "rouge1_recall_stderr": 0.0027945657189866707, "rouge2_fmeasure": 0.22343026823022358, "rouge2_fmeasure_stderr": 0.0018374594088211456, "rouge2_precision": 0.2221316806859365, "rouge2_precision_stderr": 0.0019435645476744553, "rouge2_recall": 0.24313554807879642, "rouge2_recall_stderr": 0.002262346807934513, "rougeL_fmeasure": 0.34007419588321747, "rougeL_fmeasure_stderr": 0.0017661692599286885, "rougeL_precision": 0.33868884919458336, "rougeL_precision_stderr": 0.0020005248626700075, "rougeL_recall": 0.36715355671289307, "rougeL_recall_stderr": 0.002393826810405225, "rougeLsum_fmeasure": 0.3992367697974597, "rougeLsum_fmeasure_stderr": 0.002047758775999973, "rougeLsum_precision": 0.39764801002400024, "rougeLsum_precision_stderr": 0.0023126735358181896, "rougeLsum_recall": 0.4301763419894379, "rougeLsum_recall_stderr": 0.002704714026602679}}, "3": {"generate_text_restaurant": {"bleu": 12.935887027476703, "bleu_stderr": 0.1413974704174758, "rouge1_fmeasure": 0.47748617274088134, "rouge1_fmeasure_stderr": 0.0019432464320825518, "rouge1_precision": 0.46877980581573947, "rouge1_precision_stderr": 0.002306244616020727, "rouge1_recall": 0.5201076534915446, "rouge1_recall_stderr": 0.0027589098635390622, "rouge2_fmeasure": 0.2299932736088538, "rouge2_fmeasure_stderr": 0.0018542116692296976, "rouge2_precision": 0.22504131267180502, "rouge2_precision_stderr": 0.0019096188553057005, "rouge2_recall": 0.25334102505668565, "rouge2_recall_stderr": 0.0023303517782663806, "rougeL_fmeasure": 0.3453328850410215, "rougeL_fmeasure_stderr": 0.0017788674272907377, "rougeL_precision": 0.33848754169654177, "rougeL_precision_stderr": 0.0019586798135973788, "rougeL_recall": 0.3774849420782741, "rougeL_recall_stderr": 0.002448077823046622, "rougeLsum_fmeasure": 0.4054179095581331, "rougeLsum_fmeasure_stderr": 0.002057211964943938, "rougeLsum_precision": 0.398001467577397, "rougeLsum_precision_stderr": 0.002302044463314153, "rougeLsum_recall": 0.44176973604863884, "rougeLsum_recall_stderr": 0.002731272765488879}}, "4": {"generate_text_restaurant": {"bleu": 13.062203352639571, "bleu_stderr": 0.1443635676836731, "rouge1_fmeasure": 0.480197984035446, "rouge1_fmeasure_stderr": 0.0019374104232555646, "rouge1_precision": 0.4681188396235994, "rouge1_precision_stderr": 0.0022953424581571586, "rouge1_recall": 0.5257893103591965, "rouge1_recall_stderr": 0.0027113760261248936, "rouge2_fmeasure": 0.231134956488486, "rouge2_fmeasure_stderr": 0.0018720751391330711, "rouge2_precision": 0.2248618704612403, "rouge2_precision_stderr": 0.001945938539895268, "rouge2_recall": 0.2557332161082852, "rouge2_recall_stderr": 0.0023207877819305836, "rougeL_fmeasure": 0.34575847531397613, "rougeL_fmeasure_stderr": 0.0017883470089669242, "rougeL_precision": 0.33632345011254977, "rougeL_precision_stderr": 0.0019454027156019396, "rougeL_recall": 0.38013195807046607, "rougeL_recall_stderr": 0.00244327641775733, "rougeLsum_fmeasure": 0.4073959730873966, "rougeLsum_fmeasure_stderr": 0.002067697322138944, "rougeLsum_precision": 0.39692021210935596, "rougeLsum_precision_stderr": 0.0022989702493060767, "rougeLsum_recall": 0.44638101481881887, "rougeLsum_recall_stderr": 0.002709781160431362}}, "5": {"generate_text_restaurant": {"bleu": 13.007507775940796, "bleu_stderr": 0.15953149423790455, "rouge1_fmeasure": 0.4808919059561077, "rouge1_fmeasure_stderr": 0.001952787403665255, "rouge1_precision": 0.46770150316298764, "rouge1_precision_stderr": 0.0022797897877814698, "rouge1_recall": 0.5268279632857007, "rouge1_recall_stderr": 0.0027460682371807316, "rouge2_fmeasure": 0.23283624336459657, "rouge2_fmeasure_stderr": 0.0018731934526011642, "rouge2_precision": 0.22559527103944196, "rouge2_precision_stderr": 0.0019147802508556583, "rouge2_recall": 0.2579313360551791, "rouge2_recall_stderr": 0.00233240570767885, "rougeL_fmeasure": 0.3483900918258692, "rougeL_fmeasure_stderr": 0.0018126238683006549, "rougeL_precision": 0.33809291109163425, "rougeL_precision_stderr": 0.0019479891358002816, "rougeL_recall": 0.3830487611318609, "rougeL_recall_stderr": 0.0024664916023592687, "rougeLsum_fmeasure": 0.40962759438618196, "rougeLsum_fmeasure_stderr": 0.002070580879609581, "rougeLsum_precision": 0.3985001878422045, "rougeLsum_precision_stderr": 0.002294921272754354, "rougeLsum_recall": 0.4486089837026324, "rougeLsum_recall_stderr": 0.002709717530773792}}}, "gem_xsum": {"0": {"article_DOC_summary": {"bleu": 2.202159785681064, "bleu_stderr": 0.1019905127598651, "rouge1_fmeasure": 0.21747292414186656, "rouge1_fmeasure_stderr": 0.0025362641546465615, "rouge1_precision": 0.15620442016026878, "rouge1_precision_stderr": 0.0019393097407504807, "rouge1_recall": 0.37637904496982905, "rouge1_recall_stderr": 0.004428769631922407, "rouge2_fmeasure": 0.05370104596286604, "rouge2_fmeasure_stderr": 0.001644696030213316, "rouge2_precision": 0.03798752030386553, "rouge2_precision_stderr": 0.001174899351649945, "rouge2_recall": 0.09645314548431894, "rouge2_recall_stderr": 0.0030269539528850957, "rougeL_fmeasure": 0.16392696498450032, "rougeL_fmeasure_stderr": 0.0019387441418856352, "rougeL_precision": 0.11750264664821597, "rougeL_precision_stderr": 0.001455192782942557, "rougeL_recall": 0.28553565213661397, "rougeL_recall_stderr": 0.003571545700265264, "rougeLsum_fmeasure": 0.1729737886084137, "rougeLsum_fmeasure_stderr": 0.0021734952347434375, "rougeLsum_precision": 0.12392072701085288, "rougeLsum_precision_stderr": 0.0016211314235083207, "rougeLsum_recall": 0.30146747797091933, "rougeLsum_recall_stderr": 0.003959575791577483}}, "1": {"article_DOC_summary": {"bleu": 1.9249412744961178, "bleu_stderr": 0.12178209771806298, "rouge1_fmeasure": 0.20067154816406912, "rouge1_fmeasure_stderr": 0.0026898597422456614, "rouge1_precision": 0.14293573080985697, "rouge1_precision_stderr": 0.0020020715732026848, "rouge1_recall": 0.3507450257481026, "rouge1_recall_stderr": 0.004639905013718798, "rouge2_fmeasure": 0.04598183981683866, "rouge2_fmeasure_stderr": 0.001649351483193518, "rouge2_precision": 0.0324308871516594, "rouge2_precision_stderr": 0.0011682005693517872, "rouge2_recall": 0.08264816662579652, "rouge2_recall_stderr": 0.003080246882800617, "rougeL_fmeasure": 0.15118274474995874, "rougeL_fmeasure_stderr": 0.001994655397896864, "rougeL_precision": 0.10746501641700831, "rougeL_precision_stderr": 0.0014694032015050793, "rougeL_recall": 0.2659219914279442, "rougeL_recall_stderr": 0.0035904663684219085, "rougeLsum_fmeasure": 0.160999424649348, "rougeLsum_fmeasure_stderr": 0.002240087025674008, "rougeLsum_precision": 0.11442553643678831, "rougeLsum_precision_stderr": 0.0016427072257106192, "rougeLsum_recall": 0.28320972201688277, "rougeLsum_recall_stderr": 0.00404579631504026}}, "2": {"article_DOC_summary": {"bleu": 2.354378541611583, "bleu_stderr": 0.11647407253425891, "rouge1_fmeasure": 0.22162196546785315, "rouge1_fmeasure_stderr": 0.0026821013380755065, "rouge1_precision": 0.15803061677869468, "rouge1_precision_stderr": 0.0020134830696427186, "rouge1_recall": 0.38606737885839715, "rouge1_recall_stderr": 0.0045727909552794035, "rouge2_fmeasure": 0.05795467773425469, "rouge2_fmeasure_stderr": 0.001726378828967632, "rouge2_precision": 0.04089910513966374, "rouge2_precision_stderr": 0.0012276135124666848, "rouge2_recall": 0.10377696105882783, "rouge2_recall_stderr": 0.0031669949816395633, "rougeL_fmeasure": 0.16710610962820924, "rougeL_fmeasure_stderr": 0.0020561292357138584, "rougeL_precision": 0.11895190107092266, "rougeL_precision_stderr": 0.001522240640457265, "rougeL_recall": 0.29275028181844964, "rougeL_recall_stderr": 0.0036724085051555028, "rougeLsum_fmeasure": 0.17719218883183147, "rougeLsum_fmeasure_stderr": 0.002316006750830736, "rougeLsum_precision": 0.12607152034389388, "rougeLsum_precision_stderr": 0.0017074031321102738, "rougeLsum_recall": 0.31057163498399204, "rougeLsum_recall_stderr": 0.0041042123336552}}, "3": {"article_DOC_summary": {"bleu": 2.5396858265074442, "bleu_stderr": 0.08867651581985392, "rouge1_fmeasure": 0.21823856021867855, "rouge1_fmeasure_stderr": 0.00287509423652189, "rouge1_precision": 0.15862259061034525, "rouge1_precision_stderr": 0.0022705733916664897, "rouge1_recall": 0.37475206189355903, "rouge1_recall_stderr": 0.004959725343264155, "rouge2_fmeasure": 0.05707472809987463, "rouge2_fmeasure_stderr": 0.0017670032180951126, "rouge2_precision": 0.040777801871425406, "rouge2_precision_stderr": 0.0012722722586737197, "rouge2_recall": 0.1013174193884724, "rouge2_recall_stderr": 0.0032107881395706537, "rougeL_fmeasure": 0.16363168956728244, "rougeL_fmeasure_stderr": 0.002209845051514402, "rougeL_precision": 0.11900917936528578, "rougeL_precision_stderr": 0.0017595863454497236, "rougeL_recall": 0.2823031773424627, "rougeL_recall_stderr": 0.00395533580561216, "rougeLsum_fmeasure": 0.1744236573082813, "rougeLsum_fmeasure_stderr": 0.0025092608797292787, "rougeLsum_precision": 0.1267437227686215, "rougeLsum_precision_stderr": 0.0019625874757798435, "rougeLsum_recall": 0.3009970402211979, "rougeLsum_recall_stderr": 0.00444855277167097}}, "4": {"article_DOC_summary": {"bleu": 1.2606242149604632, "bleu_stderr": 0.14038396719045979, "rouge1_fmeasure": 0.05899878787999313, "rouge1_fmeasure_stderr": 0.0031984402791436907, "rouge1_precision": 0.047304211697680565, "rouge1_precision_stderr": 0.0026448858289027655, "rouge1_recall": 0.09474278252615058, "rouge1_recall_stderr": 0.005308877220848683, "rouge2_fmeasure": 0.0155308783397458, "rouge2_fmeasure_stderr": 0.001299471111442663, "rouge2_precision": 0.011996087771023494, "rouge2_precision_stderr": 0.001099214076178898, "rouge2_recall": 0.0263417241337705, "rouge2_recall_stderr": 0.002220861663283421, "rougeL_fmeasure": 0.044337528627898845, "rougeL_fmeasure_stderr": 0.002409584552086278, "rougeL_precision": 0.03579263906355918, "rougeL_precision_stderr": 0.00203840434793067, "rougeL_recall": 0.07128613276076894, "rougeL_recall_stderr": 0.0040405231404290805, "rougeLsum_fmeasure": 0.04848597226747422, "rougeLsum_fmeasure_stderr": 0.0026607333825415256, "rougeLsum_precision": 0.03891697941827118, "rougeLsum_precision_stderr": 0.0022203695026481044, "rougeLsum_recall": 0.07811802978970729, "rougeLsum_recall_stderr": 0.004450967311039029}}, "5": {"article_DOC_summary": {"bleu": 5.904200875747917e-17, "bleu_stderr": 6.845384228352431e-14, "rouge1_fmeasure": 0.0029056409403733605, "rouge1_fmeasure_stderr": 0.0007789369963578187, "rouge1_precision": 0.002575838186588936, "rouge1_precision_stderr": 0.0007400165754621803, "rouge1_recall": 0.004319762469932286, "rouge1_recall_stderr": 0.0011903191633291926, "rouge2_fmeasure": 0.0006473343958914281, "rouge2_fmeasure_stderr": 0.0002465721330155313, "rouge2_precision": 0.0006086503070847952, "rouge2_precision_stderr": 0.0002950028606554242, "rouge2_recall": 0.000972008751741797, "rouge2_recall_stderr": 0.0003567899989116429, "rougeL_fmeasure": 0.001934058917849306, "rougeL_fmeasure_stderr": 0.0005094916809588088, "rougeL_precision": 0.0017056464200092727, "rougeL_precision_stderr": 0.0004727453480810513, "rougeL_recall": 0.002922861912775516, "rougeL_recall_stderr": 0.0008030319091531282, "rougeLsum_fmeasure": 0.002209255524001538, "rougeLsum_fmeasure_stderr": 0.0006016088430140866, "rougeLsum_precision": 0.001992523091403346, "rougeLsum_precision_stderr": 0.000590292247129764, "rougeLsum_recall": 0.0032955304150390267, "rougeLsum_recall_stderr": 0.0009334494775770981}}}} |