Muennighoff's picture
Add files
892f3c7
raw
history blame
No virus
28 kB
{"GEM/web_nlg_en": {"0": {"PALM_prompt": {"bleu": 0.3778578966148067, "bleu_stderr": 0.043108338793946065, "rouge1_fmeasure": 0.11229918414347093, "rouge1_fmeasure_stderr": 0.002038339976908837, "rouge1_precision": 0.07411555032972421, "rouge1_precision_stderr": 0.001538099367112622, "rouge1_recall": 0.309304518659125, "rouge1_recall_stderr": 0.004647036349994307, "rouge2_fmeasure": 0.05373275688087374, "rouge2_fmeasure_stderr": 0.0012922653888554133, "rouge2_precision": 0.035405873343107096, "rouge2_precision_stderr": 0.0009494477514351852, "rouge2_recall": 0.15177029561380864, "rouge2_recall_stderr": 0.0032441764358631343, "rougeL_fmeasure": 0.10836013211520433, "rougeL_fmeasure_stderr": 0.001907062297131903, "rougeL_precision": 0.07128915442841278, "rougeL_precision_stderr": 0.001421332991618732, "rougeL_recall": 0.3006366755077802, "rougeL_recall_stderr": 0.004524046109868848, "rougeLsum_fmeasure": 0.10699983162704317, "rougeLsum_fmeasure_stderr": 0.0018997512152092622, "rougeLsum_precision": 0.07058874999622211, "rougeLsum_precision_stderr": 0.0014347547189524324, "rougeLsum_recall": 0.2951817916558195, "rougeLsum_recall_stderr": 0.004352927117156272}}, "1": {"PALM_prompt": {"bleu": 0.5559292194446633, "bleu_stderr": 0.033063305669521814, "rouge1_fmeasure": 0.11519017450049537, "rouge1_fmeasure_stderr": 0.001781459047903915, "rouge1_precision": 0.07344134290778047, "rouge1_precision_stderr": 0.0013075775283346684, "rouge1_recall": 0.38367122642556717, "rouge1_recall_stderr": 0.005374779689077085, "rouge2_fmeasure": 0.05429955369368683, "rouge2_fmeasure_stderr": 0.001164101537291991, "rouge2_precision": 0.03451957379808363, "rouge2_precision_stderr": 0.0008237357497660324, "rouge2_recall": 0.1902878844491511, "rouge2_recall_stderr": 0.0038667575429744347, "rougeL_fmeasure": 0.1089395644753034, "rougeL_fmeasure_stderr": 0.001663152079550431, "rougeL_precision": 0.06953493691658816, "rougeL_precision_stderr": 0.0012180136656132438, "rougeL_recall": 0.35915530916109556, "rougeL_recall_stderr": 0.004866166233820879, "rougeLsum_fmeasure": 0.10966995207767154, "rougeLsum_fmeasure_stderr": 0.001701230535057806, "rougeLsum_precision": 0.0700241015268691, "rougeLsum_precision_stderr": 0.0012535074467763, "rougeLsum_recall": 0.36285521927513625, "rougeLsum_recall_stderr": 0.004946296798374893}}, "2": {"PALM_prompt": {"bleu": 0.5782472127932445, "bleu_stderr": 0.02876860184072706, "rouge1_fmeasure": 0.11608314556487608, "rouge1_fmeasure_stderr": 0.0016856934686361683, "rouge1_precision": 0.07332998641209827, "rouge1_precision_stderr": 0.0012278221285519305, "rouge1_recall": 0.4051352210429427, "rouge1_recall_stderr": 0.005349246205768158, "rouge2_fmeasure": 0.054101025197296336, "rouge2_fmeasure_stderr": 0.0010930137218225489, "rouge2_precision": 0.034072750089738806, "rouge2_precision_stderr": 0.0007661045363189041, "rouge2_recall": 0.20084233643875887, "rouge2_recall_stderr": 0.003927573729716624, "rougeL_fmeasure": 0.10781733963253654, "rougeL_fmeasure_stderr": 0.0015624544135440744, "rougeL_precision": 0.0682789164826936, "rougeL_precision_stderr": 0.00114056254383938, "rougeL_recall": 0.36994608434763104, "rougeL_recall_stderr": 0.004671069819142146, "rougeLsum_fmeasure": 0.10978895909106065, "rougeLsum_fmeasure_stderr": 0.0015935691932955263, "rougeLsum_precision": 0.06944433376851597, "rougeLsum_precision_stderr": 0.0011635802718539946, "rougeLsum_recall": 0.3806199258716764, "rougeLsum_recall_stderr": 0.004907310655807021}}, "3": {"PALM_prompt": {"bleu": 0.6915008150808406, "bleu_stderr": 0.03546518672506001, "rouge1_fmeasure": 0.11803876998559919, "rouge1_fmeasure_stderr": 0.0017025734287338006, "rouge1_precision": 0.07432407498828138, "rouge1_precision_stderr": 0.0012325917015022579, "rouge1_recall": 0.4104911461112403, "rouge1_recall_stderr": 0.005343537670914898, "rouge2_fmeasure": 0.05560964185032228, "rouge2_fmeasure_stderr": 0.001085229952279771, "rouge2_precision": 0.03485135568208787, "rouge2_precision_stderr": 0.0007550726857230097, "rouge2_recall": 0.20729890874003387, "rouge2_recall_stderr": 0.003943582140548173, "rougeL_fmeasure": 0.10904814717011492, "rougeL_fmeasure_stderr": 0.0015470673139562688, "rougeL_precision": 0.06880425728281662, "rougeL_precision_stderr": 0.0011244989363678815, "rougeL_recall": 0.375153241896145, "rougeL_recall_stderr": 0.004712690263932408, "rougeLsum_fmeasure": 0.11156419888096808, "rougeLsum_fmeasure_stderr": 0.0016120520944898505, "rougeLsum_precision": 0.07034752749731535, "rougeLsum_precision_stderr": 0.0011699863791661837, "rougeLsum_recall": 0.3857816920367689, "rougeLsum_recall_stderr": 0.004912882067435381}}, "4": {"PALM_prompt": {"bleu": 0.7189066936765581, "bleu_stderr": 0.037013333820727926, "rouge1_fmeasure": 0.11905897645265517, "rouge1_fmeasure_stderr": 0.0016851385659147225, "rouge1_precision": 0.0746932073820224, "rouge1_precision_stderr": 0.0012134517684081734, "rouge1_recall": 0.41771020616828414, "rouge1_recall_stderr": 0.0052465481407677345, "rouge2_fmeasure": 0.055971441098147307, "rouge2_fmeasure_stderr": 0.0010771389506484157, "rouge2_precision": 0.034925003471357664, "rouge2_precision_stderr": 0.0007449043245097383, "rouge2_recall": 0.21258956488991562, "rouge2_recall_stderr": 0.003996053593134186, "rougeL_fmeasure": 0.10871097099572738, "rougeL_fmeasure_stderr": 0.0015089792586892492, "rougeL_precision": 0.06837902016461192, "rougeL_precision_stderr": 0.0010967825484641605, "rougeL_recall": 0.3778018545867543, "rougeL_recall_stderr": 0.00455156041833246, "rougeLsum_fmeasure": 0.11244409077423552, "rougeLsum_fmeasure_stderr": 0.0015904992527627166, "rougeLsum_precision": 0.07063506078356421, "rougeLsum_precision_stderr": 0.0011518223964322905, "rougeLsum_recall": 0.39341366411170076, "rougeLsum_recall_stderr": 0.00485926225127653}}, "5": {"PALM_prompt": {"bleu": 0.7868046756108051, "bleu_stderr": 0.02991271086752641, "rouge1_fmeasure": 0.12018582936445632, "rouge1_fmeasure_stderr": 0.0016323788305252095, "rouge1_precision": 0.07492512647076705, "rouge1_precision_stderr": 0.0011666617641076609, "rouge1_recall": 0.4328553245785454, "rouge1_recall_stderr": 0.005279295280429884, "rouge2_fmeasure": 0.05660828028959127, "rouge2_fmeasure_stderr": 0.0010400981467133133, "rouge2_precision": 0.03506321715356214, "rouge2_precision_stderr": 0.0007143804415237641, "rouge2_recall": 0.22123976259437653, "rouge2_recall_stderr": 0.003995978607772992, "rougeL_fmeasure": 0.10906303355905887, "rougeL_fmeasure_stderr": 0.0014559180672523411, "rougeL_precision": 0.06818310395402347, "rougeL_precision_stderr": 0.0010562464898575118, "rougeL_recall": 0.38959556517516325, "rougeL_recall_stderr": 0.004569300260461267, "rougeLsum_fmeasure": 0.11355384378827522, "rougeLsum_fmeasure_stderr": 0.001550934113029576, "rougeLsum_precision": 0.07090266049584355, "rougeLsum_precision_stderr": 0.001113352975885553, "rougeLsum_recall": 0.4063980496121481, "rougeLsum_recall_stderr": 0.004844306040632001}}}, "GEM/wiki_lingua_en": {"0": {"tldr_en": {"bleu": 1.6474987427065775, "bleu_stderr": 0.06593859959084909, "rouge1_fmeasure": 0.1796629653377477, "rouge1_fmeasure_stderr": 0.0018831601953688906, "rouge1_precision": 0.15334539415738388, "rouge1_precision_stderr": 0.0019222806905930796, "rouge1_recall": 0.26182170525230664, "rouge1_recall_stderr": 0.0027125088120466567, "rouge2_fmeasure": 0.03752338599482476, "rouge2_fmeasure_stderr": 0.0008657026414927998, "rouge2_precision": 0.031909006707834885, "rouge2_precision_stderr": 0.0007708990454599334, "rouge2_recall": 0.05633865948240556, "rouge2_recall_stderr": 0.0014288226584569942, "rougeL_fmeasure": 0.14212961094234547, "rougeL_fmeasure_stderr": 0.0013510429063892365, "rougeL_precision": 0.11977598793404674, "rougeL_precision_stderr": 0.0013475259124603452, "rougeL_recall": 0.21260047811552407, "rougeL_recall_stderr": 0.002226957170728599, "rougeLsum_fmeasure": 0.16422175879907844, "rougeLsum_fmeasure_stderr": 0.001702104333489601, "rougeLsum_precision": 0.13994434092556626, "rougeLsum_precision_stderr": 0.0017396047429116305, "rougeLsum_recall": 0.24051441991616382, "rougeLsum_recall_stderr": 0.002515699207499435}}, "1": {"tldr_en": {"bleu": 2.786152224873671, "bleu_stderr": 0.05808815291287487, "rouge1_fmeasure": 0.22429676008256744, "rouge1_fmeasure_stderr": 0.0019215432949986416, "rouge1_precision": 0.19811750483825502, "rouge1_precision_stderr": 0.002244284359015066, "rouge1_recall": 0.3233361530990366, "rouge1_recall_stderr": 0.0027615810059661346, "rouge2_fmeasure": 0.055270992861272274, "rouge2_fmeasure_stderr": 0.0010209237932340483, "rouge2_precision": 0.04984071088538675, "rouge2_precision_stderr": 0.0011306753133130294, "rouge2_recall": 0.08194485459001105, "rouge2_recall_stderr": 0.001676052028304491, "rougeL_fmeasure": 0.15889068091572497, "rougeL_fmeasure_stderr": 0.0012757988630829789, "rougeL_precision": 0.13956446970769343, "rougeL_precision_stderr": 0.001568888728809687, "rougeL_recall": 0.23527321502693888, "rougeL_recall_stderr": 0.002186112073171261, "rougeLsum_fmeasure": 0.21089500684394413, "rougeLsum_fmeasure_stderr": 0.001812341485185825, "rougeLsum_precision": 0.18632650105602275, "rougeLsum_precision_stderr": 0.002136419893250326, "rougeLsum_recall": 0.30435788657049767, "rougeLsum_recall_stderr": 0.002623892289765707}}, "2": {"tldr_en": {"bleu": 3.230998083062549, "bleu_stderr": 0.050797557201713334, "rouge1_fmeasure": 0.22937813566648368, "rouge1_fmeasure_stderr": 0.0019219764317323842, "rouge1_precision": 0.21033059542814828, "rouge1_precision_stderr": 0.002442858582337002, "rouge1_recall": 0.32413547755906186, "rouge1_recall_stderr": 0.0028003239001999137, "rouge2_fmeasure": 0.058712455420886434, "rouge2_fmeasure_stderr": 0.0010940197542857381, "rouge2_precision": 0.05523685617830656, "rouge2_precision_stderr": 0.0012874559073350383, "rouge2_recall": 0.08462329830096554, "rouge2_recall_stderr": 0.0017673558504113702, "rougeL_fmeasure": 0.16297597705988986, "rougeL_fmeasure_stderr": 0.0013304409687103912, "rougeL_precision": 0.1497674533077381, "rougeL_precision_stderr": 0.0018524531908293406, "rougeL_recall": 0.23560418818517648, "rougeL_recall_stderr": 0.0022704842678573766, "rougeLsum_fmeasure": 0.21693278589564352, "rougeLsum_fmeasure_stderr": 0.0018227504624372965, "rougeLsum_precision": 0.19887451626852745, "rougeLsum_precision_stderr": 0.002331309192885264, "rougeLsum_recall": 0.3069248020961403, "rougeLsum_recall_stderr": 0.0026805984377935225}}, "3": {"tldr_en": {"bleu": 3.2098001105373206, "bleu_stderr": 0.09099300025969562, "rouge1_fmeasure": 0.1876832021711141, "rouge1_fmeasure_stderr": 0.0022940658612174095, "rouge1_precision": 0.1806956214983726, "rouge1_precision_stderr": 0.0027831512016435046, "rouge1_recall": 0.2623447416585146, "rouge1_recall_stderr": 0.0033680997374848517, "rouge2_fmeasure": 0.04841722766281516, "rouge2_fmeasure_stderr": 0.0011008037910137322, "rouge2_precision": 0.047673762536966334, "rouge2_precision_stderr": 0.0013822773824892138, "rouge2_recall": 0.0697044253840176, "rouge2_recall_stderr": 0.001729633370079589, "rougeL_fmeasure": 0.13587871163748794, "rougeL_fmeasure_stderr": 0.0016337548444324763, "rougeL_precision": 0.13209227506220064, "rougeL_precision_stderr": 0.002157083339054086, "rougeL_recall": 0.193574388819157, "rougeL_recall_stderr": 0.0026303701953405384, "rougeLsum_fmeasure": 0.17759916274930226, "rougeLsum_fmeasure_stderr": 0.0021766669356267855, "rougeLsum_precision": 0.1711795821823165, "rougeLsum_precision_stderr": 0.002664487441078435, "rougeLsum_recall": 0.24863617061757418, "rougeLsum_recall_stderr": 0.0032228879303417934}}, "4": {"tldr_en": {"bleu": 0.6098983821550592, "bleu_stderr": 0.057390083475920894, "rouge1_fmeasure": 0.05909725046757388, "rouge1_fmeasure_stderr": 0.0020201095521583104, "rouge1_precision": 0.05880934489289142, "rouge1_precision_stderr": 0.0022689626423463057, "rouge1_recall": 0.08575740200155547, "rouge1_recall_stderr": 0.002995322533624644, "rouge2_fmeasure": 0.014955192433241102, "rouge2_fmeasure_stderr": 0.0007610692004221399, "rouge2_precision": 0.015110877443934299, "rouge2_precision_stderr": 0.000991369440072553, "rouge2_recall": 0.022701528371762265, "rouge2_recall_stderr": 0.001245597630024608, "rougeL_fmeasure": 0.044050934610035515, "rougeL_fmeasure_stderr": 0.001498662498119108, "rougeL_precision": 0.04469761272469577, "rougeL_precision_stderr": 0.0018115322606699102, "rougeL_recall": 0.06493843037748623, "rougeL_recall_stderr": 0.0023175889760991357, "rougeLsum_fmeasure": 0.055485095239080344, "rougeLsum_fmeasure_stderr": 0.0018978766900965142, "rougeLsum_precision": 0.0553855629257085, "rougeLsum_precision_stderr": 0.0021577985213379713, "rougeLsum_recall": 0.08067508006348567, "rougeLsum_recall_stderr": 0.0028298079410380454}}, "5": {"tldr_en": {"bleu": 7.585034963472076e-07, "bleu_stderr": 1.5369928370922445e-06, "rouge1_fmeasure": 0.009438215462949508, "rouge1_fmeasure_stderr": 0.0008930219445271543, "rouge1_precision": 0.009364139423338884, "rouge1_precision_stderr": 0.0010022987284321672, "rouge1_recall": 0.014018983768781176, "rouge1_recall_stderr": 0.0013739169170373748, "rouge2_fmeasure": 0.002492491138928612, "rouge2_fmeasure_stderr": 0.00033796870035768413, "rouge2_precision": 0.002554638785654485, "rouge2_precision_stderr": 0.0004139088387696996, "rouge2_recall": 0.004058440910233081, "rouge2_recall_stderr": 0.0006059287974265584, "rougeL_fmeasure": 0.007008419627805089, "rougeL_fmeasure_stderr": 0.0006680187288932387, "rougeL_precision": 0.007004878000531978, "rougeL_precision_stderr": 0.0007704906553010422, "rougeL_recall": 0.010728122020319702, "rougeL_recall_stderr": 0.0010948722482846322, "rougeLsum_fmeasure": 0.008755675533348816, "rougeLsum_fmeasure_stderr": 0.0008272404703615799, "rougeLsum_precision": 0.008716167882302485, "rougeLsum_precision_stderr": 0.0009417371430749615, "rougeLsum_recall": 0.013083621795425198, "rougeLsum_recall_stderr": 0.0012869514383126801}}}, "e2e_nlg_cleaned": {"0": {"generate_text_restaurant": {"bleu": 2.302445011589307, "bleu_stderr": 0.06211023865546385, "rouge1_fmeasure": 0.16312944483849517, "rouge1_fmeasure_stderr": 0.0012810447257741884, "rouge1_precision": 0.12233139227806873, "rouge1_precision_stderr": 0.0010629452092601635, "rouge1_recall": 0.25742079610936297, "rouge1_recall_stderr": 0.001800775093152571, "rouge2_fmeasure": 0.04090223997307209, "rouge2_fmeasure_stderr": 0.0009736983422614277, "rouge2_precision": 0.030911049123290638, "rouge2_precision_stderr": 0.0007417529238496929, "rouge2_recall": 0.06285991268008932, "rouge2_recall_stderr": 0.0015091563495189734, "rougeL_fmeasure": 0.16171573051604754, "rougeL_fmeasure_stderr": 0.0012389880599311676, "rougeL_precision": 0.12118590550392237, "rougeL_precision_stderr": 0.0010248820684599837, "rougeL_recall": 0.2555207273914006, "rougeL_recall_stderr": 0.001760350193080484, "rougeLsum_fmeasure": 0.1280356806160262, "rougeLsum_fmeasure_stderr": 0.0012028446220128677, "rougeLsum_precision": 0.09601857609439678, "rougeLsum_precision_stderr": 0.0009739557630404562, "rougeLsum_recall": 0.20198211758201637, "rougeLsum_recall_stderr": 0.0017356209782491401}}, "1": {"generate_text_restaurant": {"bleu": 9.263924206317883, "bleu_stderr": 0.07741695657438914, "rouge1_fmeasure": 0.4034314142097248, "rouge1_fmeasure_stderr": 0.0022118879808028843, "rouge1_precision": 0.46181278849346963, "rouge1_precision_stderr": 0.003686608618192092, "rouge1_recall": 0.4286623121704012, "rouge1_recall_stderr": 0.003005228287502819, "rouge2_fmeasure": 0.18184691082787147, "rouge2_fmeasure_stderr": 0.0018176157547358858, "rouge2_precision": 0.2127064486018551, "rouge2_precision_stderr": 0.0026018988957500753, "rouge2_recall": 0.19238207615248135, "rouge2_recall_stderr": 0.00208794348752037, "rougeL_fmeasure": 0.3047130282688444, "rougeL_fmeasure_stderr": 0.0018640708877106472, "rougeL_precision": 0.3491570035267105, "rougeL_precision_stderr": 0.003076016478420658, "rougeL_recall": 0.3262548928750604, "rougeL_recall_stderr": 0.002559992101041393, "rougeLsum_fmeasure": 0.33103396853758926, "rougeLsum_fmeasure_stderr": 0.002167584950514449, "rougeLsum_precision": 0.3805884982861303, "rougeLsum_precision_stderr": 0.0034128765580002424, "rougeLsum_recall": 0.35050122813254053, "rougeLsum_recall_stderr": 0.0027309493870352275}}, "2": {"generate_text_restaurant": {"bleu": 10.065169479277689, "bleu_stderr": 0.13743485776863448, "rouge1_fmeasure": 0.41741556545511066, "rouge1_fmeasure_stderr": 0.0022731192955223276, "rouge1_precision": 0.4521349721323409, "rouge1_precision_stderr": 0.0037077133304098463, "rouge1_recall": 0.4576969276598449, "rouge1_recall_stderr": 0.002912059970191956, "rouge2_fmeasure": 0.19704389881949605, "rouge2_fmeasure_stderr": 0.0018909764984676675, "rouge2_precision": 0.2175791657307876, "rouge2_precision_stderr": 0.0026523412395747367, "rouge2_recall": 0.21609856115013357, "rouge2_recall_stderr": 0.002192652821722558, "rougeL_fmeasure": 0.32096479784507037, "rougeL_fmeasure_stderr": 0.0018970324444313584, "rougeL_precision": 0.34696313010753177, "rougeL_precision_stderr": 0.0030525069814565397, "rougeL_recall": 0.3551058458123904, "rougeL_recall_stderr": 0.00253577560262687, "rougeLsum_fmeasure": 0.349200751229774, "rougeLsum_fmeasure_stderr": 0.0022493473991314562, "rougeLsum_precision": 0.3795245084348248, "rougeLsum_precision_stderr": 0.003449429352786332, "rougeLsum_recall": 0.3815645358661485, "rougeLsum_recall_stderr": 0.002712452534885871}}, "3": {"generate_text_restaurant": {"bleu": 11.409501258883944, "bleu_stderr": 0.200735926048327, "rouge1_fmeasure": 0.4385722344979268, "rouge1_fmeasure_stderr": 0.0023100736158786, "rouge1_precision": 0.47359150110281645, "rouge1_precision_stderr": 0.0035801720410154575, "rouge1_recall": 0.46852198178337934, "rouge1_recall_stderr": 0.0028471977217635184, "rouge2_fmeasure": 0.21297415730718317, "rouge2_fmeasure_stderr": 0.002002023485009685, "rouge2_precision": 0.23359678515529092, "rouge2_precision_stderr": 0.0026715948188736267, "rouge2_recall": 0.22730491424875773, "rouge2_recall_stderr": 0.002252917174717242, "rougeL_fmeasure": 0.33437569173005427, "rougeL_fmeasure_stderr": 0.0020107174748746504, "rougeL_precision": 0.36122582263536407, "rougeL_precision_stderr": 0.0030394944731669572, "rougeL_recall": 0.35939795651767675, "rougeL_recall_stderr": 0.002511542644538787, "rougeLsum_fmeasure": 0.36932279359236814, "rougeLsum_fmeasure_stderr": 0.0023179469576599027, "rougeLsum_precision": 0.3998844531789924, "rougeLsum_precision_stderr": 0.0033854020792017285, "rougeLsum_recall": 0.3938246920292058, "rougeLsum_recall_stderr": 0.002729767161367992}}, "4": {"generate_text_restaurant": {"bleu": 12.452122590183434, "bleu_stderr": 0.16404160542943327, "rouge1_fmeasure": 0.45315190664308314, "rouge1_fmeasure_stderr": 0.002278710461652685, "rouge1_precision": 0.49497236517824444, "rouge1_precision_stderr": 0.0035535658412753006, "rouge1_recall": 0.4725995896409827, "rouge1_recall_stderr": 0.0028157186492877196, "rouge2_fmeasure": 0.22316519517459477, "rouge2_fmeasure_stderr": 0.0020371724840063865, "rouge2_precision": 0.24812095038732754, "rouge2_precision_stderr": 0.0027737064203339212, "rouge2_recall": 0.2324345352491202, "rouge2_recall_stderr": 0.002259923232212951, "rougeL_fmeasure": 0.34240410488312567, "rougeL_fmeasure_stderr": 0.0020393007899216064, "rougeL_precision": 0.3745330183490656, "rougeL_precision_stderr": 0.0030718020025572107, "rougeL_recall": 0.3585821251012964, "rougeL_recall_stderr": 0.0024911676803155646, "rougeLsum_fmeasure": 0.38201002954999475, "rougeLsum_fmeasure_stderr": 0.002335148377240596, "rougeLsum_precision": 0.4179948014646539, "rougeLsum_precision_stderr": 0.0033899691757338438, "rougeLsum_recall": 0.3979598039322067, "rougeLsum_recall_stderr": 0.0027471446794053813}}, "5": {"generate_text_restaurant": {"bleu": 13.309002924662785, "bleu_stderr": 0.24361495936574476, "rouge1_fmeasure": 0.46337099933680953, "rouge1_fmeasure_stderr": 0.0022284128767927217, "rouge1_precision": 0.5055114743909561, "rouge1_precision_stderr": 0.0034029405989093315, "rouge1_recall": 0.47439394771123267, "rouge1_recall_stderr": 0.0027085795597238727, "rouge2_fmeasure": 0.22971317638516242, "rouge2_fmeasure_stderr": 0.0020276942034306005, "rouge2_precision": 0.2543085325831986, "rouge2_precision_stderr": 0.0026833318688377957, "rouge2_recall": 0.23498034253109115, "rouge2_recall_stderr": 0.0022102671857103136, "rougeL_fmeasure": 0.3493044245188954, "rougeL_fmeasure_stderr": 0.0020072603771810445, "rougeL_precision": 0.38203696819305627, "rougeL_precision_stderr": 0.0029643784309907667, "rougeL_recall": 0.35829625222003997, "rougeL_recall_stderr": 0.002388395524420644, "rougeLsum_fmeasure": 0.39422575829822615, "rougeLsum_fmeasure_stderr": 0.0022790324609071426, "rougeLsum_precision": 0.4307656306766157, "rougeLsum_precision_stderr": 0.003270545893660294, "rougeLsum_recall": 0.4032599450584402, "rougeLsum_recall_stderr": 0.0026395356242984963}}}, "gem_xsum": {"0": {"article_DOC_summary": {"bleu": 2.061265150562031, "bleu_stderr": 0.1047194903989246, "rouge1_fmeasure": 0.2118853569842521, "rouge1_fmeasure_stderr": 0.0024831762617585746, "rouge1_precision": 0.15448121328596862, "rouge1_precision_stderr": 0.001977188397188564, "rouge1_recall": 0.35997124440611034, "rouge1_recall_stderr": 0.004298205436694583, "rouge2_fmeasure": 0.05056562034464029, "rouge2_fmeasure_stderr": 0.001595549541223809, "rouge2_precision": 0.03645241402160218, "rouge2_precision_stderr": 0.0011752236536019232, "rouge2_recall": 0.08865405071591761, "rouge2_recall_stderr": 0.0029077149755190814, "rougeL_fmeasure": 0.161553829612935, "rougeL_fmeasure_stderr": 0.0019356026144079317, "rougeL_precision": 0.11766298156431257, "rougeL_precision_stderr": 0.00154525669786904, "rougeL_recall": 0.27589374122183485, "rougeL_recall_stderr": 0.0034812956688468695, "rougeLsum_fmeasure": 0.1685758842303753, "rougeLsum_fmeasure_stderr": 0.002177154066590156, "rougeLsum_precision": 0.12262950144266513, "rougeLsum_precision_stderr": 0.0016994024464092056, "rougeLsum_recall": 0.28822399594677356, "rougeLsum_recall_stderr": 0.003908951289350794}}, "1": {"article_DOC_summary": {"bleu": 1.4701047191488112, "bleu_stderr": 0.052325655561989, "rouge1_fmeasure": 0.17677552083071896, "rouge1_fmeasure_stderr": 0.0026150769110123255, "rouge1_precision": 0.12615666366329323, "rouge1_precision_stderr": 0.0019462075646106281, "rouge1_recall": 0.3075463314111142, "rouge1_recall_stderr": 0.004435681902516454, "rouge2_fmeasure": 0.036209551359239395, "rouge2_fmeasure_stderr": 0.001431805409098863, "rouge2_precision": 0.025631403863087567, "rouge2_precision_stderr": 0.0010195570539420784, "rouge2_recall": 0.0643057936335091, "rouge2_recall_stderr": 0.0025821054535310178, "rougeL_fmeasure": 0.1375227449624894, "rougeL_fmeasure_stderr": 0.0019568848326575864, "rougeL_precision": 0.09789606233860006, "rougeL_precision_stderr": 0.0014408570567453658, "rougeL_recall": 0.2409666745294604, "rougeL_recall_stderr": 0.0034493105763191037, "rougeLsum_fmeasure": 0.13906823791458356, "rougeLsum_fmeasure_stderr": 0.002145977759148375, "rougeLsum_precision": 0.09901294724556717, "rougeLsum_precision_stderr": 0.0015797250447342009, "rougeLsum_recall": 0.24365682374976821, "rougeLsum_recall_stderr": 0.0037520223325616334}}, "2": {"article_DOC_summary": {"bleu": 1.4983004480453936, "bleu_stderr": 0.08614156872925424, "rouge1_fmeasure": 0.17977482443218196, "rouge1_fmeasure_stderr": 0.0025982011983283434, "rouge1_precision": 0.12819697138408215, "rouge1_precision_stderr": 0.001923900850974331, "rouge1_recall": 0.3131959520911201, "rouge1_recall_stderr": 0.004483015545746866, "rouge2_fmeasure": 0.03935463682151496, "rouge2_fmeasure_stderr": 0.001450577987245735, "rouge2_precision": 0.02774216419058187, "rouge2_precision_stderr": 0.0010191913758900069, "rouge2_recall": 0.07049404002692027, "rouge2_recall_stderr": 0.002708125093624563, "rougeL_fmeasure": 0.14388467760513854, "rougeL_fmeasure_stderr": 0.0019644343349970836, "rougeL_precision": 0.10245043926274368, "rougeL_precision_stderr": 0.0014451803861143982, "rougeL_recall": 0.251818647068035, "rougeL_recall_stderr": 0.003494519863990314, "rougeLsum_fmeasure": 0.13992101774839874, "rougeLsum_fmeasure_stderr": 0.002118355649079576, "rougeLsum_precision": 0.09951049154417256, "rougeLsum_precision_stderr": 0.0015455068687096165, "rougeLsum_recall": 0.24565320812202304, "rougeLsum_recall_stderr": 0.0037974977466490017}}, "3": {"article_DOC_summary": {"bleu": 1.5436814601886297, "bleu_stderr": 0.10599321563006747, "rouge1_fmeasure": 0.1716640710662149, "rouge1_fmeasure_stderr": 0.002692661486106222, "rouge1_precision": 0.12507167063309826, "rouge1_precision_stderr": 0.0020654668780499437, "rouge1_recall": 0.29352230739872903, "rouge1_recall_stderr": 0.0046129265452261245, "rouge2_fmeasure": 0.0383031309264901, "rouge2_fmeasure_stderr": 0.001471824908387901, "rouge2_precision": 0.0273731792590075, "rouge2_precision_stderr": 0.001058152769608845, "rouge2_recall": 0.06719512443269011, "rouge2_recall_stderr": 0.002640278987747084, "rougeL_fmeasure": 0.1409323879677072, "rougeL_fmeasure_stderr": 0.00215402254496125, "rougeL_precision": 0.10247899612143699, "rougeL_precision_stderr": 0.0016344209712852228, "rougeL_recall": 0.24201656560824256, "rougeL_recall_stderr": 0.0037826395255217203, "rougeLsum_fmeasure": 0.13277160506058835, "rougeLsum_fmeasure_stderr": 0.002226502076197834, "rougeLsum_precision": 0.09654487009443463, "rougeLsum_precision_stderr": 0.0016852992800909113, "rougeLsum_recall": 0.2286055088707561, "rougeLsum_recall_stderr": 0.003922038940141684}}, "4": {"article_DOC_summary": {"bleu": 0.7915506170854982, "bleu_stderr": 0.13278546480806505, "rouge1_fmeasure": 0.04863969374523076, "rouge1_fmeasure_stderr": 0.002793420771992738, "rouge1_precision": 0.0429708507344084, "rouge1_precision_stderr": 0.0028037413845202774, "rouge1_recall": 0.07465376472309838, "rouge1_recall_stderr": 0.004321865151720348, "rouge2_fmeasure": 0.011395576090619692, "rouge2_fmeasure_stderr": 0.0010345794788431668, "rouge2_precision": 0.010519316602496626, "rouge2_precision_stderr": 0.001355747591263505, "rouge2_recall": 0.017499542584772765, "rouge2_recall_stderr": 0.0015490170099444409, "rougeL_fmeasure": 0.039590536804712924, "rougeL_fmeasure_stderr": 0.0022228567744426667, "rougeL_precision": 0.0356382053447805, "rougeL_precision_stderr": 0.002395385288173853, "rougeL_recall": 0.060770117722936286, "rougeL_recall_stderr": 0.0034770592750759917, "rougeLsum_fmeasure": 0.0387553178144167, "rougeLsum_fmeasure_stderr": 0.0022066400343704485, "rougeLsum_precision": 0.035133893923727386, "rougeLsum_precision_stderr": 0.0024011989607887903, "rougeLsum_recall": 0.059405756146875044, "rougeLsum_recall_stderr": 0.003457018339558158}}, "5": {"article_DOC_summary": {"bleu": 7.197738308121429e-37, "bleu_stderr": 1.5261190640932973e-32, "rouge1_fmeasure": 0.002544363512676877, "rouge1_fmeasure_stderr": 0.0007109896306856554, "rouge1_precision": 0.0028705257493446055, "rouge1_precision_stderr": 0.0008218246257449791, "rouge1_recall": 0.0023902360458122112, "rouge1_recall_stderr": 0.000665569783756533, "rouge2_fmeasure": 0.0002809498461785326, "rouge2_fmeasure_stderr": 0.00015434551667733464, "rouge2_precision": 0.00031292391170304596, "rouge2_precision_stderr": 0.00016477755162714296, "rouge2_recall": 0.0002616879975370542, "rouge2_recall_stderr": 0.00014932256088281653, "rougeL_fmeasure": 0.0018550844925242101, "rougeL_fmeasure_stderr": 0.0005069733094142548, "rougeL_precision": 0.0021053678911906607, "rougeL_precision_stderr": 0.0005892152083882312, "rougeL_recall": 0.0017230940880273344, "rougeL_recall_stderr": 0.0004664097240871752, "rougeLsum_fmeasure": 0.001872065671306264, "rougeLsum_fmeasure_stderr": 0.0005341865975835362, "rougeLsum_precision": 0.002095488296127936, "rougeLsum_precision_stderr": 0.00060247869960542, "rougeLsum_recall": 0.001758329007481808, "rougeLsum_recall_stderr": 0.0005034233459254993}}}}