Muennighoff's picture
add
874e9d6
{"GEM/web_nlg_en": {"0": {"PALM_prompt": {"bleu": 0.22204098721417106, "bleu_stderr": 0.019276471752656146, "rouge1_fmeasure": 0.09272599269459658, "rouge1_fmeasure_stderr": 0.0018590518272379513, "rouge1_precision": 0.06820251490843392, "rouge1_precision_stderr": 0.002190060212241753, "rouge1_recall": 0.25742366202222017, "rouge1_recall_stderr": 0.004587014099735057, "rouge2_fmeasure": 0.042390866327769255, "rouge2_fmeasure_stderr": 0.0011721275022206182, "rouge2_precision": 0.030382347547938747, "rouge2_precision_stderr": 0.001325563874148569, "rouge2_recall": 0.12261012110643013, "rouge2_recall_stderr": 0.0030851119576818537, "rougeL_fmeasure": 0.08932950738509532, "rougeL_fmeasure_stderr": 0.0017637231481500931, "rougeL_precision": 0.0655229598696475, "rougeL_precision_stderr": 0.002080691586971738, "rougeL_recall": 0.24940778219529192, "rougeL_recall_stderr": 0.0044712084663273656, "rougeLsum_fmeasure": 0.08891870581707897, "rougeLsum_fmeasure_stderr": 0.0017773392560572706, "rougeLsum_precision": 0.06546043938795817, "rougeLsum_precision_stderr": 0.0020997136591453837, "rougeLsum_recall": 0.24600249631927984, "rougeLsum_recall_stderr": 0.004352692280847939}}, "1": {"PALM_prompt": {"bleu": 0.25880473374348384, "bleu_stderr": 0.022230068330364686, "rouge1_fmeasure": 0.09643446439183856, "rouge1_fmeasure_stderr": 0.001635213100878619, "rouge1_precision": 0.06214341881820663, "rouge1_precision_stderr": 0.0013268401008494578, "rouge1_recall": 0.3135113767535378, "rouge1_recall_stderr": 0.00458178939874692, "rouge2_fmeasure": 0.041870012361671795, "rouge2_fmeasure_stderr": 0.0010268693299589505, "rouge2_precision": 0.02674356463710644, "rouge2_precision_stderr": 0.000737481517994496, "rouge2_recall": 0.14093192923216838, "rouge2_recall_stderr": 0.0032013598582039324, "rougeL_fmeasure": 0.09109909484371144, "rougeL_fmeasure_stderr": 0.0015136902913600147, "rougeL_precision": 0.05869062523386566, "rougeL_precision_stderr": 0.001232443361569347, "rougeL_recall": 0.29394344095445063, "rougeL_recall_stderr": 0.00415545522823885, "rougeLsum_fmeasure": 0.09174686199983531, "rougeLsum_fmeasure_stderr": 0.001563500626588612, "rougeLsum_precision": 0.059171371743465595, "rougeLsum_precision_stderr": 0.0012667656393651446, "rougeLsum_recall": 0.29594185127017286, "rougeLsum_recall_stderr": 0.004253909411887421}}, "2": {"PALM_prompt": {"bleu": 0.2393211634348198, "bleu_stderr": 0.01363669405478336, "rouge1_fmeasure": 0.10019776051129047, "rouge1_fmeasure_stderr": 0.0015641268465643656, "rouge1_precision": 0.06396404705288909, "rouge1_precision_stderr": 0.0012415127715507308, "rouge1_recall": 0.3308127933726733, "rouge1_recall_stderr": 0.004519408234935246, "rouge2_fmeasure": 0.0442123599073847, "rouge2_fmeasure_stderr": 0.0010188311958202613, "rouge2_precision": 0.027899740610515332, "rouge2_precision_stderr": 0.0006982208286358861, "rouge2_recall": 0.15212186881504658, "rouge2_recall_stderr": 0.003314382112140982, "rougeL_fmeasure": 0.09482597060278779, "rougeL_fmeasure_stderr": 0.001496417811381322, "rougeL_precision": 0.06060643664395082, "rougeL_precision_stderr": 0.0011924899257110728, "rougeL_recall": 0.30932951543387055, "rougeL_recall_stderr": 0.004117777342615909, "rougeLsum_fmeasure": 0.09538295932329842, "rougeLsum_fmeasure_stderr": 0.0015081325735113629, "rougeLsum_precision": 0.06098395243273801, "rougeLsum_precision_stderr": 0.00120587247949826, "rougeLsum_recall": 0.3126700598012332, "rougeLsum_recall_stderr": 0.004231041528425012}}, "3": {"PALM_prompt": {"bleu": 0.243608179278288, "bleu_stderr": 0.01921722985124698, "rouge1_fmeasure": 0.09887552684011731, "rouge1_fmeasure_stderr": 0.0015126137448436914, "rouge1_precision": 0.062980698929312, "rouge1_precision_stderr": 0.0011560253524235528, "rouge1_recall": 0.3288064857402774, "rouge1_recall_stderr": 0.004505392650319931, "rouge2_fmeasure": 0.0434234299139644, "rouge2_fmeasure_stderr": 0.0009855133640151285, "rouge2_precision": 0.027407819373253286, "rouge2_precision_stderr": 0.0006726911526596678, "rouge2_recall": 0.150297514784057, "rouge2_recall_stderr": 0.003274692419504138, "rougeL_fmeasure": 0.09341700412367017, "rougeL_fmeasure_stderr": 0.0014444126215400555, "rougeL_precision": 0.059596838466450426, "rougeL_precision_stderr": 0.0011093406220706668, "rougeL_recall": 0.306836904711071, "rougeL_recall_stderr": 0.004050333621376925, "rougeLsum_fmeasure": 0.09367292323129742, "rougeLsum_fmeasure_stderr": 0.0014561404525753052, "rougeLsum_precision": 0.05978294287172372, "rougeLsum_precision_stderr": 0.001121549451045076, "rougeLsum_recall": 0.30945198315857647, "rougeLsum_recall_stderr": 0.004192482621686769}}, "4": {"PALM_prompt": {"bleu": 0.25469357669489284, "bleu_stderr": 0.011466160062729863, "rouge1_fmeasure": 0.09795089624013498, "rouge1_fmeasure_stderr": 0.0014752280354659194, "rouge1_precision": 0.0618631317942507, "rouge1_precision_stderr": 0.0010684577667011714, "rouge1_recall": 0.33031516255704996, "rouge1_recall_stderr": 0.004399762238385151, "rouge2_fmeasure": 0.04294545093994066, "rouge2_fmeasure_stderr": 0.0009854861914153005, "rouge2_precision": 0.027036694891327876, "rouge2_precision_stderr": 0.0006786696012703407, "rouge2_recall": 0.15178907375981374, "rouge2_recall_stderr": 0.003288934014065152, "rougeL_fmeasure": 0.09211011957516096, "rougeL_fmeasure_stderr": 0.001398164268402593, "rougeL_precision": 0.05822193754327873, "rougeL_precision_stderr": 0.0010062882040799146, "rougeL_recall": 0.30722086755336825, "rougeL_recall_stderr": 0.003999854761029724, "rougeLsum_fmeasure": 0.09272177672229581, "rougeLsum_fmeasure_stderr": 0.0014198657894469043, "rougeLsum_precision": 0.05863541881600006, "rougeLsum_precision_stderr": 0.0010285435974866594, "rougeLsum_recall": 0.311207211038314, "rougeLsum_recall_stderr": 0.004149397236544474}}, "5": {"PALM_prompt": {"bleu": 0.27691748608386685, "bleu_stderr": 0.015995640879981433, "rouge1_fmeasure": 0.09966142593776975, "rouge1_fmeasure_stderr": 0.0015048267603198495, "rouge1_precision": 0.06333942991310233, "rouge1_precision_stderr": 0.0011418940547432666, "rouge1_recall": 0.33995921756306285, "rouge1_recall_stderr": 0.004570773434235893, "rouge2_fmeasure": 0.04376537150499012, "rouge2_fmeasure_stderr": 0.0009904740735743225, "rouge2_precision": 0.027828991184201318, "rouge2_precision_stderr": 0.0007370699493229402, "rouge2_recall": 0.157965010733975, "rouge2_recall_stderr": 0.0034128601041511788, "rougeL_fmeasure": 0.09322044185116359, "rougeL_fmeasure_stderr": 0.001419900452172381, "rougeL_precision": 0.05930484617559427, "rougeL_precision_stderr": 0.0010763533312005465, "rougeL_recall": 0.31478838303060996, "rougeL_recall_stderr": 0.0040748760184059095, "rougeLsum_fmeasure": 0.09406629606753775, "rougeLsum_fmeasure_stderr": 0.0014505030819857486, "rougeLsum_precision": 0.05988402399317189, "rougeLsum_precision_stderr": 0.00110394812941426, "rougeLsum_recall": 0.318861682237468, "rougeLsum_recall_stderr": 0.004260180788352995}}}, "GEM/wiki_lingua_en": {"0": {"tldr_en": {"bleu": 2.0100258380996974, "bleu_stderr": 0.0674022567626575, "rouge1_fmeasure": 0.19385094273584189, "rouge1_fmeasure_stderr": 0.0018734321553455435, "rouge1_precision": 0.25651192180982535, "rouge1_precision_stderr": 0.003192972495667753, "rouge1_recall": 0.20357772346957254, "rouge1_recall_stderr": 0.0023691616330909597, "rouge2_fmeasure": 0.04574418632670163, "rouge2_fmeasure_stderr": 0.0010606792659231751, "rouge2_precision": 0.06420952629747662, "rouge2_precision_stderr": 0.001740233787620321, "rouge2_recall": 0.047450925035940276, "rouge2_recall_stderr": 0.0012113003608532503, "rougeL_fmeasure": 0.1499328780471304, "rougeL_fmeasure_stderr": 0.001400672965008572, "rougeL_precision": 0.19726470520185704, "rougeL_precision_stderr": 0.0024528871041994624, "rougeL_recall": 0.16082448423507495, "rougeL_recall_stderr": 0.001966818166827273, "rougeLsum_fmeasure": 0.17673375098232452, "rougeLsum_fmeasure_stderr": 0.0017035096350846192, "rougeLsum_precision": 0.23420349604678764, "rougeLsum_precision_stderr": 0.0029548325984343165, "rougeLsum_recall": 0.18605497488128228, "rougeLsum_recall_stderr": 0.0021889242967748847}}, "1": {"tldr_en": {"bleu": 2.392561814823777, "bleu_stderr": 0.07977645879697982, "rouge1_fmeasure": 0.19931763117357115, "rouge1_fmeasure_stderr": 0.001945244446261509, "rouge1_precision": 0.1832806657725769, "rouge1_precision_stderr": 0.0022864849006174414, "rouge1_recall": 0.2760499152437474, "rouge1_recall_stderr": 0.0027906827578709965, "rouge2_fmeasure": 0.04634772469936709, "rouge2_fmeasure_stderr": 0.0009880438967203185, "rouge2_precision": 0.042864302547953495, "rouge2_precision_stderr": 0.0010382312713116135, "rouge2_recall": 0.06566259704146062, "rouge2_recall_stderr": 0.0015296383795616662, "rougeL_fmeasure": 0.15122902314638473, "rougeL_fmeasure_stderr": 0.001408286752664184, "rougeL_precision": 0.13829619261763815, "rougeL_precision_stderr": 0.001685146390575834, "rougeL_recall": 0.21335700851041559, "rougeL_recall_stderr": 0.002244699382433614, "rougeLsum_fmeasure": 0.18570473072648863, "rougeLsum_fmeasure_stderr": 0.001801755228182078, "rougeLsum_precision": 0.17024489241466956, "rougeLsum_precision_stderr": 0.0020971881120686714, "rougeLsum_recall": 0.25820281039954457, "rougeLsum_recall_stderr": 0.0026331458494637293}}, "2": {"tldr_en": {"bleu": 2.452807488568222, "bleu_stderr": 0.056772783511996223, "rouge1_fmeasure": 0.1969213032776396, "rouge1_fmeasure_stderr": 0.0018927715762374123, "rouge1_precision": 0.18658303000344464, "rouge1_precision_stderr": 0.0024876714053664274, "rouge1_recall": 0.27019881592687406, "rouge1_recall_stderr": 0.0026813520985447185, "rouge2_fmeasure": 0.047336520137594484, "rouge2_fmeasure_stderr": 0.0009975613687996322, "rouge2_precision": 0.04585837942410683, "rouge2_precision_stderr": 0.0012627882437097654, "rouge2_recall": 0.06669830168816451, "rouge2_recall_stderr": 0.0015544563167823285, "rougeL_fmeasure": 0.14984157905412343, "rougeL_fmeasure_stderr": 0.001384998326347373, "rougeL_precision": 0.14164805980896447, "rougeL_precision_stderr": 0.0019186508467200377, "rougeL_recall": 0.2094675937761492, "rougeL_recall_stderr": 0.0021888415122521816, "rougeLsum_fmeasure": 0.1855042522850078, "rougeLsum_fmeasure_stderr": 0.0017868572908967936, "rougeLsum_precision": 0.1756013058241241, "rougeLsum_precision_stderr": 0.002345692194645983, "rougeLsum_recall": 0.25502572497532877, "rougeLsum_recall_stderr": 0.0025581605724038533}}, "3": {"tldr_en": {"bleu": 2.3426316146495734, "bleu_stderr": 0.0439248655852764, "rouge1_fmeasure": 0.16195665855465097, "rouge1_fmeasure_stderr": 0.002126427240081878, "rouge1_precision": 0.1712191795054323, "rouge1_precision_stderr": 0.003038214672650368, "rouge1_recall": 0.21594272856412056, "rouge1_recall_stderr": 0.0029979902476676957, "rouge2_fmeasure": 0.038847945393607336, "rouge2_fmeasure_stderr": 0.0009699218713344052, "rouge2_precision": 0.043337478446606736, "rouge2_precision_stderr": 0.0015646025243393384, "rouge2_recall": 0.05272569311320727, "rouge2_recall_stderr": 0.0014308065987711665, "rougeL_fmeasure": 0.12668361341610393, "rougeL_fmeasure_stderr": 0.0016364005437627088, "rougeL_precision": 0.13477870000014985, "rougeL_precision_stderr": 0.002474163264356179, "rougeL_recall": 0.1715923829723219, "rougeL_recall_stderr": 0.0024813856340995004, "rougeLsum_fmeasure": 0.15244532922301532, "rougeLsum_fmeasure_stderr": 0.0020042096241630436, "rougeLsum_precision": 0.16132070178480015, "rougeLsum_precision_stderr": 0.002889049855019625, "rougeLsum_recall": 0.20369696779143018, "rougeLsum_recall_stderr": 0.0028511803322345593}}, "4": {"tldr_en": {"bleu": 0.46325058906967104, "bleu_stderr": 0.04394833473134342, "rouge1_fmeasure": 0.051850966703194105, "rouge1_fmeasure_stderr": 0.0017980034364511734, "rouge1_precision": 0.05434591954905995, "rouge1_precision_stderr": 0.0021847405372553605, "rouge1_recall": 0.07154232786489559, "rouge1_recall_stderr": 0.002552618714453584, "rouge2_fmeasure": 0.01196468137957872, "rouge2_fmeasure_stderr": 0.0006216794386212632, "rouge2_precision": 0.013226099262045241, "rouge2_precision_stderr": 0.0009553602465401015, "rouge2_recall": 0.016794098875315702, "rouge2_recall_stderr": 0.0009699062116909224, "rougeL_fmeasure": 0.041527610533888815, "rougeL_fmeasure_stderr": 0.0014192023498900395, "rougeL_precision": 0.0438894122566985, "rougeL_precision_stderr": 0.001809708974625631, "rougeL_recall": 0.05823718911066025, "rougeL_recall_stderr": 0.002100306312673548, "rougeLsum_fmeasure": 0.04825192438978647, "rougeLsum_fmeasure_stderr": 0.0016770907170266002, "rougeLsum_precision": 0.050554768509393916, "rougeLsum_precision_stderr": 0.0020358754740706737, "rougeLsum_recall": 0.06670686746113656, "rougeLsum_recall_stderr": 0.002385990683849173}}, "5": {"tldr_en": {"bleu": 4.640112083495465e-07, "bleu_stderr": 1.5431563465623618e-06, "rouge1_fmeasure": 0.008085930973912187, "rouge1_fmeasure_stderr": 0.0007985116489437549, "rouge1_precision": 0.009514066687016848, "rouge1_precision_stderr": 0.001067782554791176, "rouge1_recall": 0.011132895953260013, "rouge1_recall_stderr": 0.0011413042455003578, "rouge2_fmeasure": 0.0020681545360381353, "rouge2_fmeasure_stderr": 0.0002778512622888749, "rouge2_precision": 0.0023322419546531734, "rouge2_precision_stderr": 0.00036373848096836806, "rouge2_recall": 0.0028701617257718094, "rouge2_recall_stderr": 0.00041073131285513086, "rougeL_fmeasure": 0.006753057844270136, "rougeL_fmeasure_stderr": 0.0006651646656046084, "rougeL_precision": 0.0079253371886185, "rougeL_precision_stderr": 0.0008863361667157557, "rougeL_recall": 0.009444647497914755, "rougeL_recall_stderr": 0.0009737316805276728, "rougeLsum_fmeasure": 0.0075115368315263375, "rougeLsum_fmeasure_stderr": 0.0007399413407804182, "rougeLsum_precision": 0.008884949331955178, "rougeLsum_precision_stderr": 0.0010015037010511325, "rougeLsum_recall": 0.010374918054262423, "rougeLsum_recall_stderr": 0.0010639082781916257}}}, "e2e_nlg_cleaned": {"0": {"generate_text_restaurant": {"bleu": 0.031874114175317256, "bleu_stderr": 0.010171142927754676, "rouge1_fmeasure": 0.022124583705193844, "rouge1_fmeasure_stderr": 0.00036956425521588213, "rouge1_precision": 0.017545253401039712, "rouge1_precision_stderr": 0.00028792788382849986, "rouge1_recall": 0.03224991125246636, "rouge1_recall_stderr": 0.0006691659270283856, "rouge2_fmeasure": 0.00048158693587850804, "rouge2_fmeasure_stderr": 8.404098395691825e-05, "rouge2_precision": 0.0003495986728970281, "rouge2_precision_stderr": 5.779816447438854e-05, "rouge2_recall": 0.0010919542924479517, "rouge2_recall_stderr": 0.0002443585246885973, "rougeL_fmeasure": 0.022053088959275772, "rougeL_fmeasure_stderr": 0.0003635452130640162, "rougeL_precision": 0.017499438105224415, "rougeL_precision_stderr": 0.00028502529390385904, "rougeL_recall": 0.03207245553588021, "rougeL_recall_stderr": 0.0006429178645877136, "rougeLsum_fmeasure": 0.021427620501656582, "rougeLsum_fmeasure_stderr": 0.0003490917593949496, "rougeLsum_precision": 0.01700676749670014, "rougeLsum_precision_stderr": 0.00027291681347983634, "rougeLsum_recall": 0.031151140783532406, "rougeLsum_recall_stderr": 0.0006286186845858172}}, "1": {"generate_text_restaurant": {"bleu": 7.737358427670204, "bleu_stderr": 0.1243933496267232, "rouge1_fmeasure": 0.2982415216184366, "rouge1_fmeasure_stderr": 0.003402861463823545, "rouge1_precision": 0.3303482508129036, "rouge1_precision_stderr": 0.004440163349073445, "rouge1_recall": 0.3252539839727599, "rouge1_recall_stderr": 0.003814116806429878, "rouge2_fmeasure": 0.1287446057253648, "rouge2_fmeasure_stderr": 0.0019282079780495018, "rouge2_precision": 0.14675546347951623, "rouge2_precision_stderr": 0.002567769311283733, "rouge2_recall": 0.13970698533556994, "rouge2_recall_stderr": 0.0021123811965536037, "rougeL_fmeasure": 0.22504111631632312, "rougeL_fmeasure_stderr": 0.0026067461379662925, "rougeL_precision": 0.2492259309197243, "rougeL_precision_stderr": 0.003483833443082128, "rougeL_recall": 0.24879844217888228, "rougeL_recall_stderr": 0.0030613005635074025, "rougeLsum_fmeasure": 0.2462918200995963, "rougeLsum_fmeasure_stderr": 0.0029579425607837257, "rougeLsum_precision": 0.27419248466368723, "rougeLsum_precision_stderr": 0.0038935555426153922, "rougeLsum_recall": 0.26840230492426825, "rougeLsum_recall_stderr": 0.003302765893096686}}, "2": {"generate_text_restaurant": {"bleu": 10.737431361718642, "bleu_stderr": 0.1840461783170779, "rouge1_fmeasure": 0.4169610393873498, "rouge1_fmeasure_stderr": 0.002550547874706905, "rouge1_precision": 0.49365022153101235, "rouge1_precision_stderr": 0.0035924604156869753, "rouge1_recall": 0.3943238796851301, "rouge1_recall_stderr": 0.00285119833026193, "rouge2_fmeasure": 0.19209651090505914, "rouge2_fmeasure_stderr": 0.0018932924526699846, "rouge2_precision": 0.23198787557606496, "rouge2_precision_stderr": 0.0025803167708078624, "rouge2_recall": 0.18103974060112446, "rouge2_recall_stderr": 0.0019507270271193976, "rougeL_fmeasure": 0.3003646464315608, "rougeL_fmeasure_stderr": 0.002147812998687083, "rougeL_precision": 0.3569435172400186, "rougeL_precision_stderr": 0.0030114499355725567, "rougeL_recall": 0.28404210746426684, "rougeL_recall_stderr": 0.002343573650216374, "rougeLsum_fmeasure": 0.34152808513161503, "rougeLsum_fmeasure_stderr": 0.0024071259364484105, "rougeLsum_precision": 0.4049223281787623, "rougeLsum_precision_stderr": 0.0033015148654210215, "rougeLsum_recall": 0.32285607750650375, "rougeLsum_recall_stderr": 0.002617503891745774}}, "3": {"generate_text_restaurant": {"bleu": 11.4082068329818, "bleu_stderr": 0.142512181823551, "rouge1_fmeasure": 0.43069192761108827, "rouge1_fmeasure_stderr": 0.002242039646042106, "rouge1_precision": 0.49391410564237026, "rouge1_precision_stderr": 0.0031606251790800345, "rouge1_recall": 0.4164073628205088, "rouge1_recall_stderr": 0.0026436925367264645, "rouge2_fmeasure": 0.1995155823140774, "rouge2_fmeasure_stderr": 0.0017793514446650905, "rouge2_precision": 0.2316111839932525, "rouge2_precision_stderr": 0.0023291413473663794, "rouge2_recall": 0.19315156556103064, "rouge2_recall_stderr": 0.0019041220133729187, "rougeL_fmeasure": 0.30690972652365295, "rougeL_fmeasure_stderr": 0.001956883803972393, "rougeL_precision": 0.352593695647614, "rougeL_precision_stderr": 0.002672099362907755, "rougeL_recall": 0.29730417788475555, "rougeL_recall_stderr": 0.0022474238332051435, "rougeLsum_fmeasure": 0.35340308240207713, "rougeLsum_fmeasure_stderr": 0.0022064062987118514, "rougeLsum_precision": 0.40550546783502256, "rougeLsum_precision_stderr": 0.002971401018763629, "rougeLsum_recall": 0.34184803538326775, "rougeLsum_recall_stderr": 0.0025000251883836966}}, "4": {"generate_text_restaurant": {"bleu": 11.707232989983671, "bleu_stderr": 0.17661551434958267, "rouge1_fmeasure": 0.43774619363724493, "rouge1_fmeasure_stderr": 0.0022078065365727408, "rouge1_precision": 0.49191044586738897, "rouge1_precision_stderr": 0.0031676988687248716, "rouge1_recall": 0.42940462402628954, "rouge1_recall_stderr": 0.0025318789423904153, "rouge2_fmeasure": 0.20646929898842112, "rouge2_fmeasure_stderr": 0.001855942831151773, "rouge2_precision": 0.23481349186140105, "rouge2_precision_stderr": 0.002405102538732441, "rouge2_recall": 0.20247145154375798, "rouge2_recall_stderr": 0.0019512616857138931, "rougeL_fmeasure": 0.3110076149641713, "rougeL_fmeasure_stderr": 0.0019640475619955044, "rougeL_precision": 0.34991350305657065, "rougeL_precision_stderr": 0.0026529488521832055, "rougeL_recall": 0.3057344606254107, "rougeL_recall_stderr": 0.0022280275675345567, "rougeLsum_fmeasure": 0.36109285519013123, "rougeLsum_fmeasure_stderr": 0.0022203743270438657, "rougeLsum_precision": 0.40569251366101383, "rougeLsum_precision_stderr": 0.0029768033739560984, "rougeLsum_recall": 0.3545497566857269, "rougeLsum_recall_stderr": 0.002478271667408176}}, "5": {"generate_text_restaurant": {"bleu": 11.489373682406253, "bleu_stderr": 0.17141746796170906, "rouge1_fmeasure": 0.43875472562966367, "rouge1_fmeasure_stderr": 0.0021511490849131696, "rouge1_precision": 0.4876723311930106, "rouge1_precision_stderr": 0.0030908538424086027, "rouge1_recall": 0.4341015013755213, "rouge1_recall_stderr": 0.002472410405872386, "rouge2_fmeasure": 0.20658901163688556, "rouge2_fmeasure_stderr": 0.0018165244743158018, "rouge2_precision": 0.2317802523884936, "rouge2_precision_stderr": 0.002284619076384955, "rouge2_recall": 0.20455605618591285, "rouge2_recall_stderr": 0.0019381468734008763, "rougeL_fmeasure": 0.3129127738356323, "rougeL_fmeasure_stderr": 0.0019396222893964643, "rougeL_precision": 0.34779027753914094, "rougeL_precision_stderr": 0.0025891057009048155, "rougeL_recall": 0.3103942740748508, "rougeL_recall_stderr": 0.002197454196068641, "rougeLsum_fmeasure": 0.3640325781149561, "rougeLsum_fmeasure_stderr": 0.002166499889117764, "rougeLsum_precision": 0.4045964151245668, "rougeLsum_precision_stderr": 0.0029122909102775136, "rougeLsum_recall": 0.3604153721054145, "rougeLsum_recall_stderr": 0.0024126106691738933}}}, "gem_xsum": {"0": {"article_DOC_summary": {"bleu": 1.8238656017720316, "bleu_stderr": 0.11417874874518819, "rouge1_fmeasure": 0.2115037779557331, "rouge1_fmeasure_stderr": 0.0028708356319735403, "rouge1_precision": 0.19599022622919288, "rouge1_precision_stderr": 0.0037030385836724893, "rouge1_recall": 0.2861530231773622, "rouge1_recall_stderr": 0.003941267645126222, "rouge2_fmeasure": 0.04699868432114206, "rouge2_fmeasure_stderr": 0.0017963663608593714, "rouge2_precision": 0.044477067311530366, "rouge2_precision_stderr": 0.0020008129573715143, "rouge2_recall": 0.06406773338735594, "rouge2_recall_stderr": 0.0024117378864816396, "rougeL_fmeasure": 0.16453401073456989, "rougeL_fmeasure_stderr": 0.0022184571170325022, "rougeL_precision": 0.15186229565287584, "rougeL_precision_stderr": 0.0029105652073766115, "rougeL_recall": 0.22489116709301912, "rougeL_recall_stderr": 0.0031573122472656817, "rougeLsum_fmeasure": 0.16554740239348353, "rougeLsum_fmeasure_stderr": 0.002374759567244112, "rougeLsum_precision": 0.1528519438724928, "rougeLsum_precision_stderr": 0.002997447293380263, "rougeLsum_recall": 0.22620973381223455, "rougeLsum_recall_stderr": 0.0034392051661351728}}, "1": {"article_DOC_summary": {"bleu": 0.9747140690123636, "bleu_stderr": 0.0642358033439856, "rouge1_fmeasure": 0.15005596547876693, "rouge1_fmeasure_stderr": 0.002071165806251677, "rouge1_precision": 0.1067178954813291, "rouge1_precision_stderr": 0.0015516479652769894, "rouge1_recall": 0.26403082472972045, "rouge1_recall_stderr": 0.003555653171535274, "rouge2_fmeasure": 0.02533409267704932, "rouge2_fmeasure_stderr": 0.0011068107209084722, "rouge2_precision": 0.017884102754992467, "rouge2_precision_stderr": 0.0007887495767181257, "rouge2_recall": 0.045633898350588745, "rouge2_recall_stderr": 0.002034227387675855, "rougeL_fmeasure": 0.12408271977812946, "rougeL_fmeasure_stderr": 0.001645794664454338, "rougeL_precision": 0.08813953720222902, "rougeL_precision_stderr": 0.001229451916286059, "rougeL_recall": 0.21930141086357025, "rougeL_recall_stderr": 0.002905453096641788, "rougeLsum_fmeasure": 0.12164431804549597, "rougeLsum_fmeasure_stderr": 0.0017110047786898439, "rougeLsum_precision": 0.08633662512896348, "rougeLsum_precision_stderr": 0.0012650237494816706, "rougeLsum_recall": 0.2152882772755343, "rougeLsum_recall_stderr": 0.00305512470858241}}, "2": {"article_DOC_summary": {"bleu": 0.9401612768042149, "bleu_stderr": 0.1074455998844054, "rouge1_fmeasure": 0.15200328621945966, "rouge1_fmeasure_stderr": 0.0021192244614926707, "rouge1_precision": 0.10784352462470646, "rouge1_precision_stderr": 0.0015844911919418766, "rouge1_recall": 0.2687388222162725, "rouge1_recall_stderr": 0.0035981608161430173, "rouge2_fmeasure": 0.025186582345938593, "rouge2_fmeasure_stderr": 0.0011237236219662, "rouge2_precision": 0.017674494926331812, "rouge2_precision_stderr": 0.0007971251244866095, "rouge2_recall": 0.045841886107298564, "rouge2_recall_stderr": 0.0020630782658520534, "rougeL_fmeasure": 0.12383654399920942, "rougeL_fmeasure_stderr": 0.001641932196115614, "rougeL_precision": 0.08767693212115871, "rougeL_precision_stderr": 0.0012160969233920977, "rougeL_recall": 0.22039385453118615, "rougeL_recall_stderr": 0.0029258322855856026, "rougeLsum_fmeasure": 0.12224943632952648, "rougeLsum_fmeasure_stderr": 0.0017620521946679973, "rougeLsum_precision": 0.0864448548753018, "rougeLsum_precision_stderr": 0.00129205793013278, "rougeLsum_recall": 0.21809724460625138, "rougeLsum_recall_stderr": 0.0031601296858344507}}, "3": {"article_DOC_summary": {"bleu": 0.9125964196948344, "bleu_stderr": 0.10349173283625816, "rouge1_fmeasure": 0.14506936890630495, "rouge1_fmeasure_stderr": 0.0022063232406169886, "rouge1_precision": 0.10569745681885233, "rouge1_precision_stderr": 0.0017941734641519266, "rouge1_recall": 0.2519938015127494, "rouge1_recall_stderr": 0.0037721439503976993, "rouge2_fmeasure": 0.0225123744327698, "rouge2_fmeasure_stderr": 0.001084899914540765, "rouge2_precision": 0.015999530326390468, "rouge2_precision_stderr": 0.0007765584487915138, "rouge2_recall": 0.04013315577622923, "rouge2_recall_stderr": 0.0019767396265527814, "rougeL_fmeasure": 0.11724826856832718, "rougeL_fmeasure_stderr": 0.0017442334878808967, "rougeL_precision": 0.08510288769980345, "rougeL_precision_stderr": 0.0013767353191387142, "rougeL_recall": 0.20461589082692738, "rougeL_recall_stderr": 0.0030742843754535247, "rougeLsum_fmeasure": 0.11714990152091816, "rougeLsum_fmeasure_stderr": 0.0017785202734303676, "rougeLsum_precision": 0.08500816119826558, "rougeLsum_precision_stderr": 0.0014080250249809561, "rougeLsum_recall": 0.20504113450222913, "rougeLsum_recall_stderr": 0.003166332666730022}}, "4": {"article_DOC_summary": {"bleu": 0.4004545229183726, "bleu_stderr": 0.08129464687265989, "rouge1_fmeasure": 0.039654325712056133, "rouge1_fmeasure_stderr": 0.002234452499892727, "rouge1_precision": 0.033034216443160166, "rouge1_precision_stderr": 0.002074390859917468, "rouge1_recall": 0.06271783703292752, "rouge1_recall_stderr": 0.003573320090796846, "rouge2_fmeasure": 0.006259157201220947, "rouge2_fmeasure_stderr": 0.0006549749685708337, "rouge2_precision": 0.005074909700736775, "rouge2_precision_stderr": 0.0007063210979306593, "rouge2_recall": 0.010211453988348025, "rouge2_recall_stderr": 0.0010169331590412585, "rougeL_fmeasure": 0.03198404880635416, "rougeL_fmeasure_stderr": 0.0017885954434438646, "rougeL_precision": 0.02698019690632726, "rougeL_precision_stderr": 0.001735469551896778, "rougeL_recall": 0.0505890303269132, "rougeL_recall_stderr": 0.002868677868848106, "rougeLsum_fmeasure": 0.03247909430999598, "rougeLsum_fmeasure_stderr": 0.0018403462507897797, "rougeLsum_precision": 0.027364283781476182, "rougeLsum_precision_stderr": 0.0017692800720310882, "rougeLsum_recall": 0.05145529104280362, "rougeLsum_recall_stderr": 0.0029602910561950676}}, "5": {"article_DOC_summary": {"bleu": 2.0249070835054943e-38, "bleu_stderr": 1.650192313769112e-32, "rouge1_fmeasure": 0.002787387532539503, "rouge1_fmeasure_stderr": 0.0007477665092571439, "rouge1_precision": 0.0030925566489121603, "rouge1_precision_stderr": 0.0008374202700281003, "rouge1_recall": 0.0026371746057504163, "rouge1_recall_stderr": 0.0007099212047178582, "rouge2_fmeasure": 0.00027951734814181563, "rouge2_fmeasure_stderr": 0.00011491010308294642, "rouge2_precision": 0.00031607697395710717, "rouge2_precision_stderr": 0.00012896679692374585, "rouge2_recall": 0.0002549614647283903, "rouge2_recall_stderr": 0.00010630638416646696, "rougeL_fmeasure": 0.0020488019643628854, "rougeL_fmeasure_stderr": 0.0005409426244889383, "rougeL_precision": 0.0022533221106443837, "rougeL_precision_stderr": 0.0005999121151851048, "rougeL_recall": 0.0019575361351732187, "rougeL_recall_stderr": 0.0005190510508041254, "rougeLsum_fmeasure": 0.0021661160507683614, "rougeLsum_fmeasure_stderr": 0.0005768959780508152, "rougeLsum_precision": 0.00239655595619729, "rougeLsum_precision_stderr": 0.0006492429312486155, "rougeLsum_recall": 0.002057857182439318, "rougeLsum_recall_stderr": 0.0005462897641703679}}}}