| {"GEM/web_nlg_en": {"0": {"PALM_prompt": {"bleu": 0.31606716251794437, "bleu_stderr": 0.02563944351471059, "rouge1_fmeasure": 0.10246108718545202, "rouge1_fmeasure_stderr": 0.0017992092481067788, "rouge1_precision": 0.06664761750887295, "rouge1_precision_stderr": 0.0013732959148702218, "rouge1_recall": 0.2940457093239289, "rouge1_recall_stderr": 0.004555499438691762, "rouge2_fmeasure": 0.04746695901782121, "rouge2_fmeasure_stderr": 0.0011129470648980045, "rouge2_precision": 0.030425492420252335, "rouge2_precision_stderr": 0.0007598510657945697, "rouge2_recall": 0.1409722690208349, "rouge2_recall_stderr": 0.0031027610869315144, "rougeL_fmeasure": 0.09860897831373452, "rougeL_fmeasure_stderr": 0.00170202692564, "rougeL_precision": 0.06400114097684483, "rougeL_precision_stderr": 0.0012983914696295615, "rougeL_recall": 0.2849573873935468, "rougeL_recall_stderr": 0.004452046846530438, "rougeLsum_fmeasure": 0.09784615421581211, "rougeLsum_fmeasure_stderr": 0.001694890791053129, "rougeLsum_precision": 0.06366499205115346, "rougeLsum_precision_stderr": 0.0013067510671992333, "rougeLsum_recall": 0.281020892101209, "rougeLsum_recall_stderr": 0.004305691903165883}}, "1": {"PALM_prompt": {"bleu": 0.4594356029919803, "bleu_stderr": 0.025125558903473632, "rouge1_fmeasure": 0.10986827089930207, "rouge1_fmeasure_stderr": 0.0017427056384300328, "rouge1_precision": 0.07027188536501679, "rouge1_precision_stderr": 0.0012558026173472138, "rouge1_recall": 0.3450765288308058, "rouge1_recall_stderr": 0.005055990718374951, "rouge2_fmeasure": 0.052665704185835084, "rouge2_fmeasure_stderr": 0.001116219363919427, "rouge2_precision": 0.03347891417115085, "rouge2_precision_stderr": 0.0007753123397897254, "rouge2_recall": 0.1749435024767411, "rouge2_recall_stderr": 0.0036147215578007344, "rougeL_fmeasure": 0.10429693361721804, "rougeL_fmeasure_stderr": 0.0016079944655777501, "rougeL_precision": 0.06659999496172114, "rougeL_precision_stderr": 0.001145948530216064, "rougeL_recall": 0.32753689197885233, "rougeL_recall_stderr": 0.004724892115185279, "rougeLsum_fmeasure": 0.10453836123127251, "rougeLsum_fmeasure_stderr": 0.0016341468252465234, "rougeLsum_precision": 0.06687788385741289, "rougeLsum_precision_stderr": 0.0011787909083336645, "rougeLsum_recall": 0.32738351484636163, "rougeLsum_recall_stderr": 0.004663465991453483}}, "2": {"PALM_prompt": {"bleu": 0.4626917691641033, "bleu_stderr": 0.026701626014007735, "rouge1_fmeasure": 0.11037120367033523, "rouge1_fmeasure_stderr": 0.0016020141226316521, "rouge1_precision": 0.07008037252994849, "rouge1_precision_stderr": 0.0012035993637679488, "rouge1_recall": 0.36892015349821927, "rouge1_recall_stderr": 0.0052030339175267275, "rouge2_fmeasure": 0.05157944416358925, "rouge2_fmeasure_stderr": 0.0010362585811456641, "rouge2_precision": 0.032540593106790174, "rouge2_precision_stderr": 0.000731515411120624, "rouge2_recall": 0.18396134575469794, "rouge2_recall_stderr": 0.0036503252463729982, "rougeL_fmeasure": 0.10359385842660361, "rougeL_fmeasure_stderr": 0.001472076271258242, "rougeL_precision": 0.06586167470031352, "rougeL_precision_stderr": 0.0011239315244069698, "rougeL_recall": 0.3440427226978943, "rougeL_recall_stderr": 0.0046759733900977925, "rougeLsum_fmeasure": 0.1053829136834338, "rougeLsum_fmeasure_stderr": 0.0015312528661206545, "rougeLsum_precision": 0.06702892136385862, "rougeLsum_precision_stderr": 0.0011636056187413796, "rougeLsum_recall": 0.3498407885544722, "rougeLsum_recall_stderr": 0.004802606835414834}}, "3": {"PALM_prompt": {"bleu": 0.5229218783075383, "bleu_stderr": 0.03287750689960854, "rouge1_fmeasure": 0.11129898486093194, "rouge1_fmeasure_stderr": 0.001603697213150543, "rouge1_precision": 0.07078968601889724, "rouge1_precision_stderr": 0.0012530189540338403, "rouge1_recall": 0.370854174943212, "rouge1_recall_stderr": 0.005131257813808184, "rouge2_fmeasure": 0.052270761889885206, "rouge2_fmeasure_stderr": 0.00103207142359725, "rouge2_precision": 0.03298499960390668, "rouge2_precision_stderr": 0.0007381370373430346, "rouge2_recall": 0.18675978429729426, "rouge2_recall_stderr": 0.0037180617775293043, "rougeL_fmeasure": 0.10352172121642274, "rougeL_fmeasure_stderr": 0.001462770227679166, "rougeL_precision": 0.06597257056782777, "rougeL_precision_stderr": 0.0011757840654232027, "rougeL_recall": 0.3435597898095353, "rougeL_recall_stderr": 0.004593814760542546, "rougeLsum_fmeasure": 0.10603634362382153, "rougeLsum_fmeasure_stderr": 0.0015192749230585549, "rougeLsum_precision": 0.06757005923050743, "rougeLsum_precision_stderr": 0.001208590145084183, "rougeLsum_recall": 0.35225955402286013, "rougeLsum_recall_stderr": 0.004772649571059099}}, "4": {"PALM_prompt": {"bleu": 0.6153677621128861, "bleu_stderr": 0.06053705735401149, "rouge1_fmeasure": 0.11264103250558938, "rouge1_fmeasure_stderr": 0.00163118942788917, "rouge1_precision": 0.07071127507433782, "rouge1_precision_stderr": 0.0011520192275434789, "rouge1_recall": 0.38147578757395145, "rouge1_recall_stderr": 0.005244875143584364, "rouge2_fmeasure": 0.05295652860215851, "rouge2_fmeasure_stderr": 0.0010479736263979194, "rouge2_precision": 0.032992739334882344, "rouge2_precision_stderr": 0.0007156556105984286, "rouge2_recall": 0.1932194114953707, "rouge2_recall_stderr": 0.00374859289181986, "rougeL_fmeasure": 0.10299927861932978, "rougeL_fmeasure_stderr": 0.0014284397671676585, "rougeL_precision": 0.06471147959433785, "rougeL_precision_stderr": 0.0010212506145839731, "rougeL_recall": 0.3483975351615344, "rougeL_recall_stderr": 0.004606426897749366, "rougeLsum_fmeasure": 0.10684797875052807, "rougeLsum_fmeasure_stderr": 0.0015286400891968755, "rougeLsum_precision": 0.06714267179992058, "rougeLsum_precision_stderr": 0.0010872321667830566, "rougeLsum_recall": 0.3609556696570317, "rougeLsum_recall_stderr": 0.004821987801086811}}, "5": {"PALM_prompt": {"bleu": 0.6522310718826546, "bleu_stderr": 0.0342543434913143, "rouge1_fmeasure": 0.11496831895443499, "rouge1_fmeasure_stderr": 0.0016131648938140647, "rouge1_precision": 0.07224798328936255, "rouge1_precision_stderr": 0.0011956217365912398, "rouge1_recall": 0.3930127103047457, "rouge1_recall_stderr": 0.005342634817712522, "rouge2_fmeasure": 0.054266401974880724, "rouge2_fmeasure_stderr": 0.0010279738093731765, "rouge2_precision": 0.03383327897010777, "rouge2_precision_stderr": 0.0007155324088112528, "rouge2_recall": 0.20017152367590102, "rouge2_recall_stderr": 0.0038194708260410088, "rougeL_fmeasure": 0.10413378847184503, "rougeL_fmeasure_stderr": 0.001404569572763983, "rougeL_precision": 0.06558923187444043, "rougeL_precision_stderr": 0.0010757591438449354, "rougeL_recall": 0.35557332046269224, "rougeL_recall_stderr": 0.0046352766809419025, "rougeLsum_fmeasure": 0.10879985852497424, "rougeLsum_fmeasure_stderr": 0.001514236323280586, "rougeLsum_precision": 0.0684743244702778, "rougeLsum_precision_stderr": 0.0011401249172099674, "rougeLsum_recall": 0.3715362630204789, "rougeLsum_recall_stderr": 0.004921937595664833}}}, "GEM/wiki_lingua_en": {"0": {"tldr_en": {"bleu": 1.8695101649478336, "bleu_stderr": 0.0774798723948649, "rouge1_fmeasure": 0.18492809283993106, "rouge1_fmeasure_stderr": 0.0019138467632652185, "rouge1_precision": 0.16049598964045364, "rouge1_precision_stderr": 0.0019462983151563367, "rouge1_recall": 0.2676713790563651, "rouge1_recall_stderr": 0.0028735302834564675, "rouge2_fmeasure": 0.04047796652620078, "rouge2_fmeasure_stderr": 0.0009161392431729087, "rouge2_precision": 0.034697662184252506, "rouge2_precision_stderr": 0.0008205861453711819, "rouge2_recall": 0.06110103740366906, "rouge2_recall_stderr": 0.0015502965185361641, "rougeL_fmeasure": 0.13965276114673036, "rougeL_fmeasure_stderr": 0.0013470236487103265, "rougeL_precision": 0.11976282577213969, "rougeL_precision_stderr": 0.0013342259804847978, "rougeL_recall": 0.20766916878715935, "rougeL_recall_stderr": 0.0023245522996809573, "rougeLsum_fmeasure": 0.17014737831445742, "rougeLsum_fmeasure_stderr": 0.0017471450796099739, "rougeLsum_precision": 0.14751551166205068, "rougeLsum_precision_stderr": 0.001780031941907223, "rougeLsum_recall": 0.24735686937216053, "rougeLsum_recall_stderr": 0.0026833728446082504}}, "1": {"tldr_en": {"bleu": 3.2332562389930515, "bleu_stderr": 0.0799951186296727, "rouge1_fmeasure": 0.23690998702342858, "rouge1_fmeasure_stderr": 0.0019890231968532827, "rouge1_precision": 0.20729964457048256, "rouge1_precision_stderr": 0.002274245844031677, "rouge1_recall": 0.33969139617897154, "rouge1_recall_stderr": 0.002833556197863864, "rouge2_fmeasure": 0.0622366147541512, "rouge2_fmeasure_stderr": 0.0011025942027406593, "rouge2_precision": 0.05460146452130771, "rouge2_precision_stderr": 0.001093799845706477, "rouge2_recall": 0.09225300993047651, "rouge2_recall_stderr": 0.0018248020314785354, "rougeL_fmeasure": 0.16727654774531026, "rougeL_fmeasure_stderr": 0.0013621791164943034, "rougeL_precision": 0.14525073667888475, "rougeL_precision_stderr": 0.0015687845277167008, "rougeL_recall": 0.24628845510672517, "rougeL_recall_stderr": 0.0023082894542053194, "rougeLsum_fmeasure": 0.2230496791129934, "rougeLsum_fmeasure_stderr": 0.0018757377324494942, "rougeLsum_precision": 0.19509659175047353, "rougeLsum_precision_stderr": 0.0021449940715420894, "rougeLsum_recall": 0.3204235648372041, "rougeLsum_recall_stderr": 0.0027128359683571725}}, "2": {"tldr_en": {"bleu": 3.5155467010727994, "bleu_stderr": 0.06141556601214586, "rouge1_fmeasure": 0.235556648636045, "rouge1_fmeasure_stderr": 0.0018848294908913575, "rouge1_precision": 0.20824164042833873, "rouge1_precision_stderr": 0.002234214827494051, "rouge1_recall": 0.3342680558497238, "rouge1_recall_stderr": 0.002719351845027267, "rouge2_fmeasure": 0.06251395339429003, "rouge2_fmeasure_stderr": 0.0011032340747877004, "rouge2_precision": 0.0553447765818299, "rouge2_precision_stderr": 0.001097279257804817, "rouge2_recall": 0.09158152498363732, "rouge2_recall_stderr": 0.00182638815550646, "rougeL_fmeasure": 0.16869690772741758, "rougeL_fmeasure_stderr": 0.0013497024922833358, "rougeL_precision": 0.14804254896591035, "rougeL_precision_stderr": 0.001582109014998804, "rougeL_recall": 0.24506636928994607, "rougeL_recall_stderr": 0.002277815665553641, "rougeLsum_fmeasure": 0.22311024372097865, "rougeLsum_fmeasure_stderr": 0.0017776265096001729, "rougeLsum_precision": 0.19708639575292217, "rougeLsum_precision_stderr": 0.0021089064966209187, "rougeLsum_recall": 0.31720897725992786, "rougeLsum_recall_stderr": 0.002596567797319611}}, "3": {"tldr_en": {"bleu": 3.504980488837104, "bleu_stderr": 0.07033302280883086, "rouge1_fmeasure": 0.1960859652047859, "rouge1_fmeasure_stderr": 0.0023366060464774423, "rouge1_precision": 0.17811439171989488, "rouge1_precision_stderr": 0.002560275363708373, "rouge1_recall": 0.27886090799993984, "rouge1_recall_stderr": 0.0034448901496326586, "rouge2_fmeasure": 0.0523326312861241, "rouge2_fmeasure_stderr": 0.0011285281285534974, "rouge2_precision": 0.04742286059353845, "rouge2_precision_stderr": 0.0011604513875678288, "rouge2_recall": 0.07742946215061461, "rouge2_recall_stderr": 0.001866825934930981, "rougeL_fmeasure": 0.14162844117143206, "rougeL_fmeasure_stderr": 0.0016899728317895791, "rougeL_precision": 0.12852552196126066, "rougeL_precision_stderr": 0.0018964172540042934, "rougeL_recall": 0.20545470726815437, "rougeL_recall_stderr": 0.0027326532184944424, "rougeLsum_fmeasure": 0.18556326066261042, "rougeLsum_fmeasure_stderr": 0.002215627597176747, "rougeLsum_precision": 0.16868014464807685, "rougeLsum_precision_stderr": 0.002438611490893621, "rougeLsum_recall": 0.26411127102133913, "rougeLsum_recall_stderr": 0.003281374640568146}}, "4": {"tldr_en": {"bleu": 0.9086939324156383, "bleu_stderr": 0.05855823137144976, "rouge1_fmeasure": 0.06282501006696624, "rouge1_fmeasure_stderr": 0.0020888213951751034, "rouge1_precision": 0.057686885490487505, "rouge1_precision_stderr": 0.002077970469715233, "rouge1_recall": 0.09385574649347103, "rouge1_recall_stderr": 0.0031890083282469467, "rouge2_fmeasure": 0.016837586892487218, "rouge2_fmeasure_stderr": 0.000790811753626707, "rouge2_precision": 0.015071313264611244, "rouge2_precision_stderr": 0.0007774016714959856, "rouge2_recall": 0.026883790080977472, "rouge2_recall_stderr": 0.0014075436212441558, "rougeL_fmeasure": 0.0461316780279477, "rougeL_fmeasure_stderr": 0.0015235672554804573, "rougeL_precision": 0.042638568215269866, "rougeL_precision_stderr": 0.0015504702364272222, "rougeL_recall": 0.07032908173779572, "rougeL_recall_stderr": 0.0024572632014890276, "rougeLsum_fmeasure": 0.05917832063435797, "rougeLsum_fmeasure_stderr": 0.001970707904332247, "rougeLsum_precision": 0.05433748981297747, "rougeLsum_precision_stderr": 0.0019639155165544035, "rougeLsum_recall": 0.0885417619284403, "rougeLsum_recall_stderr": 0.0030172562108610624}}, "5": {"tldr_en": {"bleu": 6.161453193982374e-06, "bleu_stderr": 1.2644510555241896e-05, "rouge1_fmeasure": 0.010180728590080238, "rouge1_fmeasure_stderr": 0.0009430571774107825, "rouge1_precision": 0.009722491969586005, "rouge1_precision_stderr": 0.0009564982386894138, "rouge1_recall": 0.015357271032115101, "rouge1_recall_stderr": 0.001448960021557378, "rouge2_fmeasure": 0.00281382806546607, "rouge2_fmeasure_stderr": 0.00035214119256937883, "rouge2_precision": 0.0024973101781513925, "rouge2_precision_stderr": 0.000343733403974376, "rouge2_recall": 0.0045816927074040755, "rouge2_recall_stderr": 0.0006153391357680226, "rougeL_fmeasure": 0.00759156476319381, "rougeL_fmeasure_stderr": 0.0007014066070016197, "rougeL_precision": 0.0072997926636164424, "rougeL_precision_stderr": 0.0007272617797612332, "rougeL_recall": 0.011767619522932812, "rougeL_recall_stderr": 0.0011356853451163903, "rougeLsum_fmeasure": 0.00955145315759681, "rougeLsum_fmeasure_stderr": 0.0008912980968449334, "rougeLsum_precision": 0.009129679261559958, "rougeLsum_precision_stderr": 0.0009077175108677888, "rougeLsum_recall": 0.014481417293915742, "rougeLsum_recall_stderr": 0.0013773388496390326}}}, "e2e_nlg_cleaned": {"0": {"generate_text_restaurant": {"bleu": 0.03454795333510589, "bleu_stderr": 0.010722245919714395, "rouge1_fmeasure": 0.009983083620835689, "rouge1_fmeasure_stderr": 0.0007216517112036717, "rouge1_precision": 0.008330877542768076, "rouge1_precision_stderr": 0.0006789467135202171, "rouge1_recall": 0.01512213229502354, "rouge1_recall_stderr": 0.0010598056749213033, "rouge2_fmeasure": 0.0015194719382464828, "rouge2_fmeasure_stderr": 0.0002186426847142056, "rouge2_precision": 0.0012462152328688286, "rouge2_precision_stderr": 0.0001850740246851996, "rouge2_recall": 0.0021941504736507373, "rouge2_recall_stderr": 0.00031789022057788433, "rougeL_fmeasure": 0.009451610525850281, "rougeL_fmeasure_stderr": 0.0006635438560036569, "rougeL_precision": 0.0076678486076520065, "rougeL_precision_stderr": 0.0005780206165870198, "rougeL_recall": 0.014540667195886358, "rougeL_recall_stderr": 0.0010048165449253396, "rougeLsum_fmeasure": 0.008102826704141256, "rougeLsum_fmeasure_stderr": 0.0005948187054074003, "rougeLsum_precision": 0.006854342833172471, "rougeLsum_precision_stderr": 0.0005808821610184307, "rougeLsum_recall": 0.01222352423290077, "rougeLsum_recall_stderr": 0.0008679529695598302}}, "1": {"generate_text_restaurant": {"bleu": 10.110683183008721, "bleu_stderr": 0.10856580026912326, "rouge1_fmeasure": 0.4261931768500333, "rouge1_fmeasure_stderr": 0.0020338904219177937, "rouge1_precision": 0.4273885051454009, "rouge1_precision_stderr": 0.0023386626945434775, "rouge1_recall": 0.4619168895673238, "rouge1_recall_stderr": 0.002910080537073359, "rouge2_fmeasure": 0.18637115332137155, "rouge2_fmeasure_stderr": 0.0017490252095085136, "rouge2_precision": 0.18621605242973624, "rouge2_precision_stderr": 0.0018420288481743644, "rouge2_recall": 0.20425913452615088, "rouge2_recall_stderr": 0.002171191668790452, "rougeL_fmeasure": 0.30007012360581886, "rougeL_fmeasure_stderr": 0.0017073194851728616, "rougeL_precision": 0.30141579223639636, "rougeL_precision_stderr": 0.0019324093600811055, "rougeL_recall": 0.3256528804455511, "rougeL_recall_stderr": 0.002364609519861813, "rougeLsum_fmeasure": 0.35343380568090416, "rougeLsum_fmeasure_stderr": 0.0020183396806264077, "rougeLsum_precision": 0.3549239657030783, "rougeLsum_precision_stderr": 0.0022624041723470494, "rougeLsum_recall": 0.38280848019973457, "rougeLsum_recall_stderr": 0.002716917275700221}}, "2": {"generate_text_restaurant": {"bleu": 11.76941570816289, "bleu_stderr": 0.15573900245748828, "rouge1_fmeasure": 0.45040818552274897, "rouge1_fmeasure_stderr": 0.001961202454945367, "rouge1_precision": 0.44751016860851195, "rouge1_precision_stderr": 0.002306632595634685, "rouge1_recall": 0.4895112200039268, "rouge1_recall_stderr": 0.0028440252957840422, "rouge2_fmeasure": 0.21309279835498804, "rouge2_fmeasure_stderr": 0.0018084420773651576, "rouge2_precision": 0.21124466241603482, "rouge2_precision_stderr": 0.001920141813437847, "rouge2_recall": 0.23408285111523244, "rouge2_recall_stderr": 0.0022741821628275683, "rougeL_fmeasure": 0.3267435445462492, "rougeL_fmeasure_stderr": 0.0017435336297606837, "rougeL_precision": 0.3250865088115516, "rougeL_precision_stderr": 0.0020090753832284394, "rougeL_recall": 0.35555451083591993, "rougeL_recall_stderr": 0.0024076335160479975, "rougeLsum_fmeasure": 0.37491707249596695, "rougeLsum_fmeasure_stderr": 0.0020146819194002373, "rougeLsum_precision": 0.3727655581276283, "rougeLsum_precision_stderr": 0.002277906383748808, "rougeLsum_recall": 0.40742138628815283, "rougeLsum_recall_stderr": 0.0027125462981769503}}, "3": {"generate_text_restaurant": {"bleu": 12.357057866617781, "bleu_stderr": 0.11622210780282331, "rouge1_fmeasure": 0.4562426842321961, "rouge1_fmeasure_stderr": 0.0019386232886629857, "rouge1_precision": 0.45217337104133665, "rouge1_precision_stderr": 0.002294505554504784, "rouge1_recall": 0.4942792865855869, "rouge1_recall_stderr": 0.002743597811824126, "rouge2_fmeasure": 0.22032333042194527, "rouge2_fmeasure_stderr": 0.001852412446316337, "rouge2_precision": 0.2175811124968712, "rouge2_precision_stderr": 0.0019112105040248436, "rouge2_recall": 0.2409573657644072, "rouge2_recall_stderr": 0.0023044463187969245, "rougeL_fmeasure": 0.3334482257131471, "rougeL_fmeasure_stderr": 0.0017866016624809113, "rougeL_precision": 0.33057426692006453, "rougeL_precision_stderr": 0.0020126164762619228, "rougeL_recall": 0.3619557938558922, "rougeL_recall_stderr": 0.0024177454342242813, "rougeLsum_fmeasure": 0.3816770816558835, "rougeLsum_fmeasure_stderr": 0.002007876237485467, "rougeLsum_precision": 0.37808218718729336, "rougeLsum_precision_stderr": 0.0022431062970265465, "rougeLsum_recall": 0.41390580636859037, "rougeLsum_recall_stderr": 0.0026729564370056775}}, "4": {"generate_text_restaurant": {"bleu": 12.468466502215751, "bleu_stderr": 0.09990648109577639, "rouge1_fmeasure": 0.45529352918386296, "rouge1_fmeasure_stderr": 0.0019729158566691536, "rouge1_precision": 0.45220424528442504, "rouge1_precision_stderr": 0.002337808233031794, "rouge1_recall": 0.4921231264159867, "rouge1_recall_stderr": 0.0027602306430746792, "rouge2_fmeasure": 0.21993594978939215, "rouge2_fmeasure_stderr": 0.001850258705420329, "rouge2_precision": 0.21806635417357498, "rouge2_precision_stderr": 0.0019446195531272607, "rouge2_recall": 0.2401062314536212, "rouge2_recall_stderr": 0.00230192039014965, "rougeL_fmeasure": 0.3320801238250487, "rougeL_fmeasure_stderr": 0.001796774794658876, "rougeL_precision": 0.32979623685018056, "rougeL_precision_stderr": 0.002025955430723721, "rougeL_recall": 0.35968401480469203, "rougeL_recall_stderr": 0.0024104842159546787, "rougeLsum_fmeasure": 0.38073707749695784, "rougeLsum_fmeasure_stderr": 0.0020603619333531575, "rougeLsum_precision": 0.37807324998983866, "rougeLsum_precision_stderr": 0.002305718057682757, "rougeLsum_recall": 0.4118614121463698, "rougeLsum_recall_stderr": 0.0027125157827382973}}, "5": {"generate_text_restaurant": {"bleu": 12.11108163274697, "bleu_stderr": 0.1511086038189987, "rouge1_fmeasure": 0.45448318084710065, "rouge1_fmeasure_stderr": 0.0019502573764627392, "rouge1_precision": 0.4494689335142834, "rouge1_precision_stderr": 0.0023139900407069896, "rouge1_recall": 0.49189724241328564, "rouge1_recall_stderr": 0.002720672072662264, "rouge2_fmeasure": 0.21793438022656353, "rouge2_fmeasure_stderr": 0.0018382910372242867, "rouge2_precision": 0.21502011952369768, "rouge2_precision_stderr": 0.0018993108425412735, "rouge2_recall": 0.23790406650497267, "rouge2_recall_stderr": 0.002257304748049696, "rougeL_fmeasure": 0.33100721144592343, "rougeL_fmeasure_stderr": 0.0017930595424372638, "rougeL_precision": 0.3270263161597272, "rougeL_precision_stderr": 0.001992100365911566, "rougeL_recall": 0.3590215756959229, "rougeL_recall_stderr": 0.0023843408170312035, "rougeLsum_fmeasure": 0.3800458168267657, "rougeLsum_fmeasure_stderr": 0.002019377882054415, "rougeLsum_precision": 0.3757504695199971, "rougeLsum_precision_stderr": 0.00226312608847076, "rougeLsum_recall": 0.4115209951658525, "rougeLsum_recall_stderr": 0.002643403932683506}}}, "gem_xsum": {"0": {"article_DOC_summary": {"bleu": 2.4185935712214466, "bleu_stderr": 0.11565432283117048, "rouge1_fmeasure": 0.22302727328338223, "rouge1_fmeasure_stderr": 0.002543649203320007, "rouge1_precision": 0.16079100538036975, "rouge1_precision_stderr": 0.0019317155011328527, "rouge1_recall": 0.38463169025745175, "rouge1_recall_stderr": 0.004526539026922928, "rouge2_fmeasure": 0.056442306230818876, "rouge2_fmeasure_stderr": 0.0016804520319396248, "rouge2_precision": 0.03999269013558242, "rouge2_precision_stderr": 0.0011971308201383902, "rouge2_recall": 0.10113339981669754, "rouge2_recall_stderr": 0.0031343748451553286, "rougeL_fmeasure": 0.16717619407627404, "rougeL_fmeasure_stderr": 0.0019481211634922503, "rougeL_precision": 0.12033234686017578, "rougeL_precision_stderr": 0.0014585203532609563, "rougeL_recall": 0.2903778922407286, "rougeL_recall_stderr": 0.003692559366146235, "rougeLsum_fmeasure": 0.17608763758164225, "rougeLsum_fmeasure_stderr": 0.002145834312930374, "rougeLsum_precision": 0.12659083153302422, "rougeLsum_precision_stderr": 0.0015911326356590116, "rougeLsum_recall": 0.30622228336959245, "rougeLsum_recall_stderr": 0.004035233836387343}}, "1": {"article_DOC_summary": {"bleu": 1.4753760157360585, "bleu_stderr": 0.053942288193643405, "rouge1_fmeasure": 0.17409533783255507, "rouge1_fmeasure_stderr": 0.002615183917058679, "rouge1_precision": 0.123975541885696, "rouge1_precision_stderr": 0.001937069913810257, "rouge1_recall": 0.3041634033606052, "rouge1_recall_stderr": 0.004462494037919621, "rouge2_fmeasure": 0.03598895109620969, "rouge2_fmeasure_stderr": 0.001496555270960858, "rouge2_precision": 0.02530985857085611, "rouge2_precision_stderr": 0.0010516965631042789, "rouge2_recall": 0.06497657707857857, "rouge2_recall_stderr": 0.0028062229327394097, "rougeL_fmeasure": 0.13719393806212205, "rougeL_fmeasure_stderr": 0.001988792672158033, "rougeL_precision": 0.09739516038141627, "rougeL_precision_stderr": 0.0014498365795769053, "rougeL_recall": 0.24191669859950216, "rougeL_recall_stderr": 0.0036028516933205405, "rougeLsum_fmeasure": 0.1371396960626393, "rougeLsum_fmeasure_stderr": 0.0021254210571197236, "rougeLsum_precision": 0.0973784808310999, "rougeLsum_precision_stderr": 0.0015541782441477088, "rougeLsum_recall": 0.24166767773481146, "rougeLsum_recall_stderr": 0.0037775246270440404}}, "2": {"article_DOC_summary": {"bleu": 1.4658077495541642, "bleu_stderr": 0.05656663077206122, "rouge1_fmeasure": 0.17850901621898715, "rouge1_fmeasure_stderr": 0.002631185065208956, "rouge1_precision": 0.12701574570405383, "rouge1_precision_stderr": 0.0019497483407488042, "rouge1_recall": 0.31209308297568034, "rouge1_recall_stderr": 0.0044823221140013695, "rouge2_fmeasure": 0.03728951183116744, "rouge2_fmeasure_stderr": 0.0014839130164513042, "rouge2_precision": 0.02628489874277305, "rouge2_precision_stderr": 0.0010496767573945315, "rouge2_recall": 0.06678550185926611, "rouge2_recall_stderr": 0.002741050501727463, "rougeL_fmeasure": 0.14040861303541324, "rougeL_fmeasure_stderr": 0.001957888420474033, "rougeL_precision": 0.09965436966997658, "rougeL_precision_stderr": 0.0014375571522234208, "rougeL_recall": 0.24737259975268608, "rougeL_recall_stderr": 0.003487423921250019, "rougeLsum_fmeasure": 0.1402274218021141, "rougeLsum_fmeasure_stderr": 0.00214102737994103, "rougeLsum_precision": 0.0995909554171278, "rougeLsum_precision_stderr": 0.001569684395558083, "rougeLsum_recall": 0.2465747406900749, "rougeLsum_recall_stderr": 0.0037567150545319778}}, "3": {"article_DOC_summary": {"bleu": 1.6273581251014975, "bleu_stderr": 0.08297152976943713, "rouge1_fmeasure": 0.1741691220448831, "rouge1_fmeasure_stderr": 0.0027529808698691072, "rouge1_precision": 0.12661685012408697, "rouge1_precision_stderr": 0.0021093732895884356, "rouge1_recall": 0.30042742106922904, "rouge1_recall_stderr": 0.004793262475513874, "rouge2_fmeasure": 0.03848207108872355, "rouge2_fmeasure_stderr": 0.0015349514843449124, "rouge2_precision": 0.027457383236278155, "rouge2_precision_stderr": 0.0011005894460101174, "rouge2_recall": 0.06872339351563556, "rouge2_recall_stderr": 0.0028264005600779733, "rougeL_fmeasure": 0.13848485640839917, "rougeL_fmeasure_stderr": 0.002136410452186076, "rougeL_precision": 0.10054376826357136, "rougeL_precision_stderr": 0.0016355832838556733, "rougeL_recall": 0.24044972226758587, "rougeL_recall_stderr": 0.0038558430038978684, "rougeLsum_fmeasure": 0.13794850154717367, "rougeLsum_fmeasure_stderr": 0.002276629118568194, "rougeLsum_precision": 0.10022509495467177, "rougeLsum_precision_stderr": 0.001733799927568896, "rougeLsum_recall": 0.2391221551244155, "rougeLsum_recall_stderr": 0.0040668979594426224}}, "4": {"article_DOC_summary": {"bleu": 0.9297944407512662, "bleu_stderr": 0.10452568299951195, "rouge1_fmeasure": 0.049025842019891894, "rouge1_fmeasure_stderr": 0.002761462686946734, "rouge1_precision": 0.03984641222755382, "rouge1_precision_stderr": 0.0023583006672399276, "rouge1_recall": 0.07781373363270898, "rouge1_recall_stderr": 0.0044678999283725125, "rouge2_fmeasure": 0.011276208078698832, "rouge2_fmeasure_stderr": 0.0010882501335885415, "rouge2_precision": 0.008839770813015032, "rouge2_precision_stderr": 0.0009132501416122141, "rouge2_recall": 0.018595501088417683, "rouge2_recall_stderr": 0.0018046371518142589, "rougeL_fmeasure": 0.03899309107571578, "rougeL_fmeasure_stderr": 0.0022095258634566655, "rougeL_precision": 0.03193279708670165, "rougeL_precision_stderr": 0.0019219705874772618, "rougeL_recall": 0.06201212154363477, "rougeL_recall_stderr": 0.0036181165069829016, "rougeLsum_fmeasure": 0.03871502132726552, "rougeLsum_fmeasure_stderr": 0.0021963924186294845, "rougeLsum_precision": 0.03172097901935682, "rougeLsum_precision_stderr": 0.0019113003105201993, "rougeLsum_recall": 0.06162603968016436, "rougeLsum_recall_stderr": 0.003613145314591428}}, "5": {"article_DOC_summary": {"bleu": 1.3519576766092788e-16, "bleu_stderr": 1.7148754157361587e-13, "rouge1_fmeasure": 0.002273937140206459, "rouge1_fmeasure_stderr": 0.0006514011124893405, "rouge1_precision": 0.0018747157977051885, "rouge1_precision_stderr": 0.0005217271715436668, "rouge1_recall": 0.003549283577549333, "rouge1_recall_stderr": 0.0010767599221403455, "rouge2_fmeasure": 0.0005538280315731646, "rouge2_fmeasure_stderr": 0.00021055797770595916, "rouge2_precision": 0.00047917769370046107, "rouge2_precision_stderr": 0.00017934012188651556, "rouge2_recall": 0.0007855487711203583, "rouge2_recall_stderr": 0.00030506211146057416, "rougeL_fmeasure": 0.0019019709421522583, "rougeL_fmeasure_stderr": 0.0005434789167320575, "rougeL_precision": 0.001591076043425948, "rougeL_precision_stderr": 0.00044966429790604164, "rougeL_recall": 0.002863749112737054, "rougeL_recall_stderr": 0.0008323073183414411, "rougeLsum_fmeasure": 0.0018351130157390045, "rougeLsum_fmeasure_stderr": 0.0005055637602691865, "rougeLsum_precision": 0.00156298958828556, "rougeLsum_precision_stderr": 0.00043239685994550666, "rougeLsum_recall": 0.0027767015907513405, "rougeLsum_recall_stderr": 0.0007833271709551212}}}} |