Muennighoff's picture
Add
2aef930
{"GEM/web_nlg_en": {"0": {"PALM_prompt": {"bleu": 0.32012773562587393, "bleu_stderr": 0.018886919871708343, "rouge1_fmeasure": 0.0899762528447479, "rouge1_fmeasure_stderr": 0.0020354843345656163, "rouge1_precision": 0.06825136821356759, "rouge1_precision_stderr": 0.00237062733299883, "rouge1_recall": 0.2508286238498341, "rouge1_recall_stderr": 0.004661697991334146, "rouge2_fmeasure": 0.03944916755986983, "rouge2_fmeasure_stderr": 0.001249719129780461, "rouge2_precision": 0.030615387870315716, "rouge2_precision_stderr": 0.0016384196683051863, "rouge2_recall": 0.11248984628302856, "rouge2_recall_stderr": 0.0030543468265705285, "rougeL_fmeasure": 0.08360285576779355, "rougeL_fmeasure_stderr": 0.0018856928971255989, "rougeL_precision": 0.06342619049690505, "rougeL_precision_stderr": 0.002233393033449764, "rougeL_recall": 0.23548259610722824, "rougeL_recall_stderr": 0.004438251763555299, "rougeLsum_fmeasure": 0.08427145597780734, "rougeLsum_fmeasure_stderr": 0.0019051123678010644, "rougeLsum_precision": 0.06406542591417572, "rougeLsum_precision_stderr": 0.0022429625274388077, "rougeLsum_recall": 0.234275763130725, "rougeLsum_recall_stderr": 0.00433154610375273}}, "1": {"PALM_prompt": {"bleu": 0.28781282710307465, "bleu_stderr": 0.01899808984283447, "rouge1_fmeasure": 0.07847336913595586, "rouge1_fmeasure_stderr": 0.001535955643926011, "rouge1_precision": 0.0527754711256334, "rouge1_precision_stderr": 0.0014904713251823198, "rouge1_recall": 0.2537614091915221, "rouge1_recall_stderr": 0.004702310798072158, "rouge2_fmeasure": 0.032657251493622856, "rouge2_fmeasure_stderr": 0.0009264643374386928, "rouge2_precision": 0.021533529321543874, "rouge2_precision_stderr": 0.0007685776439012483, "rouge2_recall": 0.10966078271884003, "rouge2_recall_stderr": 0.002981675456939165, "rougeL_fmeasure": 0.07228685200884048, "rougeL_fmeasure_stderr": 0.0014209363141639564, "rougeL_precision": 0.04876649614656279, "rougeL_precision_stderr": 0.001420498632004972, "rougeL_recall": 0.23339792109691904, "rougeL_recall_stderr": 0.004315010087105858, "rougeLsum_fmeasure": 0.07320160734011764, "rougeLsum_fmeasure_stderr": 0.0014251444099725329, "rougeLsum_precision": 0.04935178833491907, "rougeLsum_precision_stderr": 0.0014212538671699328, "rougeLsum_recall": 0.23635405366452086, "rougeLsum_recall_stderr": 0.00434221432817691}}, "2": {"PALM_prompt": {"bleu": 0.32085939271138914, "bleu_stderr": 0.023874716323242045, "rouge1_fmeasure": 0.08108986156959869, "rouge1_fmeasure_stderr": 0.0015435730709568757, "rouge1_precision": 0.05368960443919722, "rouge1_precision_stderr": 0.0013878849609328464, "rouge1_recall": 0.2687130245556709, "rouge1_recall_stderr": 0.004740106099310347, "rouge2_fmeasure": 0.03412133307095403, "rouge2_fmeasure_stderr": 0.0009323084416353588, "rouge2_precision": 0.022426372869437324, "rouge2_precision_stderr": 0.0008085489202082841, "rouge2_recall": 0.11689977539927107, "rouge2_recall_stderr": 0.00300061931368436, "rougeL_fmeasure": 0.07379515479031812, "rougeL_fmeasure_stderr": 0.0013763914362202537, "rougeL_precision": 0.048651633590719855, "rougeL_precision_stderr": 0.0011827185282768337, "rougeL_recall": 0.24511580579594355, "rougeL_recall_stderr": 0.004282778444187627, "rougeLsum_fmeasure": 0.07555165803520482, "rougeLsum_fmeasure_stderr": 0.0014213371826134968, "rougeLsum_precision": 0.05014569138865563, "rougeLsum_precision_stderr": 0.001314326894957353, "rougeLsum_recall": 0.24950401790874296, "rougeLsum_recall_stderr": 0.004286277514587859}}, "3": {"PALM_prompt": {"bleu": 0.328454678316601, "bleu_stderr": 0.022343422759414436, "rouge1_fmeasure": 0.07919929805647623, "rouge1_fmeasure_stderr": 0.001514394418998029, "rouge1_precision": 0.052008963484847605, "rouge1_precision_stderr": 0.0014633614953241854, "rouge1_recall": 0.26281409902133185, "rouge1_recall_stderr": 0.0047415561831233915, "rouge2_fmeasure": 0.032486553286374405, "rouge2_fmeasure_stderr": 0.0008957923404999381, "rouge2_precision": 0.02118860914793864, "rouge2_precision_stderr": 0.0008530949812868349, "rouge2_recall": 0.11276078198061254, "rouge2_recall_stderr": 0.0030219172592672325, "rougeL_fmeasure": 0.07148770019595055, "rougeL_fmeasure_stderr": 0.0013416340928285905, "rougeL_precision": 0.0471171164690475, "rougeL_precision_stderr": 0.0013827485067535008, "rougeL_recall": 0.23822249787189817, "rougeL_recall_stderr": 0.0042466165786672035, "rougeLsum_fmeasure": 0.07424172013111648, "rougeLsum_fmeasure_stderr": 0.0014133679260911725, "rougeLsum_precision": 0.04892298323961062, "rougeLsum_precision_stderr": 0.0014183478958578937, "rougeLsum_recall": 0.24590296884903542, "rougeLsum_recall_stderr": 0.004380487268920286}}, "4": {"PALM_prompt": {"bleu": 0.3319702594644372, "bleu_stderr": 0.017323146780773062, "rouge1_fmeasure": 0.08161632894859638, "rouge1_fmeasure_stderr": 0.0015256642009196088, "rouge1_precision": 0.05459708827196318, "rouge1_precision_stderr": 0.0015720228379579838, "rouge1_recall": 0.2657448353396512, "rouge1_recall_stderr": 0.004717475684567482, "rouge2_fmeasure": 0.03357767413194358, "rouge2_fmeasure_stderr": 0.0009162455741147543, "rouge2_precision": 0.023141351440564402, "rouge2_precision_stderr": 0.001127390810261633, "rouge2_recall": 0.11549040824815301, "rouge2_recall_stderr": 0.0030025248991349058, "rougeL_fmeasure": 0.07227592144254627, "rougeL_fmeasure_stderr": 0.0013148844913734015, "rougeL_precision": 0.04843785490759391, "rougeL_precision_stderr": 0.0014543602029517073, "rougeL_recall": 0.23813768049670572, "rougeL_recall_stderr": 0.004172909727083725, "rougeLsum_fmeasure": 0.07605405086627043, "rougeLsum_fmeasure_stderr": 0.0014106467606439447, "rougeLsum_precision": 0.05090666274679119, "rougeLsum_precision_stderr": 0.0014735025076296423, "rougeLsum_recall": 0.2482641520424661, "rougeLsum_recall_stderr": 0.004326751256652749}}, "5": {"PALM_prompt": {"bleu": 0.39182011395821026, "bleu_stderr": 0.03017462277769791, "rouge1_fmeasure": 0.08316112835678297, "rouge1_fmeasure_stderr": 0.0015044194584303333, "rouge1_precision": 0.05338210822991803, "rouge1_precision_stderr": 0.0011795913375033742, "rouge1_recall": 0.2739388133076789, "rouge1_recall_stderr": 0.004725041678049671, "rouge2_fmeasure": 0.03484163213544278, "rouge2_fmeasure_stderr": 0.0009120223523826239, "rouge2_precision": 0.02230990790026212, "rouge2_precision_stderr": 0.0007134756313875014, "rouge2_recall": 0.12067184027915072, "rouge2_recall_stderr": 0.003047769920528369, "rougeL_fmeasure": 0.07405669758488781, "rougeL_fmeasure_stderr": 0.0013146857723887232, "rougeL_precision": 0.04760001656977872, "rougeL_precision_stderr": 0.001056801997116071, "rougeL_recall": 0.2449561247042928, "rougeL_recall_stderr": 0.004191935654465999, "rougeLsum_fmeasure": 0.07747218411731929, "rougeLsum_fmeasure_stderr": 0.0013880210497301878, "rougeLsum_precision": 0.049818219801901514, "rougeLsum_precision_stderr": 0.0011057069363974176, "rougeLsum_recall": 0.25508548910812884, "rougeLsum_recall_stderr": 0.004349187676537093}}}, "GEM/wiki_lingua_en": {"0": {"tldr_en": {"bleu": 1.2190291379439195, "bleu_stderr": 0.08836041456372522, "rouge1_fmeasure": 0.1723366320397076, "rouge1_fmeasure_stderr": 0.0016970728587596892, "rouge1_precision": 0.14881678764247983, "rouge1_precision_stderr": 0.0018075069170291314, "rouge1_recall": 0.24793312894988265, "rouge1_recall_stderr": 0.002389930611487624, "rouge2_fmeasure": 0.02968820163157077, "rouge2_fmeasure_stderr": 0.0007214568491876274, "rouge2_precision": 0.025628754354153325, "rouge2_precision_stderr": 0.0006556947869924073, "rouge2_recall": 0.04387904423436066, "rouge2_recall_stderr": 0.0012152943972142077, "rougeL_fmeasure": 0.12964957358415072, "rougeL_fmeasure_stderr": 0.001174103551409633, "rougeL_precision": 0.11061636395219109, "rougeL_precision_stderr": 0.0012170197578614795, "rougeL_recall": 0.19130257812101642, "rougeL_recall_stderr": 0.001903442450094291, "rougeLsum_fmeasure": 0.1606987702240205, "rougeLsum_fmeasure_stderr": 0.0015723044572643534, "rougeLsum_precision": 0.13872341402711671, "rougeLsum_precision_stderr": 0.0016795577613053013, "rougeLsum_recall": 0.23159850567749277, "rougeLsum_recall_stderr": 0.002229753265274432}}, "1": {"tldr_en": {"bleu": 1.5590008346037099, "bleu_stderr": 0.06892531048465908, "rouge1_fmeasure": 0.17711899758881897, "rouge1_fmeasure_stderr": 0.0017763415721639936, "rouge1_precision": 0.15240917543961252, "rouge1_precision_stderr": 0.001893453848440131, "rouge1_recall": 0.25542377808907146, "rouge1_recall_stderr": 0.0024641171624728577, "rouge2_fmeasure": 0.03374713766036158, "rouge2_fmeasure_stderr": 0.0007818322344438194, "rouge2_precision": 0.029132226950407722, "rouge2_precision_stderr": 0.000722011658200494, "rouge2_recall": 0.049639629425446356, "rouge2_recall_stderr": 0.0012773856244254617, "rougeL_fmeasure": 0.12974115857300988, "rougeL_fmeasure_stderr": 0.0011843934409556005, "rougeL_precision": 0.10994692166995118, "rougeL_precision_stderr": 0.0012260681075949413, "rougeL_recall": 0.19293230076900478, "rougeL_recall_stderr": 0.0019284923872095526, "rougeLsum_fmeasure": 0.16618151783978977, "rougeLsum_fmeasure_stderr": 0.0016552458293647842, "rougeLsum_precision": 0.1427583503702487, "rougeLsum_precision_stderr": 0.0017641069847062667, "rougeLsum_recall": 0.24069300754030848, "rougeLsum_recall_stderr": 0.0023353688459108405}}, "2": {"tldr_en": {"bleu": 1.423539576651847, "bleu_stderr": 0.05590338188617223, "rouge1_fmeasure": 0.17612683398478715, "rouge1_fmeasure_stderr": 0.0017563955053422117, "rouge1_precision": 0.15159610505617108, "rouge1_precision_stderr": 0.0018921710224610877, "rouge1_recall": 0.2536664028604043, "rouge1_recall_stderr": 0.0023916817331507876, "rouge2_fmeasure": 0.03193124516131047, "rouge2_fmeasure_stderr": 0.000758958083313296, "rouge2_precision": 0.02782910309662972, "rouge2_precision_stderr": 0.0007111400329440863, "rouge2_recall": 0.04643317452251163, "rouge2_recall_stderr": 0.0012211811473359306, "rougeL_fmeasure": 0.1305484526211359, "rougeL_fmeasure_stderr": 0.0011976224297953603, "rougeL_precision": 0.11083516090740873, "rougeL_precision_stderr": 0.0012614447636676077, "rougeL_recall": 0.19352563235261244, "rougeL_recall_stderr": 0.0019031906464486539, "rougeLsum_fmeasure": 0.1656855868051239, "rougeLsum_fmeasure_stderr": 0.0016384579347020886, "rougeLsum_precision": 0.1424531837738363, "rougeLsum_precision_stderr": 0.0017681228614650911, "rougeLsum_recall": 0.23940558197543957, "rougeLsum_recall_stderr": 0.0022600581442295}}, "3": {"tldr_en": {"bleu": 1.402481855726376, "bleu_stderr": 0.07496831085827607, "rouge1_fmeasure": 0.14896513024586858, "rouge1_fmeasure_stderr": 0.0020016614890125467, "rouge1_precision": 0.13298493032742092, "rouge1_precision_stderr": 0.0021599143965991448, "rouge1_recall": 0.214129162398553, "rouge1_recall_stderr": 0.0028318625372094723, "rouge2_fmeasure": 0.02730656796059889, "rouge2_fmeasure_stderr": 0.0007432758390663112, "rouge2_precision": 0.0244781955065012, "rouge2_precision_stderr": 0.0007307175719718521, "rouge2_recall": 0.03981635760280176, "rouge2_recall_stderr": 0.0012026016154760618, "rougeL_fmeasure": 0.11134915972896199, "rougeL_fmeasure_stderr": 0.00140777630827098, "rougeL_precision": 0.09875466672002745, "rougeL_precision_stderr": 0.001559084136737345, "rougeL_recall": 0.1644184900777515, "rougeL_recall_stderr": 0.00222028334382692, "rougeLsum_fmeasure": 0.1397033192660591, "rougeLsum_fmeasure_stderr": 0.0018672195336514297, "rougeLsum_precision": 0.12471488513914283, "rougeLsum_precision_stderr": 0.0020316307804283357, "rougeLsum_recall": 0.20148242502649036, "rougeLsum_recall_stderr": 0.0026760218524170916}}, "4": {"tldr_en": {"bleu": 0.3627379747836102, "bleu_stderr": 0.03354762768029023, "rouge1_fmeasure": 0.0495274627219381, "rouge1_fmeasure_stderr": 0.00169718420379995, "rouge1_precision": 0.04578189123199333, "rouge1_precision_stderr": 0.0017562670636657443, "rouge1_recall": 0.07399147773842517, "rouge1_recall_stderr": 0.002550315174376835, "rouge2_fmeasure": 0.009286374730690028, "rouge2_fmeasure_stderr": 0.00050108884216674, "rouge2_precision": 0.008690556943839151, "rouge2_precision_stderr": 0.0006452419871034267, "rouge2_recall": 0.014071929895195552, "rouge2_recall_stderr": 0.0008009026229828391, "rougeL_fmeasure": 0.03797030362668432, "rougeL_fmeasure_stderr": 0.0012710366329130882, "rougeL_precision": 0.035008115979705615, "rougeL_precision_stderr": 0.0013409826184435712, "rougeL_recall": 0.058241103416270305, "rougeL_recall_stderr": 0.0020319511583359808, "rougeLsum_fmeasure": 0.046311955140639516, "rougeLsum_fmeasure_stderr": 0.0015800586441838697, "rougeLsum_precision": 0.042745554189029616, "rougeLsum_precision_stderr": 0.0016289097623771287, "rougeLsum_recall": 0.06929822143002932, "rougeLsum_recall_stderr": 0.002385334871151041}}, "5": {"tldr_en": {"bleu": 5.170172033055458e-07, "bleu_stderr": 1.1813622697325427e-06, "rouge1_fmeasure": 0.008032143708786618, "rouge1_fmeasure_stderr": 0.000769380549886739, "rouge1_precision": 0.0074834967426424225, "rouge1_precision_stderr": 0.0007736454980237687, "rouge1_recall": 0.011934633047410595, "rouge1_recall_stderr": 0.0011163746139347308, "rouge2_fmeasure": 0.0014060293109536969, "rouge2_fmeasure_stderr": 0.0002040774536152345, "rouge2_precision": 0.0011994561802445166, "rouge2_precision_stderr": 0.00018233396610689006, "rouge2_recall": 0.0022243917557991503, "rouge2_recall_stderr": 0.000328054783161663, "rougeL_fmeasure": 0.005954377693063202, "rougeL_fmeasure_stderr": 0.000556855926391102, "rougeL_precision": 0.005527948528114916, "rougeL_precision_stderr": 0.0005645889276529973, "rougeL_recall": 0.009193511694802203, "rougeL_recall_stderr": 0.0008680965592063552, "rougeLsum_fmeasure": 0.0075115815949656104, "rougeLsum_fmeasure_stderr": 0.0007197306094579381, "rougeLsum_precision": 0.007022799151439734, "rougeLsum_precision_stderr": 0.0007312149938921309, "rougeLsum_recall": 0.011189580936988842, "rougeLsum_recall_stderr": 0.0010462966465602747}}}, "e2e_nlg_cleaned": {"0": {"generate_text_restaurant": {"bleu": 0.023059028483234455, "bleu_stderr": 0.009986858835187516, "rouge1_fmeasure": 0.038140802367729314, "rouge1_fmeasure_stderr": 0.001495094420064931, "rouge1_precision": 0.08646635544730007, "rouge1_precision_stderr": 0.00377831577985332, "rouge1_recall": 0.031635634606258116, "rouge1_recall_stderr": 0.001269300288541845, "rouge2_fmeasure": 0.011993223757428687, "rouge2_fmeasure_stderr": 0.0006456302396314265, "rouge2_precision": 0.03990955933185571, "rouge2_precision_stderr": 0.0024489170391253133, "rouge2_recall": 0.00853219303645261, "rouge2_recall_stderr": 0.00046389097916627487, "rougeL_fmeasure": 0.034369983243126824, "rougeL_fmeasure_stderr": 0.0013496596592950014, "rougeL_precision": 0.07881038410549088, "rougeL_precision_stderr": 0.0035148627119781285, "rougeL_recall": 0.028615455542499727, "rougeL_recall_stderr": 0.0011483835890292063, "rougeLsum_fmeasure": 0.033892840605688854, "rougeLsum_fmeasure_stderr": 0.0013502083491247366, "rougeLsum_precision": 0.07924093489385359, "rougeLsum_precision_stderr": 0.0035579093389609888, "rougeLsum_recall": 0.027741907284705433, "rougeLsum_recall_stderr": 0.0011204355268068656}}, "1": {"generate_text_restaurant": {"bleu": 5.92327601668373, "bleu_stderr": 0.05843145852320597, "rouge1_fmeasure": 0.3195090019700737, "rouge1_fmeasure_stderr": 0.0019316739490464164, "rouge1_precision": 0.3069015502240498, "rouge1_precision_stderr": 0.0027141658342019533, "rouge1_recall": 0.39979069436919706, "rouge1_recall_stderr": 0.0027344739468908464, "rouge2_fmeasure": 0.12124769523896647, "rouge2_fmeasure_stderr": 0.0013611141408615495, "rouge2_precision": 0.11881015634283494, "rouge2_precision_stderr": 0.0018726653522764317, "rouge2_recall": 0.1547177292472664, "rouge2_recall_stderr": 0.0018688850569839306, "rougeL_fmeasure": 0.24042839740750466, "rougeL_fmeasure_stderr": 0.0014957834627688047, "rougeL_precision": 0.2310708605355665, "rougeL_precision_stderr": 0.0022062598471417403, "rougeL_recall": 0.3039710432903314, "rougeL_recall_stderr": 0.002265711626940462, "rougeLsum_fmeasure": 0.26693221189807087, "rougeLsum_fmeasure_stderr": 0.0017924495261329944, "rougeLsum_precision": 0.2575158229010334, "rougeLsum_precision_stderr": 0.002504168232503219, "rougeLsum_recall": 0.33420271307698657, "rougeLsum_recall_stderr": 0.002509091259792972}}, "2": {"generate_text_restaurant": {"bleu": 5.798513972951498, "bleu_stderr": 0.11353083630417822, "rouge1_fmeasure": 0.30806587260671714, "rouge1_fmeasure_stderr": 0.0018509005121755077, "rouge1_precision": 0.27602836621141386, "rouge1_precision_stderr": 0.0025780345869436143, "rouge1_recall": 0.4181131170949761, "rouge1_recall_stderr": 0.0026506272040465527, "rouge2_fmeasure": 0.12337486765629936, "rouge2_fmeasure_stderr": 0.0013085936094396561, "rouge2_precision": 0.11242493035118595, "rouge2_precision_stderr": 0.0017273889338398733, "rouge2_recall": 0.17096478516816419, "rouge2_recall_stderr": 0.0019293105165237693, "rougeL_fmeasure": 0.24343008869727828, "rougeL_fmeasure_stderr": 0.0014161383440201198, "rougeL_precision": 0.21692521379325555, "rougeL_precision_stderr": 0.0020430932459005492, "rougeL_recall": 0.33431954510893935, "rougeL_recall_stderr": 0.0022474731694641457, "rougeLsum_fmeasure": 0.2593626081415107, "rougeLsum_fmeasure_stderr": 0.0017672461865662792, "rougeLsum_precision": 0.23257813200591104, "rougeLsum_precision_stderr": 0.0023360478957229073, "rougeLsum_recall": 0.3524929035089362, "rougeLsum_recall_stderr": 0.0025454158780705265}}, "3": {"generate_text_restaurant": {"bleu": 5.644092780950039, "bleu_stderr": 0.10217788685749982, "rouge1_fmeasure": 0.2981344592034621, "rouge1_fmeasure_stderr": 0.0018206530175075195, "rouge1_precision": 0.26161576269851167, "rouge1_precision_stderr": 0.0025136188998387504, "rouge1_recall": 0.41515437679947936, "rouge1_recall_stderr": 0.002598826549494006, "rouge2_fmeasure": 0.11947929128220935, "rouge2_fmeasure_stderr": 0.0012973693582640367, "rouge2_precision": 0.10693721487632077, "rouge2_precision_stderr": 0.0017057516502692433, "rouge2_recall": 0.16981690105478955, "rouge2_recall_stderr": 0.0019012605105245895, "rougeL_fmeasure": 0.23991261995087904, "rougeL_fmeasure_stderr": 0.0014219136572907404, "rougeL_precision": 0.2094840503016106, "rougeL_precision_stderr": 0.002037886584044074, "rougeL_recall": 0.3376907481718358, "rougeL_recall_stderr": 0.00220926835759776, "rougeLsum_fmeasure": 0.25177947103229636, "rougeLsum_fmeasure_stderr": 0.001736956932091685, "rougeLsum_precision": 0.22116618474928101, "rougeLsum_precision_stderr": 0.00229609611848074, "rougeLsum_recall": 0.35126017567747847, "rougeLsum_recall_stderr": 0.002506017472827367}}, "4": {"generate_text_restaurant": {"bleu": 5.7499537608526206, "bleu_stderr": 0.0771735259601375, "rouge1_fmeasure": 0.297032269913346, "rouge1_fmeasure_stderr": 0.0018374797196724821, "rouge1_precision": 0.25565023567980505, "rouge1_precision_stderr": 0.0024296319398495005, "rouge1_recall": 0.4223930509739377, "rouge1_recall_stderr": 0.0025959915251734665, "rouge2_fmeasure": 0.12065447384924378, "rouge2_fmeasure_stderr": 0.001292230076177851, "rouge2_precision": 0.10591522249436582, "rouge2_precision_stderr": 0.001656138422232947, "rouge2_recall": 0.17476583770251305, "rouge2_recall_stderr": 0.0019174634136014039, "rougeL_fmeasure": 0.2401166198393427, "rougeL_fmeasure_stderr": 0.001412545210957851, "rougeL_precision": 0.2057296852438049, "rougeL_precision_stderr": 0.0019458009062281374, "rougeL_recall": 0.3452387295232376, "rougeL_recall_stderr": 0.0022232954316674606, "rougeLsum_fmeasure": 0.2520913436920952, "rougeLsum_fmeasure_stderr": 0.001756285809527599, "rougeLsum_precision": 0.2170829438014025, "rougeLsum_precision_stderr": 0.0022139919637352325, "rougeLsum_recall": 0.359511646806021, "rougeLsum_recall_stderr": 0.0025629445270113453}}, "5": {"generate_text_restaurant": {"bleu": 5.770537159308962, "bleu_stderr": 0.1190361381685094, "rouge1_fmeasure": 0.2987490942442688, "rouge1_fmeasure_stderr": 0.00182958925425156, "rouge1_precision": 0.25787672074394796, "rouge1_precision_stderr": 0.0025328256284091236, "rouge1_recall": 0.42573900503618045, "rouge1_recall_stderr": 0.0025754554062627877, "rouge2_fmeasure": 0.12169295522428568, "rouge2_fmeasure_stderr": 0.0012994307062877601, "rouge2_precision": 0.10790420126833489, "rouge2_precision_stderr": 0.001769950634717068, "rouge2_recall": 0.1764978054536251, "rouge2_recall_stderr": 0.001953358091932576, "rougeL_fmeasure": 0.24138350753763696, "rougeL_fmeasure_stderr": 0.0014118485855993332, "rougeL_precision": 0.207955556140787, "rougeL_precision_stderr": 0.002097923926132232, "rougeL_recall": 0.3476137840160232, "rougeL_recall_stderr": 0.002207282217829847, "rougeLsum_fmeasure": 0.2537764861825883, "rougeLsum_fmeasure_stderr": 0.0017644696653914508, "rougeLsum_precision": 0.21954740035518447, "rougeLsum_precision_stderr": 0.0023503093866769544, "rougeLsum_recall": 0.3624191463006945, "rougeLsum_recall_stderr": 0.0025392023747063696}}}, "gem_xsum": {"0": {"article_DOC_summary": {"bleu": 1.2602613828624476, "bleu_stderr": 0.08741245069026914, "rouge1_fmeasure": 0.1924128186381312, "rouge1_fmeasure_stderr": 0.002360900852656541, "rouge1_precision": 0.14542424202725895, "rouge1_precision_stderr": 0.0022138246399507205, "rouge1_recall": 0.31877105379992854, "rouge1_recall_stderr": 0.0039014668311384846, "rouge2_fmeasure": 0.035715714855404174, "rouge2_fmeasure_stderr": 0.0012470772810957468, "rouge2_precision": 0.026751288404993658, "rouge2_precision_stderr": 0.0010068959458770191, "rouge2_recall": 0.06119647795475897, "rouge2_recall_stderr": 0.0021992283140675147, "rougeL_fmeasure": 0.14397207180406998, "rougeL_fmeasure_stderr": 0.0017392037354323953, "rougeL_precision": 0.10850993070385385, "rougeL_precision_stderr": 0.0016022951483510026, "rougeL_recall": 0.2403257780307599, "rougeL_recall_stderr": 0.0030478006648468224, "rougeLsum_fmeasure": 0.1513854308550901, "rougeLsum_fmeasure_stderr": 0.0018706736809661465, "rougeLsum_precision": 0.1137602974676654, "rougeLsum_precision_stderr": 0.0016663613584011713, "rougeLsum_recall": 0.25349408376272603, "rougeLsum_recall_stderr": 0.0033388300752575585}}, "1": {"article_DOC_summary": {"bleu": 0.7915703643644384, "bleu_stderr": 0.08396451150549139, "rouge1_fmeasure": 0.14848707861095392, "rouge1_fmeasure_stderr": 0.0020468594975290248, "rouge1_precision": 0.10549993650520251, "rouge1_precision_stderr": 0.00153501677078187, "rouge1_recall": 0.2612212727377519, "rouge1_recall_stderr": 0.0034404286739595498, "rouge2_fmeasure": 0.01983861975775417, "rouge2_fmeasure_stderr": 0.0009966264701985932, "rouge2_precision": 0.013994761205987642, "rouge2_precision_stderr": 0.0007149071339383721, "rouge2_recall": 0.0356140526531422, "rouge2_recall_stderr": 0.0017994780886659853, "rougeL_fmeasure": 0.11531599073392822, "rougeL_fmeasure_stderr": 0.0015026013618598068, "rougeL_precision": 0.08181009058637802, "rougeL_precision_stderr": 0.0011239080238855375, "rougeL_recall": 0.20392678730897415, "rougeL_recall_stderr": 0.002600805826506937, "rougeLsum_fmeasure": 0.12077280177911864, "rougeLsum_fmeasure_stderr": 0.0016322822837075467, "rougeLsum_precision": 0.08559803726047839, "rougeLsum_precision_stderr": 0.001213987918870468, "rougeLsum_recall": 0.21400310748327384, "rougeLsum_recall_stderr": 0.0028528494274868274}}, "2": {"article_DOC_summary": {"bleu": 0.6502670718184665, "bleu_stderr": 0.05324899628422249, "rouge1_fmeasure": 0.14783482736166878, "rouge1_fmeasure_stderr": 0.001930898165701915, "rouge1_precision": 0.10471570168180548, "rouge1_precision_stderr": 0.0014494215119621229, "rouge1_recall": 0.2620545799252738, "rouge1_recall_stderr": 0.003320038801060601, "rouge2_fmeasure": 0.018873329322073275, "rouge2_fmeasure_stderr": 0.0008955667212919246, "rouge2_precision": 0.01319945934793176, "rouge2_precision_stderr": 0.0006302627050860287, "rouge2_recall": 0.03471557162965618, "rouge2_recall_stderr": 0.0016776406415917023, "rougeL_fmeasure": 0.11600786897853718, "rougeL_fmeasure_stderr": 0.0014481058046010048, "rougeL_precision": 0.08197306181617371, "rougeL_precision_stderr": 0.0010777654445218213, "rougeL_recall": 0.2071426347373322, "rougeL_recall_stderr": 0.0026041548046999877, "rougeLsum_fmeasure": 0.12019939004505038, "rougeLsum_fmeasure_stderr": 0.0016060029611780855, "rougeLsum_precision": 0.08489744619220965, "rougeLsum_precision_stderr": 0.0011830647260639108, "rougeLsum_recall": 0.21467503234909532, "rougeLsum_recall_stderr": 0.002893408444556316}}, "3": {"article_DOC_summary": {"bleu": 0.72650775578876, "bleu_stderr": 0.07009722650167388, "rouge1_fmeasure": 0.1434515966047625, "rouge1_fmeasure_stderr": 0.0021396059501441697, "rouge1_precision": 0.10410860827262407, "rouge1_precision_stderr": 0.0016985601546784064, "rouge1_recall": 0.24975935094410306, "rouge1_recall_stderr": 0.0036359468821554417, "rouge2_fmeasure": 0.01863408799342264, "rouge2_fmeasure_stderr": 0.0009121268268702102, "rouge2_precision": 0.0133838272101195, "rouge2_precision_stderr": 0.0006651947823416613, "rouge2_recall": 0.032957650415980116, "rouge2_recall_stderr": 0.0016410836459370027, "rougeL_fmeasure": 0.11028077942863275, "rougeL_fmeasure_stderr": 0.0015625007588984398, "rougeL_precision": 0.07992461082726765, "rougeL_precision_stderr": 0.0012408675788602088, "rougeL_recall": 0.1932235805685923, "rougeL_recall_stderr": 0.00277498209308085, "rougeLsum_fmeasure": 0.11596810997110246, "rougeLsum_fmeasure_stderr": 0.001710823422300248, "rougeLsum_precision": 0.0839932835001092, "rougeLsum_precision_stderr": 0.0013382454039087637, "rougeLsum_recall": 0.20290901214848292, "rougeLsum_recall_stderr": 0.0029990659468279056}}, "4": {"article_DOC_summary": {"bleu": 0.27256554319567566, "bleu_stderr": 0.05393365990560443, "rouge1_fmeasure": 0.037884638019230664, "rouge1_fmeasure_stderr": 0.00214775480739452, "rouge1_precision": 0.03133602840154907, "rouge1_precision_stderr": 0.001987959380677703, "rouge1_recall": 0.06067401952247452, "rouge1_recall_stderr": 0.003487892178028924, "rouge2_fmeasure": 0.0043759041403374135, "rouge2_fmeasure_stderr": 0.0005183680894634575, "rouge2_precision": 0.0034573763117096636, "rouge2_precision_stderr": 0.00044354666596204615, "rouge2_recall": 0.007156768365840787, "rouge2_recall_stderr": 0.0008508883614159644, "rougeL_fmeasure": 0.029266330660064416, "rougeL_fmeasure_stderr": 0.0016348070626843912, "rougeL_precision": 0.024472567308614246, "rougeL_precision_stderr": 0.0015926598243951066, "rougeL_recall": 0.04698578958663985, "rougeL_recall_stderr": 0.002673075415704531, "rougeLsum_fmeasure": 0.031041105487741426, "rougeLsum_fmeasure_stderr": 0.0017460208416643014, "rougeLsum_precision": 0.0257721881730792, "rougeLsum_precision_stderr": 0.0016575889068278311, "rougeLsum_recall": 0.04994885638600292, "rougeLsum_recall_stderr": 0.0028614395409444103}}, "5": {"article_DOC_summary": {"bleu": 2.5634857131422677e-38, "bleu_stderr": 1.7875744611015253e-32, "rouge1_fmeasure": 0.0022183238269151938, "rouge1_fmeasure_stderr": 0.0006462435715584798, "rouge1_precision": 0.002422654460959852, "rouge1_precision_stderr": 0.000701445835208553, "rouge1_recall": 0.002150434002930073, "rouge1_recall_stderr": 0.0006364013868075673, "rouge2_fmeasure": 0.00044144904818645863, "rouge2_fmeasure_stderr": 0.00024927107535141214, "rouge2_precision": 0.00047185826875061065, "rouge2_precision_stderr": 0.00025359131866297053, "rouge2_recall": 0.00042238421955403087, "rouge2_recall_stderr": 0.00024978354101036374, "rougeL_fmeasure": 0.0018677137784396751, "rougeL_fmeasure_stderr": 0.0005453913617070764, "rougeL_precision": 0.0020288572682842206, "rougeL_precision_stderr": 0.000585169484066717, "rougeL_recall": 0.0018274673120388537, "rougeL_recall_stderr": 0.0005474767964183582, "rougeLsum_fmeasure": 0.0019066970935807948, "rougeLsum_fmeasure_stderr": 0.0005494437621613826, "rougeLsum_precision": 0.00207399584371078, "rougeLsum_precision_stderr": 0.0005893776256546286, "rougeLsum_recall": 0.001865187279004104, "rougeLsum_recall_stderr": 0.0005528638398211417}}}}