| {"GEM/web_nlg_en": {"0": {"PALM_prompt": {"bleu": 0.33272479915628694, "bleu_stderr": 0.031796098410938015, "rouge1_fmeasure": 0.09992028750901691, "rouge1_fmeasure_stderr": 0.002068624719484398, "rouge1_precision": 0.06768598529946503, "rouge1_precision_stderr": 0.001826760753754374, "rouge1_recall": 0.273245918626827, "rouge1_recall_stderr": 0.004811539102181524, "rouge2_fmeasure": 0.047572357019245066, "rouge2_fmeasure_stderr": 0.0012754558397189623, "rouge2_precision": 0.0319815601358353, "rouge2_precision_stderr": 0.001123592878248015, "rouge2_recall": 0.132780352400067, "rouge2_recall_stderr": 0.0031651283586402535, "rougeL_fmeasure": 0.09656759025734364, "rougeL_fmeasure_stderr": 0.0019482031642887698, "rougeL_precision": 0.06526863289287767, "rougeL_precision_stderr": 0.00173604911565671, "rougeL_recall": 0.2659429125520888, "rougeL_recall_stderr": 0.004693559342531821, "rougeLsum_fmeasure": 0.09550510540717662, "rougeLsum_fmeasure_stderr": 0.0019437957791240722, "rougeLsum_precision": 0.06475652685202478, "rougeLsum_precision_stderr": 0.001750562854208181, "rougeLsum_recall": 0.261555669425398, "rougeLsum_recall_stderr": 0.004531537846674438}}, "1": {"PALM_prompt": {"bleu": 0.5102447245370249, "bleu_stderr": 0.035376593830697835, "rouge1_fmeasure": 0.11038438449277037, "rouge1_fmeasure_stderr": 0.0019607246874588217, "rouge1_precision": 0.07172631396783712, "rouge1_precision_stderr": 0.0015940647947642393, "rouge1_recall": 0.3498874090683673, "rouge1_recall_stderr": 0.005494538712125141, "rouge2_fmeasure": 0.0513340131604287, "rouge2_fmeasure_stderr": 0.0012161196627700137, "rouge2_precision": 0.03374360598633707, "rouge2_precision_stderr": 0.0011472248278029387, "rouge2_recall": 0.17065910212771632, "rouge2_recall_stderr": 0.0037615577096519314, "rougeL_fmeasure": 0.10363295036370204, "rougeL_fmeasure_stderr": 0.0017764857744676573, "rougeL_precision": 0.06735170136224546, "rougeL_precision_stderr": 0.0014692804169579693, "rougeL_recall": 0.32775015583004236, "rougeL_recall_stderr": 0.005027007036378035, "rougeLsum_fmeasure": 0.10476642693447911, "rougeLsum_fmeasure_stderr": 0.001844638754248624, "rougeLsum_precision": 0.06821168744641012, "rougeLsum_precision_stderr": 0.0015257497030318006, "rougeLsum_recall": 0.3303827812174427, "rougeLsum_recall_stderr": 0.005034171208777432}}, "2": {"PALM_prompt": {"bleu": 0.6028097084858823, "bleu_stderr": 0.03400607345942724, "rouge1_fmeasure": 0.11747286047545925, "rouge1_fmeasure_stderr": 0.0018369017696682527, "rouge1_precision": 0.07447162662420612, "rouge1_precision_stderr": 0.001363119521612849, "rouge1_recall": 0.39133197093760397, "rouge1_recall_stderr": 0.005455286809780116, "rouge2_fmeasure": 0.054159534529018366, "rouge2_fmeasure_stderr": 0.00112831864459488, "rouge2_precision": 0.03418924065620199, "rouge2_precision_stderr": 0.0008008890429324677, "rouge2_recall": 0.19324361036894205, "rouge2_recall_stderr": 0.0038848529810624356, "rougeL_fmeasure": 0.10807779989120546, "rougeL_fmeasure_stderr": 0.001612487862874725, "rougeL_precision": 0.06854684035035577, "rougeL_precision_stderr": 0.0012086804724451806, "rougeL_recall": 0.35968605242390533, "rougeL_recall_stderr": 0.004868740565794037, "rougeLsum_fmeasure": 0.11132296857949775, "rougeLsum_fmeasure_stderr": 0.0017256589790344656, "rougeLsum_precision": 0.0706586243525616, "rougeLsum_precision_stderr": 0.0012889308612371538, "rougeLsum_recall": 0.36945068896305344, "rougeLsum_recall_stderr": 0.0050409156545949945}}, "3": {"PALM_prompt": {"bleu": 0.701781042691669, "bleu_stderr": 0.028304269361164428, "rouge1_fmeasure": 0.1186720883935396, "rouge1_fmeasure_stderr": 0.0018557604964665015, "rouge1_precision": 0.07483297992459019, "rouge1_precision_stderr": 0.0013297778153553014, "rouge1_recall": 0.40075245309368346, "rouge1_recall_stderr": 0.005510805436391809, "rouge2_fmeasure": 0.05434522629151618, "rouge2_fmeasure_stderr": 0.0011369092672670533, "rouge2_precision": 0.03405829473639484, "rouge2_precision_stderr": 0.0007867378650100502, "rouge2_recall": 0.1965036741041513, "rouge2_recall_stderr": 0.0039013830928258273, "rougeL_fmeasure": 0.10798420755086514, "rougeL_fmeasure_stderr": 0.001585937192657532, "rougeL_precision": 0.06814102346988, "rougeL_precision_stderr": 0.001142595819228343, "rougeL_recall": 0.36375561641075393, "rougeL_recall_stderr": 0.004784629751764729, "rougeLsum_fmeasure": 0.11180266475563037, "rougeLsum_fmeasure_stderr": 0.0017161756564434687, "rougeLsum_precision": 0.0705542561432147, "rougeLsum_precision_stderr": 0.0012322784221801353, "rougeLsum_recall": 0.376368921472397, "rougeLsum_recall_stderr": 0.005042206855487164}}, "4": {"PALM_prompt": {"bleu": 0.7208477776174064, "bleu_stderr": 0.03611939053214278, "rouge1_fmeasure": 0.12065545317279747, "rouge1_fmeasure_stderr": 0.0017878857789550631, "rouge1_precision": 0.07573522475977945, "rouge1_precision_stderr": 0.0012828287982675156, "rouge1_recall": 0.4140707617730325, "rouge1_recall_stderr": 0.005500874400250013, "rouge2_fmeasure": 0.05546852434740693, "rouge2_fmeasure_stderr": 0.001093391566003447, "rouge2_precision": 0.03464259052791206, "rouge2_precision_stderr": 0.0007595549203652654, "rouge2_recall": 0.20555557401100102, "rouge2_recall_stderr": 0.003919174647287531, "rougeL_fmeasure": 0.10954384971885704, "rougeL_fmeasure_stderr": 0.001541389309718117, "rougeL_precision": 0.06882833861974198, "rougeL_precision_stderr": 0.00110954922342777, "rougeL_recall": 0.37506782401870103, "rougeL_recall_stderr": 0.004831464763832598, "rougeLsum_fmeasure": 0.11373501038504552, "rougeLsum_fmeasure_stderr": 0.0016710119042870925, "rougeLsum_precision": 0.07144735748031365, "rougeLsum_precision_stderr": 0.0011999248890901264, "rougeLsum_recall": 0.3887273820866732, "rougeLsum_recall_stderr": 0.005052183598911252}}, "5": {"PALM_prompt": {"bleu": 0.8098840843933562, "bleu_stderr": 0.042922709276963275, "rouge1_fmeasure": 0.12112590895694009, "rouge1_fmeasure_stderr": 0.0016877211094516577, "rouge1_precision": 0.07551077098651218, "rouge1_precision_stderr": 0.0011967463119907174, "rouge1_recall": 0.42778952645041607, "rouge1_recall_stderr": 0.005509208476502683, "rouge2_fmeasure": 0.05638496281385114, "rouge2_fmeasure_stderr": 0.0010526694616578302, "rouge2_precision": 0.03488380229207791, "rouge2_precision_stderr": 0.0007164646591878178, "rouge2_recall": 0.21683909270039745, "rouge2_recall_stderr": 0.0040700970178128, "rougeL_fmeasure": 0.1091505948569381, "rougeL_fmeasure_stderr": 0.0014719382275165554, "rougeL_precision": 0.06816852013471421, "rougeL_precision_stderr": 0.0010570419074259674, "rougeL_recall": 0.3851255216729155, "rougeL_recall_stderr": 0.004804722289936786, "rougeLsum_fmeasure": 0.1139947508286874, "rougeLsum_fmeasure_stderr": 0.0015813085492093937, "rougeLsum_precision": 0.07111730496416463, "rougeLsum_precision_stderr": 0.0011271521292987115, "rougeLsum_recall": 0.40225015185589585, "rougeLsum_recall_stderr": 0.005071744746719108}}}, "GEM/wiki_lingua_en": {"0": {"tldr_en": {"bleu": 1.604770833205388, "bleu_stderr": 0.045152527476120426, "rouge1_fmeasure": 0.17820031429089941, "rouge1_fmeasure_stderr": 0.001867331386262004, "rouge1_precision": 0.15167532178589505, "rouge1_precision_stderr": 0.0019073207185280718, "rouge1_recall": 0.2612333406333799, "rouge1_recall_stderr": 0.0026793907173360246, "rouge2_fmeasure": 0.03716728942279169, "rouge2_fmeasure_stderr": 0.0008623486309823396, "rouge2_precision": 0.03148570054286659, "rouge2_precision_stderr": 0.0007720646786309003, "rouge2_recall": 0.05626578766960683, "rouge2_recall_stderr": 0.0014278552081629383, "rougeL_fmeasure": 0.13833033412198834, "rougeL_fmeasure_stderr": 0.0013282918104537548, "rougeL_precision": 0.116140614745089, "rougeL_precision_stderr": 0.0013156638447678107, "rougeL_recall": 0.2083623246576857, "rougeL_recall_stderr": 0.0021996516173952707, "rougeLsum_fmeasure": 0.16463728733959723, "rougeLsum_fmeasure_stderr": 0.0017151648189316772, "rougeLsum_precision": 0.13994812048897234, "rougeLsum_precision_stderr": 0.0017518520260318953, "rougeLsum_recall": 0.2422441673257693, "rougeLsum_recall_stderr": 0.0024926109810662115}}, "1": {"tldr_en": {"bleu": 2.3579628914986084, "bleu_stderr": 0.06443336501226987, "rouge1_fmeasure": 0.20675601444211894, "rouge1_fmeasure_stderr": 0.0019509220985923807, "rouge1_precision": 0.17995455895644027, "rouge1_precision_stderr": 0.0021143646937022468, "rouge1_recall": 0.29822507703809786, "rouge1_recall_stderr": 0.0029202005379262794, "rouge2_fmeasure": 0.0485299590695294, "rouge2_fmeasure_stderr": 0.000987435381157907, "rouge2_precision": 0.04280457785161096, "rouge2_precision_stderr": 0.0010705605908791504, "rouge2_recall": 0.07256480707864589, "rouge2_recall_stderr": 0.0016883207002489, "rougeL_fmeasure": 0.14838617751760952, "rougeL_fmeasure_stderr": 0.0013193585886492735, "rougeL_precision": 0.128484042233791, "rougeL_precision_stderr": 0.0014903515496972157, "rougeL_recall": 0.21893094707653085, "rougeL_recall_stderr": 0.0022685657736807928, "rougeLsum_fmeasure": 0.19330419331545362, "rougeLsum_fmeasure_stderr": 0.001817315871702104, "rougeLsum_precision": 0.1682253075781992, "rougeLsum_precision_stderr": 0.001983258112076011, "rougeLsum_recall": 0.27945450640399006, "rougeLsum_recall_stderr": 0.002751044005784169}}, "2": {"tldr_en": {"bleu": 2.770701026929389, "bleu_stderr": 0.055755441860674826, "rouge1_fmeasure": 0.21447969004311607, "rouge1_fmeasure_stderr": 0.0018895718255246762, "rouge1_precision": 0.1942548807242778, "rouge1_precision_stderr": 0.0023454682458510967, "rouge1_recall": 0.3038516433424921, "rouge1_recall_stderr": 0.0028161999694894368, "rouge2_fmeasure": 0.05328365330541802, "rouge2_fmeasure_stderr": 0.0010288709039921085, "rouge2_precision": 0.0492948803130678, "rouge2_precision_stderr": 0.0011990391917610706, "rouge2_recall": 0.0782436349256461, "rouge2_recall_stderr": 0.0017608820777292064, "rougeL_fmeasure": 0.15374474737766516, "rougeL_fmeasure_stderr": 0.0013038739578348723, "rougeL_precision": 0.1390228041509367, "rougeL_precision_stderr": 0.0017234767147472074, "rougeL_recall": 0.22270032621786837, "rougeL_recall_stderr": 0.002252792096654515, "rougeLsum_fmeasure": 0.2018034121125251, "rougeLsum_fmeasure_stderr": 0.0017698133555769187, "rougeLsum_precision": 0.18265776299811193, "rougeLsum_precision_stderr": 0.0022101445170749252, "rougeLsum_recall": 0.28667373859931605, "rougeLsum_recall_stderr": 0.002687218604461664}}, "3": {"tldr_en": {"bleu": 2.6943492797886797, "bleu_stderr": 0.048945628141051856, "rouge1_fmeasure": 0.17584661717144687, "rouge1_fmeasure_stderr": 0.0022080154978502656, "rouge1_precision": 0.16605472663049203, "rouge1_precision_stderr": 0.0026215736776626004, "rouge1_recall": 0.24674896622444079, "rouge1_recall_stderr": 0.0032942062409122403, "rouge2_fmeasure": 0.04324074407846396, "rouge2_fmeasure_stderr": 0.001030508940585308, "rouge2_precision": 0.041252526415028114, "rouge2_precision_stderr": 0.0012562811469129071, "rouge2_recall": 0.06385056201459363, "rouge2_recall_stderr": 0.0017227611606126488, "rougeL_fmeasure": 0.12719556123913905, "rougeL_fmeasure_stderr": 0.0015628923302645156, "rougeL_precision": 0.12107072019854664, "rougeL_precision_stderr": 0.0020206323069935596, "rougeL_recall": 0.18199308221887076, "rougeL_recall_stderr": 0.0025743010221870987, "rougeLsum_fmeasure": 0.166023927031211, "rougeLsum_fmeasure_stderr": 0.0020868492894240698, "rougeLsum_precision": 0.15696755228304862, "rougeLsum_precision_stderr": 0.0025037796725520395, "rougeLsum_recall": 0.23345046038796602, "rougeLsum_recall_stderr": 0.003144339747645053}}, "4": {"tldr_en": {"bleu": 0.5943697556411244, "bleu_stderr": 0.030734589500314064, "rouge1_fmeasure": 0.05454947380142532, "rouge1_fmeasure_stderr": 0.001847757669359123, "rouge1_precision": 0.05342346190272065, "rouge1_precision_stderr": 0.002056550316894281, "rouge1_recall": 0.07978774494235341, "rouge1_recall_stderr": 0.0028101467900972705, "rouge2_fmeasure": 0.01286346881894465, "rouge2_fmeasure_stderr": 0.0006471740657104415, "rouge2_precision": 0.012258350990130428, "rouge2_precision_stderr": 0.0007138900312061555, "rouge2_recall": 0.02028789716505487, "rouge2_recall_stderr": 0.0011428305900431244, "rougeL_fmeasure": 0.0407204750127799, "rougeL_fmeasure_stderr": 0.0013676744674585327, "rougeL_precision": 0.040366367324606266, "rougeL_precision_stderr": 0.0016113191055682687, "rougeL_recall": 0.06061271598925825, "rougeL_recall_stderr": 0.0021836846333784096, "rougeLsum_fmeasure": 0.05108474776360767, "rougeLsum_fmeasure_stderr": 0.0017328648234254131, "rougeLsum_precision": 0.050133371793595845, "rougeLsum_precision_stderr": 0.0019436034391785793, "rougeLsum_recall": 0.07473111376648439, "rougeLsum_recall_stderr": 0.0026329914241005055}}, "5": {"tldr_en": {"bleu": 1.5595918572619473e-06, "bleu_stderr": 2.8487471872210672e-06, "rouge1_fmeasure": 0.008385094317414335, "rouge1_fmeasure_stderr": 0.0007962608828602142, "rouge1_precision": 0.008364381665919872, "rouge1_precision_stderr": 0.0008819285241796705, "rouge1_recall": 0.012634998947429131, "rouge1_recall_stderr": 0.0012520411703047264, "rouge2_fmeasure": 0.0020213111085609944, "rouge2_fmeasure_stderr": 0.0002694978086459766, "rouge2_precision": 0.0019514480000772428, "rouge2_precision_stderr": 0.0002950485643713033, "rouge2_recall": 0.0034586914827538628, "rouge2_recall_stderr": 0.000553626619531344, "rougeL_fmeasure": 0.006545584095103677, "rougeL_fmeasure_stderr": 0.0006266707040781551, "rougeL_precision": 0.006554032979312583, "rougeL_precision_stderr": 0.0006990429427874044, "rougeL_recall": 0.010080116076976064, "rougeL_recall_stderr": 0.0010433208473045565, "rougeLsum_fmeasure": 0.007958529393460171, "rougeLsum_fmeasure_stderr": 0.0007541972102063722, "rougeLsum_precision": 0.007976144780102256, "rougeLsum_precision_stderr": 0.0008419903349386873, "rougeLsum_recall": 0.012040227491122851, "rougeLsum_recall_stderr": 0.001201302499319246}}}, "e2e_nlg_cleaned": {"0": {"generate_text_restaurant": {"bleu": 0.01599277764818925, "bleu_stderr": 0.004308927933825235, "rouge1_fmeasure": 0.016178489257483206, "rouge1_fmeasure_stderr": 0.0003336557540954231, "rouge1_precision": 0.012870158730159176, "rouge1_precision_stderr": 0.00026604075009303314, "rouge1_recall": 0.02306192594226545, "rouge1_recall_stderr": 0.0005060585834775515, "rouge2_fmeasure": 0.00012949433318118156, "rouge2_fmeasure_stderr": 3.494334474550083e-05, "rouge2_precision": 0.00011382113821138212, "rouge2_precision_stderr": 3.0353975217624302e-05, "rouge2_recall": 0.00016007109878338666, "rouge2_recall_stderr": 4.471587603586543e-05, "rougeL_fmeasure": 0.016178489257483206, "rougeL_fmeasure_stderr": 0.0003336557540954231, "rougeL_precision": 0.012870158730159176, "rougeL_precision_stderr": 0.00026604075009303314, "rougeL_recall": 0.02306192594226545, "rougeL_recall_stderr": 0.0005060585834775515, "rougeLsum_fmeasure": 0.015580467425438196, "rougeLsum_fmeasure_stderr": 0.0003114685494407546, "rougeLsum_precision": 0.012401587301587743, "rougeLsum_precision_stderr": 0.0002495014907480676, "rougeLsum_recall": 0.022186928253083223, "rougeLsum_recall_stderr": 0.00046927560289039864}}, "1": {"generate_text_restaurant": {"bleu": 9.29730492833567, "bleu_stderr": 0.07258438562915104, "rouge1_fmeasure": 0.40179356473852385, "rouge1_fmeasure_stderr": 0.0024053635164423257, "rouge1_precision": 0.4508609495206719, "rouge1_precision_stderr": 0.0036311478842959532, "rouge1_recall": 0.4256279851535847, "rouge1_recall_stderr": 0.002998743529748849, "rouge2_fmeasure": 0.1821558520162302, "rouge2_fmeasure_stderr": 0.0018839477104031566, "rouge2_precision": 0.20803358909759323, "rouge2_precision_stderr": 0.002540052178876273, "rouge2_recall": 0.19234516196309973, "rouge2_recall_stderr": 0.0021041392938787457, "rougeL_fmeasure": 0.3001108360092531, "rougeL_fmeasure_stderr": 0.0019304143016397508, "rougeL_precision": 0.33647256551604726, "rougeL_precision_stderr": 0.0029522675564527113, "rougeL_recall": 0.32133682780546957, "rougeL_recall_stderr": 0.0025106371554624155, "rougeLsum_fmeasure": 0.3272696975463691, "rougeLsum_fmeasure_stderr": 0.002280428848910135, "rougeLsum_precision": 0.36851923372760476, "rougeLsum_precision_stderr": 0.0033065014951933927, "rougeLsum_recall": 0.3458837990441542, "rougeLsum_recall_stderr": 0.0027230707350231853}}, "2": {"generate_text_restaurant": {"bleu": 12.759775802861823, "bleu_stderr": 0.1293139727386451, "rouge1_fmeasure": 0.4496590978589395, "rouge1_fmeasure_stderr": 0.002303602978907222, "rouge1_precision": 0.5296073064762413, "rouge1_precision_stderr": 0.0033783994941725144, "rouge1_recall": 0.4363790698973518, "rouge1_recall_stderr": 0.0029267544023528365, "rouge2_fmeasure": 0.2160790254378622, "rouge2_fmeasure_stderr": 0.001955317829071995, "rouge2_precision": 0.25851059818334, "rouge2_precision_stderr": 0.0026408591114483963, "rouge2_recall": 0.20978543572844377, "rouge2_recall_stderr": 0.002146572930760848, "rougeL_fmeasure": 0.33140579758047195, "rougeL_fmeasure_stderr": 0.0020369186351820263, "rougeL_precision": 0.39232032536879197, "rougeL_precision_stderr": 0.0029964581011695346, "rougeL_recall": 0.3219131393183246, "rougeL_recall_stderr": 0.0024670087975040625, "rougeLsum_fmeasure": 0.3703216404379091, "rougeLsum_fmeasure_stderr": 0.0022909574817028392, "rougeLsum_precision": 0.4374911840880169, "rougeLsum_precision_stderr": 0.0032563934045941744, "rougeLsum_recall": 0.35889049112539584, "rougeLsum_recall_stderr": 0.0027163755824492135}}, "3": {"generate_text_restaurant": {"bleu": 13.39712229435215, "bleu_stderr": 0.2190368432916537, "rouge1_fmeasure": 0.4585328203108971, "rouge1_fmeasure_stderr": 0.0022516911107973987, "rouge1_precision": 0.5434706515030117, "rouge1_precision_stderr": 0.0032446983744738762, "rouge1_recall": 0.43747355273891847, "rouge1_recall_stderr": 0.0028993863830845397, "rouge2_fmeasure": 0.2270812503617402, "rouge2_fmeasure_stderr": 0.0019758386181450292, "rouge2_precision": 0.27356714226869305, "rouge2_precision_stderr": 0.0026390580957758175, "rouge2_recall": 0.21639197788244496, "rouge2_recall_stderr": 0.0021805025438367607, "rougeL_fmeasure": 0.34028277436237736, "rougeL_fmeasure_stderr": 0.0020545641994681512, "rougeL_precision": 0.40618251147113754, "rougeL_precision_stderr": 0.0029740816706799833, "rougeL_recall": 0.3236014788599963, "rougeL_recall_stderr": 0.0024273522496127556, "rougeLsum_fmeasure": 0.38125456908954924, "rougeLsum_fmeasure_stderr": 0.002257169022713513, "rougeLsum_precision": 0.4532770963097311, "rougeLsum_precision_stderr": 0.0031647100865919084, "rougeLsum_recall": 0.36298447462453876, "rougeLsum_recall_stderr": 0.0026887391183781422}}, "4": {"generate_text_restaurant": {"bleu": 13.278538903088437, "bleu_stderr": 0.19304270040523466, "rouge1_fmeasure": 0.4614844218085089, "rouge1_fmeasure_stderr": 0.0021663747761732207, "rouge1_precision": 0.5550942770770999, "rouge1_precision_stderr": 0.00321920680863295, "rouge1_recall": 0.43254174724244665, "rouge1_recall_stderr": 0.0027648654319805638, "rouge2_fmeasure": 0.22970482247017235, "rouge2_fmeasure_stderr": 0.00197438239706358, "rouge2_precision": 0.28123246363040955, "rouge2_precision_stderr": 0.0027007119359494314, "rouge2_recall": 0.2150097554160261, "rouge2_recall_stderr": 0.002138899675268787, "rougeL_fmeasure": 0.3427415979760685, "rougeL_fmeasure_stderr": 0.0020357821149855123, "rougeL_precision": 0.4143281149202266, "rougeL_precision_stderr": 0.002969403717017417, "rougeL_recall": 0.32090483861163693, "rougeL_recall_stderr": 0.0023977607834718777, "rougeLsum_fmeasure": 0.3847530991565415, "rougeLsum_fmeasure_stderr": 0.0022220842320301534, "rougeLsum_precision": 0.46330716929389093, "rougeLsum_precision_stderr": 0.0031399338067163917, "rougeLsum_recall": 0.3607474288264691, "rougeLsum_recall_stderr": 0.002652994557246981}}, "5": {"generate_text_restaurant": {"bleu": 13.349674798491353, "bleu_stderr": 0.2620211666324464, "rouge1_fmeasure": 0.46359996980874846, "rouge1_fmeasure_stderr": 0.0021412883557770652, "rouge1_precision": 0.5580977741060988, "rouge1_precision_stderr": 0.003152695337297477, "rouge1_recall": 0.4318929339624608, "rouge1_recall_stderr": 0.0027232610944967796, "rouge2_fmeasure": 0.2303452786552104, "rouge2_fmeasure_stderr": 0.0019438168093482682, "rouge2_precision": 0.282134536476671, "rouge2_precision_stderr": 0.0026354539351566403, "rouge2_recall": 0.21417820926964778, "rouge2_recall_stderr": 0.0020891541191163186, "rougeL_fmeasure": 0.34414481054807766, "rougeL_fmeasure_stderr": 0.0020332629423129916, "rougeL_precision": 0.416156553657584, "rougeL_precision_stderr": 0.002921110787140179, "rougeL_recall": 0.3201090740050369, "rougeL_recall_stderr": 0.0023555592018131553, "rougeLsum_fmeasure": 0.38760985028639305, "rougeLsum_fmeasure_stderr": 0.002239740316941447, "rougeLsum_precision": 0.46739254821741905, "rougeLsum_precision_stderr": 0.0031264669970885233, "rougeLsum_recall": 0.3608544692904568, "rougeLsum_recall_stderr": 0.0026213087830254975}}}, "gem_xsum": {"0": {"article_DOC_summary": {"bleu": 1.8758881711718112, "bleu_stderr": 0.06414775170791744, "rouge1_fmeasure": 0.20682985522235142, "rouge1_fmeasure_stderr": 0.002563714031203911, "rouge1_precision": 0.15826471323077757, "rouge1_precision_stderr": 0.002220888825623518, "rouge1_recall": 0.33446079519909305, "rouge1_recall_stderr": 0.004514327805033082, "rouge2_fmeasure": 0.04522961690526853, "rouge2_fmeasure_stderr": 0.0015798221742638174, "rouge2_precision": 0.03352875592509948, "rouge2_precision_stderr": 0.0012249216700579001, "rouge2_recall": 0.07724702868679346, "rouge2_recall_stderr": 0.002831153557559276, "rougeL_fmeasure": 0.1540627639559492, "rougeL_fmeasure_stderr": 0.0019062590295789597, "rougeL_precision": 0.1175738942721655, "rougeL_precision_stderr": 0.0016420722284867819, "rougeL_recall": 0.2512371460248057, "rougeL_recall_stderr": 0.003517155084540941, "rougeLsum_fmeasure": 0.16037094135484917, "rougeLsum_fmeasure_stderr": 0.0021767207134326364, "rougeLsum_precision": 0.12200871250100262, "rougeLsum_precision_stderr": 0.0017899421156850875, "rougeLsum_recall": 0.26225586640138876, "rougeLsum_recall_stderr": 0.0040169777118884645}}, "1": {"article_DOC_summary": {"bleu": 1.4877593210481137, "bleu_stderr": 0.0786306768078736, "rouge1_fmeasure": 0.17974510059897553, "rouge1_fmeasure_stderr": 0.002465987111038623, "rouge1_precision": 0.12818817016431805, "rouge1_precision_stderr": 0.0018328880795144842, "rouge1_recall": 0.3134061916653512, "rouge1_recall_stderr": 0.004249929100773614, "rouge2_fmeasure": 0.0373103830110333, "rouge2_fmeasure_stderr": 0.0014354470060085698, "rouge2_precision": 0.026250493846268503, "rouge2_precision_stderr": 0.0010076577262875675, "rouge2_recall": 0.06742089722818025, "rouge2_recall_stderr": 0.002693226728725516, "rougeL_fmeasure": 0.14142245724497754, "rougeL_fmeasure_stderr": 0.001878295390484601, "rougeL_precision": 0.10061028549996975, "rougeL_precision_stderr": 0.0013774691842900675, "rougeL_recall": 0.24845939880798545, "rougeL_recall_stderr": 0.003416347548558214, "rougeLsum_fmeasure": 0.14274126658034353, "rougeLsum_fmeasure_stderr": 0.0020267265379362424, "rougeLsum_precision": 0.10150911522087737, "rougeLsum_precision_stderr": 0.0014800824882477777, "rougeLsum_recall": 0.2508723286793532, "rougeLsum_recall_stderr": 0.003661797386209274}}, "2": {"article_DOC_summary": {"bleu": 1.5028153336333563, "bleu_stderr": 0.07627640892766649, "rouge1_fmeasure": 0.17878904396689269, "rouge1_fmeasure_stderr": 0.00243376415334862, "rouge1_precision": 0.1272806924752953, "rouge1_precision_stderr": 0.0018087494542713912, "rouge1_recall": 0.3130608961268874, "rouge1_recall_stderr": 0.0041974862144461686, "rouge2_fmeasure": 0.03670452685866085, "rouge2_fmeasure_stderr": 0.0014016808833113095, "rouge2_precision": 0.02583921544659326, "rouge2_precision_stderr": 0.0009884044996505668, "rouge2_recall": 0.06617476951559573, "rouge2_recall_stderr": 0.0026088727674303245, "rougeL_fmeasure": 0.1413735388750044, "rougeL_fmeasure_stderr": 0.0018450620692794725, "rougeL_precision": 0.10041567883791579, "rougeL_precision_stderr": 0.0013584120767201249, "rougeL_recall": 0.24945606421737898, "rougeL_recall_stderr": 0.0033610500271998743, "rougeLsum_fmeasure": 0.1419412969578001, "rougeLsum_fmeasure_stderr": 0.0019890982108612416, "rougeLsum_precision": 0.10073064727294082, "rougeLsum_precision_stderr": 0.0014545958847864858, "rougeLsum_recall": 0.2508016791258512, "rougeLsum_recall_stderr": 0.003602192602128567}}, "3": {"article_DOC_summary": {"bleu": 1.4368429875503554, "bleu_stderr": 0.06985209662692778, "rouge1_fmeasure": 0.17306626516595003, "rouge1_fmeasure_stderr": 0.002606230170311302, "rouge1_precision": 0.12623940374443, "rouge1_precision_stderr": 0.0020446872317856236, "rouge1_recall": 0.2970674436926099, "rouge1_recall_stderr": 0.004510700325635104, "rouge2_fmeasure": 0.035237949376792976, "rouge2_fmeasure_stderr": 0.0013859609116877547, "rouge2_precision": 0.025227030531171757, "rouge2_precision_stderr": 0.00099984133264785, "rouge2_recall": 0.062156816006725055, "rouge2_recall_stderr": 0.0025180978338057826, "rougeL_fmeasure": 0.1364033778870308, "rougeL_fmeasure_stderr": 0.0019668305545097802, "rougeL_precision": 0.09928754777119025, "rougeL_precision_stderr": 0.0015425645112311069, "rougeL_recall": 0.23556252311929232, "rougeL_recall_stderr": 0.003514098352558134, "rougeLsum_fmeasure": 0.13711597851384225, "rougeLsum_fmeasure_stderr": 0.002115039571938244, "rougeLsum_precision": 0.09980705574148897, "rougeLsum_precision_stderr": 0.0016450051443727947, "rougeLsum_recall": 0.23669283330652355, "rougeLsum_recall_stderr": 0.0037461804498405958}}, "4": {"article_DOC_summary": {"bleu": 0.6717545873809246, "bleu_stderr": 0.11330796657627773, "rouge1_fmeasure": 0.048983292472562175, "rouge1_fmeasure_stderr": 0.0027644367309486977, "rouge1_precision": 0.04214614218832052, "rouge1_precision_stderr": 0.0026107746281583345, "rouge1_recall": 0.07655987772910962, "rouge1_recall_stderr": 0.004452578402829074, "rouge2_fmeasure": 0.01004804307836075, "rouge2_fmeasure_stderr": 0.0009374479444550356, "rouge2_precision": 0.007766000425718809, "rouge2_precision_stderr": 0.0007712139973537835, "rouge2_recall": 0.016794467199208594, "rouge2_recall_stderr": 0.0015960487560251384, "rougeL_fmeasure": 0.03916437496912562, "rougeL_fmeasure_stderr": 0.0021783828707728175, "rougeL_precision": 0.03417705858833514, "rougeL_precision_stderr": 0.002144817166226441, "rougeL_recall": 0.0611728887335129, "rougeL_recall_stderr": 0.003535855187265437, "rougeLsum_fmeasure": 0.03924383294112677, "rougeLsum_fmeasure_stderr": 0.002217328487694054, "rougeLsum_precision": 0.034323144988876814, "rougeLsum_precision_stderr": 0.0021857348636160957, "rougeLsum_recall": 0.06145859851518466, "rougeLsum_recall_stderr": 0.003628835438679055}}, "5": {"article_DOC_summary": {"bleu": 2.1058893408297867e-36, "bleu_stderr": 2.1724367476442414e-31, "rouge1_fmeasure": 0.0032528851804285172, "rouge1_fmeasure_stderr": 0.0008749082661343398, "rouge1_precision": 0.0037186815835539475, "rouge1_precision_stderr": 0.0010258999278355571, "rouge1_recall": 0.002971904217615499, "rouge1_recall_stderr": 0.0007902202653735375, "rouge2_fmeasure": 0.0007279332281340716, "rouge2_fmeasure_stderr": 0.0002925088475825617, "rouge2_precision": 0.0008463719964829843, "rouge2_precision_stderr": 0.00034301989930096845, "rouge2_recall": 0.000656010656010656, "rouge2_recall_stderr": 0.0002674722049726138, "rougeL_fmeasure": 0.0025265679608804242, "rougeL_fmeasure_stderr": 0.0006801945500560441, "rougeL_precision": 0.002842770899097203, "rougeL_precision_stderr": 0.0007736763310592724, "rougeL_recall": 0.0023409347627226925, "rougeL_recall_stderr": 0.000630308860618993, "rougeLsum_fmeasure": 0.002627465953010381, "rougeLsum_fmeasure_stderr": 0.0007127898651991914, "rougeLsum_precision": 0.002946821953481221, "rougeLsum_precision_stderr": 0.0008038704154971681, "rougeLsum_recall": 0.00243903003284904, "rougeLsum_recall_stderr": 0.0006639365437911874}}}} |