Muennighoff's picture
Add files
892f3c7
{"GEM/web_nlg_en": {"0": {"PALM_prompt": {"bleu": 0.4177738397053596, "bleu_stderr": 0.052439714987504826, "rouge1_fmeasure": 0.11313553204694117, "rouge1_fmeasure_stderr": 0.0020976821294602234, "rouge1_precision": 0.07401331365029154, "rouge1_precision_stderr": 0.001555945380008501, "rouge1_recall": 0.309544677126812, "rouge1_recall_stderr": 0.004598258018956965, "rouge2_fmeasure": 0.05411413548524944, "rouge2_fmeasure_stderr": 0.0013020734544028827, "rouge2_precision": 0.03523505191827857, "rouge2_precision_stderr": 0.0009392296781654515, "rouge2_recall": 0.15329454407408277, "rouge2_recall_stderr": 0.003251728201432321, "rougeL_fmeasure": 0.10845705136602556, "rougeL_fmeasure_stderr": 0.0019284471387199143, "rougeL_precision": 0.07061132409656197, "rougeL_precision_stderr": 0.0014031957668770357, "rougeL_recall": 0.30042353738636374, "rougeL_recall_stderr": 0.0044778245769371994, "rougeLsum_fmeasure": 0.10792394253569278, "rougeLsum_fmeasure_stderr": 0.0019640770726289487, "rougeLsum_precision": 0.07049851230067716, "rougeLsum_precision_stderr": 0.001450359178267902, "rougeLsum_recall": 0.296810156480222, "rougeLsum_recall_stderr": 0.0043631335921961835}}, "1": {"PALM_prompt": {"bleu": 0.5808615724978651, "bleu_stderr": 0.03393350967485746, "rouge1_fmeasure": 0.12727475120836446, "rouge1_fmeasure_stderr": 0.002035424606741712, "rouge1_precision": 0.08183691647303251, "rouge1_precision_stderr": 0.0015166625147494993, "rouge1_recall": 0.40093348191479217, "rouge1_recall_stderr": 0.005450906036616762, "rouge2_fmeasure": 0.06096091447803779, "rouge2_fmeasure_stderr": 0.0012946551599852026, "rouge2_precision": 0.039062153239498784, "rouge2_precision_stderr": 0.0009349863984338872, "rouge2_recall": 0.20112348772170943, "rouge2_recall_stderr": 0.003804920107675235, "rougeL_fmeasure": 0.1192836731407637, "rougeL_fmeasure_stderr": 0.001834016996545526, "rougeL_precision": 0.07650521343895433, "rougeL_precision_stderr": 0.0013445352921906551, "rougeL_recall": 0.37517446453693076, "rougeL_recall_stderr": 0.004982125783681737, "rougeLsum_fmeasure": 0.12012804167712486, "rougeLsum_fmeasure_stderr": 0.0018942369664582516, "rougeLsum_precision": 0.07726225443418276, "rougeLsum_precision_stderr": 0.001411238354454551, "rougeLsum_recall": 0.3769882191273612, "rougeLsum_recall_stderr": 0.004973103856227287}}, "2": {"PALM_prompt": {"bleu": 0.6974388179157304, "bleu_stderr": 0.030575587628070142, "rouge1_fmeasure": 0.13158075248220336, "rouge1_fmeasure_stderr": 0.0019778747548532725, "rouge1_precision": 0.08378329306693072, "rouge1_precision_stderr": 0.001459322065449314, "rouge1_recall": 0.4295176674907729, "rouge1_recall_stderr": 0.005387840357836537, "rouge2_fmeasure": 0.06253675704279393, "rouge2_fmeasure_stderr": 0.0012350283375229683, "rouge2_precision": 0.03959861804048329, "rouge2_precision_stderr": 0.0008790815089921375, "rouge2_recall": 0.21857768529907604, "rouge2_recall_stderr": 0.003978406350005915, "rougeL_fmeasure": 0.12041670906511595, "rougeL_fmeasure_stderr": 0.001724997794417473, "rougeL_precision": 0.0765488634109198, "rougeL_precision_stderr": 0.001262760988042247, "rougeL_recall": 0.3942968542813885, "rougeL_recall_stderr": 0.004825967992749896, "rougeLsum_fmeasure": 0.12422716343042028, "rougeLsum_fmeasure_stderr": 0.0018397851260800163, "rougeLsum_precision": 0.07912745617089588, "rougeLsum_precision_stderr": 0.0013596543752117662, "rougeLsum_recall": 0.40482037642139057, "rougeLsum_recall_stderr": 0.004938559564217245}}, "3": {"PALM_prompt": {"bleu": 0.8278535585588646, "bleu_stderr": 0.04101323263962433, "rouge1_fmeasure": 0.13488847581723404, "rouge1_fmeasure_stderr": 0.0019541441973022983, "rouge1_precision": 0.08547615960283327, "rouge1_precision_stderr": 0.0014631064392462048, "rouge1_recall": 0.45233724476476256, "rouge1_recall_stderr": 0.005498610961440376, "rouge2_fmeasure": 0.06437212669435428, "rouge2_fmeasure_stderr": 0.0012436500824994457, "rouge2_precision": 0.04064020009202515, "rouge2_precision_stderr": 0.0009117668832831653, "rouge2_recall": 0.23147273606302815, "rouge2_recall_stderr": 0.004055355768121839, "rougeL_fmeasure": 0.12265416975642841, "rougeL_fmeasure_stderr": 0.001687981425852585, "rougeL_precision": 0.07766706751152817, "rougeL_precision_stderr": 0.0012705151561288445, "rougeL_recall": 0.4116826372221156, "rougeL_recall_stderr": 0.004846073095478439, "rougeLsum_fmeasure": 0.12722726363829323, "rougeLsum_fmeasure_stderr": 0.0018316120685934315, "rougeLsum_precision": 0.08067112264899551, "rougeLsum_precision_stderr": 0.0013779713860748017, "rougeLsum_recall": 0.42508315288079185, "rougeLsum_recall_stderr": 0.005020947504999342}}, "4": {"PALM_prompt": {"bleu": 0.8696996582752973, "bleu_stderr": 0.06098328946071962, "rouge1_fmeasure": 0.1345378611428427, "rouge1_fmeasure_stderr": 0.0019444813188940376, "rouge1_precision": 0.0846654378867452, "rouge1_precision_stderr": 0.0014210010721050707, "rouge1_recall": 0.4578457479151435, "rouge1_recall_stderr": 0.005514991901446975, "rouge2_fmeasure": 0.06331896436631664, "rouge2_fmeasure_stderr": 0.0012304846406140408, "rouge2_precision": 0.03959585063348627, "rouge2_precision_stderr": 0.000862580003329711, "rouge2_recall": 0.2318178313336565, "rouge2_recall_stderr": 0.0041148040681156135, "rougeL_fmeasure": 0.1206116472621873, "rougeL_fmeasure_stderr": 0.001620078997028922, "rougeL_precision": 0.07578970344610945, "rougeL_precision_stderr": 0.0011783081782238954, "rougeL_recall": 0.4122041018783002, "rougeL_recall_stderr": 0.004808418678515961, "rougeLsum_fmeasure": 0.12652519308473198, "rougeLsum_fmeasure_stderr": 0.0018015979293605463, "rougeLsum_precision": 0.0796291662268957, "rougeLsum_precision_stderr": 0.001316435535538898, "rougeLsum_recall": 0.43058423280412716, "rougeLsum_recall_stderr": 0.005076088365482536}}, "5": {"PALM_prompt": {"bleu": 0.9386565201757037, "bleu_stderr": 0.044526839780327905, "rouge1_fmeasure": 0.13836362229996832, "rouge1_fmeasure_stderr": 0.001893431540140422, "rouge1_precision": 0.08665394421115923, "rouge1_precision_stderr": 0.0013765101453522592, "rouge1_recall": 0.479351769718965, "rouge1_recall_stderr": 0.00548474489542107, "rouge2_fmeasure": 0.06552803780701107, "rouge2_fmeasure_stderr": 0.001201220687887674, "rouge2_precision": 0.04073112194630253, "rouge2_precision_stderr": 0.0008342579281972372, "rouge2_recall": 0.24709583361079115, "rouge2_recall_stderr": 0.004288275564287053, "rougeL_fmeasure": 0.12284158062218388, "rougeL_fmeasure_stderr": 0.0015900050300239478, "rougeL_precision": 0.07688627300671028, "rougeL_precision_stderr": 0.0011617752110929672, "rougeL_recall": 0.4288123063878505, "rougeL_recall_stderr": 0.004826731215989172, "rougeLsum_fmeasure": 0.1301416572009741, "rougeLsum_fmeasure_stderr": 0.001768541697398853, "rougeLsum_precision": 0.08154653189712766, "rougeLsum_precision_stderr": 0.001288193874235195, "rougeLsum_recall": 0.4505990363238062, "rougeLsum_recall_stderr": 0.005059301966187745}}}, "GEM/wiki_lingua_en": {"0": {"tldr_en": {"bleu": 1.4010466021962698, "bleu_stderr": 0.05693469656785709, "rouge1_fmeasure": 0.16422245329729376, "rouge1_fmeasure_stderr": 0.0018151110735496203, "rouge1_precision": 0.13997262682188616, "rouge1_precision_stderr": 0.0018152662704601968, "rouge1_recall": 0.23988301526777517, "rouge1_recall_stderr": 0.0026425508349757127, "rouge2_fmeasure": 0.03235069293218825, "rouge2_fmeasure_stderr": 0.0008205093824111827, "rouge2_precision": 0.02739555088551612, "rouge2_precision_stderr": 0.0007299475693711506, "rouge2_recall": 0.04882561093577656, "rouge2_recall_stderr": 0.0013519389814047277, "rougeL_fmeasure": 0.1298012454573935, "rougeL_fmeasure_stderr": 0.0013082389095494423, "rougeL_precision": 0.10940153468767774, "rougeL_precision_stderr": 0.0012797812738055785, "rougeL_recall": 0.19392296248486443, "rougeL_recall_stderr": 0.0021299443087579575, "rougeLsum_fmeasure": 0.15178310664024564, "rougeLsum_fmeasure_stderr": 0.0016581127885119964, "rougeLsum_precision": 0.12920003480420952, "rougeLsum_precision_stderr": 0.0016583776510762952, "rougeLsum_recall": 0.22237769560119033, "rougeLsum_recall_stderr": 0.002445338658648684}}, "1": {"tldr_en": {"bleu": 2.6792767534985105, "bleu_stderr": 0.08050348994884776, "rouge1_fmeasure": 0.22176158764199283, "rouge1_fmeasure_stderr": 0.0019496812102440851, "rouge1_precision": 0.19237806407108246, "rouge1_precision_stderr": 0.002156616087328965, "rouge1_recall": 0.3212993636930355, "rouge1_recall_stderr": 0.002829724921518021, "rouge2_fmeasure": 0.05436564304591471, "rouge2_fmeasure_stderr": 0.0010398581680374484, "rouge2_precision": 0.04730550033705585, "rouge2_precision_stderr": 0.0010038562816699207, "rouge2_recall": 0.0810126790953652, "rouge2_recall_stderr": 0.0016920263323925329, "rougeL_fmeasure": 0.15298606072602197, "rougeL_fmeasure_stderr": 0.001269522698605816, "rougeL_precision": 0.13189452873558555, "rougeL_precision_stderr": 0.0014440357444886517, "rougeL_recall": 0.22728266255319154, "rougeL_recall_stderr": 0.0021740082956540176, "rougeLsum_fmeasure": 0.20773701812397452, "rougeLsum_fmeasure_stderr": 0.0018267476451028011, "rougeLsum_precision": 0.1799760146194542, "rougeLsum_precision_stderr": 0.002013284357082607, "rougeLsum_recall": 0.3015175800896575, "rougeLsum_recall_stderr": 0.0026743484362997554}}, "2": {"tldr_en": {"bleu": 2.825588151177289, "bleu_stderr": 0.0827483173505062, "rouge1_fmeasure": 0.21881031202295378, "rouge1_fmeasure_stderr": 0.0018340980892655135, "rouge1_precision": 0.19587403318777896, "rouge1_precision_stderr": 0.002246482935330373, "rouge1_recall": 0.3104623013424553, "rouge1_recall_stderr": 0.0026357716525505985, "rouge2_fmeasure": 0.05407980043809886, "rouge2_fmeasure_stderr": 0.0010322675581464652, "rouge2_precision": 0.049518456494770303, "rouge2_precision_stderr": 0.001177357025652893, "rouge2_recall": 0.07843155253080596, "rouge2_recall_stderr": 0.0016707411483431178, "rougeL_fmeasure": 0.15447333837028793, "rougeL_fmeasure_stderr": 0.0012811266282334365, "rougeL_precision": 0.13795120173138903, "rougeL_precision_stderr": 0.001669101235947338, "rougeL_recall": 0.22381109650316425, "rougeL_recall_stderr": 0.002115149596829255, "rougeLsum_fmeasure": 0.20577620783096848, "rougeLsum_fmeasure_stderr": 0.0017206650892505897, "rougeLsum_precision": 0.18399939129198817, "rougeLsum_precision_stderr": 0.0021107295487964614, "rougeLsum_recall": 0.2924275031032992, "rougeLsum_recall_stderr": 0.0024986416120394883}}, "3": {"tldr_en": {"bleu": 2.77140298721746, "bleu_stderr": 0.09911601058676267, "rouge1_fmeasure": 0.17955806504481292, "rouge1_fmeasure_stderr": 0.002195205258030929, "rouge1_precision": 0.1647227013547415, "rouge1_precision_stderr": 0.0024792520261390483, "rouge1_recall": 0.2560613183847905, "rouge1_recall_stderr": 0.0032797831033041618, "rouge2_fmeasure": 0.04429422701774445, "rouge2_fmeasure_stderr": 0.0010178187766663955, "rouge2_precision": 0.040393011250336536, "rouge2_precision_stderr": 0.001120492765195676, "rouge2_recall": 0.06579426072456108, "rouge2_recall_stderr": 0.001694481658818446, "rougeL_fmeasure": 0.12746828061030624, "rougeL_fmeasure_stderr": 0.0015396980890683188, "rougeL_precision": 0.11737676404806478, "rougeL_precision_stderr": 0.0018604626033532456, "rougeL_recall": 0.1856490443924171, "rougeL_recall_stderr": 0.00253379229574718, "rougeLsum_fmeasure": 0.1689495507422565, "rougeLsum_fmeasure_stderr": 0.0020580481966186253, "rougeLsum_precision": 0.15523651118051682, "rougeLsum_precision_stderr": 0.0023598380194680005, "rougeLsum_recall": 0.24112578036228802, "rougeLsum_recall_stderr": 0.0030888339817801563}}, "4": {"tldr_en": {"bleu": 0.6374428010243339, "bleu_stderr": 0.04679817619985886, "rouge1_fmeasure": 0.05724507901787019, "rouge1_fmeasure_stderr": 0.001923136290184156, "rouge1_precision": 0.053177399565422716, "rouge1_precision_stderr": 0.001969539589668854, "rouge1_recall": 0.08460445332976693, "rouge1_recall_stderr": 0.002887654568198146, "rouge2_fmeasure": 0.014128667931700438, "rouge2_fmeasure_stderr": 0.0006962023161566057, "rouge2_precision": 0.012859547969705542, "rouge2_precision_stderr": 0.000726325510216138, "rouge2_recall": 0.02237244864266085, "rouge2_recall_stderr": 0.0012034662851936587, "rougeL_fmeasure": 0.042868526761057124, "rougeL_fmeasure_stderr": 0.0014217476738280137, "rougeL_precision": 0.03993285011532237, "rougeL_precision_stderr": 0.0014928569276828109, "rougeL_recall": 0.06466228514995502, "rougeL_recall_stderr": 0.0022622950372018576, "rougeLsum_fmeasure": 0.053934021939145045, "rougeLsum_fmeasure_stderr": 0.0018135115805431904, "rougeLsum_precision": 0.05008717864701033, "rougeLsum_precision_stderr": 0.0018614454895917413, "rougeLsum_recall": 0.07995227312474681, "rougeLsum_recall_stderr": 0.0027408841913450226}}, "5": {"tldr_en": {"bleu": 1.5497714003816197e-06, "bleu_stderr": 2.826544891292017e-06, "rouge1_fmeasure": 0.009409482800898775, "rouge1_fmeasure_stderr": 0.0008719922868900455, "rouge1_precision": 0.009250162353650573, "rouge1_precision_stderr": 0.0009501892043502089, "rouge1_recall": 0.01399225543923628, "rouge1_recall_stderr": 0.0013479443593293063, "rouge2_fmeasure": 0.0024954950292378434, "rouge2_fmeasure_stderr": 0.00030758521273803235, "rouge2_precision": 0.0025132950634529213, "rouge2_precision_stderr": 0.0003496566473256293, "rouge2_recall": 0.003986174570934941, "rouge2_recall_stderr": 0.0005228969007076435, "rougeL_fmeasure": 0.007016931130854418, "rougeL_fmeasure_stderr": 0.0006474630715093982, "rougeL_precision": 0.006939530851512524, "rougeL_precision_stderr": 0.000721287497804254, "rougeL_recall": 0.010674568197211812, "rougeL_recall_stderr": 0.0010578455964358668, "rougeLsum_fmeasure": 0.008928183444317063, "rougeLsum_fmeasure_stderr": 0.0008250504967685091, "rougeLsum_precision": 0.008770387592628782, "rougeLsum_precision_stderr": 0.0008958471929010777, "rougeLsum_recall": 0.013287426441297979, "rougeLsum_recall_stderr": 0.0012768296011753365}}}, "e2e_nlg_cleaned": {"0": {"generate_text_restaurant": {"bleu": 0.01707387064925112, "bleu_stderr": 0.004548339499332125, "rouge1_fmeasure": 0.01833385014011665, "rouge1_fmeasure_stderr": 0.0004556651351480112, "rouge1_precision": 0.01479209987025161, "rouge1_precision_stderr": 0.0003848187529004132, "rouge1_recall": 0.02647907855108807, "rouge1_recall_stderr": 0.0007373776368265799, "rouge2_fmeasure": 0.00022602188070215841, "rouge2_fmeasure_stderr": 4.551736869387828e-05, "rouge2_precision": 0.00018468533574224637, "rouge2_precision_stderr": 3.7035782299895355e-05, "rouge2_recall": 0.00032184358555587336, "rouge2_recall_stderr": 6.80865158511292e-05, "rougeL_fmeasure": 0.01828543709345876, "rougeL_fmeasure_stderr": 0.000449785707890762, "rougeL_precision": 0.014749675627827365, "rougeL_precision_stderr": 0.0003794521861304636, "rougeL_recall": 0.02642067669572227, "rougeL_recall_stderr": 0.0007319703340695989, "rougeLsum_fmeasure": 0.017042834318925764, "rougeLsum_fmeasure_stderr": 0.00038117023392555423, "rougeLsum_precision": 0.01381746395527955, "rougeLsum_precision_stderr": 0.0003369009463365385, "rougeLsum_recall": 0.024406964608590324, "rougeLsum_recall_stderr": 0.0005979225418060756}}, "1": {"generate_text_restaurant": {"bleu": 11.199945366026236, "bleu_stderr": 0.09740891554529413, "rouge1_fmeasure": 0.43361162405107295, "rouge1_fmeasure_stderr": 0.0024498717646033665, "rouge1_precision": 0.5190142019208609, "rouge1_precision_stderr": 0.003327240390036289, "rouge1_recall": 0.4114616078138066, "rouge1_recall_stderr": 0.0030408033259645612, "rouge2_fmeasure": 0.1983453767330724, "rouge2_fmeasure_stderr": 0.0019553142654631156, "rouge2_precision": 0.24092206705754915, "rouge2_precision_stderr": 0.0025432949505695425, "rouge2_recall": 0.18797583914402394, "rouge2_recall_stderr": 0.002107165588256214, "rougeL_fmeasure": 0.315514252090379, "rougeL_fmeasure_stderr": 0.0020950130049756485, "rougeL_precision": 0.3810297781145268, "rougeL_precision_stderr": 0.002955659050147338, "rougeL_recall": 0.2982904326283383, "rougeL_recall_stderr": 0.002441126924534855, "rougeLsum_fmeasure": 0.3556790279405754, "rougeLsum_fmeasure_stderr": 0.0023552583830999735, "rougeLsum_precision": 0.4272477194499663, "rougeLsum_precision_stderr": 0.0031895534936824997, "rougeLsum_recall": 0.33692836067640447, "rougeLsum_recall_stderr": 0.0027567274786219256}}, "2": {"generate_text_restaurant": {"bleu": 12.752880813365183, "bleu_stderr": 0.22532887560628184, "rouge1_fmeasure": 0.4576720641979181, "rouge1_fmeasure_stderr": 0.0022953942764252673, "rouge1_precision": 0.5483859178177682, "rouge1_precision_stderr": 0.003284509279619272, "rouge1_recall": 0.4329119599793277, "rouge1_recall_stderr": 0.002935675677350969, "rouge2_fmeasure": 0.22030084182668652, "rouge2_fmeasure_stderr": 0.0020287670329249274, "rouge2_precision": 0.26853962452756747, "rouge2_precision_stderr": 0.002740945324943779, "rouge2_recall": 0.20828673845347298, "rouge2_recall_stderr": 0.0021908686840527536, "rougeL_fmeasure": 0.33784951726273604, "rougeL_fmeasure_stderr": 0.002092067006211518, "rougeL_precision": 0.407475473407987, "rougeL_precision_stderr": 0.0030181731331604795, "rougeL_recall": 0.31883364076878173, "rougeL_recall_stderr": 0.002461630929460497, "rougeLsum_fmeasure": 0.38152814100163385, "rougeLsum_fmeasure_stderr": 0.002318898465385505, "rougeLsum_precision": 0.45802173612428515, "rougeLsum_precision_stderr": 0.003228180984559956, "rougeLsum_recall": 0.3606321592898537, "rougeLsum_recall_stderr": 0.002748101165505275}}, "3": {"generate_text_restaurant": {"bleu": 13.567475379286549, "bleu_stderr": 0.1880502425341883, "rouge1_fmeasure": 0.46365491542004894, "rouge1_fmeasure_stderr": 0.0021794833674578123, "rouge1_precision": 0.54296137339216, "rouge1_precision_stderr": 0.0032385304204834925, "rouge1_recall": 0.4468637477572891, "rouge1_recall_stderr": 0.002870747282334814, "rouge2_fmeasure": 0.22644283092674808, "rouge2_fmeasure_stderr": 0.0020104468971516875, "rouge2_precision": 0.268879550509031, "rouge2_precision_stderr": 0.0026847549706603357, "rouge2_recall": 0.21872430008911764, "rouge2_recall_stderr": 0.0022357966811142774, "rougeL_fmeasure": 0.3445418845511442, "rougeL_fmeasure_stderr": 0.002026802374084494, "rougeL_precision": 0.40563436021398125, "rougeL_precision_stderr": 0.0029671089231426426, "rougeL_recall": 0.33158522150890407, "rougeL_recall_stderr": 0.0024524778139217965, "rougeLsum_fmeasure": 0.3905619856893357, "rougeLsum_fmeasure_stderr": 0.002253731478640236, "rougeLsum_precision": 0.457618460997299, "rougeLsum_precision_stderr": 0.003163617105952389, "rougeLsum_recall": 0.37651908361075154, "rougeLsum_recall_stderr": 0.0027495326994019364}}, "4": {"generate_text_restaurant": {"bleu": 13.740384950752064, "bleu_stderr": 0.17474565384186433, "rouge1_fmeasure": 0.4606344386510922, "rouge1_fmeasure_stderr": 0.0021643969739297475, "rouge1_precision": 0.51943848236802, "rouge1_precision_stderr": 0.0031779058467164764, "rouge1_recall": 0.4567820792568219, "rouge1_recall_stderr": 0.002851642014055284, "rouge2_fmeasure": 0.22570040278921377, "rouge2_fmeasure_stderr": 0.0020088114026586526, "rouge2_precision": 0.25737502763838105, "rouge2_precision_stderr": 0.0026242680468160895, "rouge2_recall": 0.2245153764885056, "rouge2_recall_stderr": 0.0022588441708384973, "rougeL_fmeasure": 0.3427780842217158, "rougeL_fmeasure_stderr": 0.0020244481019983177, "rougeL_precision": 0.3876917725288397, "rougeL_precision_stderr": 0.0028653337007260647, "rougeL_recall": 0.3397952534482862, "rougeL_recall_stderr": 0.0024656674082997676, "rougeLsum_fmeasure": 0.3902532373292503, "rougeLsum_fmeasure_stderr": 0.0022482737601443, "rougeLsum_precision": 0.43916794242095064, "rougeLsum_precision_stderr": 0.0030589422127270337, "rougeLsum_recall": 0.3876015303869884, "rougeLsum_recall_stderr": 0.0027798320723785553}}, "5": {"generate_text_restaurant": {"bleu": 12.772366014464684, "bleu_stderr": 0.1727094167530513, "rouge1_fmeasure": 0.45315037221898985, "rouge1_fmeasure_stderr": 0.002063099268846445, "rouge1_precision": 0.4849957590476985, "rouge1_precision_stderr": 0.0029633904151518614, "rouge1_recall": 0.4698079682696499, "rouge1_recall_stderr": 0.0028147920332754844, "rouge2_fmeasure": 0.2186838500921512, "rouge2_fmeasure_stderr": 0.0018776056949733047, "rouge2_precision": 0.23597412151168465, "rouge2_precision_stderr": 0.0023313187461128483, "rouge2_recall": 0.22775944680052645, "rouge2_recall_stderr": 0.002217444405292992, "rougeL_fmeasure": 0.33617919401288165, "rougeL_fmeasure_stderr": 0.0019141754215681863, "rougeL_precision": 0.36121121776556825, "rougeL_precision_stderr": 0.002645618381599165, "rougeL_recall": 0.3483500842464673, "rougeL_recall_stderr": 0.0024310911003668787, "rougeLsum_fmeasure": 0.3862609489154149, "rougeLsum_fmeasure_stderr": 0.0021169304456593015, "rougeLsum_precision": 0.41312019009298706, "rougeLsum_precision_stderr": 0.0028317325884933, "rougeLsum_recall": 0.40082494576214567, "rougeLsum_recall_stderr": 0.0027213945607275796}}}, "gem_xsum": {"0": {"article_DOC_summary": {"bleu": 1.7916845418214005, "bleu_stderr": 0.07828212807526311, "rouge1_fmeasure": 0.20406385886176096, "rouge1_fmeasure_stderr": 0.00258155674612985, "rouge1_precision": 0.1636017883690539, "rouge1_precision_stderr": 0.0024265639944645607, "rouge1_recall": 0.3135411100199371, "rouge1_recall_stderr": 0.004414059386580781, "rouge2_fmeasure": 0.042825803126534195, "rouge2_fmeasure_stderr": 0.00160599002891498, "rouge2_precision": 0.03326860572215188, "rouge2_precision_stderr": 0.0013712483892843969, "rouge2_recall": 0.06935361806518704, "rouge2_recall_stderr": 0.002630864064398201, "rougeL_fmeasure": 0.154429756081877, "rougeL_fmeasure_stderr": 0.0019969002281278216, "rougeL_precision": 0.12376190274002842, "rougeL_precision_stderr": 0.0019110587602701528, "rougeL_recall": 0.23856624379837527, "rougeL_recall_stderr": 0.0034515198934126907, "rougeLsum_fmeasure": 0.1585898458477123, "rougeLsum_fmeasure_stderr": 0.0021649602354550605, "rougeLsum_precision": 0.12670301550297952, "rougeLsum_precision_stderr": 0.001984240932547222, "rougeLsum_recall": 0.2456847137827434, "rougeLsum_recall_stderr": 0.0037888888942200177}}, "1": {"article_DOC_summary": {"bleu": 1.3135114346532981, "bleu_stderr": 0.08463533356367237, "rouge1_fmeasure": 0.17216405786002645, "rouge1_fmeasure_stderr": 0.002413004919727933, "rouge1_precision": 0.12258398799437052, "rouge1_precision_stderr": 0.0017962630199380857, "rouge1_recall": 0.3012382161995991, "rouge1_recall_stderr": 0.004139509463692997, "rouge2_fmeasure": 0.032550109418001044, "rouge2_fmeasure_stderr": 0.0013323022688404391, "rouge2_precision": 0.022923096739945113, "rouge2_precision_stderr": 0.0009396939072749053, "rouge2_recall": 0.058554066932389494, "rouge2_recall_stderr": 0.002474769338098033, "rougeL_fmeasure": 0.13422605654232356, "rougeL_fmeasure_stderr": 0.0017698404507476406, "rougeL_precision": 0.0953766892949565, "rougeL_precision_stderr": 0.0013021773787458971, "rougeL_recall": 0.2362381442835074, "rougeL_recall_stderr": 0.0031828562476237457, "rougeLsum_fmeasure": 0.13702592659449045, "rougeLsum_fmeasure_stderr": 0.0019551406042742046, "rougeLsum_precision": 0.09729740585688308, "rougeLsum_precision_stderr": 0.001433871342903216, "rougeLsum_recall": 0.24153880156299268, "rougeLsum_recall_stderr": 0.003500903202746728}}, "2": {"article_DOC_summary": {"bleu": 1.2969951394913493, "bleu_stderr": 0.06867031320524596, "rouge1_fmeasure": 0.16848679088873222, "rouge1_fmeasure_stderr": 0.0023805185438281235, "rouge1_precision": 0.12014057910525737, "rouge1_precision_stderr": 0.00177027208032182, "rouge1_recall": 0.2937362802990173, "rouge1_recall_stderr": 0.0040558921767481415, "rouge2_fmeasure": 0.032592328628319726, "rouge2_fmeasure_stderr": 0.001360334296634944, "rouge2_precision": 0.023037471663706975, "rouge2_precision_stderr": 0.0009651714294322547, "rouge2_recall": 0.05808812201139429, "rouge2_recall_stderr": 0.002494816691771811, "rougeL_fmeasure": 0.13752060575301803, "rougeL_fmeasure_stderr": 0.0018652017270717643, "rougeL_precision": 0.09796298255577943, "rougeL_precision_stderr": 0.0013818612760360376, "rougeL_recall": 0.24059048844697575, "rougeL_recall_stderr": 0.0032525841201501613, "rougeLsum_fmeasure": 0.13274693169694082, "rougeLsum_fmeasure_stderr": 0.0019432835336852861, "rougeLsum_precision": 0.09437688045356053, "rougeLsum_precision_stderr": 0.0014232755198755626, "rougeLsum_recall": 0.23332253770052824, "rougeLsum_recall_stderr": 0.0034512361504183474}}, "3": {"article_DOC_summary": {"bleu": 1.327235232469952, "bleu_stderr": 0.09959209280385814, "rouge1_fmeasure": 0.16364844726335212, "rouge1_fmeasure_stderr": 0.002540088417740363, "rouge1_precision": 0.11962719565205662, "rouge1_precision_stderr": 0.002016131135992487, "rouge1_recall": 0.2790081357700044, "rouge1_recall_stderr": 0.0043060099015184835, "rouge2_fmeasure": 0.03286054820200277, "rouge2_fmeasure_stderr": 0.0013434565504320645, "rouge2_precision": 0.02385360834922912, "rouge2_precision_stderr": 0.000982041326291719, "rouge2_recall": 0.057563110969334454, "rouge2_recall_stderr": 0.002474970323879015, "rougeL_fmeasure": 0.13539724940510672, "rougeL_fmeasure_stderr": 0.0020807935996877674, "rougeL_precision": 0.09886948142069724, "rougeL_precision_stderr": 0.0016489525812605937, "rougeL_recall": 0.23196290924579455, "rougeL_recall_stderr": 0.003657598924470169, "rougeLsum_fmeasure": 0.12875250329964805, "rougeLsum_fmeasure_stderr": 0.0020505398481043147, "rougeLsum_precision": 0.09403709487175377, "rougeLsum_precision_stderr": 0.0016315538581778424, "rougeLsum_recall": 0.22096634372218205, "rougeLsum_recall_stderr": 0.0036039318241550657}}, "4": {"article_DOC_summary": {"bleu": 0.720494287805737, "bleu_stderr": 0.13337005008364483, "rouge1_fmeasure": 0.04714699127177818, "rouge1_fmeasure_stderr": 0.002660932299544834, "rouge1_precision": 0.04098939178475802, "rouge1_precision_stderr": 0.0026204420208068035, "rouge1_recall": 0.07322660875950299, "rouge1_recall_stderr": 0.0042459458791253716, "rouge2_fmeasure": 0.01002600655383815, "rouge2_fmeasure_stderr": 0.0009249273635939417, "rouge2_precision": 0.009005101634115067, "rouge2_precision_stderr": 0.00121171937903932, "rouge2_recall": 0.016152720952389045, "rouge2_recall_stderr": 0.0015904264999107502, "rougeL_fmeasure": 0.038851245646855916, "rougeL_fmeasure_stderr": 0.002177065038104623, "rougeL_precision": 0.034375344099908396, "rougeL_precision_stderr": 0.002283572080585189, "rougeL_recall": 0.06037717457617166, "rougeL_recall_stderr": 0.0035163081114451514, "rougeLsum_fmeasure": 0.03782418886463528, "rougeLsum_fmeasure_stderr": 0.0021755326176048475, "rougeLsum_precision": 0.03382829886719806, "rougeLsum_precision_stderr": 0.002342085999586738, "rougeLsum_recall": 0.05845333975676655, "rougeLsum_recall_stderr": 0.003459845391454891}}, "5": {"article_DOC_summary": {"bleu": 1.437491909962072e-37, "bleu_stderr": 6.679183284996885e-31, "rouge1_fmeasure": 0.002482537431673434, "rouge1_fmeasure_stderr": 0.0006590331629581881, "rouge1_precision": 0.0027818328091416475, "rouge1_precision_stderr": 0.0007401612256325405, "rouge1_recall": 0.002330798812107932, "rouge1_recall_stderr": 0.0006256804823539565, "rouge2_fmeasure": 0.00028593668938742907, "rouge2_fmeasure_stderr": 0.00011751104642033578, "rouge2_precision": 0.0003101211896994361, "rouge2_precision_stderr": 0.00012661794961734148, "rouge2_recall": 0.0002680102915951972, "rouge2_recall_stderr": 0.00011124280815470673, "rougeL_fmeasure": 0.001846067784976754, "rougeL_fmeasure_stderr": 0.0005022326643801285, "rougeL_precision": 0.0020462530294442205, "rougeL_precision_stderr": 0.0005534615847200946, "rougeL_recall": 0.0017580325391528475, "rougeL_recall_stderr": 0.0004906057300283716, "rougeLsum_fmeasure": 0.002260942501090202, "rougeLsum_fmeasure_stderr": 0.0006097815513991564, "rougeLsum_precision": 0.0025260844263122434, "rougeLsum_precision_stderr": 0.0006786126789253857, "rougeLsum_recall": 0.002133328291896597, "rougeLsum_recall_stderr": 0.000585991073578324}}}}