Muennighoff's picture
Add files
e467b8d
{"GEM/web_nlg_en": {"0": {"PALM_prompt": {"bleu": 0.29123796712848116, "bleu_stderr": 0.024099559164327343, "rouge1_fmeasure": 0.0846007331490898, "rouge1_fmeasure_stderr": 0.0017611698640008044, "rouge1_precision": 0.05684299841582745, "rouge1_precision_stderr": 0.0016887384375207904, "rouge1_recall": 0.26382466542797384, "rouge1_recall_stderr": 0.00448652393967693, "rouge2_fmeasure": 0.03751857157597345, "rouge2_fmeasure_stderr": 0.00108659069296553, "rouge2_precision": 0.024552079352862823, "rouge2_precision_stderr": 0.0009251381031279301, "rouge2_recall": 0.11720876113413588, "rouge2_recall_stderr": 0.0030359279375561524, "rougeL_fmeasure": 0.08142615853409181, "rougeL_fmeasure_stderr": 0.001670491088449438, "rougeL_precision": 0.05458027450709555, "rougeL_precision_stderr": 0.001588691365439898, "rougeL_recall": 0.2540701232644345, "rougeL_recall_stderr": 0.004311533260849107, "rougeLsum_fmeasure": 0.08051138355871504, "rougeLsum_fmeasure_stderr": 0.0016680677195043975, "rougeLsum_precision": 0.0541293635979088, "rougeLsum_precision_stderr": 0.0016039721945264953, "rougeLsum_recall": 0.24960718136284848, "rougeLsum_recall_stderr": 0.0042227139206395545}}, "1": {"PALM_prompt": {"bleu": 0.32421224846581287, "bleu_stderr": 0.022894553413488398, "rouge1_fmeasure": 0.09410633326390479, "rouge1_fmeasure_stderr": 0.001817299240652282, "rouge1_precision": 0.06133395467775901, "rouge1_precision_stderr": 0.0015235836365749833, "rouge1_recall": 0.29325251255888984, "rouge1_recall_stderr": 0.004836167389643869, "rouge2_fmeasure": 0.0422554607577646, "rouge2_fmeasure_stderr": 0.0011207429888077064, "rouge2_precision": 0.027879936369681734, "rouge2_precision_stderr": 0.0010974239499863508, "rouge2_recall": 0.13641679853598052, "rouge2_recall_stderr": 0.0032756808482751125, "rougeL_fmeasure": 0.08936406691785198, "rougeL_fmeasure_stderr": 0.001707660234429849, "rougeL_precision": 0.05824013808849948, "rougeL_precision_stderr": 0.0014483059111597553, "rougeL_recall": 0.2785195263881824, "rougeL_recall_stderr": 0.004526853798643564, "rougeLsum_fmeasure": 0.08953461085050565, "rougeLsum_fmeasure_stderr": 0.0017195795746719645, "rougeLsum_precision": 0.058404727742803225, "rougeLsum_precision_stderr": 0.0014611973721867918, "rougeLsum_recall": 0.2786788137098633, "rougeLsum_recall_stderr": 0.004519860762866795}}, "2": {"PALM_prompt": {"bleu": 0.34830681706460126, "bleu_stderr": 0.01684214623603046, "rouge1_fmeasure": 0.0986364025189687, "rouge1_fmeasure_stderr": 0.0017250228996667696, "rouge1_precision": 0.06326435773545039, "rouge1_precision_stderr": 0.0013542606641520488, "rouge1_recall": 0.3156608861325991, "rouge1_recall_stderr": 0.0047388400050451, "rouge2_fmeasure": 0.044559368109694755, "rouge2_fmeasure_stderr": 0.0010908531224967327, "rouge2_precision": 0.028634240678455197, "rouge2_precision_stderr": 0.0008657767199386355, "rouge2_recall": 0.14832007806184763, "rouge2_recall_stderr": 0.003300168476456189, "rougeL_fmeasure": 0.09365962833176038, "rougeL_fmeasure_stderr": 0.001614688994804722, "rougeL_precision": 0.06001818231619863, "rougeL_precision_stderr": 0.0012484272002343752, "rougeL_recall": 0.299123246297464, "rougeL_recall_stderr": 0.0044103995135310195, "rougeLsum_fmeasure": 0.09390588584336734, "rougeLsum_fmeasure_stderr": 0.0016304255047587266, "rougeLsum_precision": 0.06019532321096589, "rougeLsum_precision_stderr": 0.0012630463084520604, "rougeLsum_recall": 0.30043891693048896, "rougeLsum_recall_stderr": 0.004444660524612687}}, "3": {"PALM_prompt": {"bleu": 0.36470600269670195, "bleu_stderr": 0.018280048766308375, "rouge1_fmeasure": 0.10011450605217301, "rouge1_fmeasure_stderr": 0.0016506911228713907, "rouge1_precision": 0.06330533770140873, "rouge1_precision_stderr": 0.0011600203995117304, "rouge1_recall": 0.3259947504941901, "rouge1_recall_stderr": 0.004809345100214171, "rouge2_fmeasure": 0.04497027193243351, "rouge2_fmeasure_stderr": 0.0010238315815248355, "rouge2_precision": 0.028285266360899328, "rouge2_precision_stderr": 0.0006938944946883647, "rouge2_recall": 0.15459267483010083, "rouge2_recall_stderr": 0.00340681133628092, "rougeL_fmeasure": 0.09444059545614306, "rougeL_fmeasure_stderr": 0.0015438279184580702, "rougeL_precision": 0.05972837538221139, "rougeL_precision_stderr": 0.0010878264157076817, "rougeL_recall": 0.3073051758906017, "rougeL_recall_stderr": 0.004478239792374778, "rougeLsum_fmeasure": 0.09513479449596876, "rougeLsum_fmeasure_stderr": 0.0015626056932077051, "rougeLsum_precision": 0.06020601780769939, "rougeLsum_precision_stderr": 0.001104187247297194, "rougeLsum_recall": 0.3095076259209654, "rougeLsum_recall_stderr": 0.004504005664338164}}, "4": {"PALM_prompt": {"bleu": 0.34279547123639, "bleu_stderr": 0.02166437435240052, "rouge1_fmeasure": 0.10065904593799764, "rouge1_fmeasure_stderr": 0.0016754751356902707, "rouge1_precision": 0.06367441592900581, "rouge1_precision_stderr": 0.001194655773448425, "rouge1_recall": 0.3273817810829883, "rouge1_recall_stderr": 0.004763653283179556, "rouge2_fmeasure": 0.04523413495038415, "rouge2_fmeasure_stderr": 0.0010527829629444607, "rouge2_precision": 0.028523558899898493, "rouge2_precision_stderr": 0.0007310056361867258, "rouge2_recall": 0.15423603065118352, "rouge2_recall_stderr": 0.0032851282926083694, "rougeL_fmeasure": 0.09483171445464417, "rougeL_fmeasure_stderr": 0.0015525134351789466, "rougeL_precision": 0.05993520541418932, "rougeL_precision_stderr": 0.0011028564197777878, "rougeL_recall": 0.30883518804645416, "rougeL_recall_stderr": 0.004444159365713122, "rougeLsum_fmeasure": 0.09570320653415937, "rougeLsum_fmeasure_stderr": 0.0015864428965022782, "rougeLsum_precision": 0.06057732250287014, "rougeLsum_precision_stderr": 0.0011347979681458663, "rougeLsum_recall": 0.31052564238961033, "rougeLsum_recall_stderr": 0.004439053679763851}}, "5": {"PALM_prompt": {"bleu": 0.43068686455258365, "bleu_stderr": 0.024558626439848394, "rouge1_fmeasure": 0.10410497627752861, "rouge1_fmeasure_stderr": 0.0017128654339676542, "rouge1_precision": 0.06591108347919172, "rouge1_precision_stderr": 0.0012472199657513222, "rouge1_recall": 0.3403235719405941, "rouge1_recall_stderr": 0.004965628611695927, "rouge2_fmeasure": 0.0477723289558304, "rouge2_fmeasure_stderr": 0.0010828661653623512, "rouge2_precision": 0.03003354094036042, "rouge2_precision_stderr": 0.0007445009962094013, "rouge2_recall": 0.1663946980145394, "rouge2_recall_stderr": 0.003627902758005641, "rougeL_fmeasure": 0.09752610184478055, "rougeL_fmeasure_stderr": 0.0015891934785872816, "rougeL_precision": 0.061647771870220795, "rougeL_precision_stderr": 0.0011365079087437059, "rougeL_recall": 0.31937107624477157, "rougeL_recall_stderr": 0.004623821764283096, "rougeLsum_fmeasure": 0.09881610204913661, "rougeLsum_fmeasure_stderr": 0.0016204593561223266, "rougeLsum_precision": 0.06251543627392657, "rougeLsum_precision_stderr": 0.0011656752479938524, "rougeLsum_recall": 0.32334680308556674, "rougeLsum_recall_stderr": 0.004688368905057958}}}, "GEM/wiki_lingua_en": {"0": {"tldr_en": {"bleu": 1.150037493962955, "bleu_stderr": 0.03792522803644501, "rouge1_fmeasure": 0.16466297522045426, "rouge1_fmeasure_stderr": 0.0017464500568992482, "rouge1_precision": 0.14094551178968198, "rouge1_precision_stderr": 0.0017988042403353308, "rouge1_recall": 0.2383379873289029, "rouge1_recall_stderr": 0.0024508365201313925, "rouge2_fmeasure": 0.03044265380148028, "rouge2_fmeasure_stderr": 0.0007549449327851908, "rouge2_precision": 0.025826231379801598, "rouge2_precision_stderr": 0.0006644756372248472, "rouge2_recall": 0.04562095099618684, "rouge2_recall_stderr": 0.001260309972555968, "rougeL_fmeasure": 0.13521621786999796, "rougeL_fmeasure_stderr": 0.0013074426897338972, "rougeL_precision": 0.1141936744607556, "rougeL_precision_stderr": 0.001311074823465258, "rougeL_recall": 0.20047392294507563, "rougeL_recall_stderr": 0.0020851227283842106, "rougeLsum_fmeasure": 0.1498377131098679, "rougeLsum_fmeasure_stderr": 0.0015625059702703778, "rougeLsum_precision": 0.1281224911907099, "rougeLsum_precision_stderr": 0.0016180585138979911, "rougeLsum_recall": 0.2177477559969978, "rougeLsum_recall_stderr": 0.002237821831406095}}, "1": {"tldr_en": {"bleu": 1.5968121086484615, "bleu_stderr": 0.054851748142751296, "rouge1_fmeasure": 0.1683204053948335, "rouge1_fmeasure_stderr": 0.001892698106994734, "rouge1_precision": 0.14622799391003813, "rouge1_precision_stderr": 0.0020068025807149733, "rouge1_recall": 0.24101862122339654, "rouge1_recall_stderr": 0.0026276208678892242, "rouge2_fmeasure": 0.03354144102579964, "rouge2_fmeasure_stderr": 0.000822566284455867, "rouge2_precision": 0.029667497362948447, "rouge2_precision_stderr": 0.0008466619702056509, "rouge2_recall": 0.048440765255034476, "rouge2_recall_stderr": 0.0012946101473055032, "rougeL_fmeasure": 0.13222515812033397, "rougeL_fmeasure_stderr": 0.0013920016810944796, "rougeL_precision": 0.1138608269905594, "rougeL_precision_stderr": 0.0014746185711284013, "rougeL_recall": 0.1931547974295735, "rougeL_recall_stderr": 0.0021274307166620926, "rougeLsum_fmeasure": 0.15608955729869492, "rougeLsum_fmeasure_stderr": 0.0017500765734040384, "rougeLsum_precision": 0.13544349261022215, "rougeLsum_precision_stderr": 0.0018568387839824677, "rougeLsum_recall": 0.22406954780205265, "rougeLsum_recall_stderr": 0.002449960379940128}}, "2": {"tldr_en": {"bleu": 1.7092164171091249, "bleu_stderr": 0.08765489082275082, "rouge1_fmeasure": 0.17044100733247006, "rouge1_fmeasure_stderr": 0.0018672130638160281, "rouge1_precision": 0.15460966487470837, "rouge1_precision_stderr": 0.002233041531383059, "rouge1_recall": 0.23977523386714922, "rouge1_recall_stderr": 0.0025640624695031644, "rouge2_fmeasure": 0.03537634555402942, "rouge2_fmeasure_stderr": 0.0008649089367972104, "rouge2_precision": 0.03324641794167163, "rouge2_precision_stderr": 0.0010616588597732964, "rouge2_recall": 0.051106504151232426, "rouge2_recall_stderr": 0.0013379696967192748, "rougeL_fmeasure": 0.13554325862504094, "rougeL_fmeasure_stderr": 0.0014028716662179363, "rougeL_precision": 0.1222092984923369, "rougeL_precision_stderr": 0.0017390941193497359, "rougeL_recall": 0.19463277997734565, "rougeL_recall_stderr": 0.0021294441696277336, "rougeLsum_fmeasure": 0.15795207740196257, "rougeLsum_fmeasure_stderr": 0.0017219827845479745, "rougeLsum_precision": 0.14302654547194457, "rougeLsum_precision_stderr": 0.002060935061365854, "rougeLsum_recall": 0.2233107296658696, "rougeLsum_recall_stderr": 0.0024112074184366853}}, "3": {"tldr_en": {"bleu": 1.5463404291438052, "bleu_stderr": 0.08984875953099804, "rouge1_fmeasure": 0.14408176000895695, "rouge1_fmeasure_stderr": 0.0020016420554769035, "rouge1_precision": 0.1406901039188124, "rouge1_precision_stderr": 0.0025666252762842315, "rouge1_recall": 0.19970447237610153, "rouge1_recall_stderr": 0.0028390196402756584, "rouge2_fmeasure": 0.029377172063398457, "rouge2_fmeasure_stderr": 0.0008005810773268516, "rouge2_precision": 0.02922353525732899, "rouge2_precision_stderr": 0.0011010583273786127, "rouge2_recall": 0.04191034328930793, "rouge2_recall_stderr": 0.0012547885060256734, "rougeL_fmeasure": 0.1153303057335899, "rougeL_fmeasure_stderr": 0.0015400634901938468, "rougeL_precision": 0.11281690861703962, "rougeL_precision_stderr": 0.0021122923732267928, "rougeL_recall": 0.1629060920599739, "rougeL_recall_stderr": 0.0023571083502973668, "rougeLsum_fmeasure": 0.13347692311901044, "rougeLsum_fmeasure_stderr": 0.001853011425694174, "rougeLsum_precision": 0.13076056418582657, "rougeLsum_precision_stderr": 0.0024324238744350382, "rougeLsum_recall": 0.1857999771905377, "rougeLsum_recall_stderr": 0.0026706910367050693}}, "4": {"tldr_en": {"bleu": 0.3661448228518088, "bleu_stderr": 0.033027262924505495, "rouge1_fmeasure": 0.047912419187255355, "rouge1_fmeasure_stderr": 0.0016885974181252042, "rouge1_precision": 0.047637385711642166, "rouge1_precision_stderr": 0.0019406862995964113, "rouge1_recall": 0.06935875426191872, "rouge1_recall_stderr": 0.002476239873059244, "rouge2_fmeasure": 0.010490684660423407, "rouge2_fmeasure_stderr": 0.0005736260642904359, "rouge2_precision": 0.010533587881846619, "rouge2_precision_stderr": 0.0006829459294496357, "rouge2_recall": 0.01575083046773536, "rouge2_recall_stderr": 0.0009533335963566146, "rougeL_fmeasure": 0.039331394950418846, "rougeL_fmeasure_stderr": 0.001357076427861084, "rougeL_precision": 0.038907290376934564, "rougeL_precision_stderr": 0.0015632211619916261, "rougeL_recall": 0.058100266035812934, "rougeL_recall_stderr": 0.0020878258346479737, "rougeLsum_fmeasure": 0.0444398924940209, "rougeLsum_fmeasure_stderr": 0.0015649101599922706, "rougeLsum_precision": 0.04422693909381412, "rougeLsum_precision_stderr": 0.0018055836955325499, "rougeLsum_recall": 0.06455710260564228, "rougeLsum_recall_stderr": 0.0023114528926315003}}, "5": {"tldr_en": {"bleu": 6.367443124232542e-07, "bleu_stderr": 1.2685163547005723e-06, "rouge1_fmeasure": 0.008313843592026254, "rouge1_fmeasure_stderr": 0.0008265470763649947, "rouge1_precision": 0.008290393984892647, "rouge1_precision_stderr": 0.0009001034412792107, "rouge1_recall": 0.011802367196652718, "rouge1_recall_stderr": 0.0011618281791076293, "rouge2_fmeasure": 0.002040994959246997, "rouge2_fmeasure_stderr": 0.00030407491270912355, "rouge2_precision": 0.0020266217301853685, "rouge2_precision_stderr": 0.0003393709813488467, "rouge2_recall": 0.0029487651946005756, "rouge2_recall_stderr": 0.0004412972611158346, "rougeL_fmeasure": 0.006771006570745668, "rougeL_fmeasure_stderr": 0.0006635749098480861, "rougeL_precision": 0.006721799139189244, "rougeL_precision_stderr": 0.0007186545260376111, "rougeL_recall": 0.0098857093481712, "rougeL_recall_stderr": 0.0009864294742971877, "rougeLsum_fmeasure": 0.007705400987609899, "rougeLsum_fmeasure_stderr": 0.0007633405146045267, "rougeLsum_precision": 0.007648580835406893, "rougeLsum_precision_stderr": 0.0008266968946583269, "rougeLsum_recall": 0.011070549839007678, "rougeLsum_recall_stderr": 0.0010938104264188817}}}, "e2e_nlg_cleaned": {"0": {"generate_text_restaurant": {"bleu": 3.967183056283888, "bleu_stderr": 0.0614451409180861, "rouge1_fmeasure": 0.22316500100906603, "rouge1_fmeasure_stderr": 0.001595359423456744, "rouge1_precision": 0.17322199542522593, "rouge1_precision_stderr": 0.001766739101818456, "rouge1_recall": 0.3497612117638542, "rouge1_recall_stderr": 0.002145765234933453, "rouge2_fmeasure": 0.08520789194179026, "rouge2_fmeasure_stderr": 0.0010270065001763392, "rouge2_precision": 0.06666478811553239, "rouge2_precision_stderr": 0.001052128094651409, "rouge2_recall": 0.13513990600107753, "rouge2_recall_stderr": 0.0016103984793018583, "rougeL_fmeasure": 0.1988974965351846, "rougeL_fmeasure_stderr": 0.001304080390696196, "rougeL_precision": 0.15393062571271574, "rougeL_precision_stderr": 0.0014926257950038774, "rougeL_recall": 0.3136929917594451, "rougeL_recall_stderr": 0.0018044289406178228, "rougeLsum_fmeasure": 0.19244613018340564, "rougeLsum_fmeasure_stderr": 0.001468684623588083, "rougeLsum_precision": 0.14930193885489784, "rougeLsum_precision_stderr": 0.0016069977963074835, "rougeLsum_recall": 0.30276071858573167, "rougeLsum_recall_stderr": 0.002055681489475386}}, "1": {"generate_text_restaurant": {"bleu": 7.24858195158816, "bleu_stderr": 0.12182015441698014, "rouge1_fmeasure": 0.3648604782443927, "rouge1_fmeasure_stderr": 0.002228919554367123, "rouge1_precision": 0.40889005404754675, "rouge1_precision_stderr": 0.003409449253825524, "rouge1_recall": 0.38260655862871273, "rouge1_recall_stderr": 0.0026522545736220606, "rouge2_fmeasure": 0.1492665013164553, "rouge2_fmeasure_stderr": 0.0016682679997427913, "rouge2_precision": 0.17304656619126002, "rouge2_precision_stderr": 0.0024265933354054277, "rouge2_recall": 0.15533741505167725, "rouge2_recall_stderr": 0.0017940218081133016, "rougeL_fmeasure": 0.27089646277222484, "rougeL_fmeasure_stderr": 0.0017762835796866921, "rougeL_precision": 0.30433231462665566, "rougeL_precision_stderr": 0.0028037834853861434, "rougeL_recall": 0.2870278031145814, "rougeL_recall_stderr": 0.0022278844415098828, "rougeLsum_fmeasure": 0.2988385773578741, "rougeLsum_fmeasure_stderr": 0.002083312510474344, "rougeLsum_precision": 0.3368390621347027, "rougeLsum_precision_stderr": 0.0031362360403701063, "rougeLsum_recall": 0.3129980401000163, "rougeLsum_recall_stderr": 0.002411291755571875}}, "2": {"generate_text_restaurant": {"bleu": 9.8132898005392, "bleu_stderr": 0.13889694589808027, "rouge1_fmeasure": 0.40949266454624667, "rouge1_fmeasure_stderr": 0.002227174072645473, "rouge1_precision": 0.472247337392176, "rouge1_precision_stderr": 0.003509675155475942, "rouge1_recall": 0.4109851055076836, "rouge1_recall_stderr": 0.00266754752683629, "rouge2_fmeasure": 0.18759073054766637, "rouge2_fmeasure_stderr": 0.0018155332514371313, "rouge2_precision": 0.2221300194890402, "rouge2_precision_stderr": 0.0026008629952829765, "rouge2_recall": 0.18747167156183062, "rouge2_recall_stderr": 0.001966631075668386, "rougeL_fmeasure": 0.30101808824060367, "rougeL_fmeasure_stderr": 0.001845167102197219, "rougeL_precision": 0.34810606304380215, "rougeL_precision_stderr": 0.0029168836617550075, "rougeL_recall": 0.3037441519487516, "rougeL_recall_stderr": 0.0022352968777445397, "rougeLsum_fmeasure": 0.33997209628594915, "rougeLsum_fmeasure_stderr": 0.0021704693429880294, "rougeLsum_precision": 0.3930359663685668, "rougeLsum_precision_stderr": 0.0032821280577162463, "rougeLsum_recall": 0.34128557450637836, "rougeLsum_recall_stderr": 0.0025177617791370846}}, "3": {"generate_text_restaurant": {"bleu": 10.606901971322037, "bleu_stderr": 0.1876717173587565, "rouge1_fmeasure": 0.423107786753922, "rouge1_fmeasure_stderr": 0.0022021533625304172, "rouge1_precision": 0.4792720578842871, "rouge1_precision_stderr": 0.003435623212611771, "rouge1_recall": 0.4299540279680867, "rouge1_recall_stderr": 0.002709552589644585, "rouge2_fmeasure": 0.19914466926004393, "rouge2_fmeasure_stderr": 0.00183134409853892, "rouge2_precision": 0.22961096510876788, "rouge2_precision_stderr": 0.0025354521714354276, "rouge2_recall": 0.2028531159711805, "rouge2_recall_stderr": 0.0020459562906288337, "rougeL_fmeasure": 0.3089647180477385, "rougeL_fmeasure_stderr": 0.0018748237534710302, "rougeL_precision": 0.3508612926375425, "rougeL_precision_stderr": 0.0028773466225418217, "rougeL_recall": 0.31576853558586987, "rougeL_recall_stderr": 0.0023159029356283776, "rougeLsum_fmeasure": 0.35385970959123086, "rougeLsum_fmeasure_stderr": 0.0021714504772349687, "rougeLsum_precision": 0.4010458372923884, "rougeLsum_precision_stderr": 0.0032049720170719783, "rougeLsum_recall": 0.36015366099876867, "rougeLsum_recall_stderr": 0.002587495579628278}}, "4": {"generate_text_restaurant": {"bleu": 10.637879863244894, "bleu_stderr": 0.16226309008051826, "rouge1_fmeasure": 0.42194593310296813, "rouge1_fmeasure_stderr": 0.0022114287389486177, "rouge1_precision": 0.4652304352934913, "rouge1_precision_stderr": 0.003337521287505696, "rouge1_recall": 0.43528505234512976, "rouge1_recall_stderr": 0.0026695917030513756, "rouge2_fmeasure": 0.19912988966042086, "rouge2_fmeasure_stderr": 0.0018245099743948883, "rouge2_precision": 0.22302025310290544, "rouge2_precision_stderr": 0.002458367724539737, "rouge2_recall": 0.20597912934683074, "rouge2_recall_stderr": 0.002051470584078235, "rougeL_fmeasure": 0.3089991444775559, "rougeL_fmeasure_stderr": 0.0018682388377063268, "rougeL_precision": 0.34089523951143247, "rougeL_precision_stderr": 0.002747821577994244, "rougeL_recall": 0.3209553243957463, "rougeL_recall_stderr": 0.0023209551472440425, "rougeLsum_fmeasure": 0.35671544335154326, "rougeLsum_fmeasure_stderr": 0.002156063389652602, "rougeLsum_precision": 0.3927848741866132, "rougeLsum_precision_stderr": 0.003065974270261921, "rougeLsum_recall": 0.3689097427358982, "rougeLsum_recall_stderr": 0.002571023680832107}}, "5": {"generate_text_restaurant": {"bleu": 10.26475738478149, "bleu_stderr": 0.10488019812696231, "rouge1_fmeasure": 0.41955022171167694, "rouge1_fmeasure_stderr": 0.002065255587289289, "rouge1_precision": 0.4479742544722184, "rouge1_precision_stderr": 0.003108871411245775, "rouge1_recall": 0.4423554172558611, "rouge1_recall_stderr": 0.0025756769738496397, "rouge2_fmeasure": 0.19644636492905912, "rouge2_fmeasure_stderr": 0.001708355406787911, "rouge2_precision": 0.2123975185096454, "rouge2_precision_stderr": 0.0022240580364677317, "rouge2_recall": 0.20778597326112527, "rouge2_recall_stderr": 0.00197971650755932, "rougeL_fmeasure": 0.30489490110399153, "rougeL_fmeasure_stderr": 0.0017356656037540608, "rougeL_precision": 0.3257902997295537, "rougeL_precision_stderr": 0.0025340439153237536, "rougeL_recall": 0.3232398560031394, "rougeL_recall_stderr": 0.0022135147638730015, "rougeLsum_fmeasure": 0.35648196691681816, "rougeLsum_fmeasure_stderr": 0.0020231414730809993, "rougeLsum_precision": 0.38025656291521354, "rougeLsum_precision_stderr": 0.002865492941990049, "rougeLsum_recall": 0.3766640128082206, "rougeLsum_recall_stderr": 0.002485268728296478}}}, "gem_xsum": {"0": {"article_DOC_summary": {"bleu": 2.1575498448959216, "bleu_stderr": 0.08919411230958109, "rouge1_fmeasure": 0.20694913889331623, "rouge1_fmeasure_stderr": 0.0026118174574717734, "rouge1_precision": 0.14955286652112415, "rouge1_precision_stderr": 0.0020266295880405774, "rouge1_recall": 0.35543546517620694, "rouge1_recall_stderr": 0.00442547747797648, "rouge2_fmeasure": 0.05271536971805359, "rouge2_fmeasure_stderr": 0.0016602940533088598, "rouge2_precision": 0.0376041381568334, "rouge2_precision_stderr": 0.001193655014731505, "rouge2_recall": 0.0933869055501563, "rouge2_recall_stderr": 0.003010569547553423, "rougeL_fmeasure": 0.16253221143739943, "rougeL_fmeasure_stderr": 0.0019871124537594923, "rougeL_precision": 0.11702196333102838, "rougeL_precision_stderr": 0.001508489395430335, "rougeL_recall": 0.281518689350463, "rougeL_recall_stderr": 0.0035793211165099544, "rougeLsum_fmeasure": 0.16153438576143062, "rougeLsum_fmeasure_stderr": 0.002249256594915832, "rougeLsum_precision": 0.1163142271090814, "rougeLsum_precision_stderr": 0.0016972579238893975, "rougeLsum_recall": 0.2797387075449087, "rougeLsum_recall_stderr": 0.0039649519854766495}}, "1": {"article_DOC_summary": {"bleu": 1.5635386724766893, "bleu_stderr": 0.11199220007541402, "rouge1_fmeasure": 0.1687358123113738, "rouge1_fmeasure_stderr": 0.0024129362829470083, "rouge1_precision": 0.11987004390929652, "rouge1_precision_stderr": 0.0017838594123509761, "rouge1_recall": 0.2966409602445348, "rouge1_recall_stderr": 0.004159126214657732, "rouge2_fmeasure": 0.03787201010606323, "rouge2_fmeasure_stderr": 0.0014498387144822385, "rouge2_precision": 0.026631555586252555, "rouge2_precision_stderr": 0.0010212047218259958, "rouge2_recall": 0.06832787071429165, "rouge2_recall_stderr": 0.0026781644808146748, "rougeL_fmeasure": 0.14027382835276725, "rougeL_fmeasure_stderr": 0.001921605105364016, "rougeL_precision": 0.09946412096799201, "rougeL_precision_stderr": 0.0014047697344840638, "rougeL_recall": 0.248112655710228, "rougeL_recall_stderr": 0.0034716802936847493, "rougeLsum_fmeasure": 0.13228905712132874, "rougeLsum_fmeasure_stderr": 0.0020123169172413372, "rougeLsum_precision": 0.09372299032008248, "rougeLsum_precision_stderr": 0.0014604124390732933, "rougeLsum_recall": 0.23430014881481423, "rougeLsum_recall_stderr": 0.0036250515591870363}}, "2": {"article_DOC_summary": {"bleu": 1.5884835216922304, "bleu_stderr": 0.0694220243258812, "rouge1_fmeasure": 0.17272164395046263, "rouge1_fmeasure_stderr": 0.0024442934880362266, "rouge1_precision": 0.12261802535697702, "rouge1_precision_stderr": 0.001802015575276267, "rouge1_recall": 0.3042881483021127, "rouge1_recall_stderr": 0.004239856666150261, "rouge2_fmeasure": 0.03985376122882166, "rouge2_fmeasure_stderr": 0.0014771066414781765, "rouge2_precision": 0.02801123042219147, "rouge2_precision_stderr": 0.0010421626554945002, "rouge2_recall": 0.07221142765808251, "rouge2_recall_stderr": 0.0027494039338407683, "rougeL_fmeasure": 0.14412504060617204, "rougeL_fmeasure_stderr": 0.0019378546005162558, "rougeL_precision": 0.10218618041428032, "rougeL_precision_stderr": 0.0014181507052656937, "rougeL_recall": 0.2550776992609646, "rougeL_recall_stderr": 0.00349622255520093, "rougeLsum_fmeasure": 0.1350224868091867, "rougeLsum_fmeasure_stderr": 0.0020648079219729885, "rougeLsum_precision": 0.09563780121752037, "rougeLsum_precision_stderr": 0.001506049442354842, "rougeLsum_recall": 0.23952794956934653, "rougeLsum_recall_stderr": 0.0036934108853552503}}, "3": {"article_DOC_summary": {"bleu": 1.548658255159644, "bleu_stderr": 0.09243037162628143, "rouge1_fmeasure": 0.1651398268476812, "rouge1_fmeasure_stderr": 0.0025732765693385513, "rouge1_precision": 0.12058771231639086, "rouge1_precision_stderr": 0.002066164336399918, "rouge1_recall": 0.283378982179243, "rouge1_recall_stderr": 0.004430498021847181, "rouge2_fmeasure": 0.03726421510075795, "rouge2_fmeasure_stderr": 0.0014326890233943264, "rouge2_precision": 0.026878830813233837, "rouge2_precision_stderr": 0.0010536649719391797, "rouge2_recall": 0.06558476547253786, "rouge2_recall_stderr": 0.002641200590918728, "rougeL_fmeasure": 0.13662385100336102, "rougeL_fmeasure_stderr": 0.0020655105556114887, "rougeL_precision": 0.09972103113703992, "rougeL_precision_stderr": 0.001673601901658887, "rougeL_recall": 0.23548429603769053, "rougeL_recall_stderr": 0.00364743143336554, "rougeLsum_fmeasure": 0.1296880556548729, "rougeLsum_fmeasure_stderr": 0.002127865421306681, "rougeLsum_precision": 0.09474676528107442, "rougeLsum_precision_stderr": 0.001734800385670887, "rougeLsum_recall": 0.22375657894123885, "rougeLsum_recall_stderr": 0.003765688599090495}}, "4": {"article_DOC_summary": {"bleu": 0.6621697454846989, "bleu_stderr": 0.10164971536579874, "rouge1_fmeasure": 0.04630458791276842, "rouge1_fmeasure_stderr": 0.0025747339870623113, "rouge1_precision": 0.03871656302800435, "rouge1_precision_stderr": 0.0023171515461883206, "rouge1_recall": 0.07297233644463587, "rouge1_recall_stderr": 0.00419731966694904, "rouge2_fmeasure": 0.009197972474873806, "rouge2_fmeasure_stderr": 0.000868833115217779, "rouge2_precision": 0.007010252770233402, "rouge2_precision_stderr": 0.000677642525994807, "rouge2_recall": 0.015453001281963676, "rouge2_recall_stderr": 0.0014999985743029969, "rougeL_fmeasure": 0.03723052598616332, "rougeL_fmeasure_stderr": 0.0020759578853067283, "rougeL_precision": 0.03131649789252053, "rougeL_precision_stderr": 0.0019045755355521208, "rougeL_recall": 0.05884937656119138, "rougeL_recall_stderr": 0.003409137251073175, "rougeLsum_fmeasure": 0.03645148435287092, "rougeLsum_fmeasure_stderr": 0.002076771980839672, "rougeLsum_precision": 0.030881510184046758, "rougeLsum_precision_stderr": 0.0019314337019311182, "rougeLsum_recall": 0.05735625281670475, "rougeLsum_recall_stderr": 0.003380740089049823}}, "5": {"article_DOC_summary": {"bleu": 1.2741760295045995e-38, "bleu_stderr": 6.398898398772146e-33, "rouge1_fmeasure": 0.0033252826117525294, "rouge1_fmeasure_stderr": 0.0008934297630156492, "rouge1_precision": 0.0036570101092707552, "rouge1_precision_stderr": 0.0009755024739951457, "rouge1_recall": 0.003158552109934381, "rouge1_recall_stderr": 0.000860982778191664, "rouge2_fmeasure": 0.0006422730362464498, "rouge2_fmeasure_stderr": 0.00022885115664468214, "rouge2_precision": 0.0006632141135470769, "rouge2_precision_stderr": 0.00022782933435935797, "rouge2_recall": 0.0006369853770402868, "rouge2_recall_stderr": 0.00023576116891012097, "rougeL_fmeasure": 0.0023002231158666315, "rougeL_fmeasure_stderr": 0.0006174742913966595, "rougeL_precision": 0.002516549335872895, "rougeL_precision_stderr": 0.0006650456872731031, "rougeL_recall": 0.0022033496898103025, "rougeL_recall_stderr": 0.0006061893464627548, "rougeLsum_fmeasure": 0.0028016428299652346, "rougeLsum_fmeasure_stderr": 0.0007514162209604014, "rougeLsum_precision": 0.0030601262050967064, "rougeLsum_precision_stderr": 0.0008066078492200342, "rougeLsum_recall": 0.002680985690153414, "rougeLsum_recall_stderr": 0.0007365936380419417}}}}