Muennighoff's picture
Add
2aef930
{"GEM/web_nlg_en": {"0": {"PALM_prompt": {"bleu": 0.34350884519310554, "bleu_stderr": 0.038772150149038065, "rouge1_fmeasure": 0.10544276754647447, "rouge1_fmeasure_stderr": 0.0021544893348497355, "rouge1_precision": 0.07173003966213615, "rouge1_precision_stderr": 0.001891427473975356, "rouge1_recall": 0.28960101855358183, "rouge1_recall_stderr": 0.004686243089174828, "rouge2_fmeasure": 0.05038765662771961, "rouge2_fmeasure_stderr": 0.0013708215929186423, "rouge2_precision": 0.03426167301990358, "rouge2_precision_stderr": 0.0012315349939346193, "rouge2_recall": 0.1392743239236764, "rouge2_recall_stderr": 0.0032402937101130005, "rougeL_fmeasure": 0.10030410348988913, "rougeL_fmeasure_stderr": 0.001982177743894177, "rougeL_precision": 0.06788583144299273, "rougeL_precision_stderr": 0.0017322495246173835, "rougeL_recall": 0.2789368995485402, "rougeL_recall_stderr": 0.004534363609043255, "rougeLsum_fmeasure": 0.10000096230678256, "rougeLsum_fmeasure_stderr": 0.0020180656843696763, "rougeLsum_precision": 0.06804073106746164, "rougeLsum_precision_stderr": 0.0017862439598119247, "rougeLsum_recall": 0.2748870394126657, "rougeLsum_recall_stderr": 0.004363263583019278}}, "1": {"PALM_prompt": {"bleu": 0.4045455604224073, "bleu_stderr": 0.0236576374456469, "rouge1_fmeasure": 0.10223984226049061, "rouge1_fmeasure_stderr": 0.00175780338655891, "rouge1_precision": 0.0658970899010487, "rouge1_precision_stderr": 0.0014479646288584037, "rouge1_recall": 0.3525261563529861, "rouge1_recall_stderr": 0.0050415399648793355, "rouge2_fmeasure": 0.04600863612485982, "rouge2_fmeasure_stderr": 0.0011042614632539437, "rouge2_precision": 0.029637673551245882, "rouge2_precision_stderr": 0.0009108165706734375, "rouge2_recall": 0.1656326153435222, "rouge2_recall_stderr": 0.0035022509689606276, "rougeL_fmeasure": 0.09408291635077375, "rougeL_fmeasure_stderr": 0.0015927729242144477, "rougeL_precision": 0.06067096918490614, "rougeL_precision_stderr": 0.0013097575690947149, "rougeL_recall": 0.32060026791609386, "rougeL_recall_stderr": 0.00440422446137861, "rougeLsum_fmeasure": 0.09636959670083528, "rougeLsum_fmeasure_stderr": 0.001661162141611167, "rougeLsum_precision": 0.06224519569533051, "rougeLsum_precision_stderr": 0.0013718123071500563, "rougeLsum_recall": 0.33007977466199706, "rougeLsum_recall_stderr": 0.00463723121449382}}, "2": {"PALM_prompt": {"bleu": 0.4841613222907723, "bleu_stderr": 0.015039273978834939, "rouge1_fmeasure": 0.10929288546298149, "rouge1_fmeasure_stderr": 0.0017988667388595812, "rouge1_precision": 0.06966385259464293, "rouge1_precision_stderr": 0.0013937412637180038, "rouge1_recall": 0.37512398125219343, "rouge1_recall_stderr": 0.005116912749333124, "rouge2_fmeasure": 0.050112452100538586, "rouge2_fmeasure_stderr": 0.0011570842093378976, "rouge2_precision": 0.03198301338818694, "rouge2_precision_stderr": 0.0008718774993262271, "rouge2_recall": 0.18094325736423483, "rouge2_recall_stderr": 0.0036323707654308335, "rougeL_fmeasure": 0.09977161025587211, "rougeL_fmeasure_stderr": 0.0016243784066598424, "rougeL_precision": 0.06360059097903424, "rougeL_precision_stderr": 0.0012449705718618718, "rougeL_recall": 0.3388899116424299, "rougeL_recall_stderr": 0.004438023718580559, "rougeLsum_fmeasure": 0.10273089804493778, "rougeLsum_fmeasure_stderr": 0.0016928851028229573, "rougeLsum_precision": 0.0655984906937379, "rougeLsum_precision_stderr": 0.0013223896668450679, "rougeLsum_recall": 0.35115785035117936, "rougeLsum_recall_stderr": 0.004705333926430955}}, "3": {"PALM_prompt": {"bleu": 0.5848578510766751, "bleu_stderr": 0.02382820842952149, "rouge1_fmeasure": 0.1123642181797315, "rouge1_fmeasure_stderr": 0.0018086780742506458, "rouge1_precision": 0.07146406939302619, "rouge1_precision_stderr": 0.0014453804488559735, "rouge1_recall": 0.3923331320425209, "rouge1_recall_stderr": 0.005255569174563494, "rouge2_fmeasure": 0.05189108829034796, "rouge2_fmeasure_stderr": 0.0011675575856479941, "rouge2_precision": 0.03311041175360562, "rouge2_precision_stderr": 0.000955769810908034, "rouge2_recall": 0.19200440577658992, "rouge2_recall_stderr": 0.0038021308525194295, "rougeL_fmeasure": 0.10153877113079328, "rougeL_fmeasure_stderr": 0.0016163226649112037, "rougeL_precision": 0.06458792165995919, "rougeL_precision_stderr": 0.0012821596441060375, "rougeL_recall": 0.35290395771176203, "rougeL_recall_stderr": 0.004621707552330829, "rougeLsum_fmeasure": 0.1052784059414783, "rougeLsum_fmeasure_stderr": 0.0017096425628278053, "rougeLsum_precision": 0.06707064624330737, "rougeLsum_precision_stderr": 0.0013662159713619777, "rougeLsum_recall": 0.3662637426139491, "rougeLsum_recall_stderr": 0.004856741037403349}}, "4": {"PALM_prompt": {"bleu": 0.5815622592156788, "bleu_stderr": 0.029409084100340988, "rouge1_fmeasure": 0.11600454183618039, "rouge1_fmeasure_stderr": 0.0017414056230866818, "rouge1_precision": 0.073350621026601, "rouge1_precision_stderr": 0.0013008441046774397, "rouge1_recall": 0.402711193766134, "rouge1_recall_stderr": 0.005268855314940937, "rouge2_fmeasure": 0.05350261302900716, "rouge2_fmeasure_stderr": 0.0011180842631744589, "rouge2_precision": 0.03375946119188094, "rouge2_precision_stderr": 0.0008125358382760585, "rouge2_recall": 0.19912887839246102, "rouge2_recall_stderr": 0.003887307664703985, "rougeL_fmeasure": 0.10528355390377818, "rougeL_fmeasure_stderr": 0.0015840788654041859, "rougeL_precision": 0.06666295825312767, "rougeL_precision_stderr": 0.001186073659230382, "rougeL_recall": 0.3633610895084421, "rougeL_recall_stderr": 0.004665095807994941, "rougeLsum_fmeasure": 0.10893873510925292, "rougeLsum_fmeasure_stderr": 0.0016436803370992086, "rougeLsum_precision": 0.06900491931707611, "rougeLsum_precision_stderr": 0.0012357509964065728, "rougeLsum_recall": 0.37672100976400624, "rougeLsum_recall_stderr": 0.0048637174582481756}}, "5": {"PALM_prompt": {"bleu": 0.6292734470145089, "bleu_stderr": 0.032038534440523625, "rouge1_fmeasure": 0.11745960029316531, "rouge1_fmeasure_stderr": 0.0017300682232481712, "rouge1_precision": 0.07430554120104693, "rouge1_precision_stderr": 0.0013333669684835047, "rouge1_recall": 0.40910724158477596, "rouge1_recall_stderr": 0.005285245988912935, "rouge2_fmeasure": 0.05452068929305587, "rouge2_fmeasure_stderr": 0.0011284229311503077, "rouge2_precision": 0.03448188474999599, "rouge2_precision_stderr": 0.0008618085647059942, "rouge2_recall": 0.20431478176242832, "rouge2_recall_stderr": 0.0039032533628420053, "rougeL_fmeasure": 0.10569984600090632, "rougeL_fmeasure_stderr": 0.0015559332991619912, "rougeL_precision": 0.06699056196994188, "rougeL_precision_stderr": 0.001214766584623908, "rougeL_recall": 0.36652587603372083, "rougeL_recall_stderr": 0.0046510504742824435, "rougeLsum_fmeasure": 0.10969123482143882, "rougeLsum_fmeasure_stderr": 0.0016247884404989854, "rougeLsum_precision": 0.06952080008680515, "rougeLsum_precision_stderr": 0.0012664771484443501, "rougeLsum_recall": 0.38090153422695555, "rougeLsum_recall_stderr": 0.004832634454846149}}}, "GEM/wiki_lingua_en": {"0": {"tldr_en": {"bleu": 1.4638786550080012, "bleu_stderr": 0.08267943817716743, "rouge1_fmeasure": 0.1735899714732908, "rouge1_fmeasure_stderr": 0.0018379295907133386, "rouge1_precision": 0.1501551653167452, "rouge1_precision_stderr": 0.0019145985531852103, "rouge1_recall": 0.2489709412710993, "rouge1_recall_stderr": 0.002565698467707567, "rouge2_fmeasure": 0.03527159968688606, "rouge2_fmeasure_stderr": 0.000856000364522866, "rouge2_precision": 0.030202594861558258, "rouge2_precision_stderr": 0.000759198757195269, "rouge2_recall": 0.05179351194647759, "rouge2_recall_stderr": 0.0013706134138774457, "rougeL_fmeasure": 0.13542458385119363, "rougeL_fmeasure_stderr": 0.0013094512830872681, "rougeL_precision": 0.11587674124907248, "rougeL_precision_stderr": 0.0013578078418251586, "rougeL_recall": 0.19905321222991249, "rougeL_recall_stderr": 0.002072708736632529, "rougeLsum_fmeasure": 0.15998195547427285, "rougeLsum_fmeasure_stderr": 0.0016735883778822192, "rougeLsum_precision": 0.13806383555422214, "rougeLsum_precision_stderr": 0.0017411900348176868, "rougeLsum_recall": 0.23066945559291627, "rougeLsum_recall_stderr": 0.0023890574843587445}}, "1": {"tldr_en": {"bleu": 2.251037388830426, "bleu_stderr": 0.06386416803226096, "rouge1_fmeasure": 0.20517386588028216, "rouge1_fmeasure_stderr": 0.0019096420138433956, "rouge1_precision": 0.17561493820630653, "rouge1_precision_stderr": 0.002048580212979638, "rouge1_recall": 0.2975242805713054, "rouge1_recall_stderr": 0.002661646132459767, "rouge2_fmeasure": 0.04509174855817, "rouge2_fmeasure_stderr": 0.0009362703351931108, "rouge2_precision": 0.038705255482649484, "rouge2_precision_stderr": 0.0008641576645556467, "rouge2_recall": 0.06721747132871511, "rouge2_recall_stderr": 0.0015546205463413934, "rougeL_fmeasure": 0.1461985663690308, "rougeL_fmeasure_stderr": 0.0012629826687957297, "rougeL_precision": 0.12348273344528769, "rougeL_precision_stderr": 0.0013241963423884194, "rougeL_recall": 0.2182708873208918, "rougeL_recall_stderr": 0.002078335701646665, "rougeLsum_fmeasure": 0.19199261777381824, "rougeLsum_fmeasure_stderr": 0.0017768312743395834, "rougeLsum_precision": 0.16411787830700947, "rougeLsum_precision_stderr": 0.001905726984632049, "rougeLsum_recall": 0.2793462022470309, "rougeLsum_recall_stderr": 0.00252183230288639}}, "2": {"tldr_en": {"bleu": 2.638972923238051, "bleu_stderr": 0.04079081483713292, "rouge1_fmeasure": 0.2149553929096824, "rouge1_fmeasure_stderr": 0.0018159340053845016, "rouge1_precision": 0.18279672864000174, "rouge1_precision_stderr": 0.001990030228234584, "rouge1_recall": 0.31492793105361294, "rouge1_recall_stderr": 0.0025616011512098248, "rouge2_fmeasure": 0.050099922234849326, "rouge2_fmeasure_stderr": 0.0009396332686045797, "rouge2_precision": 0.042646009741889805, "rouge2_precision_stderr": 0.0008649264691986515, "rouge2_recall": 0.07496946538732863, "rouge2_recall_stderr": 0.0015594180926328848, "rougeL_fmeasure": 0.152189270942713, "rougeL_fmeasure_stderr": 0.0012132534448735604, "rougeL_precision": 0.12807089612938685, "rougeL_precision_stderr": 0.0013124423288503014, "rougeL_recall": 0.22896480825128132, "rougeL_recall_stderr": 0.0020362817656302, "rougeLsum_fmeasure": 0.20261963860140034, "rougeLsum_fmeasure_stderr": 0.001699260136326749, "rougeLsum_precision": 0.1719794802172194, "rougeLsum_precision_stderr": 0.0018519473657900671, "rougeLsum_recall": 0.29789003880343934, "rougeLsum_recall_stderr": 0.002450408388704567}}, "3": {"tldr_en": {"bleu": 2.7817782152958124, "bleu_stderr": 0.04494580041852014, "rouge1_fmeasure": 0.1811722525980339, "rouge1_fmeasure_stderr": 0.0022088859505497234, "rouge1_precision": 0.15880336071647017, "rouge1_precision_stderr": 0.0022944434654695485, "rouge1_recall": 0.26506418569211093, "rouge1_recall_stderr": 0.0032637292322135534, "rouge2_fmeasure": 0.04316445582714641, "rouge2_fmeasure_stderr": 0.000956046878850861, "rouge2_precision": 0.0374298998336526, "rouge2_precision_stderr": 0.0009347509198517388, "rouge2_recall": 0.06524543251395427, "rouge2_recall_stderr": 0.001603994023546246, "rougeL_fmeasure": 0.12842259890093402, "rougeL_fmeasure_stderr": 0.0015101623900602265, "rougeL_precision": 0.11189815593178445, "rougeL_precision_stderr": 0.001600964481991733, "rougeL_recall": 0.1930856830862472, "rougeL_recall_stderr": 0.0025117226250944077, "rougeLsum_fmeasure": 0.1708671620256238, "rougeLsum_fmeasure_stderr": 0.0020803868308500607, "rougeLsum_precision": 0.14949474498482374, "rougeLsum_precision_stderr": 0.0021540706302144844, "rougeLsum_recall": 0.2508189749530171, "rougeLsum_recall_stderr": 0.0031145852012745777}}, "4": {"tldr_en": {"bleu": 0.5997291080192819, "bleu_stderr": 0.034966523246928005, "rouge1_fmeasure": 0.058148219500646206, "rouge1_fmeasure_stderr": 0.0019439260562197995, "rouge1_precision": 0.0526082191649819, "rouge1_precision_stderr": 0.0019579711254660813, "rouge1_recall": 0.08887123055545011, "rouge1_recall_stderr": 0.002973119831747629, "rouge2_fmeasure": 0.013391403283503953, "rouge2_fmeasure_stderr": 0.0006305028420949355, "rouge2_precision": 0.012404560376357416, "rouge2_precision_stderr": 0.000765615351847643, "rouge2_recall": 0.021336430842142755, "rouge2_recall_stderr": 0.001118116808651589, "rougeL_fmeasure": 0.042154106197481285, "rougeL_fmeasure_stderr": 0.001383034127114084, "rougeL_precision": 0.038334561197559465, "rougeL_precision_stderr": 0.001465640058040743, "rougeL_recall": 0.06619947973463458, "rougeL_recall_stderr": 0.0022604433031636296, "rougeLsum_fmeasure": 0.05448171126882292, "rougeLsum_fmeasure_stderr": 0.0018181715140947877, "rougeLsum_precision": 0.049466020968478554, "rougeLsum_precision_stderr": 0.0018544231085558262, "rougeLsum_recall": 0.08334408075199987, "rougeLsum_recall_stderr": 0.002792361572274234}}, "5": {"tldr_en": {"bleu": 1.0320053783861012e-06, "bleu_stderr": 1.6548309745966328e-06, "rouge1_fmeasure": 0.009101109725055801, "rouge1_fmeasure_stderr": 0.000849061484627802, "rouge1_precision": 0.00828795189621696, "rouge1_precision_stderr": 0.0008084030145764894, "rouge1_recall": 0.013904833680136126, "rouge1_recall_stderr": 0.0013152248622154829, "rouge2_fmeasure": 0.0021173402290246453, "rouge2_fmeasure_stderr": 0.0002651969883574264, "rouge2_precision": 0.0017579778442265573, "rouge2_precision_stderr": 0.00022272256203822104, "rouge2_recall": 0.0034824583016457547, "rouge2_recall_stderr": 0.0004707745855497479, "rougeL_fmeasure": 0.006671364196388791, "rougeL_fmeasure_stderr": 0.0006155682683130244, "rougeL_precision": 0.00606164612301448, "rougeL_precision_stderr": 0.0005820824170547412, "rougeL_recall": 0.010516775330575035, "rougeL_recall_stderr": 0.0010286453150278683, "rougeLsum_fmeasure": 0.00852403124177262, "rougeLsum_fmeasure_stderr": 0.000789483822967171, "rougeLsum_precision": 0.0077547689033896795, "rougeLsum_precision_stderr": 0.0007519757597042171, "rougeLsum_recall": 0.013113865139552568, "rougeLsum_recall_stderr": 0.0012437323588959986}}}, "e2e_nlg_cleaned": {"0": {"generate_text_restaurant": {"bleu": 1.4456822172834254, "bleu_stderr": 0.04276533070237041, "rouge1_fmeasure": 0.10550747830492155, "rouge1_fmeasure_stderr": 0.001600046418184004, "rouge1_precision": 0.08084608817477075, "rouge1_precision_stderr": 0.0013037630358869862, "rouge1_recall": 0.16055476672730024, "rouge1_recall_stderr": 0.0022564902307428436, "rouge2_fmeasure": 0.023111704860364103, "rouge2_fmeasure_stderr": 0.0008023451007582199, "rouge2_precision": 0.0180883910143694, "rouge2_precision_stderr": 0.0006324971623061661, "rouge2_recall": 0.03352985411112681, "rouge2_recall_stderr": 0.0011860257734223087, "rougeL_fmeasure": 0.10309579699961463, "rougeL_fmeasure_stderr": 0.0014856345287328617, "rougeL_precision": 0.07897160421844947, "rougeL_precision_stderr": 0.0012157586325601468, "rougeL_recall": 0.15704150708399545, "rougeL_recall_stderr": 0.0020880518954252106, "rougeLsum_fmeasure": 0.085687119444743, "rougeLsum_fmeasure_stderr": 0.0014326281774339593, "rougeLsum_precision": 0.06566532991903784, "rougeLsum_precision_stderr": 0.00115593325264158, "rougeLsum_recall": 0.13043930012149813, "rougeLsum_recall_stderr": 0.0020438483091751833}}, "1": {"generate_text_restaurant": {"bleu": 7.854550343569453, "bleu_stderr": 0.11842361375802873, "rouge1_fmeasure": 0.37960517377654424, "rouge1_fmeasure_stderr": 0.0021312179107678742, "rouge1_precision": 0.35242925608961834, "rouge1_precision_stderr": 0.0025862879156174677, "rouge1_recall": 0.4593871286009479, "rouge1_recall_stderr": 0.0027718307444898073, "rouge2_fmeasure": 0.16225548525605324, "rouge2_fmeasure_stderr": 0.001628980531143478, "rouge2_precision": 0.15016846460595357, "rouge2_precision_stderr": 0.0016925643088238768, "rouge2_recall": 0.1987661075234813, "rouge2_recall_stderr": 0.002085741403395336, "rougeL_fmeasure": 0.2751099734003478, "rougeL_fmeasure_stderr": 0.0015986731793980245, "rougeL_precision": 0.2535878033618753, "rougeL_precision_stderr": 0.0018603284522068176, "rougeL_recall": 0.3373488751020238, "rougeL_recall_stderr": 0.0023042860742874356, "rougeLsum_fmeasure": 0.31764028681903844, "rougeLsum_fmeasure_stderr": 0.0020166639615139246, "rougeLsum_precision": 0.2947167761956799, "rougeLsum_precision_stderr": 0.002321783937504011, "rougeLsum_recall": 0.3850310566251188, "rougeLsum_recall_stderr": 0.0026364808102144186}}, "2": {"generate_text_restaurant": {"bleu": 10.584259500465588, "bleu_stderr": 0.1544206935916045, "rouge1_fmeasure": 0.41716631446436636, "rouge1_fmeasure_stderr": 0.001904443983975073, "rouge1_precision": 0.4101598697462684, "rouge1_precision_stderr": 0.002246311055501821, "rouge1_recall": 0.4603951235406536, "rouge1_recall_stderr": 0.002736343584240638, "rouge2_fmeasure": 0.18592733733343356, "rouge2_fmeasure_stderr": 0.001651511887316203, "rouge2_precision": 0.1817762545465421, "rouge2_precision_stderr": 0.0017054003975476711, "rouge2_recall": 0.20814546072005263, "rouge2_recall_stderr": 0.0021073018090344247, "rougeL_fmeasure": 0.29825905325627894, "rougeL_fmeasure_stderr": 0.0016671912167031061, "rougeL_precision": 0.29271400984628115, "rougeL_precision_stderr": 0.0018520206075962242, "rougeL_recall": 0.3307167069836982, "rougeL_recall_stderr": 0.002352222065176941, "rougeLsum_fmeasure": 0.3497622641102556, "rougeLsum_fmeasure_stderr": 0.0019222555310956092, "rougeLsum_precision": 0.3438330605735075, "rougeLsum_precision_stderr": 0.0021559258341024025, "rougeLsum_recall": 0.3863382687718853, "rougeLsum_recall_stderr": 0.0026264477519150294}}, "3": {"generate_text_restaurant": {"bleu": 11.005027804713954, "bleu_stderr": 0.14913713325107694, "rouge1_fmeasure": 0.4199469764935773, "rouge1_fmeasure_stderr": 0.001866102905923008, "rouge1_precision": 0.4128283610854264, "rouge1_precision_stderr": 0.00218582649540743, "rouge1_recall": 0.4617654209580726, "rouge1_recall_stderr": 0.0027204559282358, "rouge2_fmeasure": 0.18965165207657023, "rouge2_fmeasure_stderr": 0.0016611244058807987, "rouge2_precision": 0.18554586275444523, "rouge2_precision_stderr": 0.0017040263392683272, "rouge2_recall": 0.2117021500635163, "rouge2_recall_stderr": 0.002152756842715476, "rougeL_fmeasure": 0.298413421066599, "rougeL_fmeasure_stderr": 0.0016514441907895666, "rougeL_precision": 0.29313420912472204, "rougeL_precision_stderr": 0.0018337994526123047, "rougeL_recall": 0.32931921594254, "rougeL_recall_stderr": 0.0023370831957328685, "rougeLsum_fmeasure": 0.3531127839068146, "rougeLsum_fmeasure_stderr": 0.0018773997153010787, "rougeLsum_precision": 0.34697556096050464, "rougeLsum_precision_stderr": 0.002097945215373547, "rougeLsum_recall": 0.3888925774714783, "rougeLsum_recall_stderr": 0.002615178055125266}}, "4": {"generate_text_restaurant": {"bleu": 11.363725115618854, "bleu_stderr": 0.1349892134607558, "rouge1_fmeasure": 0.4214008037563902, "rouge1_fmeasure_stderr": 0.0018957274669436463, "rouge1_precision": 0.41369428294464894, "rouge1_precision_stderr": 0.0022630498681273214, "rouge1_recall": 0.463073205676912, "rouge1_recall_stderr": 0.002620101280268744, "rouge2_fmeasure": 0.19224882966800977, "rouge2_fmeasure_stderr": 0.001688941669379114, "rouge2_precision": 0.18853767720104403, "rouge2_precision_stderr": 0.0017966301373649335, "rouge2_recall": 0.21376292605494995, "rouge2_recall_stderr": 0.0021133996361269876, "rougeL_fmeasure": 0.30045503720645306, "rougeL_fmeasure_stderr": 0.0017243402211031724, "rougeL_precision": 0.2947773213194346, "rougeL_precision_stderr": 0.0019453260402410404, "rougeL_recall": 0.33160719324501514, "rougeL_recall_stderr": 0.0023386028746102032, "rougeLsum_fmeasure": 0.35440044254437, "rougeLsum_fmeasure_stderr": 0.001939185206150459, "rougeLsum_precision": 0.34793871661300624, "rougeLsum_precision_stderr": 0.0022022816802554548, "rougeLsum_recall": 0.38987225844490936, "rougeLsum_recall_stderr": 0.0025624343675698957}}, "5": {"generate_text_restaurant": {"bleu": 11.396192996497414, "bleu_stderr": 0.16654357094855035, "rouge1_fmeasure": 0.42256346127489886, "rouge1_fmeasure_stderr": 0.0018711992463432423, "rouge1_precision": 0.415343404582103, "rouge1_precision_stderr": 0.0022395714603746343, "rouge1_recall": 0.462339881403203, "rouge1_recall_stderr": 0.002606515070610007, "rouge2_fmeasure": 0.19258472578075223, "rouge2_fmeasure_stderr": 0.0016595774845375585, "rouge2_precision": 0.18874947831873545, "rouge2_precision_stderr": 0.0017363983679664929, "rouge2_recall": 0.21329100699058842, "rouge2_recall_stderr": 0.0020862831128997342, "rougeL_fmeasure": 0.29935707532452077, "rougeL_fmeasure_stderr": 0.0016828692465751755, "rougeL_precision": 0.29366555957532514, "rougeL_precision_stderr": 0.0018624351126946828, "rougeL_recall": 0.32911404216108797, "rougeL_recall_stderr": 0.0023155754665530786, "rougeLsum_fmeasure": 0.3555436949251867, "rougeLsum_fmeasure_stderr": 0.0019127831146169912, "rougeLsum_precision": 0.34963846222070455, "rougeLsum_precision_stderr": 0.0021787598409919178, "rougeLsum_recall": 0.3890874281204962, "rougeLsum_recall_stderr": 0.0025265070175629857}}}, "gem_xsum": {"0": {"article_DOC_summary": {"bleu": 1.8234981410881652, "bleu_stderr": 0.09861688194525574, "rouge1_fmeasure": 0.20889878659689404, "rouge1_fmeasure_stderr": 0.002458161766680771, "rouge1_precision": 0.15422621570346934, "rouge1_precision_stderr": 0.0020039005936603317, "rouge1_recall": 0.3506635490563916, "rouge1_recall_stderr": 0.0042556493547655115, "rouge2_fmeasure": 0.04565942952067972, "rouge2_fmeasure_stderr": 0.001484562672483921, "rouge2_precision": 0.03307990095257621, "rouge2_precision_stderr": 0.0011002276404168225, "rouge2_recall": 0.07910944220650014, "rouge2_recall_stderr": 0.0026293603468150466, "rougeL_fmeasure": 0.15587034501708355, "rougeL_fmeasure_stderr": 0.0018431637093872144, "rougeL_precision": 0.11490133308951496, "rougeL_precision_stderr": 0.001481297426684668, "rougeL_recall": 0.26284399370938016, "rougeL_recall_stderr": 0.0033084414512192374, "rougeLsum_fmeasure": 0.1651849748571103, "rougeLsum_fmeasure_stderr": 0.002039061494531475, "rougeLsum_precision": 0.12158807333409381, "rougeLsum_precision_stderr": 0.0016089880194761488, "rougeLsum_recall": 0.278789316707468, "rougeLsum_recall_stderr": 0.00364738944247525}}, "1": {"article_DOC_summary": {"bleu": 1.4511145888771138, "bleu_stderr": 0.09215852910549645, "rouge1_fmeasure": 0.18254418171842912, "rouge1_fmeasure_stderr": 0.0024443411491113813, "rouge1_precision": 0.12978400090119854, "rouge1_precision_stderr": 0.0018214048412026733, "rouge1_recall": 0.32027413224988105, "rouge1_recall_stderr": 0.00416743115408514, "rouge2_fmeasure": 0.036825241144522146, "rouge2_fmeasure_stderr": 0.0014067669670603119, "rouge2_precision": 0.025920284045820686, "rouge2_precision_stderr": 0.0009915583067368265, "rouge2_recall": 0.06631766447507839, "rouge2_recall_stderr": 0.0026016286386155744, "rougeL_fmeasure": 0.1379121041144307, "rougeL_fmeasure_stderr": 0.0018159806506780998, "rougeL_precision": 0.09779168145477703, "rougeL_precision_stderr": 0.0013336831707437397, "rougeL_recall": 0.24393449987832236, "rougeL_recall_stderr": 0.0032690620169295624, "rougeLsum_fmeasure": 0.14685271867556554, "rougeLsum_fmeasure_stderr": 0.00202786402481471, "rougeLsum_precision": 0.10419708360998835, "rougeLsum_precision_stderr": 0.0014908021891115058, "rougeLsum_recall": 0.2591470200293115, "rougeLsum_recall_stderr": 0.0035902088886349626}}, "2": {"article_DOC_summary": {"bleu": 1.4173910716715976, "bleu_stderr": 0.1269050055569669, "rouge1_fmeasure": 0.1784133650153775, "rouge1_fmeasure_stderr": 0.002434527345664647, "rouge1_precision": 0.12682893488466288, "rouge1_precision_stderr": 0.0018115124386976255, "rouge1_recall": 0.3129238773710033, "rouge1_recall_stderr": 0.004144317584991236, "rouge2_fmeasure": 0.03377646994942601, "rouge2_fmeasure_stderr": 0.0013577113683580135, "rouge2_precision": 0.023792739813654398, "rouge2_precision_stderr": 0.0009538695469598671, "rouge2_recall": 0.060628286518002124, "rouge2_recall_stderr": 0.002544171640335871, "rougeL_fmeasure": 0.13445676544883162, "rougeL_fmeasure_stderr": 0.001742983161792639, "rougeL_precision": 0.09538132852222156, "rougeL_precision_stderr": 0.0012844315555328582, "rougeL_recall": 0.23736904076265325, "rougeL_recall_stderr": 0.0031180197306729797, "rougeLsum_fmeasure": 0.14302327166537732, "rougeLsum_fmeasure_stderr": 0.0020121565752601223, "rougeLsum_precision": 0.10150079343006048, "rougeLsum_precision_stderr": 0.0014805542361053387, "rougeLsum_recall": 0.25224041568358746, "rougeLsum_recall_stderr": 0.00356325287772434}}, "3": {"article_DOC_summary": {"bleu": 1.4410854543220795, "bleu_stderr": 0.11065939978206533, "rouge1_fmeasure": 0.17405000505151677, "rouge1_fmeasure_stderr": 0.0026158795444079694, "rouge1_precision": 0.12682835665999379, "rouge1_precision_stderr": 0.00213008962319155, "rouge1_recall": 0.3009777871605996, "rouge1_recall_stderr": 0.0045155564803296844, "rouge2_fmeasure": 0.03375564198727498, "rouge2_fmeasure_stderr": 0.0014032677780195426, "rouge2_precision": 0.02441534481786468, "rouge2_precision_stderr": 0.0010675183688113013, "rouge2_recall": 0.060023335309239284, "rouge2_recall_stderr": 0.0025544641047680868, "rougeL_fmeasure": 0.13287002402660542, "rougeL_fmeasure_stderr": 0.0019574198182001363, "rougeL_precision": 0.09672846502785581, "rougeL_precision_stderr": 0.001605939754348312, "rougeL_recall": 0.23129794905638065, "rougeL_recall_stderr": 0.003504325859643222, "rougeLsum_fmeasure": 0.14072796227018858, "rougeLsum_fmeasure_stderr": 0.002188698179032325, "rougeLsum_precision": 0.10242219504173285, "rougeLsum_precision_stderr": 0.0017649678079630277, "rougeLsum_recall": 0.2447872835150151, "rougeLsum_recall_stderr": 0.0038950725453768833}}, "4": {"article_DOC_summary": {"bleu": 0.6753547790268645, "bleu_stderr": 0.09678811316166971, "rouge1_fmeasure": 0.046992144100321806, "rouge1_fmeasure_stderr": 0.002618786666967082, "rouge1_precision": 0.041064589753945765, "rouge1_precision_stderr": 0.002574722440175742, "rouge1_recall": 0.07375404829054749, "rouge1_recall_stderr": 0.004261542973214119, "rouge2_fmeasure": 0.008636963128827568, "rouge2_fmeasure_stderr": 0.0008391846215142884, "rouge2_precision": 0.0072827259137400735, "rouge2_precision_stderr": 0.0008839873299209189, "rouge2_recall": 0.01434569739075993, "rouge2_recall_stderr": 0.0014362041655696376, "rougeL_fmeasure": 0.03548036137516894, "rougeL_fmeasure_stderr": 0.001955807555849124, "rougeL_precision": 0.03137075485796663, "rougeL_precision_stderr": 0.0020006363883442293, "rougeL_recall": 0.05624031413634613, "rougeL_recall_stderr": 0.0032626943561910897, "rougeLsum_fmeasure": 0.03810619457684465, "rougeLsum_fmeasure_stderr": 0.0021359009016179383, "rougeLsum_precision": 0.03357423627999912, "rougeLsum_precision_stderr": 0.0021310282339018806, "rougeLsum_recall": 0.059996937228044826, "rougeLsum_recall_stderr": 0.003508594344969223}}, "5": {"article_DOC_summary": {"bleu": 3.8720991740133824e-38, "bleu_stderr": 6.757775100349013e-33, "rouge1_fmeasure": 0.0021338767527660316, "rouge1_fmeasure_stderr": 0.000606716788713842, "rouge1_precision": 0.002394598265414318, "rouge1_precision_stderr": 0.0007029813930147865, "rouge1_recall": 0.0019954716710551207, "rouge1_recall_stderr": 0.0005584193559240988, "rouge2_fmeasure": 0.00011901404509555748, "rouge2_fmeasure_stderr": 6.872962972148577e-05, "rouge2_precision": 0.0001469327010392493, "rouge2_precision_stderr": 8.511648046715374e-05, "rouge2_recall": 0.00010241330996047977, "rouge2_recall_stderr": 5.9726635104036084e-05, "rougeL_fmeasure": 0.0015909130557671355, "rougeL_fmeasure_stderr": 0.0004446509241590643, "rougeL_precision": 0.0017715789785566055, "rougeL_precision_stderr": 0.0005103213321970242, "rougeL_recall": 0.0015030111824248839, "rougeL_recall_stderr": 0.0004165975224565321, "rougeLsum_fmeasure": 0.001799689332800904, "rougeLsum_fmeasure_stderr": 0.0005143272355042585, "rougeLsum_precision": 0.0020245246393824, "rougeLsum_precision_stderr": 0.0006015169025391406, "rougeLsum_recall": 0.0016826910638698292, "rougeLsum_recall_stderr": 0.0004718028635824783}}}}