Muennighoff's picture
Add files
e467b8d
{"GEM/web_nlg_en": {"0": {"PALM_prompt": {"bleu": 0.36676283856494113, "bleu_stderr": 0.0474507783379639, "rouge1_fmeasure": 0.09441575378592391, "rouge1_fmeasure_stderr": 0.0020680531546244394, "rouge1_precision": 0.062332014806189766, "rouge1_precision_stderr": 0.0016383703848229427, "rouge1_recall": 0.293777806984314, "rouge1_recall_stderr": 0.005252782658193723, "rouge2_fmeasure": 0.04314501248705826, "rouge2_fmeasure_stderr": 0.001258246183189075, "rouge2_precision": 0.028711966510953046, "rouge2_precision_stderr": 0.000984576654338761, "rouge2_recall": 0.1322458599845081, "rouge2_recall_stderr": 0.003314534134287909, "rougeL_fmeasure": 0.0882116048398588, "rougeL_fmeasure_stderr": 0.0018389749448658346, "rougeL_precision": 0.057942425405580346, "rougeL_precision_stderr": 0.0014255082882140484, "rougeL_recall": 0.2776785385893423, "rougeL_recall_stderr": 0.0049436461818446135, "rougeLsum_fmeasure": 0.08927510610731734, "rougeLsum_fmeasure_stderr": 0.001938092014044731, "rougeLsum_precision": 0.058934717518613434, "rougeLsum_precision_stderr": 0.001525972938212972, "rougeLsum_recall": 0.27624443355923034, "rougeLsum_recall_stderr": 0.004852154002930374}}, "1": {"PALM_prompt": {"bleu": 0.42447490695849177, "bleu_stderr": 0.031118881647332453, "rouge1_fmeasure": 0.11353731182395607, "rouge1_fmeasure_stderr": 0.0019319506260635304, "rouge1_precision": 0.07242166849415733, "rouge1_precision_stderr": 0.0013848386081542273, "rouge1_recall": 0.3588660487979018, "rouge1_recall_stderr": 0.005213387725734495, "rouge2_fmeasure": 0.051698558921326514, "rouge2_fmeasure_stderr": 0.0012001219460540538, "rouge2_precision": 0.03288701360932817, "rouge2_precision_stderr": 0.000839098109533103, "rouge2_recall": 0.17107042365285788, "rouge2_recall_stderr": 0.0036083953475667513, "rougeL_fmeasure": 0.10521613042548694, "rougeL_fmeasure_stderr": 0.0017181082493525662, "rougeL_precision": 0.0670061822698939, "rougeL_precision_stderr": 0.001227160746048086, "rougeL_recall": 0.3346245385921824, "rougeL_recall_stderr": 0.004814146748998719, "rougeLsum_fmeasure": 0.10736276773335406, "rougeLsum_fmeasure_stderr": 0.0018148053880352902, "rougeLsum_precision": 0.06851784863794814, "rougeLsum_precision_stderr": 0.0013044655089246824, "rougeLsum_recall": 0.33834197646314856, "rougeLsum_recall_stderr": 0.004780908665148567}}, "2": {"PALM_prompt": {"bleu": 0.5078474394915784, "bleu_stderr": 0.04940313819145897, "rouge1_fmeasure": 0.11839194985760551, "rouge1_fmeasure_stderr": 0.0018550236570084812, "rouge1_precision": 0.07524299617261106, "rouge1_precision_stderr": 0.0013542247809418073, "rouge1_recall": 0.3789792715638066, "rouge1_recall_stderr": 0.005087267508547312, "rouge2_fmeasure": 0.05453717672261224, "rouge2_fmeasure_stderr": 0.0012063786187369366, "rouge2_precision": 0.03451419278556197, "rouge2_precision_stderr": 0.0008480461582178029, "rouge2_recall": 0.18485893110508558, "rouge2_recall_stderr": 0.0037439432130783046, "rougeL_fmeasure": 0.10986668151378429, "rougeL_fmeasure_stderr": 0.0016757644991035844, "rougeL_precision": 0.06970631509385179, "rougeL_precision_stderr": 0.0012132144640462751, "rougeL_recall": 0.35342460023270555, "rougeL_recall_stderr": 0.0047409890816951, "rougeLsum_fmeasure": 0.11142211614255489, "rougeLsum_fmeasure_stderr": 0.0017402016546960485, "rougeLsum_precision": 0.07085029048321866, "rougeLsum_precision_stderr": 0.001272417656582146, "rougeLsum_recall": 0.35589542269045665, "rougeLsum_recall_stderr": 0.004677996287698992}}, "3": {"PALM_prompt": {"bleu": 0.5321467980679849, "bleu_stderr": 0.030789259184486762, "rouge1_fmeasure": 0.11775282391938749, "rouge1_fmeasure_stderr": 0.0018121209623013599, "rouge1_precision": 0.07467739697980223, "rouge1_precision_stderr": 0.0013056742555484042, "rouge1_recall": 0.3765931475512988, "rouge1_recall_stderr": 0.005136827785933215, "rouge2_fmeasure": 0.05437250272050667, "rouge2_fmeasure_stderr": 0.0011494478736656965, "rouge2_precision": 0.03425895499250951, "rouge2_precision_stderr": 0.0007949938460894235, "rouge2_recall": 0.1857701112713038, "rouge2_recall_stderr": 0.0037899558051587997, "rougeL_fmeasure": 0.109142035871985, "rougeL_fmeasure_stderr": 0.0016567099883848363, "rougeL_precision": 0.0691367241290362, "rougeL_precision_stderr": 0.0011898077979863157, "rougeL_recall": 0.35044113186494674, "rougeL_recall_stderr": 0.004789067731865496, "rougeLsum_fmeasure": 0.11055745133283143, "rougeLsum_fmeasure_stderr": 0.0017021172309438397, "rougeLsum_precision": 0.07016534933559325, "rougeLsum_precision_stderr": 0.001231446670361234, "rougeLsum_recall": 0.3527313952049522, "rougeLsum_recall_stderr": 0.004720204023911692}}, "4": {"PALM_prompt": {"bleu": 0.5836215112044281, "bleu_stderr": 0.0373980578845506, "rouge1_fmeasure": 0.12273951831524596, "rouge1_fmeasure_stderr": 0.0018568477885135075, "rouge1_precision": 0.07814979242067882, "rouge1_precision_stderr": 0.0013719481084767942, "rouge1_recall": 0.3904381500627582, "rouge1_recall_stderr": 0.005108365571685621, "rouge2_fmeasure": 0.05731193809218633, "rouge2_fmeasure_stderr": 0.0012015065055436362, "rouge2_precision": 0.036278020218023364, "rouge2_precision_stderr": 0.0008590667413980339, "rouge2_recall": 0.19568480085429035, "rouge2_recall_stderr": 0.0037894995606282777, "rougeL_fmeasure": 0.11294640173282941, "rougeL_fmeasure_stderr": 0.0016715462444065227, "rougeL_precision": 0.07184600146882388, "rougeL_precision_stderr": 0.0012338794593141857, "rougeL_recall": 0.361289411306646, "rougeL_recall_stderr": 0.004721144658086456, "rougeLsum_fmeasure": 0.11548902373578677, "rougeLsum_fmeasure_stderr": 0.0017405908622108689, "rougeLsum_precision": 0.07360622983361918, "rougeLsum_precision_stderr": 0.0012935410743410267, "rougeLsum_recall": 0.3670374936279833, "rougeLsum_recall_stderr": 0.004716543868495296}}, "5": {"PALM_prompt": {"bleu": 0.594609825520194, "bleu_stderr": 0.04115839696833975, "rouge1_fmeasure": 0.12086027376047605, "rouge1_fmeasure_stderr": 0.0017433543864987184, "rouge1_precision": 0.07606093952092045, "rouge1_precision_stderr": 0.0012363342608298056, "rouge1_recall": 0.3956239968710567, "rouge1_recall_stderr": 0.005142405199368944, "rouge2_fmeasure": 0.055825671549297295, "rouge2_fmeasure_stderr": 0.0011219041594589493, "rouge2_precision": 0.034848706116865254, "rouge2_precision_stderr": 0.0007661213026779092, "rouge2_recall": 0.1971845061377734, "rouge2_recall_stderr": 0.003781803943041313, "rougeL_fmeasure": 0.11109358926885284, "rougeL_fmeasure_stderr": 0.001582946667660359, "rougeL_precision": 0.06988703720341218, "rougeL_precision_stderr": 0.001122929060032178, "rougeL_recall": 0.3647605769777058, "rougeL_recall_stderr": 0.0047210888757834, "rougeLsum_fmeasure": 0.11358138097063522, "rougeLsum_fmeasure_stderr": 0.0016202519807538079, "rougeLsum_precision": 0.07150521311673122, "rougeLsum_precision_stderr": 0.0011539037542073426, "rougeLsum_recall": 0.3721409413587192, "rougeLsum_recall_stderr": 0.0047326985289146365}}}, "GEM/wiki_lingua_en": {"0": {"tldr_en": {"bleu": 1.318952551089346, "bleu_stderr": 0.04329525521577347, "rouge1_fmeasure": 0.15459597826273924, "rouge1_fmeasure_stderr": 0.0018270611999879997, "rouge1_precision": 0.1319714359255099, "rouge1_precision_stderr": 0.0018067861281345137, "rouge1_recall": 0.22663257957285188, "rouge1_recall_stderr": 0.002733984829707475, "rouge2_fmeasure": 0.027936413268100608, "rouge2_fmeasure_stderr": 0.0007972095177959765, "rouge2_precision": 0.02346568721104801, "rouge2_precision_stderr": 0.0006971468696509421, "rouge2_recall": 0.04305065808208426, "rouge2_recall_stderr": 0.0013646495534821036, "rougeL_fmeasure": 0.12417210909685761, "rougeL_fmeasure_stderr": 0.0013302228377918145, "rougeL_precision": 0.1050094945336366, "rougeL_precision_stderr": 0.0012983078223279439, "rougeL_recall": 0.18568833868889176, "rougeL_recall_stderr": 0.0022086628996599916, "rougeLsum_fmeasure": 0.1422075831554883, "rougeLsum_fmeasure_stderr": 0.0016619749917407194, "rougeLsum_precision": 0.1211307288912133, "rougeLsum_precision_stderr": 0.001638963005635593, "rougeLsum_recall": 0.20936613117867833, "rougeLsum_recall_stderr": 0.0025285661065844287}}, "1": {"tldr_en": {"bleu": 2.4993327349018104, "bleu_stderr": 0.060039405630241266, "rouge1_fmeasure": 0.20579895579192997, "rouge1_fmeasure_stderr": 0.0019171748643174895, "rouge1_precision": 0.17493391960845747, "rouge1_precision_stderr": 0.0019881056363054072, "rouge1_recall": 0.30039251220979346, "rouge1_recall_stderr": 0.0027564678289120448, "rouge2_fmeasure": 0.04823668695482641, "rouge2_fmeasure_stderr": 0.0009745669933822557, "rouge2_precision": 0.040554616651465696, "rouge2_precision_stderr": 0.0008659890131539827, "rouge2_recall": 0.07316485920387228, "rouge2_recall_stderr": 0.0016147073802019601, "rougeL_fmeasure": 0.1484222303241806, "rougeL_fmeasure_stderr": 0.0013020741099865607, "rougeL_precision": 0.124842470774516, "rougeL_precision_stderr": 0.001319051588032341, "rougeL_recall": 0.22232295572810765, "rougeL_recall_stderr": 0.00218343118232531, "rougeLsum_fmeasure": 0.19302273540773426, "rougeLsum_fmeasure_stderr": 0.001789695068656324, "rougeLsum_precision": 0.16389878356035073, "rougeLsum_precision_stderr": 0.0018573417662959208, "rougeLsum_recall": 0.2828415570261487, "rougeLsum_recall_stderr": 0.002627261412365232}}, "2": {"tldr_en": {"bleu": 2.848425645647928, "bleu_stderr": 0.07632604642356548, "rouge1_fmeasure": 0.215446597689823, "rouge1_fmeasure_stderr": 0.0018467682989689277, "rouge1_precision": 0.18456973112779013, "rouge1_precision_stderr": 0.002015516204243605, "rouge1_recall": 0.31320510678716973, "rouge1_recall_stderr": 0.0026816066901912826, "rouge2_fmeasure": 0.05230636200823752, "rouge2_fmeasure_stderr": 0.0009952603118013488, "rouge2_precision": 0.04451908592886625, "rouge2_precision_stderr": 0.0009130557961238952, "rouge2_recall": 0.07879022976243907, "rouge2_recall_stderr": 0.0016883257356260532, "rougeL_fmeasure": 0.15530146813359313, "rougeL_fmeasure_stderr": 0.0012696789175546876, "rougeL_precision": 0.1316268882646582, "rougeL_precision_stderr": 0.0013690654713722978, "rougeL_recall": 0.23148383110872217, "rougeL_recall_stderr": 0.002153117823688896, "rougeLsum_fmeasure": 0.20267202658830938, "rougeLsum_fmeasure_stderr": 0.001723884821520709, "rougeLsum_precision": 0.17349312338034656, "rougeLsum_precision_stderr": 0.0018858372860279045, "rougeLsum_recall": 0.29539552159407584, "rougeLsum_recall_stderr": 0.0025507540114149945}}, "3": {"tldr_en": {"bleu": 2.803251560776854, "bleu_stderr": 0.0956254167064949, "rouge1_fmeasure": 0.18186666197279194, "rouge1_fmeasure_stderr": 0.002214876076414925, "rouge1_precision": 0.1616397163764498, "rouge1_precision_stderr": 0.0023460161842419813, "rouge1_recall": 0.26019267483379616, "rouge1_recall_stderr": 0.0032056026696719647, "rouge2_fmeasure": 0.04453744596750722, "rouge2_fmeasure_stderr": 0.0009892511091368977, "rouge2_precision": 0.03925295558880392, "rouge2_precision_stderr": 0.0009449386730106019, "rouge2_recall": 0.06561949094566538, "rouge2_recall_stderr": 0.0016314095494124245, "rougeL_fmeasure": 0.13202316706879197, "rougeL_fmeasure_stderr": 0.001565731448359357, "rougeL_precision": 0.11667604287371745, "rougeL_precision_stderr": 0.0016762280786544305, "rougeL_recall": 0.19390457934260266, "rougeL_recall_stderr": 0.0025516384846018345, "rougeLsum_fmeasure": 0.17153352468735855, "rougeLsum_fmeasure_stderr": 0.0020795362207751736, "rougeLsum_precision": 0.15230978309868673, "rougeLsum_precision_stderr": 0.0022054724157184874, "rougeLsum_recall": 0.2461258416944667, "rougeLsum_recall_stderr": 0.003046019155993613}}, "4": {"tldr_en": {"bleu": 0.6541873598701015, "bleu_stderr": 0.04137927662792639, "rouge1_fmeasure": 0.05848926036885533, "rouge1_fmeasure_stderr": 0.001947796388751384, "rouge1_precision": 0.0540655546367526, "rouge1_precision_stderr": 0.0019863598257229935, "rouge1_recall": 0.08630893835073304, "rouge1_recall_stderr": 0.0028923078072790034, "rouge2_fmeasure": 0.014698290853528981, "rouge2_fmeasure_stderr": 0.0006960360254178698, "rouge2_precision": 0.013419788420821602, "rouge2_precision_stderr": 0.0007196640004372746, "rouge2_recall": 0.022948179606902694, "rouge2_recall_stderr": 0.0011746702031675198, "rougeL_fmeasure": 0.044046354099571715, "rougeL_fmeasure_stderr": 0.0014521599460521, "rougeL_precision": 0.04061005184395829, "rougeL_precision_stderr": 0.0015089448751204634, "rougeL_recall": 0.06684826672013897, "rougeL_recall_stderr": 0.0023100255832951676, "rougeLsum_fmeasure": 0.05480556417744295, "rougeLsum_fmeasure_stderr": 0.0018205484087403967, "rougeLsum_precision": 0.05070517916237353, "rougeLsum_precision_stderr": 0.0018676632653238442, "rougeLsum_recall": 0.08116451423168446, "rougeLsum_recall_stderr": 0.0027292176658861946}}, "5": {"tldr_en": {"bleu": 1.8017672277263173e-06, "bleu_stderr": 3.4167644481328265e-06, "rouge1_fmeasure": 0.009922885274947888, "rouge1_fmeasure_stderr": 0.00091535752249209, "rouge1_precision": 0.009622620991293292, "rouge1_precision_stderr": 0.0009755776848685625, "rouge1_recall": 0.014660623303221735, "rouge1_recall_stderr": 0.0013738443681724601, "rouge2_fmeasure": 0.0027535231928660694, "rouge2_fmeasure_stderr": 0.00034248340049010525, "rouge2_precision": 0.0025945823584633773, "rouge2_precision_stderr": 0.0003550261333440917, "rouge2_recall": 0.004296371055249484, "rouge2_recall_stderr": 0.000576258075124869, "rougeL_fmeasure": 0.007698903693431021, "rougeL_fmeasure_stderr": 0.0007102473355679709, "rougeL_precision": 0.007418445736015545, "rougeL_precision_stderr": 0.0007597278932642448, "rougeL_recall": 0.01150875523797143, "rougeL_recall_stderr": 0.001083700258541403, "rougeLsum_fmeasure": 0.009228479004212309, "rougeLsum_fmeasure_stderr": 0.0008517809180671035, "rougeLsum_precision": 0.008921009893079637, "rougeLsum_precision_stderr": 0.0009010991448249183, "rougeLsum_recall": 0.01368434519987409, "rougeLsum_recall_stderr": 0.0012818488127390474}}}, "e2e_nlg_cleaned": {"0": {"generate_text_restaurant": {"bleu": 3.2944515852286527, "bleu_stderr": 0.0687957809640445, "rouge1_fmeasure": 0.1814799362167216, "rouge1_fmeasure_stderr": 0.0017831836075280368, "rouge1_precision": 0.13683365368832767, "rouge1_precision_stderr": 0.0014688301287434024, "rouge1_recall": 0.28316158012799547, "rouge1_recall_stderr": 0.0025200608344027693, "rouge2_fmeasure": 0.06187846081562434, "rouge2_fmeasure_stderr": 0.001129424676101297, "rouge2_precision": 0.046755060522420185, "rouge2_precision_stderr": 0.0008806060921358351, "rouge2_recall": 0.09586697768686785, "rouge2_recall_stderr": 0.001719510820833045, "rougeL_fmeasure": 0.16841364171833556, "rougeL_fmeasure_stderr": 0.0015464664247715663, "rougeL_precision": 0.12660643084306702, "rougeL_precision_stderr": 0.00126456533149021, "rougeL_recall": 0.264267984967182, "rougeL_recall_stderr": 0.0022332757179524803, "rougeLsum_fmeasure": 0.15579956125425456, "rougeLsum_fmeasure_stderr": 0.0016372102304097094, "rougeLsum_precision": 0.11737623006499737, "rougeLsum_precision_stderr": 0.0013285621448530893, "rougeLsum_recall": 0.24349593138163397, "rougeLsum_recall_stderr": 0.002354566720998469}}, "1": {"generate_text_restaurant": {"bleu": 8.52641209830111, "bleu_stderr": 0.12582983777195597, "rouge1_fmeasure": 0.3977363846975939, "rouge1_fmeasure_stderr": 0.0022382388166838187, "rouge1_precision": 0.44140716426798104, "rouge1_precision_stderr": 0.0032213924886028253, "rouge1_recall": 0.4052286843296632, "rouge1_recall_stderr": 0.002639166874418895, "rouge2_fmeasure": 0.16696906460089045, "rouge2_fmeasure_stderr": 0.0017222149044682246, "rouge2_precision": 0.18864819780738046, "rouge2_precision_stderr": 0.0022621645695871918, "rouge2_recall": 0.16963873808583682, "rouge2_recall_stderr": 0.001847799566651559, "rougeL_fmeasure": 0.2829785990744798, "rougeL_fmeasure_stderr": 0.001784528829213968, "rougeL_precision": 0.31455069215794823, "rougeL_precision_stderr": 0.0025903719800358703, "rougeL_recall": 0.2903012525772825, "rougeL_recall_stderr": 0.002143374874342348, "rougeLsum_fmeasure": 0.3201857670611568, "rougeLsum_fmeasure_stderr": 0.002098087765270582, "rougeLsum_precision": 0.3567420815242637, "rougeLsum_precision_stderr": 0.0029468018540509057, "rougeLsum_recall": 0.3256533312057627, "rougeLsum_recall_stderr": 0.0023856069656370727}}, "2": {"generate_text_restaurant": {"bleu": 9.630291369867987, "bleu_stderr": 0.13549753046024302, "rouge1_fmeasure": 0.4181223330310302, "rouge1_fmeasure_stderr": 0.0020232576936325647, "rouge1_precision": 0.44886308747052966, "rouge1_precision_stderr": 0.0030653689427961226, "rouge1_recall": 0.4345078703253225, "rouge1_recall_stderr": 0.0025475650430768814, "rouge2_fmeasure": 0.18635767606167977, "rouge2_fmeasure_stderr": 0.0016723047591652514, "rouge2_precision": 0.20393782443251954, "rouge2_precision_stderr": 0.0022988281035972273, "rouge2_recall": 0.19337736914798762, "rouge2_recall_stderr": 0.00185489954602544, "rougeL_fmeasure": 0.2928097571700884, "rougeL_fmeasure_stderr": 0.0017552966978288125, "rougeL_precision": 0.31607957889707133, "rougeL_precision_stderr": 0.002589473433632966, "rougeL_recall": 0.3043881139321235, "rougeL_recall_stderr": 0.002132304038142002, "rougeLsum_fmeasure": 0.3438100939181177, "rougeLsum_fmeasure_stderr": 0.0019679894394683483, "rougeLsum_precision": 0.3695227255731898, "rougeLsum_precision_stderr": 0.00282070031070788, "rougeLsum_recall": 0.3571271332319229, "rougeLsum_recall_stderr": 0.0023658526732539117}}, "3": {"generate_text_restaurant": {"bleu": 10.771336904004668, "bleu_stderr": 0.15312208049452972, "rouge1_fmeasure": 0.4246139438060347, "rouge1_fmeasure_stderr": 0.002068822985960878, "rouge1_precision": 0.47121262761824606, "rouge1_precision_stderr": 0.0031706802673694546, "rouge1_recall": 0.4285131204444559, "rouge1_recall_stderr": 0.00259084813925993, "rouge2_fmeasure": 0.19583480506260798, "rouge2_fmeasure_stderr": 0.0017745784799472742, "rouge2_precision": 0.22192545824696955, "rouge2_precision_stderr": 0.0024446292469949274, "rouge2_recall": 0.19735042748477633, "rouge2_recall_stderr": 0.001962335262395526, "rougeL_fmeasure": 0.3025604202708821, "rougeL_fmeasure_stderr": 0.0018763118742909542, "rougeL_precision": 0.33776452672838364, "rougeL_precision_stderr": 0.002772013880864643, "rougeL_recall": 0.3053908517936716, "rougeL_recall_stderr": 0.0022386749143566537, "rougeLsum_fmeasure": 0.35175775657317715, "rougeLsum_fmeasure_stderr": 0.0020815737481426283, "rougeLsum_precision": 0.3904903633666419, "rougeLsum_precision_stderr": 0.0029686040326820764, "rougeLsum_recall": 0.3552152361692601, "rougeLsum_recall_stderr": 0.002487386620131327}}, "4": {"generate_text_restaurant": {"bleu": 11.267530539514095, "bleu_stderr": 0.1677573231958913, "rouge1_fmeasure": 0.43249984090343835, "rouge1_fmeasure_stderr": 0.002029303339376666, "rouge1_precision": 0.4875664382154273, "rouge1_precision_stderr": 0.003185218088206128, "rouge1_recall": 0.4282782601002331, "rouge1_recall_stderr": 0.0024811809614885827, "rouge2_fmeasure": 0.20132801941812545, "rouge2_fmeasure_stderr": 0.0017679869293689926, "rouge2_precision": 0.23104550813725375, "rouge2_precision_stderr": 0.0024366019088569594, "rouge2_recall": 0.19888718264029498, "rouge2_recall_stderr": 0.001882516080327131, "rougeL_fmeasure": 0.3066167803857757, "rougeL_fmeasure_stderr": 0.001864747310583765, "rougeL_precision": 0.3469917638960595, "rougeL_precision_stderr": 0.0027307278162448678, "rougeL_recall": 0.30357116962664776, "rougeL_recall_stderr": 0.002153172746913521, "rougeLsum_fmeasure": 0.356433479440808, "rougeLsum_fmeasure_stderr": 0.002068322803762821, "rougeLsum_precision": 0.4016050584122585, "rougeLsum_precision_stderr": 0.0029687484050154784, "rougeLsum_recall": 0.35340408132516204, "rougeLsum_recall_stderr": 0.0024203053725328372}}, "5": {"generate_text_restaurant": {"bleu": 10.805990819642968, "bleu_stderr": 0.11545747726371132, "rouge1_fmeasure": 0.42703858045940735, "rouge1_fmeasure_stderr": 0.002035276652428456, "rouge1_precision": 0.46998019703375354, "rouge1_precision_stderr": 0.0031239647333913445, "rouge1_recall": 0.43070572612561325, "rouge1_recall_stderr": 0.002457470355676941, "rouge2_fmeasure": 0.19734778489236487, "rouge2_fmeasure_stderr": 0.0017398333866025894, "rouge2_precision": 0.22095953832665552, "rouge2_precision_stderr": 0.002353597555734135, "rouge2_recall": 0.1987243871558035, "rouge2_recall_stderr": 0.0018784818554072877, "rougeL_fmeasure": 0.3017510704812495, "rougeL_fmeasure_stderr": 0.0018231271871051772, "rougeL_precision": 0.3325206520940773, "rougeL_precision_stderr": 0.002612965421345996, "rougeL_recall": 0.3056110355009581, "rougeL_recall_stderr": 0.002176897829405239, "rougeLsum_fmeasure": 0.3526562252374031, "rougeLsum_fmeasure_stderr": 0.002039422626192226, "rougeLsum_precision": 0.3883766916064333, "rougeLsum_precision_stderr": 0.002916081958006691, "rougeLsum_recall": 0.35559042723108397, "rougeLsum_recall_stderr": 0.0023422683169970725}}}, "gem_xsum": {"0": {"article_DOC_summary": {"bleu": 2.1814410356065763, "bleu_stderr": 0.11929627005647012, "rouge1_fmeasure": 0.2188247155119966, "rouge1_fmeasure_stderr": 0.0026101698852964428, "rouge1_precision": 0.1682140354361548, "rouge1_precision_stderr": 0.0024311651181596846, "rouge1_recall": 0.35168988214341523, "rouge1_recall_stderr": 0.004257802996267162, "rouge2_fmeasure": 0.049755066362456114, "rouge2_fmeasure_stderr": 0.001711057906744696, "rouge2_precision": 0.03791114624887027, "rouge2_precision_stderr": 0.001430715346143808, "rouge2_recall": 0.08181326285418697, "rouge2_recall_stderr": 0.0027684668080112493, "rougeL_fmeasure": 0.16347253111222268, "rougeL_fmeasure_stderr": 0.0020596404700326306, "rougeL_precision": 0.12558538899658162, "rougeL_precision_stderr": 0.0019306618262220862, "rougeL_recall": 0.26406296625514597, "rougeL_recall_stderr": 0.0034141022743443975, "rougeLsum_fmeasure": 0.1707786995081715, "rougeLsum_fmeasure_stderr": 0.002220764586073378, "rougeLsum_precision": 0.13072162961307798, "rougeLsum_precision_stderr": 0.0019975037472617324, "rougeLsum_recall": 0.27675311185951984, "rougeLsum_recall_stderr": 0.003756707707901523}}, "1": {"article_DOC_summary": {"bleu": 1.4164772106615187, "bleu_stderr": 0.08503842048783962, "rouge1_fmeasure": 0.17485668915463046, "rouge1_fmeasure_stderr": 0.0024040861492345958, "rouge1_precision": 0.12394690078102485, "rouge1_precision_stderr": 0.0017820854664639617, "rouge1_recall": 0.30883381009085337, "rouge1_recall_stderr": 0.004143617002757454, "rouge2_fmeasure": 0.034970894707131765, "rouge2_fmeasure_stderr": 0.0013750874506006509, "rouge2_precision": 0.02454039849295794, "rouge2_precision_stderr": 0.0009642339010215241, "rouge2_recall": 0.06338989802824146, "rouge2_recall_stderr": 0.0025845302772511, "rougeL_fmeasure": 0.13792484720753254, "rougeL_fmeasure_stderr": 0.00184311444020864, "rougeL_precision": 0.09759605191150027, "rougeL_precision_stderr": 0.0013546647766234851, "rougeL_recall": 0.24498653012258598, "rougeL_recall_stderr": 0.0032922471031046553, "rougeLsum_fmeasure": 0.14106410762921118, "rougeLsum_fmeasure_stderr": 0.00197754854435336, "rougeLsum_precision": 0.09975522247129645, "rougeLsum_precision_stderr": 0.001443168667820945, "rougeLsum_recall": 0.25068739231214776, "rougeLsum_recall_stderr": 0.003536217595269335}}, "2": {"article_DOC_summary": {"bleu": 1.3211406116055093, "bleu_stderr": 0.05632158339691826, "rouge1_fmeasure": 0.17119896569207846, "rouge1_fmeasure_stderr": 0.0023973191304758746, "rouge1_precision": 0.1212713815463862, "rouge1_precision_stderr": 0.001783930979666327, "rouge1_recall": 0.3027696164744973, "rouge1_recall_stderr": 0.004069720967342189, "rouge2_fmeasure": 0.032088581665832575, "rouge2_fmeasure_stderr": 0.0013254566404233465, "rouge2_precision": 0.022526851037537605, "rouge2_precision_stderr": 0.0009300320053962364, "rouge2_recall": 0.05803699224106711, "rouge2_recall_stderr": 0.002478507440389671, "rougeL_fmeasure": 0.1331419291803311, "rougeL_fmeasure_stderr": 0.0018112812768873992, "rougeL_precision": 0.09410711927777662, "rougeL_precision_stderr": 0.0013305323171338883, "rougeL_recall": 0.2369780862526828, "rougeL_recall_stderr": 0.0032212483252820195, "rougeLsum_fmeasure": 0.1378737759652496, "rougeLsum_fmeasure_stderr": 0.0019533435435502575, "rougeLsum_precision": 0.0973756908203134, "rougeLsum_precision_stderr": 0.0014271599181187183, "rougeLsum_recall": 0.24589465344432024, "rougeLsum_recall_stderr": 0.0035007571446406256}}, "3": {"article_DOC_summary": {"bleu": 1.4406275619553672, "bleu_stderr": 0.058943511303575426, "rouge1_fmeasure": 0.16908880821212016, "rouge1_fmeasure_stderr": 0.0025898440173812076, "rouge1_precision": 0.12267341712650358, "rouge1_precision_stderr": 0.00207297750674979, "rouge1_recall": 0.29346318087456813, "rouge1_recall_stderr": 0.004412522962315509, "rouge2_fmeasure": 0.03314896853957152, "rouge2_fmeasure_stderr": 0.0013908257283640876, "rouge2_precision": 0.023615304490600033, "rouge2_precision_stderr": 0.0010046076586988078, "rouge2_recall": 0.05931770918646783, "rouge2_recall_stderr": 0.002583579920531965, "rougeL_fmeasure": 0.13158510148593067, "rougeL_fmeasure_stderr": 0.0020014770100106496, "rougeL_precision": 0.09519232603078606, "rougeL_precision_stderr": 0.0015734855162649944, "rougeL_recall": 0.22996956742200556, "rougeL_recall_stderr": 0.00356629562100884, "rougeLsum_fmeasure": 0.13667047371150057, "rougeLsum_fmeasure_stderr": 0.0021600836418570976, "rougeLsum_precision": 0.0987948573594369, "rougeLsum_precision_stderr": 0.001680092786160822, "rougeLsum_recall": 0.23916103459926824, "rougeLsum_recall_stderr": 0.003841293731139315}}, "4": {"article_DOC_summary": {"bleu": 0.6685820712764758, "bleu_stderr": 0.11003965221099908, "rouge1_fmeasure": 0.04566365412307027, "rouge1_fmeasure_stderr": 0.002608741489638274, "rouge1_precision": 0.036834822457244766, "rouge1_precision_stderr": 0.0022079340145582244, "rouge1_recall": 0.07337453869001616, "rouge1_recall_stderr": 0.004314314932527252, "rouge2_fmeasure": 0.00874385192747724, "rouge2_fmeasure_stderr": 0.0008092464001035177, "rouge2_precision": 0.006497191357163194, "rouge2_precision_stderr": 0.0006016918414205361, "rouge2_recall": 0.014978313036291765, "rouge2_recall_stderr": 0.0014510780480090683, "rougeL_fmeasure": 0.03550416488438028, "rougeL_fmeasure_stderr": 0.0020020706708868776, "rougeL_precision": 0.028775879177447013, "rougeL_precision_stderr": 0.0017095958814072434, "rougeL_recall": 0.05725787803054188, "rougeL_recall_stderr": 0.003351554553300089, "rougeLsum_fmeasure": 0.03770504825258967, "rougeLsum_fmeasure_stderr": 0.0021688966924711204, "rougeLsum_precision": 0.03052315595597832, "rougeLsum_precision_stderr": 0.0018382248537160094, "rougeLsum_recall": 0.06056408978110664, "rougeLsum_recall_stderr": 0.0035955665511950294}}, "5": {"article_DOC_summary": {"bleu": 3.330855196908569e-39, "bleu_stderr": 2.2953575552071226e-33, "rouge1_fmeasure": 0.002202987774184108, "rouge1_fmeasure_stderr": 0.0006658652488222124, "rouge1_precision": 0.0025092290685345187, "rouge1_precision_stderr": 0.0008065208895136817, "rouge1_recall": 0.00204279104163942, "rouge1_recall_stderr": 0.0005925317015988438, "rouge2_fmeasure": 0.00024851863402463746, "rouge2_fmeasure_stderr": 0.00020210817841172796, "rouge2_precision": 0.00031845928766017557, "rouge2_precision_stderr": 0.0002726745419818294, "rouge2_recall": 0.00021032426692804053, "rouge2_recall_stderr": 0.00016342749062440463, "rougeL_fmeasure": 0.0016217715192546416, "rougeL_fmeasure_stderr": 0.00048067108652986303, "rougeL_precision": 0.0018256414840619524, "rougeL_precision_stderr": 0.0005744051717215062, "rougeL_recall": 0.0015255275808323426, "rougeL_recall_stderr": 0.0004364013489751857, "rougeLsum_fmeasure": 0.0017788861730293213, "rougeLsum_fmeasure_stderr": 0.0005248009571798277, "rougeLsum_precision": 0.0020224773879338985, "rougeLsum_precision_stderr": 0.0006369133276637897, "rougeLsum_recall": 0.001658634237434707, "rougeLsum_recall_stderr": 0.0004694737360395629}}}}