{"GEM/web_nlg_en": {"0": {"PALM_prompt": {"bleu": 0.45419048482755325, "bleu_stderr": 0.03343264900668279, "rouge1_fmeasure": 0.12050264484641364, "rouge1_fmeasure_stderr": 0.0019557997342759008, "rouge1_precision": 0.07656848458551854, "rouge1_precision_stderr": 0.0014013614212390725, "rouge1_recall": 0.4036790488281202, "rouge1_recall_stderr": 0.005315114093965629, "rouge2_fmeasure": 0.052832415905400075, "rouge2_fmeasure_stderr": 0.0011839640636500091, "rouge2_precision": 0.033428842308488534, "rouge2_precision_stderr": 0.0008128053819647495, "rouge2_recall": 0.18340526600302984, "rouge2_recall_stderr": 0.003727031912672351, "rougeL_fmeasure": 0.11109523222583549, "rougeL_fmeasure_stderr": 0.0017383601500938328, "rougeL_precision": 0.07054587229335195, "rougeL_precision_stderr": 0.0012459171875782095, "rougeL_recall": 0.37462626179690983, "rougeL_recall_stderr": 0.004966030287557139, "rougeLsum_fmeasure": 0.11161406434102886, "rougeLsum_fmeasure_stderr": 0.0018124941447083965, "rougeLsum_precision": 0.07110053256257555, "rougeLsum_precision_stderr": 0.0013096550789070658, "rougeLsum_recall": 0.3724362458459577, "rougeLsum_recall_stderr": 0.004863022252389103}}, "1": {"PALM_prompt": {"bleu": 0.5850021236636699, "bleu_stderr": 0.03819693214469707, "rouge1_fmeasure": 0.1677409926355529, "rouge1_fmeasure_stderr": 0.004030921408273657, "rouge1_precision": 0.15109588314127873, "rouge1_precision_stderr": 0.004953399230808383, "rouge1_recall": 0.325670897152676, "rouge1_recall_stderr": 0.005147150507406254, "rouge2_fmeasure": 0.0882203961704786, "rouge2_fmeasure_stderr": 0.0027304069330761974, "rouge2_precision": 0.08184320047143445, "rouge2_precision_stderr": 0.003449022357977633, "rouge2_recall": 0.17132523279025044, "rouge2_recall_stderr": 0.00367610399739497, "rougeL_fmeasure": 0.15245069014322057, "rougeL_fmeasure_stderr": 0.00345251550628098, "rougeL_precision": 0.13599215274261797, "rougeL_precision_stderr": 0.004360821088518568, "rougeL_recall": 0.3051575499297103, "rougeL_recall_stderr": 0.004723568587467038, "rougeLsum_fmeasure": 0.15494868008248852, "rougeLsum_fmeasure_stderr": 0.003528355370205954, "rougeLsum_precision": 0.13850001433454043, "rougeLsum_precision_stderr": 0.004436787945937485, "rougeLsum_recall": 0.30775803342597885, "rougeLsum_recall_stderr": 0.004752694198738615}}, "2": {"PALM_prompt": {"bleu": 0.7246766267092646, "bleu_stderr": 0.05216754042228656, "rouge1_fmeasure": 0.19302680914857126, "rouge1_fmeasure_stderr": 0.004550241366319154, "rouge1_precision": 0.16997361970056543, "rouge1_precision_stderr": 0.005336466087297649, "rouge1_recall": 0.3624866589291664, "rouge1_recall_stderr": 0.005051573422247833, "rouge2_fmeasure": 0.10607455474495636, "rouge2_fmeasure_stderr": 0.0031850991496843, "rouge2_precision": 0.09695911898895748, "rouge2_precision_stderr": 0.003772749560662997, "rouge2_recall": 0.19796654029903527, "rouge2_recall_stderr": 0.003829948250927247, "rougeL_fmeasure": 0.17343940636186816, "rougeL_fmeasure_stderr": 0.003866556548338404, "rougeL_precision": 0.1505856722307468, "rougeL_precision_stderr": 0.004601030271832378, "rougeL_recall": 0.33798352518669805, "rougeL_recall_stderr": 0.004605226083895095, "rougeLsum_fmeasure": 0.17821185760691358, "rougeLsum_fmeasure_stderr": 0.004029760056556632, "rougeLsum_precision": 0.15526534529621946, "rougeLsum_precision_stderr": 0.004777197445287186, "rougeLsum_recall": 0.34354280660789954, "rougeLsum_recall_stderr": 0.004693627364580387}}, "3": {"PALM_prompt": {"bleu": 0.912401774785461, "bleu_stderr": 0.05499172600355808, "rouge1_fmeasure": 0.2027515169133416, "rouge1_fmeasure_stderr": 0.004616866259808885, "rouge1_precision": 0.177739891947758, "rouge1_precision_stderr": 0.005377477441053506, "rouge1_recall": 0.37571301827708603, "rouge1_recall_stderr": 0.005155063555837091, "rouge2_fmeasure": 0.11011224841518844, "rouge2_fmeasure_stderr": 0.0032287748904178603, "rouge2_precision": 0.09925086869826542, "rouge2_precision_stderr": 0.0037360879884190974, "rouge2_recall": 0.2039607362114278, "rouge2_recall_stderr": 0.004009008079403255, "rougeL_fmeasure": 0.17817494628022673, "rougeL_fmeasure_stderr": 0.003810921024330032, "rougeL_precision": 0.15305639487114978, "rougeL_precision_stderr": 0.004468138904157244, "rougeL_recall": 0.34454827318886916, "rougeL_recall_stderr": 0.004597031286799378, "rougeLsum_fmeasure": 0.185206448541148, "rougeLsum_fmeasure_stderr": 0.004057582364193407, "rougeLsum_precision": 0.16073321051848882, "rougeLsum_precision_stderr": 0.004766423801226516, "rougeLsum_recall": 0.35191122444688017, "rougeLsum_recall_stderr": 0.004722893850454437}}, "4": {"PALM_prompt": {"bleu": 0.9362020995122441, "bleu_stderr": 0.07456263807984138, "rouge1_fmeasure": 0.20398642955440918, "rouge1_fmeasure_stderr": 0.0044990621443271265, "rouge1_precision": 0.1801767792651148, "rouge1_precision_stderr": 0.0053176999629491305, "rouge1_recall": 0.38030055324748463, "rouge1_recall_stderr": 0.005130695248034955, "rouge2_fmeasure": 0.11134812760048587, "rouge2_fmeasure_stderr": 0.0031257086692601643, "rouge2_precision": 0.10092720165635745, "rouge2_precision_stderr": 0.0036595986543100584, "rouge2_recall": 0.2093414664405995, "rouge2_recall_stderr": 0.004066301941452167, "rougeL_fmeasure": 0.18020750722912687, "rougeL_fmeasure_stderr": 0.0037228657207143273, "rougeL_precision": 0.1562295618700323, "rougeL_precision_stderr": 0.004447831421456536, "rougeL_recall": 0.3500026913388304, "rougeL_recall_stderr": 0.00457250105781178, "rougeLsum_fmeasure": 0.18803470835441047, "rougeLsum_fmeasure_stderr": 0.003990573990048456, "rougeLsum_precision": 0.1646531954640878, "rougeLsum_precision_stderr": 0.0047752145526076765, "rougeLsum_recall": 0.35859704442011836, "rougeLsum_recall_stderr": 0.004708359064341005}}, "5": {"PALM_prompt": {"bleu": 1.1473284737488645, "bleu_stderr": 0.07257359326088067, "rouge1_fmeasure": 0.22344029518114394, "rouge1_fmeasure_stderr": 0.0047579906981359355, "rouge1_precision": 0.19695121461258075, "rouge1_precision_stderr": 0.005543936314076539, "rouge1_recall": 0.39862816336821605, "rouge1_recall_stderr": 0.005230455011065989, "rouge2_fmeasure": 0.12320959484950564, "rouge2_fmeasure_stderr": 0.0033292695883422856, "rouge2_precision": 0.1118421615652518, "rouge2_precision_stderr": 0.003869244868009604, "rouge2_recall": 0.22068136349930514, "rouge2_recall_stderr": 0.004119383941992751, "rougeL_fmeasure": 0.19693845048375522, "rougeL_fmeasure_stderr": 0.003977166542530307, "rougeL_precision": 0.1712293574036339, "rougeL_precision_stderr": 0.004702901005328839, "rougeL_recall": 0.36465485161639194, "rougeL_recall_stderr": 0.004657456646320378, "rougeLsum_fmeasure": 0.20542437703481312, "rougeLsum_fmeasure_stderr": 0.004254659038175917, "rougeLsum_precision": 0.1800833361396532, "rougeLsum_precision_stderr": 0.00501549579335833, "rougeLsum_recall": 0.3739480609864003, "rougeLsum_recall_stderr": 0.004813185015660923}}}, "GEM/wiki_lingua_en": {"0": {"tldr_en": {"bleu": 2.5247944854894806, "bleu_stderr": 0.0879841385659621, "rouge1_fmeasure": 0.14904907950315077, "rouge1_fmeasure_stderr": 0.0024558774712346303, "rouge1_precision": 0.1384834766411849, "rouge1_precision_stderr": 0.002631651930646105, "rouge1_recall": 0.1986797302552911, "rouge1_recall_stderr": 0.003301745364935552, "rouge2_fmeasure": 0.035598696037042944, "rouge2_fmeasure_stderr": 0.0010333687243820114, "rouge2_precision": 0.03225938464648384, "rouge2_precision_stderr": 0.000980163943008181, "rouge2_recall": 0.04862171566457941, "rouge2_recall_stderr": 0.0015116459850371242, "rougeL_fmeasure": 0.11791797807562439, "rougeL_fmeasure_stderr": 0.0018560003669397872, "rougeL_precision": 0.10896306382058518, "rougeL_precision_stderr": 0.002036973587521335, "rougeL_recall": 0.1604599066510129, "rougeL_recall_stderr": 0.0026801418820689106, "rougeLsum_fmeasure": 0.13814732526217105, "rougeLsum_fmeasure_stderr": 0.0022950179887594627, "rougeLsum_precision": 0.1285709971312458, "rougeLsum_precision_stderr": 0.0024834562723841675, "rougeLsum_recall": 0.1844269890660411, "rougeLsum_recall_stderr": 0.003094769735687356}}, "1": {"tldr_en": {"bleu": 3.0785238389209355, "bleu_stderr": 0.12100023309172617, "rouge1_fmeasure": 0.19932748144830872, "rouge1_fmeasure_stderr": 0.0023746278349365216, "rouge1_precision": 0.3077283488063351, "rouge1_precision_stderr": 0.004482468614194303, "rouge1_recall": 0.20156170597255982, "rouge1_recall_stderr": 0.0028613140412138494, "rouge2_fmeasure": 0.05627709313767569, "rouge2_fmeasure_stderr": 0.001427328834770283, "rouge2_precision": 0.09669759370794292, "rouge2_precision_stderr": 0.002865381089616566, "rouge2_recall": 0.0555415827995515, "rouge2_recall_stderr": 0.00153691704948828, "rougeL_fmeasure": 0.15700774611111312, "rougeL_fmeasure_stderr": 0.0019119812430907841, "rougeL_precision": 0.24842926652738595, "rougeL_precision_stderr": 0.0038947924223351827, "rougeL_recall": 0.15799128474542956, "rougeL_recall_stderr": 0.002265547666522197, "rougeLsum_fmeasure": 0.1874016150707306, "rougeLsum_fmeasure_stderr": 0.0022396190663859935, "rougeLsum_precision": 0.29106256830073524, "rougeLsum_precision_stderr": 0.004316037155064917, "rougeLsum_recall": 0.18921966019379916, "rougeLsum_recall_stderr": 0.0026890228631320456}}, "2": {"tldr_en": {"bleu": 3.652111781813624, "bleu_stderr": 0.10486391893167614, "rouge1_fmeasure": 0.2283435942520453, "rouge1_fmeasure_stderr": 0.002353258676899788, "rouge1_precision": 0.36924759348379244, "rouge1_precision_stderr": 0.004371000269537104, "rouge1_recall": 0.2161281279844684, "rouge1_recall_stderr": 0.0027903795763512965, "rouge2_fmeasure": 0.0689053644873375, "rouge2_fmeasure_stderr": 0.0015082619422947736, "rouge2_precision": 0.12155473826758335, "rouge2_precision_stderr": 0.0030290361967967947, "rouge2_recall": 0.06398344341696371, "rouge2_recall_stderr": 0.0015954786097649597, "rougeL_fmeasure": 0.1806325741208752, "rougeL_fmeasure_stderr": 0.0018958600514033847, "rougeL_precision": 0.29809803146126795, "rougeL_precision_stderr": 0.0037990348444261793, "rougeL_recall": 0.17039689340892664, "rougeL_recall_stderr": 0.0022336612525983126, "rougeLsum_fmeasure": 0.21643866687270513, "rougeLsum_fmeasure_stderr": 0.0022530258028476487, "rougeLsum_precision": 0.35169516629927816, "rougeLsum_precision_stderr": 0.004252566315780221, "rougeLsum_recall": 0.2045309406583435, "rougeLsum_recall_stderr": 0.0026458064196168626}}, "3": {"tldr_en": {"bleu": 2.30710280652967, "bleu_stderr": 0.09094590687124952, "rouge1_fmeasure": 0.1945336408406022, "rouge1_fmeasure_stderr": 0.0026446921596933503, "rouge1_precision": 0.3236204752072193, "rouge1_precision_stderr": 0.0047276363208619545, "rouge1_recall": 0.1778973939940185, "rouge1_recall_stderr": 0.002915566666838674, "rouge2_fmeasure": 0.059175735072984945, "rouge2_fmeasure_stderr": 0.0015008631332196428, "rouge2_precision": 0.10514218669712877, "rouge2_precision_stderr": 0.0029331277208536808, "rouge2_recall": 0.05366081871257144, "rouge2_recall_stderr": 0.0015514417031996504, "rougeL_fmeasure": 0.1547742780157689, "rougeL_fmeasure_stderr": 0.0021406675865622577, "rougeL_precision": 0.2617516967205688, "rougeL_precision_stderr": 0.004024319520519343, "rougeL_recall": 0.14136929228154757, "rougeL_recall_stderr": 0.0023577454595674853, "rougeLsum_fmeasure": 0.18473010709149373, "rougeLsum_fmeasure_stderr": 0.0025203297464613237, "rougeLsum_precision": 0.30869344193505416, "rougeLsum_precision_stderr": 0.004557374401231459, "rougeLsum_recall": 0.16856250527976735, "rougeLsum_recall_stderr": 0.0027602819187965205}}, "4": {"tldr_en": {"bleu": 0.01997228189371226, "bleu_stderr": 0.004164437604071004, "rouge1_fmeasure": 0.0642661368715624, "rouge1_fmeasure_stderr": 0.002311467107094036, "rouge1_precision": 0.10579363907416886, "rouge1_precision_stderr": 0.0038996170266521225, "rouge1_recall": 0.05989991930806105, "rouge1_recall_stderr": 0.002383270863537302, "rouge2_fmeasure": 0.020118442009674838, "rouge2_fmeasure_stderr": 0.001072025516558785, "rouge2_precision": 0.03603840886780009, "rouge2_precision_stderr": 0.0020500166307483576, "rouge2_recall": 0.01870103420296575, "rouge2_recall_stderr": 0.0011326153028213988, "rougeL_fmeasure": 0.052479963022099216, "rougeL_fmeasure_stderr": 0.0019019460257588422, "rougeL_precision": 0.08768306117325718, "rougeL_precision_stderr": 0.003312003426848069, "rougeL_recall": 0.04882499641240493, "rougeL_recall_stderr": 0.0019528616148385455, "rougeLsum_fmeasure": 0.06058158326550758, "rougeLsum_fmeasure_stderr": 0.0021794146863436045, "rougeLsum_precision": 0.10049299845393068, "rougeLsum_precision_stderr": 0.0037366898545692227, "rougeLsum_recall": 0.056172794670012766, "rougeLsum_recall_stderr": 0.0022208852083168873}}, "5": {"tldr_en": {"bleu": 6.720014938526705e-25, "bleu_stderr": 1.368232575017575e-23, "rouge1_fmeasure": 0.008551690929725, "rouge1_fmeasure_stderr": 0.0009563473253764333, "rouge1_precision": 0.015189081718840411, "rouge1_precision_stderr": 0.0016914095953933566, "rouge1_recall": 0.007820035481039486, "rouge1_recall_stderr": 0.0009666086539579351, "rouge2_fmeasure": 0.0030989992660247776, "rouge2_fmeasure_stderr": 0.00045069838543670873, "rouge2_precision": 0.005792228464995174, "rouge2_precision_stderr": 0.0008621781228084065, "rouge2_recall": 0.002930153771964047, "rouge2_recall_stderr": 0.0005187699239656753, "rougeL_fmeasure": 0.007168225022246425, "rougeL_fmeasure_stderr": 0.0008110437096733947, "rougeL_precision": 0.01284373251270546, "rougeL_precision_stderr": 0.0014549043740755003, "rougeL_recall": 0.0065817077301885156, "rougeL_recall_stderr": 0.0008324133884409117, "rougeLsum_fmeasure": 0.008101674490294078, "rougeLsum_fmeasure_stderr": 0.0009108848536289975, "rougeLsum_precision": 0.014339494923437973, "rougeLsum_precision_stderr": 0.0016066549399758809, "rougeLsum_recall": 0.0074702858797809375, "rougeLsum_recall_stderr": 0.0009377181101147522}}}, "e2e_nlg_cleaned": {"0": {"generate_text_restaurant": {"bleu": 0.2174856161906872, "bleu_stderr": 0.015923894878958702, "rouge1_fmeasure": 0.09849126682765423, "rouge1_fmeasure_stderr": 0.0014923228309475303, "rouge1_precision": 0.10975769964880429, "rouge1_precision_stderr": 0.0015870675246378444, "rouge1_recall": 0.09928819244999808, "rouge1_recall_stderr": 0.0017021351064544997, "rouge2_fmeasure": 0.008098169031211164, "rouge2_fmeasure_stderr": 0.0005382144957334649, "rouge2_precision": 0.007623464868246138, "rouge2_precision_stderr": 0.0005009913285230473, "rouge2_recall": 0.009301745941549075, "rouge2_recall_stderr": 0.0006509937552160252, "rougeL_fmeasure": 0.0736904154736711, "rougeL_fmeasure_stderr": 0.0010858349093197835, "rougeL_precision": 0.08356464635738844, "rougeL_precision_stderr": 0.0012285431730394058, "rougeL_recall": 0.07404637900035545, "rougeL_recall_stderr": 0.0012403578700447176, "rougeLsum_fmeasure": 0.09038375273205482, "rougeLsum_fmeasure_stderr": 0.0014028476096075255, "rougeLsum_precision": 0.1006889250238476, "rougeLsum_precision_stderr": 0.0014871743224185528, "rougeLsum_recall": 0.09132141334499083, "rougeLsum_recall_stderr": 0.0016087849316541365}}, "1": {"generate_text_restaurant": {"bleu": 13.603186674422444, "bleu_stderr": 0.16720918384264621, "rouge1_fmeasure": 0.49485627314549524, "rouge1_fmeasure_stderr": 0.0024544062699189814, "rouge1_precision": 0.5979241216990805, "rouge1_precision_stderr": 0.003249159766185611, "rouge1_recall": 0.4639078870638987, "rouge1_recall_stderr": 0.003148275112212192, "rouge2_fmeasure": 0.24123039025136075, "rouge2_fmeasure_stderr": 0.002180045932319959, "rouge2_precision": 0.2956478031764748, "rouge2_precision_stderr": 0.00278907091106282, "rouge2_recall": 0.22605648093866812, "rouge2_recall_stderr": 0.0023685889739160394, "rougeL_fmeasure": 0.35989371492803346, "rougeL_fmeasure_stderr": 0.0022080667678571124, "rougeL_precision": 0.43850922077428195, "rougeL_precision_stderr": 0.0030731074026139234, "rougeL_recall": 0.33651308226541454, "rougeL_recall_stderr": 0.0025991623791134935, "rougeLsum_fmeasure": 0.4091180712168849, "rougeLsum_fmeasure_stderr": 0.0024997075802474684, "rougeLsum_precision": 0.494681105830301, "rougeLsum_precision_stderr": 0.0032392131317364663, "rougeLsum_recall": 0.3838741776920783, "rougeLsum_recall_stderr": 0.002994592667557759}}, "2": {"generate_text_restaurant": {"bleu": 16.576086891653166, "bleu_stderr": 0.1984305930797547, "rouge1_fmeasure": 0.5406367365743524, "rouge1_fmeasure_stderr": 0.0022538009424502856, "rouge1_precision": 0.6107310269990832, "rouge1_precision_stderr": 0.003015577689861615, "rouge1_recall": 0.5221390359885365, "rouge1_recall_stderr": 0.0029512899488828535, "rouge2_fmeasure": 0.2734427432548749, "rouge2_fmeasure_stderr": 0.0022099035880405217, "rouge2_precision": 0.31025817915664383, "rouge2_precision_stderr": 0.0026272739666680675, "rouge2_recall": 0.2649860705420364, "rouge2_recall_stderr": 0.0024508343474972704, "rougeL_fmeasure": 0.39198077065688064, "rougeL_fmeasure_stderr": 0.002182514239974999, "rougeL_precision": 0.4439430176815307, "rougeL_precision_stderr": 0.0028358702473415052, "rougeL_recall": 0.3785721561496246, "rougeL_recall_stderr": 0.002595192473566268, "rougeLsum_fmeasure": 0.45178684887136245, "rougeLsum_fmeasure_stderr": 0.0024132990759076346, "rougeLsum_precision": 0.5096418612798311, "rougeLsum_precision_stderr": 0.0030192956186345364, "rougeLsum_recall": 0.43688135096476943, "rougeLsum_recall_stderr": 0.002910558794257935}}, "3": {"generate_text_restaurant": {"bleu": 18.0845433681664, "bleu_stderr": 0.1777813122477081, "rouge1_fmeasure": 0.5569933886386429, "rouge1_fmeasure_stderr": 0.002199268289167996, "rouge1_precision": 0.6137536153047778, "rouge1_precision_stderr": 0.002904157765234221, "rouge1_recall": 0.5442156551577437, "rouge1_recall_stderr": 0.002885723399368904, "rouge2_fmeasure": 0.28763411022506213, "rouge2_fmeasure_stderr": 0.0022477495833815196, "rouge2_precision": 0.31771337110021336, "rouge2_precision_stderr": 0.002612043327366063, "rouge2_recall": 0.2820443575315225, "rouge2_recall_stderr": 0.002486793380575716, "rougeL_fmeasure": 0.4035567493026598, "rougeL_fmeasure_stderr": 0.0021951888628519655, "rougeL_precision": 0.44521250737924556, "rougeL_precision_stderr": 0.002748868729929973, "rougeL_recall": 0.3945188323134259, "rougeL_recall_stderr": 0.0025907833781845116, "rougeLsum_fmeasure": 0.46891207559259884, "rougeLsum_fmeasure_stderr": 0.0024057218135253083, "rougeLsum_precision": 0.5161460637873506, "rougeLsum_precision_stderr": 0.0029604827844778962, "rougeLsum_recall": 0.45840539581253936, "rougeLsum_recall_stderr": 0.002872125220850784}}, "4": {"generate_text_restaurant": {"bleu": 18.51503235974728, "bleu_stderr": 0.137264758627985, "rouge1_fmeasure": 0.5613974208808915, "rouge1_fmeasure_stderr": 0.002229445477122744, "rouge1_precision": 0.6120787062374268, "rouge1_precision_stderr": 0.0029210193021996945, "rouge1_recall": 0.551131861972078, "rouge1_recall_stderr": 0.002878591933639494, "rouge2_fmeasure": 0.2923497201090039, "rouge2_fmeasure_stderr": 0.002320583768019888, "rouge2_precision": 0.31927245421777867, "rouge2_precision_stderr": 0.0026652064038851435, "rouge2_recall": 0.2880520521380086, "rouge2_recall_stderr": 0.002555894661960643, "rougeL_fmeasure": 0.4041359208213478, "rougeL_fmeasure_stderr": 0.002238652049241865, "rougeL_precision": 0.4410030855945479, "rougeL_precision_stderr": 0.0027444185755603635, "rougeL_recall": 0.3968570780449371, "rougeL_recall_stderr": 0.002615164584024417, "rougeLsum_fmeasure": 0.47289433229350847, "rougeLsum_fmeasure_stderr": 0.002447850484296981, "rougeLsum_precision": 0.5150329022926635, "rougeLsum_precision_stderr": 0.002968021858154739, "rougeLsum_recall": 0.46450424841976723, "rougeLsum_recall_stderr": 0.002904435277766539}}, "5": {"generate_text_restaurant": {"bleu": 18.31902300887679, "bleu_stderr": 0.21660929188675368, "rouge1_fmeasure": 0.560533216370765, "rouge1_fmeasure_stderr": 0.002197938637338113, "rouge1_precision": 0.6075691463019105, "rouge1_precision_stderr": 0.002877547740801876, "rouge1_recall": 0.5519116595173106, "rouge1_recall_stderr": 0.002825353291269693, "rouge2_fmeasure": 0.2901019845755836, "rouge2_fmeasure_stderr": 0.0022752845282833444, "rouge2_precision": 0.3145544773242325, "rouge2_precision_stderr": 0.002564671139370085, "rouge2_recall": 0.2871130624175668, "rouge2_recall_stderr": 0.002534307523052322, "rougeL_fmeasure": 0.4050393820619599, "rougeL_fmeasure_stderr": 0.0022368299932115226, "rougeL_precision": 0.43853503664166193, "rougeL_precision_stderr": 0.0026803764592891635, "rougeL_recall": 0.39978015472393064, "rougeL_recall_stderr": 0.0026469457358851683, "rougeLsum_fmeasure": 0.4728370986753031, "rougeLsum_fmeasure_stderr": 0.0024112597225851803, "rougeLsum_precision": 0.5118762996951014, "rougeLsum_precision_stderr": 0.0029189311646059903, "rougeLsum_recall": 0.46611352612043305, "rougeLsum_recall_stderr": 0.0028714705658076977}}}, "gem_xsum": {"0": {"article_DOC_summary": {"bleu": 1.824437063172752, "bleu_stderr": 0.1295959938779033, "rouge1_fmeasure": 0.19064385039008325, "rouge1_fmeasure_stderr": 0.0026847919999498783, "rouge1_precision": 0.13889553377394204, "rouge1_precision_stderr": 0.0020470938512401043, "rouge1_recall": 0.3224174898964051, "rouge1_recall_stderr": 0.0047323832955649394, "rouge2_fmeasure": 0.04310473913800793, "rouge2_fmeasure_stderr": 0.0015909694285954996, "rouge2_precision": 0.030770546785531084, "rouge2_precision_stderr": 0.0011485507935108212, "rouge2_recall": 0.07627788908402264, "rouge2_recall_stderr": 0.0029161006551518855, "rougeL_fmeasure": 0.14803927722404647, "rougeL_fmeasure_stderr": 0.002024044592590105, "rougeL_precision": 0.1076726505455253, "rougeL_precision_stderr": 0.0015263290004438454, "rougeL_recall": 0.2516553160702365, "rougeL_recall_stderr": 0.0037251276937883744, "rougeLsum_fmeasure": 0.1506543367359999, "rougeLsum_fmeasure_stderr": 0.0022302335824208926, "rougeLsum_precision": 0.10954802882008673, "rougeLsum_precision_stderr": 0.001670554704114846, "rougeLsum_recall": 0.2563589341875558, "rougeLsum_recall_stderr": 0.004093935928498495}}, "1": {"article_DOC_summary": {"bleu": 1.7609819893980598, "bleu_stderr": 0.09673219339225483, "rouge1_fmeasure": 0.18745377329593618, "rouge1_fmeasure_stderr": 0.0028616444790333095, "rouge1_precision": 0.1556677591501949, "rouge1_precision_stderr": 0.0028313144238476637, "rouge1_recall": 0.28181566724348217, "rouge1_recall_stderr": 0.0046620008628106705, "rouge2_fmeasure": 0.03804941171577492, "rouge2_fmeasure_stderr": 0.0016796104857723759, "rouge2_precision": 0.03124209990455104, "rouge2_precision_stderr": 0.0015863039800586146, "rouge2_recall": 0.05959322682370301, "rouge2_recall_stderr": 0.0026033301572952875, "rougeL_fmeasure": 0.14217542198253097, "rougeL_fmeasure_stderr": 0.0021914393891234374, "rougeL_precision": 0.11865350137721012, "rougeL_precision_stderr": 0.002261907056323959, "rougeL_recall": 0.21376373660006684, "rougeL_recall_stderr": 0.00356630705358284, "rougeLsum_fmeasure": 0.15022526225239208, "rougeLsum_fmeasure_stderr": 0.0023683857139214465, "rougeLsum_precision": 0.12449107117970809, "rougeLsum_precision_stderr": 0.002329800484842638, "rougeLsum_recall": 0.227483012391418, "rougeLsum_recall_stderr": 0.003955993366379117}}, "2": {"article_DOC_summary": {"bleu": 2.0844403527225617, "bleu_stderr": 0.18103428706460614, "rouge1_fmeasure": 0.21367633738963315, "rouge1_fmeasure_stderr": 0.0033554954700050752, "rouge1_precision": 0.19935476907025304, "rouge1_precision_stderr": 0.0038598266568137785, "rouge1_recall": 0.2706926378266182, "rouge1_recall_stderr": 0.004156883055461473, "rouge2_fmeasure": 0.04593830462341063, "rouge2_fmeasure_stderr": 0.0020168943686124465, "rouge2_precision": 0.044027605832549326, "rouge2_precision_stderr": 0.002125094239368793, "rouge2_recall": 0.05675910399033515, "rouge2_recall_stderr": 0.0024265127143739836, "rougeL_fmeasure": 0.16184982863572556, "rougeL_fmeasure_stderr": 0.0026008492724763654, "rougeL_precision": 0.15107166602542463, "rougeL_precision_stderr": 0.0030007609375925313, "rougeL_recall": 0.20556159886471823, "rougeL_recall_stderr": 0.0032143700207118648, "rougeLsum_fmeasure": 0.1658443102086597, "rougeLsum_fmeasure_stderr": 0.002655700581774396, "rougeLsum_precision": 0.15408614394681422, "rougeLsum_precision_stderr": 0.003005649518177271, "rougeLsum_recall": 0.2120361542004191, "rougeLsum_recall_stderr": 0.0034289113513717964}}, "3": {"article_DOC_summary": {"bleu": 2.6157705705080483, "bleu_stderr": 0.1931328754738087, "rouge1_fmeasure": 0.21733976037468944, "rouge1_fmeasure_stderr": 0.0036238273509993928, "rouge1_precision": 0.21476053304129508, "rouge1_precision_stderr": 0.004210457868862111, "rouge1_recall": 0.2548785666224053, "rouge1_recall_stderr": 0.004327640907101733, "rouge2_fmeasure": 0.05057991242538114, "rouge2_fmeasure_stderr": 0.0021902733567216452, "rouge2_precision": 0.05108878519401023, "rouge2_precision_stderr": 0.00238600623033403, "rouge2_recall": 0.058040451447882946, "rouge2_recall_stderr": 0.002461257596090234, "rougeL_fmeasure": 0.1669642989094155, "rougeL_fmeasure_stderr": 0.0029609461708291133, "rougeL_precision": 0.16532395838276415, "rougeL_precision_stderr": 0.0034399821384294557, "rougeL_recall": 0.19583029758598305, "rougeL_recall_stderr": 0.0034969216930147515, "rougeLsum_fmeasure": 0.16989940378849605, "rougeLsum_fmeasure_stderr": 0.002996828651281411, "rougeLsum_precision": 0.16782197382314246, "rougeLsum_precision_stderr": 0.0034561917258272806, "rougeLsum_recall": 0.20028204694266308, "rougeLsum_recall_stderr": 0.0036507354923465485}}, "4": {"article_DOC_summary": {"bleu": 0.24290172552446196, "bleu_stderr": 0.056581491175426914, "rouge1_fmeasure": 0.05851076846542915, "rouge1_fmeasure_stderr": 0.0033565789806109434, "rouge1_precision": 0.06774270444285756, "rouge1_precision_stderr": 0.004232420643142785, "rouge1_recall": 0.06344049540701503, "rouge1_recall_stderr": 0.0037875385187947238, "rouge2_fmeasure": 0.012864663909485747, "rouge2_fmeasure_stderr": 0.0012115981535214609, "rouge2_precision": 0.015101385764716672, "rouge2_precision_stderr": 0.0015922733167297797, "rouge2_recall": 0.014184749823453857, "rouge2_recall_stderr": 0.0014191161123945839, "rougeL_fmeasure": 0.044310535444670965, "rougeL_fmeasure_stderr": 0.002566821173611681, "rougeL_precision": 0.05231134411266022, "rougeL_precision_stderr": 0.0034387489181517653, "rougeL_recall": 0.04797296934231772, "rougeL_recall_stderr": 0.0028959645784639894, "rougeLsum_fmeasure": 0.04489857322141054, "rougeLsum_fmeasure_stderr": 0.0025974168309322184, "rougeLsum_precision": 0.05280348194292997, "rougeLsum_precision_stderr": 0.003452891291164583, "rougeLsum_recall": 0.048834354415796526, "rougeLsum_recall_stderr": 0.00297075040562579}}, "5": {"article_DOC_summary": {"bleu": 6.130780440334243e-47, "bleu_stderr": 9.503426174895799e-44, "rouge1_fmeasure": 0.002244737752786088, "rouge1_fmeasure_stderr": 0.0006095570789287521, "rouge1_precision": 0.003117611880602497, "rouge1_precision_stderr": 0.0009842144959043254, "rouge1_recall": 0.0019488182977195217, "rouge1_recall_stderr": 0.0005249211324998764, "rouge2_fmeasure": 0.00030536930193877015, "rouge2_fmeasure_stderr": 0.0001813875271676511, "rouge2_precision": 0.0008079370976590439, "rouge2_precision_stderr": 0.0006502336039399843, "rouge2_recall": 0.0002226782651310953, "rouge2_recall_stderr": 0.00011959198904763001, "rougeL_fmeasure": 0.0016390641129216145, "rougeL_fmeasure_stderr": 0.00045172367777572114, "rougeL_precision": 0.00237811186000067, "rougeL_precision_stderr": 0.000838173352270679, "rougeL_recall": 0.001419537348620057, "rougeL_recall_stderr": 0.00038663520349704417, "rougeLsum_fmeasure": 0.0016975367824715818, "rougeLsum_fmeasure_stderr": 0.0004551946310914248, "rougeLsum_precision": 0.0024324846668707023, "rougeLsum_precision_stderr": 0.0008373236753933433, "rougeLsum_recall": 0.001479673753096084, "rougeLsum_recall_stderr": 0.00039335345523923025}}}}