| {"GEM/web_nlg_en": {"0": {"PALM_prompt": {"bleu": 0.3841955455859648, "bleu_stderr": 0.03834484804445635, "rouge1_fmeasure": 0.12051532399725066, "rouge1_fmeasure_stderr": 0.002201660726069953, "rouge1_precision": 0.08014992228438296, "rouge1_precision_stderr": 0.0017168290656594826, "rouge1_recall": 0.3261497758575972, "rouge1_recall_stderr": 0.004673915338473915, "rouge2_fmeasure": 0.05636376429781428, "rouge2_fmeasure_stderr": 0.001380678937179018, "rouge2_precision": 0.037046602853886695, "rouge2_precision_stderr": 0.0010494705661268828, "rouge2_recall": 0.1571021450899692, "rouge2_recall_stderr": 0.0033056759391242784, "rougeL_fmeasure": 0.11589156234984295, "rougeL_fmeasure_stderr": 0.002019174904591411, "rougeL_precision": 0.07675495084341123, "rougeL_precision_stderr": 0.0015593801603559256, "rougeL_recall": 0.3167777456526712, "rougeL_recall_stderr": 0.0045215943809518, "rougeLsum_fmeasure": 0.11479926239465861, "rougeLsum_fmeasure_stderr": 0.0020583922218685075, "rougeLsum_precision": 0.07631587685180155, "rougeLsum_precision_stderr": 0.0016101491986833256, "rougeLsum_recall": 0.31168339901047554, "rougeLsum_recall_stderr": 0.004419194664667104}}, "1": {"PALM_prompt": {"bleu": 0.42759204004197143, "bleu_stderr": 0.023184098740316197, "rouge1_fmeasure": 0.11872984928779891, "rouge1_fmeasure_stderr": 0.0019464789074927673, "rouge1_precision": 0.0764954377721011, "rouge1_precision_stderr": 0.0014403924566495617, "rouge1_recall": 0.3699228352820796, "rouge1_recall_stderr": 0.004905399646426089, "rouge2_fmeasure": 0.05494866999157076, "rouge2_fmeasure_stderr": 0.0012146887370210208, "rouge2_precision": 0.03527667126582558, "rouge2_precision_stderr": 0.0008695445202518543, "rouge2_recall": 0.17789638991052, "rouge2_recall_stderr": 0.0035278151906693064, "rougeL_fmeasure": 0.1129384334238869, "rougeL_fmeasure_stderr": 0.0018191890467148604, "rougeL_precision": 0.07272581922783473, "rougeL_precision_stderr": 0.0013349614051097628, "rougeL_recall": 0.34880705084622615, "rougeL_recall_stderr": 0.004490070517958085, "rougeLsum_fmeasure": 0.11356822062600092, "rougeLsum_fmeasure_stderr": 0.0018599619391754974, "rougeLsum_precision": 0.07321976744637436, "rougeLsum_precision_stderr": 0.0013772614644632743, "rougeLsum_recall": 0.3519663428654811, "rougeLsum_recall_stderr": 0.004562356824400081}}, "2": {"PALM_prompt": {"bleu": 0.4856534095490541, "bleu_stderr": 0.02443151487945902, "rouge1_fmeasure": 0.12115437420866133, "rouge1_fmeasure_stderr": 0.0017815531385909358, "rouge1_precision": 0.07721718276217579, "rouge1_precision_stderr": 0.0013119823062237108, "rouge1_recall": 0.39692380063364113, "rouge1_recall_stderr": 0.004838247650813131, "rouge2_fmeasure": 0.05613328052522034, "rouge2_fmeasure_stderr": 0.0011336256501373859, "rouge2_precision": 0.035589537397562925, "rouge2_precision_stderr": 0.0007970484569143277, "rouge2_recall": 0.19548525884545162, "rouge2_recall_stderr": 0.003705977303917903, "rougeL_fmeasure": 0.11469727176936799, "rougeL_fmeasure_stderr": 0.0016974540069808568, "rougeL_precision": 0.07320664477451425, "rougeL_precision_stderr": 0.00124331025548219, "rougeL_recall": 0.36961196243693584, "rougeL_recall_stderr": 0.004355138581855341, "rougeLsum_fmeasure": 0.11594842776998675, "rougeLsum_fmeasure_stderr": 0.0017162153027005642, "rougeLsum_precision": 0.07398228224748984, "rougeLsum_precision_stderr": 0.0012654062337437574, "rougeLsum_recall": 0.3771975381479834, "rougeLsum_recall_stderr": 0.004532808747113653}}, "3": {"PALM_prompt": {"bleu": 0.5126461546548764, "bleu_stderr": 0.023481707085499674, "rouge1_fmeasure": 0.12296680669192865, "rouge1_fmeasure_stderr": 0.001771390257741117, "rouge1_precision": 0.07818118915673905, "rouge1_precision_stderr": 0.001307597764643951, "rouge1_recall": 0.40552198761426156, "rouge1_recall_stderr": 0.004891057939341875, "rouge2_fmeasure": 0.05780751377987367, "rouge2_fmeasure_stderr": 0.0011295131135826688, "rouge2_precision": 0.03650686263182726, "rouge2_precision_stderr": 0.0007906653215721775, "rouge2_recall": 0.2032738453519446, "rouge2_recall_stderr": 0.003736335783154159, "rougeL_fmeasure": 0.11565624884195182, "rougeL_fmeasure_stderr": 0.0016653289676033045, "rougeL_precision": 0.07364405212863913, "rougeL_precision_stderr": 0.0012259573312863687, "rougeL_recall": 0.3755672149905026, "rougeL_recall_stderr": 0.004294385844287458, "rougeLsum_fmeasure": 0.11715743772138398, "rougeLsum_fmeasure_stderr": 0.0016964195102981497, "rougeLsum_precision": 0.07457144104571109, "rougeLsum_precision_stderr": 0.001254395221332194, "rougeLsum_recall": 0.383723870677269, "rougeLsum_recall_stderr": 0.004507602950858476}}, "4": {"PALM_prompt": {"bleu": 0.5768263836110397, "bleu_stderr": 0.033531304625404476, "rouge1_fmeasure": 0.12484492984248315, "rouge1_fmeasure_stderr": 0.0017733677490337002, "rouge1_precision": 0.07912332276140266, "rouge1_precision_stderr": 0.001308722937203902, "rouge1_recall": 0.4163756942667881, "rouge1_recall_stderr": 0.0049142362912846065, "rouge2_fmeasure": 0.0588262051974305, "rouge2_fmeasure_stderr": 0.0011381389114864023, "rouge2_precision": 0.03703974751248662, "rouge2_precision_stderr": 0.000798849362280762, "rouge2_recall": 0.20955667473009687, "rouge2_recall_stderr": 0.003786190119236611, "rougeL_fmeasure": 0.11679920573658832, "rougeL_fmeasure_stderr": 0.0016587330040215838, "rougeL_precision": 0.07414629204331873, "rougeL_precision_stderr": 0.0012180987225705276, "rougeL_recall": 0.3839203236439917, "rougeL_recall_stderr": 0.0043260019772130365, "rougeLsum_fmeasure": 0.11925978856110157, "rougeLsum_fmeasure_stderr": 0.0016998268553025208, "rougeLsum_precision": 0.07566523029296329, "rougeLsum_precision_stderr": 0.0012550312341550222, "rougeLsum_recall": 0.3951330344622166, "rougeLsum_recall_stderr": 0.004544810736094279}}, "5": {"PALM_prompt": {"bleu": 0.6000731585078155, "bleu_stderr": 0.02958850942035399, "rouge1_fmeasure": 0.12519311022366508, "rouge1_fmeasure_stderr": 0.0017687940658429597, "rouge1_precision": 0.07936877002627572, "rouge1_precision_stderr": 0.0013478728108461428, "rouge1_recall": 0.42485523830131044, "rouge1_recall_stderr": 0.004961789167035332, "rouge2_fmeasure": 0.05914854622489272, "rouge2_fmeasure_stderr": 0.001134713521503068, "rouge2_precision": 0.03729344715424889, "rouge2_precision_stderr": 0.0008381379859023699, "rouge2_recall": 0.21558831324782035, "rouge2_recall_stderr": 0.00382217803604959, "rougeL_fmeasure": 0.11624930186573486, "rougeL_fmeasure_stderr": 0.0016499833416766872, "rougeL_precision": 0.07374550717756582, "rougeL_precision_stderr": 0.001229003964772475, "rougeL_recall": 0.3896512196098555, "rougeL_recall_stderr": 0.00438967659644571, "rougeLsum_fmeasure": 0.11877149951275545, "rougeLsum_fmeasure_stderr": 0.0016790431278768587, "rougeLsum_precision": 0.07529523941861134, "rougeLsum_precision_stderr": 0.0012574009028455731, "rougeLsum_recall": 0.4005167169588075, "rougeLsum_recall_stderr": 0.004552442433337306}}}, "GEM/wiki_lingua_en": {"0": {"tldr_en": {"bleu": 1.383140911898804, "bleu_stderr": 0.06745292495577788, "rouge1_fmeasure": 0.1673082764887814, "rouge1_fmeasure_stderr": 0.001865906276285246, "rouge1_precision": 0.14252443763236, "rouge1_precision_stderr": 0.0018590735935872559, "rouge1_recall": 0.2433207401530673, "rouge1_recall_stderr": 0.0027216367874257704, "rouge2_fmeasure": 0.03242729118049159, "rouge2_fmeasure_stderr": 0.000822088219708237, "rouge2_precision": 0.027172539820821053, "rouge2_precision_stderr": 0.0007118578268436691, "rouge2_recall": 0.0491985860574383, "rouge2_recall_stderr": 0.0013607577897608023, "rougeL_fmeasure": 0.13361933070882745, "rougeL_fmeasure_stderr": 0.0013437669695864618, "rougeL_precision": 0.11248849161329692, "rougeL_precision_stderr": 0.0013075864685883915, "rougeL_recall": 0.19869623082735052, "rougeL_recall_stderr": 0.0021898356243837697, "rougeLsum_fmeasure": 0.15365517848220148, "rougeLsum_fmeasure_stderr": 0.001684866108354418, "rougeLsum_precision": 0.13063172936064044, "rougeLsum_precision_stderr": 0.0016740540617278972, "rougeLsum_recall": 0.22441355121485976, "rougeLsum_recall_stderr": 0.002501090278748021}}, "1": {"tldr_en": {"bleu": 2.7831136014630777, "bleu_stderr": 0.05823735961787848, "rouge1_fmeasure": 0.2160954413299178, "rouge1_fmeasure_stderr": 0.0019654215171466417, "rouge1_precision": 0.18512017707721384, "rouge1_precision_stderr": 0.0021094437947065357, "rouge1_recall": 0.3158252638107596, "rouge1_recall_stderr": 0.0028417150098632967, "rouge2_fmeasure": 0.051296962531802784, "rouge2_fmeasure_stderr": 0.0010375664756837545, "rouge2_precision": 0.04376467946822878, "rouge2_precision_stderr": 0.0009756253583246246, "rouge2_recall": 0.07778902526231471, "rouge2_recall_stderr": 0.0017144407061461767, "rougeL_fmeasure": 0.15429878943917802, "rougeL_fmeasure_stderr": 0.0013508750340413321, "rougeL_precision": 0.13071111972941768, "rougeL_precision_stderr": 0.0014200606755908336, "rougeL_recall": 0.23169837875792845, "rougeL_recall_stderr": 0.002280199313309875, "rougeLsum_fmeasure": 0.20352880625344108, "rougeLsum_fmeasure_stderr": 0.0018405295838661016, "rougeLsum_precision": 0.17416190886149602, "rougeLsum_precision_stderr": 0.0019763988764514343, "rougeLsum_recall": 0.29830367981123657, "rougeLsum_recall_stderr": 0.0026966353421627575}}, "2": {"tldr_en": {"bleu": 3.2957837666594587, "bleu_stderr": 0.08034379540818389, "rouge1_fmeasure": 0.22869891032831227, "rouge1_fmeasure_stderr": 0.001930285464026905, "rouge1_precision": 0.20719943998381424, "rouge1_precision_stderr": 0.002491870168779193, "rouge1_recall": 0.3275862651091397, "rouge1_recall_stderr": 0.0027741119190619616, "rouge2_fmeasure": 0.05835798348350554, "rouge2_fmeasure_stderr": 0.0011051187337092607, "rouge2_precision": 0.054125628291332856, "rouge2_precision_stderr": 0.0013199800821959524, "rouge2_recall": 0.08630431560199675, "rouge2_recall_stderr": 0.0018086295613497908, "rougeL_fmeasure": 0.16408965991494653, "rougeL_fmeasure_stderr": 0.0013803822196969012, "rougeL_precision": 0.148528573150794, "rougeL_precision_stderr": 0.0018930555426512554, "rougeL_recall": 0.24049407805551332, "rougeL_recall_stderr": 0.002292588701907806, "rougeLsum_fmeasure": 0.21661695161689976, "rougeLsum_fmeasure_stderr": 0.0018306086871906694, "rougeLsum_precision": 0.19626454756871028, "rougeLsum_precision_stderr": 0.0023738870826537344, "rougeLsum_recall": 0.3106148563327418, "rougeLsum_recall_stderr": 0.00264458163926524}}, "3": {"tldr_en": {"bleu": 3.117766006224522, "bleu_stderr": 0.08844168500594013, "rouge1_fmeasure": 0.18494884132953612, "rouge1_fmeasure_stderr": 0.0022949571244732228, "rouge1_precision": 0.1801846981582515, "rouge1_precision_stderr": 0.002966508978680055, "rouge1_recall": 0.25914746469386185, "rouge1_recall_stderr": 0.0033244732230100858, "rouge2_fmeasure": 0.04724388490620084, "rouge2_fmeasure_stderr": 0.0011136170490785228, "rouge2_precision": 0.048034735096925886, "rouge2_precision_stderr": 0.0015464762014200295, "rouge2_recall": 0.06803447603698609, "rouge2_recall_stderr": 0.0017069831079943856, "rougeL_fmeasure": 0.13464181051994895, "rougeL_fmeasure_stderr": 0.0016797153921897026, "rougeL_precision": 0.1324468640336949, "rougeL_precision_stderr": 0.0023342385848593035, "rougeL_recall": 0.19202614173003765, "rougeL_recall_stderr": 0.002624571586313395, "rougeLsum_fmeasure": 0.17539853983167855, "rougeLsum_fmeasure_stderr": 0.002171008535901723, "rougeLsum_precision": 0.17068094752096957, "rougeLsum_precision_stderr": 0.0028086345613548606, "rougeLsum_recall": 0.24641584828527527, "rougeLsum_recall_stderr": 0.0031770926187417964}}, "4": {"tldr_en": {"bleu": 0.5914410987220908, "bleu_stderr": 0.03510174866934131, "rouge1_fmeasure": 0.05827542021821347, "rouge1_fmeasure_stderr": 0.001989638358607021, "rouge1_precision": 0.060746566102344496, "rouge1_precision_stderr": 0.0024802575898741574, "rouge1_recall": 0.0844520531515112, "rouge1_recall_stderr": 0.0029460126839031564, "rouge2_fmeasure": 0.01535069013326034, "rouge2_fmeasure_stderr": 0.0007972694044836853, "rouge2_precision": 0.01708667593672377, "rouge2_precision_stderr": 0.0012309085284382452, "rouge2_recall": 0.023158372631812345, "rouge2_recall_stderr": 0.001255540288620037, "rougeL_fmeasure": 0.043279163481274745, "rougeL_fmeasure_stderr": 0.0014817290632566425, "rougeL_precision": 0.04628144425563542, "rougeL_precision_stderr": 0.0020233599391486622, "rougeL_recall": 0.06365609520147814, "rougeL_recall_stderr": 0.002267970708853241, "rougeLsum_fmeasure": 0.054917664734240174, "rougeLsum_fmeasure_stderr": 0.0018755702048733026, "rougeLsum_precision": 0.0574384376172157, "rougeLsum_precision_stderr": 0.002362476755396724, "rougeLsum_recall": 0.07967217250561419, "rougeLsum_recall_stderr": 0.0027846813063251916}}, "5": {"tldr_en": {"bleu": 4.2206706508824354e-07, "bleu_stderr": 9.033374866710449e-07, "rouge1_fmeasure": 0.008757736475992225, "rouge1_fmeasure_stderr": 0.000830866197712448, "rouge1_precision": 0.009084734687542615, "rouge1_precision_stderr": 0.001035058563997235, "rouge1_recall": 0.013139853227511232, "rouge1_recall_stderr": 0.001287810296386965, "rouge2_fmeasure": 0.002325818245704019, "rouge2_fmeasure_stderr": 0.00031017440648810845, "rouge2_precision": 0.002883518719217727, "rouge2_precision_stderr": 0.0005696461607134438, "rouge2_recall": 0.0035342303209918327, "rouge2_recall_stderr": 0.0005062242713917856, "rougeL_fmeasure": 0.0068130585987481495, "rougeL_fmeasure_stderr": 0.0006449066053870117, "rougeL_precision": 0.007262975272974422, "rougeL_precision_stderr": 0.0008786946312435219, "rougeL_recall": 0.01037090312723551, "rougeL_recall_stderr": 0.0010286097141161677, "rougeLsum_fmeasure": 0.008317350447949961, "rougeLsum_fmeasure_stderr": 0.0007883086779573902, "rougeLsum_precision": 0.008666293877274517, "rougeLsum_precision_stderr": 0.000996353612238138, "rougeLsum_recall": 0.012494692152033124, "rougeLsum_recall_stderr": 0.001221173699832202}}}, "e2e_nlg_cleaned": {"0": {"generate_text_restaurant": {"bleu": 5.285882687642843, "bleu_stderr": 0.06697426008552022, "rouge1_fmeasure": 0.23951822437486534, "rouge1_fmeasure_stderr": 0.0017048049458819286, "rouge1_precision": 0.19340923170637989, "rouge1_precision_stderr": 0.0016098131373697873, "rouge1_recall": 0.36655908361004397, "rouge1_recall_stderr": 0.002604816098151851, "rouge2_fmeasure": 0.10058915023610071, "rouge2_fmeasure_stderr": 0.0012779590967870102, "rouge2_precision": 0.07638118077243172, "rouge2_precision_stderr": 0.0010271765749693493, "rouge2_recall": 0.16004590783643435, "rouge2_recall_stderr": 0.002018059971951962, "rougeL_fmeasure": 0.21218418778210568, "rougeL_fmeasure_stderr": 0.0014038041647419447, "rougeL_precision": 0.16992379812238415, "rougeL_precision_stderr": 0.0012959255203026498, "rougeL_recall": 0.32762918553762216, "rougeL_recall_stderr": 0.0022741947911686495, "rougeLsum_fmeasure": 0.21087391773473857, "rougeLsum_fmeasure_stderr": 0.0016466676007216732, "rougeLsum_precision": 0.16993592420494444, "rougeLsum_precision_stderr": 0.0015045811195205502, "rougeLsum_recall": 0.32347836326516793, "rougeLsum_recall_stderr": 0.002536061380650285}}, "1": {"generate_text_restaurant": {"bleu": 8.759868718384176, "bleu_stderr": 0.08986207189239839, "rouge1_fmeasure": 0.39045142557557627, "rouge1_fmeasure_stderr": 0.0019753647001218705, "rouge1_precision": 0.3825672121452994, "rouge1_precision_stderr": 0.00234517833697759, "rouge1_recall": 0.4382865336266532, "rouge1_recall_stderr": 0.0027794348254113546, "rouge2_fmeasure": 0.15977592553077005, "rouge2_fmeasure_stderr": 0.0016281989808774435, "rouge2_precision": 0.1562403146993971, "rouge2_precision_stderr": 0.0017105000210557784, "rouge2_recall": 0.18141451294370953, "rouge2_recall_stderr": 0.0020502392167278793, "rougeL_fmeasure": 0.2774015144515331, "rougeL_fmeasure_stderr": 0.0016146206236499572, "rougeL_precision": 0.27150380747664543, "rougeL_precision_stderr": 0.0018690865365730313, "rougeL_recall": 0.31307144412730237, "rougeL_recall_stderr": 0.0022863268336661626, "rougeLsum_fmeasure": 0.32595782319940814, "rougeLsum_fmeasure_stderr": 0.0019248153927043945, "rougeLsum_precision": 0.31953264548547916, "rougeLsum_precision_stderr": 0.002206836566776707, "rougeLsum_recall": 0.3659092525728581, "rougeLsum_recall_stderr": 0.0025888812249551894}}, "2": {"generate_text_restaurant": {"bleu": 10.10327848388186, "bleu_stderr": 0.13416893009812642, "rouge1_fmeasure": 0.4150614272126317, "rouge1_fmeasure_stderr": 0.0019038601009108084, "rouge1_precision": 0.40047122427428994, "rouge1_precision_stderr": 0.0023102636338495812, "rouge1_recall": 0.4691288386223476, "rouge1_recall_stderr": 0.0026887985201774624, "rouge2_fmeasure": 0.18872461991388448, "rouge2_fmeasure_stderr": 0.0017027808165788005, "rouge2_precision": 0.18175344294276033, "rouge2_precision_stderr": 0.0017821897624685544, "rouge2_recall": 0.21581298714587557, "rouge2_recall_stderr": 0.0021699718182286156, "rougeL_fmeasure": 0.3077697188688082, "rougeL_fmeasure_stderr": 0.0016516793472863517, "rougeL_precision": 0.2962608515862683, "rougeL_precision_stderr": 0.001897045239202071, "rougeL_recall": 0.34990861003729856, "rougeL_recall_stderr": 0.0023602136361034433, "rougeLsum_fmeasure": 0.3519730669933395, "rougeLsum_fmeasure_stderr": 0.0019358104213338006, "rougeLsum_precision": 0.3398362419135114, "rougeLsum_precision_stderr": 0.0022378563960927657, "rougeLsum_recall": 0.3975797506250789, "rougeLsum_recall_stderr": 0.0025704790531562126}}, "3": {"generate_text_restaurant": {"bleu": 11.232267102526988, "bleu_stderr": 0.14068760640127415, "rouge1_fmeasure": 0.42815668930435585, "rouge1_fmeasure_stderr": 0.001927157531196204, "rouge1_precision": 0.41817325284774387, "rouge1_precision_stderr": 0.0023053737236325977, "rouge1_recall": 0.4752160858627036, "rouge1_recall_stderr": 0.0027142554814264357, "rouge2_fmeasure": 0.2016971233453876, "rouge2_fmeasure_stderr": 0.0017734485816419255, "rouge2_precision": 0.1964731857257769, "rouge2_precision_stderr": 0.0018466850642394885, "rouge2_recall": 0.22633557348204866, "rouge2_recall_stderr": 0.0022240683617011222, "rougeL_fmeasure": 0.3188281781066986, "rougeL_fmeasure_stderr": 0.0017307512933631892, "rougeL_precision": 0.3108487463908802, "rougeL_precision_stderr": 0.0019544617537378835, "rougeL_recall": 0.3553930435732314, "rougeL_recall_stderr": 0.0024025865771174024, "rougeLsum_fmeasure": 0.3640392540141833, "rougeLsum_fmeasure_stderr": 0.00199772383540772, "rougeLsum_precision": 0.355398185837249, "rougeLsum_precision_stderr": 0.002250685549026275, "rougeLsum_recall": 0.4042983855328548, "rougeLsum_recall_stderr": 0.0026636540624325345}}, "4": {"generate_text_restaurant": {"bleu": 11.52714583973097, "bleu_stderr": 0.16566149983325942, "rouge1_fmeasure": 0.43395966766003585, "rouge1_fmeasure_stderr": 0.001919830319829728, "rouge1_precision": 0.4224736137769234, "rouge1_precision_stderr": 0.002344672239310868, "rouge1_recall": 0.4824757808782152, "rouge1_recall_stderr": 0.002671564917406434, "rouge2_fmeasure": 0.20671915111813988, "rouge2_fmeasure_stderr": 0.001774125867426217, "rouge2_precision": 0.20102260284035095, "rouge2_precision_stderr": 0.0018660070700133957, "rouge2_recall": 0.2320395634175057, "rouge2_recall_stderr": 0.0022223744066551293, "rougeL_fmeasure": 0.32341769588154473, "rougeL_fmeasure_stderr": 0.001729818154828205, "rougeL_precision": 0.31443730192952396, "rougeL_precision_stderr": 0.001986378360109619, "rougeL_recall": 0.3608360400202065, "rougeL_recall_stderr": 0.002374485765520169, "rougeLsum_fmeasure": 0.3693259817282329, "rougeLsum_fmeasure_stderr": 0.002017414187660604, "rougeLsum_precision": 0.35940740482707384, "rougeLsum_precision_stderr": 0.002294856169924013, "rougeLsum_recall": 0.4106478368865337, "rougeLsum_recall_stderr": 0.002652156433027331}}, "5": {"generate_text_restaurant": {"bleu": 11.470373655769501, "bleu_stderr": 0.12527529313499408, "rouge1_fmeasure": 0.4356867279269184, "rouge1_fmeasure_stderr": 0.0019525540843502926, "rouge1_precision": 0.421800370876118, "rouge1_precision_stderr": 0.0023646580883461706, "rouge1_recall": 0.4865640272606994, "rouge1_recall_stderr": 0.002675409006075987, "rouge2_fmeasure": 0.20755693489144728, "rouge2_fmeasure_stderr": 0.001772980726536381, "rouge2_precision": 0.20064053316690955, "rouge2_precision_stderr": 0.0018548156820547273, "rouge2_recall": 0.23383994456326945, "rouge2_recall_stderr": 0.0021887036234265046, "rougeL_fmeasure": 0.32464613664724695, "rougeL_fmeasure_stderr": 0.0017180101489382377, "rougeL_precision": 0.31356023285448703, "rougeL_precision_stderr": 0.0019519642683972734, "rougeL_recall": 0.36423548391706, "rougeL_recall_stderr": 0.0023618289325691875, "rougeLsum_fmeasure": 0.3709229849290071, "rougeLsum_fmeasure_stderr": 0.002028707851697601, "rougeLsum_precision": 0.35931617332832466, "rougeLsum_precision_stderr": 0.00232575064650851, "rougeLsum_recall": 0.4139321110238479, "rougeLsum_recall_stderr": 0.002614052034797568}}}, "gem_xsum": {"0": {"article_DOC_summary": {"bleu": 2.286764120955454, "bleu_stderr": 0.10487671432151699, "rouge1_fmeasure": 0.2170704363655291, "rouge1_fmeasure_stderr": 0.0026009964674546487, "rouge1_precision": 0.16086222686885998, "rouge1_precision_stderr": 0.0022252447270736404, "rouge1_recall": 0.363993757386026, "rouge1_recall_stderr": 0.004447906860355032, "rouge2_fmeasure": 0.05426109744027298, "rouge2_fmeasure_stderr": 0.0017575127883179419, "rouge2_precision": 0.03965743348041025, "rouge2_precision_stderr": 0.0014470240504900656, "rouge2_recall": 0.09447416461397456, "rouge2_recall_stderr": 0.003039878935146692, "rougeL_fmeasure": 0.1645988844863308, "rougeL_fmeasure_stderr": 0.0020230326221713562, "rougeL_precision": 0.12165923066163074, "rougeL_precision_stderr": 0.001738521026475504, "rougeL_recall": 0.27815207821679444, "rougeL_recall_stderr": 0.0036330563038200624, "rougeLsum_fmeasure": 0.17049497991799512, "rougeLsum_fmeasure_stderr": 0.002199479559253552, "rougeLsum_precision": 0.12592899489421042, "rougeLsum_precision_stderr": 0.0018469201981654569, "rougeLsum_recall": 0.28818031436396413, "rougeLsum_recall_stderr": 0.00395186316132106}}, "1": {"article_DOC_summary": {"bleu": 1.601855503412538, "bleu_stderr": 0.07258015457329471, "rouge1_fmeasure": 0.18432241198153712, "rouge1_fmeasure_stderr": 0.0025753000481448644, "rouge1_precision": 0.13106642326274354, "rouge1_precision_stderr": 0.0019193860865765633, "rouge1_recall": 0.3234658508585958, "rouge1_recall_stderr": 0.0043661264753635486, "rouge2_fmeasure": 0.04002835284879521, "rouge2_fmeasure_stderr": 0.0014781883740027449, "rouge2_precision": 0.02822515438220016, "rouge2_precision_stderr": 0.0010434086746188042, "rouge2_recall": 0.07162285378667402, "rouge2_recall_stderr": 0.002714817358725964, "rougeL_fmeasure": 0.14101261823875597, "rougeL_fmeasure_stderr": 0.0019068168040762914, "rougeL_precision": 0.10003470838188194, "rougeL_precision_stderr": 0.0014061413510224204, "rougeL_recall": 0.24915600486179032, "rougeL_recall_stderr": 0.003347425480308083, "rougeLsum_fmeasure": 0.14771150001250982, "rougeLsum_fmeasure_stderr": 0.00211511203484802, "rougeLsum_precision": 0.10480543277054401, "rougeLsum_precision_stderr": 0.0015545955460983404, "rougeLsum_recall": 0.2607965323547307, "rougeLsum_recall_stderr": 0.003724571304451384}}, "2": {"article_DOC_summary": {"bleu": 1.8380438639962695, "bleu_stderr": 0.10811928358813763, "rouge1_fmeasure": 0.19535202200220275, "rouge1_fmeasure_stderr": 0.0026346536005903373, "rouge1_precision": 0.13887280196688523, "rouge1_precision_stderr": 0.001956740885200385, "rouge1_recall": 0.34294827785468185, "rouge1_recall_stderr": 0.004514777263625162, "rouge2_fmeasure": 0.04546623699775454, "rouge2_fmeasure_stderr": 0.001612092783689185, "rouge2_precision": 0.0320190408417148, "rouge2_precision_stderr": 0.0011343925357226905, "rouge2_recall": 0.08177449666512925, "rouge2_recall_stderr": 0.003014469934741339, "rougeL_fmeasure": 0.14811536601585223, "rougeL_fmeasure_stderr": 0.00196180609857125, "rougeL_precision": 0.10508517578596618, "rougeL_precision_stderr": 0.0014455778496582211, "rougeL_recall": 0.26185041154157507, "rougeL_recall_stderr": 0.003505120843276718, "rougeLsum_fmeasure": 0.1571036308870091, "rougeLsum_fmeasure_stderr": 0.0021764703685117513, "rougeLsum_precision": 0.11141636053588261, "rougeLsum_precision_stderr": 0.0015953318320649059, "rougeLsum_recall": 0.27772475736482033, "rougeLsum_recall_stderr": 0.003883573652450414}}, "3": {"article_DOC_summary": {"bleu": 1.8731170479468633, "bleu_stderr": 0.12212530111306877, "rouge1_fmeasure": 0.1850973564810976, "rouge1_fmeasure_stderr": 0.0028685807268665573, "rouge1_precision": 0.13393465093211152, "rouge1_precision_stderr": 0.002178546476915688, "rouge1_recall": 0.3208349496275703, "rouge1_recall_stderr": 0.005017270430039093, "rouge2_fmeasure": 0.04301170567438614, "rouge2_fmeasure_stderr": 0.0016643347985338668, "rouge2_precision": 0.030603540250172215, "rouge2_precision_stderr": 0.0012053283031466103, "rouge2_recall": 0.07656078303232518, "rouge2_recall_stderr": 0.003042910587753952, "rougeL_fmeasure": 0.14087163035130615, "rougeL_fmeasure_stderr": 0.002174721918788832, "rougeL_precision": 0.10190253909758554, "rougeL_precision_stderr": 0.001662230819445601, "rougeL_recall": 0.2452262253929823, "rougeL_recall_stderr": 0.0038665453486106385, "rougeLsum_fmeasure": 0.14807083425641282, "rougeLsum_fmeasure_stderr": 0.0023776983157151816, "rougeLsum_precision": 0.10713139947740546, "rougeLsum_precision_stderr": 0.001810818001072249, "rougeLsum_recall": 0.2577398531586797, "rougeLsum_recall_stderr": 0.004224949592217397}}, "4": {"article_DOC_summary": {"bleu": 0.8072921803610522, "bleu_stderr": 0.13481405520653453, "rouge1_fmeasure": 0.04957113221677667, "rouge1_fmeasure_stderr": 0.002776223278435835, "rouge1_precision": 0.04237213490568202, "rouge1_precision_stderr": 0.002644486260111252, "rouge1_recall": 0.07779789094117907, "rouge1_recall_stderr": 0.004474695319161571, "rouge2_fmeasure": 0.010629103476078454, "rouge2_fmeasure_stderr": 0.0009487229867910699, "rouge2_precision": 0.00882760521824164, "rouge2_precision_stderr": 0.0009353280430989058, "rouge2_recall": 0.017870091729374663, "rouge2_recall_stderr": 0.0016736090478303408, "rougeL_fmeasure": 0.03785078570554781, "rougeL_fmeasure_stderr": 0.002102296416669563, "rougeL_precision": 0.032755367117331305, "rougeL_precision_stderr": 0.0020851660139623363, "rougeL_recall": 0.059623992862197994, "rougeL_recall_stderr": 0.0034445885527070548, "rougeLsum_fmeasure": 0.040118179164564276, "rougeLsum_fmeasure_stderr": 0.002244409483615815, "rougeLsum_precision": 0.03457603039331168, "rougeLsum_precision_stderr": 0.00217697156328438, "rougeLsum_recall": 0.06328733938197696, "rougeLsum_recall_stderr": 0.003695669480428956}}, "5": {"article_DOC_summary": {"bleu": 3.474750506260909e-38, "bleu_stderr": 2.4761840064885677e-32, "rouge1_fmeasure": 0.0022401437562342683, "rouge1_fmeasure_stderr": 0.0007153938341072901, "rouge1_precision": 0.002595925373248815, "rouge1_precision_stderr": 0.0008354910877971658, "rouge1_recall": 0.001999825463947682, "rouge1_recall_stderr": 0.000634288246013444, "rouge2_fmeasure": 0.00022888298907867294, "rouge2_fmeasure_stderr": 0.00012995777833085082, "rouge2_precision": 0.00027170862025409603, "rouge2_precision_stderr": 0.00014974174761724665, "rouge2_recall": 0.00019881893910750738, "rouge2_recall_stderr": 0.00011559008179568124, "rougeL_fmeasure": 0.0014744333692215336, "rougeL_fmeasure_stderr": 0.00042158052355062295, "rougeL_precision": 0.0016970776755226781, "rougeL_precision_stderr": 0.0004959302048426671, "rougeL_recall": 0.001329703638978752, "rougeL_recall_stderr": 0.0003765201577760315, "rougeLsum_fmeasure": 0.0015935490543749545, "rougeLsum_fmeasure_stderr": 0.000460457141424318, "rougeLsum_precision": 0.0018375087990719742, "rougeLsum_precision_stderr": 0.0005450511389629724, "rougeLsum_recall": 0.0014340716678750828, "rougeLsum_recall_stderr": 0.0004083189310550863}}}} |