Muennighoff's picture
Add
29393c3
raw
history blame
No virus
28.1 kB
{"GEM/web_nlg_en": {"0": {"PALM_prompt": {"bleu": 0.33153388648094195, "bleu_stderr": 0.033005772984634425, "rouge1_fmeasure": 0.10892120808244464, "rouge1_fmeasure_stderr": 0.0019623579408930523, "rouge1_precision": 0.07122303608863641, "rouge1_precision_stderr": 0.0014591848220124259, "rouge1_recall": 0.30715399283349226, "rouge1_recall_stderr": 0.004708720401522559, "rouge2_fmeasure": 0.05087917177498001, "rouge2_fmeasure_stderr": 0.0012052999188796845, "rouge2_precision": 0.03301457183266829, "rouge2_precision_stderr": 0.0008587185375204866, "rouge2_recall": 0.14854387481989287, "rouge2_recall_stderr": 0.003193281253509643, "rougeL_fmeasure": 0.1046596223130991, "rougeL_fmeasure_stderr": 0.0018274939775881785, "rougeL_precision": 0.06820659069603296, "rougeL_precision_stderr": 0.0013384312711305548, "rougeL_recall": 0.29787923352571516, "rougeL_recall_stderr": 0.004614486799091354, "rougeLsum_fmeasure": 0.10379069725870145, "rougeLsum_fmeasure_stderr": 0.0018395610209924003, "rougeLsum_precision": 0.06782306790846614, "rougeLsum_precision_stderr": 0.0013642733366910549, "rougeLsum_recall": 0.29321572118705336, "rougeLsum_recall_stderr": 0.004444992160741671}}, "1": {"PALM_prompt": {"bleu": 0.4390216732028977, "bleu_stderr": 0.02835432276037686, "rouge1_fmeasure": 0.11512333876359498, "rouge1_fmeasure_stderr": 0.0017974110536525595, "rouge1_precision": 0.07291258825421418, "rouge1_precision_stderr": 0.0012781399789461385, "rouge1_recall": 0.3797532045177941, "rouge1_recall_stderr": 0.0054586371665182355, "rouge2_fmeasure": 0.05213699889610434, "rouge2_fmeasure_stderr": 0.0010956033295937493, "rouge2_precision": 0.032868611308100475, "rouge2_precision_stderr": 0.0007540345266181282, "rouge2_recall": 0.18168266286903503, "rouge2_recall_stderr": 0.0037422324762068537, "rougeL_fmeasure": 0.10756044811692632, "rougeL_fmeasure_stderr": 0.001603262453041204, "rougeL_precision": 0.06806601322392085, "rougeL_precision_stderr": 0.0011368722533979258, "rougeL_recall": 0.3553819785767932, "rougeL_recall_stderr": 0.004968399489043776, "rougeLsum_fmeasure": 0.10900979568571047, "rougeLsum_fmeasure_stderr": 0.0016850432132498889, "rougeLsum_precision": 0.06910714253449175, "rougeLsum_precision_stderr": 0.0012031621148103201, "rougeLsum_recall": 0.3583493585506855, "rougeLsum_recall_stderr": 0.005014235277134646}}, "2": {"PALM_prompt": {"bleu": 0.49541929016035524, "bleu_stderr": 0.025797242026580104, "rouge1_fmeasure": 0.11565855599729363, "rouge1_fmeasure_stderr": 0.0016715046204442972, "rouge1_precision": 0.07266725444927156, "rouge1_precision_stderr": 0.0011715118352015903, "rouge1_recall": 0.392286147400258, "rouge1_recall_stderr": 0.005249827988828273, "rouge2_fmeasure": 0.05321206929632585, "rouge2_fmeasure_stderr": 0.001036190867375003, "rouge2_precision": 0.03317260466126409, "rouge2_precision_stderr": 0.000696598360418341, "rouge2_recall": 0.1942947439780873, "rouge2_recall_stderr": 0.0038612870273807783, "rougeL_fmeasure": 0.10849753112690429, "rougeL_fmeasure_stderr": 0.0015324126427550334, "rougeL_precision": 0.06822626222269808, "rougeL_precision_stderr": 0.0010788080778881023, "rougeL_recall": 0.3658441206667177, "rougeL_recall_stderr": 0.004744182177069523, "rougeLsum_fmeasure": 0.10994078611093397, "rougeLsum_fmeasure_stderr": 0.0015743454993528729, "rougeLsum_precision": 0.06911868824793722, "rougeLsum_precision_stderr": 0.0011075456309651759, "rougeLsum_recall": 0.3723196892015273, "rougeLsum_recall_stderr": 0.004901964131441716}}, "3": {"PALM_prompt": {"bleu": 0.5491960579253196, "bleu_stderr": 0.039648429482997495, "rouge1_fmeasure": 0.11408517238759823, "rouge1_fmeasure_stderr": 0.0016665220312756322, "rouge1_precision": 0.07160364848852087, "rouge1_precision_stderr": 0.0011783430176818728, "rouge1_recall": 0.3927842849413568, "rouge1_recall_stderr": 0.00522433426165448, "rouge2_fmeasure": 0.052818017804867626, "rouge2_fmeasure_stderr": 0.0010623028200577843, "rouge2_precision": 0.03296327776337767, "rouge2_precision_stderr": 0.0007230725204977183, "rouge2_recall": 0.19533584043693603, "rouge2_recall_stderr": 0.0038707201775201655, "rougeL_fmeasure": 0.10630291986513662, "rougeL_fmeasure_stderr": 0.001526814085910438, "rougeL_precision": 0.06680503273038688, "rougeL_precision_stderr": 0.0010837322892585253, "rougeL_recall": 0.36333847242647704, "rougeL_recall_stderr": 0.004665099933938704, "rougeLsum_fmeasure": 0.10846020883153136, "rougeLsum_fmeasure_stderr": 0.0015890200535555973, "rougeLsum_precision": 0.0681283239197468, "rougeLsum_precision_stderr": 0.0011259165449605442, "rougeLsum_recall": 0.37225854905210065, "rougeLsum_recall_stderr": 0.004887731193821206}}, "4": {"PALM_prompt": {"bleu": 0.6089661489117988, "bleu_stderr": 0.04699623217901871, "rouge1_fmeasure": 0.11514000344336653, "rouge1_fmeasure_stderr": 0.0016184571331864207, "rouge1_precision": 0.07213518977803757, "rouge1_precision_stderr": 0.0011476197609056422, "rouge1_recall": 0.3992239446300711, "rouge1_recall_stderr": 0.005128894156765551, "rouge2_fmeasure": 0.05332935191373514, "rouge2_fmeasure_stderr": 0.0010277690042407401, "rouge2_precision": 0.033158630338207526, "rouge2_precision_stderr": 0.0006987407020504501, "rouge2_recall": 0.20032190789144683, "rouge2_recall_stderr": 0.0038236156171148734, "rougeL_fmeasure": 0.10644937066363529, "rougeL_fmeasure_stderr": 0.0014847353193029158, "rougeL_precision": 0.06683680650160255, "rougeL_precision_stderr": 0.0010578019098300508, "rougeL_recall": 0.36520991395591773, "rougeL_recall_stderr": 0.004493220490046675, "rougeLsum_fmeasure": 0.10920289975227614, "rougeLsum_fmeasure_stderr": 0.0015389130963739533, "rougeLsum_precision": 0.06848539496662703, "rougeLsum_precision_stderr": 0.001092766850551142, "rougeLsum_recall": 0.3773679563441165, "rougeLsum_recall_stderr": 0.004791768779964645}}, "5": {"PALM_prompt": {"bleu": 0.6220539692203896, "bleu_stderr": 0.027241061650766073, "rouge1_fmeasure": 0.11402382459454527, "rouge1_fmeasure_stderr": 0.0015862357548837988, "rouge1_precision": 0.0712682874127396, "rouge1_precision_stderr": 0.0011261508589404943, "rouge1_recall": 0.40368204669190927, "rouge1_recall_stderr": 0.005176457083171882, "rouge2_fmeasure": 0.05353546076223042, "rouge2_fmeasure_stderr": 0.0010071474225918618, "rouge2_precision": 0.0332020137953197, "rouge2_precision_stderr": 0.0006861186130499352, "rouge2_recall": 0.20677377146703504, "rouge2_recall_stderr": 0.0039525209229281264, "rougeL_fmeasure": 0.10577538472070054, "rougeL_fmeasure_stderr": 0.0014621636026219001, "rougeL_precision": 0.06625798608998291, "rougeL_precision_stderr": 0.0010442629568554243, "rougeL_recall": 0.3704875696637656, "rougeL_recall_stderr": 0.004602314366146881, "rougeLsum_fmeasure": 0.10844065292929861, "rougeLsum_fmeasure_stderr": 0.0015071351512198398, "rougeLsum_precision": 0.06783456627617492, "rougeLsum_precision_stderr": 0.001071886270802083, "rougeLsum_recall": 0.382465197548837, "rougeLsum_recall_stderr": 0.004842551860701479}}}, "GEM/wiki_lingua_en": {"0": {"tldr_en": {"bleu": 1.5993765093997294, "bleu_stderr": 0.07506085369601702, "rouge1_fmeasure": 0.1779625720124565, "rouge1_fmeasure_stderr": 0.0018340890133845323, "rouge1_precision": 0.15182550911429873, "rouge1_precision_stderr": 0.0018688893384549484, "rouge1_recall": 0.2589242894485067, "rouge1_recall_stderr": 0.0026517724171458952, "rouge2_fmeasure": 0.036223836197762725, "rouge2_fmeasure_stderr": 0.0008360695449580615, "rouge2_precision": 0.030739869666078615, "rouge2_precision_stderr": 0.0007500707956482545, "rouge2_recall": 0.05422083314217582, "rouge2_recall_stderr": 0.0013617275020705638, "rougeL_fmeasure": 0.13797458766444107, "rougeL_fmeasure_stderr": 0.00128706736916593, "rougeL_precision": 0.1163914580615846, "rougeL_precision_stderr": 0.0012923332758585293, "rougeL_recall": 0.20559642048990517, "rougeL_recall_stderr": 0.0021063218448770372, "rougeLsum_fmeasure": 0.1625132579484488, "rougeLsum_fmeasure_stderr": 0.0016598158056400846, "rougeLsum_precision": 0.13832783036931234, "rougeLsum_precision_stderr": 0.0016858294437463758, "rougeLsum_recall": 0.23756775868205818, "rougeLsum_recall_stderr": 0.002450945116586128}}, "1": {"tldr_en": {"bleu": 2.5200403089231775, "bleu_stderr": 0.05693901717280776, "rouge1_fmeasure": 0.21598714377615563, "rouge1_fmeasure_stderr": 0.0019024221215778328, "rouge1_precision": 0.18496096563065467, "rouge1_precision_stderr": 0.002050002215955609, "rouge1_recall": 0.3135599264124284, "rouge1_recall_stderr": 0.0027341763298141864, "rouge2_fmeasure": 0.05092387173534868, "rouge2_fmeasure_stderr": 0.0009502922893863336, "rouge2_precision": 0.043438836648193035, "rouge2_precision_stderr": 0.0008698319584098167, "rouge2_recall": 0.07611495800976509, "rouge2_recall_stderr": 0.0016061241867093036, "rougeL_fmeasure": 0.15160062635446855, "rougeL_fmeasure_stderr": 0.001239572009665517, "rougeL_precision": 0.1281515256406243, "rougeL_precision_stderr": 0.001291169012274189, "rougeL_recall": 0.2264556395402032, "rougeL_recall_stderr": 0.0021416748555613593, "rougeLsum_fmeasure": 0.2019926405301408, "rougeLsum_fmeasure_stderr": 0.0017749314312316205, "rougeLsum_precision": 0.17280855254177024, "rougeLsum_precision_stderr": 0.0019099792075058242, "rougeLsum_recall": 0.2938664218975422, "rougeLsum_recall_stderr": 0.0025815210408538384}}, "2": {"tldr_en": {"bleu": 2.8246220069939314, "bleu_stderr": 0.05436929747000312, "rouge1_fmeasure": 0.22231924312892618, "rouge1_fmeasure_stderr": 0.0018757379527855871, "rouge1_precision": 0.19241271397106163, "rouge1_precision_stderr": 0.002086863578689543, "rouge1_recall": 0.32031046447154404, "rouge1_recall_stderr": 0.0027181669208385484, "rouge2_fmeasure": 0.05579012272313604, "rouge2_fmeasure_stderr": 0.0010124966408794026, "rouge2_precision": 0.048019665884255235, "rouge2_precision_stderr": 0.000949724643152317, "rouge2_recall": 0.0836751095859514, "rouge2_recall_stderr": 0.0017264035814644186, "rougeL_fmeasure": 0.15627127285797618, "rougeL_fmeasure_stderr": 0.0012523054332758818, "rougeL_precision": 0.13376141964932425, "rougeL_precision_stderr": 0.0013725108527129226, "rougeL_recall": 0.23124667730229143, "rougeL_recall_stderr": 0.0021820014245572915, "rougeLsum_fmeasure": 0.20921146077018363, "rougeLsum_fmeasure_stderr": 0.001755514182451968, "rougeLsum_precision": 0.18081556496647747, "rougeLsum_precision_stderr": 0.0019520981988559959, "rougeLsum_recall": 0.3025117234925768, "rougeLsum_recall_stderr": 0.0026055764102078075}}, "3": {"tldr_en": {"bleu": 2.775126184527832, "bleu_stderr": 0.04964262533072551, "rouge1_fmeasure": 0.1848100615479409, "rouge1_fmeasure_stderr": 0.0022579690258614704, "rouge1_precision": 0.16640193920440474, "rouge1_precision_stderr": 0.002472882187893366, "rouge1_recall": 0.2649663905434579, "rouge1_recall_stderr": 0.0032993991901049875, "rouge2_fmeasure": 0.04536872008122934, "rouge2_fmeasure_stderr": 0.001002873578150144, "rouge2_precision": 0.04051313387433241, "rouge2_precision_stderr": 0.001042560540352432, "rouge2_recall": 0.06748612349747192, "rouge2_recall_stderr": 0.0016580523507809426, "rougeL_fmeasure": 0.13129086818074612, "rougeL_fmeasure_stderr": 0.001545448883255699, "rougeL_precision": 0.11778833422399672, "rougeL_precision_stderr": 0.001764546075584022, "rougeL_recall": 0.19297885421052255, "rougeL_recall_stderr": 0.002524627264850371, "rougeLsum_fmeasure": 0.17351085580896572, "rougeLsum_fmeasure_stderr": 0.002116003523751111, "rougeLsum_precision": 0.1560147423913123, "rougeLsum_precision_stderr": 0.0023125754138923474, "rougeLsum_recall": 0.249482350470566, "rougeLsum_recall_stderr": 0.0031348571322463346}}, "4": {"tldr_en": {"bleu": 0.6328100673630783, "bleu_stderr": 0.039922860842299984, "rouge1_fmeasure": 0.05762199753523481, "rouge1_fmeasure_stderr": 0.0019234101466023426, "rouge1_precision": 0.05264325356647027, "rouge1_precision_stderr": 0.0019548941831179097, "rouge1_recall": 0.08637392317712084, "rouge1_recall_stderr": 0.0029446541600125875, "rouge2_fmeasure": 0.013932175935494801, "rouge2_fmeasure_stderr": 0.000677479417971868, "rouge2_precision": 0.012435473489888542, "rouge2_precision_stderr": 0.0006697583811981027, "rouge2_recall": 0.022066243551567184, "rouge2_recall_stderr": 0.001176386791377328, "rougeL_fmeasure": 0.042630350228712206, "rougeL_fmeasure_stderr": 0.0014055059931358702, "rougeL_precision": 0.038774748862737, "rougeL_precision_stderr": 0.0014187651157647537, "rougeL_recall": 0.06558722529459496, "rougeL_recall_stderr": 0.002298264781788869, "rougeLsum_fmeasure": 0.05397101577019339, "rougeLsum_fmeasure_stderr": 0.001795986537373056, "rougeLsum_precision": 0.049317168459700536, "rougeLsum_precision_stderr": 0.0018317279159510054, "rougeLsum_recall": 0.08119886671766297, "rougeLsum_recall_stderr": 0.002771971428999714}}, "5": {"tldr_en": {"bleu": 1.8294461842495436e-06, "bleu_stderr": 2.8960441784514307e-06, "rouge1_fmeasure": 0.009114245109778818, "rouge1_fmeasure_stderr": 0.0008561600546824989, "rouge1_precision": 0.008573781066321003, "rouge1_precision_stderr": 0.0008654762638624486, "rouge1_recall": 0.013672256166431493, "rouge1_recall_stderr": 0.0012985268683484443, "rouge2_fmeasure": 0.0021689783329266383, "rouge2_fmeasure_stderr": 0.00026415328416558304, "rouge2_precision": 0.001966748909838605, "rouge2_precision_stderr": 0.00025417327235094497, "rouge2_recall": 0.0033662241091160935, "rouge2_recall_stderr": 0.0004534618115491094, "rougeL_fmeasure": 0.006612705879560682, "rougeL_fmeasure_stderr": 0.0006186105809635613, "rougeL_precision": 0.006239534916325571, "rougeL_precision_stderr": 0.0006307296825652261, "rougeL_recall": 0.010041041492697021, "rougeL_recall_stderr": 0.0009608570474005339, "rougeLsum_fmeasure": 0.008378974054458118, "rougeLsum_fmeasure_stderr": 0.0007859574648450136, "rougeLsum_precision": 0.007874956167229618, "rougeLsum_precision_stderr": 0.0007946305678768076, "rougeLsum_recall": 0.01258508198697765, "rougeLsum_recall_stderr": 0.0011929631283971707}}}, "e2e_nlg_cleaned": {"0": {"generate_text_restaurant": {"bleu": 1.4134342817933134, "bleu_stderr": 0.10321165497606506, "rouge1_fmeasure": 0.07268079919042715, "rouge1_fmeasure_stderr": 0.0013299276492676378, "rouge1_precision": 0.10247313979693526, "rouge1_precision_stderr": 0.0016595089176992329, "rouge1_recall": 0.08798141485351638, "rouge1_recall_stderr": 0.0020421795807805876, "rouge2_fmeasure": 0.00993468622248673, "rouge2_fmeasure_stderr": 0.0005343002508124515, "rouge2_precision": 0.00887479842846684, "rouge2_precision_stderr": 0.0005272736841464594, "rouge2_recall": 0.014404059874404535, "rouge2_recall_stderr": 0.0007753598252854332, "rougeL_fmeasure": 0.07081998927780214, "rougeL_fmeasure_stderr": 0.0012624377157260348, "rougeL_precision": 0.10002794388883973, "rougeL_precision_stderr": 0.0015746721314263722, "rougeL_recall": 0.08578186838136309, "rougeL_recall_stderr": 0.001963617682885378, "rougeLsum_fmeasure": 0.06325547718223694, "rougeLsum_fmeasure_stderr": 0.001146593422118666, "rougeLsum_precision": 0.09505113511885002, "rougeLsum_precision_stderr": 0.0016104542116781076, "rougeLsum_recall": 0.07341402605300737, "rougeLsum_recall_stderr": 0.0017014954492227232}}, "1": {"generate_text_restaurant": {"bleu": 11.161361331881567, "bleu_stderr": 0.12372614680699576, "rouge1_fmeasure": 0.4325678229581062, "rouge1_fmeasure_stderr": 0.002292323583369995, "rouge1_precision": 0.5102128961431266, "rouge1_precision_stderr": 0.0032435467042979615, "rouge1_recall": 0.41996959404299955, "rouge1_recall_stderr": 0.003000739317309415, "rouge2_fmeasure": 0.19587297305804474, "rouge2_fmeasure_stderr": 0.0019046996832194681, "rouge2_precision": 0.2347486548964982, "rouge2_precision_stderr": 0.0025124030520577855, "rouge2_recall": 0.18995161561629698, "rouge2_recall_stderr": 0.002108346628324476, "rougeL_fmeasure": 0.3125033610005072, "rougeL_fmeasure_stderr": 0.001959745932298407, "rougeL_precision": 0.3718563664348661, "rougeL_precision_stderr": 0.0028475505595708522, "rougeL_recall": 0.302335969435588, "rougeL_recall_stderr": 0.002389554465547073, "rougeLsum_fmeasure": 0.35360222601109786, "rougeLsum_fmeasure_stderr": 0.002221056794276662, "rougeLsum_precision": 0.41834560442201607, "rougeLsum_precision_stderr": 0.0030773847535100003, "rougeLsum_recall": 0.3428712422996488, "rougeLsum_recall_stderr": 0.0027256967100605344}}, "2": {"generate_text_restaurant": {"bleu": 11.178478800336915, "bleu_stderr": 0.18720778468970048, "rouge1_fmeasure": 0.43564156295510353, "rouge1_fmeasure_stderr": 0.002087610230342593, "rouge1_precision": 0.4641458682797714, "rouge1_precision_stderr": 0.002971633166316723, "rouge1_recall": 0.45712689402679485, "rouge1_recall_stderr": 0.0028529123911751396, "rouge2_fmeasure": 0.20007291305638683, "rouge2_fmeasure_stderr": 0.0018220503474021836, "rouge2_precision": 0.21534769962339712, "rouge2_precision_stderr": 0.0023043178046714048, "rouge2_recall": 0.21108519516124935, "rouge2_recall_stderr": 0.002144830729960772, "rougeL_fmeasure": 0.3154129310627208, "rougeL_fmeasure_stderr": 0.0017997732274878523, "rougeL_precision": 0.3373737455708324, "rougeL_precision_stderr": 0.002541494576877095, "rougeL_recall": 0.3312050835060631, "rougeL_recall_stderr": 0.0023578769935104662, "rougeLsum_fmeasure": 0.36253839271187577, "rougeLsum_fmeasure_stderr": 0.0020879729234347427, "rougeLsum_precision": 0.38666807747150694, "rougeLsum_precision_stderr": 0.002816195982796137, "rougeLsum_recall": 0.3803128282949514, "rougeLsum_recall_stderr": 0.002684776810203093}}, "3": {"generate_text_restaurant": {"bleu": 11.078551573988406, "bleu_stderr": 0.1775440487553758, "rouge1_fmeasure": 0.4326675462538715, "rouge1_fmeasure_stderr": 0.0019582645124443902, "rouge1_precision": 0.43295946805897406, "rouge1_precision_stderr": 0.0024929063336741916, "rouge1_recall": 0.47117854558838085, "rouge1_recall_stderr": 0.0027664367541802696, "rouge2_fmeasure": 0.200583189798169, "rouge2_fmeasure_stderr": 0.0017572494683324837, "rouge2_precision": 0.2009303237548315, "rouge2_precision_stderr": 0.0019532985877392488, "rouge2_recall": 0.22075863091567335, "rouge2_recall_stderr": 0.0021918759824511784, "rougeL_fmeasure": 0.31563666321158207, "rougeL_fmeasure_stderr": 0.0017274457082887083, "rougeL_precision": 0.31641399110077373, "rougeL_precision_stderr": 0.002147128833979884, "rougeL_recall": 0.3443145885276902, "rougeL_recall_stderr": 0.002348509165132024, "rougeLsum_fmeasure": 0.36464056912358683, "rougeLsum_fmeasure_stderr": 0.002012766885114503, "rougeLsum_precision": 0.3650689748250584, "rougeLsum_precision_stderr": 0.0024222254606659755, "rougeLsum_recall": 0.3971452452707439, "rougeLsum_recall_stderr": 0.0026671950920676476}}, "4": {"generate_text_restaurant": {"bleu": 11.26779671250681, "bleu_stderr": 0.20945092499394355, "rouge1_fmeasure": 0.43468339695150743, "rouge1_fmeasure_stderr": 0.0019192301545953678, "rouge1_precision": 0.42504057259498224, "rouge1_precision_stderr": 0.002302694388890242, "rouge1_recall": 0.479467443521395, "rouge1_recall_stderr": 0.002694693864079371, "rouge2_fmeasure": 0.202879451815592, "rouge2_fmeasure_stderr": 0.001765189527045149, "rouge2_precision": 0.19787815742992643, "rouge2_precision_stderr": 0.0018370754370625954, "rouge2_recall": 0.22626550198253664, "rouge2_recall_stderr": 0.002204792167524998, "rougeL_fmeasure": 0.3172808489106893, "rougeL_fmeasure_stderr": 0.0017201307043284524, "rougeL_precision": 0.31019836982770554, "rougeL_precision_stderr": 0.001959650847184396, "rougeL_recall": 0.3507681740649588, "rougeL_recall_stderr": 0.0023395609242667513, "rougeLsum_fmeasure": 0.36655599606622596, "rougeLsum_fmeasure_stderr": 0.0019897208220121514, "rougeLsum_precision": 0.3582038693968529, "rougeLsum_precision_stderr": 0.0022423131040152167, "rougeLsum_recall": 0.40461547051620306, "rougeLsum_recall_stderr": 0.0026339178059616598}}, "5": {"generate_text_restaurant": {"bleu": 11.056827999458564, "bleu_stderr": 0.18078644474517908, "rouge1_fmeasure": 0.4309560903845341, "rouge1_fmeasure_stderr": 0.001893293831351894, "rouge1_precision": 0.41637768269876485, "rouge1_precision_stderr": 0.002227557311413217, "rouge1_recall": 0.48001165743040636, "rouge1_recall_stderr": 0.0026762804898328154, "rouge2_fmeasure": 0.20083246520570572, "rouge2_fmeasure_stderr": 0.0017445182528093705, "rouge2_precision": 0.19341945111333012, "rouge2_precision_stderr": 0.0017901333419283593, "rouge2_recall": 0.22629146190496788, "rouge2_recall_stderr": 0.002191585425335327, "rougeL_fmeasure": 0.31519997823452967, "rougeL_fmeasure_stderr": 0.0017133598116412512, "rougeL_precision": 0.303929949160996, "rougeL_precision_stderr": 0.0018891083086755413, "rougeL_recall": 0.35261189373922003, "rougeL_recall_stderr": 0.0023727357497467937, "rougeLsum_fmeasure": 0.3646984779801211, "rougeLsum_fmeasure_stderr": 0.001960028955951922, "rougeLsum_precision": 0.35227968062569365, "rougeLsum_precision_stderr": 0.0021866137017689286, "rougeLsum_recall": 0.4064043196987044, "rougeLsum_recall_stderr": 0.002605112678915691}}}, "gem_xsum": {"0": {"article_DOC_summary": {"bleu": 2.295517441700607, "bleu_stderr": 0.09915357248852676, "rouge1_fmeasure": 0.21824095908596577, "rouge1_fmeasure_stderr": 0.0025874062237003148, "rouge1_precision": 0.16347573034711765, "rouge1_precision_stderr": 0.002235052767052065, "rouge1_recall": 0.361809595461701, "rouge1_recall_stderr": 0.004450055018587551, "rouge2_fmeasure": 0.055096743612893836, "rouge2_fmeasure_stderr": 0.0017015215521108862, "rouge2_precision": 0.04080119463614899, "rouge2_precision_stderr": 0.0013586822504416986, "rouge2_recall": 0.09489684727762387, "rouge2_recall_stderr": 0.0030304863214365187, "rougeL_fmeasure": 0.1649602106468539, "rougeL_fmeasure_stderr": 0.0019703191216796398, "rougeL_precision": 0.12349304284569401, "rougeL_precision_stderr": 0.0017244637096469517, "rougeL_recall": 0.27540408956152623, "rougeL_recall_stderr": 0.0035538299823413846, "rougeLsum_fmeasure": 0.1710468546463645, "rougeLsum_fmeasure_stderr": 0.0022098555753275687, "rougeLsum_precision": 0.12787359610941754, "rougeLsum_precision_stderr": 0.0018576292031407871, "rougeLsum_recall": 0.2854470256837463, "rougeLsum_recall_stderr": 0.003942621790562841}}, "1": {"article_DOC_summary": {"bleu": 1.3192475830096537, "bleu_stderr": 0.07504584122763394, "rouge1_fmeasure": 0.1759444559759621, "rouge1_fmeasure_stderr": 0.0024983727013912576, "rouge1_precision": 0.12498263517558904, "rouge1_precision_stderr": 0.0018439932798174727, "rouge1_recall": 0.30997040065867815, "rouge1_recall_stderr": 0.004377559967707829, "rouge2_fmeasure": 0.03416151854233213, "rouge2_fmeasure_stderr": 0.0013809223175216116, "rouge2_precision": 0.023984343121594594, "rouge2_precision_stderr": 0.0009703036853821361, "rouge2_recall": 0.061937587800487796, "rouge2_recall_stderr": 0.0025773754792855217, "rougeL_fmeasure": 0.13659440083004393, "rougeL_fmeasure_stderr": 0.0018529344115148084, "rougeL_precision": 0.09683506809823249, "rougeL_precision_stderr": 0.0013556223253912536, "rougeL_recall": 0.24217304938796147, "rougeL_recall_stderr": 0.003372900627372106, "rougeLsum_fmeasure": 0.14008466520947307, "rougeLsum_fmeasure_stderr": 0.0020194523247221608, "rougeLsum_precision": 0.099266332557722, "rougeLsum_precision_stderr": 0.0014699947767357671, "rougeLsum_recall": 0.2484370722635638, "rougeLsum_recall_stderr": 0.0036565129132140007}}, "2": {"article_DOC_summary": {"bleu": 1.3941983933749893, "bleu_stderr": 0.07778092606300743, "rouge1_fmeasure": 0.17317479594583315, "rouge1_fmeasure_stderr": 0.0024306874343318695, "rouge1_precision": 0.12308471402675025, "rouge1_precision_stderr": 0.0017964024163926668, "rouge1_recall": 0.30420591170874123, "rouge1_recall_stderr": 0.0042091034345315345, "rouge2_fmeasure": 0.03548103421040685, "rouge2_fmeasure_stderr": 0.0013648086670444103, "rouge2_precision": 0.024998880277592218, "rouge2_precision_stderr": 0.0009660509776349401, "rouge2_recall": 0.06368455444982171, "rouge2_recall_stderr": 0.002497504245191044, "rougeL_fmeasure": 0.13747942038634384, "rougeL_fmeasure_stderr": 0.0018617507575533767, "rougeL_precision": 0.09766064805279387, "rougeL_precision_stderr": 0.0013763841420730348, "rougeL_recall": 0.24210898643660594, "rougeL_recall_stderr": 0.003269851529578185, "rougeLsum_fmeasure": 0.13676635773915868, "rougeLsum_fmeasure_stderr": 0.002012262737653545, "rougeLsum_precision": 0.09700451417856086, "rougeLsum_precision_stderr": 0.0014713838347837971, "rougeLsum_recall": 0.2416228650888391, "rougeLsum_recall_stderr": 0.003570749791914669}}, "3": {"article_DOC_summary": {"bleu": 1.447300262525524, "bleu_stderr": 0.0647434385662156, "rouge1_fmeasure": 0.17052015726603906, "rouge1_fmeasure_stderr": 0.0026006019517768233, "rouge1_precision": 0.1238798362783257, "rouge1_precision_stderr": 0.0020371925631676394, "rouge1_recall": 0.2938277668513655, "rouge1_recall_stderr": 0.004445484366807697, "rouge2_fmeasure": 0.03519128429327673, "rouge2_fmeasure_stderr": 0.0013864951253610754, "rouge2_precision": 0.025223685922742684, "rouge2_precision_stderr": 0.0010126897278031643, "rouge2_recall": 0.06217111485022419, "rouge2_recall_stderr": 0.0025204701650283143, "rougeL_fmeasure": 0.1359902514132361, "rougeL_fmeasure_stderr": 0.002000179300648128, "rougeL_precision": 0.09880564731360271, "rougeL_precision_stderr": 0.0015869573723169535, "rougeL_recall": 0.2348719293167949, "rougeL_recall_stderr": 0.0034616442328126336, "rougeLsum_fmeasure": 0.13420532702105284, "rougeLsum_fmeasure_stderr": 0.0020736765057759775, "rougeLsum_precision": 0.09736356730337334, "rougeLsum_precision_stderr": 0.0016253165748697476, "rougeLsum_recall": 0.23279761437533245, "rougeLsum_recall_stderr": 0.0036609997549228836}}, "4": {"article_DOC_summary": {"bleu": 0.6399540831907461, "bleu_stderr": 0.0665572258832638, "rouge1_fmeasure": 0.04587682793613896, "rouge1_fmeasure_stderr": 0.0026664431362576437, "rouge1_precision": 0.03916972701362441, "rouge1_precision_stderr": 0.0025232037599719035, "rouge1_recall": 0.0705187151734879, "rouge1_recall_stderr": 0.0041033703238095975, "rouge2_fmeasure": 0.008749872613988179, "rouge2_fmeasure_stderr": 0.0008910869873582503, "rouge2_precision": 0.007496872523694719, "rouge2_precision_stderr": 0.0009023223955939198, "rouge2_recall": 0.013768613253728622, "rouge2_recall_stderr": 0.0013735135943198867, "rougeL_fmeasure": 0.03641897598226805, "rougeL_fmeasure_stderr": 0.0020590368431718546, "rougeL_precision": 0.03154543945422246, "rougeL_precision_stderr": 0.0020528668246378276, "rougeL_recall": 0.05618648837737757, "rougeL_recall_stderr": 0.0032188263348742517, "rougeLsum_fmeasure": 0.036286088799465356, "rougeLsum_fmeasure_stderr": 0.002099169574521433, "rougeLsum_precision": 0.031542117455926555, "rougeLsum_precision_stderr": 0.0021071412880804725, "rougeLsum_recall": 0.055916896434064445, "rougeLsum_recall_stderr": 0.003269542426299847}}, "5": {"article_DOC_summary": {"bleu": 4.294601973766167e-36, "bleu_stderr": 7.391409466573723e-32, "rouge1_fmeasure": 0.002797377262876916, "rouge1_fmeasure_stderr": 0.0008436395309397021, "rouge1_precision": 0.0030262317078135763, "rouge1_precision_stderr": 0.0008861957572341574, "rouge1_recall": 0.002682824319713878, "rouge1_recall_stderr": 0.0008349754331976099, "rouge2_fmeasure": 0.0005852654722501501, "rouge2_fmeasure_stderr": 0.00037583234587724155, "rouge2_precision": 0.0005864695792553728, "rouge2_precision_stderr": 0.0003600452195293311, "rouge2_recall": 0.0005925913708932577, "rouge2_recall_stderr": 0.00039524060846512425, "rougeL_fmeasure": 0.002169100825975142, "rougeL_fmeasure_stderr": 0.0006545600161608136, "rougeL_precision": 0.0023057883289935395, "rougeL_precision_stderr": 0.0006706823613650493, "rougeL_recall": 0.002115155017368573, "rougeL_recall_stderr": 0.0006595785512806381, "rougeLsum_fmeasure": 0.002243893464585761, "rougeLsum_fmeasure_stderr": 0.0006801725997564016, "rougeLsum_precision": 0.00240202126410433, "rougeLsum_precision_stderr": 0.0007072328465422081, "rougeLsum_recall": 0.0021726632985610644, "rougeLsum_recall_stderr": 0.0006770960348507971}}}}