Muennighoff's picture
Add
29393c3
raw
history blame
No virus
28 kB
{"GEM/web_nlg_en": {"0": {"PALM_prompt": {"bleu": 0.34441376096478077, "bleu_stderr": 0.03364738239161352, "rouge1_fmeasure": 0.10791921496577737, "rouge1_fmeasure_stderr": 0.002171402381627088, "rouge1_precision": 0.07156437671140904, "rouge1_precision_stderr": 0.0016916866568706518, "rouge1_recall": 0.29498663582371476, "rouge1_recall_stderr": 0.0047504849601230975, "rouge2_fmeasure": 0.0506136487550108, "rouge2_fmeasure_stderr": 0.0013544155568851314, "rouge2_precision": 0.03339629860790558, "rouge2_precision_stderr": 0.0010276756756951227, "rouge2_recall": 0.14089640762105182, "rouge2_recall_stderr": 0.003169219645311096, "rougeL_fmeasure": 0.10397564759824128, "rougeL_fmeasure_stderr": 0.002024130402320653, "rougeL_precision": 0.06867849616024986, "rougeL_precision_stderr": 0.0015588261952769657, "rougeL_recall": 0.2865361097530141, "rougeL_recall_stderr": 0.004609475551865619, "rougeLsum_fmeasure": 0.10284733675284609, "rougeLsum_fmeasure_stderr": 0.0020471999326618765, "rougeLsum_precision": 0.06816360012566612, "rougeLsum_precision_stderr": 0.001597766711115546, "rougeLsum_recall": 0.2811330280761629, "rougeLsum_recall_stderr": 0.004465952639791254}}, "1": {"PALM_prompt": {"bleu": 0.4687199126816133, "bleu_stderr": 0.036800374006492664, "rouge1_fmeasure": 0.11753553291473576, "rouge1_fmeasure_stderr": 0.0019140656759965315, "rouge1_precision": 0.07570221536151728, "rouge1_precision_stderr": 0.0014363865463457549, "rouge1_recall": 0.37281196342463774, "rouge1_recall_stderr": 0.005425026995807581, "rouge2_fmeasure": 0.054731274015692305, "rouge2_fmeasure_stderr": 0.0011992442792975787, "rouge2_precision": 0.03517849994399333, "rouge2_precision_stderr": 0.0008874020071430252, "rouge2_recall": 0.18207060381703669, "rouge2_recall_stderr": 0.003664740082406787, "rougeL_fmeasure": 0.11105152882900622, "rougeL_fmeasure_stderr": 0.0017516497637055164, "rougeL_precision": 0.07143954952407837, "rougeL_precision_stderr": 0.001305238902060498, "rougeL_recall": 0.35175875189308164, "rougeL_recall_stderr": 0.0049642525171124975, "rougeLsum_fmeasure": 0.11134944889691471, "rougeLsum_fmeasure_stderr": 0.001795094595999485, "rougeLsum_precision": 0.07178061720744913, "rougeLsum_precision_stderr": 0.0013540467985344866, "rougeLsum_recall": 0.35171330673154494, "rougeLsum_recall_stderr": 0.004937137016938597}}, "2": {"PALM_prompt": {"bleu": 0.5235717824828133, "bleu_stderr": 0.03767810577658163, "rouge1_fmeasure": 0.12260704886786168, "rouge1_fmeasure_stderr": 0.0018070929383927695, "rouge1_precision": 0.0783700606217331, "rouge1_precision_stderr": 0.0013622939044074152, "rouge1_recall": 0.39995054593345924, "rouge1_recall_stderr": 0.0052804057805626164, "rouge2_fmeasure": 0.05717657732704682, "rouge2_fmeasure_stderr": 0.001147470465886568, "rouge2_precision": 0.03627187434475958, "rouge2_precision_stderr": 0.0008236125331839457, "rouge2_recall": 0.19905166470669564, "rouge2_recall_stderr": 0.0038388111983134595, "rougeL_fmeasure": 0.11517678618925936, "rougeL_fmeasure_stderr": 0.0016478650517612742, "rougeL_precision": 0.07359908440403741, "rougeL_precision_stderr": 0.001237832140736892, "rougeL_recall": 0.37356398478304126, "rougeL_recall_stderr": 0.004770085055809505, "rougeLsum_fmeasure": 0.1165772048673089, "rougeLsum_fmeasure_stderr": 0.0016980264714204242, "rougeLsum_precision": 0.07453785183849788, "rougeLsum_precision_stderr": 0.0012849507538737566, "rougeLsum_recall": 0.3794084560485554, "rougeLsum_recall_stderr": 0.0049017847382029295}}, "3": {"PALM_prompt": {"bleu": 0.5916343641542043, "bleu_stderr": 0.04024225062945221, "rouge1_fmeasure": 0.12387093846990074, "rouge1_fmeasure_stderr": 0.001885726927501542, "rouge1_precision": 0.07888158387802857, "rouge1_precision_stderr": 0.0013905334633539245, "rouge1_recall": 0.4033319142330156, "rouge1_recall_stderr": 0.005299089005220485, "rouge2_fmeasure": 0.058284289461857604, "rouge2_fmeasure_stderr": 0.0012101468635650288, "rouge2_precision": 0.0369653886039744, "rouge2_precision_stderr": 0.0008664032303747072, "rouge2_recall": 0.20236135540846556, "rouge2_recall_stderr": 0.0038733010690355342, "rougeL_fmeasure": 0.11544325899200131, "rougeL_fmeasure_stderr": 0.0016990426527488723, "rougeL_precision": 0.073511276121497, "rougeL_precision_stderr": 0.001251002353845416, "rougeL_recall": 0.37511361165748164, "rougeL_recall_stderr": 0.004789107031378535, "rougeLsum_fmeasure": 0.11762103770674365, "rougeLsum_fmeasure_stderr": 0.0017726486791392565, "rougeLsum_precision": 0.07497143356596919, "rougeLsum_precision_stderr": 0.0013133945848135208, "rougeLsum_recall": 0.3819932847239564, "rougeLsum_recall_stderr": 0.004902385390105475}}, "4": {"PALM_prompt": {"bleu": 0.584148826341706, "bleu_stderr": 0.032088259094079065, "rouge1_fmeasure": 0.12197092014603778, "rouge1_fmeasure_stderr": 0.0017607850151334767, "rouge1_precision": 0.07737100502750222, "rouge1_precision_stderr": 0.0013014310515114744, "rouge1_recall": 0.4039418841652104, "rouge1_recall_stderr": 0.00530796073731901, "rouge2_fmeasure": 0.05693950723216792, "rouge2_fmeasure_stderr": 0.0011236415767176787, "rouge2_precision": 0.035917415755917156, "rouge2_precision_stderr": 0.0008009838171179654, "rouge2_recall": 0.20296997665907882, "rouge2_recall_stderr": 0.0038561197119444304, "rougeL_fmeasure": 0.11390315132939448, "rougeL_fmeasure_stderr": 0.0015842511141082533, "rougeL_precision": 0.07227090942349099, "rougeL_precision_stderr": 0.001170080155549711, "rougeL_recall": 0.37605665528150317, "rougeL_recall_stderr": 0.004782196417125406, "rougeLsum_fmeasure": 0.11605708607515382, "rougeLsum_fmeasure_stderr": 0.001657698456603933, "rougeLsum_precision": 0.07366718744107867, "rougeLsum_precision_stderr": 0.001228472532147223, "rougeLsum_recall": 0.3838102958885374, "rougeLsum_recall_stderr": 0.004940246508662335}}, "5": {"PALM_prompt": {"bleu": 0.643769416521065, "bleu_stderr": 0.04327961614658416, "rouge1_fmeasure": 0.12362474434882809, "rouge1_fmeasure_stderr": 0.0017387117939925156, "rouge1_precision": 0.0778714729225077, "rouge1_precision_stderr": 0.0012716812804740509, "rouge1_recall": 0.4199879645762265, "rouge1_recall_stderr": 0.00535881210434279, "rouge2_fmeasure": 0.05758469671440457, "rouge2_fmeasure_stderr": 0.0011051399672881632, "rouge2_precision": 0.036051220083070316, "rouge2_precision_stderr": 0.000777501535408198, "rouge2_recall": 0.21150748306290545, "rouge2_recall_stderr": 0.0039302718094465635, "rougeL_fmeasure": 0.11417482723461402, "rougeL_fmeasure_stderr": 0.0015386798608318928, "rougeL_precision": 0.0719478472042638, "rougeL_precision_stderr": 0.0011295516496439356, "rougeL_recall": 0.38653994641960504, "rougeL_recall_stderr": 0.004712427125192832, "rougeLsum_fmeasure": 0.1169653954794077, "rougeLsum_fmeasure_stderr": 0.0016283607844766808, "rougeLsum_precision": 0.0737393959127114, "rougeLsum_precision_stderr": 0.001196371537872998, "rougeLsum_recall": 0.39623787521806264, "rougeLsum_recall_stderr": 0.004912468268398718}}}, "GEM/wiki_lingua_en": {"0": {"tldr_en": {"bleu": 1.5029930497312527, "bleu_stderr": 0.050686861917854, "rouge1_fmeasure": 0.1799962602325878, "rouge1_fmeasure_stderr": 0.00184248350208152, "rouge1_precision": 0.1537922187888957, "rouge1_precision_stderr": 0.0018933213102104863, "rouge1_recall": 0.2625407961087503, "rouge1_recall_stderr": 0.002682894905994936, "rouge2_fmeasure": 0.03586670200965267, "rouge2_fmeasure_stderr": 0.0008450513639399489, "rouge2_precision": 0.030157104540943284, "rouge2_precision_stderr": 0.0007476727834062231, "rouge2_recall": 0.055001050533522555, "rouge2_recall_stderr": 0.0014448444524840297, "rougeL_fmeasure": 0.13967379634609953, "rougeL_fmeasure_stderr": 0.0013162078681435803, "rougeL_precision": 0.11780986849918428, "rougeL_precision_stderr": 0.0013162517308047393, "rougeL_recall": 0.20916963040579825, "rougeL_recall_stderr": 0.002196518290796577, "rougeLsum_fmeasure": 0.16507864218420232, "rougeLsum_fmeasure_stderr": 0.0016765101940476469, "rougeLsum_precision": 0.14081205310262065, "rougeLsum_precision_stderr": 0.0017218252583982084, "rougeLsum_recall": 0.2419875104700217, "rougeLsum_recall_stderr": 0.002500846878935716}}, "1": {"tldr_en": {"bleu": 2.7242641167777077, "bleu_stderr": 0.07938213037481555, "rouge1_fmeasure": 0.21295884672876816, "rouge1_fmeasure_stderr": 0.001991739006687224, "rouge1_precision": 0.18419539466594548, "rouge1_precision_stderr": 0.00216315844926582, "rouge1_recall": 0.30850131448570595, "rouge1_recall_stderr": 0.002881646502827461, "rouge2_fmeasure": 0.051942458861991954, "rouge2_fmeasure_stderr": 0.0010199515581882507, "rouge2_precision": 0.044713693466448406, "rouge2_precision_stderr": 0.000968138913860097, "rouge2_recall": 0.07839796746781187, "rouge2_recall_stderr": 0.0017417848523259565, "rougeL_fmeasure": 0.15484936057383927, "rougeL_fmeasure_stderr": 0.001347730246639345, "rougeL_precision": 0.1326981808478002, "rougeL_precision_stderr": 0.0014579507711624912, "rougeL_recall": 0.23011492408104228, "rougeL_recall_stderr": 0.00229754097749749, "rougeLsum_fmeasure": 0.1992303563413742, "rougeLsum_fmeasure_stderr": 0.0018619630110637574, "rougeLsum_precision": 0.17205251851388254, "rougeLsum_precision_stderr": 0.0020202953529773735, "rougeLsum_recall": 0.28974852616388547, "rougeLsum_recall_stderr": 0.002737913509276009}}, "2": {"tldr_en": {"bleu": 2.86942295772908, "bleu_stderr": 0.08758910211106738, "rouge1_fmeasure": 0.20703905721090818, "rouge1_fmeasure_stderr": 0.001929567362026057, "rouge1_precision": 0.1997095751146021, "rouge1_precision_stderr": 0.002703732640041402, "rouge1_recall": 0.2883485784255837, "rouge1_recall_stderr": 0.002841589718801568, "rouge2_fmeasure": 0.051520411225961356, "rouge2_fmeasure_stderr": 0.001031129051354628, "rouge2_precision": 0.052135221349108814, "rouge2_precision_stderr": 0.0014902691345396325, "rouge2_recall": 0.07402543775497225, "rouge2_recall_stderr": 0.001656124634067446, "rougeL_fmeasure": 0.15441401199805835, "rougeL_fmeasure_stderr": 0.0013920098120515118, "rougeL_precision": 0.1503544839184264, "rougeL_precision_stderr": 0.002191707211555614, "rougeL_recall": 0.21866995964876715, "rougeL_recall_stderr": 0.0022872119612051362, "rougeLsum_fmeasure": 0.1949510570568441, "rougeLsum_fmeasure_stderr": 0.001804660306034504, "rougeLsum_precision": 0.18828746764086687, "rougeLsum_precision_stderr": 0.002574176036533358, "rougeLsum_recall": 0.27233360792883826, "rougeLsum_recall_stderr": 0.0027083132609021184}}, "3": {"tldr_en": {"bleu": 3.0330716712469843, "bleu_stderr": 0.09425863264675978, "rouge1_fmeasure": 0.17391868610816388, "rouge1_fmeasure_stderr": 0.002277407569748311, "rouge1_precision": 0.19702312634415606, "rouge1_precision_stderr": 0.0035795334816332027, "rouge1_recall": 0.22825422304548265, "rouge1_recall_stderr": 0.003232347523636064, "rouge2_fmeasure": 0.04463749924381735, "rouge2_fmeasure_stderr": 0.0010686000964725524, "rouge2_precision": 0.05667983844146617, "rouge2_precision_stderr": 0.002120538883847141, "rouge2_recall": 0.059228247136442105, "rouge2_recall_stderr": 0.0015413764801780459, "rougeL_fmeasure": 0.12950729491278481, "rougeL_fmeasure_stderr": 0.00167294588483517, "rougeL_precision": 0.15076982480282128, "rougeL_precision_stderr": 0.0030098254531581766, "rougeL_recall": 0.17209850822866807, "rougeL_recall_stderr": 0.0025209050965990243, "rougeLsum_fmeasure": 0.1642422006919473, "rougeLsum_fmeasure_stderr": 0.002147002697595944, "rougeLsum_precision": 0.1860026881384513, "rougeLsum_precision_stderr": 0.003405588840643614, "rougeLsum_recall": 0.21613806050396925, "rougeLsum_recall_stderr": 0.0030779584306118175}}, "4": {"tldr_en": {"bleu": 0.4039582112595248, "bleu_stderr": 0.03484552558450677, "rouge1_fmeasure": 0.05441509889844838, "rouge1_fmeasure_stderr": 0.001922155872957772, "rouge1_precision": 0.06862907083042237, "rouge1_precision_stderr": 0.0029137045746235116, "rouge1_recall": 0.07213602119470613, "rouge1_recall_stderr": 0.002675324630242608, "rouge2_fmeasure": 0.014130696002074776, "rouge2_fmeasure_stderr": 0.0007469700039793996, "rouge2_precision": 0.019800771477798358, "rouge2_precision_stderr": 0.0014215056199837948, "rouge2_recall": 0.019407609285097115, "rouge2_recall_stderr": 0.0011737580125973422, "rougeL_fmeasure": 0.04132917986525425, "rougeL_fmeasure_stderr": 0.001453754043869357, "rougeL_precision": 0.054030861033230786, "rougeL_precision_stderr": 0.002428473990666629, "rougeL_recall": 0.055369844370012286, "rougeL_recall_stderr": 0.0020897273452589395, "rougeLsum_fmeasure": 0.051839091609912694, "rougeLsum_fmeasure_stderr": 0.00182789753930337, "rougeLsum_precision": 0.06581471030428865, "rougeLsum_precision_stderr": 0.0028148588567455577, "rougeLsum_recall": 0.06855419478068313, "rougeLsum_recall_stderr": 0.002540543323104449}}, "5": {"tldr_en": {"bleu": 2.0014137810446263e-08, "bleu_stderr": 5.022609361040328e-08, "rouge1_fmeasure": 0.008187248278912505, "rouge1_fmeasure_stderr": 0.0008215139146136158, "rouge1_precision": 0.010184074003326236, "rouge1_precision_stderr": 0.001185280919251267, "rouge1_recall": 0.010530222683810939, "rouge1_recall_stderr": 0.0010849872451804167, "rouge2_fmeasure": 0.0020440057618351945, "rouge2_fmeasure_stderr": 0.0002894852867481284, "rouge2_precision": 0.003045190089865129, "rouge2_precision_stderr": 0.000629256262446744, "rouge2_recall": 0.0025316582919952747, "rouge2_recall_stderr": 0.00035954782149502667, "rougeL_fmeasure": 0.006141492653296614, "rougeL_fmeasure_stderr": 0.000619473069682991, "rougeL_precision": 0.00801661098513702, "rougeL_precision_stderr": 0.0009926654487693505, "rougeL_recall": 0.007789272405875561, "rougeL_recall_stderr": 0.0008037973390293996, "rougeLsum_fmeasure": 0.007792108172262034, "rougeLsum_fmeasure_stderr": 0.0007861479859061975, "rougeLsum_precision": 0.009784563527498156, "rougeLsum_precision_stderr": 0.0011539456656877766, "rougeLsum_recall": 0.009966706597956685, "rougeLsum_recall_stderr": 0.001029454113884746}}}, "e2e_nlg_cleaned": {"0": {"generate_text_restaurant": {"bleu": 0.1668198320527802, "bleu_stderr": 0.01897983257333898, "rouge1_fmeasure": 0.022506347386715704, "rouge1_fmeasure_stderr": 0.0005868062207608241, "rouge1_precision": 0.030286876271392194, "rouge1_precision_stderr": 0.001036156882791465, "rouge1_recall": 0.027143500611213456, "rouge1_recall_stderr": 0.0007465539304065285, "rouge2_fmeasure": 0.0010842906651617643, "rouge2_fmeasure_stderr": 0.0001636612072099844, "rouge2_precision": 0.0011223500556642703, "rouge2_precision_stderr": 0.0002013011694364979, "rouge2_recall": 0.0015238484363635906, "rouge2_recall_stderr": 0.00022622383493949605, "rougeL_fmeasure": 0.022348380076958108, "rougeL_fmeasure_stderr": 0.0005776004107689916, "rougeL_precision": 0.029891451434790904, "rougeL_precision_stderr": 0.0010048119314992631, "rougeL_recall": 0.027040559559811043, "rougeL_recall_stderr": 0.0007436210949765598, "rougeLsum_fmeasure": 0.02171066987180087, "rougeLsum_fmeasure_stderr": 0.0005513649905399339, "rougeLsum_precision": 0.02960870450534663, "rougeLsum_precision_stderr": 0.0010175867142908736, "rougeLsum_recall": 0.025998503793795025, "rougeLsum_recall_stderr": 0.0006867190478188373}}, "1": {"generate_text_restaurant": {"bleu": 11.497789088857585, "bleu_stderr": 0.1207333221383202, "rouge1_fmeasure": 0.437040451945744, "rouge1_fmeasure_stderr": 0.002333774145212166, "rouge1_precision": 0.5193372726053079, "rouge1_precision_stderr": 0.0032827860366154518, "rouge1_recall": 0.4187417243003722, "rouge1_recall_stderr": 0.0029601462557396806, "rouge2_fmeasure": 0.20198550157867662, "rouge2_fmeasure_stderr": 0.0019395848816704526, "rouge2_precision": 0.24404637097851045, "rouge2_precision_stderr": 0.0025862116613527076, "rouge2_recall": 0.1933021952228981, "rouge2_recall_stderr": 0.002111531045223336, "rougeL_fmeasure": 0.31702593617702457, "rougeL_fmeasure_stderr": 0.0020123220115816466, "rougeL_precision": 0.3793149671052253, "rougeL_precision_stderr": 0.0028788724723207175, "rougeL_recall": 0.303084323993645, "rougeL_recall_stderr": 0.0023997981815417927, "rougeLsum_fmeasure": 0.3567272344346471, "rougeLsum_fmeasure_stderr": 0.002273204999670106, "rougeLsum_precision": 0.424766622860286, "rougeLsum_precision_stderr": 0.0031065633020390844, "rougeLsum_recall": 0.34158689328494163, "rougeLsum_recall_stderr": 0.0027234093565780253}}, "2": {"generate_text_restaurant": {"bleu": 13.232352061213327, "bleu_stderr": 0.18438572640282935, "rouge1_fmeasure": 0.46686827804183195, "rouge1_fmeasure_stderr": 0.0021857893913537927, "rouge1_precision": 0.5438295687735817, "rouge1_precision_stderr": 0.0032626249125624544, "rouge1_recall": 0.4519156735724399, "rouge1_recall_stderr": 0.0028471232903033885, "rouge2_fmeasure": 0.22608889723213235, "rouge2_fmeasure_stderr": 0.001981518091728108, "rouge2_precision": 0.2677592832314449, "rouge2_precision_stderr": 0.002678442807946661, "rouge2_recall": 0.21857181845743923, "rouge2_recall_stderr": 0.0021530696594196743, "rougeL_fmeasure": 0.34083378350431404, "rougeL_fmeasure_stderr": 0.0020309168195614307, "rougeL_precision": 0.3988680585181114, "rougeL_precision_stderr": 0.0029405304248634437, "rougeL_recall": 0.3293160518559301, "rougeL_recall_stderr": 0.002411675944122487, "rougeLsum_fmeasure": 0.38531835059376945, "rougeLsum_fmeasure_stderr": 0.0022236074600925494, "rougeLsum_precision": 0.44900069330118875, "rougeLsum_precision_stderr": 0.0031269512646810997, "rougeLsum_recall": 0.3728742942560764, "rougeLsum_recall_stderr": 0.002675120241181924}}, "3": {"generate_text_restaurant": {"bleu": 14.1599321841023, "bleu_stderr": 0.1879116618302546, "rouge1_fmeasure": 0.4695262322349431, "rouge1_fmeasure_stderr": 0.00215490562453037, "rouge1_precision": 0.5316343436240858, "rouge1_precision_stderr": 0.0032625643740183926, "rouge1_recall": 0.4648983433320942, "rouge1_recall_stderr": 0.002828266123213244, "rouge2_fmeasure": 0.23062310394414082, "rouge2_fmeasure_stderr": 0.0019690665088102194, "rouge2_precision": 0.26457242284963084, "rouge2_precision_stderr": 0.0026154624845308966, "rouge2_recall": 0.2286713763984792, "rouge2_recall_stderr": 0.002213558974457314, "rougeL_fmeasure": 0.3421096115443624, "rougeL_fmeasure_stderr": 0.0020310235455138293, "rougeL_precision": 0.3891085104737073, "rougeL_precision_stderr": 0.0029515533104354013, "rougeL_recall": 0.3385179926519356, "rougeL_recall_stderr": 0.002447035400467983, "rougeLsum_fmeasure": 0.3897046712016254, "rougeLsum_fmeasure_stderr": 0.0022104074028312126, "rougeLsum_precision": 0.44153945634327574, "rougeLsum_precision_stderr": 0.003131733329038247, "rougeLsum_recall": 0.3859861563616844, "rougeLsum_recall_stderr": 0.0027050660850819557}}, "4": {"generate_text_restaurant": {"bleu": 14.215875217167579, "bleu_stderr": 0.19854834212398645, "rouge1_fmeasure": 0.46760558865318314, "rouge1_fmeasure_stderr": 0.0021274829390602406, "rouge1_precision": 0.5190910100984744, "rouge1_precision_stderr": 0.003294663292154946, "rouge1_recall": 0.47129632991643877, "rouge1_recall_stderr": 0.002752331164331658, "rouge2_fmeasure": 0.23112566064185652, "rouge2_fmeasure_stderr": 0.001973386702544114, "rouge2_precision": 0.2607371623810947, "rouge2_precision_stderr": 0.0026626721914091273, "rouge2_recall": 0.23271303570323362, "rouge2_recall_stderr": 0.002186914450625737, "rougeL_fmeasure": 0.33922485306684963, "rougeL_fmeasure_stderr": 0.0020379531080847698, "rougeL_precision": 0.37743317581253305, "rougeL_precision_stderr": 0.002922501161012456, "rougeL_recall": 0.3421754841859648, "rougeL_recall_stderr": 0.002448897823883138, "rougeLsum_fmeasure": 0.39088870724203995, "rougeLsum_fmeasure_stderr": 0.0022061435555151025, "rougeLsum_precision": 0.43332497676504134, "rougeLsum_precision_stderr": 0.0031201843719093183, "rougeLsum_recall": 0.39450016226821116, "rougeLsum_recall_stderr": 0.002683555554853958}}, "5": {"generate_text_restaurant": {"bleu": 13.675372357471726, "bleu_stderr": 0.1772679235890945, "rouge1_fmeasure": 0.4652741436608286, "rouge1_fmeasure_stderr": 0.0020856290234426084, "rouge1_precision": 0.5079146856634101, "rouge1_precision_stderr": 0.003244631875951903, "rouge1_recall": 0.4750602535272041, "rouge1_recall_stderr": 0.002707456752563758, "rouge2_fmeasure": 0.22596116871891767, "rouge2_fmeasure_stderr": 0.0019272220902171223, "rouge2_precision": 0.2506185278912072, "rouge2_precision_stderr": 0.0025688729450509744, "rouge2_recall": 0.23020274907523836, "rouge2_recall_stderr": 0.0021319283224229416, "rougeL_fmeasure": 0.3336418614264682, "rougeL_fmeasure_stderr": 0.0020082018536239574, "rougeL_precision": 0.3646830222320307, "rougeL_precision_stderr": 0.002836137970051408, "rougeL_recall": 0.34124704138322626, "rougeL_recall_stderr": 0.002433024945476074, "rougeLsum_fmeasure": 0.38639018088252236, "rougeLsum_fmeasure_stderr": 0.0021588490021418913, "rougeLsum_precision": 0.42108375995240394, "rougeLsum_precision_stderr": 0.003034856921594324, "rougeLsum_recall": 0.3952453063898795, "rougeLsum_recall_stderr": 0.0026571910552197976}}}, "gem_xsum": {"0": {"article_DOC_summary": {"bleu": 1.9965727451782298, "bleu_stderr": 0.15826205801047227, "rouge1_fmeasure": 0.2181226869116415, "rouge1_fmeasure_stderr": 0.0027581474749694035, "rouge1_precision": 0.17780010896090837, "rouge1_precision_stderr": 0.0028657687702784394, "rouge1_recall": 0.33168127958194993, "rouge1_recall_stderr": 0.0043909919411222464, "rouge2_fmeasure": 0.048528921002958546, "rouge2_fmeasure_stderr": 0.0017764487817816764, "rouge2_precision": 0.03931279207892139, "rouge2_precision_stderr": 0.0016581578355807393, "rouge2_recall": 0.07619599508022841, "rouge2_recall_stderr": 0.00272241500352495, "rougeL_fmeasure": 0.16205491808395142, "rougeL_fmeasure_stderr": 0.002184657948901955, "rougeL_precision": 0.13228242420416667, "rougeL_precision_stderr": 0.0023035178337467654, "rougeL_recall": 0.24740150573619668, "rougeL_recall_stderr": 0.003505699991405706, "rougeLsum_fmeasure": 0.16995115866612748, "rougeLsum_fmeasure_stderr": 0.0023209836007670715, "rougeLsum_precision": 0.13792549177526942, "rougeLsum_precision_stderr": 0.002344912834751097, "rougeLsum_recall": 0.26116272332322926, "rougeLsum_recall_stderr": 0.0038687142611478474}}, "1": {"article_DOC_summary": {"bleu": 1.521961099148944, "bleu_stderr": 0.1067162997839333, "rouge1_fmeasure": 0.17785826511919287, "rouge1_fmeasure_stderr": 0.002506168575309281, "rouge1_precision": 0.12623297679712753, "rouge1_precision_stderr": 0.00185031477682142, "rouge1_recall": 0.31355314687479174, "rouge1_recall_stderr": 0.004381874835308543, "rouge2_fmeasure": 0.03812763380493433, "rouge2_fmeasure_stderr": 0.0014499362846337098, "rouge2_precision": 0.02671739102876372, "rouge2_precision_stderr": 0.0010147304084239857, "rouge2_recall": 0.06963018507899452, "rouge2_recall_stderr": 0.002768236684178756, "rougeL_fmeasure": 0.13961978647843165, "rougeL_fmeasure_stderr": 0.0018876284466631298, "rougeL_precision": 0.0989142119051423, "rougeL_precision_stderr": 0.0013791496324926688, "rougeL_recall": 0.24757016935280626, "rougeL_recall_stderr": 0.0034520987132384117, "rougeLsum_fmeasure": 0.1418358500050043, "rougeLsum_fmeasure_stderr": 0.0020742150121420516, "rougeLsum_precision": 0.10042944590263467, "rougeLsum_precision_stderr": 0.0015100489954681905, "rougeLsum_recall": 0.2518445443289288, "rougeLsum_recall_stderr": 0.003780328500383181}}, "2": {"article_DOC_summary": {"bleu": 1.5280857149419538, "bleu_stderr": 0.07885108475340596, "rouge1_fmeasure": 0.17992305299553213, "rouge1_fmeasure_stderr": 0.002471474032703446, "rouge1_precision": 0.12776888363608563, "rouge1_precision_stderr": 0.0018271531287357235, "rouge1_recall": 0.31621003695806416, "rouge1_recall_stderr": 0.004292592593741099, "rouge2_fmeasure": 0.038746331277995295, "rouge2_fmeasure_stderr": 0.001439750042341812, "rouge2_precision": 0.02713599956564803, "rouge2_precision_stderr": 0.0010066515368428789, "rouge2_recall": 0.07048237066918879, "rouge2_recall_stderr": 0.0027207468576705084, "rougeL_fmeasure": 0.14290468633219328, "rougeL_fmeasure_stderr": 0.0019087949950632504, "rougeL_precision": 0.10123566070632635, "rougeL_precision_stderr": 0.0013895764877661831, "rougeL_recall": 0.2528390510389675, "rougeL_recall_stderr": 0.003483747346972295, "rougeLsum_fmeasure": 0.14276376154853065, "rougeLsum_fmeasure_stderr": 0.002040901548342001, "rougeLsum_precision": 0.10104760152172992, "rougeLsum_precision_stderr": 0.0014792769919128913, "rougeLsum_recall": 0.2530463368650048, "rougeLsum_recall_stderr": 0.0037161332717751}}, "3": {"article_DOC_summary": {"bleu": 1.521537278708307, "bleu_stderr": 0.1340390241992026, "rouge1_fmeasure": 0.16685520709327625, "rouge1_fmeasure_stderr": 0.002665570155443094, "rouge1_precision": 0.12121822408668065, "rouge1_precision_stderr": 0.0020739133661264075, "rouge1_recall": 0.287891057927081, "rouge1_recall_stderr": 0.004579134322254905, "rouge2_fmeasure": 0.03502142308268661, "rouge2_fmeasure_stderr": 0.001453833565879767, "rouge2_precision": 0.024946562796427662, "rouge2_precision_stderr": 0.0010295220175533656, "rouge2_recall": 0.062229435333035196, "rouge2_recall_stderr": 0.0027102677143777706, "rougeL_fmeasure": 0.13219464959176125, "rougeL_fmeasure_stderr": 0.002089625494358884, "rougeL_precision": 0.09584883568666924, "rougeL_precision_stderr": 0.0016019599062301714, "rougeL_recall": 0.22935087983395927, "rougeL_recall_stderr": 0.003723896150091747, "rougeLsum_fmeasure": 0.13360679199458778, "rougeLsum_fmeasure_stderr": 0.0022032590659256113, "rougeLsum_precision": 0.09677327103730465, "rougeLsum_precision_stderr": 0.0016860407775182488, "rougeLsum_recall": 0.23249987999606497, "rougeLsum_recall_stderr": 0.003931934403157173}}, "4": {"article_DOC_summary": {"bleu": 0.629879023989858, "bleu_stderr": 0.12544962320083983, "rouge1_fmeasure": 0.04534730746066439, "rouge1_fmeasure_stderr": 0.002611229049263828, "rouge1_precision": 0.038078096723767996, "rouge1_precision_stderr": 0.0023781047408131164, "rouge1_recall": 0.07110840872162687, "rouge1_recall_stderr": 0.0041655460986093325, "rouge2_fmeasure": 0.009137318621937963, "rouge2_fmeasure_stderr": 0.0009714552620996167, "rouge2_precision": 0.00755130939213845, "rouge2_precision_stderr": 0.0009407309816817791, "rouge2_recall": 0.01456763376419491, "rouge2_recall_stderr": 0.0015059193465168199, "rougeL_fmeasure": 0.036178777224856525, "rougeL_fmeasure_stderr": 0.0020901567682781942, "rougeL_precision": 0.030895255217096195, "rougeL_precision_stderr": 0.002026498228282476, "rougeL_recall": 0.05673417944538178, "rougeL_recall_stderr": 0.0033250538537188097, "rougeLsum_fmeasure": 0.03747044675977351, "rougeLsum_fmeasure_stderr": 0.002195978615372179, "rougeLsum_precision": 0.03193887181863606, "rougeLsum_precision_stderr": 0.002103908155038245, "rougeLsum_recall": 0.05872079534060702, "rougeLsum_recall_stderr": 0.0034877968907706214}}, "5": {"article_DOC_summary": {"bleu": 8.029951400668467e-38, "bleu_stderr": 8.999389473215882e-33, "rouge1_fmeasure": 0.0024480546534426002, "rouge1_fmeasure_stderr": 0.0006663143862102796, "rouge1_precision": 0.0028153785061314713, "rouge1_precision_stderr": 0.0008109014775672004, "rouge1_recall": 0.0022397022323243287, "rouge1_recall_stderr": 0.0005923742999126791, "rouge2_fmeasure": 0.00025593065551168283, "rouge2_fmeasure_stderr": 0.00014085048380669117, "rouge2_precision": 0.00032960010762452495, "rouge2_precision_stderr": 0.0001942158416689748, "rouge2_recall": 0.00021523288032721994, "rouge2_recall_stderr": 0.00011457292554383501, "rougeL_fmeasure": 0.0018728301034077845, "rougeL_fmeasure_stderr": 0.0005184193716142723, "rougeL_precision": 0.0021686356526300445, "rougeL_precision_stderr": 0.0006433045803199352, "rougeL_recall": 0.00171133818409571, "rougeL_recall_stderr": 0.0004578910681243736, "rougeLsum_fmeasure": 0.0021046719353290323, "rougeLsum_fmeasure_stderr": 0.0005793875805849997, "rougeLsum_precision": 0.0024191989997527706, "rougeLsum_precision_stderr": 0.0007056629627390068, "rougeLsum_recall": 0.0019291072387565224, "rougeLsum_recall_stderr": 0.0005158196897264791}}}}