{"GEM/web_nlg_en": {"0": {"PALM_prompt": {"bleu": 0.22823240153546337, "bleu_stderr": 0.019801328507653555, "rouge1_fmeasure": 0.09278812248464041, "rouge1_fmeasure_stderr": 0.0019451208940882462, "rouge1_precision": 0.06488132852178101, "rouge1_precision_stderr": 0.0019983200287404636, "rouge1_recall": 0.2694613973506335, "rouge1_recall_stderr": 0.004689917452744887, "rouge2_fmeasure": 0.043062923489258886, "rouge2_fmeasure_stderr": 0.0011955223112274191, "rouge2_precision": 0.03049969544111268, "rouge2_precision_stderr": 0.0014195164318779048, "rouge2_recall": 0.12616507029445545, "rouge2_recall_stderr": 0.003145765839594005, "rougeL_fmeasure": 0.08987712765401562, "rougeL_fmeasure_stderr": 0.0018570238876570958, "rougeL_precision": 0.06277531818573256, "rougeL_precision_stderr": 0.0019255483147167943, "rougeL_recall": 0.26204267960081423, "rougeL_recall_stderr": 0.004572745714241958, "rougeLsum_fmeasure": 0.08897530462885096, "rougeLsum_fmeasure_stderr": 0.0018637844480694857, "rougeLsum_precision": 0.062396574817472954, "rougeLsum_precision_stderr": 0.001949378798188583, "rougeLsum_recall": 0.2575118059057066, "rougeLsum_recall_stderr": 0.004447426802462746}}, "1": {"PALM_prompt": {"bleu": 0.3661841801825079, "bleu_stderr": 0.02563149821206728, "rouge1_fmeasure": 0.10942376581457419, "rouge1_fmeasure_stderr": 0.0018798780952399333, "rouge1_precision": 0.07083770111936527, "rouge1_precision_stderr": 0.0014702310183376884, "rouge1_recall": 0.3470278622959199, "rouge1_recall_stderr": 0.0049553242440100185, "rouge2_fmeasure": 0.05003844184852099, "rouge2_fmeasure_stderr": 0.0011747503323877196, "rouge2_precision": 0.03224100861794047, "rouge2_precision_stderr": 0.0008797529232351612, "rouge2_recall": 0.1629607516749881, "rouge2_recall_stderr": 0.003471799684879311, "rougeL_fmeasure": 0.10321985245908673, "rougeL_fmeasure_stderr": 0.0017162487713120534, "rougeL_precision": 0.06675253029318402, "rougeL_precision_stderr": 0.0013359347871140462, "rougeL_recall": 0.3264833708205708, "rougeL_recall_stderr": 0.004550418676968034, "rougeLsum_fmeasure": 0.10443938348190776, "rougeLsum_fmeasure_stderr": 0.0017943553372490961, "rougeLsum_precision": 0.06768091521368075, "rougeLsum_precision_stderr": 0.0014117297702072977, "rougeLsum_recall": 0.32967316098048005, "rougeLsum_recall_stderr": 0.004616088914018551}}, "2": {"PALM_prompt": {"bleu": 0.4407900141469654, "bleu_stderr": 0.0323167010621195, "rouge1_fmeasure": 0.11440451965537006, "rouge1_fmeasure_stderr": 0.0018124345601119877, "rouge1_precision": 0.07367342181261477, "rouge1_precision_stderr": 0.0014829437502766741, "rouge1_recall": 0.3719044219842431, "rouge1_recall_stderr": 0.00477089503485067, "rouge2_fmeasure": 0.052510412804003204, "rouge2_fmeasure_stderr": 0.001161074783078678, "rouge2_precision": 0.03399629764627388, "rouge2_precision_stderr": 0.0009924732443245534, "rouge2_recall": 0.17886553819187756, "rouge2_recall_stderr": 0.003495523044565052, "rougeL_fmeasure": 0.1081021771197844, "rougeL_fmeasure_stderr": 0.0016842278535025275, "rougeL_precision": 0.06963671261885444, "rougeL_precision_stderr": 0.001383680359402878, "rougeL_recall": 0.3486950741986897, "rougeL_recall_stderr": 0.0043656658470662135, "rougeLsum_fmeasure": 0.10922703731482176, "rougeLsum_fmeasure_stderr": 0.0017377919109765759, "rougeLsum_precision": 0.07041609903242399, "rougeLsum_precision_stderr": 0.0014339871134255062, "rougeLsum_recall": 0.3537894575591342, "rougeLsum_recall_stderr": 0.004485079469708994}}, "3": {"PALM_prompt": {"bleu": 0.4466003889413579, "bleu_stderr": 0.029566651496688107, "rouge1_fmeasure": 0.11485365257915954, "rouge1_fmeasure_stderr": 0.0017656536007023573, "rouge1_precision": 0.07299482462643084, "rouge1_precision_stderr": 0.0013027934781524187, "rouge1_recall": 0.3766877383768923, "rouge1_recall_stderr": 0.004855020535693255, "rouge2_fmeasure": 0.05249781726283433, "rouge2_fmeasure_stderr": 0.0011107151159447624, "rouge2_precision": 0.03319871477020421, "rouge2_precision_stderr": 0.0007814167138878587, "rouge2_recall": 0.18122070914268562, "rouge2_recall_stderr": 0.0035476324822892387, "rougeL_fmeasure": 0.10790582240037933, "rougeL_fmeasure_stderr": 0.0016126105841386515, "rougeL_precision": 0.06853966061247058, "rougeL_precision_stderr": 0.001173030755309074, "rougeL_recall": 0.35045572978503337, "rougeL_recall_stderr": 0.004340732169898299, "rougeLsum_fmeasure": 0.1093595107745124, "rougeLsum_fmeasure_stderr": 0.0016743636963225566, "rougeLsum_precision": 0.0695306625372233, "rougeLsum_precision_stderr": 0.0012361693266576337, "rougeLsum_recall": 0.3569668908645508, "rougeLsum_recall_stderr": 0.004507395219482628}}, "4": {"PALM_prompt": {"bleu": 0.487050312474933, "bleu_stderr": 0.03607205735455871, "rouge1_fmeasure": 0.11648487474193464, "rouge1_fmeasure_stderr": 0.0017721469641833675, "rouge1_precision": 0.07396468654034809, "rouge1_precision_stderr": 0.001288920146199216, "rouge1_recall": 0.3813221117629107, "rouge1_recall_stderr": 0.004861483986307508, "rouge2_fmeasure": 0.05356639642925066, "rouge2_fmeasure_stderr": 0.0011294372559632658, "rouge2_precision": 0.03382639123113972, "rouge2_precision_stderr": 0.0007889725664873102, "rouge2_recall": 0.18653704114196332, "rouge2_recall_stderr": 0.0036151812865906443, "rougeL_fmeasure": 0.10916764420003369, "rougeL_fmeasure_stderr": 0.001618727645899262, "rougeL_precision": 0.06930980722047882, "rougeL_precision_stderr": 0.0011715656957547833, "rougeL_recall": 0.3554813029943238, "rougeL_recall_stderr": 0.004410895398774957, "rougeLsum_fmeasure": 0.11097231310945427, "rougeLsum_fmeasure_stderr": 0.001686654148524125, "rougeLsum_precision": 0.07051571464958685, "rougeLsum_precision_stderr": 0.0012288916026023105, "rougeLsum_recall": 0.3623967921619407, "rougeLsum_recall_stderr": 0.004563172681319971}}, "5": {"PALM_prompt": {"bleu": 0.5397098988068925, "bleu_stderr": 0.036026287961208193, "rouge1_fmeasure": 0.11701396324144628, "rouge1_fmeasure_stderr": 0.0017917711999714296, "rouge1_precision": 0.07425114855720495, "rouge1_precision_stderr": 0.0013099248484394475, "rouge1_recall": 0.3830995799564378, "rouge1_recall_stderr": 0.00489237854555699, "rouge2_fmeasure": 0.053747641849556244, "rouge2_fmeasure_stderr": 0.0011442658690604846, "rouge2_precision": 0.03392002961701272, "rouge2_precision_stderr": 0.0008050168112872793, "rouge2_recall": 0.18691540396802492, "rouge2_recall_stderr": 0.0035729305211479787, "rougeL_fmeasure": 0.10873350954319214, "rougeL_fmeasure_stderr": 0.001623917279486683, "rougeL_precision": 0.06897611448091759, "rougeL_precision_stderr": 0.0011802923800557673, "rougeL_recall": 0.35391589444854826, "rougeL_recall_stderr": 0.004352932319637079, "rougeLsum_fmeasure": 0.11104846189066431, "rougeLsum_fmeasure_stderr": 0.0016911151955166914, "rougeLsum_precision": 0.07051724516851579, "rougeLsum_precision_stderr": 0.0012374326489376225, "rougeLsum_recall": 0.36206603074240407, "rougeLsum_recall_stderr": 0.004520194020448341}}}, "GEM/wiki_lingua_en": {"0": {"tldr_en": {"bleu": 1.448281189434789, "bleu_stderr": 0.043687187905172974, "rouge1_fmeasure": 0.17597234365678907, "rouge1_fmeasure_stderr": 0.0018425883141842628, "rouge1_precision": 0.15008607008803437, "rouge1_precision_stderr": 0.0018601006191885032, "rouge1_recall": 0.2557790788700999, "rouge1_recall_stderr": 0.0026277056136050623, "rouge2_fmeasure": 0.03605723207630101, "rouge2_fmeasure_stderr": 0.0008357986241834882, "rouge2_precision": 0.030323067859554097, "rouge2_precision_stderr": 0.0007317604807993408, "rouge2_recall": 0.05443329398449302, "rouge2_recall_stderr": 0.00141532094214201, "rougeL_fmeasure": 0.1423375418286688, "rougeL_fmeasure_stderr": 0.0013578084929713739, "rougeL_precision": 0.12015006900667996, "rougeL_precision_stderr": 0.0013538934502534572, "rougeL_recall": 0.2114978327363309, "rougeL_recall_stderr": 0.002161888757192885, "rougeLsum_fmeasure": 0.16018030489449112, "rougeLsum_fmeasure_stderr": 0.001662237048905438, "rougeLsum_precision": 0.13635035795299258, "rougeLsum_precision_stderr": 0.0016762285015091921, "rougeLsum_recall": 0.23411616572646593, "rougeLsum_recall_stderr": 0.0024292424381029474}}, "1": {"tldr_en": {"bleu": 2.4771863151121267, "bleu_stderr": 0.06776329006842716, "rouge1_fmeasure": 0.20613079171954835, "rouge1_fmeasure_stderr": 0.00198790447206624, "rouge1_precision": 0.1799251922119011, "rouge1_precision_stderr": 0.0021296048274116225, "rouge1_recall": 0.29307731722151764, "rouge1_recall_stderr": 0.0028769505493505395, "rouge2_fmeasure": 0.05061691983629231, "rouge2_fmeasure_stderr": 0.0010260625512296302, "rouge2_precision": 0.04408218261083662, "rouge2_precision_stderr": 0.0009705977120723668, "rouge2_recall": 0.07439629666386674, "rouge2_recall_stderr": 0.0017087707910905313, "rougeL_fmeasure": 0.15685595746582018, "rougeL_fmeasure_stderr": 0.0013926553308231432, "rougeL_precision": 0.13570179337405314, "rougeL_precision_stderr": 0.001482289478470975, "rougeL_recall": 0.22754064537842192, "rougeL_recall_stderr": 0.0022783134373401074, "rougeLsum_fmeasure": 0.1915120511455412, "rougeLsum_fmeasure_stderr": 0.0018508952358904137, "rougeLsum_precision": 0.16695539260829864, "rougeLsum_precision_stderr": 0.0019794474426647083, "rougeLsum_recall": 0.27322645374414084, "rougeLsum_recall_stderr": 0.0027198090833989628}}, "2": {"tldr_en": {"bleu": 2.5971654922191916, "bleu_stderr": 0.07231754735552207, "rouge1_fmeasure": 0.20579252650321492, "rouge1_fmeasure_stderr": 0.0019347999276799514, "rouge1_precision": 0.18193541117316303, "rouge1_precision_stderr": 0.002129022757679657, "rouge1_recall": 0.2873271136787168, "rouge1_recall_stderr": 0.0027757324346008626, "rouge2_fmeasure": 0.052038438662649955, "rouge2_fmeasure_stderr": 0.001033768052074922, "rouge2_precision": 0.04585562124835071, "rouge2_precision_stderr": 0.000987613878134528, "rouge2_recall": 0.07485086144628574, "rouge2_recall_stderr": 0.0016500579154340113, "rougeL_fmeasure": 0.16233798956689643, "rougeL_fmeasure_stderr": 0.0014285375845216534, "rougeL_precision": 0.14212357929533947, "rougeL_precision_stderr": 0.001534668369261251, "rougeL_recall": 0.23092536679601577, "rougeL_recall_stderr": 0.0023083235968400194, "rougeLsum_fmeasure": 0.19060273378557263, "rougeLsum_fmeasure_stderr": 0.0017906790063786202, "rougeLsum_precision": 0.16802587348839354, "rougeLsum_precision_stderr": 0.0019533651000337255, "rougeLsum_recall": 0.26735252969355866, "rougeLsum_recall_stderr": 0.002625978487494257}}, "3": {"tldr_en": {"bleu": 2.6344153317715175, "bleu_stderr": 0.08503440436205431, "rouge1_fmeasure": 0.1743109316643425, "rouge1_fmeasure_stderr": 0.002206836232239465, "rouge1_precision": 0.16050894171948427, "rouge1_precision_stderr": 0.0024100514703960206, "rouge1_recall": 0.24283730708449638, "rouge1_recall_stderr": 0.0032126308751215795, "rouge2_fmeasure": 0.04434221317654373, "rouge2_fmeasure_stderr": 0.0010212597712348022, "rouge2_precision": 0.040363396793793804, "rouge2_precision_stderr": 0.0010438141177973716, "rouge2_recall": 0.0642798756210113, "rouge2_recall_stderr": 0.0016775914985579477, "rougeL_fmeasure": 0.13765815446156848, "rougeL_fmeasure_stderr": 0.001669109955926649, "rougeL_precision": 0.1263857167912172, "rougeL_precision_stderr": 0.0018569367920588345, "rougeL_recall": 0.19505495367647274, "rougeL_recall_stderr": 0.002639115007673249, "rougeLsum_fmeasure": 0.1625350254941212, "rougeLsum_fmeasure_stderr": 0.0020529206650028065, "rougeLsum_precision": 0.14962894160355625, "rougeLsum_precision_stderr": 0.0022515883799491287, "rougeLsum_recall": 0.2273490498335059, "rougeLsum_recall_stderr": 0.0030400460462734805}}, "4": {"tldr_en": {"bleu": 0.6935784123394136, "bleu_stderr": 0.037117118101581, "rouge1_fmeasure": 0.058334104546958664, "rouge1_fmeasure_stderr": 0.0019424473260893508, "rouge1_precision": 0.05430645822023474, "rouge1_precision_stderr": 0.0019806913087909678, "rouge1_recall": 0.08525381293697526, "rouge1_recall_stderr": 0.0029115181219816705, "rouge2_fmeasure": 0.014683899167593325, "rouge2_fmeasure_stderr": 0.0006904611688238195, "rouge2_precision": 0.013305245187707022, "rouge2_precision_stderr": 0.0006795482619014736, "rouge2_recall": 0.023040441919977284, "rouge2_recall_stderr": 0.0012094550673333144, "rougeL_fmeasure": 0.0453971126653514, "rougeL_fmeasure_stderr": 0.0014854698835850076, "rougeL_precision": 0.04223912463330309, "rougeL_precision_stderr": 0.0015456523042882138, "rougeL_recall": 0.06789064162959188, "rougeL_recall_stderr": 0.002360717874503064, "rougeLsum_fmeasure": 0.054378661639440586, "rougeLsum_fmeasure_stderr": 0.0018102104175546382, "rougeLsum_precision": 0.050625780842237005, "rougeLsum_precision_stderr": 0.001851652248586665, "rougeLsum_recall": 0.0798186917428021, "rougeLsum_recall_stderr": 0.0027367896999417234}}, "5": {"tldr_en": {"bleu": 4.942519396132508e-06, "bleu_stderr": 7.900655099204328e-06, "rouge1_fmeasure": 0.00973539490830721, "rouge1_fmeasure_stderr": 0.0008844226509773655, "rouge1_precision": 0.009892829148004599, "rouge1_precision_stderr": 0.0009735613257064788, "rouge1_recall": 0.014431890646129451, "rouge1_recall_stderr": 0.0013569083898125143, "rouge2_fmeasure": 0.0025645649630508895, "rouge2_fmeasure_stderr": 0.00032276345763389736, "rouge2_precision": 0.00252421633933382, "rouge2_precision_stderr": 0.000377998208069803, "rouge2_recall": 0.004045696439072071, "rouge2_recall_stderr": 0.0005345734135970881, "rougeL_fmeasure": 0.007755952948994762, "rougeL_fmeasure_stderr": 0.0007020625911996639, "rougeL_precision": 0.007913179064992113, "rougeL_precision_stderr": 0.0007973074868105818, "rougeL_recall": 0.011792588225184406, "rougeL_recall_stderr": 0.0011400182766348275, "rougeLsum_fmeasure": 0.009070666142968765, "rougeLsum_fmeasure_stderr": 0.0008231845717527685, "rougeLsum_precision": 0.00914536574048143, "rougeLsum_precision_stderr": 0.0008957548358299954, "rougeLsum_recall": 0.013493539148258968, "rougeLsum_recall_stderr": 0.0012759343183650173}}}, "e2e_nlg_cleaned": {"0": {"generate_text_restaurant": {"bleu": 2.1930690971863127, "bleu_stderr": 0.056687850782170965, "rouge1_fmeasure": 0.1878406531881343, "rouge1_fmeasure_stderr": 0.0012989451234580226, "rouge1_precision": 0.1429481399444759, "rouge1_precision_stderr": 0.0011565979029840442, "rouge1_recall": 0.29077511497038705, "rouge1_recall_stderr": 0.0018252280720869973, "rouge2_fmeasure": 0.04470849859270079, "rouge2_fmeasure_stderr": 0.0009406338502407552, "rouge2_precision": 0.03387362544764098, "rouge2_precision_stderr": 0.0007280854317065066, "rouge2_recall": 0.06980838714554283, "rouge2_recall_stderr": 0.0014665741377635003, "rougeL_fmeasure": 0.18167840406484337, "rougeL_fmeasure_stderr": 0.0011691157929579112, "rougeL_precision": 0.1379239272755364, "rougeL_precision_stderr": 0.0010249937289556548, "rougeL_recall": 0.282055407082142, "rougeL_recall_stderr": 0.0016756844442888477, "rougeLsum_fmeasure": 0.14684587587101583, "rougeLsum_fmeasure_stderr": 0.0012655964375177, "rougeLsum_precision": 0.11190322389127284, "rougeLsum_precision_stderr": 0.0010864937044464242, "rougeLsum_recall": 0.2269219536298954, "rougeLsum_recall_stderr": 0.0018279163341351945}}, "1": {"generate_text_restaurant": {"bleu": 9.418632832486113, "bleu_stderr": 0.15892088683907937, "rouge1_fmeasure": 0.3954201252360898, "rouge1_fmeasure_stderr": 0.0021957704553682567, "rouge1_precision": 0.47163188984542315, "rouge1_precision_stderr": 0.0032775365220683987, "rouge1_recall": 0.38270380914695573, "rouge1_recall_stderr": 0.0026942942607581883, "rouge2_fmeasure": 0.1690464759571803, "rouge2_fmeasure_stderr": 0.001791849078574847, "rouge2_precision": 0.20643841115958284, "rouge2_precision_stderr": 0.002452864241411027, "rouge2_recall": 0.16255723484968757, "rouge2_recall_stderr": 0.0018974959638824289, "rougeL_fmeasure": 0.2918320542459967, "rougeL_fmeasure_stderr": 0.0018703627623678988, "rougeL_precision": 0.3500552455605647, "rougeL_precision_stderr": 0.002819656762714209, "rougeL_recall": 0.2825970007466028, "rougeL_recall_stderr": 0.0022176737240157613, "rougeLsum_fmeasure": 0.326122364264301, "rougeLsum_fmeasure_stderr": 0.002124773392271949, "rougeLsum_precision": 0.3894346048213154, "rougeLsum_precision_stderr": 0.0030440975161392437, "rougeLsum_recall": 0.3156932402715717, "rougeLsum_recall_stderr": 0.0024964558829624114}}, "2": {"generate_text_restaurant": {"bleu": 11.157046042091494, "bleu_stderr": 0.22230912389093138, "rouge1_fmeasure": 0.41600816576099753, "rouge1_fmeasure_stderr": 0.002175752395461552, "rouge1_precision": 0.49125485302264194, "rouge1_precision_stderr": 0.003436345592117948, "rouge1_recall": 0.40692976602128633, "rouge1_recall_stderr": 0.0026701582120549137, "rouge2_fmeasure": 0.19315023086977673, "rouge2_fmeasure_stderr": 0.0018551400655270958, "rouge2_precision": 0.23319168418773684, "rouge2_precision_stderr": 0.0026655336361967345, "rouge2_recall": 0.18866131101543013, "rouge2_recall_stderr": 0.0020054934856301864, "rougeL_fmeasure": 0.31720505793101433, "rougeL_fmeasure_stderr": 0.0019047277615318289, "rougeL_precision": 0.37587753599102547, "rougeL_precision_stderr": 0.0030096046402435773, "rougeL_recall": 0.31127927557367574, "rougeL_recall_stderr": 0.0022995330104551115, "rougeLsum_fmeasure": 0.35124044195594184, "rougeLsum_fmeasure_stderr": 0.0021467843216000176, "rougeLsum_precision": 0.4153979997965865, "rougeLsum_precision_stderr": 0.003260911582709945, "rougeLsum_recall": 0.34370226391464437, "rougeLsum_recall_stderr": 0.0025225743998368595}}, "3": {"generate_text_restaurant": {"bleu": 11.85176645344793, "bleu_stderr": 0.2111782087019858, "rouge1_fmeasure": 0.41943531430791064, "rouge1_fmeasure_stderr": 0.0021527237387675337, "rouge1_precision": 0.491635847758295, "rouge1_precision_stderr": 0.0033990781081896203, "rouge1_recall": 0.4083984861443366, "rouge1_recall_stderr": 0.002572988732153086, "rouge2_fmeasure": 0.19799186403146818, "rouge2_fmeasure_stderr": 0.0018867520137521249, "rouge2_precision": 0.23811538412663988, "rouge2_precision_stderr": 0.0027210673636900535, "rouge2_recall": 0.19191761966553353, "rouge2_recall_stderr": 0.0019828033145899418, "rougeL_fmeasure": 0.3222366071758124, "rougeL_fmeasure_stderr": 0.0019270427825323075, "rougeL_precision": 0.3791841332466743, "rougeL_precision_stderr": 0.0030188679062324066, "rougeL_recall": 0.31428033033093916, "rougeL_recall_stderr": 0.0022404895896611845, "rougeLsum_fmeasure": 0.35705938021982625, "rougeLsum_fmeasure_stderr": 0.002152684592453826, "rougeLsum_precision": 0.41907603224901663, "rougeLsum_precision_stderr": 0.003233518240730724, "rougeLsum_recall": 0.34758989478390145, "rougeLsum_recall_stderr": 0.002468301879990052}}, "4": {"generate_text_restaurant": {"bleu": 12.213594934959904, "bleu_stderr": 0.17055645700844593, "rouge1_fmeasure": 0.42203788611472176, "rouge1_fmeasure_stderr": 0.002140927059483002, "rouge1_precision": 0.49389784953566224, "rouge1_precision_stderr": 0.003360677973991826, "rouge1_recall": 0.4084911763885813, "rouge1_recall_stderr": 0.0025681818250945453, "rouge2_fmeasure": 0.20046771550907586, "rouge2_fmeasure_stderr": 0.001900500158864706, "rouge2_precision": 0.24027533133594514, "rouge2_precision_stderr": 0.002717518145210136, "rouge2_recall": 0.1931689047942646, "rouge2_recall_stderr": 0.0019976751697372373, "rougeL_fmeasure": 0.3250827572900466, "rougeL_fmeasure_stderr": 0.0019242346482233237, "rougeL_precision": 0.3818307774217645, "rougeL_precision_stderr": 0.002997133945547209, "rougeL_recall": 0.314926852332832, "rougeL_recall_stderr": 0.00222944689068758, "rougeLsum_fmeasure": 0.36123637490493443, "rougeLsum_fmeasure_stderr": 0.0021695678925136796, "rougeLsum_precision": 0.4230876627442121, "rougeLsum_precision_stderr": 0.003228575618923689, "rougeLsum_recall": 0.3496643183193398, "rougeLsum_recall_stderr": 0.002491187104271206}}, "5": {"generate_text_restaurant": {"bleu": 12.236709448372414, "bleu_stderr": 0.14843010141725657, "rouge1_fmeasure": 0.4253127800982302, "rouge1_fmeasure_stderr": 0.0020707929304555938, "rouge1_precision": 0.4997594688814884, "rouge1_precision_stderr": 0.003305753668973342, "rouge1_recall": 0.4090412035280527, "rouge1_recall_stderr": 0.00251586811815331, "rouge2_fmeasure": 0.20204503717178296, "rouge2_fmeasure_stderr": 0.0018444156267695426, "rouge2_precision": 0.24277805797177893, "rouge2_precision_stderr": 0.0026344699743377476, "rouge2_recall": 0.19353472778536238, "rouge2_recall_stderr": 0.0019368139370174791, "rougeL_fmeasure": 0.3273140656892835, "rougeL_fmeasure_stderr": 0.0019260484275470976, "rougeL_precision": 0.3858614644050571, "rougeL_precision_stderr": 0.0029726208789718437, "rougeL_recall": 0.3148985662207896, "rougeL_recall_stderr": 0.002219870397709864, "rougeLsum_fmeasure": 0.36408266488946983, "rougeLsum_fmeasure_stderr": 0.0021286587722579102, "rougeLsum_precision": 0.4284452395301663, "rougeLsum_precision_stderr": 0.003202306041199407, "rougeLsum_recall": 0.34976945417244226, "rougeLsum_recall_stderr": 0.0024232597648873983}}}, "gem_xsum": {"0": {"article_DOC_summary": {"bleu": 1.988238441001108, "bleu_stderr": 0.10949772127470961, "rouge1_fmeasure": 0.20686542088274673, "rouge1_fmeasure_stderr": 0.0024902036554014517, "rouge1_precision": 0.15302415683116935, "rouge1_precision_stderr": 0.0019851919515352376, "rouge1_recall": 0.3456886390551113, "rouge1_recall_stderr": 0.004315559637897738, "rouge2_fmeasure": 0.04696069247147477, "rouge2_fmeasure_stderr": 0.0015159747704938896, "rouge2_precision": 0.034018860231617355, "rouge2_precision_stderr": 0.001109162098832389, "rouge2_recall": 0.08143980891307401, "rouge2_recall_stderr": 0.002687566610952875, "rougeL_fmeasure": 0.15803246501095908, "rougeL_fmeasure_stderr": 0.001921548169434307, "rougeL_precision": 0.11681806758450688, "rougeL_precision_stderr": 0.0015393348907235753, "rougeL_recall": 0.2653922138123509, "rougeL_recall_stderr": 0.0034550152868841446, "rougeLsum_fmeasure": 0.16176874488861362, "rougeLsum_fmeasure_stderr": 0.0021510210289138135, "rougeLsum_precision": 0.11940647407681726, "rougeLsum_precision_stderr": 0.0016788400209633819, "rougeLsum_recall": 0.27201835686506154, "rougeLsum_recall_stderr": 0.003841749314846245}}, "1": {"article_DOC_summary": {"bleu": 1.5909474225090259, "bleu_stderr": 0.08800468492254938, "rouge1_fmeasure": 0.18507867023037966, "rouge1_fmeasure_stderr": 0.0025273674673725126, "rouge1_precision": 0.13152298566138992, "rouge1_precision_stderr": 0.0018868845425239439, "rouge1_recall": 0.3254583697191521, "rouge1_recall_stderr": 0.004322661638768359, "rouge2_fmeasure": 0.0380992656895211, "rouge2_fmeasure_stderr": 0.0014717030228569784, "rouge2_precision": 0.02689834498641723, "rouge2_precision_stderr": 0.0010461133533795838, "rouge2_recall": 0.06825421680606394, "rouge2_recall_stderr": 0.002680033168291131, "rougeL_fmeasure": 0.14309819474429272, "rougeL_fmeasure_stderr": 0.0018603866545710576, "rougeL_precision": 0.10149961917396043, "rougeL_precision_stderr": 0.00137753127127783, "rougeL_recall": 0.2532452910717512, "rougeL_recall_stderr": 0.003347172355658309, "rougeLsum_fmeasure": 0.14818866993420235, "rougeLsum_fmeasure_stderr": 0.002096775864782495, "rougeLsum_precision": 0.10503370198820076, "rougeLsum_precision_stderr": 0.001543510074115588, "rougeLsum_recall": 0.26248948719670867, "rougeLsum_recall_stderr": 0.0037288758856769653}}, "2": {"article_DOC_summary": {"bleu": 1.6356065306879652, "bleu_stderr": 0.08830570761410386, "rouge1_fmeasure": 0.19218962833273628, "rouge1_fmeasure_stderr": 0.0024770217525976845, "rouge1_precision": 0.13666091199269473, "rouge1_precision_stderr": 0.0018515926312016866, "rouge1_recall": 0.33730135278754275, "rouge1_recall_stderr": 0.00425282063617627, "rouge2_fmeasure": 0.04236560512098692, "rouge2_fmeasure_stderr": 0.0014536675075888475, "rouge2_precision": 0.029820018955821724, "rouge2_precision_stderr": 0.0010279167305570138, "rouge2_recall": 0.07638292429540472, "rouge2_recall_stderr": 0.0026839104282915466, "rougeL_fmeasure": 0.1480568822982458, "rougeL_fmeasure_stderr": 0.001849879468332256, "rougeL_precision": 0.10503833134735464, "rougeL_precision_stderr": 0.0013653085071660164, "rougeL_recall": 0.261752589120252, "rougeL_recall_stderr": 0.003367463350710988, "rougeLsum_fmeasure": 0.1527273124518781, "rougeLsum_fmeasure_stderr": 0.0020547393393318906, "rougeLsum_precision": 0.10828638412884824, "rougeLsum_precision_stderr": 0.0015066731606435022, "rougeLsum_recall": 0.2701647127318581, "rougeLsum_recall_stderr": 0.003716055569742923}}, "3": {"article_DOC_summary": {"bleu": 1.686714514186135, "bleu_stderr": 0.05743658327131587, "rouge1_fmeasure": 0.1867578685619972, "rouge1_fmeasure_stderr": 0.0027076829707336327, "rouge1_precision": 0.13506962844381415, "rouge1_precision_stderr": 0.002067491453716875, "rouge1_recall": 0.3234728739069624, "rouge1_recall_stderr": 0.004727722874229317, "rouge2_fmeasure": 0.04083587951791368, "rouge2_fmeasure_stderr": 0.0014903605347383073, "rouge2_precision": 0.028931791862333082, "rouge2_precision_stderr": 0.0010588495462508073, "rouge2_recall": 0.07274733136509248, "rouge2_recall_stderr": 0.0027548263183176493, "rougeL_fmeasure": 0.14341449152788618, "rougeL_fmeasure_stderr": 0.0020607906605954966, "rougeL_precision": 0.10368955828025853, "rougeL_precision_stderr": 0.0015784859184918452, "rougeL_recall": 0.24943189152228584, "rougeL_recall_stderr": 0.0037105916710632896, "rougeLsum_fmeasure": 0.1474850025435713, "rougeLsum_fmeasure_stderr": 0.0022564487363751556, "rougeLsum_precision": 0.10646045098053993, "rougeLsum_precision_stderr": 0.0017003493427749877, "rougeLsum_recall": 0.2568065885506006, "rougeLsum_recall_stderr": 0.004046522118014673}}, "4": {"article_DOC_summary": {"bleu": 0.8129834334474599, "bleu_stderr": 0.15535127400795215, "rouge1_fmeasure": 0.05229837627979885, "rouge1_fmeasure_stderr": 0.0028280084619077004, "rouge1_precision": 0.043902442296154094, "rouge1_precision_stderr": 0.0025879990015873823, "rouge1_recall": 0.08288624748163502, "rouge1_recall_stderr": 0.004634354203292547, "rouge2_fmeasure": 0.011004483045456277, "rouge2_fmeasure_stderr": 0.0009603677039917673, "rouge2_precision": 0.009017448289244204, "rouge2_precision_stderr": 0.000928647656293355, "rouge2_recall": 0.018080481336643847, "rouge2_recall_stderr": 0.0016363270970734646, "rougeL_fmeasure": 0.04070040451617707, "rougeL_fmeasure_stderr": 0.002174967302991672, "rougeL_precision": 0.03488188104345912, "rougeL_precision_stderr": 0.002148001214796994, "rougeL_recall": 0.06435420549635136, "rougeL_recall_stderr": 0.003580029698198211, "rougeLsum_fmeasure": 0.04267039522633286, "rougeLsum_fmeasure_stderr": 0.0023258157432622987, "rougeLsum_precision": 0.036478926891635684, "rougeLsum_precision_stderr": 0.0022479298210774765, "rougeLsum_recall": 0.06756132264586166, "rougeLsum_recall_stderr": 0.0038580697422047013}}, "5": {"article_DOC_summary": {"bleu": 4.26014647829622e-17, "bleu_stderr": 7.166752191638402e-14, "rouge1_fmeasure": 0.002779538343382174, "rouge1_fmeasure_stderr": 0.0007508746959336377, "rouge1_precision": 0.0024186506858969573, "rouge1_precision_stderr": 0.0006967044143553388, "rouge1_recall": 0.0041229184244589556, "rouge1_recall_stderr": 0.0011500680823563949, "rouge2_fmeasure": 0.00046142390179033124, "rouge2_fmeasure_stderr": 0.00017271322964265627, "rouge2_precision": 0.00039931331341648866, "rouge2_precision_stderr": 0.00015818778079209174, "rouge2_recall": 0.0006722407263472746, "rouge2_recall_stderr": 0.00025410945724169213, "rougeL_fmeasure": 0.0019880056310394296, "rougeL_fmeasure_stderr": 0.0005217836114821875, "rougeL_precision": 0.0017122099344230371, "rougeL_precision_stderr": 0.00047036977131503896, "rougeL_recall": 0.002921391378644953, "rougeL_recall_stderr": 0.0007787714133802412, "rougeLsum_fmeasure": 0.002161633417710008, "rougeLsum_fmeasure_stderr": 0.0005959969166706748, "rougeLsum_precision": 0.001894605060970088, "rougeLsum_precision_stderr": 0.0005535101918445765, "rougeLsum_recall": 0.003119076993452435, "rougeLsum_recall_stderr": 0.0008855064599210934}}}}