| {"GEM/web_nlg_en": {"0": {"PALM_prompt": {"bleu": 0.3579887269792864, "bleu_stderr": 0.026290518420849302, "rouge1_fmeasure": 0.11160017527885356, "rouge1_fmeasure_stderr": 0.002086339624165716, "rouge1_precision": 0.07644779924173684, "rouge1_precision_stderr": 0.0019932242938081966, "rouge1_recall": 0.3140122825865788, "rouge1_recall_stderr": 0.00473174688731337, "rouge2_fmeasure": 0.05256140915596622, "rouge2_fmeasure_stderr": 0.0013357763866491004, "rouge2_precision": 0.036750727321617986, "rouge2_precision_stderr": 0.0014370097396917577, "rouge2_recall": 0.15168790833091741, "rouge2_recall_stderr": 0.00327314149676359, "rougeL_fmeasure": 0.10687286315069298, "rougeL_fmeasure_stderr": 0.0019210923887298273, "rougeL_precision": 0.07269010424631774, "rougeL_precision_stderr": 0.001804168947117905, "rougeL_recall": 0.3041843708869263, "rougeL_recall_stderr": 0.004620263011253791, "rougeLsum_fmeasure": 0.10569938398495801, "rougeLsum_fmeasure_stderr": 0.001946898177292707, "rougeLsum_precision": 0.07227657951942407, "rougeLsum_precision_stderr": 0.00185889534489746, "rougeLsum_recall": 0.2984357765608249, "rougeLsum_recall_stderr": 0.004438297298642072}}, "1": {"PALM_prompt": {"bleu": 0.4328473667055116, "bleu_stderr": 0.031563762685550605, "rouge1_fmeasure": 0.11463482618723982, "rouge1_fmeasure_stderr": 0.00197087410254774, "rouge1_precision": 0.0754889284841584, "rouge1_precision_stderr": 0.0016723482751950882, "rouge1_recall": 0.3568638973024857, "rouge1_recall_stderr": 0.005165847905772782, "rouge2_fmeasure": 0.05300336339554896, "rouge2_fmeasure_stderr": 0.0012527897061983034, "rouge2_precision": 0.034839983704867496, "rouge2_precision_stderr": 0.0010807913331387338, "rouge2_recall": 0.17043864684015358, "rouge2_recall_stderr": 0.0035541748574541812, "rougeL_fmeasure": 0.10863611949978016, "rougeL_fmeasure_stderr": 0.0018167063875338652, "rougeL_precision": 0.07141065068254121, "rougeL_precision_stderr": 0.0015343434909276881, "rougeL_recall": 0.3372654888293409, "rougeL_recall_stderr": 0.00480063635478594, "rougeLsum_fmeasure": 0.10860271374971142, "rougeLsum_fmeasure_stderr": 0.0018589526903866466, "rougeLsum_precision": 0.07156229719066953, "rougeLsum_precision_stderr": 0.0015834391719402176, "rougeLsum_recall": 0.3365254803044947, "rougeLsum_recall_stderr": 0.004741753523327779}}, "2": {"PALM_prompt": {"bleu": 0.5073706859748068, "bleu_stderr": 0.027251670973455218, "rouge1_fmeasure": 0.11731724091581561, "rouge1_fmeasure_stderr": 0.0018279205620823124, "rouge1_precision": 0.07477018632600506, "rouge1_precision_stderr": 0.0013374652593092398, "rouge1_recall": 0.3853613042032073, "rouge1_recall_stderr": 0.005084199730294221, "rouge2_fmeasure": 0.054398212153947176, "rouge2_fmeasure_stderr": 0.0011494317288632408, "rouge2_precision": 0.03450347196801284, "rouge2_precision_stderr": 0.0008069658633736817, "rouge2_recall": 0.18812965530793743, "rouge2_recall_stderr": 0.0036778797391502018, "rougeL_fmeasure": 0.1099832807060729, "rougeL_fmeasure_stderr": 0.0016704019125235296, "rougeL_precision": 0.07011638477370233, "rougeL_precision_stderr": 0.0012204936295153403, "rougeL_recall": 0.35849809185801473, "rougeL_recall_stderr": 0.0046303938730760524, "rougeLsum_fmeasure": 0.11132965753457637, "rougeLsum_fmeasure_stderr": 0.0017274518924526628, "rougeLsum_precision": 0.07103828558262268, "rougeLsum_precision_stderr": 0.0012708649576852631, "rougeLsum_recall": 0.36403900050794064, "rougeLsum_recall_stderr": 0.004706458824337533}}, "3": {"PALM_prompt": {"bleu": 0.5538460949994922, "bleu_stderr": 0.030619449581908684, "rouge1_fmeasure": 0.11752080822643646, "rouge1_fmeasure_stderr": 0.0017050984817057536, "rouge1_precision": 0.07426375527493968, "rouge1_precision_stderr": 0.0012328595556948653, "rouge1_recall": 0.3983512111896526, "rouge1_recall_stderr": 0.005149038831273021, "rouge2_fmeasure": 0.0540512381152691, "rouge2_fmeasure_stderr": 0.0010792706844501199, "rouge2_precision": 0.033961307188594206, "rouge2_precision_stderr": 0.0007463446959629993, "rouge2_recall": 0.1952126067967436, "rouge2_recall_stderr": 0.003765073237022532, "rougeL_fmeasure": 0.10991735862485745, "rougeL_fmeasure_stderr": 0.0015699707120844398, "rougeL_precision": 0.06949936881635287, "rougeL_precision_stderr": 0.0011319691770803394, "rougeL_recall": 0.37006814411969174, "rougeL_recall_stderr": 0.004674296339620147, "rougeLsum_fmeasure": 0.11131671255602878, "rougeLsum_fmeasure_stderr": 0.0016176588983060458, "rougeLsum_precision": 0.07044905911860123, "rougeLsum_precision_stderr": 0.001176713991457994, "rougeLsum_recall": 0.37587119622632176, "rougeLsum_recall_stderr": 0.004781764656765029}}, "4": {"PALM_prompt": {"bleu": 0.6169374982628473, "bleu_stderr": 0.028180215419142937, "rouge1_fmeasure": 0.12047953054602768, "rouge1_fmeasure_stderr": 0.001780264034076078, "rouge1_precision": 0.0767326292344124, "rouge1_precision_stderr": 0.0014332822108225588, "rouge1_recall": 0.4103530916408206, "rouge1_recall_stderr": 0.00509047707981648, "rouge2_fmeasure": 0.05558232740932497, "rouge2_fmeasure_stderr": 0.001135018703614793, "rouge2_precision": 0.03499884029225629, "rouge2_precision_stderr": 0.0008094705242409413, "rouge2_recall": 0.2026200591285694, "rouge2_recall_stderr": 0.003815007228485857, "rougeL_fmeasure": 0.11157234028587232, "rougeL_fmeasure_stderr": 0.0016088633608836555, "rougeL_precision": 0.07108155586037897, "rougeL_precision_stderr": 0.001313667101340276, "rougeL_recall": 0.3782120432625062, "rougeL_recall_stderr": 0.004617236907586467, "rougeLsum_fmeasure": 0.11358754564009298, "rougeLsum_fmeasure_stderr": 0.0016693342491592073, "rougeLsum_precision": 0.07245164237036843, "rougeLsum_precision_stderr": 0.0013644934676994799, "rougeLsum_recall": 0.38546769487210003, "rougeLsum_recall_stderr": 0.004699371603496402}}, "5": {"PALM_prompt": {"bleu": 0.632423656885609, "bleu_stderr": 0.028226340827669782, "rouge1_fmeasure": 0.11988252526283717, "rouge1_fmeasure_stderr": 0.0016490877395048458, "rouge1_precision": 0.07526495412948489, "rouge1_precision_stderr": 0.001204246999888188, "rouge1_recall": 0.42062114998353867, "rouge1_recall_stderr": 0.005033683779474927, "rouge2_fmeasure": 0.055498817735751244, "rouge2_fmeasure_stderr": 0.0010589061036010714, "rouge2_precision": 0.034675995706119275, "rouge2_precision_stderr": 0.0007442574236283384, "rouge2_recall": 0.20926298715883546, "rouge2_recall_stderr": 0.003683114100456131, "rougeL_fmeasure": 0.11135810184452252, "rougeL_fmeasure_stderr": 0.0015369060589554874, "rougeL_precision": 0.07006024451876049, "rougeL_precision_stderr": 0.0011240361260165595, "rougeL_recall": 0.38589026277969496, "rougeL_recall_stderr": 0.004490738431562092, "rougeLsum_fmeasure": 0.11309222791137312, "rougeLsum_fmeasure_stderr": 0.0015640021065237441, "rougeLsum_precision": 0.07114809662806877, "rougeLsum_precision_stderr": 0.0011495349005282837, "rougeLsum_recall": 0.3936098602902287, "rougeLsum_recall_stderr": 0.0045617868695433765}}}, "GEM/wiki_lingua_en": {"0": {"tldr_en": {"bleu": 1.479840115154661, "bleu_stderr": 0.06192138875344975, "rouge1_fmeasure": 0.1739448080653134, "rouge1_fmeasure_stderr": 0.0017812637598698018, "rouge1_precision": 0.14856509653732575, "rouge1_precision_stderr": 0.0018254841646619102, "rouge1_recall": 0.2530843717572759, "rouge1_recall_stderr": 0.002561813616922569, "rouge2_fmeasure": 0.03363388229490879, "rouge2_fmeasure_stderr": 0.0008046892555277539, "rouge2_precision": 0.028680910397583907, "rouge2_precision_stderr": 0.0007309262656611866, "rouge2_recall": 0.04964133355945333, "rouge2_recall_stderr": 0.0012722258808951824, "rougeL_fmeasure": 0.1356825751645128, "rougeL_fmeasure_stderr": 0.001248347814560266, "rougeL_precision": 0.11450942282690393, "rougeL_precision_stderr": 0.00125441708167449, "rougeL_recall": 0.20194947355319803, "rougeL_recall_stderr": 0.002036043567273002, "rougeLsum_fmeasure": 0.15980668292164993, "rougeLsum_fmeasure_stderr": 0.0016147589069422257, "rougeLsum_precision": 0.13625270653555904, "rougeLsum_precision_stderr": 0.001652617510622267, "rougeLsum_recall": 0.23341366110800826, "rougeLsum_recall_stderr": 0.002362328963636213}}, "1": {"tldr_en": {"bleu": 1.981909383109318, "bleu_stderr": 0.05332516266779298, "rouge1_fmeasure": 0.19417109314553332, "rouge1_fmeasure_stderr": 0.001883210730156311, "rouge1_precision": 0.16835595579581658, "rouge1_precision_stderr": 0.002031666300326454, "rouge1_recall": 0.2806656784585871, "rouge1_recall_stderr": 0.0027672810294863573, "rouge2_fmeasure": 0.040651231388572934, "rouge2_fmeasure_stderr": 0.000902016269913738, "rouge2_precision": 0.035233958419524904, "rouge2_precision_stderr": 0.0008649748434638386, "rouge2_recall": 0.06143446486171677, "rouge2_recall_stderr": 0.001577849822119161, "rougeL_fmeasure": 0.1387439887170405, "rougeL_fmeasure_stderr": 0.0012504777440338955, "rougeL_precision": 0.1193490581771219, "rougeL_precision_stderr": 0.0013674052231292708, "rougeL_recall": 0.20532600196964043, "rougeL_recall_stderr": 0.0021274206192724754, "rougeLsum_fmeasure": 0.18182771582932875, "rougeLsum_fmeasure_stderr": 0.0017585897563365122, "rougeLsum_precision": 0.15746346469094924, "rougeLsum_precision_stderr": 0.0019014604717123935, "rougeLsum_recall": 0.26376920789314967, "rougeLsum_recall_stderr": 0.0026265866392503625}}, "2": {"tldr_en": {"bleu": 2.3053974418740095, "bleu_stderr": 0.062242295007834764, "rouge1_fmeasure": 0.20692906953227413, "rouge1_fmeasure_stderr": 0.0018626056904197973, "rouge1_precision": 0.18001599549049535, "rouge1_precision_stderr": 0.002067162897845645, "rouge1_recall": 0.2980834661386306, "rouge1_recall_stderr": 0.002718524425472361, "rouge2_fmeasure": 0.04771532156348015, "rouge2_fmeasure_stderr": 0.0009515856581990172, "rouge2_precision": 0.04168050641100919, "rouge2_precision_stderr": 0.0009329665950699056, "rouge2_recall": 0.07039082545521896, "rouge2_recall_stderr": 0.0015628124045716759, "rougeL_fmeasure": 0.1467421325562737, "rougeL_fmeasure_stderr": 0.0012320807479736066, "rougeL_precision": 0.12674020027802077, "rougeL_precision_stderr": 0.0013962287618468083, "rougeL_recall": 0.21605276651528466, "rougeL_recall_stderr": 0.002081973016979306, "rougeLsum_fmeasure": 0.1942357263873664, "rougeLsum_fmeasure_stderr": 0.001742315830991206, "rougeLsum_precision": 0.16885381994157256, "rougeLsum_precision_stderr": 0.0019411704039521405, "rougeLsum_recall": 0.28047729608851496, "rougeLsum_recall_stderr": 0.002572231479292717}}, "3": {"tldr_en": {"bleu": 2.215156589671629, "bleu_stderr": 0.052535459933850885, "rouge1_fmeasure": 0.1696666381478316, "rouge1_fmeasure_stderr": 0.0021244410583731014, "rouge1_precision": 0.15364291614196499, "rouge1_precision_stderr": 0.002344969887146126, "rouge1_recall": 0.24376613072160627, "rouge1_recall_stderr": 0.003153183899770761, "rouge2_fmeasure": 0.03742000865261107, "rouge2_fmeasure_stderr": 0.0008889339032554892, "rouge2_precision": 0.03332167612450043, "rouge2_precision_stderr": 0.0008876153127825206, "rouge2_recall": 0.056658256520863745, "rouge2_recall_stderr": 0.001523337513038456, "rougeL_fmeasure": 0.12178749841451295, "rougeL_fmeasure_stderr": 0.0014680968157523093, "rougeL_precision": 0.11017417512546807, "rougeL_precision_stderr": 0.0017051424179066485, "rougeL_recall": 0.1791576899841882, "rougeL_recall_stderr": 0.0024356487242317496, "rougeLsum_fmeasure": 0.15898747044638634, "rougeLsum_fmeasure_stderr": 0.001985653665401712, "rougeLsum_precision": 0.14386673374882758, "rougeLsum_precision_stderr": 0.0022027329843523624, "rougeLsum_recall": 0.22930536403174942, "rougeLsum_recall_stderr": 0.00299463589962154}}, "4": {"tldr_en": {"bleu": 0.5131502979968497, "bleu_stderr": 0.03608605201687368, "rouge1_fmeasure": 0.053737140223689486, "rouge1_fmeasure_stderr": 0.0018027194165493082, "rouge1_precision": 0.049838643415747924, "rouge1_precision_stderr": 0.0018648700546221163, "rouge1_recall": 0.08127263942152925, "rouge1_recall_stderr": 0.002809816576781384, "rouge2_fmeasure": 0.011577372832860292, "rouge2_fmeasure_stderr": 0.0005741552055829621, "rouge2_precision": 0.010454163862870928, "rouge2_precision_stderr": 0.0006314369138935627, "rouge2_recall": 0.018556447747239968, "rouge2_recall_stderr": 0.0010227312175774936, "rougeL_fmeasure": 0.03964909379605471, "rougeL_fmeasure_stderr": 0.0013037832006282204, "rougeL_precision": 0.03679280580552151, "rougeL_precision_stderr": 0.0013808305653870323, "rougeL_recall": 0.06130836046537618, "rougeL_recall_stderr": 0.0021484750687546955, "rougeLsum_fmeasure": 0.05008741643259905, "rougeLsum_fmeasure_stderr": 0.0016808712625286486, "rougeLsum_precision": 0.04645621651758715, "rougeLsum_precision_stderr": 0.0017446445354945056, "rougeLsum_recall": 0.07583414283710693, "rougeLsum_recall_stderr": 0.0026217037949781957}}, "5": {"tldr_en": {"bleu": 1.248461374492507e-06, "bleu_stderr": 1.819428886922986e-06, "rouge1_fmeasure": 0.008601438929896699, "rouge1_fmeasure_stderr": 0.0008253043334091997, "rouge1_precision": 0.008297906112439548, "rouge1_precision_stderr": 0.000868651228038671, "rouge1_recall": 0.012867955004852301, "rouge1_recall_stderr": 0.0012711068547619942, "rouge2_fmeasure": 0.0018806245405111135, "rouge2_fmeasure_stderr": 0.0002580913633728736, "rouge2_precision": 0.0017481031836950151, "rouge2_precision_stderr": 0.0002752325580060782, "rouge2_recall": 0.002944671420000278, "rouge2_recall_stderr": 0.0004173458971296761, "rougeL_fmeasure": 0.006365417216740395, "rougeL_fmeasure_stderr": 0.0006037507741744518, "rougeL_precision": 0.006245166550957495, "rougeL_precision_stderr": 0.0006614482390967565, "rougeL_recall": 0.009611486285848429, "rougeL_recall_stderr": 0.0009555297578227913, "rougeLsum_fmeasure": 0.007901285151488387, "rougeLsum_fmeasure_stderr": 0.0007528984377933357, "rougeLsum_precision": 0.0076110422658591855, "rougeLsum_precision_stderr": 0.0007924852197189941, "rougeLsum_recall": 0.01188342258046937, "rougeLsum_recall_stderr": 0.001169956076721688}}}, "e2e_nlg_cleaned": {"0": {"generate_text_restaurant": {"bleu": 1.3188894749612563, "bleu_stderr": 0.044830637788985425, "rouge1_fmeasure": 0.09522733995608121, "rouge1_fmeasure_stderr": 0.0015050928361733534, "rouge1_precision": 0.12753556537606628, "rouge1_precision_stderr": 0.0029272372203605237, "rouge1_recall": 0.11864860513231083, "rouge1_recall_stderr": 0.0020905699726606005, "rouge2_fmeasure": 0.019204879284699994, "rouge2_fmeasure_stderr": 0.0006727499673039849, "rouge2_precision": 0.025675743778735428, "rouge2_precision_stderr": 0.001823036204109364, "rouge2_recall": 0.027052675155158974, "rouge2_recall_stderr": 0.0009673837604817755, "rougeL_fmeasure": 0.09185452447122286, "rougeL_fmeasure_stderr": 0.0014535063646756094, "rougeL_precision": 0.12067831736125931, "rougeL_precision_stderr": 0.0027766523050170443, "rougeL_recall": 0.11582003123688629, "rougeL_recall_stderr": 0.0020540885948462668, "rougeLsum_fmeasure": 0.08317942954808118, "rougeLsum_fmeasure_stderr": 0.0013322108791823542, "rougeLsum_precision": 0.1149608836927157, "rougeLsum_precision_stderr": 0.0028163032532190157, "rougeLsum_recall": 0.10237960786694723, "rougeLsum_recall_stderr": 0.0017967159967308072}}, "1": {"generate_text_restaurant": {"bleu": 8.268856250299471, "bleu_stderr": 0.10325577622421016, "rouge1_fmeasure": 0.38556499935543515, "rouge1_fmeasure_stderr": 0.002123280312714465, "rouge1_precision": 0.39554488581088626, "rouge1_precision_stderr": 0.0029681190545171763, "rouge1_recall": 0.43199771563925204, "rouge1_recall_stderr": 0.0028203929947275682, "rouge2_fmeasure": 0.16338292931453433, "rouge2_fmeasure_stderr": 0.0016456210441298405, "rouge2_precision": 0.16992099167287691, "rouge2_precision_stderr": 0.002094780486214531, "rouge2_recall": 0.1840776136278433, "rouge2_recall_stderr": 0.0019786136819072175, "rougeL_fmeasure": 0.27474972705805406, "rougeL_fmeasure_stderr": 0.0016803548099252608, "rougeL_precision": 0.28133109075015317, "rougeL_precision_stderr": 0.0023505923542842607, "rougeL_recall": 0.31196940533650747, "rougeL_recall_stderr": 0.0023918677481109705, "rougeLsum_fmeasure": 0.3161202268836757, "rougeLsum_fmeasure_stderr": 0.0019874232963612653, "rougeLsum_precision": 0.32483786204383086, "rougeLsum_precision_stderr": 0.002682647469519991, "rougeLsum_recall": 0.3546352816567669, "rougeLsum_recall_stderr": 0.0026072410079706235}}, "2": {"generate_text_restaurant": {"bleu": 8.752044150279037, "bleu_stderr": 0.17075525038552697, "rouge1_fmeasure": 0.38728648242815544, "rouge1_fmeasure_stderr": 0.0020736700072837727, "rouge1_precision": 0.3917573801974604, "rouge1_precision_stderr": 0.0031721059033143527, "rouge1_recall": 0.4480941133150411, "rouge1_recall_stderr": 0.002696304554783389, "rouge2_fmeasure": 0.1746241953539603, "rouge2_fmeasure_stderr": 0.0016245037242248635, "rouge2_precision": 0.1794594258413998, "rouge2_precision_stderr": 0.0022089039588187673, "rouge2_recall": 0.20362379083864202, "rouge2_recall_stderr": 0.0020059762697191225, "rougeL_fmeasure": 0.2888107866114557, "rougeL_fmeasure_stderr": 0.0016557523363002642, "rougeL_precision": 0.28989350350875787, "rougeL_precision_stderr": 0.002475041036978829, "rougeL_recall": 0.34036245653680275, "rougeL_recall_stderr": 0.0024309386217453996, "rougeLsum_fmeasure": 0.3205192518960678, "rougeLsum_fmeasure_stderr": 0.001992166841602722, "rougeLsum_precision": 0.3243897832360314, "rougeLsum_precision_stderr": 0.0028658165108453233, "rougeLsum_recall": 0.3715817073712579, "rougeLsum_recall_stderr": 0.002575962312302599}}, "3": {"generate_text_restaurant": {"bleu": 9.215917819944979, "bleu_stderr": 0.16750978186871135, "rouge1_fmeasure": 0.39498047709327316, "rouge1_fmeasure_stderr": 0.001995573628273643, "rouge1_precision": 0.3934162440731124, "rouge1_precision_stderr": 0.002870244512079275, "rouge1_recall": 0.45219902355874647, "rouge1_recall_stderr": 0.0026418133009258812, "rouge2_fmeasure": 0.17866109909559874, "rouge2_fmeasure_stderr": 0.0016358926141113962, "rouge2_precision": 0.17874070190714092, "rouge2_precision_stderr": 0.001975746196223423, "rouge2_recall": 0.20680510069987115, "rouge2_recall_stderr": 0.0020223490797835085, "rougeL_fmeasure": 0.29363065430769997, "rougeL_fmeasure_stderr": 0.0016676977783533096, "rougeL_precision": 0.290448701839473, "rougeL_precision_stderr": 0.002253601724914918, "rougeL_recall": 0.3411730757008735, "rougeL_recall_stderr": 0.0024103631845953434, "rougeLsum_fmeasure": 0.32908024305027606, "rougeLsum_fmeasure_stderr": 0.0019846013693823068, "rougeLsum_precision": 0.3277880264847081, "rougeLsum_precision_stderr": 0.00263580422255914, "rougeLsum_recall": 0.37671227249787725, "rougeLsum_recall_stderr": 0.0025378175774952855}}, "4": {"generate_text_restaurant": {"bleu": 9.29752714617784, "bleu_stderr": 0.1812520347088303, "rouge1_fmeasure": 0.3976120017477611, "rouge1_fmeasure_stderr": 0.001957196228653569, "rouge1_precision": 0.3936925579222371, "rouge1_precision_stderr": 0.0027027511186824126, "rouge1_recall": 0.4504460639681705, "rouge1_recall_stderr": 0.002571460027706377, "rouge2_fmeasure": 0.17875573947192416, "rouge2_fmeasure_stderr": 0.0016236641548062869, "rouge2_precision": 0.17770870518037865, "rouge2_precision_stderr": 0.0019011602774487565, "rouge2_recall": 0.20457826240041674, "rouge2_recall_stderr": 0.0020025597786927523, "rougeL_fmeasure": 0.2928958152017805, "rougeL_fmeasure_stderr": 0.0016441524187754983, "rougeL_precision": 0.2884163348982613, "rougeL_precision_stderr": 0.0021258462775742035, "rougeL_recall": 0.33596502253160176, "rougeL_recall_stderr": 0.0023345162307640745, "rougeLsum_fmeasure": 0.3318533780355719, "rougeLsum_fmeasure_stderr": 0.0019701005892539393, "rougeLsum_precision": 0.3286132019532869, "rougeLsum_precision_stderr": 0.0025120908786034103, "rougeLsum_recall": 0.375851104366494, "rougeLsum_recall_stderr": 0.0024995842860145783}}, "5": {"generate_text_restaurant": {"bleu": 9.362612934017736, "bleu_stderr": 0.10855778575738645, "rouge1_fmeasure": 0.3990120255227092, "rouge1_fmeasure_stderr": 0.0019178676126783694, "rouge1_precision": 0.3932319285778918, "rouge1_precision_stderr": 0.002548301621920845, "rouge1_recall": 0.4510310118426822, "rouge1_recall_stderr": 0.002590862288359499, "rouge2_fmeasure": 0.1796078353066716, "rouge2_fmeasure_stderr": 0.0016133475250028491, "rouge2_precision": 0.17695121418361603, "rouge2_precision_stderr": 0.001812178520561456, "rouge2_recall": 0.20535927412310515, "rouge2_recall_stderr": 0.002007657859036802, "rougeL_fmeasure": 0.29339815308032224, "rougeL_fmeasure_stderr": 0.0016446577983633287, "rougeL_precision": 0.2876654999305798, "rougeL_precision_stderr": 0.0020218264371153357, "rougeL_recall": 0.3353144854132937, "rougeL_recall_stderr": 0.0023517253283072198, "rougeLsum_fmeasure": 0.33456104383687457, "rougeLsum_fmeasure_stderr": 0.0019432720388950727, "rougeLsum_precision": 0.32975716195855664, "rougeLsum_precision_stderr": 0.0024048861669270427, "rougeLsum_recall": 0.3783760396312408, "rougeLsum_recall_stderr": 0.0025325615406918676}}}, "gem_xsum": {"0": {"article_DOC_summary": {"bleu": 1.768869507594394, "bleu_stderr": 0.08294604134047384, "rouge1_fmeasure": 0.2094281184112181, "rouge1_fmeasure_stderr": 0.0025790884426142523, "rouge1_precision": 0.1617749224002556, "rouge1_precision_stderr": 0.00237970226939903, "rouge1_recall": 0.335879396267748, "rouge1_recall_stderr": 0.0042531362256949, "rouge2_fmeasure": 0.04546276335000291, "rouge2_fmeasure_stderr": 0.0016156509146664276, "rouge2_precision": 0.03504593519505288, "rouge2_precision_stderr": 0.0013848794166905064, "rouge2_recall": 0.07425434107051126, "rouge2_recall_stderr": 0.002587335093539296, "rougeL_fmeasure": 0.15494261699819858, "rougeL_fmeasure_stderr": 0.002017114732994929, "rougeL_precision": 0.12002490384443826, "rougeL_precision_stderr": 0.0019143143405997343, "rougeL_recall": 0.24893620991791676, "rougeL_recall_stderr": 0.0033039443386605792, "rougeLsum_fmeasure": 0.16626632596350763, "rougeLsum_fmeasure_stderr": 0.0022125352263972875, "rougeLsum_precision": 0.12816677371397414, "rougeLsum_precision_stderr": 0.0019982013307588676, "rougeLsum_recall": 0.2682403202658057, "rougeLsum_recall_stderr": 0.003730829120509885}}, "1": {"article_DOC_summary": {"bleu": 1.264412591105362, "bleu_stderr": 0.058305941586244456, "rouge1_fmeasure": 0.17646870602303902, "rouge1_fmeasure_stderr": 0.002449669051301199, "rouge1_precision": 0.12542707936195607, "rouge1_precision_stderr": 0.0018304227801297888, "rouge1_recall": 0.30968982238658754, "rouge1_recall_stderr": 0.004101305886296608, "rouge2_fmeasure": 0.032922044625399265, "rouge2_fmeasure_stderr": 0.001308615681086968, "rouge2_precision": 0.02318241288852908, "rouge2_precision_stderr": 0.0009280565789217983, "rouge2_recall": 0.05908257096692382, "rouge2_recall_stderr": 0.002371758279207681, "rougeL_fmeasure": 0.13369172824813308, "rougeL_fmeasure_stderr": 0.0017713795391967972, "rougeL_precision": 0.0948327244688056, "rougeL_precision_stderr": 0.0013161667351585, "rougeL_recall": 0.23622628224705486, "rougeL_recall_stderr": 0.003080369698520929, "rougeLsum_fmeasure": 0.14119956709209672, "rougeLsum_fmeasure_stderr": 0.0019694996230184697, "rougeLsum_precision": 0.10008486714316106, "rougeLsum_precision_stderr": 0.0014521255501553532, "rougeLsum_recall": 0.24979473984092346, "rougeLsum_recall_stderr": 0.003444251234794886}}, "2": {"article_DOC_summary": {"bleu": 1.0987519725426753, "bleu_stderr": 0.03522818842665886, "rouge1_fmeasure": 0.16824394153138908, "rouge1_fmeasure_stderr": 0.0023490737769116094, "rouge1_precision": 0.11927780806435477, "rouge1_precision_stderr": 0.0017463880188515342, "rouge1_recall": 0.2969707610281187, "rouge1_recall_stderr": 0.004016473347933986, "rouge2_fmeasure": 0.03002721161354905, "rouge2_fmeasure_stderr": 0.0012316383364728099, "rouge2_precision": 0.021171125258080348, "rouge2_precision_stderr": 0.0008758008694717519, "rouge2_recall": 0.05384967895719866, "rouge2_recall_stderr": 0.002250067986717671, "rougeL_fmeasure": 0.13066203951989017, "rougeL_fmeasure_stderr": 0.001754156774657369, "rougeL_precision": 0.09253346970549631, "rougeL_precision_stderr": 0.001298228053049304, "rougeL_recall": 0.2315438648892566, "rougeL_recall_stderr": 0.003076756651824853, "rougeLsum_fmeasure": 0.13477311818536933, "rougeLsum_fmeasure_stderr": 0.001925520917624478, "rougeLsum_precision": 0.09538915399787434, "rougeLsum_precision_stderr": 0.001420693211469294, "rougeLsum_recall": 0.23912980735259662, "rougeLsum_recall_stderr": 0.00337672312378502}}, "3": {"article_DOC_summary": {"bleu": 0.997414867115136, "bleu_stderr": 0.05869103709177821, "rouge1_fmeasure": 0.15664009606941512, "rouge1_fmeasure_stderr": 0.0023702211117633955, "rouge1_precision": 0.11322746770756971, "rouge1_precision_stderr": 0.0018344350541308469, "rouge1_recall": 0.2726532450488621, "rouge1_recall_stderr": 0.004047751477113823, "rouge2_fmeasure": 0.026648660253339233, "rouge2_fmeasure_stderr": 0.0011756202673366485, "rouge2_precision": 0.01909537949600744, "rouge2_precision_stderr": 0.0008844078702649576, "rouge2_recall": 0.04741007757753075, "rouge2_recall_stderr": 0.0021059105310903435, "rougeL_fmeasure": 0.12256309804036948, "rougeL_fmeasure_stderr": 0.0017906867596916383, "rougeL_precision": 0.08861904770272214, "rougeL_precision_stderr": 0.0014108872664219377, "rougeL_recall": 0.21417348286977264, "rougeL_recall_stderr": 0.003130791990726019, "rougeLsum_fmeasure": 0.12555539609750047, "rougeLsum_fmeasure_stderr": 0.0019248864380343744, "rougeLsum_precision": 0.09067669669398595, "rougeLsum_precision_stderr": 0.0014934281129849842, "rougeLsum_recall": 0.21981690830637074, "rougeLsum_recall_stderr": 0.0033769616222655936}}, "4": {"article_DOC_summary": {"bleu": 0.3595681922766225, "bleu_stderr": 0.08302724390926437, "rouge1_fmeasure": 0.03912775891417527, "rouge1_fmeasure_stderr": 0.0022480249298505086, "rouge1_precision": 0.03336165212470275, "rouge1_precision_stderr": 0.0021721323035229496, "rouge1_recall": 0.06236797991424603, "rouge1_recall_stderr": 0.0036619285809241045, "rouge2_fmeasure": 0.005235866586219103, "rouge2_fmeasure_stderr": 0.0006173680600711812, "rouge2_precision": 0.003971072059610982, "rouge2_precision_stderr": 0.00047320081741051575, "rouge2_recall": 0.008875812344588924, "rouge2_recall_stderr": 0.0010797839682602972, "rougeL_fmeasure": 0.03069726623941213, "rougeL_fmeasure_stderr": 0.001712938549346239, "rougeL_precision": 0.026450065274545246, "rougeL_precision_stderr": 0.0017610900025980948, "rougeL_recall": 0.04941272986819276, "rougeL_recall_stderr": 0.0028669831282231704, "rougeLsum_fmeasure": 0.03131245006422282, "rougeLsum_fmeasure_stderr": 0.0017856839944735646, "rougeLsum_precision": 0.02698730446907224, "rougeLsum_precision_stderr": 0.001808112917392319, "rougeLsum_recall": 0.05033676703226922, "rougeLsum_recall_stderr": 0.0029803792624128944}}, "5": {"article_DOC_summary": {"bleu": 2.509258762242429e-38, "bleu_stderr": 9.767050327558104e-33, "rouge1_fmeasure": 0.0024515154297121964, "rouge1_fmeasure_stderr": 0.0006528237081721469, "rouge1_precision": 0.002809717218415156, "rouge1_precision_stderr": 0.0007799122566045872, "rouge1_recall": 0.002297493928770826, "rouge1_recall_stderr": 0.0006137569684554244, "rouge2_fmeasure": 0.00038400865766981235, "rouge2_fmeasure_stderr": 0.0002420252471501388, "rouge2_precision": 0.00044803756323120775, "rouge2_precision_stderr": 0.0002593397015980247, "rouge2_recall": 0.000357347055460263, "rouge2_recall_stderr": 0.00024108107952276452, "rougeL_fmeasure": 0.0019564763828564848, "rougeL_fmeasure_stderr": 0.0005370357747414661, "rougeL_precision": 0.002223032693562514, "rougeL_precision_stderr": 0.0006311357223918826, "rougeL_recall": 0.0018590186982094326, "rougeL_recall_stderr": 0.0005204880276058125, "rougeLsum_fmeasure": 0.0019564763828564848, "rougeLsum_fmeasure_stderr": 0.0005370357747414661, "rougeLsum_precision": 0.002223032693562514, "rougeLsum_precision_stderr": 0.0006311357223918826, "rougeLsum_recall": 0.0018590186982094326, "rougeLsum_recall_stderr": 0.0005204880276058125}}}} |