Muennighoff's picture
Add
29393c3
{"GEM/web_nlg_en": {"0": {"PALM_prompt": {"bleu": 0.32506312223519424, "bleu_stderr": 0.025893772747977932, "rouge1_fmeasure": 0.10433065433582071, "rouge1_fmeasure_stderr": 0.002045800614155292, "rouge1_precision": 0.06859349032117355, "rouge1_precision_stderr": 0.0016038312506390985, "rouge1_recall": 0.2941813489555871, "rouge1_recall_stderr": 0.004674021263394906, "rouge2_fmeasure": 0.04861844568830817, "rouge2_fmeasure_stderr": 0.0012939214664659474, "rouge2_precision": 0.03212658698266832, "rouge2_precision_stderr": 0.0010530735655225297, "rouge2_recall": 0.1386778384920652, "rouge2_recall_stderr": 0.003191413613494901, "rougeL_fmeasure": 0.1002621421342238, "rougeL_fmeasure_stderr": 0.001895084957108719, "rougeL_precision": 0.0656345480369304, "rougeL_precision_stderr": 0.0014573529495999864, "rougeL_recall": 0.28522310200632683, "rougeL_recall_stderr": 0.004520389282639347, "rougeLsum_fmeasure": 0.0995539972933265, "rougeLsum_fmeasure_stderr": 0.0019160684835195488, "rougeLsum_precision": 0.0653980881972399, "rougeLsum_precision_stderr": 0.0015014419295994892, "rougeLsum_recall": 0.28098744657798685, "rougeLsum_recall_stderr": 0.004381748686678463}}, "1": {"PALM_prompt": {"bleu": 0.5118016227412238, "bleu_stderr": 0.042623635278415395, "rouge1_fmeasure": 0.12088955331968472, "rouge1_fmeasure_stderr": 0.0019846793174451657, "rouge1_precision": 0.07757602455405031, "rouge1_precision_stderr": 0.0014534753546664488, "rouge1_recall": 0.3774716404768995, "rouge1_recall_stderr": 0.005305929451821015, "rouge2_fmeasure": 0.05672274465750321, "rouge2_fmeasure_stderr": 0.001258226651168741, "rouge2_precision": 0.0362851421424562, "rouge2_precision_stderr": 0.0008956093546268954, "rouge2_recall": 0.18524426315371975, "rouge2_recall_stderr": 0.003693116007080752, "rougeL_fmeasure": 0.11361139238348571, "rougeL_fmeasure_stderr": 0.0017875116804568483, "rougeL_precision": 0.07274599749024604, "rougeL_precision_stderr": 0.0012926720587857284, "rougeL_recall": 0.355092924706001, "rougeL_recall_stderr": 0.004854299370978627, "rougeLsum_fmeasure": 0.11510174006220572, "rougeLsum_fmeasure_stderr": 0.001863391319217601, "rougeLsum_precision": 0.07390123759045333, "rougeLsum_precision_stderr": 0.0013654602434686925, "rougeLsum_recall": 0.35831256976638354, "rougeLsum_recall_stderr": 0.004899522927326924}}, "2": {"PALM_prompt": {"bleu": 0.5840093945354913, "bleu_stderr": 0.04188339745568021, "rouge1_fmeasure": 0.12465621096807115, "rouge1_fmeasure_stderr": 0.0018703655658613531, "rouge1_precision": 0.07945750342123815, "rouge1_precision_stderr": 0.0014479489207553783, "rouge1_recall": 0.40825594120059006, "rouge1_recall_stderr": 0.005278174669595266, "rouge2_fmeasure": 0.05789739591362932, "rouge2_fmeasure_stderr": 0.001199170279038378, "rouge2_precision": 0.036744757326768296, "rouge2_precision_stderr": 0.0008792578328470093, "rouge2_recall": 0.2014423793700631, "rouge2_recall_stderr": 0.003818247451375373, "rougeL_fmeasure": 0.1154624476975127, "rougeL_fmeasure_stderr": 0.0016597153867437839, "rougeL_precision": 0.07347030137035865, "rougeL_precision_stderr": 0.0012477621361375887, "rougeL_recall": 0.37768137597443896, "rougeL_recall_stderr": 0.004751545894119024, "rougeLsum_fmeasure": 0.11837084927351957, "rougeLsum_fmeasure_stderr": 0.0017500298514746227, "rougeLsum_precision": 0.07540873858516584, "rougeLsum_precision_stderr": 0.0013179555493755973, "rougeLsum_recall": 0.38689757544087583, "rougeLsum_recall_stderr": 0.004882699109184072}}, "3": {"PALM_prompt": {"bleu": 0.6709398206896122, "bleu_stderr": 0.047769423505985516, "rouge1_fmeasure": 0.12486308816974763, "rouge1_fmeasure_stderr": 0.0018141719077548872, "rouge1_precision": 0.07881100544030407, "rouge1_precision_stderr": 0.001304955554970252, "rouge1_recall": 0.4124057146266478, "rouge1_recall_stderr": 0.005246109209443818, "rouge2_fmeasure": 0.05845298625034767, "rouge2_fmeasure_stderr": 0.0011862590488282388, "rouge2_precision": 0.036635961889873093, "rouge2_precision_stderr": 0.0008213071324834968, "rouge2_recall": 0.208225542736028, "rouge2_recall_stderr": 0.0039369080476096795, "rougeL_fmeasure": 0.11521943163869033, "rougeL_fmeasure_stderr": 0.001610539558916774, "rougeL_precision": 0.07274153773680196, "rougeL_precision_stderr": 0.0011633821312709138, "rougeL_recall": 0.38089519585678455, "rougeL_recall_stderr": 0.004728063182941111, "rougeLsum_fmeasure": 0.1183484530055362, "rougeLsum_fmeasure_stderr": 0.0017083674826636145, "rougeLsum_precision": 0.07477045841836422, "rougeLsum_precision_stderr": 0.0012355331377793054, "rougeLsum_recall": 0.3904327127987759, "rougeLsum_recall_stderr": 0.004884028804456976}}, "4": {"PALM_prompt": {"bleu": 0.717226798564371, "bleu_stderr": 0.05235423902349165, "rouge1_fmeasure": 0.1295714035230327, "rouge1_fmeasure_stderr": 0.0018420327565204727, "rouge1_precision": 0.08203688523709225, "rouge1_precision_stderr": 0.0013485494203466766, "rouge1_recall": 0.42140862503962817, "rouge1_recall_stderr": 0.005164591516935246, "rouge2_fmeasure": 0.06051792994698306, "rouge2_fmeasure_stderr": 0.0012071931655537776, "rouge2_precision": 0.03804051677909412, "rouge2_precision_stderr": 0.000845643440624378, "rouge2_recall": 0.21149985749947484, "rouge2_recall_stderr": 0.003860620724040806, "rougeL_fmeasure": 0.11864284534704603, "rougeL_fmeasure_stderr": 0.0016324931494254408, "rougeL_precision": 0.07507594990590853, "rougeL_precision_stderr": 0.0011943518000838561, "rougeL_recall": 0.38649010128141226, "rougeL_recall_stderr": 0.004628444756913378, "rougeLsum_fmeasure": 0.12258797563270211, "rougeLsum_fmeasure_stderr": 0.0017216462979010524, "rougeLsum_precision": 0.07768635173205395, "rougeLsum_precision_stderr": 0.0012677627883765405, "rougeLsum_recall": 0.3979491074259348, "rougeLsum_recall_stderr": 0.004743571661336718}}, "5": {"PALM_prompt": {"bleu": 0.7837024299010963, "bleu_stderr": 0.04687108913758884, "rouge1_fmeasure": 0.12867770755532376, "rouge1_fmeasure_stderr": 0.0017907995403965442, "rouge1_precision": 0.08098981255155412, "rouge1_precision_stderr": 0.0012986711907095154, "rouge1_recall": 0.4294396683796783, "rouge1_recall_stderr": 0.005256939492907656, "rouge2_fmeasure": 0.05997095205778236, "rouge2_fmeasure_stderr": 0.0011763036318809183, "rouge2_precision": 0.03749292107154646, "rouge2_precision_stderr": 0.0008203811898837323, "rouge2_recall": 0.21661276600273288, "rouge2_recall_stderr": 0.003990616331353259, "rougeL_fmeasure": 0.11712871574656816, "rougeL_fmeasure_stderr": 0.0015783462905322296, "rougeL_precision": 0.07372036929996381, "rougeL_precision_stderr": 0.0011482103405321168, "rougeL_recall": 0.3915126182515876, "rougeL_recall_stderr": 0.0046668052784097185, "rougeLsum_fmeasure": 0.1214298733155526, "rougeLsum_fmeasure_stderr": 0.0016873280471566882, "rougeLsum_precision": 0.07647590415348687, "rougeLsum_precision_stderr": 0.0012280522580962734, "rougeLsum_recall": 0.40419873137833984, "rougeLsum_recall_stderr": 0.004827520663821318}}}, "GEM/wiki_lingua_en": {"0": {"tldr_en": {"bleu": 1.4608584188826386, "bleu_stderr": 0.0530791011108354, "rouge1_fmeasure": 0.17322809310474896, "rouge1_fmeasure_stderr": 0.0017908446486168677, "rouge1_precision": 0.14654900702824386, "rouge1_precision_stderr": 0.0018063404204406743, "rouge1_recall": 0.25503720319711043, "rouge1_recall_stderr": 0.0026160039796892633, "rouge2_fmeasure": 0.034298445515984884, "rouge2_fmeasure_stderr": 0.0008203354371417247, "rouge2_precision": 0.028612548548136534, "rouge2_precision_stderr": 0.0007127877744078934, "rouge2_recall": 0.05279174190112992, "rouge2_recall_stderr": 0.001379618447010414, "rougeL_fmeasure": 0.13592864767523646, "rougeL_fmeasure_stderr": 0.0012935373206819489, "rougeL_precision": 0.11363888589301006, "rougeL_precision_stderr": 0.0012703980384269685, "rougeL_recall": 0.20501713486527137, "rougeL_recall_stderr": 0.002147517762826042, "rougeLsum_fmeasure": 0.1599177121150833, "rougeLsum_fmeasure_stderr": 0.0016445158655453984, "rougeLsum_precision": 0.13510478941478388, "rougeLsum_precision_stderr": 0.0016545178102930402, "rougeLsum_recall": 0.23604870436592665, "rougeLsum_recall_stderr": 0.002421328558194817}}, "1": {"tldr_en": {"bleu": 2.3966066814918157, "bleu_stderr": 0.05367929210307168, "rouge1_fmeasure": 0.1982032455796027, "rouge1_fmeasure_stderr": 0.0020176984061830703, "rouge1_precision": 0.1734392435728412, "rouge1_precision_stderr": 0.0022005941412746063, "rouge1_recall": 0.2835869137995969, "rouge1_recall_stderr": 0.002885685597988053, "rouge2_fmeasure": 0.04668447958482574, "rouge2_fmeasure_stderr": 0.0010022474154175907, "rouge2_precision": 0.04149997490553237, "rouge2_precision_stderr": 0.0010674584264283784, "rouge2_recall": 0.06868219059074646, "rouge2_recall_stderr": 0.0016243497803729017, "rougeL_fmeasure": 0.14863788313374796, "rougeL_fmeasure_stderr": 0.0013761560951888873, "rougeL_precision": 0.12919613127158547, "rougeL_precision_stderr": 0.0015642451075119819, "rougeL_recall": 0.21761320862142447, "rougeL_recall_stderr": 0.0022591710241408394, "rougeLsum_fmeasure": 0.18428785278478904, "rougeLsum_fmeasure_stderr": 0.0018795396325519526, "rougeLsum_precision": 0.16103026799665304, "rougeLsum_precision_stderr": 0.002048994341301177, "rougeLsum_recall": 0.26462971235663546, "rougeLsum_recall_stderr": 0.002734346549211203}}, "2": {"tldr_en": {"bleu": 2.8945524687514457, "bleu_stderr": 0.07184698921333843, "rouge1_fmeasure": 0.22000975094048222, "rouge1_fmeasure_stderr": 0.0019196293722291687, "rouge1_precision": 0.19457689329314268, "rouge1_precision_stderr": 0.002260756056763997, "rouge1_recall": 0.314039100456002, "rouge1_recall_stderr": 0.0027595985462308755, "rouge2_fmeasure": 0.05512243219484514, "rouge2_fmeasure_stderr": 0.0010318753523195182, "rouge2_precision": 0.0494730237951709, "rouge2_precision_stderr": 0.0011272834928775885, "rouge2_recall": 0.0810667814947236, "rouge2_recall_stderr": 0.0016990089475787328, "rougeL_fmeasure": 0.15989123909343908, "rougeL_fmeasure_stderr": 0.0013276007999853572, "rougeL_precision": 0.14093298706922133, "rougeL_precision_stderr": 0.001654821217199275, "rougeL_recall": 0.23368231370987727, "rougeL_recall_stderr": 0.0022516888453590965, "rougeLsum_fmeasure": 0.20653141298637975, "rougeLsum_fmeasure_stderr": 0.0017934155889773602, "rougeLsum_precision": 0.1825978062155656, "rougeLsum_precision_stderr": 0.002130225159997019, "rougeLsum_recall": 0.29579669341488013, "rougeLsum_recall_stderr": 0.002637070044280065}}, "3": {"tldr_en": {"bleu": 3.0602276174662797, "bleu_stderr": 0.08140252545516478, "rouge1_fmeasure": 0.18719041840682565, "rouge1_fmeasure_stderr": 0.002263749209581055, "rouge1_precision": 0.17154995366414352, "rouge1_precision_stderr": 0.002562308241187173, "rouge1_recall": 0.2676757228726807, "rouge1_recall_stderr": 0.0033611913545249297, "rouge2_fmeasure": 0.047560822644652924, "rouge2_fmeasure_stderr": 0.0010445651116964955, "rouge2_precision": 0.04292321928703632, "rouge2_precision_stderr": 0.001064702716287979, "rouge2_recall": 0.07068433635722526, "rouge2_recall_stderr": 0.0017497586284916746, "rougeL_fmeasure": 0.1354379034088655, "rougeL_fmeasure_stderr": 0.0016042022099017302, "rougeL_precision": 0.12421934115552721, "rougeL_precision_stderr": 0.0019015982358437386, "rougeL_recall": 0.19821540363389906, "rougeL_recall_stderr": 0.0026681499144326185, "rougeLsum_fmeasure": 0.17652791528010714, "rougeLsum_fmeasure_stderr": 0.0021286102824532036, "rougeLsum_precision": 0.16183366894292667, "rougeLsum_precision_stderr": 0.0024239308899604867, "rougeLsum_recall": 0.2533167464662618, "rougeLsum_recall_stderr": 0.0032102990450269485}}, "4": {"tldr_en": {"bleu": 0.6934835415911031, "bleu_stderr": 0.049667470868950084, "rouge1_fmeasure": 0.06085530545718036, "rouge1_fmeasure_stderr": 0.00203307390969258, "rouge1_precision": 0.05713222279079333, "rouge1_precision_stderr": 0.0021266654785382483, "rouge1_recall": 0.09058330612542118, "rouge1_recall_stderr": 0.003079513808745527, "rouge2_fmeasure": 0.015173414928652448, "rouge2_fmeasure_stderr": 0.0007150751207413451, "rouge2_precision": 0.014207618224936538, "rouge2_precision_stderr": 0.0008214073022225183, "rouge2_recall": 0.02408636460856734, "rouge2_recall_stderr": 0.0012343919074854972, "rougeL_fmeasure": 0.0450507360001391, "rougeL_fmeasure_stderr": 0.0014926765541292855, "rougeL_precision": 0.042414718667727, "rougeL_precision_stderr": 0.0015987476163280138, "rougeL_recall": 0.06883510681650253, "rougeL_recall_stderr": 0.0024186528354051195, "rougeLsum_fmeasure": 0.05703443465650266, "rougeLsum_fmeasure_stderr": 0.0019072034434628312, "rougeLsum_precision": 0.05347341120866329, "rougeLsum_precision_stderr": 0.001986260479403247, "rougeLsum_recall": 0.08506757665131119, "rougeLsum_recall_stderr": 0.002909995691190911}}, "5": {"tldr_en": {"bleu": 1.581309668123882e-06, "bleu_stderr": 2.4592802738754113e-06, "rouge1_fmeasure": 0.009690917181266634, "rouge1_fmeasure_stderr": 0.0008967008433661314, "rouge1_precision": 0.009326365925988343, "rouge1_precision_stderr": 0.0009238891705239445, "rouge1_recall": 0.014943156822805441, "rouge1_recall_stderr": 0.0014270358715897308, "rouge2_fmeasure": 0.002268834117142696, "rouge2_fmeasure_stderr": 0.0002916739063088069, "rouge2_precision": 0.0019508123925038809, "rouge2_precision_stderr": 0.0002665571578964472, "rouge2_recall": 0.00398100278797549, "rouge2_recall_stderr": 0.0005950165807991629, "rougeL_fmeasure": 0.006943264579604218, "rougeL_fmeasure_stderr": 0.0006330411491022215, "rougeL_precision": 0.006685088969622301, "rougeL_precision_stderr": 0.0006601897650917386, "rougeL_recall": 0.01106204631934071, "rougeL_recall_stderr": 0.0010938254411800782, "rougeLsum_fmeasure": 0.00910140326625081, "rougeLsum_fmeasure_stderr": 0.0008378756467906282, "rougeLsum_precision": 0.008768623444343692, "rougeLsum_precision_stderr": 0.0008666782347407663, "rougeLsum_recall": 0.014121358378765587, "rougeLsum_recall_stderr": 0.001350760934994208}}}, "e2e_nlg_cleaned": {"0": {"generate_text_restaurant": {"bleu": 0.015589228807418672, "bleu_stderr": 0.003691217032514631, "rouge1_fmeasure": 0.03512570831981043, "rouge1_fmeasure_stderr": 0.0007028508250409884, "rouge1_precision": 0.08238834340384042, "rouge1_precision_stderr": 0.0016031811195891402, "rouge1_recall": 0.025430011369854285, "rouge1_recall_stderr": 0.0006498826885017055, "rouge2_fmeasure": 0.00032804483755933243, "rouge2_fmeasure_stderr": 8.20801366964415e-05, "rouge2_precision": 0.0009723255571910732, "rouge2_precision_stderr": 0.00024982188929618097, "rouge2_recall": 0.00029303535674764464, "rouge2_recall_stderr": 9.939261536575641e-05, "rougeL_fmeasure": 0.03480594809918208, "rougeL_fmeasure_stderr": 0.0006948353713699121, "rougeL_precision": 0.08144389895939601, "rougeL_precision_stderr": 0.0015698164934837453, "rougeL_recall": 0.025235905197915645, "rougeL_recall_stderr": 0.000647019518371156, "rougeLsum_fmeasure": 0.03432140843843363, "rougeLsum_fmeasure_stderr": 0.0006753530356000441, "rougeLsum_precision": 0.08173127808720583, "rougeLsum_precision_stderr": 0.0016008167026965942, "rougeLsum_recall": 0.024195685454103392, "rougeLsum_recall_stderr": 0.0005527347315330655}}, "1": {"generate_text_restaurant": {"bleu": 6.836179529973976, "bleu_stderr": 0.0808622381692175, "rouge1_fmeasure": 0.35350598832846664, "rouge1_fmeasure_stderr": 0.0020049438944572543, "rouge1_precision": 0.32884898005646757, "rouge1_precision_stderr": 0.002746055697580347, "rouge1_recall": 0.44575132680164475, "rouge1_recall_stderr": 0.002825021204102268, "rouge2_fmeasure": 0.14487745848120898, "rouge2_fmeasure_stderr": 0.0015129362043146879, "rouge2_precision": 0.13607489118649332, "rouge2_precision_stderr": 0.0018147007082345516, "rouge2_recall": 0.18458105214823597, "rouge2_recall_stderr": 0.0020132959428884193, "rougeL_fmeasure": 0.2625755338174827, "rougeL_fmeasure_stderr": 0.001535900050678149, "rougeL_precision": 0.24335207327056155, "rougeL_precision_stderr": 0.0021318513982543723, "rougeL_recall": 0.33532204803532295, "rougeL_recall_stderr": 0.002383375008474535, "rougeLsum_fmeasure": 0.2893417910289629, "rougeLsum_fmeasure_stderr": 0.0019000123325331364, "rougeLsum_precision": 0.26974981288358574, "rougeLsum_precision_stderr": 0.002469140003825862, "rougeLsum_recall": 0.3644056974222114, "rougeLsum_recall_stderr": 0.0026205219344870726}}, "2": {"generate_text_restaurant": {"bleu": 7.593692630726807, "bleu_stderr": 0.12147840458175509, "rouge1_fmeasure": 0.3650716348139436, "rouge1_fmeasure_stderr": 0.0018388019470279935, "rouge1_precision": 0.32070413847189994, "rouge1_precision_stderr": 0.002359554141426242, "rouge1_recall": 0.47928591751649846, "rouge1_recall_stderr": 0.002722114189800939, "rouge2_fmeasure": 0.16097050153867934, "rouge2_fmeasure_stderr": 0.0014656932148909823, "rouge2_precision": 0.14103295618834455, "rouge2_precision_stderr": 0.0015746461899898117, "rouge2_recall": 0.21563029482851057, "rouge2_recall_stderr": 0.002136380088242833, "rougeL_fmeasure": 0.27596556132236433, "rougeL_fmeasure_stderr": 0.0014888754707697203, "rougeL_precision": 0.24046287771000435, "rougeL_precision_stderr": 0.001798012166542668, "rougeL_recall": 0.3679421301525328, "rougeL_recall_stderr": 0.0025079121076047625, "rougeLsum_fmeasure": 0.3002423567504504, "rougeLsum_fmeasure_stderr": 0.0018046105124439181, "rougeLsum_precision": 0.2637914012671533, "rougeLsum_precision_stderr": 0.0021472511284155046, "rougeLsum_recall": 0.3948037364571785, "rougeLsum_recall_stderr": 0.002648544902201612}}, "3": {"generate_text_restaurant": {"bleu": 8.742374199936782, "bleu_stderr": 0.09424505315134048, "rouge1_fmeasure": 0.3899947455542205, "rouge1_fmeasure_stderr": 0.0019080696284148931, "rouge1_precision": 0.35039399690574724, "rouge1_precision_stderr": 0.002305847291735412, "rouge1_recall": 0.48660889841428495, "rouge1_recall_stderr": 0.002662644687856354, "rouge2_fmeasure": 0.17904291710237294, "rouge2_fmeasure_stderr": 0.0015715270006421594, "rouge2_precision": 0.1599868739123523, "rouge2_precision_stderr": 0.0015782362564147653, "rouge2_recall": 0.227448454804275, "rouge2_recall_stderr": 0.0021747446525376547, "rougeL_fmeasure": 0.2920617305214459, "rougeL_fmeasure_stderr": 0.0015719969421114034, "rougeL_precision": 0.2602583118911549, "rougeL_precision_stderr": 0.001737371791496901, "rougeL_recall": 0.36945692088555687, "rougeL_recall_stderr": 0.0024499926133160622, "rougeLsum_fmeasure": 0.32444631733345547, "rougeLsum_fmeasure_stderr": 0.0018967884322166942, "rougeLsum_precision": 0.2913246360455281, "rougeLsum_precision_stderr": 0.002124454204809321, "rougeLsum_recall": 0.40523354266323236, "rougeLsum_recall_stderr": 0.0026084638294323506}}, "4": {"generate_text_restaurant": {"bleu": 9.715088335051762, "bleu_stderr": 0.1753473511599001, "rouge1_fmeasure": 0.40775875197875355, "rouge1_fmeasure_stderr": 0.0019664206284239825, "rouge1_precision": 0.37658509845981214, "rouge1_precision_stderr": 0.002384636357332195, "rouge1_recall": 0.486714622072443, "rouge1_recall_stderr": 0.0026221329215418985, "rouge2_fmeasure": 0.18976514478592516, "rouge2_fmeasure_stderr": 0.0016958589616437444, "rouge2_precision": 0.1747916801012778, "rouge2_precision_stderr": 0.0017350307207232446, "rouge2_recall": 0.22931314976608455, "rouge2_recall_stderr": 0.0022024157955143195, "rougeL_fmeasure": 0.3023558736561066, "rougeL_fmeasure_stderr": 0.0016456600817606013, "rougeL_precision": 0.2776183901125436, "rougeL_precision_stderr": 0.001855703858157366, "rougeL_recall": 0.36494128754990124, "rougeL_recall_stderr": 0.0023932425770631528, "rougeLsum_fmeasure": 0.3424660839752939, "rougeLsum_fmeasure_stderr": 0.001996421212700881, "rougeLsum_precision": 0.3162075740349658, "rougeLsum_precision_stderr": 0.0022600138968863186, "rougeLsum_recall": 0.40902136651768844, "rougeLsum_recall_stderr": 0.0026079274805328985}}, "5": {"generate_text_restaurant": {"bleu": 10.31740400799245, "bleu_stderr": 0.17344138200062734, "rouge1_fmeasure": 0.4160635303296256, "rouge1_fmeasure_stderr": 0.0019167446694135697, "rouge1_precision": 0.3911617622914696, "rouge1_precision_stderr": 0.0023614083172843452, "rouge1_recall": 0.4840060164486427, "rouge1_recall_stderr": 0.0025607770603185355, "rouge2_fmeasure": 0.19513439898691012, "rouge2_fmeasure_stderr": 0.0016801719843503758, "rouge2_precision": 0.18311975241328707, "rouge2_precision_stderr": 0.0017530732674177275, "rouge2_recall": 0.22944970891513594, "rouge2_recall_stderr": 0.002134666804521969, "rougeL_fmeasure": 0.30846083197605884, "rougeL_fmeasure_stderr": 0.001637729985430372, "rougeL_precision": 0.28869111802776204, "rougeL_precision_stderr": 0.001879336189442547, "rougeL_recall": 0.36202682605226727, "rougeL_recall_stderr": 0.0023254592064409552, "rougeLsum_fmeasure": 0.3513163230656758, "rougeLsum_fmeasure_stderr": 0.001957980092746368, "rougeLsum_precision": 0.33010797860958013, "rougeLsum_precision_stderr": 0.0022472175989479344, "rougeLsum_recall": 0.4090265340755352, "rougeLsum_recall_stderr": 0.002546467237868763}}}, "gem_xsum": {"0": {"article_DOC_summary": {"bleu": 2.1407026541783893, "bleu_stderr": 0.09037567653449961, "rouge1_fmeasure": 0.2130534919539574, "rouge1_fmeasure_stderr": 0.0025029827276464548, "rouge1_precision": 0.15787173182833486, "rouge1_precision_stderr": 0.0020401967493817856, "rouge1_recall": 0.3575349440272045, "rouge1_recall_stderr": 0.0044992439078584915, "rouge2_fmeasure": 0.05093449549500333, "rouge2_fmeasure_stderr": 0.0015982440427958716, "rouge2_precision": 0.036995243747182334, "rouge2_precision_stderr": 0.001189777484488148, "rouge2_recall": 0.08887777631236293, "rouge2_recall_stderr": 0.0028946858955236896, "rougeL_fmeasure": 0.15848964083025063, "rougeL_fmeasure_stderr": 0.001895901022123941, "rougeL_precision": 0.11735551251948108, "rougeL_precision_stderr": 0.0015519522146072052, "rougeL_recall": 0.26754759258055894, "rougeL_recall_stderr": 0.0035643834192978716, "rougeLsum_fmeasure": 0.16921433699659624, "rougeLsum_fmeasure_stderr": 0.0021331443008039677, "rougeLsum_precision": 0.12511375969112523, "rougeLsum_precision_stderr": 0.0016999095838239333, "rougeLsum_recall": 0.285784101072217, "rougeLsum_recall_stderr": 0.003970274987518834}}, "1": {"article_DOC_summary": {"bleu": 1.5258803326642025, "bleu_stderr": 0.04802303753716418, "rouge1_fmeasure": 0.18060678306331202, "rouge1_fmeasure_stderr": 0.0025809573229702634, "rouge1_precision": 0.12866810306322857, "rouge1_precision_stderr": 0.0019102479517656475, "rouge1_recall": 0.3152190979928625, "rouge1_recall_stderr": 0.004462238018541599, "rouge2_fmeasure": 0.03807299304872921, "rouge2_fmeasure_stderr": 0.0014688491194977736, "rouge2_precision": 0.02676557417591505, "rouge2_precision_stderr": 0.0010345920327863589, "rouge2_recall": 0.06868703168878479, "rouge2_recall_stderr": 0.0027290584553812565, "rougeL_fmeasure": 0.14041635566457955, "rougeL_fmeasure_stderr": 0.0019382870753545767, "rougeL_precision": 0.09984151880119294, "rougeL_precision_stderr": 0.0014227004264263632, "rougeL_recall": 0.24649628118013558, "rougeL_recall_stderr": 0.003467176011262577, "rougeLsum_fmeasure": 0.1431680713585917, "rougeLsum_fmeasure_stderr": 0.0021366368130727436, "rougeLsum_precision": 0.10174290101033899, "rougeLsum_precision_stderr": 0.0015628179713401368, "rougeLsum_recall": 0.2515700448017643, "rougeLsum_recall_stderr": 0.003812752448423601}}, "2": {"article_DOC_summary": {"bleu": 1.4807110641239705, "bleu_stderr": 0.05642507718368326, "rouge1_fmeasure": 0.17919800155343935, "rouge1_fmeasure_stderr": 0.0024773560103552544, "rouge1_precision": 0.12762605157499543, "rouge1_precision_stderr": 0.0018347498284269797, "rouge1_recall": 0.3130722022576149, "rouge1_recall_stderr": 0.004288622872438158, "rouge2_fmeasure": 0.03829786428664246, "rouge2_fmeasure_stderr": 0.0014210624037590423, "rouge2_precision": 0.027038903613225806, "rouge2_precision_stderr": 0.0010036982915438686, "rouge2_recall": 0.06847210404764151, "rouge2_recall_stderr": 0.0026456020226303906, "rougeL_fmeasure": 0.14394583719234913, "rougeL_fmeasure_stderr": 0.0019028216895477855, "rougeL_precision": 0.10241448305776109, "rougeL_precision_stderr": 0.001406273732891567, "rougeL_recall": 0.2524259625919352, "rougeL_recall_stderr": 0.0033729592986806267, "rougeLsum_fmeasure": 0.14111487802968178, "rougeLsum_fmeasure_stderr": 0.0020103034855313232, "rougeLsum_precision": 0.1002779789628322, "rougeLsum_precision_stderr": 0.001472636844565553, "rougeLsum_recall": 0.24825857387427142, "rougeLsum_recall_stderr": 0.0036037687382947966}}, "3": {"article_DOC_summary": {"bleu": 1.5480716201391962, "bleu_stderr": 0.04259756224632486, "rouge1_fmeasure": 0.1708616882829907, "rouge1_fmeasure_stderr": 0.0026372448948957907, "rouge1_precision": 0.1245146875791404, "rouge1_precision_stderr": 0.0020452410734284427, "rouge1_recall": 0.29245279417648024, "rouge1_recall_stderr": 0.004518130032710362, "rouge2_fmeasure": 0.03633421176029688, "rouge2_fmeasure_stderr": 0.001423553912853919, "rouge2_precision": 0.025988881798573865, "rouge2_precision_stderr": 0.0010211664215581159, "rouge2_recall": 0.06407684856222447, "rouge2_recall_stderr": 0.002609965847216835, "rougeL_fmeasure": 0.13811589968950733, "rougeL_fmeasure_stderr": 0.002059269651225793, "rougeL_precision": 0.10062009439170647, "rougeL_precision_stderr": 0.0016054032423320594, "rougeL_recall": 0.23738866114842447, "rougeL_recall_stderr": 0.0036328476884833756, "rougeLsum_fmeasure": 0.13501624474663962, "rougeLsum_fmeasure_stderr": 0.0021698097402404657, "rougeLsum_precision": 0.09834084127829348, "rougeLsum_precision_stderr": 0.0016818769932268626, "rougeLsum_recall": 0.23253064424615483, "rougeLsum_recall_stderr": 0.0038178300293972766}}, "4": {"article_DOC_summary": {"bleu": 0.6276187214183829, "bleu_stderr": 0.10466473087339175, "rouge1_fmeasure": 0.0475846797438099, "rouge1_fmeasure_stderr": 0.00265141713171967, "rouge1_precision": 0.043316822403892084, "rouge1_precision_stderr": 0.0028900125408040456, "rouge1_recall": 0.07276841656671419, "rouge1_recall_stderr": 0.004133235807638063, "rouge2_fmeasure": 0.009377022747940285, "rouge2_fmeasure_stderr": 0.000854007658898027, "rouge2_precision": 0.0093576557082385, "rouge2_precision_stderr": 0.0014626698630045996, "rouge2_recall": 0.014492420646261656, "rouge2_recall_stderr": 0.0013238813272262598, "rougeL_fmeasure": 0.03832605984378281, "rougeL_fmeasure_stderr": 0.0021137783954494655, "rougeL_precision": 0.035639613494581245, "rougeL_precision_stderr": 0.0025150520302418987, "rougeL_recall": 0.05854363623579474, "rougeL_recall_stderr": 0.003308989848879334, "rougeLsum_fmeasure": 0.03855249240002344, "rougeLsum_fmeasure_stderr": 0.002170801274633859, "rougeLsum_precision": 0.035795061037585306, "rougeLsum_precision_stderr": 0.002539847586499542, "rougeLsum_recall": 0.05893322820138485, "rougeLsum_recall_stderr": 0.0034149524939063266}}, "5": {"article_DOC_summary": {"bleu": 4.750313828560887e-40, "bleu_stderr": 1.219522064952425e-32, "rouge1_fmeasure": 0.002884301686287677, "rouge1_fmeasure_stderr": 0.0007752057983486471, "rouge1_precision": 0.003333596131072619, "rouge1_precision_stderr": 0.0009161215054684143, "rouge1_recall": 0.002627738914142911, "rouge1_recall_stderr": 0.0007104755333532985, "rouge2_fmeasure": 0.0005666193916622732, "rouge2_fmeasure_stderr": 0.0002695930799049985, "rouge2_precision": 0.0006633042010400501, "rouge2_precision_stderr": 0.0002992483341086919, "rouge2_recall": 0.0005217005217005217, "rouge2_recall_stderr": 0.0002680851938493634, "rougeL_fmeasure": 0.002387639095962103, "rougeL_fmeasure_stderr": 0.000654167470455253, "rougeL_precision": 0.0027764850648050597, "rougeL_precision_stderr": 0.0007798529533808385, "rougeL_recall": 0.0021689895202009484, "rougeL_recall_stderr": 0.0005997028831033762, "rougeLsum_fmeasure": 0.0023944782740570364, "rougeLsum_fmeasure_stderr": 0.0006504412933734339, "rougeLsum_precision": 0.002779638127059121, "rougeLsum_precision_stderr": 0.0007743437565217287, "rougeLsum_recall": 0.0021785988527847533, "rougeLsum_recall_stderr": 0.000597762769700717}}}}