{"GEM/web_nlg_en": {"0": {"PALM_prompt": {"bleu": 0.38535441961499517, "bleu_stderr": 0.03552663485548509, "rouge1_fmeasure": 0.11065558909994337, "rouge1_fmeasure_stderr": 0.0020016224462212732, "rouge1_precision": 0.07392314530016614, "rouge1_precision_stderr": 0.0017416928662543226, "rouge1_recall": 0.31161026039179884, "rouge1_recall_stderr": 0.0047814670849113125, "rouge2_fmeasure": 0.052101576521840554, "rouge2_fmeasure_stderr": 0.001254434060918415, "rouge2_precision": 0.03387963683203527, "rouge2_precision_stderr": 0.0009418685192906572, "rouge2_recall": 0.15167229813850266, "rouge2_recall_stderr": 0.003249849487394629, "rougeL_fmeasure": 0.10721119439428567, "rougeL_fmeasure_stderr": 0.001872014217214712, "rougeL_precision": 0.07143509621818969, "rougeL_precision_stderr": 0.0016292918867949191, "rougeL_recall": 0.30392322887986606, "rougeL_recall_stderr": 0.004670559568432556, "rougeLsum_fmeasure": 0.10596966360979974, "rougeLsum_fmeasure_stderr": 0.001881280054371966, "rougeLsum_precision": 0.0707943641461647, "rougeLsum_precision_stderr": 0.0016472302036406458, "rougeLsum_recall": 0.2986281388001843, "rougeLsum_recall_stderr": 0.0045364052998747}}, "1": {"PALM_prompt": {"bleu": 0.5512129467367316, "bleu_stderr": 0.0395418255366758, "rouge1_fmeasure": 0.1276921926781691, "rouge1_fmeasure_stderr": 0.0018832476710271726, "rouge1_precision": 0.08196746460318716, "rouge1_precision_stderr": 0.0014754369831595647, "rouge1_recall": 0.40914147014095936, "rouge1_recall_stderr": 0.0053861796031930845, "rouge2_fmeasure": 0.05919617667381684, "rouge2_fmeasure_stderr": 0.0012055006346489835, "rouge2_precision": 0.03760548245806836, "rouge2_precision_stderr": 0.0008485772447386252, "rouge2_recall": 0.2004779256099399, "rouge2_recall_stderr": 0.0039022297404803946, "rougeL_fmeasure": 0.12093972964797003, "rougeL_fmeasure_stderr": 0.0017235569265706195, "rougeL_precision": 0.07759729021254366, "rougeL_precision_stderr": 0.0013607454921227458, "rougeL_recall": 0.38809219654571864, "rougeL_recall_stderr": 0.005037385606363737, "rougeLsum_fmeasure": 0.12119435037639528, "rougeLsum_fmeasure_stderr": 0.001776101552985325, "rougeLsum_precision": 0.07790072285955618, "rougeLsum_precision_stderr": 0.00140465482895153, "rougeLsum_recall": 0.38623053862621287, "rougeLsum_recall_stderr": 0.004945962835138011}}, "2": {"PALM_prompt": {"bleu": 0.5933018254177376, "bleu_stderr": 0.032599794867965604, "rouge1_fmeasure": 0.12805421977747078, "rouge1_fmeasure_stderr": 0.0017731859601500346, "rouge1_precision": 0.08138207976281618, "rouge1_precision_stderr": 0.001320028581758322, "rouge1_recall": 0.41969083219702635, "rouge1_recall_stderr": 0.0051938217749552314, "rouge2_fmeasure": 0.05973961241278947, "rouge2_fmeasure_stderr": 0.0011408079330925724, "rouge2_precision": 0.03774533356166905, "rouge2_precision_stderr": 0.0008138836014742545, "rouge2_recall": 0.21183011597903806, "rouge2_recall_stderr": 0.0039019044052842713, "rougeL_fmeasure": 0.12034876582957013, "rougeL_fmeasure_stderr": 0.0016107770822709627, "rougeL_precision": 0.07647361432812638, "rougeL_precision_stderr": 0.001197053850440824, "rougeL_recall": 0.3943345910974271, "rougeL_recall_stderr": 0.004791104064669637, "rougeLsum_fmeasure": 0.12158519620974508, "rougeLsum_fmeasure_stderr": 0.0016694470344012931, "rougeLsum_precision": 0.07733964505952771, "rougeLsum_precision_stderr": 0.001246953646848645, "rougeLsum_recall": 0.3972043924885929, "rougeLsum_recall_stderr": 0.0047988833920575725}}, "3": {"PALM_prompt": {"bleu": 0.6676820645573561, "bleu_stderr": 0.029698241159243657, "rouge1_fmeasure": 0.12983004472435894, "rouge1_fmeasure_stderr": 0.0017904512351955197, "rouge1_precision": 0.08199443734871886, "rouge1_precision_stderr": 0.0013044083678416126, "rouge1_recall": 0.4326296696301956, "rouge1_recall_stderr": 0.005319027568329476, "rouge2_fmeasure": 0.06110341345845585, "rouge2_fmeasure_stderr": 0.0011495434475286368, "rouge2_precision": 0.03836456544897309, "rouge2_precision_stderr": 0.0008016019880007896, "rouge2_recall": 0.2182970907135364, "rouge2_recall_stderr": 0.0039434390311428045, "rougeL_fmeasure": 0.12124821447948028, "rougeL_fmeasure_stderr": 0.0016083744034722292, "rougeL_precision": 0.07660172161550755, "rougeL_precision_stderr": 0.0011750201739650409, "rougeL_recall": 0.4026463135770865, "rougeL_recall_stderr": 0.004800741095877209, "rougeLsum_fmeasure": 0.12313018758539385, "rougeLsum_fmeasure_stderr": 0.0016863121667983272, "rougeLsum_precision": 0.07783198204724436, "rougeLsum_precision_stderr": 0.0012330922500882204, "rougeLsum_recall": 0.40862496584299657, "rougeLsum_recall_stderr": 0.004878219295388798}}, "4": {"PALM_prompt": {"bleu": 0.6836151545167003, "bleu_stderr": 0.029089321693769803, "rouge1_fmeasure": 0.13090538213539582, "rouge1_fmeasure_stderr": 0.0017570477742261594, "rouge1_precision": 0.08237641519365944, "rouge1_precision_stderr": 0.0012712811379550952, "rouge1_recall": 0.4410392252234467, "rouge1_recall_stderr": 0.005252924753314178, "rouge2_fmeasure": 0.061203868765094024, "rouge2_fmeasure_stderr": 0.001147850507777741, "rouge2_precision": 0.038294697830682935, "rouge2_precision_stderr": 0.0007935145188603823, "rouge2_recall": 0.22196349128777046, "rouge2_recall_stderr": 0.0039874400036358035, "rougeL_fmeasure": 0.12140909248039315, "rougeL_fmeasure_stderr": 0.00158909093789567, "rougeL_precision": 0.07647361824568906, "rougeL_precision_stderr": 0.0011522230823326422, "rougeL_recall": 0.40690715092516466, "rougeL_recall_stderr": 0.0047151717706141886, "rougeLsum_fmeasure": 0.12407530125753383, "rougeLsum_fmeasure_stderr": 0.0016569917198277998, "rougeLsum_precision": 0.07814715491035078, "rougeLsum_precision_stderr": 0.0012030810779768226, "rougeLsum_recall": 0.4163700311086396, "rougeLsum_recall_stderr": 0.00483547149960936}}, "5": {"PALM_prompt": {"bleu": 0.770273022704267, "bleu_stderr": 0.034315297186777595, "rouge1_fmeasure": 0.13101067212098677, "rouge1_fmeasure_stderr": 0.0017066218312728107, "rouge1_precision": 0.08203708357705593, "rouge1_precision_stderr": 0.0012436710783140608, "rouge1_recall": 0.4527088578344478, "rouge1_recall_stderr": 0.005270512909014665, "rouge2_fmeasure": 0.061162270106061005, "rouge2_fmeasure_stderr": 0.001104511682001034, "rouge2_precision": 0.03796634902700147, "rouge2_precision_stderr": 0.0007628000916252061, "rouge2_recall": 0.23182459931655927, "rouge2_recall_stderr": 0.004137297126449473, "rougeL_fmeasure": 0.12018039624183414, "rougeL_fmeasure_stderr": 0.0015114350444937687, "rougeL_precision": 0.07531042150309193, "rougeL_precision_stderr": 0.0011067305255883584, "rougeL_recall": 0.41469386205754033, "rougeL_recall_stderr": 0.004724284504576538, "rougeLsum_fmeasure": 0.1235732065654381, "rougeLsum_fmeasure_stderr": 0.0015991738579748697, "rougeLsum_precision": 0.07740826323217029, "rougeLsum_precision_stderr": 0.0011667399100477348, "rougeLsum_recall": 0.426759509472668, "rougeLsum_recall_stderr": 0.004893799458515002}}}, "GEM/wiki_lingua_en": {"0": {"tldr_en": {"bleu": 1.8921440063023223, "bleu_stderr": 0.07135112924486753, "rouge1_fmeasure": 0.18416362480898446, "rouge1_fmeasure_stderr": 0.0019831229958442082, "rouge1_precision": 0.15679162263674679, "rouge1_precision_stderr": 0.0019991369518845767, "rouge1_recall": 0.2689745748726192, "rouge1_recall_stderr": 0.0029016224540331552, "rouge2_fmeasure": 0.04094718247147155, "rouge2_fmeasure_stderr": 0.0009244238662338802, "rouge2_precision": 0.03467120760519669, "rouge2_precision_stderr": 0.0008221744008462381, "rouge2_recall": 0.06209758141565476, "rouge2_recall_stderr": 0.0015832249597357217, "rougeL_fmeasure": 0.14338902877501125, "rougeL_fmeasure_stderr": 0.0014226956074527863, "rougeL_precision": 0.12082089693911753, "rougeL_precision_stderr": 0.0014097474863449463, "rougeL_recall": 0.2144029920856489, "rougeL_recall_stderr": 0.002350903120057298, "rougeLsum_fmeasure": 0.1686525979999314, "rougeLsum_fmeasure_stderr": 0.0018124703517444088, "rougeLsum_precision": 0.1433977232378843, "rougeLsum_precision_stderr": 0.0018222721919399013, "rougeLsum_recall": 0.24699886538862653, "rougeLsum_recall_stderr": 0.0026942999677837982}}, "1": {"tldr_en": {"bleu": 2.8056438776711543, "bleu_stderr": 0.0837473028373607, "rouge1_fmeasure": 0.22027730929537712, "rouge1_fmeasure_stderr": 0.0019608589609497263, "rouge1_precision": 0.18997860617259896, "rouge1_precision_stderr": 0.0021315131916909724, "rouge1_recall": 0.31970644615930655, "rouge1_recall_stderr": 0.0028665402668271315, "rouge2_fmeasure": 0.05398367197056974, "rouge2_fmeasure_stderr": 0.0010308834876363582, "rouge2_precision": 0.046578501178857534, "rouge2_precision_stderr": 0.0009806080013812627, "rouge2_recall": 0.08133508293170587, "rouge2_recall_stderr": 0.0017593067161220152, "rougeL_fmeasure": 0.15563014047034032, "rougeL_fmeasure_stderr": 0.0013088183409122065, "rougeL_precision": 0.1329141418602316, "rougeL_precision_stderr": 0.0014073779291519839, "rougeL_recall": 0.23157078499816725, "rougeL_recall_stderr": 0.002239708119405446, "rougeLsum_fmeasure": 0.2072131798418733, "rougeLsum_fmeasure_stderr": 0.0018385432787880404, "rougeLsum_precision": 0.1786247909527116, "rougeLsum_precision_stderr": 0.0020029209788265186, "rougeLsum_recall": 0.3014126188767162, "rougeLsum_recall_stderr": 0.0027138736966177968}}, "2": {"tldr_en": {"bleu": 2.9780392590967417, "bleu_stderr": 0.07485005723665485, "rouge1_fmeasure": 0.22219895534581124, "rouge1_fmeasure_stderr": 0.0019115852755068978, "rouge1_precision": 0.19848212426092088, "rouge1_precision_stderr": 0.0023139570614517783, "rouge1_recall": 0.31608172323314615, "rouge1_recall_stderr": 0.0027622954997235665, "rouge2_fmeasure": 0.05522229843864866, "rouge2_fmeasure_stderr": 0.0010366643780952015, "rouge2_precision": 0.049990983654620055, "rouge2_precision_stderr": 0.0011071845883649219, "rouge2_recall": 0.08099563488003071, "rouge2_recall_stderr": 0.0017279951131225705, "rougeL_fmeasure": 0.15589253405198344, "rougeL_fmeasure_stderr": 0.0012973150218916173, "rougeL_precision": 0.1388108427148649, "rougeL_precision_stderr": 0.0016626769142365268, "rougeL_recall": 0.22710405861686703, "rougeL_recall_stderr": 0.0022002521830572098, "rougeLsum_fmeasure": 0.2100590256285955, "rougeLsum_fmeasure_stderr": 0.0018001298788378707, "rougeLsum_precision": 0.18757113799557207, "rougeLsum_precision_stderr": 0.0021914037253074584, "rougeLsum_recall": 0.2994878980311641, "rougeLsum_recall_stderr": 0.0026463012724863054}}, "3": {"tldr_en": {"bleu": 2.847512210211642, "bleu_stderr": 0.08130288880844025, "rouge1_fmeasure": 0.18197691858961074, "rouge1_fmeasure_stderr": 0.002206594668965237, "rouge1_precision": 0.17134837432784916, "rouge1_precision_stderr": 0.002648910653676966, "rouge1_recall": 0.25800000600290435, "rouge1_recall_stderr": 0.003313810821871368, "rouge2_fmeasure": 0.044357885260241585, "rouge2_fmeasure_stderr": 0.0009768044123671569, "rouge2_precision": 0.04161503586356084, "rouge2_precision_stderr": 0.0011270454940689701, "rouge2_recall": 0.06562904781876294, "rouge2_recall_stderr": 0.0016912238278118353, "rougeL_fmeasure": 0.13010623261113158, "rougeL_fmeasure_stderr": 0.0015513282273767694, "rougeL_precision": 0.12351815672543218, "rougeL_precision_stderr": 0.002041531952456252, "rougeL_recall": 0.18830813752138773, "rougeL_recall_stderr": 0.0025923821492611896, "rougeLsum_fmeasure": 0.17213683153876608, "rougeLsum_fmeasure_stderr": 0.0020822081122974664, "rougeLsum_precision": 0.16212518594924535, "rougeLsum_precision_stderr": 0.0025194852893668154, "rougeLsum_recall": 0.24439649503938565, "rougeLsum_recall_stderr": 0.0031617457131678586}}, "4": {"tldr_en": {"bleu": 0.6551089372553552, "bleu_stderr": 0.04895444931980532, "rouge1_fmeasure": 0.057107296289159025, "rouge1_fmeasure_stderr": 0.0019494380017288225, "rouge1_precision": 0.05513001019844826, "rouge1_precision_stderr": 0.00215178654051168, "rouge1_recall": 0.08454226315750968, "rouge1_recall_stderr": 0.002935250128250436, "rouge2_fmeasure": 0.014135921586219569, "rouge2_fmeasure_stderr": 0.0006914493317450905, "rouge2_precision": 0.013800421209577515, "rouge2_precision_stderr": 0.000858478532665541, "rouge2_recall": 0.021959372595934164, "rouge2_recall_stderr": 0.001194364786706014, "rougeL_fmeasure": 0.04216170229604133, "rougeL_fmeasure_stderr": 0.0014236179778487777, "rougeL_precision": 0.04128275764961394, "rougeL_precision_stderr": 0.0016823042515051513, "rougeL_recall": 0.0637605084786262, "rougeL_recall_stderr": 0.0022692310247988275, "rougeLsum_fmeasure": 0.05379079735955767, "rougeLsum_fmeasure_stderr": 0.0018282128528245283, "rougeLsum_precision": 0.051975929888249256, "rougeLsum_precision_stderr": 0.002028731950450667, "rougeLsum_recall": 0.07986443919003557, "rougeLsum_recall_stderr": 0.0027755366306270973}}, "5": {"tldr_en": {"bleu": 9.282109221159003e-07, "bleu_stderr": 2.2223612520502284e-06, "rouge1_fmeasure": 0.009311675141314384, "rouge1_fmeasure_stderr": 0.0008747369590243084, "rouge1_precision": 0.009676230361373621, "rouge1_precision_stderr": 0.0010092112696239383, "rouge1_recall": 0.014009287778858652, "rouge1_recall_stderr": 0.0013693091057835286, "rouge2_fmeasure": 0.002405387772695905, "rouge2_fmeasure_stderr": 0.00030042578765582695, "rouge2_precision": 0.002516778405932201, "rouge2_precision_stderr": 0.0003813647101277748, "rouge2_recall": 0.004189787625575326, "rouge2_recall_stderr": 0.0006261364681498638, "rougeL_fmeasure": 0.006932807281073693, "rougeL_fmeasure_stderr": 0.0006486704498845653, "rougeL_precision": 0.007375708880019688, "rougeL_precision_stderr": 0.0007995038887537955, "rougeL_recall": 0.010624417220719972, "rougeL_recall_stderr": 0.0010701965664864565, "rougeLsum_fmeasure": 0.008662236702193958, "rougeLsum_fmeasure_stderr": 0.0008161476026799892, "rougeLsum_precision": 0.009118809831121096, "rougeLsum_precision_stderr": 0.0009682743549182715, "rougeLsum_recall": 0.01302829985395723, "rougeLsum_recall_stderr": 0.0012830127121259097}}}, "e2e_nlg_cleaned": {"0": {"generate_text_restaurant": {"bleu": 0.6114974539510816, "bleu_stderr": 0.04527113203185075, "rouge1_fmeasure": 0.03492593073320387, "rouge1_fmeasure_stderr": 0.0010376513872745155, "rouge1_precision": 0.05869533205508546, "rouge1_precision_stderr": 0.001497949313805969, "rouge1_recall": 0.03571922348667764, "rouge1_recall_stderr": 0.0013948024749901261, "rouge2_fmeasure": 0.004517028931517297, "rouge2_fmeasure_stderr": 0.00036439768835932237, "rouge2_precision": 0.004063213985026975, "rouge2_precision_stderr": 0.0003541545577591494, "rouge2_recall": 0.006573047412918524, "rouge2_recall_stderr": 0.0005456263764429907, "rougeL_fmeasure": 0.03456601494605734, "rougeL_fmeasure_stderr": 0.0010229273732960667, "rougeL_precision": 0.05805625987920658, "rougeL_precision_stderr": 0.0014726688390761706, "rougeL_recall": 0.03532952206585685, "rougeL_recall_stderr": 0.0013716820040930184, "rougeLsum_fmeasure": 0.033356146432655866, "rougeLsum_fmeasure_stderr": 0.0009612249675140079, "rougeLsum_precision": 0.057416666705387066, "rougeLsum_precision_stderr": 0.001471227198507916, "rougeLsum_recall": 0.033493295914568566, "rougeLsum_recall_stderr": 0.0012685265746055889}}, "1": {"generate_text_restaurant": {"bleu": 11.33447911090928, "bleu_stderr": 0.14535102796873467, "rouge1_fmeasure": 0.433797396683994, "rouge1_fmeasure_stderr": 0.0022987607409721217, "rouge1_precision": 0.5083802018676299, "rouge1_precision_stderr": 0.0032791833916447554, "rouge1_recall": 0.42190893586204214, "rouge1_recall_stderr": 0.002971819042737358, "rouge2_fmeasure": 0.19719568941249035, "rouge2_fmeasure_stderr": 0.0019377495452543357, "rouge2_precision": 0.23512517549601986, "rouge2_precision_stderr": 0.0025920962511690763, "rouge2_recall": 0.19142011398550732, "rouge2_recall_stderr": 0.0021166855984481392, "rougeL_fmeasure": 0.31401062106699107, "rougeL_fmeasure_stderr": 0.0019834092080858665, "rougeL_precision": 0.37102243518103833, "rougeL_precision_stderr": 0.002904005844748298, "rougeL_recall": 0.30457624020087987, "rougeL_recall_stderr": 0.0024007135826919603, "rougeLsum_fmeasure": 0.3549188128484648, "rougeLsum_fmeasure_stderr": 0.002246841679471083, "rougeLsum_precision": 0.41705381489741356, "rougeLsum_precision_stderr": 0.003122960946648587, "rougeLsum_recall": 0.34480646003082416, "rougeLsum_recall_stderr": 0.0027214625950243783}}, "2": {"generate_text_restaurant": {"bleu": 12.915730606248113, "bleu_stderr": 0.20474125011289426, "rouge1_fmeasure": 0.4631809810602233, "rouge1_fmeasure_stderr": 0.002254496022709034, "rouge1_precision": 0.5479863902027133, "rouge1_precision_stderr": 0.0032369184668208516, "rouge1_recall": 0.441447062617084, "rouge1_recall_stderr": 0.0029152320911209556, "rouge2_fmeasure": 0.22387083492928028, "rouge2_fmeasure_stderr": 0.0019825042986668373, "rouge2_precision": 0.2694942093855683, "rouge2_precision_stderr": 0.002668904008037024, "rouge2_recall": 0.2131243378825482, "rouge2_recall_stderr": 0.0021529009824731303, "rougeL_fmeasure": 0.34081459166299144, "rougeL_fmeasure_stderr": 0.002030967494387809, "rougeL_precision": 0.4057365701684737, "rougeL_precision_stderr": 0.0029348734509084765, "rougeL_recall": 0.3240876063453124, "rougeL_recall_stderr": 0.002423564725696539, "rougeLsum_fmeasure": 0.382975161960982, "rougeLsum_fmeasure_stderr": 0.0022658855724966864, "rougeLsum_precision": 0.45419008644409004, "rougeLsum_precision_stderr": 0.0031526651706947012, "rougeLsum_recall": 0.3644738218767085, "rougeLsum_recall_stderr": 0.0027027920241602162}}, "3": {"generate_text_restaurant": {"bleu": 13.799049670661745, "bleu_stderr": 0.1818766642053644, "rouge1_fmeasure": 0.4733021068886725, "rouge1_fmeasure_stderr": 0.002229748270982301, "rouge1_precision": 0.5538154552713349, "rouge1_precision_stderr": 0.0032031754343585057, "rouge1_recall": 0.4530213630135714, "rouge1_recall_stderr": 0.002889071639596583, "rouge2_fmeasure": 0.23393615456741612, "rouge2_fmeasure_stderr": 0.0020284322092199397, "rouge2_precision": 0.2776711960124572, "rouge2_precision_stderr": 0.002669354319886314, "rouge2_recall": 0.22402395817155157, "rouge2_recall_stderr": 0.0022252252780088967, "rougeL_fmeasure": 0.34984277963163096, "rougeL_fmeasure_stderr": 0.0020650055785518843, "rougeL_precision": 0.4112498098162674, "rougeL_precision_stderr": 0.002912753431059431, "rougeL_recall": 0.33431398302211607, "rougeL_recall_stderr": 0.0024572409829041286, "rougeLsum_fmeasure": 0.3937728879658398, "rougeLsum_fmeasure_stderr": 0.0022887568890525446, "rougeLsum_precision": 0.46138958037109395, "rougeLsum_precision_stderr": 0.0031283915205367083, "rougeLsum_recall": 0.37645205860452513, "rougeLsum_recall_stderr": 0.0027190821967377665}}, "4": {"generate_text_restaurant": {"bleu": 14.332946979780699, "bleu_stderr": 0.187321161876581, "rouge1_fmeasure": 0.47698101030399137, "rouge1_fmeasure_stderr": 0.002304125507421037, "rouge1_precision": 0.5502767036745366, "rouge1_precision_stderr": 0.0032191855076160905, "rouge1_recall": 0.4601167935637563, "rouge1_recall_stderr": 0.002933097976024252, "rouge2_fmeasure": 0.23686616389681567, "rouge2_fmeasure_stderr": 0.0020891392412113624, "rouge2_precision": 0.2764817164388747, "rouge2_precision_stderr": 0.002683961252587485, "rouge2_recall": 0.22893953263224417, "rouge2_recall_stderr": 0.002301850243468405, "rougeL_fmeasure": 0.35299999087704836, "rougeL_fmeasure_stderr": 0.002138766539340371, "rougeL_precision": 0.4088077687087317, "rougeL_precision_stderr": 0.0029284110175963112, "rougeL_recall": 0.34034029264854043, "rougeL_recall_stderr": 0.002546438349753808, "rougeLsum_fmeasure": 0.3988932621808988, "rougeLsum_fmeasure_stderr": 0.002365288784954707, "rougeLsum_precision": 0.46022437266752997, "rougeLsum_precision_stderr": 0.0031504453494794983, "rougeLsum_recall": 0.38497978756866746, "rougeLsum_recall_stderr": 0.00282067010132265}}, "5": {"generate_text_restaurant": {"bleu": 14.123246792588205, "bleu_stderr": 0.18981316484333496, "rouge1_fmeasure": 0.4771521080848, "rouge1_fmeasure_stderr": 0.002247583418148515, "rouge1_precision": 0.5508575470527967, "rouge1_precision_stderr": 0.003172543361692212, "rouge1_recall": 0.4596250362933734, "rouge1_recall_stderr": 0.0028838674948470076, "rouge2_fmeasure": 0.23757613806327457, "rouge2_fmeasure_stderr": 0.0020631855681245196, "rouge2_precision": 0.27785561114819307, "rouge2_precision_stderr": 0.0026789931891456594, "rouge2_recall": 0.22893900538597906, "rouge2_recall_stderr": 0.002250810965306422, "rougeL_fmeasure": 0.35646844538814754, "rougeL_fmeasure_stderr": 0.002140481161608752, "rougeL_precision": 0.4128922710964347, "rougeL_precision_stderr": 0.0029408076764540847, "rougeL_recall": 0.3432096183345724, "rougeL_recall_stderr": 0.0025317938331892898, "rougeLsum_fmeasure": 0.4021976919673297, "rougeLsum_fmeasure_stderr": 0.0023234845320029575, "rougeLsum_precision": 0.46456472542175714, "rougeLsum_precision_stderr": 0.0031248622936883626, "rougeLsum_recall": 0.3874763961501519, "rougeLsum_recall_stderr": 0.0027737834865428587}}}, "gem_xsum": {"0": {"article_DOC_summary": {"bleu": 1.949120361010708, "bleu_stderr": 0.0913394024073436, "rouge1_fmeasure": 0.20731019337768042, "rouge1_fmeasure_stderr": 0.0026329404650807355, "rouge1_precision": 0.15967577438396582, "rouge1_precision_stderr": 0.002367262573167645, "rouge1_recall": 0.3344097957704383, "rouge1_recall_stderr": 0.004542927765114456, "rouge2_fmeasure": 0.04779740432400501, "rouge2_fmeasure_stderr": 0.0016427567157124747, "rouge2_precision": 0.03607001702892568, "rouge2_precision_stderr": 0.001380428573706143, "rouge2_recall": 0.08085696005427423, "rouge2_recall_stderr": 0.0028599271086292063, "rougeL_fmeasure": 0.1576331231529663, "rougeL_fmeasure_stderr": 0.0019951539963787477, "rougeL_precision": 0.12124210013250766, "rougeL_precision_stderr": 0.0018353599935403793, "rougeL_recall": 0.25607740438919824, "rougeL_recall_stderr": 0.0036003883952627205, "rougeLsum_fmeasure": 0.16181781523790845, "rougeLsum_fmeasure_stderr": 0.0022319416867268445, "rougeLsum_precision": 0.1242181328811872, "rougeLsum_precision_stderr": 0.0019619556407432866, "rougeLsum_recall": 0.26337373173306655, "rougeLsum_recall_stderr": 0.004025744770152854}}, "1": {"article_DOC_summary": {"bleu": 1.3894434901616817, "bleu_stderr": 0.0696818577382309, "rouge1_fmeasure": 0.17081587570763854, "rouge1_fmeasure_stderr": 0.002498720216403539, "rouge1_precision": 0.12169091971501833, "rouge1_precision_stderr": 0.0018485062787122516, "rouge1_recall": 0.2985653730389386, "rouge1_recall_stderr": 0.004290053847052186, "rouge2_fmeasure": 0.03675651772088566, "rouge2_fmeasure_stderr": 0.0014655540573612757, "rouge2_precision": 0.02579297493046093, "rouge2_precision_stderr": 0.0010284490730061247, "rouge2_recall": 0.06657394965502363, "rouge2_recall_stderr": 0.0027184784375237805, "rougeL_fmeasure": 0.1393113978609222, "rougeL_fmeasure_stderr": 0.0019655986810200457, "rougeL_precision": 0.09903048460831103, "rougeL_precision_stderr": 0.0014377536580800821, "rougeL_recall": 0.24509693147391448, "rougeL_recall_stderr": 0.003518979975606831, "rougeLsum_fmeasure": 0.13592809650365684, "rougeLsum_fmeasure_stderr": 0.0021149395154476942, "rougeLsum_precision": 0.09661401587871966, "rougeLsum_precision_stderr": 0.0015465093492546976, "rougeLsum_recall": 0.23906516897153357, "rougeLsum_recall_stderr": 0.003723173758494015}}, "2": {"article_DOC_summary": {"bleu": 1.519028859842843, "bleu_stderr": 0.10932835465017057, "rouge1_fmeasure": 0.1812341104304252, "rouge1_fmeasure_stderr": 0.0024420789648274964, "rouge1_precision": 0.12932415674769882, "rouge1_precision_stderr": 0.0018169766878992155, "rouge1_recall": 0.31588294560858055, "rouge1_recall_stderr": 0.004216644148639617, "rouge2_fmeasure": 0.04085037987286443, "rouge2_fmeasure_stderr": 0.0014441866865235443, "rouge2_precision": 0.02882443972103835, "rouge2_precision_stderr": 0.0010221845705623207, "rouge2_recall": 0.07321267293223659, "rouge2_recall_stderr": 0.0026752083496981217, "rougeL_fmeasure": 0.1497403639141996, "rougeL_fmeasure_stderr": 0.0019366476236409818, "rougeL_precision": 0.10675121708053566, "rougeL_precision_stderr": 0.0014369855194212536, "rougeL_recall": 0.26192576739698237, "rougeL_recall_stderr": 0.003428288975677526, "rougeLsum_fmeasure": 0.1406991990555183, "rougeLsum_fmeasure_stderr": 0.0019931907678247163, "rougeLsum_precision": 0.10009767181496847, "rougeLsum_precision_stderr": 0.0014618075217660356, "rougeLsum_recall": 0.2471962036151299, "rougeLsum_recall_stderr": 0.003570649420240086}}, "3": {"article_DOC_summary": {"bleu": 1.6370716620193742, "bleu_stderr": 0.0965616345735323, "rouge1_fmeasure": 0.17398457366386533, "rouge1_fmeasure_stderr": 0.0026011912639339633, "rouge1_precision": 0.12669828356422383, "rouge1_precision_stderr": 0.0020094917781438, "rouge1_recall": 0.2991027968300709, "rouge1_recall_stderr": 0.004591383921824911, "rouge2_fmeasure": 0.03976972720010616, "rouge2_fmeasure_stderr": 0.0015117103431558975, "rouge2_precision": 0.02846440216262034, "rouge2_precision_stderr": 0.0010956946533866802, "rouge2_recall": 0.0706413058306802, "rouge2_recall_stderr": 0.0027868384974826573, "rougeL_fmeasure": 0.14481676263378276, "rougeL_fmeasure_stderr": 0.0021155906125953196, "rougeL_precision": 0.10522998362089304, "rougeL_precision_stderr": 0.0016066968369183466, "rougeL_recall": 0.24989448115090335, "rougeL_recall_stderr": 0.003818419767894932, "rougeLsum_fmeasure": 0.13514679304649532, "rougeLsum_fmeasure_stderr": 0.002182435634289256, "rougeLsum_precision": 0.09817348971720044, "rougeLsum_precision_stderr": 0.0016441110742716834, "rougeLsum_recall": 0.23394639249573773, "rougeLsum_recall_stderr": 0.0039702384387275}}, "4": {"article_DOC_summary": {"bleu": 0.8669272479971863, "bleu_stderr": 0.1405646989169273, "rouge1_fmeasure": 0.05007677852098019, "rouge1_fmeasure_stderr": 0.0028520829549217, "rouge1_precision": 0.04259238619227563, "rouge1_precision_stderr": 0.0027101471976600064, "rouge1_recall": 0.07720379689124833, "rouge1_recall_stderr": 0.0044603739276368026, "rouge2_fmeasure": 0.011518858251746018, "rouge2_fmeasure_stderr": 0.00100875710859823, "rouge2_precision": 0.01039550194215322, "rouge2_precision_stderr": 0.0013002683205402986, "rouge2_recall": 0.01810305312651028, "rouge2_recall_stderr": 0.0015721872697551358, "rougeL_fmeasure": 0.04100139142500078, "rougeL_fmeasure_stderr": 0.002305891008745547, "rougeL_precision": 0.03523709895823149, "rougeL_precision_stderr": 0.00227881816047799, "rougeL_recall": 0.06319492439650329, "rougeL_recall_stderr": 0.0036104810452688464, "rougeLsum_fmeasure": 0.040275422096666895, "rougeLsum_fmeasure_stderr": 0.0023372301427381265, "rougeLsum_precision": 0.03483815068281454, "rougeLsum_precision_stderr": 0.0023451054837002874, "rougeLsum_recall": 0.06212330010384987, "rougeLsum_recall_stderr": 0.00366876474124129}}, "5": {"article_DOC_summary": {"bleu": 1.0463937563324107e-36, "bleu_stderr": 3.980151871433784e-31, "rouge1_fmeasure": 0.0031002107990313337, "rouge1_fmeasure_stderr": 0.0008747175919556528, "rouge1_precision": 0.003588402424856072, "rouge1_precision_stderr": 0.001048591574930412, "rouge1_recall": 0.0028604653610329457, "rouge1_recall_stderr": 0.0007986614088290892, "rouge2_fmeasure": 0.0006390516220219271, "rouge2_fmeasure_stderr": 0.00030954190704298026, "rouge2_precision": 0.0007923025611704858, "rouge2_precision_stderr": 0.0003921450634363378, "rouge2_recall": 0.0005498039696152904, "rouge2_recall_stderr": 0.0002641981773098142, "rougeL_fmeasure": 0.002386725038982092, "rougeL_fmeasure_stderr": 0.0006780512190033147, "rougeL_precision": 0.0027648078129268614, "rougeL_precision_stderr": 0.0008127087627131919, "rougeL_recall": 0.0021867338334639443, "rougeL_recall_stderr": 0.0006127280790696822, "rougeLsum_fmeasure": 0.00262981517645366, "rougeLsum_fmeasure_stderr": 0.0007507411641340949, "rougeLsum_precision": 0.0030462311312536203, "rougeLsum_precision_stderr": 0.0009151504800039854, "rougeLsum_recall": 0.0024328059752266973, "rougeLsum_recall_stderr": 0.0006814073788898694}}}}