| {"GEM/web_nlg_en": {"0": {"PALM_prompt": {"bleu": 0.33618386090404295, "bleu_stderr": 0.043286547374004225, "rouge1_fmeasure": 0.09550360928926843, "rouge1_fmeasure_stderr": 0.0021611192824620468, "rouge1_precision": 0.07608115633976532, "rouge1_precision_stderr": 0.0028424335866037475, "rouge1_recall": 0.243734587530279, "rouge1_recall_stderr": 0.005032751672173048, "rouge2_fmeasure": 0.04353421604632926, "rouge2_fmeasure_stderr": 0.0013022741040944032, "rouge2_precision": 0.03391274645846755, "rouge2_precision_stderr": 0.0017782441786429572, "rouge2_recall": 0.11477361563470867, "rouge2_recall_stderr": 0.0030177112931945443, "rougeL_fmeasure": 0.0908905716888711, "rougeL_fmeasure_stderr": 0.0019748576875776485, "rougeL_precision": 0.07249954185930807, "rougeL_precision_stderr": 0.002716866763111571, "rougeL_recall": 0.23447583587320983, "rougeL_recall_stderr": 0.004820896551192642, "rougeLsum_fmeasure": 0.09063319866429098, "rougeLsum_fmeasure_stderr": 0.002018782468480028, "rougeLsum_precision": 0.07260565563718514, "rougeLsum_precision_stderr": 0.0027622865524293628, "rougeLsum_recall": 0.2312007323793673, "rougeLsum_recall_stderr": 0.004666750865618609}}, "1": {"PALM_prompt": {"bleu": 0.5152510207869508, "bleu_stderr": 0.039697768768641464, "rouge1_fmeasure": 0.15419793855600986, "rouge1_fmeasure_stderr": 0.0037752055082234935, "rouge1_precision": 0.1335251141437586, "rouge1_precision_stderr": 0.004421796872864802, "rouge1_recall": 0.3040669240102272, "rouge1_recall_stderr": 0.0049926465687368735, "rouge2_fmeasure": 0.07820906828691397, "rouge2_fmeasure_stderr": 0.0026222161094111586, "rouge2_precision": 0.06857339375782437, "rouge2_precision_stderr": 0.0030273264083127568, "rouge2_recall": 0.1555986112064758, "rouge2_recall_stderr": 0.0036341014671041087, "rougeL_fmeasure": 0.13965714245032726, "rougeL_fmeasure_stderr": 0.0032487392690607572, "rougeL_precision": 0.1195649771956543, "rougeL_precision_stderr": 0.0038518942294089972, "rougeL_recall": 0.2838951533263151, "rougeL_recall_stderr": 0.004599064364517073, "rougeLsum_fmeasure": 0.14150307262693815, "rougeLsum_fmeasure_stderr": 0.0033007395324502467, "rougeLsum_precision": 0.12140487798820795, "rougeLsum_precision_stderr": 0.003915984273012587, "rougeLsum_recall": 0.2857833042522088, "rougeLsum_recall_stderr": 0.004601461544101827}}, "2": {"PALM_prompt": {"bleu": 0.6450721424031474, "bleu_stderr": 0.035938592978876936, "rouge1_fmeasure": 0.19228537050298922, "rouge1_fmeasure_stderr": 0.004356183491682661, "rouge1_precision": 0.17715496451419446, "rouge1_precision_stderr": 0.005377686826508908, "rouge1_recall": 0.3442204927205235, "rouge1_recall_stderr": 0.00499209962075588, "rouge2_fmeasure": 0.1017490401630499, "rouge2_fmeasure_stderr": 0.003080557280075834, "rouge2_precision": 0.09659406582034752, "rouge2_precision_stderr": 0.0036720254666308344, "rouge2_recall": 0.1816245156374427, "rouge2_recall_stderr": 0.0038421174433974025, "rougeL_fmeasure": 0.17158392384169643, "rougeL_fmeasure_stderr": 0.0037128302671958994, "rougeL_precision": 0.15519367504713033, "rougeL_precision_stderr": 0.004580706449804959, "rougeL_recall": 0.31893881029765586, "rougeL_recall_stderr": 0.004597766706728441, "rougeLsum_fmeasure": 0.17498254398589475, "rougeLsum_fmeasure_stderr": 0.0037985612156152086, "rougeLsum_precision": 0.1592800915810083, "rougeLsum_precision_stderr": 0.0047149524911017215, "rougeLsum_recall": 0.3221825821541532, "rougeLsum_recall_stderr": 0.0046252310161258746}}, "3": {"PALM_prompt": {"bleu": 0.8785043636862591, "bleu_stderr": 0.02652000083973547, "rouge1_fmeasure": 0.21217682060449367, "rouge1_fmeasure_stderr": 0.004581243352642801, "rouge1_precision": 0.2002191357399255, "rouge1_precision_stderr": 0.005700191155087746, "rouge1_recall": 0.3622650735119951, "rouge1_recall_stderr": 0.005105318033672305, "rouge2_fmeasure": 0.11312048852329888, "rouge2_fmeasure_stderr": 0.003186877123824252, "rouge2_precision": 0.10955905558045385, "rouge2_precision_stderr": 0.0038849982073218873, "rouge2_recall": 0.19262377036723086, "rouge2_recall_stderr": 0.003902442560309681, "rougeL_fmeasure": 0.1874319081280966, "rougeL_fmeasure_stderr": 0.0038899168243038715, "rougeL_precision": 0.1744946205047383, "rougeL_precision_stderr": 0.004899868234689971, "rougeL_recall": 0.33190561350734876, "rougeL_recall_stderr": 0.004628476785750535, "rougeLsum_fmeasure": 0.19207381785134825, "rougeLsum_fmeasure_stderr": 0.004003703743860644, "rougeLsum_precision": 0.17972186968155374, "rougeLsum_precision_stderr": 0.005058207025529124, "rougeLsum_recall": 0.33723235220496645, "rougeLsum_recall_stderr": 0.0046889691038068775}}, "4": {"PALM_prompt": {"bleu": 1.020225734756704, "bleu_stderr": 0.06946466420275214, "rouge1_fmeasure": 0.22615455778377724, "rouge1_fmeasure_stderr": 0.004584303113870005, "rouge1_precision": 0.21447559212644274, "rouge1_precision_stderr": 0.005787602630220149, "rouge1_recall": 0.3797811786576114, "rouge1_recall_stderr": 0.005078572769442694, "rouge2_fmeasure": 0.12153309984630654, "rouge2_fmeasure_stderr": 0.0032009564132827184, "rouge2_precision": 0.11802182161980528, "rouge2_precision_stderr": 0.003954053081043237, "rouge2_recall": 0.20495230642568182, "rouge2_recall_stderr": 0.003956396099130858, "rougeL_fmeasure": 0.1985084531863174, "rougeL_fmeasure_stderr": 0.003863020108912202, "rougeL_precision": 0.18574729294363898, "rougeL_precision_stderr": 0.00493965653212434, "rougeL_recall": 0.34661430398431914, "rougeL_recall_stderr": 0.004643977843173891, "rougeLsum_fmeasure": 0.20493355705865743, "rougeLsum_fmeasure_stderr": 0.004011218572127487, "rougeLsum_precision": 0.19295820334137398, "rougeLsum_precision_stderr": 0.005149923293184489, "rougeLsum_recall": 0.3532599821115898, "rougeLsum_recall_stderr": 0.004685486372918684}}, "5": {"PALM_prompt": {"bleu": 1.1738991703843653, "bleu_stderr": 0.05137420728965795, "rouge1_fmeasure": 0.2452749113827306, "rouge1_fmeasure_stderr": 0.004866057995099286, "rouge1_precision": 0.23842752486609714, "rouge1_precision_stderr": 0.00616558462817229, "rouge1_recall": 0.39104608539227964, "rouge1_recall_stderr": 0.005079097315439687, "rouge2_fmeasure": 0.13673599319945717, "rouge2_fmeasure_stderr": 0.003545382189555846, "rouge2_precision": 0.13743673376990653, "rouge2_precision_stderr": 0.004448566773563913, "rouge2_recall": 0.21617363071605727, "rouge2_recall_stderr": 0.004065117072186819, "rougeL_fmeasure": 0.2145149869812429, "rougeL_fmeasure_stderr": 0.004135695136449003, "rougeL_precision": 0.20669362004199143, "rougeL_precision_stderr": 0.0053303444381744315, "rougeL_recall": 0.35345362943589836, "rougeL_recall_stderr": 0.004581784867877382, "rougeLsum_fmeasure": 0.22169261840373009, "rougeLsum_fmeasure_stderr": 0.004292938565416988, "rougeLsum_precision": 0.21482050441032427, "rougeLsum_precision_stderr": 0.005549487778372521, "rougeLsum_recall": 0.3612051449037077, "rougeLsum_recall_stderr": 0.004657096205531439}}}, "GEM/wiki_lingua_en": {"0": {"tldr_en": {"bleu": 3.2204812581094187, "bleu_stderr": 0.0968937530189579, "rouge1_fmeasure": 0.17281704832161807, "rouge1_fmeasure_stderr": 0.0025639705499622615, "rouge1_precision": 0.16222110345712215, "rouge1_precision_stderr": 0.002918181626000938, "rouge1_recall": 0.23556142979563985, "rouge1_recall_stderr": 0.0035092798940514463, "rouge2_fmeasure": 0.04445750772336212, "rouge2_fmeasure_stderr": 0.0010694173040695087, "rouge2_precision": 0.04035916262517482, "rouge2_precision_stderr": 0.0011089852877097363, "rouge2_recall": 0.06187933259063034, "rouge2_recall_stderr": 0.0015927286355937283, "rougeL_fmeasure": 0.12828595447707558, "rougeL_fmeasure_stderr": 0.0018630698897748783, "rougeL_precision": 0.12115800294799915, "rougeL_precision_stderr": 0.0023302786580353405, "rougeL_recall": 0.1793437869920672, "rougeL_recall_stderr": 0.0027904364481447434, "rougeLsum_fmeasure": 0.16125234602130137, "rougeLsum_fmeasure_stderr": 0.0024054029356366125, "rougeLsum_precision": 0.15193645088089489, "rougeLsum_precision_stderr": 0.002794596188541928, "rougeLsum_recall": 0.22017606445792967, "rougeLsum_recall_stderr": 0.003307741344782461}}, "1": {"tldr_en": {"bleu": 3.030764799858383, "bleu_stderr": 0.10180137949258324, "rouge1_fmeasure": 0.20057722026752264, "rouge1_fmeasure_stderr": 0.00237727127672953, "rouge1_precision": 0.24835405674131716, "rouge1_precision_stderr": 0.003595946507957674, "rouge1_recall": 0.22065222520601965, "rouge1_recall_stderr": 0.0030326234032250735, "rouge2_fmeasure": 0.053780768787129375, "rouge2_fmeasure_stderr": 0.0012652221510456923, "rouge2_precision": 0.07072572329707479, "rouge2_precision_stderr": 0.002023483136430399, "rouge2_recall": 0.05888749376061464, "rouge2_recall_stderr": 0.0015271270172799948, "rougeL_fmeasure": 0.15099195793433165, "rougeL_fmeasure_stderr": 0.0017939149386485946, "rougeL_precision": 0.18962847615836217, "rougeL_precision_stderr": 0.0029056148560385174, "rougeL_recall": 0.16669593752772216, "rougeL_recall_stderr": 0.0023452388157941375, "rougeLsum_fmeasure": 0.18619742012806825, "rougeLsum_fmeasure_stderr": 0.0022080861119325576, "rougeLsum_precision": 0.23119707647225618, "rougeLsum_precision_stderr": 0.0034029730598757074, "rougeLsum_recall": 0.20514467867088854, "rougeLsum_recall_stderr": 0.0028358663517956315}}, "2": {"tldr_en": {"bleu": 4.074528254683577, "bleu_stderr": 0.10710940903995719, "rouge1_fmeasure": 0.24392276306894944, "rouge1_fmeasure_stderr": 0.0023000547396419086, "rouge1_precision": 0.30679877376441267, "rouge1_precision_stderr": 0.003595563898423582, "rouge1_recall": 0.25602196677157735, "rouge1_recall_stderr": 0.002878244091822486, "rouge2_fmeasure": 0.07100355255541753, "rouge2_fmeasure_stderr": 0.0014153910474231026, "rouge2_precision": 0.09387841885638748, "rouge2_precision_stderr": 0.002194124801129067, "rouge2_recall": 0.0740439804559834, "rouge2_recall_stderr": 0.001644608125064704, "rougeL_fmeasure": 0.18445520873996413, "rougeL_fmeasure_stderr": 0.001797621869515743, "rougeL_precision": 0.23412738417408802, "rougeL_precision_stderr": 0.0029250825035858734, "rougeL_recall": 0.19426592228730813, "rougeL_recall_stderr": 0.0023089496783281213, "rougeLsum_fmeasure": 0.2286765314746336, "rougeLsum_fmeasure_stderr": 0.0021801688851002263, "rougeLsum_precision": 0.28859199947210284, "rougeLsum_precision_stderr": 0.003452141980034977, "rougeLsum_recall": 0.23966421160449644, "rougeLsum_recall_stderr": 0.0027125548096589747}}, "3": {"tldr_en": {"bleu": 3.168617248016535, "bleu_stderr": 0.08041979746938775, "rouge1_fmeasure": 0.2094195871488414, "rouge1_fmeasure_stderr": 0.0027068429969493734, "rouge1_precision": 0.272311629129121, "rouge1_precision_stderr": 0.0039505188546921826, "rouge1_recall": 0.21816270627496134, "rouge1_recall_stderr": 0.0032448735585025937, "rouge2_fmeasure": 0.06204427812400913, "rouge2_fmeasure_stderr": 0.0014401113659882462, "rouge2_precision": 0.08329439938013247, "rouge2_precision_stderr": 0.0021782819294409984, "rouge2_recall": 0.06480971019253767, "rouge2_recall_stderr": 0.0016827399941316222, "rougeL_fmeasure": 0.1590668148316741, "rougeL_fmeasure_stderr": 0.0020766324795938023, "rougeL_precision": 0.20896331681491714, "rougeL_precision_stderr": 0.0031500865399556595, "rougeL_recall": 0.1664625275086072, "rougeL_recall_stderr": 0.0025592493419649177, "rougeLsum_fmeasure": 0.1964756114951262, "rougeLsum_fmeasure_stderr": 0.0025500807038816515, "rougeLsum_precision": 0.2563037368454477, "rougeLsum_precision_stderr": 0.0037619221351167056, "rougeLsum_recall": 0.20447650361202882, "rougeLsum_recall_stderr": 0.0030540843932082493}}, "4": {"tldr_en": {"bleu": 0.07788444152267485, "bleu_stderr": 0.01315525656911281, "rouge1_fmeasure": 0.06757697669893872, "rouge1_fmeasure_stderr": 0.0023707490073172043, "rouge1_precision": 0.0910819200952716, "rouge1_precision_stderr": 0.0033747683121654196, "rouge1_recall": 0.07028567198192245, "rouge1_recall_stderr": 0.002640964970940966, "rouge2_fmeasure": 0.019948424307073904, "rouge2_fmeasure_stderr": 0.000986170441488306, "rouge2_precision": 0.028646478253466095, "rouge2_precision_stderr": 0.0016076285180980135, "rouge2_recall": 0.020868526921797886, "rouge2_recall_stderr": 0.0011537893245677335, "rougeL_fmeasure": 0.05201990108593777, "rougeL_fmeasure_stderr": 0.0018314763879696625, "rougeL_precision": 0.07082578661014885, "rougeL_precision_stderr": 0.002691634510208164, "rougeL_recall": 0.05448506471222756, "rougeL_recall_stderr": 0.0020854622601667937, "rougeLsum_fmeasure": 0.06308719820573185, "rougeLsum_fmeasure_stderr": 0.002213451741392458, "rougeLsum_precision": 0.08551950005220435, "rougeLsum_precision_stderr": 0.0031983492312005384, "rougeLsum_recall": 0.06543250975997009, "rougeLsum_recall_stderr": 0.0024532813023277916}}, "5": {"tldr_en": {"bleu": 1.4470192084599072e-15, "bleu_stderr": 5.1547920765171173e-14, "rouge1_fmeasure": 0.010473201550267177, "rouge1_fmeasure_stderr": 0.0010554421691169314, "rouge1_precision": 0.014515441910190443, "rouge1_precision_stderr": 0.001501466217296952, "rouge1_recall": 0.011301943813768834, "rouge1_recall_stderr": 0.0012288119306628567, "rouge2_fmeasure": 0.0035604598673033626, "rouge2_fmeasure_stderr": 0.0004625418185814249, "rouge2_precision": 0.004591980814271401, "rouge2_precision_stderr": 0.0006515529824929627, "rouge2_recall": 0.00416888931272546, "rouge2_recall_stderr": 0.0005930107839352501, "rougeL_fmeasure": 0.008371164394493067, "rougeL_fmeasure_stderr": 0.0008468942819407445, "rougeL_precision": 0.011779972055249343, "rougeL_precision_stderr": 0.0012586537746088814, "rougeL_recall": 0.009040049894954919, "rougeL_recall_stderr": 0.0009873007391796482, "rougeLsum_fmeasure": 0.009841875351812794, "rougeLsum_fmeasure_stderr": 0.000994934070773035, "rougeLsum_precision": 0.013708349668480058, "rougeLsum_precision_stderr": 0.0014293611241212706, "rougeLsum_recall": 0.010579263673799228, "rougeLsum_recall_stderr": 0.0011521180305532216}}}, "e2e_nlg_cleaned": {"0": {"generate_text_restaurant": {"bleu": 1.8080075016885704, "bleu_stderr": 0.061027545228237855, "rouge1_fmeasure": 0.17861979049522314, "rouge1_fmeasure_stderr": 0.0018002125016461491, "rouge1_precision": 0.1356910382997071, "rouge1_precision_stderr": 0.0015410643240858764, "rouge1_recall": 0.2778453886224831, "rouge1_recall_stderr": 0.0023539268248121705, "rouge2_fmeasure": 0.046215425350075, "rouge2_fmeasure_stderr": 0.0010566397123776003, "rouge2_precision": 0.03490809623131593, "rouge2_precision_stderr": 0.0008357898041576343, "rouge2_recall": 0.07284634942140401, "rouge2_recall_stderr": 0.0015701168954429102, "rougeL_fmeasure": 0.16201597249905292, "rougeL_fmeasure_stderr": 0.0013971090679042123, "rougeL_precision": 0.12227403244327856, "rougeL_precision_stderr": 0.0011855454993101654, "rougeL_recall": 0.2551033251187225, "rougeL_recall_stderr": 0.0019031145709281366, "rougeLsum_fmeasure": 0.14908466648922475, "rougeLsum_fmeasure_stderr": 0.0016626826909044133, "rougeLsum_precision": 0.113242028542405, "rougeLsum_precision_stderr": 0.0013998996791185847, "rougeLsum_recall": 0.23203443734017606, "rougeLsum_recall_stderr": 0.0022390418934348437}}, "1": {"generate_text_restaurant": {"bleu": 12.173849341913149, "bleu_stderr": 0.0669092468478733, "rouge1_fmeasure": 0.48129644782721304, "rouge1_fmeasure_stderr": 0.0023219173855042303, "rouge1_precision": 0.5970385739901486, "rouge1_precision_stderr": 0.003272991717133695, "rouge1_recall": 0.44205108840831364, "rouge1_recall_stderr": 0.002990943407358534, "rouge2_fmeasure": 0.23032000484043905, "rouge2_fmeasure_stderr": 0.0021147211593944798, "rouge2_precision": 0.2911262146867607, "rouge2_precision_stderr": 0.002892523328423528, "rouge2_recall": 0.2107609477318019, "rouge2_recall_stderr": 0.0022166981158979714, "rougeL_fmeasure": 0.34966965256911114, "rougeL_fmeasure_stderr": 0.002108342891501849, "rougeL_precision": 0.4377488624210833, "rougeL_precision_stderr": 0.003110832463080634, "rougeL_recall": 0.3198170788492075, "rougeL_recall_stderr": 0.002444190246186975, "rougeLsum_fmeasure": 0.39331173897680705, "rougeLsum_fmeasure_stderr": 0.0023364505709058668, "rougeLsum_precision": 0.48957738460024036, "rougeLsum_precision_stderr": 0.00327157474691632, "rougeLsum_recall": 0.36068779636155734, "rougeLsum_recall_stderr": 0.0027524175233159713}}, "2": {"generate_text_restaurant": {"bleu": 14.360624153571306, "bleu_stderr": 0.15724700369597677, "rouge1_fmeasure": 0.5041317140273615, "rouge1_fmeasure_stderr": 0.0022753134233410278, "rouge1_precision": 0.6032331597687249, "rouge1_precision_stderr": 0.003142877448057622, "rouge1_recall": 0.4697575589134947, "rouge1_recall_stderr": 0.0029526957130554953, "rouge2_fmeasure": 0.25374280478792693, "rouge2_fmeasure_stderr": 0.002169411661246531, "rouge2_precision": 0.30851618494266825, "rouge2_precision_stderr": 0.002855313490834544, "rouge2_recall": 0.23616858770973606, "rouge2_recall_stderr": 0.002325964607821345, "rougeL_fmeasure": 0.3721296496966484, "rougeL_fmeasure_stderr": 0.002164018647000424, "rougeL_precision": 0.4477614821909179, "rougeL_precision_stderr": 0.003011118677636196, "rougeL_recall": 0.3459816794847227, "rougeL_recall_stderr": 0.002532543665969986, "rougeLsum_fmeasure": 0.42160904040581204, "rougeLsum_fmeasure_stderr": 0.002384317338752149, "rougeLsum_precision": 0.5054563233222107, "rougeLsum_precision_stderr": 0.0032185989379280733, "rougeLsum_recall": 0.39233324008569126, "rougeLsum_recall_stderr": 0.0027964602331100393}}, "3": {"generate_text_restaurant": {"bleu": 15.173778916293744, "bleu_stderr": 0.24020125390484678, "rouge1_fmeasure": 0.5122282123885756, "rouge1_fmeasure_stderr": 0.0022794016747342454, "rouge1_precision": 0.6038782195503243, "rouge1_precision_stderr": 0.003130218028564903, "rouge1_recall": 0.4797961783746489, "rouge1_recall_stderr": 0.0029264432136497623, "rouge2_fmeasure": 0.2611392423531194, "rouge2_fmeasure_stderr": 0.0021928684064362373, "rouge2_precision": 0.31128306325561933, "rouge2_precision_stderr": 0.0028044649859898306, "rouge2_recall": 0.2447494516430458, "rouge2_recall_stderr": 0.002368198668181156, "rougeL_fmeasure": 0.37928627551530325, "rougeL_fmeasure_stderr": 0.0021871071072142663, "rougeL_precision": 0.44868202075612884, "rougeL_precision_stderr": 0.0029681578589764264, "rougeL_recall": 0.35482043982343436, "rougeL_recall_stderr": 0.002532913929369527, "rougeLsum_fmeasure": 0.43123333798993546, "rougeLsum_fmeasure_stderr": 0.002401597688343299, "rougeLsum_precision": 0.5087702457406414, "rougeLsum_precision_stderr": 0.0031818356512290486, "rougeLsum_recall": 0.4036850753818513, "rougeLsum_recall_stderr": 0.0028061971662930287}}, "4": {"generate_text_restaurant": {"bleu": 15.78836334652692, "bleu_stderr": 0.16277087917874616, "rouge1_fmeasure": 0.5201963806927633, "rouge1_fmeasure_stderr": 0.0022664890545995124, "rouge1_precision": 0.6052306848983445, "rouge1_precision_stderr": 0.0031205758451821283, "rouge1_recall": 0.49015291142822803, "rouge1_recall_stderr": 0.002870806275113502, "rouge2_fmeasure": 0.2653610425045864, "rouge2_fmeasure_stderr": 0.0021838284720614534, "rouge2_precision": 0.31194428367362853, "rouge2_precision_stderr": 0.0027609843407215874, "rouge2_recall": 0.2500276639929066, "rouge2_recall_stderr": 0.0023425058959290804, "rougeL_fmeasure": 0.3838642484464721, "rougeL_fmeasure_stderr": 0.002185515405072229, "rougeL_precision": 0.4475978408946653, "rougeL_precision_stderr": 0.002901824428209634, "rougeL_recall": 0.36147111146407906, "rougeL_recall_stderr": 0.002523200720958866, "rougeLsum_fmeasure": 0.43919378367441203, "rougeLsum_fmeasure_stderr": 0.002408659068024605, "rougeLsum_precision": 0.5110579537103325, "rougeLsum_precision_stderr": 0.0031404148777386892, "rougeLsum_recall": 0.4135967411759738, "rougeLsum_recall_stderr": 0.0027946622087117543}}, "5": {"generate_text_restaurant": {"bleu": 15.879323420491742, "bleu_stderr": 0.1522927233333457, "rouge1_fmeasure": 0.5216373530710218, "rouge1_fmeasure_stderr": 0.002262224044659468, "rouge1_precision": 0.6064323245894362, "rouge1_precision_stderr": 0.00315510278665659, "rouge1_recall": 0.49013366730559393, "rouge1_recall_stderr": 0.0028136604439425025, "rouge2_fmeasure": 0.26786622625063644, "rouge2_fmeasure_stderr": 0.002208434520877025, "rouge2_precision": 0.3150817079641561, "rouge2_precision_stderr": 0.002829192112850875, "rouge2_recall": 0.25132514912770915, "rouge2_recall_stderr": 0.002318826430015561, "rougeL_fmeasure": 0.38681699896646954, "rougeL_fmeasure_stderr": 0.002220989687079745, "rougeL_precision": 0.45023806138186195, "rougeL_precision_stderr": 0.002949168521598567, "rougeL_recall": 0.36355539000425124, "rougeL_recall_stderr": 0.002526510160020316, "rougeLsum_fmeasure": 0.4417889417099761, "rougeLsum_fmeasure_stderr": 0.0024158193931717187, "rougeLsum_precision": 0.5137337228447252, "rougeLsum_precision_stderr": 0.0031936836223124105, "rougeLsum_recall": 0.41496788459604567, "rougeLsum_recall_stderr": 0.0027605438893900454}}}, "gem_xsum": {"0": {"article_DOC_summary": {"bleu": 1.9472662234201847, "bleu_stderr": 0.0954010664780363, "rouge1_fmeasure": 0.20062931818668506, "rouge1_fmeasure_stderr": 0.002892087092668822, "rouge1_precision": 0.1512189693389312, "rouge1_precision_stderr": 0.002590198483449934, "rouge1_recall": 0.32951007687075756, "rouge1_recall_stderr": 0.004923756202298708, "rouge2_fmeasure": 0.044133865209903714, "rouge2_fmeasure_stderr": 0.0015693045278532822, "rouge2_precision": 0.03240083882273609, "rouge2_precision_stderr": 0.0011887319293568278, "rouge2_recall": 0.07461053739480651, "rouge2_recall_stderr": 0.0027791525130900266, "rougeL_fmeasure": 0.14533977808404885, "rougeL_fmeasure_stderr": 0.0021630231020242576, "rougeL_precision": 0.11056422701824653, "rougeL_precision_stderr": 0.0021853162208514175, "rougeL_recall": 0.23921769394978765, "rougeL_recall_stderr": 0.003783594428094317, "rougeLsum_fmeasure": 0.15912733837926105, "rougeLsum_fmeasure_stderr": 0.0023937408312475765, "rougeLsum_precision": 0.12055829236568064, "rougeLsum_precision_stderr": 0.002297890666943901, "rougeLsum_recall": 0.2623026232832005, "rougeLsum_recall_stderr": 0.004182995633448934}}, "1": {"article_DOC_summary": {"bleu": 2.857997728240847, "bleu_stderr": 0.15132505328438867, "rouge1_fmeasure": 0.24058051563117627, "rouge1_fmeasure_stderr": 0.003619950901783304, "rouge1_precision": 0.2431489069099882, "rouge1_precision_stderr": 0.004319149380207122, "rouge1_recall": 0.27274551008869324, "rouge1_recall_stderr": 0.004181125297952178, "rouge2_fmeasure": 0.05891708042714147, "rouge2_fmeasure_stderr": 0.002369248568269019, "rouge2_precision": 0.06156338993755893, "rouge2_precision_stderr": 0.0027090151794028584, "rouge2_recall": 0.06564279411701872, "rouge2_recall_stderr": 0.0026141410795920464, "rougeL_fmeasure": 0.1845786738464429, "rougeL_fmeasure_stderr": 0.0030093215424524295, "rougeL_precision": 0.18703509762652787, "rougeL_precision_stderr": 0.0036036431129194833, "rougeL_recall": 0.20956010556672522, "rougeL_recall_stderr": 0.00345405751329193, "rougeLsum_fmeasure": 0.18768186260751757, "rougeLsum_fmeasure_stderr": 0.003017598467168456, "rougeLsum_precision": 0.18954846036997042, "rougeLsum_precision_stderr": 0.0035941447605698394, "rougeLsum_recall": 0.21418956311713871, "rougeLsum_recall_stderr": 0.0035468160066617596}}, "2": {"article_DOC_summary": {"bleu": 3.19195992073562, "bleu_stderr": 0.2067955639958893, "rouge1_fmeasure": 0.24657160673903905, "rouge1_fmeasure_stderr": 0.0037739176215048444, "rouge1_precision": 0.25234682823435783, "rouge1_precision_stderr": 0.004406932928762655, "rouge1_recall": 0.26739840698638306, "rouge1_recall_stderr": 0.0039999072862688684, "rouge2_fmeasure": 0.06271701269177109, "rouge2_fmeasure_stderr": 0.0025663699767628305, "rouge2_precision": 0.06567480327233229, "rouge2_precision_stderr": 0.0027842377535723913, "rouge2_recall": 0.06599412859644187, "rouge2_recall_stderr": 0.0026775951767211374, "rougeL_fmeasure": 0.1876781101224112, "rougeL_fmeasure_stderr": 0.0031437463539169125, "rougeL_precision": 0.1921361411782326, "rougeL_precision_stderr": 0.0036263536814562453, "rougeL_recall": 0.20386135964058816, "rougeL_recall_stderr": 0.0033147209011893724, "rougeLsum_fmeasure": 0.1896272533115015, "rougeLsum_fmeasure_stderr": 0.0031550558124475133, "rougeLsum_precision": 0.19374913452852363, "rougeLsum_precision_stderr": 0.0036251531161871544, "rougeLsum_recall": 0.20676693183261305, "rougeLsum_recall_stderr": 0.0034014354284824795}}, "3": {"article_DOC_summary": {"bleu": 3.267835808853254, "bleu_stderr": 0.26356764701611307, "rouge1_fmeasure": 0.23697855013529284, "rouge1_fmeasure_stderr": 0.003931784147472208, "rouge1_precision": 0.2511767032658256, "rouge1_precision_stderr": 0.004670743744963309, "rouge1_recall": 0.2497224746972405, "rouge1_recall_stderr": 0.004054437554455434, "rouge2_fmeasure": 0.059313458488013185, "rouge2_fmeasure_stderr": 0.0025641694242472487, "rouge2_precision": 0.06435388180319074, "rouge2_precision_stderr": 0.002934840810442915, "rouge2_recall": 0.060376215777618605, "rouge2_recall_stderr": 0.002521653823700491, "rougeL_fmeasure": 0.17977672776005849, "rougeL_fmeasure_stderr": 0.00326317345808302, "rougeL_precision": 0.19057534922020994, "rougeL_precision_stderr": 0.0038620821553629983, "rougeL_recall": 0.1901634518957205, "rougeL_recall_stderr": 0.0033714037003502494, "rougeLsum_fmeasure": 0.18163235303784986, "rougeLsum_fmeasure_stderr": 0.003264460230665997, "rougeLsum_precision": 0.19211901704097034, "rougeLsum_precision_stderr": 0.003850775083612694, "rougeLsum_recall": 0.19288110429850555, "rougeLsum_recall_stderr": 0.003421247538700275}}, "4": {"article_DOC_summary": {"bleu": 0.17970307621766216, "bleu_stderr": 0.04965869269887041, "rouge1_fmeasure": 0.05891769720848019, "rouge1_fmeasure_stderr": 0.0035369396004201713, "rouge1_precision": 0.06645727693786248, "rouge1_precision_stderr": 0.004158365862658779, "rouge1_recall": 0.061174931724787315, "rouge1_recall_stderr": 0.003797370735030977, "rouge2_fmeasure": 0.015297632126595406, "rouge2_fmeasure_stderr": 0.00149002417901287, "rouge2_precision": 0.01730890961224063, "rouge2_precision_stderr": 0.0017698712455992984, "rouge2_recall": 0.016289532767626923, "rouge2_recall_stderr": 0.0017234032328131926, "rougeL_fmeasure": 0.04476173097758684, "rougeL_fmeasure_stderr": 0.0027730017560448727, "rougeL_precision": 0.050637820115463826, "rougeL_precision_stderr": 0.0032826504244346, "rougeL_recall": 0.04683971382625969, "rougeL_recall_stderr": 0.003039332848507969, "rougeLsum_fmeasure": 0.04533434532971928, "rougeLsum_fmeasure_stderr": 0.0028025558912498296, "rougeLsum_precision": 0.051192679124604304, "rougeLsum_precision_stderr": 0.0033047254109378095, "rougeLsum_recall": 0.0475395827212547, "rougeLsum_recall_stderr": 0.0030900986283582004}}, "5": {"article_DOC_summary": {"bleu": 1.393056311124318e-43, "bleu_stderr": 1.2487431746784071e-33, "rouge1_fmeasure": 0.0025036711184808556, "rouge1_fmeasure_stderr": 0.000808568948388182, "rouge1_precision": 0.0025272416860947825, "rouge1_precision_stderr": 0.0007813236132809655, "rouge1_recall": 0.002586618259740399, "rouge1_recall_stderr": 0.0008670624223009818, "rouge2_fmeasure": 0.0003242107125389267, "rouge2_fmeasure_stderr": 0.00014221025181447073, "rouge2_precision": 0.0003236042782341223, "rouge2_precision_stderr": 0.0001381414258477455, "rouge2_recall": 0.0003324696313480705, "rouge2_recall_stderr": 0.00015129466488844655, "rougeL_fmeasure": 0.00159555474061474, "rougeL_fmeasure_stderr": 0.0004956987539243005, "rougeL_precision": 0.0016454419652040672, "rougeL_precision_stderr": 0.0004929867496820194, "rougeL_recall": 0.001639076487035711, "rougeL_recall_stderr": 0.0005281423440330004, "rougeLsum_fmeasure": 0.00159555474061474, "rougeLsum_fmeasure_stderr": 0.0004956987539243005, "rougeLsum_precision": 0.0016454419652040672, "rougeLsum_precision_stderr": 0.0004929867496820194, "rougeLsum_recall": 0.001639076487035711, "rougeLsum_recall_stderr": 0.0005281423440330004}}}} |