File size: 28,019 Bytes
b220bd1
1
{"GEM/web_nlg_en": {"0": {"PALM_prompt": {"bleu": 0.4373157998206226, "bleu_stderr": 0.056741486001354216, "rouge1_fmeasure": 0.10947380559420297, "rouge1_fmeasure_stderr": 0.0022511546576554292, "rouge1_precision": 0.07630675677312203, "rouge1_precision_stderr": 0.0021365872076980082, "rouge1_recall": 0.2947830429134024, "rouge1_recall_stderr": 0.0047665492114514684, "rouge2_fmeasure": 0.051001464150726095, "rouge2_fmeasure_stderr": 0.0014146940985046523, "rouge2_precision": 0.03437396040114199, "rouge2_precision_stderr": 0.0011646295650624351, "rouge2_recall": 0.13907462394894776, "rouge2_recall_stderr": 0.0031715068123442996, "rougeL_fmeasure": 0.10417993615217146, "rougeL_fmeasure_stderr": 0.002043414019393663, "rougeL_precision": 0.07227253003813615, "rougeL_precision_stderr": 0.001955466598501427, "rougeL_recall": 0.28336049631237586, "rougeL_recall_stderr": 0.004569573466829386, "rougeLsum_fmeasure": 0.10462419732455051, "rougeLsum_fmeasure_stderr": 0.002115527416565905, "rougeLsum_precision": 0.07290032072974349, "rougeLsum_precision_stderr": 0.002034641349821296, "rougeLsum_recall": 0.2825727583996548, "rougeLsum_recall_stderr": 0.004541613699421234}}, "1": {"PALM_prompt": {"bleu": 0.5816764130686213, "bleu_stderr": 0.054147923323820346, "rouge1_fmeasure": 0.11727270364668571, "rouge1_fmeasure_stderr": 0.0021476260743326565, "rouge1_precision": 0.07783086970109386, "rouge1_precision_stderr": 0.001926390801136041, "rouge1_recall": 0.36711372145643695, "rouge1_recall_stderr": 0.005207087210896133, "rouge2_fmeasure": 0.05455324665630359, "rouge2_fmeasure_stderr": 0.0013665856855669073, "rouge2_precision": 0.035941971570071736, "rouge2_precision_stderr": 0.0011116447277521812, "rouge2_recall": 0.17604536516651662, "rouge2_recall_stderr": 0.0036353372642678756, "rougeL_fmeasure": 0.10871994085882164, "rougeL_fmeasure_stderr": 0.0019153699814912425, "rougeL_precision": 0.07209000868611247, "rougeL_precision_stderr": 0.0017559014471748775, "rougeL_recall": 0.33901675935925657, "rougeL_recall_stderr": 0.004687996190515175, "rougeLsum_fmeasure": 0.11053867463797286, "rougeLsum_fmeasure_stderr": 0.0020173857832705686, "rougeLsum_precision": 0.0735230628158407, "rougeLsum_precision_stderr": 0.0018435905984185187, "rougeLsum_recall": 0.34433610068323095, "rougeLsum_recall_stderr": 0.004792623835429767}}, "2": {"PALM_prompt": {"bleu": 0.6801735381749798, "bleu_stderr": 0.04514863078336761, "rouge1_fmeasure": 0.11972585427910692, "rouge1_fmeasure_stderr": 0.001963983917319172, "rouge1_precision": 0.07666591908388082, "rouge1_precision_stderr": 0.0015425382902699712, "rouge1_recall": 0.40028519820196484, "rouge1_recall_stderr": 0.0053218199498182555, "rouge2_fmeasure": 0.055583861631680276, "rouge2_fmeasure_stderr": 0.0012687258801338563, "rouge2_precision": 0.03562073396147935, "rouge2_precision_stderr": 0.0009954366405729978, "rouge2_recall": 0.19724892000097954, "rouge2_recall_stderr": 0.004019172908229666, "rougeL_fmeasure": 0.10999138993564177, "rougeL_fmeasure_stderr": 0.0017648420950003858, "rougeL_precision": 0.07037367893965144, "rougeL_precision_stderr": 0.0013558489579657599, "rougeL_recall": 0.3648716666842121, "rougeL_recall_stderr": 0.004723267009132289, "rougeLsum_fmeasure": 0.1122905686653009, "rougeLsum_fmeasure_stderr": 0.0018425170251459826, "rougeLsum_precision": 0.07198504559682002, "rougeLsum_precision_stderr": 0.0014532243063151847, "rougeLsum_recall": 0.3737640227903558, "rougeLsum_recall_stderr": 0.004892612299725926}}, "3": {"PALM_prompt": {"bleu": 0.8393015493701177, "bleu_stderr": 0.049868510474836, "rouge1_fmeasure": 0.12332290364001403, "rouge1_fmeasure_stderr": 0.0020213255478620834, "rouge1_precision": 0.07934496701755703, "rouge1_precision_stderr": 0.0017108996646152186, "rouge1_recall": 0.41957311539245606, "rouge1_recall_stderr": 0.005383968460349908, "rouge2_fmeasure": 0.05769919253564089, "rouge2_fmeasure_stderr": 0.001315453385968732, "rouge2_precision": 0.03700401446806371, "rouge2_precision_stderr": 0.0010754080423489075, "rouge2_recall": 0.20785188427731804, "rouge2_recall_stderr": 0.0039850136524860235, "rougeL_fmeasure": 0.11171273283361995, "rougeL_fmeasure_stderr": 0.0017620828691461753, "rougeL_precision": 0.07186075331384528, "rougeL_precision_stderr": 0.0015065682717614625, "rougeL_recall": 0.3792930717112658, "rougeL_recall_stderr": 0.004756348746075166, "rougeLsum_fmeasure": 0.11543602475589927, "rougeLsum_fmeasure_stderr": 0.001888123216509075, "rougeLsum_precision": 0.07439776049493438, "rougeLsum_precision_stderr": 0.0016078356678010679, "rougeLsum_recall": 0.39147213524665503, "rougeLsum_recall_stderr": 0.004968164479358761}}, "4": {"PALM_prompt": {"bleu": 0.8436391155168642, "bleu_stderr": 0.049789928911136136, "rouge1_fmeasure": 0.12951808355992003, "rouge1_fmeasure_stderr": 0.0019403013558157668, "rouge1_precision": 0.08188000384427346, "rouge1_precision_stderr": 0.0015429926759057174, "rouge1_recall": 0.45225212783083296, "rouge1_recall_stderr": 0.005452056426418837, "rouge2_fmeasure": 0.06050302495157815, "rouge2_fmeasure_stderr": 0.0012369724150331927, "rouge2_precision": 0.03789712819393572, "rouge2_precision_stderr": 0.0009152136077591718, "rouge2_recall": 0.22689495723762804, "rouge2_recall_stderr": 0.004067188852506108, "rougeL_fmeasure": 0.11592286526905457, "rougeL_fmeasure_stderr": 0.0016906240203803347, "rougeL_precision": 0.07330729359090057, "rougeL_precision_stderr": 0.0013644419423480823, "rougeL_recall": 0.4045943171397325, "rougeL_recall_stderr": 0.0048320778663538955, "rougeLsum_fmeasure": 0.12060522562383363, "rougeLsum_fmeasure_stderr": 0.0018022149452879743, "rougeLsum_precision": 0.07637812548771711, "rougeLsum_precision_stderr": 0.0014540942217052375, "rougeLsum_recall": 0.4207633762253156, "rougeLsum_recall_stderr": 0.005005614020197891}}, "5": {"PALM_prompt": {"bleu": 0.968801645723095, "bleu_stderr": 0.05462868115593731, "rouge1_fmeasure": 0.13468892691608006, "rouge1_fmeasure_stderr": 0.0019240731337134673, "rouge1_precision": 0.08408541082259362, "rouge1_precision_stderr": 0.001415159971957011, "rouge1_recall": 0.4730441639084742, "rouge1_recall_stderr": 0.005431978662817184, "rouge2_fmeasure": 0.06252454636994373, "rouge2_fmeasure_stderr": 0.0012377179103821956, "rouge2_precision": 0.038803485654806714, "rouge2_precision_stderr": 0.0008788058278028121, "rouge2_recall": 0.2379631167113304, "rouge2_recall_stderr": 0.004152278672512853, "rougeL_fmeasure": 0.11896213494013362, "rougeL_fmeasure_stderr": 0.001650634135835398, "rougeL_precision": 0.07423644311431606, "rougeL_precision_stderr": 0.0012142160071926726, "rougeL_recall": 0.4194644730807224, "rougeL_recall_stderr": 0.0047799777603664715, "rougeLsum_fmeasure": 0.12479160570822044, "rougeLsum_fmeasure_stderr": 0.0017844920178026805, "rougeLsum_precision": 0.07800322392434518, "rougeLsum_precision_stderr": 0.0013202039315876929, "rougeLsum_recall": 0.43851085762444947, "rougeLsum_recall_stderr": 0.004968418620592047}}}, "GEM/wiki_lingua_en": {"0": {"tldr_en": {"bleu": 1.8310798418084737, "bleu_stderr": 0.06119305662626742, "rouge1_fmeasure": 0.19188833167040015, "rouge1_fmeasure_stderr": 0.0018702943944022418, "rouge1_precision": 0.1628352267958049, "rouge1_precision_stderr": 0.0019076289743005436, "rouge1_recall": 0.28137034403026634, "rouge1_recall_stderr": 0.002726139405286867, "rouge2_fmeasure": 0.04191366659253858, "rouge2_fmeasure_stderr": 0.000917658619128283, "rouge2_precision": 0.035168122195033014, "rouge2_precision_stderr": 0.0008051014260490183, "rouge2_recall": 0.06371619685684557, "rouge2_recall_stderr": 0.0015314676134498058, "rougeL_fmeasure": 0.14614932555210797, "rougeL_fmeasure_stderr": 0.0012956973040530264, "rougeL_precision": 0.12246239102421737, "rougeL_precision_stderr": 0.001285311648356421, "rougeL_recall": 0.2201424968967575, "rougeL_recall_stderr": 0.0022006617198564397, "rougeLsum_fmeasure": 0.17662543049894286, "rougeLsum_fmeasure_stderr": 0.001716560474974557, "rougeLsum_precision": 0.14960133985735732, "rougeLsum_precision_stderr": 0.0017445585328390875, "rougeLsum_recall": 0.2600296050390341, "rougeLsum_recall_stderr": 0.002552101400202146}}, "1": {"tldr_en": {"bleu": 2.463691563435929, "bleu_stderr": 0.056238669871763534, "rouge1_fmeasure": 0.20607218590152535, "rouge1_fmeasure_stderr": 0.0019348192676270253, "rouge1_precision": 0.17507251962841255, "rouge1_precision_stderr": 0.0019979193178610104, "rouge1_recall": 0.3008600636001003, "rouge1_recall_stderr": 0.002760929751246215, "rouge2_fmeasure": 0.04827166271383884, "rouge2_fmeasure_stderr": 0.000981638580890638, "rouge2_precision": 0.040814840621502924, "rouge2_precision_stderr": 0.0008769075552676463, "rouge2_recall": 0.07239534384858555, "rouge2_recall_stderr": 0.0015745819458817655, "rougeL_fmeasure": 0.14993882097099004, "rougeL_fmeasure_stderr": 0.0013143528095662098, "rougeL_precision": 0.12604513290190442, "rougeL_precision_stderr": 0.001331288983523961, "rougeL_recall": 0.22410236240350495, "rougeL_recall_stderr": 0.0021252698749924166, "rougeLsum_fmeasure": 0.19267274247494454, "rougeLsum_fmeasure_stderr": 0.0018042087124662393, "rougeLsum_precision": 0.1634506211607229, "rougeLsum_precision_stderr": 0.0018573519091366366, "rougeLsum_recall": 0.282240921650429, "rougeLsum_recall_stderr": 0.002619133620350951}}, "2": {"tldr_en": {"bleu": 3.013745331324814, "bleu_stderr": 0.06592229302797037, "rouge1_fmeasure": 0.22344837173188767, "rouge1_fmeasure_stderr": 0.0018933971382747686, "rouge1_precision": 0.19198287608229725, "rouge1_precision_stderr": 0.0021092410953077365, "rouge1_recall": 0.32589953688933776, "rouge1_recall_stderr": 0.002753157025629824, "rouge2_fmeasure": 0.05600464749019431, "rouge2_fmeasure_stderr": 0.001035304930307184, "rouge2_precision": 0.048137852198349124, "rouge2_precision_stderr": 0.0010124293758406351, "rouge2_recall": 0.08482162860321114, "rouge2_recall_stderr": 0.0017481381213950958, "rougeL_fmeasure": 0.15854970566001372, "rougeL_fmeasure_stderr": 0.0012774189115518982, "rougeL_precision": 0.13481580311964722, "rougeL_precision_stderr": 0.0014071194011638184, "rougeL_recall": 0.23733416551629913, "rougeL_recall_stderr": 0.00219502068666546, "rougeLsum_fmeasure": 0.21107970658856343, "rougeLsum_fmeasure_stderr": 0.0017866890110014018, "rougeLsum_precision": 0.18117711700554173, "rougeLsum_precision_stderr": 0.0019909544088953742, "rougeLsum_recall": 0.30882558318305736, "rougeLsum_recall_stderr": 0.0026454321668364913}}, "3": {"tldr_en": {"bleu": 2.986263870634216, "bleu_stderr": 0.0869488541072268, "rouge1_fmeasure": 0.1883894874399809, "rouge1_fmeasure_stderr": 0.0022518375274135087, "rouge1_precision": 0.16688833624223554, "rouge1_precision_stderr": 0.0024001395431129838, "rouge1_recall": 0.27404204769144364, "rouge1_recall_stderr": 0.003375962083519381, "rouge2_fmeasure": 0.04708204631655152, "rouge2_fmeasure_stderr": 0.0010069752068567668, "rouge2_precision": 0.04136653299690803, "rouge2_precision_stderr": 0.0010174651332227344, "rouge2_recall": 0.07172155304298297, "rouge2_recall_stderr": 0.0017383368313820028, "rougeL_fmeasure": 0.13391288059874437, "rougeL_fmeasure_stderr": 0.001564486351392238, "rougeL_precision": 0.11810699062222797, "rougeL_precision_stderr": 0.001714836740267086, "rougeL_recall": 0.19959382723616914, "rougeL_recall_stderr": 0.002605476332476844, "rougeLsum_fmeasure": 0.17834159419543702, "rougeLsum_fmeasure_stderr": 0.002133544799751138, "rougeLsum_precision": 0.15789252138792423, "rougeLsum_precision_stderr": 0.0022764600108588808, "rougeLsum_recall": 0.26023963410461465, "rougeLsum_recall_stderr": 0.003240567155894993}}, "4": {"tldr_en": {"bleu": 0.7653537900871676, "bleu_stderr": 0.049323102026813614, "rouge1_fmeasure": 0.06229352605061771, "rouge1_fmeasure_stderr": 0.002059973094043126, "rouge1_precision": 0.05571162128505982, "rouge1_precision_stderr": 0.0019790843122430768, "rouge1_recall": 0.09490155511879607, "rouge1_recall_stderr": 0.003216109108055619, "rouge2_fmeasure": 0.01596233535299914, "rouge2_fmeasure_stderr": 0.0007332643966253175, "rouge2_precision": 0.013746904154847127, "rouge2_precision_stderr": 0.000658207908545434, "rouge2_recall": 0.02605352352304377, "rouge2_recall_stderr": 0.0013317962968417952, "rougeL_fmeasure": 0.04502172063067562, "rougeL_fmeasure_stderr": 0.0014806563009305842, "rougeL_precision": 0.04028867827357096, "rougeL_precision_stderr": 0.0014354449068175981, "rougeL_recall": 0.07013160574213247, "rougeL_recall_stderr": 0.0024380518058086703, "rougeLsum_fmeasure": 0.05884434373920439, "rougeLsum_fmeasure_stderr": 0.0019486127272992522, "rougeLsum_precision": 0.0526446584524354, "rougeLsum_precision_stderr": 0.0018735818695187819, "rougeLsum_recall": 0.08977749314111799, "rougeLsum_recall_stderr": 0.0030541817569144}}, "5": {"tldr_en": {"bleu": 2.313122283850011e-06, "bleu_stderr": 4.438365983452618e-06, "rouge1_fmeasure": 0.010262809104423124, "rouge1_fmeasure_stderr": 0.000941433577191994, "rouge1_precision": 0.009989872401580602, "rouge1_precision_stderr": 0.0009952828000827124, "rouge1_recall": 0.015276156161555617, "rouge1_recall_stderr": 0.001444671711873694, "rouge2_fmeasure": 0.0025848086028049965, "rouge2_fmeasure_stderr": 0.0003301678198930521, "rouge2_precision": 0.0024167502513949756, "rouge2_precision_stderr": 0.00033798462070527304, "rouge2_recall": 0.004213844763908219, "rouge2_recall_stderr": 0.0006183240014712593, "rougeL_fmeasure": 0.007530769725575652, "rougeL_fmeasure_stderr": 0.0006918159097560924, "rougeL_precision": 0.007350732687047713, "rougeL_precision_stderr": 0.000736612195363616, "rougeL_recall": 0.011512337859684543, "rougeL_recall_stderr": 0.0011311946838375108, "rougeLsum_fmeasure": 0.009601062566883777, "rougeLsum_fmeasure_stderr": 0.0008823539930029628, "rougeLsum_precision": 0.009401823549618816, "rougeLsum_precision_stderr": 0.0009477935776177291, "rougeLsum_recall": 0.014304994804442096, "rougeLsum_recall_stderr": 0.0013529102153531946}}}, "e2e_nlg_cleaned": {"0": {"generate_text_restaurant": {"bleu": 0.3016960813220789, "bleu_stderr": 0.04082243698870125, "rouge1_fmeasure": 0.08446489060239885, "rouge1_fmeasure_stderr": 0.000832880994211257, "rouge1_precision": 0.0628362517057776, "rouge1_precision_stderr": 0.0006647851313912593, "rouge1_recall": 0.137799699754724, "rouge1_recall_stderr": 0.0013399199497499206, "rouge2_fmeasure": 0.013098749477153882, "rouge2_fmeasure_stderr": 0.00036393407871382073, "rouge2_precision": 0.009897778438587298, "rouge2_precision_stderr": 0.0002813167869752497, "rouge2_recall": 0.02030644827526888, "rouge2_recall_stderr": 0.0005626168002295672, "rougeL_fmeasure": 0.08185345358329085, "rougeL_fmeasure_stderr": 0.0007758077715250189, "rougeL_precision": 0.060894085509621707, "rougeL_precision_stderr": 0.0006165662598640652, "rougeL_recall": 0.1334600824136164, "rougeL_recall_stderr": 0.0012622226683087598, "rougeLsum_fmeasure": 0.07821933484300712, "rougeLsum_fmeasure_stderr": 0.000742258462877918, "rougeLsum_precision": 0.05822489106803366, "rougeLsum_precision_stderr": 0.00059732648786741, "rougeLsum_recall": 0.12759747263850774, "rougeLsum_recall_stderr": 0.0011920315451119745}}, "1": {"generate_text_restaurant": {"bleu": 9.014911506469076, "bleu_stderr": 0.10639404635916568, "rouge1_fmeasure": 0.4071860181343587, "rouge1_fmeasure_stderr": 0.002172401493926826, "rouge1_precision": 0.4220547738164344, "rouge1_precision_stderr": 0.0029747898853502135, "rouge1_recall": 0.44890682882262095, "rouge1_recall_stderr": 0.0030482256607117985, "rouge2_fmeasure": 0.17675735102863532, "rouge2_fmeasure_stderr": 0.0016983524897307275, "rouge2_precision": 0.18398717679998686, "rouge2_precision_stderr": 0.002070314538395242, "rouge2_recall": 0.19695708046780447, "rouge2_recall_stderr": 0.0021253468809232486, "rougeL_fmeasure": 0.2901955244768342, "rougeL_fmeasure_stderr": 0.0017445755551563752, "rougeL_precision": 0.301979337271323, "rougeL_precision_stderr": 0.002426170411020153, "rougeL_recall": 0.32120889976820555, "rougeL_recall_stderr": 0.0024556761259021593, "rougeLsum_fmeasure": 0.3366538075182426, "rougeLsum_fmeasure_stderr": 0.0020840116286440125, "rougeLsum_precision": 0.3498631569304881, "rougeLsum_precision_stderr": 0.00275693533807641, "rougeLsum_recall": 0.3704033862486897, "rougeLsum_recall_stderr": 0.00277359280896307}}, "2": {"generate_text_restaurant": {"bleu": 11.1355912496663, "bleu_stderr": 0.13104161087327487, "rouge1_fmeasure": 0.4449026725503146, "rouge1_fmeasure_stderr": 0.0020303864410380614, "rouge1_precision": 0.45419518183344554, "rouge1_precision_stderr": 0.0027266345121146297, "rouge1_recall": 0.48044140772752547, "rouge1_recall_stderr": 0.002817950150203246, "rouge2_fmeasure": 0.20791813280930055, "rouge2_fmeasure_stderr": 0.0017732074653438918, "rouge2_precision": 0.2124884501715128, "rouge2_precision_stderr": 0.0020421137596173576, "rouge2_recall": 0.22663601203825093, "rouge2_recall_stderr": 0.0021799430214164035, "rougeL_fmeasure": 0.32200623778436555, "rougeL_fmeasure_stderr": 0.0017788348099423016, "rougeL_precision": 0.32873823752244813, "rougeL_precision_stderr": 0.002262430136729236, "rougeL_recall": 0.34880236417169236, "rougeL_recall_stderr": 0.0024064753259342344, "rougeLsum_fmeasure": 0.37259609212766276, "rougeLsum_fmeasure_stderr": 0.0020305961255707534, "rougeLsum_precision": 0.38047010773438, "rougeLsum_precision_stderr": 0.002559842275120574, "rougeLsum_recall": 0.40224234667337105, "rougeLsum_recall_stderr": 0.002660545444016772}}, "3": {"generate_text_restaurant": {"bleu": 12.10470203084112, "bleu_stderr": 0.160895558301053, "rouge1_fmeasure": 0.4492382386896765, "rouge1_fmeasure_stderr": 0.0019699301602619833, "rouge1_precision": 0.45456971607102353, "rouge1_precision_stderr": 0.0023960763531178423, "rouge1_recall": 0.47953391372338766, "rouge1_recall_stderr": 0.0027865520920584822, "rouge2_fmeasure": 0.2138339925008178, "rouge2_fmeasure_stderr": 0.0018445417129634963, "rouge2_precision": 0.2163784140584202, "rouge2_precision_stderr": 0.001980036007401307, "rouge2_recall": 0.23028758666497792, "rouge2_recall_stderr": 0.0022756293438486903, "rougeL_fmeasure": 0.3303919839118561, "rougeL_fmeasure_stderr": 0.001783388701966232, "rougeL_precision": 0.33426681511660167, "rougeL_precision_stderr": 0.002069523940604892, "rougeL_recall": 0.35354783483337526, "rougeL_recall_stderr": 0.0024228991972543336, "rougeLsum_fmeasure": 0.378239342272828, "rougeLsum_fmeasure_stderr": 0.002043462221499771, "rougeLsum_precision": 0.3827360863233357, "rougeLsum_precision_stderr": 0.002359678766192712, "rougeLsum_recall": 0.40399025031746394, "rougeLsum_recall_stderr": 0.002710450542079631}}, "4": {"generate_text_restaurant": {"bleu": 12.44085622955195, "bleu_stderr": 0.13067375364343567, "rouge1_fmeasure": 0.4511875093908521, "rouge1_fmeasure_stderr": 0.001948885960105966, "rouge1_precision": 0.45479182860495637, "rouge1_precision_stderr": 0.0023107278825576553, "rouge1_recall": 0.48017725960351876, "rouge1_recall_stderr": 0.0027316537664281945, "rouge2_fmeasure": 0.21707781052843164, "rouge2_fmeasure_stderr": 0.00185164014349205, "rouge2_precision": 0.21833473257724795, "rouge2_precision_stderr": 0.0019502917664114363, "rouge2_recall": 0.23333710855434647, "rouge2_recall_stderr": 0.002269432186215575, "rougeL_fmeasure": 0.33434874026181494, "rougeL_fmeasure_stderr": 0.0017786642192651214, "rougeL_precision": 0.3366370287941819, "rougeL_precision_stderr": 0.0019965287497770777, "rougeL_recall": 0.35684028344910274, "rougeL_recall_stderr": 0.0024057773390550254, "rougeLsum_fmeasure": 0.38297835064075053, "rougeLsum_fmeasure_stderr": 0.0020438066934495387, "rougeLsum_precision": 0.38571523251054607, "rougeLsum_precision_stderr": 0.0022865314323742805, "rougeLsum_recall": 0.40803304829345277, "rougeLsum_recall_stderr": 0.0027038368009947755}}, "5": {"generate_text_restaurant": {"bleu": 12.352678257477072, "bleu_stderr": 0.1229858870702429, "rouge1_fmeasure": 0.4520495564262539, "rouge1_fmeasure_stderr": 0.0019091091728356577, "rouge1_precision": 0.4536679355694742, "rouge1_precision_stderr": 0.002282805690194143, "rouge1_recall": 0.48257839264210245, "rouge1_recall_stderr": 0.002694452362144022, "rouge2_fmeasure": 0.21807002700335165, "rouge2_fmeasure_stderr": 0.0018243298667958761, "rouge2_precision": 0.2184937204533077, "rouge2_precision_stderr": 0.0019084340007320115, "rouge2_recall": 0.2348008779716612, "rouge2_recall_stderr": 0.0022303214323899125, "rougeL_fmeasure": 0.336313193439231, "rougeL_fmeasure_stderr": 0.001791714678974818, "rougeL_precision": 0.33692930278278704, "rougeL_precision_stderr": 0.0019923203298548866, "rougeL_recall": 0.36002100624003847, "rougeL_recall_stderr": 0.0024053149539646364, "rougeLsum_fmeasure": 0.38490335194628533, "rougeLsum_fmeasure_stderr": 0.002018489316229454, "rougeLsum_precision": 0.38599958036488224, "rougeLsum_precision_stderr": 0.002272531904720447, "rougeLsum_recall": 0.4113378384062774, "rougeLsum_recall_stderr": 0.002667546056299814}}}, "gem_xsum": {"0": {"article_DOC_summary": {"bleu": 2.194933977793404, "bleu_stderr": 0.09650169688197711, "rouge1_fmeasure": 0.2157374708631877, "rouge1_fmeasure_stderr": 0.002508783327476019, "rouge1_precision": 0.15954668519186138, "rouge1_precision_stderr": 0.002100617390256336, "rouge1_recall": 0.36309739763041776, "rouge1_recall_stderr": 0.004368615445871372, "rouge2_fmeasure": 0.05279448511938101, "rouge2_fmeasure_stderr": 0.001664044690700437, "rouge2_precision": 0.03857312620535916, "rouge2_precision_stderr": 0.0012905906114606838, "rouge2_recall": 0.09177566784631346, "rouge2_recall_stderr": 0.0029866334470645636, "rougeL_fmeasure": 0.1604319788556621, "rougeL_fmeasure_stderr": 0.0019556284658093183, "rougeL_precision": 0.11839547499241576, "rougeL_precision_stderr": 0.001646949604960197, "rougeL_recall": 0.27198898577078495, "rougeL_recall_stderr": 0.0035222426961979128, "rougeLsum_fmeasure": 0.1697976651408494, "rougeLsum_fmeasure_stderr": 0.002135233558113895, "rougeLsum_precision": 0.1250746587410693, "rougeLsum_precision_stderr": 0.0017464873888176696, "rougeLsum_recall": 0.28828909491111, "rougeLsum_recall_stderr": 0.0038785736556512756}}, "1": {"article_DOC_summary": {"bleu": 1.638275312642142, "bleu_stderr": 0.11197811159644402, "rouge1_fmeasure": 0.18261422772647087, "rouge1_fmeasure_stderr": 0.00258517997013667, "rouge1_precision": 0.130085376048313, "rouge1_precision_stderr": 0.0019273226219467348, "rouge1_recall": 0.31899443410148204, "rouge1_recall_stderr": 0.004375864955378675, "rouge2_fmeasure": 0.03829439148207006, "rouge2_fmeasure_stderr": 0.0015268296315399182, "rouge2_precision": 0.027035766317831913, "rouge2_precision_stderr": 0.0010834329723279196, "rouge2_recall": 0.06843246331973844, "rouge2_recall_stderr": 0.002783755254166952, "rougeL_fmeasure": 0.13872448607191418, "rougeL_fmeasure_stderr": 0.0019214547149178605, "rougeL_precision": 0.09860861520075329, "rougeL_precision_stderr": 0.0014180838773530536, "rougeL_recall": 0.2439616017337858, "rougeL_recall_stderr": 0.003388978319546548, "rougeLsum_fmeasure": 0.14673205236069722, "rougeLsum_fmeasure_stderr": 0.002156691093638724, "rougeLsum_precision": 0.10431817474650688, "rougeLsum_precision_stderr": 0.0015880489605249845, "rougeLsum_recall": 0.25778306821268704, "rougeLsum_recall_stderr": 0.0037812899736781526}}, "2": {"article_DOC_summary": {"bleu": 2.0210914476360786, "bleu_stderr": 0.12454216962651855, "rouge1_fmeasure": 0.1978001315070318, "rouge1_fmeasure_stderr": 0.002669936318830053, "rouge1_precision": 0.14059986141007405, "rouge1_precision_stderr": 0.001980010991959053, "rouge1_recall": 0.34704590818514364, "rouge1_recall_stderr": 0.004609783640663682, "rouge2_fmeasure": 0.04760922765448965, "rouge2_fmeasure_stderr": 0.001702755511678876, "rouge2_precision": 0.033448694107769246, "rouge2_precision_stderr": 0.0011984145262489562, "rouge2_recall": 0.08605872654054372, "rouge2_recall_stderr": 0.003191665944600775, "rougeL_fmeasure": 0.1511855886298728, "rougeL_fmeasure_stderr": 0.0020261890172370246, "rougeL_precision": 0.10721276455620249, "rougeL_precision_stderr": 0.0014796729903083395, "rougeL_recall": 0.26727650609085896, "rougeL_recall_stderr": 0.0036995069904560843, "rougeLsum_fmeasure": 0.16004925294103853, "rougeLsum_fmeasure_stderr": 0.0022364087298009884, "rougeLsum_precision": 0.11346372550782761, "rougeLsum_precision_stderr": 0.0016303825401644061, "rougeLsum_recall": 0.28288787023938955, "rougeLsum_recall_stderr": 0.004038388892533831}}, "3": {"article_DOC_summary": {"bleu": 2.03791695157546, "bleu_stderr": 0.1342348737065576, "rouge1_fmeasure": 0.19482488018157684, "rouge1_fmeasure_stderr": 0.0028449440307477085, "rouge1_precision": 0.14077378985561326, "rouge1_precision_stderr": 0.002167627071465062, "rouge1_recall": 0.3365881713882994, "rouge1_recall_stderr": 0.004904093832075129, "rouge2_fmeasure": 0.04702347182983231, "rouge2_fmeasure_stderr": 0.001623530160402657, "rouge2_precision": 0.03346907677060051, "rouge2_precision_stderr": 0.00115993469618386, "rouge2_recall": 0.08385926778368435, "rouge2_recall_stderr": 0.0030304591639245464, "rougeL_fmeasure": 0.14665273300314152, "rougeL_fmeasure_stderr": 0.00212580713201847, "rougeL_precision": 0.10579758272401656, "rougeL_precision_stderr": 0.0016080916023179224, "rougeL_recall": 0.25509688514423123, "rougeL_recall_stderr": 0.003826588022233898, "rougeLsum_fmeasure": 0.15621401458929957, "rougeLsum_fmeasure_stderr": 0.00234420229722605, "rougeLsum_precision": 0.11263878026618175, "rougeLsum_precision_stderr": 0.00176128619109869, "rougeLsum_recall": 0.2715816804884895, "rougeLsum_recall_stderr": 0.004199504898315826}}, "4": {"article_DOC_summary": {"bleu": 0.9907623400783704, "bleu_stderr": 0.12144441541342028, "rouge1_fmeasure": 0.05341124486563334, "rouge1_fmeasure_stderr": 0.0029118807193791816, "rouge1_precision": 0.04332722979741195, "rouge1_precision_stderr": 0.0025397484135024503, "rouge1_recall": 0.08638484320409213, "rouge1_recall_stderr": 0.004855712915740289, "rouge2_fmeasure": 0.0126600494371876, "rouge2_fmeasure_stderr": 0.0010393927624132967, "rouge2_precision": 0.009371982127377696, "rouge2_precision_stderr": 0.0007761604812612375, "rouge2_recall": 0.02197790550576286, "rouge2_recall_stderr": 0.0018737167719494205, "rougeL_fmeasure": 0.04031062592059575, "rougeL_fmeasure_stderr": 0.0022065055222514843, "rougeL_precision": 0.03308111037957417, "rougeL_precision_stderr": 0.002037483672167313, "rougeL_recall": 0.06547067873377617, "rougeL_recall_stderr": 0.0037402890017668913, "rougeLsum_fmeasure": 0.04344922023460101, "rougeLsum_fmeasure_stderr": 0.002384615926685988, "rougeLsum_precision": 0.03547102946933422, "rougeLsum_precision_stderr": 0.002145817702406172, "rougeLsum_recall": 0.07066149952031933, "rougeLsum_recall_stderr": 0.004048133700252855}}, "5": {"article_DOC_summary": {"bleu": 1.959625061740418e-19, "bleu_stderr": 1.1984703371139495e-15, "rouge1_fmeasure": 0.0026267053439145405, "rouge1_fmeasure_stderr": 0.0006851925438686376, "rouge1_precision": 0.002432491256372859, "rouge1_precision_stderr": 0.0006531802890059347, "rouge1_recall": 0.0035688165030904754, "rouge1_recall_stderr": 0.000969634171191206, "rouge2_fmeasure": 0.0003000575858304317, "rouge2_fmeasure_stderr": 0.00012455541465929192, "rouge2_precision": 0.0002462802129838755, "rouge2_precision_stderr": 0.00010248150275091556, "rouge2_recall": 0.00045873937383371344, "rouge2_recall_stderr": 0.0002027676865696476, "rougeL_fmeasure": 0.001963800127619678, "rougeL_fmeasure_stderr": 0.0005077215919641312, "rougeL_precision": 0.001824459823195743, "rougeL_precision_stderr": 0.000493813415204384, "rougeL_recall": 0.002706254470313614, "rougeL_recall_stderr": 0.0007319861753860738, "rougeLsum_fmeasure": 0.002094899399917077, "rougeLsum_fmeasure_stderr": 0.0005500941719652507, "rougeLsum_precision": 0.001947339725356528, "rougeLsum_precision_stderr": 0.0005292516418451348, "rougeLsum_recall": 0.0028418243363945105, "rougeLsum_recall_stderr": 0.0007704086076680828}}}}