File size: 28,023 Bytes
8263782 |
1 |
{"GEM/web_nlg_en": {"0": {"PALM_prompt": {"bleu": 0.2883786280202115, "bleu_stderr": 0.03936084799729088, "rouge1_fmeasure": 0.103421554792752, "rouge1_fmeasure_stderr": 0.001762257816978338, "rouge1_precision": 0.06719578938907746, "rouge1_precision_stderr": 0.0013004585757370683, "rouge1_recall": 0.2933408335090845, "rouge1_recall_stderr": 0.004382296370554512, "rouge2_fmeasure": 0.04762017526127606, "rouge2_fmeasure_stderr": 0.0010873320211799394, "rouge2_precision": 0.030556722468906044, "rouge2_precision_stderr": 0.0007492988401010578, "rouge2_recall": 0.14088496408629886, "rouge2_recall_stderr": 0.003049315486738709, "rougeL_fmeasure": 0.09993996529791976, "rougeL_fmeasure_stderr": 0.0016728671052772506, "rougeL_precision": 0.06486438547957983, "rougeL_precision_stderr": 0.001231171118936048, "rougeL_recall": 0.28447763202238135, "rougeL_recall_stderr": 0.0042288031883992855, "rougeLsum_fmeasure": 0.09965071694396466, "rougeLsum_fmeasure_stderr": 0.0016836029502195003, "rougeLsum_precision": 0.0647465837461535, "rougeLsum_precision_stderr": 0.00124366132201253, "rougeLsum_recall": 0.28232976762951584, "rougeLsum_recall_stderr": 0.004163361732330291}}, "1": {"PALM_prompt": {"bleu": 0.5634646538427781, "bleu_stderr": 0.03736988855205685, "rouge1_fmeasure": 0.12131056010238059, "rouge1_fmeasure_stderr": 0.0018129711840276857, "rouge1_precision": 0.07697654849580207, "rouge1_precision_stderr": 0.0012951272613183852, "rouge1_recall": 0.3969061719233893, "rouge1_recall_stderr": 0.0056851136357343015, "rouge2_fmeasure": 0.05785803759738568, "rouge2_fmeasure_stderr": 0.0011523078709876162, "rouge2_precision": 0.03642271932626906, "rouge2_precision_stderr": 0.0007956739937252943, "rouge2_recall": 0.2051665201143765, "rouge2_recall_stderr": 0.0041594883413927294, "rougeL_fmeasure": 0.11462071685790733, "rougeL_fmeasure_stderr": 0.001624892567642086, "rougeL_precision": 0.07267273013759175, "rougeL_precision_stderr": 0.0011552399753195406, "rougeL_recall": 0.3755810527939102, "rougeL_recall_stderr": 0.00528545382584031, "rougeLsum_fmeasure": 0.11540379904462905, "rougeLsum_fmeasure_stderr": 0.0016960835886338564, "rougeLsum_precision": 0.07333558102707188, "rougeLsum_precision_stderr": 0.0012195728859027712, "rougeLsum_recall": 0.3757551406945481, "rougeLsum_recall_stderr": 0.005219245200343907}}, "2": {"PALM_prompt": {"bleu": 0.6828060703023814, "bleu_stderr": 0.0425207483296129, "rouge1_fmeasure": 0.12552592683219344, "rouge1_fmeasure_stderr": 0.001752255131105832, "rouge1_precision": 0.0790865886214714, "rouge1_precision_stderr": 0.0012505450756042313, "rouge1_recall": 0.427035567540795, "rouge1_recall_stderr": 0.005749871140223685, "rouge2_fmeasure": 0.05940509370992996, "rouge2_fmeasure_stderr": 0.0011135855631122815, "rouge2_precision": 0.037142287807399386, "rouge2_precision_stderr": 0.000765558996913647, "rouge2_recall": 0.21988251267080597, "rouge2_recall_stderr": 0.00425697447376351, "rougeL_fmeasure": 0.11527329683828981, "rougeL_fmeasure_stderr": 0.001524101349020404, "rougeL_precision": 0.07265150298226193, "rougeL_precision_stderr": 0.0011031397973466682, "rougeL_recall": 0.3936959005975406, "rougeL_recall_stderr": 0.005187697908305124, "rougeLsum_fmeasure": 0.11923137803967343, "rougeLsum_fmeasure_stderr": 0.0016398034437248557, "rougeLsum_precision": 0.07517938427479466, "rougeLsum_precision_stderr": 0.0011789577603185614, "rougeLsum_recall": 0.404943656992868, "rougeLsum_recall_stderr": 0.005313046062998814}}, "3": {"PALM_prompt": {"bleu": 0.8336982343397022, "bleu_stderr": 0.0327887377326258, "rouge1_fmeasure": 0.12549315081985135, "rouge1_fmeasure_stderr": 0.0017756300197492854, "rouge1_precision": 0.07862496938468061, "rouge1_precision_stderr": 0.0012544372219464325, "rouge1_recall": 0.43336757562100137, "rouge1_recall_stderr": 0.005813975851408121, "rouge2_fmeasure": 0.06022531877051832, "rouge2_fmeasure_stderr": 0.0011563600202083746, "rouge2_precision": 0.03741379787478959, "rouge2_precision_stderr": 0.0007895630732377968, "rouge2_recall": 0.22623496077748528, "rouge2_recall_stderr": 0.0042712928549412735, "rougeL_fmeasure": 0.11360185571717625, "rougeL_fmeasure_stderr": 0.0015268821384323132, "rougeL_precision": 0.07124494381793388, "rougeL_precision_stderr": 0.0010962640285763162, "rougeL_recall": 0.39321959371417686, "rougeL_recall_stderr": 0.005101213428819951, "rougeLsum_fmeasure": 0.11874541206482168, "rougeLsum_fmeasure_stderr": 0.0016641712015728286, "rougeLsum_precision": 0.07448805733289557, "rougeLsum_precision_stderr": 0.001187320005987778, "rougeLsum_recall": 0.4097236474085259, "rougeLsum_recall_stderr": 0.005356713714674863}}, "4": {"PALM_prompt": {"bleu": 0.8048993474300223, "bleu_stderr": 0.04157871677547976, "rouge1_fmeasure": 0.12696507303445326, "rouge1_fmeasure_stderr": 0.0017668948839916938, "rouge1_precision": 0.07952578574480215, "rouge1_precision_stderr": 0.0012661942787102602, "rouge1_recall": 0.4386081219638241, "rouge1_recall_stderr": 0.005677266555057123, "rouge2_fmeasure": 0.06061578220428707, "rouge2_fmeasure_stderr": 0.0011175090259571937, "rouge2_precision": 0.0376951838080061, "rouge2_precision_stderr": 0.0007761144319241388, "rouge2_recall": 0.22894151277692995, "rouge2_recall_stderr": 0.004196410528544762, "rougeL_fmeasure": 0.11378598207760166, "rougeL_fmeasure_stderr": 0.0014923445088795922, "rougeL_precision": 0.07134231184259153, "rougeL_precision_stderr": 0.0010918605781200322, "rougeL_recall": 0.39486889829999067, "rougeL_recall_stderr": 0.004923545353622342, "rougeLsum_fmeasure": 0.1197281993743887, "rougeLsum_fmeasure_stderr": 0.0016590997843029978, "rougeLsum_precision": 0.07509698381413346, "rougeLsum_precision_stderr": 0.0012018963700845971, "rougeLsum_recall": 0.41258265582996795, "rougeLsum_recall_stderr": 0.0051847453818666765}}, "5": {"PALM_prompt": {"bleu": 0.9424030277847187, "bleu_stderr": 0.052987929389338294, "rouge1_fmeasure": 0.12911370685505766, "rouge1_fmeasure_stderr": 0.0017515798700797859, "rouge1_precision": 0.08025169576842368, "rouge1_precision_stderr": 0.001236439325453276, "rouge1_recall": 0.4579613447211886, "rouge1_recall_stderr": 0.005880996871821512, "rouge2_fmeasure": 0.0624035474416899, "rouge2_fmeasure_stderr": 0.0011352673015657528, "rouge2_precision": 0.03846872592808952, "rouge2_precision_stderr": 0.0007759633225274091, "rouge2_recall": 0.24371157528692775, "rouge2_recall_stderr": 0.004498931653094872, "rougeL_fmeasure": 0.1142452159028682, "rougeL_fmeasure_stderr": 0.0014684795581487694, "rougeL_precision": 0.07114235942831466, "rougeL_precision_stderr": 0.0010624631237322504, "rougeL_recall": 0.40714301284245485, "rougeL_recall_stderr": 0.005064627475792024, "rougeLsum_fmeasure": 0.12145176665328596, "rougeLsum_fmeasure_stderr": 0.0016352600982162296, "rougeLsum_precision": 0.0756038827316064, "rougeLsum_precision_stderr": 0.0011672546888864264, "rougeLsum_recall": 0.42963457818781536, "rougeLsum_recall_stderr": 0.0053743909806075905}}}, "GEM/wiki_lingua_en": {"0": {"tldr_en": {"bleu": 1.6054713437075743, "bleu_stderr": 0.05437478201375844, "rouge1_fmeasure": 0.17747760370302318, "rouge1_fmeasure_stderr": 0.0019053538765698758, "rouge1_precision": 0.1502175136439869, "rouge1_precision_stderr": 0.0019030361852174719, "rouge1_recall": 0.261455388498779, "rouge1_recall_stderr": 0.0028100578970410993, "rouge2_fmeasure": 0.037091167992168994, "rouge2_fmeasure_stderr": 0.0008718507339161006, "rouge2_precision": 0.03115494637566214, "rouge2_precision_stderr": 0.0007718936573069445, "rouge2_recall": 0.05641110971379137, "rouge2_recall_stderr": 0.0014645457777589359, "rougeL_fmeasure": 0.1361541337117608, "rougeL_fmeasure_stderr": 0.0013435136569955786, "rougeL_precision": 0.11393251734177375, "rougeL_precision_stderr": 0.0013110775704154515, "rougeL_recall": 0.20550271197177267, "rougeL_recall_stderr": 0.0022393561246885608, "rougeLsum_fmeasure": 0.16373807275193125, "rougeLsum_fmeasure_stderr": 0.0017484417302425664, "rougeLsum_precision": 0.13840143550418207, "rougeLsum_precision_stderr": 0.0017472927323399304, "rougeLsum_recall": 0.24208617369571592, "rougeLsum_recall_stderr": 0.002615495423998821}}, "1": {"tldr_en": {"bleu": 3.3568815479070158, "bleu_stderr": 0.062408281042864173, "rouge1_fmeasure": 0.2384414177661812, "rouge1_fmeasure_stderr": 0.001967738213001087, "rouge1_precision": 0.20521455786196224, "rouge1_precision_stderr": 0.0021566423356602616, "rouge1_recall": 0.3450088538250452, "rouge1_recall_stderr": 0.0028141198924903532, "rouge2_fmeasure": 0.06328901574064953, "rouge2_fmeasure_stderr": 0.0011184668519141068, "rouge2_precision": 0.0541891609093382, "rouge2_precision_stderr": 0.0010252409370391552, "rouge2_recall": 0.09354429527016248, "rouge2_recall_stderr": 0.0017970539715243055, "rougeL_fmeasure": 0.16967595559198553, "rougeL_fmeasure_stderr": 0.0013571592618223686, "rougeL_precision": 0.14442950228734072, "rougeL_precision_stderr": 0.0014388633343097553, "rougeL_recall": 0.25157906179953965, "rougeL_recall_stderr": 0.002266706627328072, "rougeLsum_fmeasure": 0.22437259777229618, "rougeLsum_fmeasure_stderr": 0.0018534765898883354, "rougeLsum_precision": 0.19302045441232318, "rougeLsum_precision_stderr": 0.002028535492752175, "rougeLsum_recall": 0.3251189492217731, "rougeLsum_recall_stderr": 0.0026790268923513527}}, "2": {"tldr_en": {"bleu": 3.9743938237550784, "bleu_stderr": 0.07475699238187014, "rouge1_fmeasure": 0.2476037847532769, "rouge1_fmeasure_stderr": 0.002025823379351112, "rouge1_precision": 0.22168273116215406, "rouge1_precision_stderr": 0.002435239313498893, "rouge1_recall": 0.34743629317668956, "rouge1_recall_stderr": 0.0028712547192456107, "rouge2_fmeasure": 0.07067445283939051, "rouge2_fmeasure_stderr": 0.0012417394471129861, "rouge2_precision": 0.06376061872271946, "rouge2_precision_stderr": 0.0013048039083209525, "rouge2_recall": 0.101241459889032, "rouge2_recall_stderr": 0.001953242205361602, "rougeL_fmeasure": 0.1802673381893277, "rougeL_fmeasure_stderr": 0.001478295743890994, "rougeL_precision": 0.16023681566231104, "rougeL_precision_stderr": 0.001772038861775115, "rougeL_recall": 0.25897094370699875, "rougeL_recall_stderr": 0.002426935392898513, "rougeLsum_fmeasure": 0.23404735258003787, "rougeLsum_fmeasure_stderr": 0.0019207642560461376, "rougeLsum_precision": 0.20950862810749826, "rougeLsum_precision_stderr": 0.002314989258793673, "rougeLsum_recall": 0.32880876166482065, "rougeLsum_recall_stderr": 0.002739608654356716}}, "3": {"tldr_en": {"bleu": 3.9817750726027175, "bleu_stderr": 0.09479747244511556, "rouge1_fmeasure": 0.2047867720982337, "rouge1_fmeasure_stderr": 0.0024642538193857724, "rouge1_precision": 0.1929078707094695, "rouge1_precision_stderr": 0.0028265761167604094, "rouge1_recall": 0.28273526242062413, "rouge1_recall_stderr": 0.003552029067040685, "rouge2_fmeasure": 0.0583824000959267, "rouge2_fmeasure_stderr": 0.0012189630804918103, "rouge2_precision": 0.054778926280360955, "rouge2_precision_stderr": 0.0013556972713623368, "rouge2_recall": 0.08337730610072844, "rouge2_recall_stderr": 0.0019188280227343476, "rougeL_fmeasure": 0.1504897955536091, "rougeL_fmeasure_stderr": 0.0018172498103686094, "rougeL_precision": 0.1417601937646707, "rougeL_precision_stderr": 0.0021376668461159194, "rougeL_recall": 0.21204142844316634, "rougeL_recall_stderr": 0.002858744024264778, "rougeLsum_fmeasure": 0.19403204633681076, "rougeLsum_fmeasure_stderr": 0.0023374505495094874, "rougeLsum_precision": 0.18285584254571302, "rougeLsum_precision_stderr": 0.0026982092402270926, "rougeLsum_recall": 0.268579149278918, "rougeLsum_recall_stderr": 0.0034097338970395575}}, "4": {"tldr_en": {"bleu": 0.8498125282802876, "bleu_stderr": 0.07488095870505093, "rouge1_fmeasure": 0.06567263366786005, "rouge1_fmeasure_stderr": 0.0021904578073412223, "rouge1_precision": 0.06349732024114886, "rouge1_precision_stderr": 0.00234492312222753, "rouge1_recall": 0.09340855339099945, "rouge1_recall_stderr": 0.003159444376659221, "rouge2_fmeasure": 0.018412425374697422, "rouge2_fmeasure_stderr": 0.0008441162033876125, "rouge2_precision": 0.01738674391302479, "rouge2_precision_stderr": 0.000886017251546639, "rouge2_recall": 0.02721797575693733, "rouge2_recall_stderr": 0.0013454614244059475, "rougeL_fmeasure": 0.04945824665200398, "rougeL_fmeasure_stderr": 0.0016373751055148418, "rougeL_precision": 0.04817497329724485, "rougeL_precision_stderr": 0.0018235195878999154, "rougeL_recall": 0.07173904334429866, "rougeL_recall_stderr": 0.002478097323273335, "rougeLsum_fmeasure": 0.06188112367809635, "rougeLsum_fmeasure_stderr": 0.002069249663413523, "rougeLsum_precision": 0.05985219645183224, "rougeLsum_precision_stderr": 0.0022220794271589225, "rougeLsum_recall": 0.0881853688625359, "rougeLsum_recall_stderr": 0.0029988916997001343}}, "5": {"tldr_en": {"bleu": 2.8683848179992505e-06, "bleu_stderr": 7.381534992907998e-06, "rouge1_fmeasure": 0.010706535802039367, "rouge1_fmeasure_stderr": 0.0009930611949791836, "rouge1_precision": 0.010748286830524562, "rouge1_precision_stderr": 0.0010977103345240155, "rouge1_recall": 0.015508382128794362, "rouge1_recall_stderr": 0.001446236589386957, "rouge2_fmeasure": 0.002970906530619929, "rouge2_fmeasure_stderr": 0.0003682132280639809, "rouge2_precision": 0.0030969030541188967, "rouge2_precision_stderr": 0.0005268236540414107, "rouge2_recall": 0.004556824944932366, "rouge2_recall_stderr": 0.0005664861641115252, "rougeL_fmeasure": 0.008019691411733835, "rougeL_fmeasure_stderr": 0.000754515109085896, "rougeL_precision": 0.008049434192397904, "rougeL_precision_stderr": 0.0008462473363861482, "rougeL_recall": 0.011951304347862953, "rougeL_recall_stderr": 0.0011515347961576568, "rougeLsum_fmeasure": 0.010182849522984623, "rougeLsum_fmeasure_stderr": 0.0009497792801374568, "rougeLsum_precision": 0.010213486554639387, "rougeLsum_precision_stderr": 0.001056290927469812, "rougeLsum_recall": 0.014853652320406176, "rougeLsum_recall_stderr": 0.0013945219376869788}}}, "e2e_nlg_cleaned": {"0": {"generate_text_restaurant": {"bleu": 0.16951406402821598, "bleu_stderr": 0.014615585721645268, "rouge1_fmeasure": 0.14902951599302275, "rouge1_fmeasure_stderr": 0.0011936812421680112, "rouge1_precision": 0.15133664159023066, "rouge1_precision_stderr": 0.003090044411839824, "rouge1_recall": 0.20829872832019666, "rouge1_recall_stderr": 0.0012350500662973555, "rouge2_fmeasure": 0.012769294373367771, "rouge2_fmeasure_stderr": 0.0005241002980862521, "rouge2_precision": 0.03637204499081546, "rouge2_precision_stderr": 0.0028085435311582378, "rouge2_recall": 0.012949043111655439, "rouge2_recall_stderr": 0.0005016259904639799, "rougeL_fmeasure": 0.14100584281893078, "rougeL_fmeasure_stderr": 0.0009038280484109508, "rougeL_precision": 0.139679315386246, "rougeL_precision_stderr": 0.0027670544139910772, "rougeL_recall": 0.2016577246385112, "rougeL_recall_stderr": 0.0012040942408512864, "rougeLsum_fmeasure": 0.1028831030157934, "rougeLsum_fmeasure_stderr": 0.001075855762070383, "rougeLsum_precision": 0.113513620222634, "rougeLsum_precision_stderr": 0.0030413500876753405, "rougeLsum_recall": 0.14029728805033925, "rougeLsum_recall_stderr": 0.0010082613852652347}}, "1": {"generate_text_restaurant": {"bleu": 10.067385696344799, "bleu_stderr": 0.10607089517794384, "rouge1_fmeasure": 0.4237261154678058, "rouge1_fmeasure_stderr": 0.0020488737967454696, "rouge1_precision": 0.42917506799106997, "rouge1_precision_stderr": 0.002365499643400411, "rouge1_recall": 0.45662630550997346, "rouge1_recall_stderr": 0.002963335187859022, "rouge2_fmeasure": 0.18427344702091913, "rouge2_fmeasure_stderr": 0.0017323159960132722, "rouge2_precision": 0.1861748094036103, "rouge2_precision_stderr": 0.0018728109018732715, "rouge2_recall": 0.20088789046913377, "rouge2_recall_stderr": 0.0021605722507918876, "rougeL_fmeasure": 0.30096531146642097, "rougeL_fmeasure_stderr": 0.001710001515688343, "rougeL_precision": 0.3059227854981379, "rougeL_precision_stderr": 0.001998310078066914, "rougeL_recall": 0.32448538965781326, "rougeL_recall_stderr": 0.0023860439595277186, "rougeLsum_fmeasure": 0.3528207417266004, "rougeLsum_fmeasure_stderr": 0.0020083480221353787, "rougeLsum_precision": 0.3579690622651419, "rougeLsum_precision_stderr": 0.0022901580739891005, "rougeLsum_recall": 0.38007301761756745, "rougeLsum_recall_stderr": 0.002747710382969998}}, "2": {"generate_text_restaurant": {"bleu": 11.636919978386004, "bleu_stderr": 0.19788162907948217, "rouge1_fmeasure": 0.45290381111986455, "rouge1_fmeasure_stderr": 0.0019462177421565893, "rouge1_precision": 0.44970849663299084, "rouge1_precision_stderr": 0.0022619593433166924, "rouge1_recall": 0.49228985626567096, "rouge1_recall_stderr": 0.0028656589338168894, "rouge2_fmeasure": 0.2101765831183815, "rouge2_fmeasure_stderr": 0.0017952071516282025, "rouge2_precision": 0.20827536079463077, "rouge2_precision_stderr": 0.0018769282280709765, "rouge2_recall": 0.23091649040389164, "rouge2_recall_stderr": 0.002254284484281101, "rougeL_fmeasure": 0.3265472292605653, "rougeL_fmeasure_stderr": 0.0017398385407963483, "rougeL_precision": 0.3243950518654991, "rougeL_precision_stderr": 0.0019552548930316443, "rougeL_recall": 0.35557783678320415, "rougeL_recall_stderr": 0.002428507434228921, "rougeLsum_fmeasure": 0.3773556348099214, "rougeLsum_fmeasure_stderr": 0.0019945557891501518, "rougeLsum_precision": 0.3749727434579744, "rougeLsum_precision_stderr": 0.002236863975642526, "rougeLsum_recall": 0.4099709634067351, "rougeLsum_recall_stderr": 0.002706090262648214}}, "3": {"generate_text_restaurant": {"bleu": 12.426631559674204, "bleu_stderr": 0.11440038355745161, "rouge1_fmeasure": 0.46304132819339217, "rouge1_fmeasure_stderr": 0.0020173924707804184, "rouge1_precision": 0.4562949226921436, "rouge1_precision_stderr": 0.002294468118391725, "rouge1_recall": 0.5049085061040581, "rouge1_recall_stderr": 0.0029021179641736915, "rouge2_fmeasure": 0.22103332973061124, "rouge2_fmeasure_stderr": 0.0019041506003672232, "rouge2_precision": 0.21679230842159727, "rouge2_precision_stderr": 0.0019314339034455107, "rouge2_recall": 0.24402017960207578, "rouge2_recall_stderr": 0.002398918086552701, "rougeL_fmeasure": 0.33425485052465553, "rougeL_fmeasure_stderr": 0.0018145324900473829, "rougeL_precision": 0.3294449670016489, "rougeL_precision_stderr": 0.0019862700698188526, "rougeL_recall": 0.36499231892760226, "rougeL_recall_stderr": 0.002472604135584095, "rougeLsum_fmeasure": 0.38784195443176667, "rougeLsum_fmeasure_stderr": 0.002095047300699444, "rougeLsum_precision": 0.3822668655881195, "rougeLsum_precision_stderr": 0.0022831595508053123, "rougeLsum_recall": 0.42289921789097146, "rougeLsum_recall_stderr": 0.0028059845754771946}}, "4": {"generate_text_restaurant": {"bleu": 12.590553484195926, "bleu_stderr": 0.1557062455646749, "rouge1_fmeasure": 0.4665951594342427, "rouge1_fmeasure_stderr": 0.0019811140237555058, "rouge1_precision": 0.45730914793351857, "rouge1_precision_stderr": 0.0022800216801940523, "rouge1_recall": 0.5099063296772233, "rouge1_recall_stderr": 0.002848408606334223, "rouge2_fmeasure": 0.22268786623363584, "rouge2_fmeasure_stderr": 0.0018973436430830147, "rouge2_precision": 0.21739148517372925, "rouge2_precision_stderr": 0.0019197356806646647, "rouge2_recall": 0.24585802349091362, "rouge2_recall_stderr": 0.002367288796030392, "rougeL_fmeasure": 0.3359737739996741, "rougeL_fmeasure_stderr": 0.0018304708156164022, "rougeL_precision": 0.32920126816755724, "rougeL_precision_stderr": 0.0019885426030395704, "rougeL_recall": 0.3675548516076049, "rougeL_recall_stderr": 0.0024640793870539996, "rougeLsum_fmeasure": 0.39000018030735667, "rougeLsum_fmeasure_stderr": 0.0020682797216599685, "rougeLsum_precision": 0.3822321205301913, "rougeLsum_precision_stderr": 0.002266945541059726, "rougeLsum_recall": 0.4260724023535776, "rougeLsum_recall_stderr": 0.0027436023351126207}}, "5": {"generate_text_restaurant": {"bleu": 12.568675301062258, "bleu_stderr": 0.16224872119521075, "rouge1_fmeasure": 0.46892055322657583, "rouge1_fmeasure_stderr": 0.0019557972473512363, "rouge1_precision": 0.46019703610358126, "rouge1_precision_stderr": 0.002310541944330683, "rouge1_recall": 0.5121643724875744, "rouge1_recall_stderr": 0.0028028895695916085, "rouge2_fmeasure": 0.22475547301426657, "rouge2_fmeasure_stderr": 0.0018950527696092341, "rouge2_precision": 0.22000376959092752, "rouge2_precision_stderr": 0.0019418480260118285, "rouge2_recall": 0.24793505182999162, "rouge2_recall_stderr": 0.0023724004656612103, "rougeL_fmeasure": 0.338538223656329, "rougeL_fmeasure_stderr": 0.0018504743886393609, "rougeL_precision": 0.3318569141781424, "rougeL_precision_stderr": 0.002016776093642391, "rougeL_recall": 0.37058399083148463, "rougeL_recall_stderr": 0.0024982918049127, "rougeLsum_fmeasure": 0.39172408140249776, "rougeLsum_fmeasure_stderr": 0.0020299941320428634, "rougeLsum_precision": 0.38438568129064205, "rougeLsum_precision_stderr": 0.002263964644987408, "rougeLsum_recall": 0.42799017201029466, "rougeLsum_recall_stderr": 0.0027129978907711573}}}, "gem_xsum": {"0": {"article_DOC_summary": {"bleu": 2.123641882512125, "bleu_stderr": 0.11311464309535657, "rouge1_fmeasure": 0.21703276545763875, "rouge1_fmeasure_stderr": 0.002515369600939235, "rouge1_precision": 0.1660896826959829, "rouge1_precision_stderr": 0.002107288082741575, "rouge1_recall": 0.35083498826967574, "rouge1_recall_stderr": 0.004593723083105133, "rouge2_fmeasure": 0.04768368310993588, "rouge2_fmeasure_stderr": 0.0016080049517398576, "rouge2_precision": 0.035059732318482924, "rouge2_precision_stderr": 0.0011977915786786503, "rouge2_recall": 0.08226070946861705, "rouge2_recall_stderr": 0.0028797184426689847, "rougeL_fmeasure": 0.15826337701676133, "rougeL_fmeasure_stderr": 0.0019458792115624524, "rougeL_precision": 0.12091074416538322, "rougeL_precision_stderr": 0.0016031624561767372, "rougeL_recall": 0.2576388464400407, "rougeL_recall_stderr": 0.00369472688602631, "rougeLsum_fmeasure": 0.16763228337149372, "rougeLsum_fmeasure_stderr": 0.002117910852275356, "rougeLsum_precision": 0.12768714774937476, "rougeLsum_precision_stderr": 0.0016996047438811593, "rougeLsum_recall": 0.27322366216085703, "rougeLsum_recall_stderr": 0.003964231303059884}}, "1": {"article_DOC_summary": {"bleu": 1.824798489457088, "bleu_stderr": 0.07127603588876777, "rouge1_fmeasure": 0.19596597830254703, "rouge1_fmeasure_stderr": 0.0027034863790677227, "rouge1_precision": 0.13945719874562185, "rouge1_precision_stderr": 0.0019983868750527664, "rouge1_recall": 0.34308219072003043, "rouge1_recall_stderr": 0.004720352047720588, "rouge2_fmeasure": 0.045112546772934525, "rouge2_fmeasure_stderr": 0.0016064335304974058, "rouge2_precision": 0.03178740757757239, "rouge2_precision_stderr": 0.0011392122530476615, "rouge2_recall": 0.08118275228432598, "rouge2_recall_stderr": 0.0029455220106513707, "rougeL_fmeasure": 0.15024907208625723, "rougeL_fmeasure_stderr": 0.002045800799748567, "rougeL_precision": 0.10681129267314027, "rougeL_precision_stderr": 0.0015073695015672187, "rougeL_recall": 0.2641425374203942, "rougeL_recall_stderr": 0.003651992949055377, "rougeLsum_fmeasure": 0.15587486680514107, "rougeLsum_fmeasure_stderr": 0.0022911401506731394, "rougeLsum_precision": 0.11073338724734512, "rougeLsum_precision_stderr": 0.0016753848690916494, "rougeLsum_recall": 0.2742974784323833, "rougeLsum_recall_stderr": 0.004087132157440376}}, "2": {"article_DOC_summary": {"bleu": 1.9202286782616684, "bleu_stderr": 0.10294125559660114, "rouge1_fmeasure": 0.19441013280698327, "rouge1_fmeasure_stderr": 0.0026788744932156566, "rouge1_precision": 0.13831430998317307, "rouge1_precision_stderr": 0.001976957405007506, "rouge1_recall": 0.34054180926843874, "rouge1_recall_stderr": 0.004697948807654975, "rouge2_fmeasure": 0.04741261419771178, "rouge2_fmeasure_stderr": 0.0016319693236568167, "rouge2_precision": 0.03335127280499144, "rouge2_precision_stderr": 0.001154865026778613, "rouge2_recall": 0.0856058058231469, "rouge2_recall_stderr": 0.003020560704657517, "rougeL_fmeasure": 0.1548115500775745, "rougeL_fmeasure_stderr": 0.0021179712451710035, "rougeL_precision": 0.11005048631596476, "rougeL_precision_stderr": 0.0015585194589067973, "rougeL_recall": 0.2721344790344476, "rougeL_recall_stderr": 0.003803909579012272, "rougeLsum_fmeasure": 0.15284300610999954, "rougeLsum_fmeasure_stderr": 0.0022472050629649657, "rougeLsum_precision": 0.10851611339383292, "rougeLsum_precision_stderr": 0.0016395893229652913, "rougeLsum_recall": 0.2694877082238382, "rougeLsum_recall_stderr": 0.004071472128097917}}, "3": {"article_DOC_summary": {"bleu": 1.960346415562878, "bleu_stderr": 0.10375544830060275, "rouge1_fmeasure": 0.18698891886072055, "rouge1_fmeasure_stderr": 0.0028344896483067416, "rouge1_precision": 0.13614805917908393, "rouge1_precision_stderr": 0.002182928610973459, "rouge1_recall": 0.319067828970501, "rouge1_recall_stderr": 0.004854901693972656, "rouge2_fmeasure": 0.04579306632360622, "rouge2_fmeasure_stderr": 0.0016499700154799003, "rouge2_precision": 0.03255285607712267, "rouge2_precision_stderr": 0.0011709136544211735, "rouge2_recall": 0.08091915270893477, "rouge2_recall_stderr": 0.0030319428460283114, "rougeL_fmeasure": 0.14999604713991269, "rougeL_fmeasure_stderr": 0.0022346501948052253, "rougeL_precision": 0.10907064034611987, "rougeL_precision_stderr": 0.0016952538239699338, "rougeL_recall": 0.25710809104483, "rougeL_recall_stderr": 0.003938425696647421, "rougeLsum_fmeasure": 0.1481937356361328, "rougeLsum_fmeasure_stderr": 0.0023789575527353485, "rougeLsum_precision": 0.10781469737345471, "rougeLsum_precision_stderr": 0.0018160899239560767, "rougeLsum_recall": 0.25437759661970666, "rougeLsum_recall_stderr": 0.004197817376394927}}, "4": {"article_DOC_summary": {"bleu": 1.147010044637203, "bleu_stderr": 0.1483287532182548, "rouge1_fmeasure": 0.05597846129733605, "rouge1_fmeasure_stderr": 0.0030736717398869183, "rouge1_precision": 0.0461290015156943, "rouge1_precision_stderr": 0.0026493012385445263, "rouge1_recall": 0.08781737838132268, "rouge1_recall_stderr": 0.004925448191329273, "rouge2_fmeasure": 0.014349999093671009, "rouge2_fmeasure_stderr": 0.00119440286191344, "rouge2_precision": 0.011276409349861457, "rouge2_precision_stderr": 0.0009910327288713146, "rouge2_recall": 0.02322309514343149, "rouge2_recall_stderr": 0.0019591268818172957, "rougeL_fmeasure": 0.0441258641947338, "rougeL_fmeasure_stderr": 0.002422435816075437, "rougeL_precision": 0.036708426223707534, "rougeL_precision_stderr": 0.0021597446633885207, "rougeL_recall": 0.06933837439843676, "rougeL_recall_stderr": 0.0039167983045230665, "rougeLsum_fmeasure": 0.04374778712530494, "rougeLsum_fmeasure_stderr": 0.0024277919295063437, "rougeLsum_precision": 0.036521786784889244, "rougeLsum_precision_stderr": 0.0021744741340258226, "rougeLsum_recall": 0.06862432645657374, "rougeLsum_recall_stderr": 0.003921758075614257}}, "5": {"article_DOC_summary": {"bleu": 7.432818302647882e-17, "bleu_stderr": 6.736262144559321e-14, "rouge1_fmeasure": 0.002840764770276708, "rouge1_fmeasure_stderr": 0.0007742945701180914, "rouge1_precision": 0.002495597025413209, "rouge1_precision_stderr": 0.0007589560712051177, "rouge1_recall": 0.004261862032154927, "rouge1_recall_stderr": 0.0011922597752018513, "rouge2_fmeasure": 0.00046551069178623087, "rouge2_fmeasure_stderr": 0.0001919512728404723, "rouge2_precision": 0.0004857664430361433, "rouge2_precision_stderr": 0.000238899022126221, "rouge2_recall": 0.0005700394684856393, "rouge2_recall_stderr": 0.000211601005978903, "rougeL_fmeasure": 0.0020608235251966707, "rougeL_fmeasure_stderr": 0.0005517756786268286, "rougeL_precision": 0.0018255732115487248, "rougeL_precision_stderr": 0.0005443002896546889, "rougeL_recall": 0.003014099249198048, "rougeL_recall_stderr": 0.0008089040705550355, "rougeLsum_fmeasure": 0.002211561514290958, "rougeLsum_fmeasure_stderr": 0.0006392646801827694, "rougeLsum_precision": 0.0020616490944038632, "rougeLsum_precision_stderr": 0.000695995858568096, "rougeLsum_recall": 0.0030417584845173606, "rougeLsum_recall_stderr": 0.0008279029688397777}}}} |