Muennighoff's picture
Add
62be092
raw
history blame
No virus
28 kB
{"GEM/web_nlg_en": {"0": {"PALM_prompt": {"bleu": 0.337746444985717, "bleu_stderr": 0.025723799062097357, "rouge1_fmeasure": 0.10699666188240244, "rouge1_fmeasure_stderr": 0.0020715439556135856, "rouge1_precision": 0.07154439549214156, "rouge1_precision_stderr": 0.0017336240537181998, "rouge1_recall": 0.2907495295799977, "rouge1_recall_stderr": 0.004750778150173152, "rouge2_fmeasure": 0.0496610495623841, "rouge2_fmeasure_stderr": 0.0012786198242892095, "rouge2_precision": 0.032651135682866636, "rouge2_precision_stderr": 0.0009790662341297523, "rouge2_recall": 0.13889633432164433, "rouge2_recall_stderr": 0.0031638491379812144, "rougeL_fmeasure": 0.10307737641713036, "rougeL_fmeasure_stderr": 0.0019404835522627694, "rougeL_precision": 0.06874609619456303, "rougeL_precision_stderr": 0.0016401795191502446, "rougeL_recall": 0.2832070044815099, "rougeL_recall_stderr": 0.004644147729239302, "rougeLsum_fmeasure": 0.1022096386866131, "rougeLsum_fmeasure_stderr": 0.0019502533617406566, "rougeLsum_precision": 0.06835400621228219, "rougeLsum_precision_stderr": 0.0016588648038417056, "rougeLsum_recall": 0.2789782483365015, "rougeLsum_recall_stderr": 0.004537060909134837}}, "1": {"PALM_prompt": {"bleu": 0.44221469722463974, "bleu_stderr": 0.02401688151148588, "rouge1_fmeasure": 0.11489205026406475, "rouge1_fmeasure_stderr": 0.0019010515409538693, "rouge1_precision": 0.07357217745226205, "rouge1_precision_stderr": 0.0013960392328370031, "rouge1_recall": 0.3724825385267637, "rouge1_recall_stderr": 0.005268948067138151, "rouge2_fmeasure": 0.052745549051089635, "rouge2_fmeasure_stderr": 0.0011729442490595935, "rouge2_precision": 0.03367618513053426, "rouge2_precision_stderr": 0.0008400543404787215, "rouge2_recall": 0.17885444723939406, "rouge2_recall_stderr": 0.0036383095838150538, "rougeL_fmeasure": 0.10766933323845415, "rougeL_fmeasure_stderr": 0.0017216577903843573, "rougeL_precision": 0.06889590942448652, "rougeL_precision_stderr": 0.0012588679883559991, "rougeL_recall": 0.34761179041427176, "rougeL_recall_stderr": 0.004789875650121897, "rougeLsum_fmeasure": 0.10956147806296142, "rougeLsum_fmeasure_stderr": 0.0017969280594553598, "rougeLsum_precision": 0.07016497115925935, "rougeLsum_precision_stderr": 0.0013203486052967008, "rougeLsum_recall": 0.35401233636459406, "rougeLsum_recall_stderr": 0.004901242696057935}}, "2": {"PALM_prompt": {"bleu": 0.5485489383394867, "bleu_stderr": 0.01790737693206069, "rouge1_fmeasure": 0.12120324729580192, "rouge1_fmeasure_stderr": 0.0017626765360765897, "rouge1_precision": 0.07669749888993721, "rouge1_precision_stderr": 0.0012755649427057204, "rouge1_recall": 0.4062443547431919, "rouge1_recall_stderr": 0.005263639496501723, "rouge2_fmeasure": 0.0557224969133641, "rouge2_fmeasure_stderr": 0.0010953891257082233, "rouge2_precision": 0.03500587575956195, "rouge2_precision_stderr": 0.0007606471378820799, "rouge2_recall": 0.20169128468123082, "rouge2_recall_stderr": 0.00393131906399693, "rougeL_fmeasure": 0.11283425649046286, "rougeL_fmeasure_stderr": 0.0015992962521854334, "rougeL_precision": 0.07141851141509838, "rougeL_precision_stderr": 0.0011578468997379412, "rougeL_recall": 0.3756270546409128, "rougeL_recall_stderr": 0.0046913817507348516, "rougeLsum_fmeasure": 0.1152997721272069, "rougeLsum_fmeasure_stderr": 0.001662152742412373, "rougeLsum_precision": 0.07300514391759354, "rougeLsum_precision_stderr": 0.0012059988666926027, "rougeLsum_recall": 0.3853014589476076, "rougeLsum_recall_stderr": 0.004874986404199831}}, "3": {"PALM_prompt": {"bleu": 0.6496721788783876, "bleu_stderr": 0.03484244121461029, "rouge1_fmeasure": 0.12308411899277691, "rouge1_fmeasure_stderr": 0.0017449229527573052, "rouge1_precision": 0.07749371235858858, "rouge1_precision_stderr": 0.001253481960803683, "rouge1_recall": 0.4213854800694553, "rouge1_recall_stderr": 0.005269609312837115, "rouge2_fmeasure": 0.05683740531643655, "rouge2_fmeasure_stderr": 0.0011144676569323996, "rouge2_precision": 0.03554310003530167, "rouge2_precision_stderr": 0.0007652889217454437, "rouge2_recall": 0.20927869801583537, "rouge2_recall_stderr": 0.003918454237886759, "rougeL_fmeasure": 0.11330634883742734, "rougeL_fmeasure_stderr": 0.0015785250217636106, "rougeL_precision": 0.07144229275560832, "rougeL_precision_stderr": 0.0011390445579545457, "rougeL_recall": 0.3849127466778927, "rougeL_recall_stderr": 0.004677394156948758, "rougeLsum_fmeasure": 0.11627697741506937, "rougeLsum_fmeasure_stderr": 0.0016392300523315432, "rougeLsum_precision": 0.07327500871356527, "rougeLsum_precision_stderr": 0.001182198318100844, "rougeLsum_recall": 0.3969544557796036, "rougeLsum_recall_stderr": 0.0048799142212498405}}, "4": {"PALM_prompt": {"bleu": 0.7063533008902111, "bleu_stderr": 0.041503393980893345, "rouge1_fmeasure": 0.12490488842474952, "rouge1_fmeasure_stderr": 0.001751968407342958, "rouge1_precision": 0.07869761394047567, "rouge1_precision_stderr": 0.0012843291997566327, "rouge1_recall": 0.43139319692630373, "rouge1_recall_stderr": 0.0053726307301372594, "rouge2_fmeasure": 0.058162655218062444, "rouge2_fmeasure_stderr": 0.0011149124837102626, "rouge2_precision": 0.036359740408457415, "rouge2_precision_stderr": 0.0007776718631115706, "rouge2_recall": 0.21806386747709874, "rouge2_recall_stderr": 0.004048675903663093, "rougeL_fmeasure": 0.11463548920624382, "rougeL_fmeasure_stderr": 0.0015524057930605569, "rougeL_precision": 0.07225894127941825, "rougeL_precision_stderr": 0.0011363194413938492, "rougeL_recall": 0.3936320975032421, "rougeL_recall_stderr": 0.004712896930705, "rougeLsum_fmeasure": 0.11798687550094664, "rougeLsum_fmeasure_stderr": 0.0016525439565771675, "rougeLsum_precision": 0.07440943974928929, "rougeLsum_precision_stderr": 0.0012124956313511869, "rougeLsum_recall": 0.40557839359434195, "rougeLsum_recall_stderr": 0.004943759882653278}}, "5": {"PALM_prompt": {"bleu": 0.7644478357888255, "bleu_stderr": 0.04044640947525235, "rouge1_fmeasure": 0.1251676620217877, "rouge1_fmeasure_stderr": 0.0017408310462218254, "rouge1_precision": 0.078351420633796, "rouge1_precision_stderr": 0.0012551804296270308, "rouge1_recall": 0.43825182984532646, "rouge1_recall_stderr": 0.005391904886462587, "rouge2_fmeasure": 0.05850978580112579, "rouge2_fmeasure_stderr": 0.001111412719141575, "rouge2_precision": 0.0363945221025962, "rouge2_precision_stderr": 0.0007712087576040486, "rouge2_recall": 0.22246888624823535, "rouge2_recall_stderr": 0.004068791084834974, "rougeL_fmeasure": 0.11376002849024609, "rougeL_fmeasure_stderr": 0.0015439403607715781, "rougeL_precision": 0.07132096428316809, "rougeL_precision_stderr": 0.0011264668954042189, "rougeL_recall": 0.3970604607736315, "rougeL_recall_stderr": 0.004724563154652359, "rougeLsum_fmeasure": 0.11803699373061594, "rougeLsum_fmeasure_stderr": 0.0016508662232470068, "rougeLsum_precision": 0.07396885211594155, "rougeLsum_precision_stderr": 0.0011966084679290122, "rougeLsum_recall": 0.41186690485603944, "rougeLsum_recall_stderr": 0.004961891570144808}}}, "GEM/wiki_lingua_en": {"0": {"tldr_en": {"bleu": 1.29726012835879, "bleu_stderr": 0.05174941081008606, "rouge1_fmeasure": 0.16544681433754094, "rouge1_fmeasure_stderr": 0.0017759555724936034, "rouge1_precision": 0.1404477778269389, "rouge1_precision_stderr": 0.0017876317480673908, "rouge1_recall": 0.24247894259245917, "rouge1_recall_stderr": 0.0025695769282577715, "rouge2_fmeasure": 0.0306979603593394, "rouge2_fmeasure_stderr": 0.0007506213998392401, "rouge2_precision": 0.02562865789268299, "rouge2_precision_stderr": 0.0006479863699509775, "rouge2_recall": 0.047849251812341224, "rouge2_recall_stderr": 0.0013371976897474666, "rougeL_fmeasure": 0.13143431833041172, "rougeL_fmeasure_stderr": 0.0012775326317089723, "rougeL_precision": 0.11006552593322298, "rougeL_precision_stderr": 0.0012474076298105842, "rougeL_recall": 0.1978169515135589, "rougeL_recall_stderr": 0.002120727420623227, "rougeLsum_fmeasure": 0.1514959430773454, "rougeLsum_fmeasure_stderr": 0.001622186051965178, "rougeLsum_precision": 0.12848267626833101, "rougeLsum_precision_stderr": 0.001630974223392642, "rougeLsum_recall": 0.22279087321132093, "rougeLsum_recall_stderr": 0.002389106143127278}}, "1": {"tldr_en": {"bleu": 2.7168288745150733, "bleu_stderr": 0.027788811943268626, "rouge1_fmeasure": 0.21680348134366537, "rouge1_fmeasure_stderr": 0.001989050230715222, "rouge1_precision": 0.19597965324143293, "rouge1_precision_stderr": 0.002422969033603622, "rouge1_recall": 0.30807161900164537, "rouge1_recall_stderr": 0.002888279311677417, "rouge2_fmeasure": 0.05286064770219989, "rouge2_fmeasure_stderr": 0.001047082376265833, "rouge2_precision": 0.04887204666302114, "rouge2_precision_stderr": 0.0012101120560090112, "rouge2_recall": 0.07830452489784998, "rouge2_recall_stderr": 0.001753737328157415, "rougeL_fmeasure": 0.1553125942912949, "rougeL_fmeasure_stderr": 0.0013586358162531915, "rougeL_precision": 0.1402306406868289, "rougeL_precision_stderr": 0.0017685483088721319, "rougeL_recall": 0.22562889491438992, "rougeL_recall_stderr": 0.0022551494750589806, "rougeLsum_fmeasure": 0.20291465452025823, "rougeLsum_fmeasure_stderr": 0.0018629082145186966, "rougeLsum_precision": 0.18311803161699944, "rougeLsum_precision_stderr": 0.002265837034209399, "rougeLsum_recall": 0.2891682061871711, "rougeLsum_recall_stderr": 0.0027405901383416903}}, "2": {"tldr_en": {"bleu": 3.2675360746374724, "bleu_stderr": 0.08683258860928667, "rouge1_fmeasure": 0.22866230908807564, "rouge1_fmeasure_stderr": 0.0020147705579940042, "rouge1_precision": 0.23230533068977285, "rouge1_precision_stderr": 0.0030036752804623442, "rouge1_recall": 0.3046485703206422, "rouge1_recall_stderr": 0.0028750423991394805, "rouge2_fmeasure": 0.060888223333973694, "rouge2_fmeasure_stderr": 0.0011653353070712725, "rouge2_precision": 0.0652728801755514, "rouge2_precision_stderr": 0.0017161092137583064, "rouge2_recall": 0.0829058837249749, "rouge2_recall_stderr": 0.001754132805519974, "rougeL_fmeasure": 0.16851985026250754, "rougeL_fmeasure_stderr": 0.0014514848028756428, "rougeL_precision": 0.17315090439930816, "rougeL_precision_stderr": 0.0024174186948284536, "rougeL_recall": 0.2282124017379743, "rougeL_recall_stderr": 0.002300871235282163, "rougeLsum_fmeasure": 0.21471496541744928, "rougeLsum_fmeasure_stderr": 0.0018967756817875995, "rougeLsum_precision": 0.21850921488114095, "rougeLsum_precision_stderr": 0.0028650070816662525, "rougeLsum_recall": 0.28681670261831177, "rougeLsum_recall_stderr": 0.0027453385383248543}}, "3": {"tldr_en": {"bleu": 3.4571170815517798, "bleu_stderr": 0.11185440921709665, "rouge1_fmeasure": 0.1910453925224341, "rouge1_fmeasure_stderr": 0.0024449942883835243, "rouge1_precision": 0.22121771598118475, "rouge1_precision_stderr": 0.0036882275444359075, "rouge1_recall": 0.23831799110246993, "rouge1_recall_stderr": 0.0033080637379997095, "rouge2_fmeasure": 0.051529814219383546, "rouge2_fmeasure_stderr": 0.001189886793038056, "rouge2_precision": 0.06323707056301245, "rouge2_precision_stderr": 0.0019407853996773528, "rouge2_recall": 0.06522283466577794, "rouge2_recall_stderr": 0.0016219133310123761, "rougeL_fmeasure": 0.14250487351665606, "rougeL_fmeasure_stderr": 0.0018287728747596122, "rougeL_precision": 0.16832253284028867, "rougeL_precision_stderr": 0.003029446243881275, "rougeL_recall": 0.17973410123077083, "rougeL_recall_stderr": 0.002596216187256791, "rougeLsum_fmeasure": 0.17980500124329604, "rougeLsum_fmeasure_stderr": 0.00230448407318417, "rougeLsum_precision": 0.2086767811307107, "rougeLsum_precision_stderr": 0.003528683033645415, "rougeLsum_recall": 0.2247899549532754, "rougeLsum_recall_stderr": 0.0031404458370532153}}, "4": {"tldr_en": {"bleu": 0.37512729284497387, "bleu_stderr": 0.04665793523101002, "rouge1_fmeasure": 0.05947904000070367, "rouge1_fmeasure_stderr": 0.0021033921236477135, "rouge1_precision": 0.07326898576418932, "rouge1_precision_stderr": 0.0029804014060718044, "rouge1_recall": 0.07568799959655953, "rouge1_recall_stderr": 0.0028074751240550607, "rouge2_fmeasure": 0.01728296372186625, "rouge2_fmeasure_stderr": 0.0008908091784950728, "rouge2_precision": 0.022965556707184615, "rouge2_precision_stderr": 0.0015228642864160765, "rouge2_recall": 0.022402099751607542, "rouge2_recall_stderr": 0.001220343284119567, "rougeL_fmeasure": 0.04552738337911959, "rougeL_fmeasure_stderr": 0.0016243803916888954, "rougeL_precision": 0.057052188452132516, "rougeL_precision_stderr": 0.002416482137095571, "rougeL_recall": 0.058506117501988836, "rougeL_recall_stderr": 0.0022193304609485686, "rougeLsum_fmeasure": 0.05588569971582654, "rougeLsum_fmeasure_stderr": 0.0019793675363465393, "rougeLsum_precision": 0.06908057532182588, "rougeLsum_precision_stderr": 0.0028326856194194608, "rougeLsum_recall": 0.07122286980128628, "rougeLsum_recall_stderr": 0.0026515883528468198}}, "5": {"tldr_en": {"bleu": 9.057918358584415e-10, "bleu_stderr": 1.3090455690116953e-08, "rouge1_fmeasure": 0.009146625387598535, "rouge1_fmeasure_stderr": 0.0009114133020918803, "rouge1_precision": 0.012546600724961473, "rouge1_precision_stderr": 0.0014221423920746097, "rouge1_recall": 0.011324922357585625, "rouge1_recall_stderr": 0.0012011987663360973, "rouge2_fmeasure": 0.0027845645104624837, "rouge2_fmeasure_stderr": 0.0003641282643201026, "rouge2_precision": 0.0043709718753766535, "rouge2_precision_stderr": 0.0007392598479393059, "rouge2_recall": 0.0033895837395352384, "rouge2_recall_stderr": 0.00047051146459395213, "rougeL_fmeasure": 0.007342736230521302, "rougeL_fmeasure_stderr": 0.0007380543407074755, "rougeL_precision": 0.01045006896437003, "rougeL_precision_stderr": 0.0012453848216518722, "rougeL_recall": 0.009122577990200997, "rougeL_recall_stderr": 0.000983100115431667, "rougeLsum_fmeasure": 0.008574866517808083, "rougeLsum_fmeasure_stderr": 0.0008563811700283816, "rougeLsum_precision": 0.011775345328321534, "rougeLsum_precision_stderr": 0.0013398695127862124, "rougeLsum_recall": 0.010638508770344847, "rougeLsum_recall_stderr": 0.001134108586551112}}}, "e2e_nlg_cleaned": {"0": {"generate_text_restaurant": {"bleu": 0.738880340832374, "bleu_stderr": 0.04651887226561536, "rouge1_fmeasure": 0.050118755058782646, "rouge1_fmeasure_stderr": 0.0014742729328469702, "rouge1_precision": 0.052408016752691446, "rouge1_precision_stderr": 0.002069413491304116, "rouge1_recall": 0.06611213352593753, "rouge1_recall_stderr": 0.0019169506619435516, "rouge2_fmeasure": 0.008068622381751343, "rouge2_fmeasure_stderr": 0.00048397220318496613, "rouge2_precision": 0.009264205385647836, "rouge2_precision_stderr": 0.0008993357508819185, "rouge2_recall": 0.010746367103802498, "rouge2_recall_stderr": 0.0006591451074415208, "rougeL_fmeasure": 0.047155147289973866, "rougeL_fmeasure_stderr": 0.001334985116334414, "rougeL_precision": 0.048471629139317844, "rougeL_precision_stderr": 0.0018609513634729462, "rougeL_recall": 0.06283863413145736, "rougeL_recall_stderr": 0.0017661414810148984, "rougeLsum_fmeasure": 0.0431973996383776, "rougeLsum_fmeasure_stderr": 0.001255164747503297, "rougeLsum_precision": 0.0456867380026897, "rougeLsum_precision_stderr": 0.00185315034592773, "rougeLsum_recall": 0.05692816128408565, "rougeLsum_recall_stderr": 0.0016193064852484875}}, "1": {"generate_text_restaurant": {"bleu": 11.446421761894344, "bleu_stderr": 0.111190971889358, "rouge1_fmeasure": 0.43859504317443493, "rouge1_fmeasure_stderr": 0.0025277589360022685, "rouge1_precision": 0.5152581147319953, "rouge1_precision_stderr": 0.0035154951461692165, "rouge1_recall": 0.42583753387509593, "rouge1_recall_stderr": 0.0030236799087489867, "rouge2_fmeasure": 0.20211483492826335, "rouge2_fmeasure_stderr": 0.0019943148357916317, "rouge2_precision": 0.24162888518806513, "rouge2_precision_stderr": 0.0026220142738116506, "rouge2_recall": 0.1957847381688039, "rouge2_recall_stderr": 0.0021367049073086515, "rougeL_fmeasure": 0.3160711002960154, "rougeL_fmeasure_stderr": 0.002105227505008761, "rougeL_precision": 0.3735691048948855, "rougeL_precision_stderr": 0.0029961441661871457, "rougeL_recall": 0.30725639156678053, "rougeL_recall_stderr": 0.0024531169122745545, "rougeLsum_fmeasure": 0.35510314962800665, "rougeLsum_fmeasure_stderr": 0.002412378682482004, "rougeLsum_precision": 0.41876922944473616, "rougeLsum_precision_stderr": 0.0032969473599339, "rougeLsum_recall": 0.3442066200646512, "rougeLsum_recall_stderr": 0.002749257268367504}}, "2": {"generate_text_restaurant": {"bleu": 12.893868597748744, "bleu_stderr": 0.17839036102138914, "rouge1_fmeasure": 0.4727847178064714, "rouge1_fmeasure_stderr": 0.0022559995050162435, "rouge1_precision": 0.568712540533982, "rouge1_precision_stderr": 0.0033582948446322244, "rouge1_recall": 0.4455355451042784, "rouge1_recall_stderr": 0.002891663668222815, "rouge2_fmeasure": 0.229219242456448, "rouge2_fmeasure_stderr": 0.0020169224365506767, "rouge2_precision": 0.28075626370538587, "rouge2_precision_stderr": 0.0027909661932880576, "rouge2_recall": 0.21574668142339343, "rouge2_recall_stderr": 0.0021570905432228143, "rougeL_fmeasure": 0.34299042747431135, "rougeL_fmeasure_stderr": 0.002062382050630995, "rougeL_precision": 0.4156345621332711, "rougeL_precision_stderr": 0.00308485694082615, "rougeL_recall": 0.3224976494814963, "rougeL_recall_stderr": 0.0024104306364720602, "rougeLsum_fmeasure": 0.3867022093227863, "rougeLsum_fmeasure_stderr": 0.0022789845452372347, "rougeLsum_precision": 0.4666392155482241, "rougeLsum_precision_stderr": 0.0032864555203226007, "rougeLsum_recall": 0.3639494683421977, "rougeLsum_recall_stderr": 0.002679273232452678}}, "3": {"generate_text_restaurant": {"bleu": 13.63961900281485, "bleu_stderr": 0.17788218998077254, "rouge1_fmeasure": 0.48078987509500615, "rouge1_fmeasure_stderr": 0.0021929316300569263, "rouge1_precision": 0.5754932228162358, "rouge1_precision_stderr": 0.0032590679502994637, "rouge1_recall": 0.4517617719347589, "rouge1_recall_stderr": 0.0028165475670176676, "rouge2_fmeasure": 0.23822209960416982, "rouge2_fmeasure_stderr": 0.0020467054694790665, "rouge2_precision": 0.28993439870311544, "rouge2_precision_stderr": 0.0027900264921732216, "rouge2_recall": 0.22348428301675585, "rouge2_recall_stderr": 0.0021878663239347515, "rougeL_fmeasure": 0.3491781912080909, "rougeL_fmeasure_stderr": 0.0021046356381219707, "rougeL_precision": 0.42055457185243106, "rougeL_precision_stderr": 0.0030592051391566963, "rougeL_recall": 0.32734330354293284, "rougeL_recall_stderr": 0.002420584401467437, "rougeLsum_fmeasure": 0.3942653928984815, "rougeLsum_fmeasure_stderr": 0.002285077612873893, "rougeLsum_precision": 0.4731870305833878, "rougeLsum_precision_stderr": 0.003239199105701286, "rougeLsum_recall": 0.36991647341846207, "rougeLsum_recall_stderr": 0.00266037590253722}}, "4": {"generate_text_restaurant": {"bleu": 13.706332171059909, "bleu_stderr": 0.17357539752293022, "rouge1_fmeasure": 0.48357693456583833, "rouge1_fmeasure_stderr": 0.0022217417972761177, "rouge1_precision": 0.580340744845304, "rouge1_precision_stderr": 0.0033301065448643466, "rouge1_recall": 0.4533472286558441, "rouge1_recall_stderr": 0.0028274471021811996, "rouge2_fmeasure": 0.24026329345887795, "rouge2_fmeasure_stderr": 0.0020310162284047782, "rouge2_precision": 0.29364093390036733, "rouge2_precision_stderr": 0.002808483607800915, "rouge2_recall": 0.2250159933431281, "rouge2_recall_stderr": 0.002181345454753508, "rougeL_fmeasure": 0.34902580610434175, "rougeL_fmeasure_stderr": 0.0021099334383203596, "rougeL_precision": 0.42100879430000404, "rougeL_precision_stderr": 0.003064615520959508, "rougeL_recall": 0.32697853591664555, "rougeL_recall_stderr": 0.002454893444584628, "rougeLsum_fmeasure": 0.39552361553161913, "rougeLsum_fmeasure_stderr": 0.002319765372714739, "rougeLsum_precision": 0.47504731799692856, "rougeLsum_precision_stderr": 0.003260042215555032, "rougeLsum_recall": 0.3709711786676177, "rougeLsum_recall_stderr": 0.0027214153769374}}, "5": {"generate_text_restaurant": {"bleu": 13.874473042661693, "bleu_stderr": 0.19433557311613792, "rouge1_fmeasure": 0.48439831489977875, "rouge1_fmeasure_stderr": 0.0022107968893640417, "rouge1_precision": 0.5763764969347113, "rouge1_precision_stderr": 0.0033401713453945284, "rouge1_recall": 0.4557042429829976, "rouge1_recall_stderr": 0.002782164054925254, "rouge2_fmeasure": 0.24162268466989079, "rouge2_fmeasure_stderr": 0.002004297882388908, "rouge2_precision": 0.29246933045258144, "rouge2_precision_stderr": 0.0027370025774699114, "rouge2_recall": 0.2267723714767104, "rouge2_recall_stderr": 0.0021325910040586294, "rougeL_fmeasure": 0.3484000057187485, "rougeL_fmeasure_stderr": 0.0021061285704237257, "rougeL_precision": 0.4158636729381195, "rougeL_precision_stderr": 0.003006341057324312, "rougeL_recall": 0.3275521712743745, "rougeL_recall_stderr": 0.002417468603854672, "rougeLsum_fmeasure": 0.3962957295452578, "rougeLsum_fmeasure_stderr": 0.002317649273528697, "rougeLsum_precision": 0.4719057774413631, "rougeLsum_precision_stderr": 0.0032547651494311985, "rougeLsum_recall": 0.3727454885428157, "rougeLsum_recall_stderr": 0.0026751481666428003}}}, "gem_xsum": {"0": {"article_DOC_summary": {"bleu": 1.8397297017505467, "bleu_stderr": 0.0975788369778515, "rouge1_fmeasure": 0.20765947458451095, "rouge1_fmeasure_stderr": 0.0024949975339913135, "rouge1_precision": 0.14863424101475148, "rouge1_precision_stderr": 0.001889235728566759, "rouge1_recall": 0.3611280371267823, "rouge1_recall_stderr": 0.004309337837275094, "rouge2_fmeasure": 0.04709848078089926, "rouge2_fmeasure_stderr": 0.001509616630471501, "rouge2_precision": 0.033300888872525, "rouge2_precision_stderr": 0.0010747171841351266, "rouge2_recall": 0.08464992936654857, "rouge2_recall_stderr": 0.0027992823728708364, "rougeL_fmeasure": 0.15553665911046835, "rougeL_fmeasure_stderr": 0.0018617800659320165, "rougeL_precision": 0.1111376094065842, "rougeL_precision_stderr": 0.0013958730750838581, "rougeL_recall": 0.2719983089652059, "rougeL_recall_stderr": 0.003375307850115804, "rougeLsum_fmeasure": 0.1639946283991839, "rougeLsum_fmeasure_stderr": 0.0020904960358978327, "rougeLsum_precision": 0.11708609526596682, "rougeLsum_precision_stderr": 0.0015516278773820243, "rougeLsum_recall": 0.28710107671237667, "rougeLsum_recall_stderr": 0.0037825062377304913}}, "1": {"article_DOC_summary": {"bleu": 1.6553470688151115, "bleu_stderr": 0.09590796158391537, "rouge1_fmeasure": 0.1838955898661093, "rouge1_fmeasure_stderr": 0.002519438099815121, "rouge1_precision": 0.13091259350658735, "rouge1_precision_stderr": 0.001884606689398822, "rouge1_recall": 0.32261620498355015, "rouge1_recall_stderr": 0.004298941602696091, "rouge2_fmeasure": 0.04033553334600084, "rouge2_fmeasure_stderr": 0.0015013678761037455, "rouge2_precision": 0.02840336441434044, "rouge2_precision_stderr": 0.0010609385580752778, "rouge2_recall": 0.07271493381713101, "rouge2_recall_stderr": 0.0027803945064812582, "rougeL_fmeasure": 0.14334395601866984, "rougeL_fmeasure_stderr": 0.0018863495401931067, "rougeL_precision": 0.10180221611921418, "rougeL_precision_stderr": 0.0013914776864634845, "rougeL_recall": 0.25327849734415897, "rougeL_recall_stderr": 0.003414998206683635, "rougeLsum_fmeasure": 0.14862352990067781, "rougeLsum_fmeasure_stderr": 0.0021101020714172206, "rougeLsum_precision": 0.10552933002715077, "rougeLsum_precision_stderr": 0.0015539874224615002, "rougeLsum_recall": 0.26234547935998204, "rougeLsum_recall_stderr": 0.003741165599591686}}, "2": {"article_DOC_summary": {"bleu": 1.7260347212167786, "bleu_stderr": 0.09379967942900527, "rouge1_fmeasure": 0.19261782339396993, "rouge1_fmeasure_stderr": 0.0025012415561919904, "rouge1_precision": 0.13686236595948673, "rouge1_precision_stderr": 0.0018586773458732157, "rouge1_recall": 0.3392020933900856, "rouge1_recall_stderr": 0.004362855594876969, "rouge2_fmeasure": 0.04342909149683322, "rouge2_fmeasure_stderr": 0.0014772333098834758, "rouge2_precision": 0.030531145414807732, "rouge2_precision_stderr": 0.001043741309814839, "rouge2_recall": 0.0784703368760383, "rouge2_recall_stderr": 0.0027384750987831906, "rougeL_fmeasure": 0.15058038559332929, "rougeL_fmeasure_stderr": 0.001896589233843395, "rougeL_precision": 0.10680509448736829, "rougeL_precision_stderr": 0.0013945518685996993, "rougeL_recall": 0.266591727731496, "rougeL_recall_stderr": 0.0034535876908137675, "rougeLsum_fmeasure": 0.15300151314661534, "rougeLsum_fmeasure_stderr": 0.002084264405489951, "rougeLsum_precision": 0.10841342799525587, "rougeLsum_precision_stderr": 0.0015247169077855051, "rougeLsum_recall": 0.27145334576678937, "rougeLsum_recall_stderr": 0.0037737714627561793}}, "3": {"article_DOC_summary": {"bleu": 1.7657865425649448, "bleu_stderr": 0.08784292280554437, "rouge1_fmeasure": 0.18454086793583163, "rouge1_fmeasure_stderr": 0.0026884351712387036, "rouge1_precision": 0.13426328561680495, "rouge1_precision_stderr": 0.0020952435382080334, "rouge1_recall": 0.31793760566995066, "rouge1_recall_stderr": 0.004672185209431927, "rouge2_fmeasure": 0.042742113597443655, "rouge2_fmeasure_stderr": 0.001480226206590244, "rouge2_precision": 0.030672509863059055, "rouge2_precision_stderr": 0.001071374244565695, "rouge2_recall": 0.07566282036135609, "rouge2_recall_stderr": 0.0026968059572813887, "rougeL_fmeasure": 0.14670609076269023, "rougeL_fmeasure_stderr": 0.0020959224179861844, "rougeL_precision": 0.10650878158540643, "rougeL_precision_stderr": 0.0016129244849752715, "rougeL_recall": 0.2539521089029489, "rougeL_recall_stderr": 0.0037626482110457867, "rougeLsum_fmeasure": 0.14652576211008259, "rougeLsum_fmeasure_stderr": 0.0022572828156902716, "rougeLsum_precision": 0.10658151873272122, "rougeLsum_precision_stderr": 0.0017550430346461852, "rougeLsum_recall": 0.2536276945583284, "rougeLsum_recall_stderr": 0.00400889163237277}}, "4": {"article_DOC_summary": {"bleu": 0.799504863010099, "bleu_stderr": 0.14772171245429597, "rouge1_fmeasure": 0.051814503429919195, "rouge1_fmeasure_stderr": 0.0028539972571649933, "rouge1_precision": 0.04497331060218232, "rouge1_precision_stderr": 0.002814626684315661, "rouge1_recall": 0.08123782006917032, "rouge1_recall_stderr": 0.004591818366865356, "rouge2_fmeasure": 0.011332244290967035, "rouge2_fmeasure_stderr": 0.0009751133313839088, "rouge2_precision": 0.008667148602784157, "rouge2_precision_stderr": 0.0007853858434933216, "rouge2_recall": 0.018754617379423303, "rouge2_recall_stderr": 0.0016184423254747898, "rougeL_fmeasure": 0.040210659587378024, "rougeL_fmeasure_stderr": 0.0022170222599325216, "rougeL_precision": 0.035206749441193126, "rougeL_precision_stderr": 0.0023005984651959794, "rougeL_recall": 0.06336348650827417, "rougeL_recall_stderr": 0.003615987862576232, "rougeLsum_fmeasure": 0.04095730396603746, "rougeLsum_fmeasure_stderr": 0.002280962495996791, "rougeLsum_precision": 0.0360038531299483, "rougeLsum_precision_stderr": 0.0023602351409316006, "rougeLsum_recall": 0.06441398241214587, "rougeLsum_recall_stderr": 0.0037121565270241174}}, "5": {"article_DOC_summary": {"bleu": 5.458377653225689e-38, "bleu_stderr": 1.8035741413249208e-33, "rouge1_fmeasure": 0.0029282243132696126, "rouge1_fmeasure_stderr": 0.0008041631143247972, "rouge1_precision": 0.003355513733237315, "rouge1_precision_stderr": 0.0009455055533347477, "rouge1_recall": 0.002718861130313723, "rouge1_recall_stderr": 0.0007459270614612365, "rouge2_fmeasure": 0.0005606574915282881, "rouge2_fmeasure_stderr": 0.00024596800551172275, "rouge2_precision": 0.0006489002118857834, "rouge2_precision_stderr": 0.0002814932710759057, "rouge2_recall": 0.0005128639396119974, "rouge2_recall_stderr": 0.00023203066957191624, "rougeL_fmeasure": 0.0023043621016504206, "rougeL_fmeasure_stderr": 0.0006375673352876025, "rougeL_precision": 0.002644232937328328, "rougeL_precision_stderr": 0.0007503935532346942, "rougeL_recall": 0.0021224087356534397, "rougeL_recall_stderr": 0.0005862503437927338, "rougeLsum_fmeasure": 0.0024184751660207746, "rougeLsum_fmeasure_stderr": 0.0006657117606404112, "rougeLsum_precision": 0.0027423282074546746, "rougeLsum_precision_stderr": 0.0007726079722089125, "rougeLsum_recall": 0.0022760374270179803, "rougeLsum_recall_stderr": 0.0006320851976915994}}}}