Muennighoff's picture
Add
29393c3
raw
history blame contribute delete
No virus
28.1 kB
{"GEM/web_nlg_en": {"0": {"PALM_prompt": {"bleu": 0.3751221736027223, "bleu_stderr": 0.04603981713785397, "rouge1_fmeasure": 0.10655282549139757, "rouge1_fmeasure_stderr": 0.002069892427617646, "rouge1_precision": 0.07050754951097193, "rouge1_precision_stderr": 0.0015950749741378038, "rouge1_recall": 0.2930621241248632, "rouge1_recall_stderr": 0.0047039720667729585, "rouge2_fmeasure": 0.05052209059024575, "rouge2_fmeasure_stderr": 0.0012866888304456589, "rouge2_precision": 0.03327005966333133, "rouge2_precision_stderr": 0.0009772300003902292, "rouge2_recall": 0.14224611225552608, "rouge2_recall_stderr": 0.0031500776280318555, "rougeL_fmeasure": 0.10267935520945128, "rougeL_fmeasure_stderr": 0.0019389896303185993, "rougeL_precision": 0.0677233404229661, "rougeL_precision_stderr": 0.0014833039402630307, "rougeL_recall": 0.28507940697548506, "rougeL_recall_stderr": 0.004611898165464154, "rougeLsum_fmeasure": 0.10179374812954574, "rougeLsum_fmeasure_stderr": 0.0019553887116743455, "rougeLsum_precision": 0.06739541442277049, "rougeLsum_precision_stderr": 0.0015164320427077738, "rougeLsum_recall": 0.27995528365978256, "rougeLsum_recall_stderr": 0.004446276996131344}}, "1": {"PALM_prompt": {"bleu": 0.5198830574890386, "bleu_stderr": 0.03504017360483535, "rouge1_fmeasure": 0.12070700921084229, "rouge1_fmeasure_stderr": 0.002002150459250641, "rouge1_precision": 0.07738811110777072, "rouge1_precision_stderr": 0.0015304988936609128, "rouge1_recall": 0.3862577997016925, "rouge1_recall_stderr": 0.00572058610283539, "rouge2_fmeasure": 0.05531307099139748, "rouge2_fmeasure_stderr": 0.0012137549494064656, "rouge2_precision": 0.03507152315512706, "rouge2_precision_stderr": 0.0008467381062339321, "rouge2_recall": 0.18709836433905874, "rouge2_recall_stderr": 0.003833792467120382, "rougeL_fmeasure": 0.11194710382233043, "rougeL_fmeasure_stderr": 0.0017263614451165634, "rougeL_precision": 0.07158564602943736, "rougeL_precision_stderr": 0.0013356095688320767, "rougeL_recall": 0.3620899416623159, "rougeL_recall_stderr": 0.005273165348503305, "rougeLsum_fmeasure": 0.11393170029640054, "rougeLsum_fmeasure_stderr": 0.0018446583441229345, "rougeLsum_precision": 0.07309280304036243, "rougeLsum_precision_stderr": 0.0014294724139865343, "rougeLsum_recall": 0.36442715703356776, "rougeLsum_recall_stderr": 0.005241997303110117}}, "2": {"PALM_prompt": {"bleu": 0.5772980788839762, "bleu_stderr": 0.0351401276773091, "rouge1_fmeasure": 0.12373316030300299, "rouge1_fmeasure_stderr": 0.0018974475884765722, "rouge1_precision": 0.07813906472896695, "rouge1_precision_stderr": 0.0013627013823755202, "rouge1_recall": 0.4101295780853266, "rouge1_recall_stderr": 0.005693087311032938, "rouge2_fmeasure": 0.0570319859750151, "rouge2_fmeasure_stderr": 0.0011521977790571885, "rouge2_precision": 0.03581354421318794, "rouge2_precision_stderr": 0.0008022617515173707, "rouge2_recall": 0.2032111746093155, "rouge2_recall_stderr": 0.003954708803559, "rougeL_fmeasure": 0.11350896035348979, "rougeL_fmeasure_stderr": 0.0016169887067107285, "rougeL_precision": 0.07158825167996366, "rougeL_precision_stderr": 0.0011655724191791303, "rougeL_recall": 0.3794140508633469, "rougeL_recall_stderr": 0.005145968326494213, "rougeLsum_fmeasure": 0.11690863992503238, "rougeLsum_fmeasure_stderr": 0.0017500511668341343, "rougeLsum_precision": 0.07387016720939305, "rougeLsum_precision_stderr": 0.0012627844516927061, "rougeLsum_recall": 0.38737624946784815, "rougeLsum_recall_stderr": 0.005248864126942714}}, "3": {"PALM_prompt": {"bleu": 0.6456226857113138, "bleu_stderr": 0.040165536189754096, "rouge1_fmeasure": 0.12436437584313036, "rouge1_fmeasure_stderr": 0.001814950124577219, "rouge1_precision": 0.0778881396479436, "rouge1_precision_stderr": 0.0012769567386518232, "rouge1_recall": 0.42296024366383517, "rouge1_recall_stderr": 0.00569044382493207, "rouge2_fmeasure": 0.05661337603042263, "rouge2_fmeasure_stderr": 0.001071749411178637, "rouge2_precision": 0.03521828535740504, "rouge2_precision_stderr": 0.0007298691703855176, "rouge2_recall": 0.20809711310932535, "rouge2_recall_stderr": 0.003931907827643346, "rougeL_fmeasure": 0.11292204203780767, "rougeL_fmeasure_stderr": 0.0015573442585516018, "rougeL_precision": 0.07076272874827239, "rougeL_precision_stderr": 0.0011113411679509696, "rougeL_recall": 0.3866270125315969, "rougeL_recall_stderr": 0.005107912406441445, "rougeLsum_fmeasure": 0.1168466330708585, "rougeLsum_fmeasure_stderr": 0.0016763512625120776, "rougeLsum_precision": 0.0732788083787352, "rougeLsum_precision_stderr": 0.0011890321940136864, "rougeLsum_recall": 0.39617638119143006, "rougeLsum_recall_stderr": 0.0051662731631678}}, "4": {"PALM_prompt": {"bleu": 0.7394949248334012, "bleu_stderr": 0.0375339718418186, "rouge1_fmeasure": 0.12719292338738244, "rouge1_fmeasure_stderr": 0.0017548996669778086, "rouge1_precision": 0.07935954064608862, "rouge1_precision_stderr": 0.0012440228309059662, "rouge1_recall": 0.44189075126537175, "rouge1_recall_stderr": 0.0056160164221400995, "rouge2_fmeasure": 0.058223377247645175, "rouge2_fmeasure_stderr": 0.001073250860654579, "rouge2_precision": 0.03609299322498633, "rouge2_precision_stderr": 0.0007391134009433947, "rouge2_recall": 0.21980568290237434, "rouge2_recall_stderr": 0.004020542118197972, "rougeL_fmeasure": 0.1144359922322097, "rougeL_fmeasure_stderr": 0.0014869489906081234, "rougeL_precision": 0.07145742950585998, "rougeL_precision_stderr": 0.0010699196551391536, "rougeL_recall": 0.3991369324047731, "rougeL_recall_stderr": 0.0049417529681389525, "rougeLsum_fmeasure": 0.11931787390462796, "rougeLsum_fmeasure_stderr": 0.0016294893480413802, "rougeLsum_precision": 0.07454021703025861, "rougeLsum_precision_stderr": 0.0011655709781687874, "rougeLsum_recall": 0.41368909933661674, "rougeLsum_recall_stderr": 0.005127640598028314}}, "5": {"PALM_prompt": {"bleu": 0.7350884275632563, "bleu_stderr": 0.04285525370548216, "rouge1_fmeasure": 0.12790081410584203, "rouge1_fmeasure_stderr": 0.001762758952960184, "rouge1_precision": 0.07963440574460627, "rouge1_precision_stderr": 0.0012450999827039412, "rouge1_recall": 0.450750421306443, "rouge1_recall_stderr": 0.005688854042032203, "rouge2_fmeasure": 0.058684632135392434, "rouge2_fmeasure_stderr": 0.0010628257100155462, "rouge2_precision": 0.03626337631746513, "rouge2_precision_stderr": 0.0007247188269312321, "rouge2_recall": 0.22702405178339297, "rouge2_recall_stderr": 0.004195235523736308, "rougeL_fmeasure": 0.11440641190075858, "rougeL_fmeasure_stderr": 0.0014753694031490337, "rougeL_precision": 0.07125643393688096, "rougeL_precision_stderr": 0.00105707615542693, "rougeL_recall": 0.4063747251874938, "rougeL_recall_stderr": 0.005069676186964856, "rougeLsum_fmeasure": 0.11957698534047122, "rougeLsum_fmeasure_stderr": 0.0016217012306438583, "rougeLsum_precision": 0.07452930873504321, "rougeLsum_precision_stderr": 0.0011537233047546483, "rougeLsum_recall": 0.42116829387113064, "rougeLsum_recall_stderr": 0.005204895411040752}}}, "GEM/wiki_lingua_en": {"0": {"tldr_en": {"bleu": 1.5445764212442845, "bleu_stderr": 0.046348567423538295, "rouge1_fmeasure": 0.17846806393672296, "rouge1_fmeasure_stderr": 0.0018156572490314613, "rouge1_precision": 0.15229529499726693, "rouge1_precision_stderr": 0.0018532935787449235, "rouge1_recall": 0.2584223718261279, "rouge1_recall_stderr": 0.0025516613510239644, "rouge2_fmeasure": 0.035498190179559366, "rouge2_fmeasure_stderr": 0.0008425007414760624, "rouge2_precision": 0.030189999709011046, "rouge2_precision_stderr": 0.0007527178027814116, "rouge2_recall": 0.05276107785013939, "rouge2_recall_stderr": 0.0013537005512275853, "rougeL_fmeasure": 0.13992548854671796, "rougeL_fmeasure_stderr": 0.0012925170885687428, "rougeL_precision": 0.11790693896267036, "rougeL_precision_stderr": 0.001294367886229787, "rougeL_recall": 0.20826559324975696, "rougeL_recall_stderr": 0.0020968023223764095, "rougeLsum_fmeasure": 0.16300806309885615, "rougeLsum_fmeasure_stderr": 0.0016517242441511555, "rougeLsum_precision": 0.1388827214194179, "rougeLsum_precision_stderr": 0.0016844636725997805, "rougeLsum_recall": 0.2370411466342553, "rougeLsum_recall_stderr": 0.002357902527598024}}, "1": {"tldr_en": {"bleu": 2.9354736259244234, "bleu_stderr": 0.08184998217131226, "rouge1_fmeasure": 0.22871763440008758, "rouge1_fmeasure_stderr": 0.0019504250194142293, "rouge1_precision": 0.19660419529835046, "rouge1_precision_stderr": 0.0021703512663018435, "rouge1_recall": 0.33305075642202464, "rouge1_recall_stderr": 0.0027422057559937344, "rouge2_fmeasure": 0.056810181676750955, "rouge2_fmeasure_stderr": 0.0010692773805419653, "rouge2_precision": 0.048646612266404474, "rouge2_precision_stderr": 0.0010079743018688542, "rouge2_recall": 0.08571356139913104, "rouge2_recall_stderr": 0.0017928353996558705, "rougeL_fmeasure": 0.1584532961497466, "rougeL_fmeasure_stderr": 0.0012813295440813953, "rougeL_precision": 0.13473919020916866, "rougeL_precision_stderr": 0.0014138439503997033, "rougeL_recall": 0.2377264850157444, "rougeL_recall_stderr": 0.0022081866868395457, "rougeLsum_fmeasure": 0.21440206759227748, "rougeLsum_fmeasure_stderr": 0.0018298647451743082, "rougeLsum_precision": 0.18408931555378133, "rougeLsum_precision_stderr": 0.0020314434795525877, "rougeLsum_recall": 0.3130915982176866, "rougeLsum_recall_stderr": 0.002608677189171684}}, "2": {"tldr_en": {"bleu": 2.988336179481119, "bleu_stderr": 0.07284534182808335, "rouge1_fmeasure": 0.2216752304780583, "rouge1_fmeasure_stderr": 0.0018496410521841634, "rouge1_precision": 0.19308251629949974, "rouge1_precision_stderr": 0.0021372296672672315, "rouge1_recall": 0.3226572993341573, "rouge1_recall_stderr": 0.002715283947112145, "rouge2_fmeasure": 0.05419402589748163, "rouge2_fmeasure_stderr": 0.0010092487989924672, "rouge2_precision": 0.04755808223353882, "rouge2_precision_stderr": 0.001056965112675896, "rouge2_recall": 0.08157607236301773, "rouge2_recall_stderr": 0.0016928843275132437, "rougeL_fmeasure": 0.15534336307223465, "rougeL_fmeasure_stderr": 0.0012446244313757237, "rougeL_precision": 0.13475955724902108, "rougeL_precision_stderr": 0.0015213837884005157, "rougeL_recall": 0.23151769344902068, "rougeL_recall_stderr": 0.002143281502769755, "rougeLsum_fmeasure": 0.2092469074780288, "rougeLsum_fmeasure_stderr": 0.0017297088792391818, "rougeLsum_precision": 0.18213738467572518, "rougeLsum_precision_stderr": 0.0020147435204007475, "rougeLsum_recall": 0.3053278835262653, "rougeLsum_recall_stderr": 0.0025811768541287375}}, "3": {"tldr_en": {"bleu": 2.955313094852994, "bleu_stderr": 0.0766356215689601, "rouge1_fmeasure": 0.18235828185303843, "rouge1_fmeasure_stderr": 0.0022330522398271444, "rouge1_precision": 0.16818607657817242, "rouge1_precision_stderr": 0.002571340600589284, "rouge1_recall": 0.2618591281994728, "rouge1_recall_stderr": 0.0033215062620397654, "rouge2_fmeasure": 0.04352751746326409, "rouge2_fmeasure_stderr": 0.000986420480404656, "rouge2_precision": 0.039906055320126824, "rouge2_precision_stderr": 0.0011176532929901056, "rouge2_recall": 0.06504905939729995, "rouge2_recall_stderr": 0.0016338067696316037, "rougeL_fmeasure": 0.12850084937451378, "rougeL_fmeasure_stderr": 0.0015346657748469231, "rougeL_precision": 0.11910589220232795, "rougeL_precision_stderr": 0.001919539273889145, "rougeL_recall": 0.18906464586111238, "rougeL_recall_stderr": 0.002550157025960148, "rougeLsum_fmeasure": 0.17275184259901263, "rougeLsum_fmeasure_stderr": 0.0021141809407287217, "rougeLsum_precision": 0.1592819269786109, "rougeLsum_precision_stderr": 0.0024458047067507224, "rougeLsum_recall": 0.24869687852492026, "rougeLsum_recall_stderr": 0.00317986279337076}}, "4": {"tldr_en": {"bleu": 0.6681174311441812, "bleu_stderr": 0.044021606714169687, "rouge1_fmeasure": 0.0587450878634487, "rouge1_fmeasure_stderr": 0.001987849748246455, "rouge1_precision": 0.05651284854563454, "rouge1_precision_stderr": 0.002164889280586853, "rouge1_recall": 0.08771427792659671, "rouge1_recall_stderr": 0.003046668032178251, "rouge2_fmeasure": 0.014698951085450463, "rouge2_fmeasure_stderr": 0.0007071025730658953, "rouge2_precision": 0.01373423070578025, "rouge2_precision_stderr": 0.0007944242550989159, "rouge2_recall": 0.023902876010557156, "rouge2_recall_stderr": 0.0012871698398313374, "rougeL_fmeasure": 0.04283521055248602, "rougeL_fmeasure_stderr": 0.001420656788711465, "rougeL_precision": 0.041455127649633716, "rougeL_precision_stderr": 0.001604158922614608, "rougeL_recall": 0.06565381938564946, "rougeL_recall_stderr": 0.002338953948684061, "rougeLsum_fmeasure": 0.05516099966060376, "rougeLsum_fmeasure_stderr": 0.0018676755144161564, "rougeLsum_precision": 0.053065857077570854, "rougeLsum_precision_stderr": 0.0020380922902812288, "rougeLsum_recall": 0.08260798722441874, "rougeLsum_recall_stderr": 0.002886226452230474}}, "5": {"tldr_en": {"bleu": 8.138411373037316e-07, "bleu_stderr": 1.7429365149014433e-06, "rouge1_fmeasure": 0.009157992753346606, "rouge1_fmeasure_stderr": 0.000856510665924713, "rouge1_precision": 0.008744552174562775, "rouge1_precision_stderr": 0.0008820534430831269, "rouge1_recall": 0.014063870074080958, "rouge1_recall_stderr": 0.0013626675606431993, "rouge2_fmeasure": 0.002073109168721178, "rouge2_fmeasure_stderr": 0.00025579423912383813, "rouge2_precision": 0.001867598511771763, "rouge2_precision_stderr": 0.0002589055645534681, "rouge2_recall": 0.0037526556188222397, "rouge2_recall_stderr": 0.0005665830894881638, "rougeL_fmeasure": 0.006597140236099842, "rougeL_fmeasure_stderr": 0.0006134117940431641, "rougeL_precision": 0.006278467313776165, "rougeL_precision_stderr": 0.0006318463479225579, "rougeL_recall": 0.010544788230721835, "rougeL_recall_stderr": 0.0010639298188298192, "rougeLsum_fmeasure": 0.008602211224573027, "rougeLsum_fmeasure_stderr": 0.0007971656716790751, "rougeLsum_precision": 0.00823467650006455, "rougeLsum_precision_stderr": 0.000829000231276819, "rougeLsum_recall": 0.013318449806788014, "rougeLsum_recall_stderr": 0.0012936214066513207}}}, "e2e_nlg_cleaned": {"0": {"generate_text_restaurant": {"bleu": 0.1675172437507659, "bleu_stderr": 0.027600643399440884, "rouge1_fmeasure": 0.024088126860004336, "rouge1_fmeasure_stderr": 0.0006566077823850723, "rouge1_precision": 0.028701737940994714, "rouge1_precision_stderr": 0.0010195754285503126, "rouge1_recall": 0.02982766113489123, "rouge1_recall_stderr": 0.0008471594561940423, "rouge2_fmeasure": 0.001114996015022125, "rouge2_fmeasure_stderr": 0.00018328608469909375, "rouge2_precision": 0.0015626210476206773, "rouge2_precision_stderr": 0.0003728911300811695, "rouge2_recall": 0.0014347430615192808, "rouge2_recall_stderr": 0.00023769294132393532, "rougeL_fmeasure": 0.023944632138488853, "rougeL_fmeasure_stderr": 0.0006463198681447033, "rougeL_precision": 0.028417386089142856, "rougeL_precision_stderr": 0.0009947648295870358, "rougeL_recall": 0.029685273969587405, "rougeL_recall_stderr": 0.00083480831932383, "rougeLsum_fmeasure": 0.022309991073370505, "rougeLsum_fmeasure_stderr": 0.0005760998972707722, "rougeLsum_precision": 0.02728685295948081, "rougeLsum_precision_stderr": 0.0009885875546693994, "rougeLsum_recall": 0.02727004908623676, "rougeLsum_recall_stderr": 0.0007114664570306672}}, "1": {"generate_text_restaurant": {"bleu": 5.8311861735166675, "bleu_stderr": 0.06388138684732117, "rouge1_fmeasure": 0.3211813837867464, "rouge1_fmeasure_stderr": 0.002018437643374035, "rouge1_precision": 0.2601081962246765, "rouge1_precision_stderr": 0.0021349255671127927, "rouge1_recall": 0.4686781469942304, "rouge1_recall_stderr": 0.002825480648369596, "rouge2_fmeasure": 0.13429472916574672, "rouge2_fmeasure_stderr": 0.0014217210935365725, "rouge2_precision": 0.10907314684339463, "rouge2_precision_stderr": 0.0013682678699487114, "rouge2_recall": 0.1992897827723483, "rouge2_recall_stderr": 0.0021146365213576476, "rougeL_fmeasure": 0.25612256110358006, "rougeL_fmeasure_stderr": 0.0014268806319662325, "rougeL_precision": 0.2056686183422757, "rougeL_precision_stderr": 0.0015071237696962308, "rougeL_recall": 0.37982651296992087, "rougeL_recall_stderr": 0.0023920704305803887, "rougeLsum_fmeasure": 0.2605843619987691, "rougeLsum_fmeasure_stderr": 0.0019094298729220246, "rougeLsum_precision": 0.2117404050410904, "rougeLsum_precision_stderr": 0.0019554275881996357, "rougeLsum_recall": 0.379262023761823, "rougeLsum_recall_stderr": 0.0026640542361163967}}, "2": {"generate_text_restaurant": {"bleu": 8.283032143741265, "bleu_stderr": 0.12324083863995262, "rouge1_fmeasure": 0.386855872645816, "rouge1_fmeasure_stderr": 0.0021481774383948936, "rouge1_precision": 0.3538185229938564, "rouge1_precision_stderr": 0.0026093673205933284, "rouge1_recall": 0.47654923761453416, "rouge1_recall_stderr": 0.002742670643307486, "rouge2_fmeasure": 0.17540917102638537, "rouge2_fmeasure_stderr": 0.001676199795834029, "rouge2_precision": 0.16058763409752866, "rouge2_precision_stderr": 0.0017929892307175898, "rouge2_recall": 0.2186758841759895, "rouge2_recall_stderr": 0.0021644223522511653, "rougeL_fmeasure": 0.29032162387497273, "rougeL_fmeasure_stderr": 0.0016448424366105137, "rougeL_precision": 0.2634180709043917, "rougeL_precision_stderr": 0.0019363360461210728, "rougeL_recall": 0.3633286847976612, "rougeL_recall_stderr": 0.002418760103075258, "rougeLsum_fmeasure": 0.3215658810211159, "rougeLsum_fmeasure_stderr": 0.0020865232232060243, "rougeLsum_precision": 0.2943420649549215, "rougeLsum_precision_stderr": 0.0024049285177976626, "rougeLsum_recall": 0.396021431067016, "rougeLsum_recall_stderr": 0.0026539511959613863}}, "3": {"generate_text_restaurant": {"bleu": 10.390741038004455, "bleu_stderr": 0.16864807456665598, "rouge1_fmeasure": 0.4265219434574998, "rouge1_fmeasure_stderr": 0.00200022371619217, "rouge1_precision": 0.4170328570049967, "rouge1_precision_stderr": 0.002406804998864227, "rouge1_recall": 0.4755330496164165, "rouge1_recall_stderr": 0.0027356944570645627, "rouge2_fmeasure": 0.19794956049387477, "rouge2_fmeasure_stderr": 0.0017257612820525093, "rouge2_precision": 0.19311277752964032, "rouge2_precision_stderr": 0.0018435166685741753, "rouge2_recall": 0.2234558315509727, "rouge2_recall_stderr": 0.00217671447753381, "rougeL_fmeasure": 0.30937209897451035, "rougeL_fmeasure_stderr": 0.0017399874604572011, "rougeL_precision": 0.3018404766668879, "rougeL_precision_stderr": 0.0019954675660840008, "rougeL_recall": 0.34733784496925735, "rougeL_recall_stderr": 0.002410859115489849, "rougeLsum_fmeasure": 0.35577353404582346, "rougeLsum_fmeasure_stderr": 0.002018349673780584, "rougeLsum_precision": 0.34804273669533864, "rougeLsum_precision_stderr": 0.002320309559338597, "rougeLsum_recall": 0.39674483976023345, "rougeLsum_recall_stderr": 0.002636069670789193}}, "4": {"generate_text_restaurant": {"bleu": 11.329341641449828, "bleu_stderr": 0.17960715134758612, "rouge1_fmeasure": 0.4404396724578438, "rouge1_fmeasure_stderr": 0.0019501997658908016, "rouge1_precision": 0.43540537755676456, "rouge1_precision_stderr": 0.0023276114946809037, "rouge1_recall": 0.4809839727831288, "rouge1_recall_stderr": 0.0026909272047918853, "rouge2_fmeasure": 0.20632107444632167, "rouge2_fmeasure_stderr": 0.0017999776378623833, "rouge2_precision": 0.20335070986022913, "rouge2_precision_stderr": 0.0018630249723704795, "rouge2_recall": 0.2277953855378017, "rouge2_recall_stderr": 0.002231447665036813, "rougeL_fmeasure": 0.3146665867607543, "rougeL_fmeasure_stderr": 0.001793539263470212, "rougeL_precision": 0.31052804922692206, "rougeL_precision_stderr": 0.0019906703253583058, "rougeL_recall": 0.34538706806048836, "rougeL_recall_stderr": 0.0024265779869813795, "rougeLsum_fmeasure": 0.3681598682721843, "rougeLsum_fmeasure_stderr": 0.0020492701030304073, "rougeLsum_precision": 0.36360422785078816, "rougeLsum_precision_stderr": 0.002278768446357271, "rougeLsum_recall": 0.40267975309659465, "rougeLsum_recall_stderr": 0.002691014459855529}}, "5": {"generate_text_restaurant": {"bleu": 11.285255750718802, "bleu_stderr": 0.18888005349774178, "rouge1_fmeasure": 0.4415151553259178, "rouge1_fmeasure_stderr": 0.0018967405556148942, "rouge1_precision": 0.4365680288096621, "rouge1_precision_stderr": 0.0023563761935207865, "rouge1_recall": 0.48375423799463574, "rouge1_recall_stderr": 0.002636920734911192, "rouge2_fmeasure": 0.20666903463506434, "rouge2_fmeasure_stderr": 0.0017287346978560685, "rouge2_precision": 0.2041613364300487, "rouge2_precision_stderr": 0.0018478653045982886, "rouge2_recall": 0.2286562929012743, "rouge2_recall_stderr": 0.0021444262626903934, "rougeL_fmeasure": 0.31404489497308175, "rougeL_fmeasure_stderr": 0.0017489740232863793, "rougeL_precision": 0.3097317177052037, "rougeL_precision_stderr": 0.0019875430217516188, "rougeL_recall": 0.3463247383671021, "rougeL_recall_stderr": 0.0024086631359451073, "rougeLsum_fmeasure": 0.3693839714597318, "rougeLsum_fmeasure_stderr": 0.001956221447002133, "rougeLsum_precision": 0.36511129451802127, "rougeLsum_precision_stderr": 0.002275854131726726, "rougeLsum_recall": 0.40524349161687195, "rougeLsum_recall_stderr": 0.002592210635732001}}}, "gem_xsum": {"0": {"article_DOC_summary": {"bleu": 1.9920111933130942, "bleu_stderr": 0.09083971543338792, "rouge1_fmeasure": 0.21238019045835924, "rouge1_fmeasure_stderr": 0.0026416842263647295, "rouge1_precision": 0.16661991011320432, "rouge1_precision_stderr": 0.0024239320503688508, "rouge1_recall": 0.3334279529769119, "rouge1_recall_stderr": 0.004505784466073162, "rouge2_fmeasure": 0.0474651150579007, "rouge2_fmeasure_stderr": 0.0016508808672473486, "rouge2_precision": 0.036458947908946444, "rouge2_precision_stderr": 0.0013971876206545527, "rouge2_recall": 0.07797973705513334, "rouge2_recall_stderr": 0.0027575216878305796, "rougeL_fmeasure": 0.1574172507962458, "rougeL_fmeasure_stderr": 0.0019726023490667156, "rougeL_precision": 0.12350643841301835, "rougeL_precision_stderr": 0.0018449748802517576, "rougeL_recall": 0.24834266376447475, "rougeL_recall_stderr": 0.0034694940835095387, "rougeLsum_fmeasure": 0.16564203891769072, "rougeLsum_fmeasure_stderr": 0.0021922015182424493, "rougeLsum_precision": 0.12930576998616114, "rougeLsum_precision_stderr": 0.001943629127681205, "rougeLsum_recall": 0.2628771358874318, "rougeLsum_recall_stderr": 0.003928661472441744}}, "1": {"article_DOC_summary": {"bleu": 1.3911048134042985, "bleu_stderr": 0.10897719788542379, "rouge1_fmeasure": 0.17238543114114188, "rouge1_fmeasure_stderr": 0.0024273582171495467, "rouge1_precision": 0.12220764132281824, "rouge1_precision_stderr": 0.0017962553489656822, "rouge1_recall": 0.3046016264780442, "rouge1_recall_stderr": 0.004195472170007382, "rouge2_fmeasure": 0.03433659588366439, "rouge2_fmeasure_stderr": 0.0013916698462749025, "rouge2_precision": 0.02404240814314951, "rouge2_precision_stderr": 0.0009715966898615973, "rouge2_recall": 0.06279570551371068, "rouge2_recall_stderr": 0.0026393784630938297, "rougeL_fmeasure": 0.13411490255282393, "rougeL_fmeasure_stderr": 0.001857806891825946, "rougeL_precision": 0.0948627092015581, "rougeL_precision_stderr": 0.0013564109394382858, "rougeL_recall": 0.23873232992980792, "rougeL_recall_stderr": 0.0033732063257411065, "rougeLsum_fmeasure": 0.1377971067717085, "rougeLsum_fmeasure_stderr": 0.0019961553438677753, "rougeLsum_precision": 0.09744320598123982, "rougeLsum_precision_stderr": 0.0014533168661689533, "rougeLsum_recall": 0.24526431304855986, "rougeLsum_recall_stderr": 0.0036135020193240157}}, "2": {"article_DOC_summary": {"bleu": 1.5131027243134945, "bleu_stderr": 0.09818604218520245, "rouge1_fmeasure": 0.1796260802555828, "rouge1_fmeasure_stderr": 0.0024295120173709354, "rouge1_precision": 0.12742301658282565, "rouge1_precision_stderr": 0.0018019437038001125, "rouge1_recall": 0.31650559447584714, "rouge1_recall_stderr": 0.0041632693268193, "rouge2_fmeasure": 0.03828129617404584, "rouge2_fmeasure_stderr": 0.0014588717099132717, "rouge2_precision": 0.026873267786760833, "rouge2_precision_stderr": 0.0010274689542246274, "rouge2_recall": 0.06937748072287012, "rouge2_recall_stderr": 0.002720274634345644, "rougeL_fmeasure": 0.14088593992593365, "rougeL_fmeasure_stderr": 0.0018545171064126879, "rougeL_precision": 0.09972086437810422, "rougeL_precision_stderr": 0.0013615528035081867, "rougeL_recall": 0.25006918430896163, "rougeL_recall_stderr": 0.0033224978911440477, "rougeLsum_fmeasure": 0.14453096950758154, "rougeLsum_fmeasure_stderr": 0.0020492721061134787, "rougeLsum_precision": 0.10228150708865971, "rougeLsum_precision_stderr": 0.001498292749384224, "rougeLsum_recall": 0.2564975734365291, "rougeLsum_recall_stderr": 0.003645659171226953}}, "3": {"article_DOC_summary": {"bleu": 1.5589813395856684, "bleu_stderr": 0.10558852439347298, "rouge1_fmeasure": 0.17393387340194993, "rouge1_fmeasure_stderr": 0.0026232973050223565, "rouge1_precision": 0.12560830490871291, "rouge1_precision_stderr": 0.0019805809749753123, "rouge1_recall": 0.30202505876515096, "rouge1_recall_stderr": 0.004562458827775563, "rouge2_fmeasure": 0.03719404523373464, "rouge2_fmeasure_stderr": 0.0014264985251086694, "rouge2_precision": 0.02632965637304347, "rouge2_precision_stderr": 0.0010168079119372074, "rouge2_recall": 0.06654262996214515, "rouge2_recall_stderr": 0.002628246685221607, "rougeL_fmeasure": 0.1367280753200056, "rougeL_fmeasure_stderr": 0.0020569662559889986, "rougeL_precision": 0.09872111817099473, "rougeL_precision_stderr": 0.0015538240912434773, "rougeL_recall": 0.23817398946563523, "rougeL_recall_stderr": 0.0036574265400714056, "rougeLsum_fmeasure": 0.13995698919988145, "rougeLsum_fmeasure_stderr": 0.0021562163365348155, "rougeLsum_precision": 0.10088738488275732, "rougeLsum_precision_stderr": 0.0016123154477431468, "rougeLsum_recall": 0.24479219612186495, "rougeLsum_recall_stderr": 0.0038858502767361853}}, "4": {"article_DOC_summary": {"bleu": 0.7800465095373856, "bleu_stderr": 0.110140635740535, "rouge1_fmeasure": 0.04714278099581509, "rouge1_fmeasure_stderr": 0.002671918175318051, "rouge1_precision": 0.039875289966317076, "rouge1_precision_stderr": 0.0024501045936788945, "rouge1_recall": 0.07430021940128062, "rouge1_recall_stderr": 0.004312735443842743, "rouge2_fmeasure": 0.009927038748098277, "rouge2_fmeasure_stderr": 0.0009411928436840111, "rouge2_precision": 0.00812289150475277, "rouge2_precision_stderr": 0.0009151347143203979, "rouge2_recall": 0.016372857345750558, "rouge2_recall_stderr": 0.0015796426861189893, "rougeL_fmeasure": 0.03725830963733278, "rougeL_fmeasure_stderr": 0.0020970987843492487, "rougeL_precision": 0.031900774626537044, "rougeL_precision_stderr": 0.0020006091032227793, "rougeL_recall": 0.058775527889088235, "rougeL_recall_stderr": 0.0033989669828951557, "rougeLsum_fmeasure": 0.03901707398161308, "rougeLsum_fmeasure_stderr": 0.0022151386053289395, "rougeLsum_precision": 0.03342763825361942, "rougeLsum_precision_stderr": 0.002105461480850086, "rougeLsum_recall": 0.06157534488712963, "rougeLsum_recall_stderr": 0.003610155719272957}}, "5": {"article_DOC_summary": {"bleu": 6.009065394749386e-37, "bleu_stderr": 1.386737757665829e-31, "rouge1_fmeasure": 0.0030037230280197226, "rouge1_fmeasure_stderr": 0.0008566665942648847, "rouge1_precision": 0.0033882933420727682, "rouge1_precision_stderr": 0.000994288954345408, "rouge1_recall": 0.002780937524962328, "rouge1_recall_stderr": 0.0007843603020955971, "rouge2_fmeasure": 0.000983708450751863, "rouge2_fmeasure_stderr": 0.0004420715282406731, "rouge2_precision": 0.001120152102248019, "rouge2_precision_stderr": 0.0004966314099881747, "rouge2_recall": 0.0009065462839047746, "rouge2_recall_stderr": 0.0004161603469287444, "rougeL_fmeasure": 0.002337297608841716, "rougeL_fmeasure_stderr": 0.0007032854409325233, "rougeL_precision": 0.0026091624396139845, "rougeL_precision_stderr": 0.0007993813642794688, "rougeL_recall": 0.002187358356350872, "rougeL_recall_stderr": 0.0006548878815934947, "rougeLsum_fmeasure": 0.002540252346941857, "rougeLsum_fmeasure_stderr": 0.0007562653583340974, "rougeLsum_precision": 0.0028561523161821077, "rougeLsum_precision_stderr": 0.000870682583927747, "rougeLsum_recall": 0.002361092427287286, "rougeLsum_recall_stderr": 0.0006961516518425747}}}}