| {"GEM/web_nlg_en": {"0": {"PALM_prompt": {"bleu": 0.3056985698060885, "bleu_stderr": 0.02037727591015296, "rouge1_fmeasure": 0.1041010135673265, "rouge1_fmeasure_stderr": 0.0020426766002203623, "rouge1_precision": 0.07003252145378697, "rouge1_precision_stderr": 0.0017782398203109468, "rouge1_recall": 0.29203668815673745, "rouge1_recall_stderr": 0.00463136764747632, "rouge2_fmeasure": 0.04860923158958796, "rouge2_fmeasure_stderr": 0.0012225487600062404, "rouge2_precision": 0.0332378018219376, "rouge2_precision_stderr": 0.0011349058010884613, "rouge2_recall": 0.13749957036557914, "rouge2_recall_stderr": 0.003196748550458682, "rougeL_fmeasure": 0.10041814595908975, "rougeL_fmeasure_stderr": 0.0019026376308031996, "rougeL_precision": 0.06718224746092341, "rougeL_precision_stderr": 0.0016048036895014346, "rougeL_recall": 0.284110989145015, "rougeL_recall_stderr": 0.004532716214582295, "rougeLsum_fmeasure": 0.0995435574009657, "rougeLsum_fmeasure_stderr": 0.0019249335289248614, "rougeLsum_precision": 0.06682529423751103, "rougeLsum_precision_stderr": 0.0016323321821141092, "rougeLsum_recall": 0.279078746288203, "rougeLsum_recall_stderr": 0.004459389412998906}}, "1": {"PALM_prompt": {"bleu": 0.47118961796111253, "bleu_stderr": 0.03698103082931082, "rouge1_fmeasure": 0.1177743328825882, "rouge1_fmeasure_stderr": 0.001968188676645897, "rouge1_precision": 0.0771933656618608, "rouge1_precision_stderr": 0.0015982731846139909, "rouge1_recall": 0.3718112290369406, "rouge1_recall_stderr": 0.005070882434958457, "rouge2_fmeasure": 0.05451596763365407, "rouge2_fmeasure_stderr": 0.001220440063099909, "rouge2_precision": 0.036081371178737776, "rouge2_precision_stderr": 0.001015398673414324, "rouge2_recall": 0.1783833017712426, "rouge2_recall_stderr": 0.003533942569843169, "rougeL_fmeasure": 0.11130332023816736, "rougeL_fmeasure_stderr": 0.0018115727050860737, "rougeL_precision": 0.07295630439059424, "rougeL_precision_stderr": 0.0014912307741854292, "rougeL_recall": 0.34998602256792577, "rougeL_recall_stderr": 0.004635684392541653, "rougeLsum_fmeasure": 0.1123812114309373, "rougeLsum_fmeasure_stderr": 0.001868171085940279, "rougeLsum_precision": 0.07379279366484903, "rougeLsum_precision_stderr": 0.0015372531917501194, "rougeLsum_recall": 0.352791769527236, "rougeLsum_recall_stderr": 0.004687142295790851}}, "2": {"PALM_prompt": {"bleu": 0.533916369829073, "bleu_stderr": 0.03236121557558326, "rouge1_fmeasure": 0.11840000027377959, "rouge1_fmeasure_stderr": 0.0018926983365336872, "rouge1_precision": 0.07681910931236588, "rouge1_precision_stderr": 0.0015377577308842757, "rouge1_recall": 0.38510316670877215, "rouge1_recall_stderr": 0.00510951140732995, "rouge2_fmeasure": 0.05478096245624173, "rouge2_fmeasure_stderr": 0.0011716039831968148, "rouge2_precision": 0.035783217444623636, "rouge2_precision_stderr": 0.000976654693795426, "rouge2_recall": 0.18984984078562042, "rouge2_recall_stderr": 0.0038247509890711063, "rougeL_fmeasure": 0.1109268884100491, "rougeL_fmeasure_stderr": 0.0017396910638209685, "rougeL_precision": 0.0720673505406942, "rougeL_precision_stderr": 0.0014392854438264812, "rougeL_recall": 0.3590172306490562, "rougeL_recall_stderr": 0.004627049792255802, "rougeLsum_fmeasure": 0.11265574136485931, "rougeLsum_fmeasure_stderr": 0.0018002243925544347, "rougeLsum_precision": 0.07321894524691384, "rougeLsum_precision_stderr": 0.0014825495999582067, "rougeLsum_recall": 0.36495395152990295, "rougeLsum_recall_stderr": 0.0047347356869845165}}, "3": {"PALM_prompt": {"bleu": 0.5595499974128665, "bleu_stderr": 0.037451927861185196, "rouge1_fmeasure": 0.1195630864031263, "rouge1_fmeasure_stderr": 0.00192698764288485, "rouge1_precision": 0.0779317898938085, "rouge1_precision_stderr": 0.0016112650938220434, "rouge1_recall": 0.38762436841783615, "rouge1_recall_stderr": 0.0050758147406836035, "rouge2_fmeasure": 0.05609871570970779, "rouge2_fmeasure_stderr": 0.0012335930575023653, "rouge2_precision": 0.03687332306481112, "rouge2_precision_stderr": 0.0010617608016665735, "rouge2_recall": 0.19234698280186005, "rouge2_recall_stderr": 0.003750582513370695, "rougeL_fmeasure": 0.1120155525419754, "rougeL_fmeasure_stderr": 0.001772429101944478, "rougeL_precision": 0.073041109974632, "rougeL_precision_stderr": 0.0014857335049320345, "rougeL_recall": 0.36061760063023685, "rougeL_recall_stderr": 0.004568863945261958, "rougeLsum_fmeasure": 0.11375064173975076, "rougeLsum_fmeasure_stderr": 0.0018326619772365102, "rougeLsum_precision": 0.07415983300145405, "rougeLsum_precision_stderr": 0.001517950201385796, "rougeLsum_recall": 0.3676109059529136, "rougeLsum_recall_stderr": 0.004730150437103061}}, "4": {"PALM_prompt": {"bleu": 0.600990283111048, "bleu_stderr": 0.034277269466224586, "rouge1_fmeasure": 0.12037133162822398, "rouge1_fmeasure_stderr": 0.00182661073083092, "rouge1_precision": 0.07788179321838232, "rouge1_precision_stderr": 0.0015013142830281594, "rouge1_recall": 0.39994843389146706, "rouge1_recall_stderr": 0.00499808834668635, "rouge2_fmeasure": 0.05640172523608126, "rouge2_fmeasure_stderr": 0.001156416498416956, "rouge2_precision": 0.036729400826605405, "rouge2_precision_stderr": 0.0009707795653244158, "rouge2_recall": 0.20068990178179008, "rouge2_recall_stderr": 0.0038369503757506584, "rougeL_fmeasure": 0.11217146023041902, "rougeL_fmeasure_stderr": 0.001709041887848104, "rougeL_precision": 0.0727796364763943, "rougeL_precision_stderr": 0.0014273675233445258, "rougeL_recall": 0.3686191869505379, "rougeL_recall_stderr": 0.004446290243901058, "rougeLsum_fmeasure": 0.11462098219560242, "rougeLsum_fmeasure_stderr": 0.0017512279921868023, "rougeLsum_precision": 0.07432987376050701, "rougeLsum_precision_stderr": 0.0014578128593730135, "rougeLsum_recall": 0.3785969497473814, "rougeLsum_recall_stderr": 0.004640411180240199}}, "5": {"PALM_prompt": {"bleu": 0.6493610426477754, "bleu_stderr": 0.04632676737275454, "rouge1_fmeasure": 0.12068693871021649, "rouge1_fmeasure_stderr": 0.0017912623734371875, "rouge1_precision": 0.07748205634617567, "rouge1_precision_stderr": 0.001453985027637336, "rouge1_recall": 0.41054791184729794, "rouge1_recall_stderr": 0.004995597119369392, "rouge2_fmeasure": 0.05650487878947583, "rouge2_fmeasure_stderr": 0.0011343334162232442, "rouge2_precision": 0.03639203356358758, "rouge2_precision_stderr": 0.0009275341362302266, "rouge2_recall": 0.20615921276358995, "rouge2_recall_stderr": 0.0037483811580489817, "rougeL_fmeasure": 0.11124019861288943, "rougeL_fmeasure_stderr": 0.0016486705656890794, "rougeL_precision": 0.0716220983354236, "rougeL_precision_stderr": 0.0013593103462355548, "rougeL_recall": 0.3738691644956053, "rougeL_recall_stderr": 0.004316527656281062, "rougeLsum_fmeasure": 0.11456244519233316, "rougeLsum_fmeasure_stderr": 0.0017091885356239022, "rougeLsum_precision": 0.07368867272301145, "rougeLsum_precision_stderr": 0.0014007140781525382, "rougeLsum_recall": 0.38732626297948775, "rougeLsum_recall_stderr": 0.004596911969728994}}}, "GEM/wiki_lingua_en": {"0": {"tldr_en": {"bleu": 1.3330159057137432, "bleu_stderr": 0.0488742999692044, "rouge1_fmeasure": 0.165509440090111, "rouge1_fmeasure_stderr": 0.001885757880608957, "rouge1_precision": 0.141331703238122, "rouge1_precision_stderr": 0.001900860421203431, "rouge1_recall": 0.24159721817911073, "rouge1_recall_stderr": 0.002719597450403811, "rouge2_fmeasure": 0.031517777959615835, "rouge2_fmeasure_stderr": 0.0008078153472147894, "rouge2_precision": 0.02669836310001385, "rouge2_precision_stderr": 0.0007156929489602658, "rouge2_recall": 0.04779652460533507, "rouge2_recall_stderr": 0.0013664090841134524, "rougeL_fmeasure": 0.1304904422471148, "rougeL_fmeasure_stderr": 0.0013630786843314023, "rougeL_precision": 0.10997003023895942, "rougeL_precision_stderr": 0.0013406611259386123, "rougeL_recall": 0.19583040922151732, "rougeL_recall_stderr": 0.002241329057684982, "rougeLsum_fmeasure": 0.1520296742001466, "rougeLsum_fmeasure_stderr": 0.0017239456047265416, "rougeLsum_precision": 0.1296243531663802, "rougeLsum_precision_stderr": 0.0017327493840537764, "rougeLsum_recall": 0.2226802105122421, "rougeLsum_recall_stderr": 0.002519165452551483}}, "1": {"tldr_en": {"bleu": 2.6461954540180517, "bleu_stderr": 0.0686607101579094, "rouge1_fmeasure": 0.21776898864919678, "rouge1_fmeasure_stderr": 0.0019444140343936993, "rouge1_precision": 0.19155876571103367, "rouge1_precision_stderr": 0.002235574181803164, "rouge1_recall": 0.31538809129393497, "rouge1_recall_stderr": 0.0027758196777476055, "rouge2_fmeasure": 0.05327544506657774, "rouge2_fmeasure_stderr": 0.0009940356897765103, "rouge2_precision": 0.04732904074441193, "rouge2_precision_stderr": 0.0010360766648087926, "rouge2_recall": 0.07972267565974463, "rouge2_recall_stderr": 0.0016475159287438514, "rougeL_fmeasure": 0.1540568103772324, "rougeL_fmeasure_stderr": 0.0012940294587542422, "rougeL_precision": 0.13475235285926426, "rougeL_precision_stderr": 0.0015468525973368185, "rougeL_recall": 0.22894884785015995, "rougeL_recall_stderr": 0.002173977332942091, "rougeLsum_fmeasure": 0.20425015913438996, "rougeLsum_fmeasure_stderr": 0.0018113854464497062, "rougeLsum_precision": 0.17953406416101728, "rougeLsum_precision_stderr": 0.0020944383459417203, "rougeLsum_recall": 0.29675466574734266, "rougeLsum_recall_stderr": 0.002631907411205019}}, "2": {"tldr_en": {"bleu": 2.901173035530729, "bleu_stderr": 0.05342955865413849, "rouge1_fmeasure": 0.22064842886466463, "rouge1_fmeasure_stderr": 0.001912119893056796, "rouge1_precision": 0.2159533628570682, "rouge1_precision_stderr": 0.002791865511024776, "rouge1_recall": 0.30331115752873467, "rouge1_recall_stderr": 0.002766040617891812, "rouge2_fmeasure": 0.057864776743445145, "rouge2_fmeasure_stderr": 0.0010769988684922042, "rouge2_precision": 0.05993156312422532, "rouge2_precision_stderr": 0.0016401679053386375, "rouge2_recall": 0.08140349201064899, "rouge2_recall_stderr": 0.0016894533790392091, "rougeL_fmeasure": 0.16022824117745368, "rougeL_fmeasure_stderr": 0.001353671145413634, "rougeL_precision": 0.1583382277260483, "rougeL_precision_stderr": 0.0022683450533058772, "rougeL_recall": 0.22488747911377632, "rougeL_recall_stderr": 0.002243037827514705, "rougeLsum_fmeasure": 0.20741540180362425, "rougeLsum_fmeasure_stderr": 0.001786464041080481, "rougeLsum_precision": 0.20328152598542265, "rougeLsum_precision_stderr": 0.002668656156379896, "rougeLsum_recall": 0.2859559600281066, "rougeLsum_recall_stderr": 0.002647687376069602}}, "3": {"tldr_en": {"bleu": 2.8536144517225503, "bleu_stderr": 0.11123670367846313, "rouge1_fmeasure": 0.1795577823082448, "rouge1_fmeasure_stderr": 0.0022472758798550777, "rouge1_precision": 0.18489561929921422, "rouge1_precision_stderr": 0.003137550370770306, "rouge1_recall": 0.24573209214855274, "rouge1_recall_stderr": 0.003309411692082243, "rouge2_fmeasure": 0.04723677657570569, "rouge2_fmeasure_stderr": 0.0010843010239386048, "rouge2_precision": 0.05085763209734922, "rouge2_precision_stderr": 0.0016343790426841317, "rouge2_recall": 0.06635653571954948, "rouge2_recall_stderr": 0.0016849742371905798, "rougeL_fmeasure": 0.13192124238531389, "rougeL_fmeasure_stderr": 0.001640698669618877, "rougeL_precision": 0.13823892948584393, "rougeL_precision_stderr": 0.002555329177823708, "rougeL_recall": 0.18353805339680163, "rougeL_recall_stderr": 0.002620675134490683, "rougeLsum_fmeasure": 0.16886339863190594, "rougeLsum_fmeasure_stderr": 0.0021148662932854957, "rougeLsum_precision": 0.17421610987286962, "rougeLsum_precision_stderr": 0.0029928898493940675, "rougeLsum_recall": 0.23156674787506518, "rougeLsum_recall_stderr": 0.003147427389660552}}, "4": {"tldr_en": {"bleu": 0.5390525330469651, "bleu_stderr": 0.0408109714920231, "rouge1_fmeasure": 0.05703592133005884, "rouge1_fmeasure_stderr": 0.001942831946209364, "rouge1_precision": 0.05870358383616785, "rouge1_precision_stderr": 0.0023430529684724016, "rouge1_recall": 0.08093434137408964, "rouge1_recall_stderr": 0.0028367817835456407, "rouge2_fmeasure": 0.014808001674755853, "rouge2_fmeasure_stderr": 0.0007238729065264632, "rouge2_precision": 0.016328545160307874, "rouge2_precision_stderr": 0.0011000353784742687, "rouge2_recall": 0.02180350520016562, "rouge2_recall_stderr": 0.0011411604156949377, "rougeL_fmeasure": 0.04260019909764127, "rougeL_fmeasure_stderr": 0.0014424624483373777, "rougeL_precision": 0.044888286166910714, "rougeL_precision_stderr": 0.001896455231106093, "rougeL_recall": 0.061444546156244624, "rougeL_recall_stderr": 0.0022065275178083242, "rougeLsum_fmeasure": 0.05352907711826245, "rougeLsum_fmeasure_stderr": 0.0018257144932056115, "rougeLsum_precision": 0.05510529257082465, "rougeLsum_precision_stderr": 0.0022153343918295677, "rougeLsum_recall": 0.07627563508448673, "rougeLsum_recall_stderr": 0.0026884645736360985}}, "5": {"tldr_en": {"bleu": 1.1864794949178182e-06, "bleu_stderr": 2.2172651577024026e-06, "rouge1_fmeasure": 0.008834057407774154, "rouge1_fmeasure_stderr": 0.0008234294750612254, "rouge1_precision": 0.008584563764438044, "rouge1_precision_stderr": 0.0008753066342352569, "rouge1_recall": 0.01304332354397915, "rouge1_recall_stderr": 0.0012616701774741266, "rouge2_fmeasure": 0.0021982092172172316, "rouge2_fmeasure_stderr": 0.0002702560692849953, "rouge2_precision": 0.0020643566994266315, "rouge2_precision_stderr": 0.0002999865807491949, "rouge2_recall": 0.003514834079841484, "rouge2_recall_stderr": 0.00046085843512874496, "rougeL_fmeasure": 0.006719281513421419, "rougeL_fmeasure_stderr": 0.0006225359173726148, "rougeL_precision": 0.0065299312398118745, "rougeL_precision_stderr": 0.0006600353263555559, "rougeL_recall": 0.010172425010043205, "rougeL_recall_stderr": 0.0010133996136714378, "rougeLsum_fmeasure": 0.008173501201069725, "rougeLsum_fmeasure_stderr": 0.0007588029707814247, "rougeLsum_precision": 0.007865790760235851, "rougeLsum_precision_stderr": 0.0007878955854092591, "rougeLsum_recall": 0.012211564420719438, "rougeLsum_recall_stderr": 0.0011927076918159406}}}, "e2e_nlg_cleaned": {"0": {"generate_text_restaurant": {"bleu": 4.765682760423997, "bleu_stderr": 0.05422767541309084, "rouge1_fmeasure": 0.24332659914676713, "rouge1_fmeasure_stderr": 0.0019769029717195945, "rouge1_precision": 0.17988772034955686, "rouge1_precision_stderr": 0.0016071110305014198, "rouge1_recall": 0.39581785916900913, "rouge1_recall_stderr": 0.0029310989695743622, "rouge2_fmeasure": 0.09956430250623664, "rouge2_fmeasure_stderr": 0.0012064988114572355, "rouge2_precision": 0.07299811599029202, "rouge2_precision_stderr": 0.0009192181950106493, "rouge2_recall": 0.1655787870611749, "rouge2_recall_stderr": 0.0019941826207487525, "rougeL_fmeasure": 0.2048927917623883, "rougeL_fmeasure_stderr": 0.0015629945995320966, "rougeL_precision": 0.1508460812164152, "rougeL_precision_stderr": 0.0012497621473603125, "rougeL_recall": 0.33638856499484304, "rougeL_recall_stderr": 0.002462317442145038, "rougeLsum_fmeasure": 0.21696200359533935, "rougeLsum_fmeasure_stderr": 0.0018532122825693418, "rougeLsum_precision": 0.16020564267536394, "rougeLsum_precision_stderr": 0.0014848327378428146, "rougeLsum_recall": 0.35379035235820266, "rougeLsum_recall_stderr": 0.0028050151273689558}}, "1": {"generate_text_restaurant": {"bleu": 10.468883179786745, "bleu_stderr": 0.14513499791603968, "rouge1_fmeasure": 0.41142927258080764, "rouge1_fmeasure_stderr": 0.0020372645566246617, "rouge1_precision": 0.4461560307039274, "rouge1_precision_stderr": 0.0027882222137359425, "rouge1_recall": 0.4223727993701862, "rouge1_recall_stderr": 0.002779466413933148, "rouge2_fmeasure": 0.17546734923272342, "rouge2_fmeasure_stderr": 0.0017675801853763418, "rouge2_precision": 0.19138036565463667, "rouge2_precision_stderr": 0.0021373415792973888, "rouge2_recall": 0.18105398962411778, "rouge2_recall_stderr": 0.0020434906060036568, "rougeL_fmeasure": 0.29720682946492366, "rougeL_fmeasure_stderr": 0.0018058222015338043, "rougeL_precision": 0.3234887060013004, "rougeL_precision_stderr": 0.002422772594833981, "rougeL_recall": 0.3050111498702241, "rougeL_recall_stderr": 0.0023058891158011475, "rougeLsum_fmeasure": 0.3408169753521894, "rougeLsum_fmeasure_stderr": 0.0020222041567187483, "rougeLsum_precision": 0.36955424114426116, "rougeLsum_precision_stderr": 0.002627564057426632, "rougeLsum_recall": 0.35002355749667186, "rougeLsum_recall_stderr": 0.0025913666710418912}}, "2": {"generate_text_restaurant": {"bleu": 13.15937757187936, "bleu_stderr": 0.17402618441844517, "rouge1_fmeasure": 0.44974386997659066, "rouge1_fmeasure_stderr": 0.0021587456909989825, "rouge1_precision": 0.5116677117570123, "rouge1_precision_stderr": 0.003328551040183069, "rouge1_recall": 0.4467016147483925, "rouge1_recall_stderr": 0.0028150384160634126, "rouge2_fmeasure": 0.21686040386653943, "rouge2_fmeasure_stderr": 0.0019364096185227812, "rouge2_precision": 0.25116353200124875, "rouge2_precision_stderr": 0.002675343325002614, "rouge2_recall": 0.21531631345677743, "rouge2_recall_stderr": 0.0021418289381007287, "rougeL_fmeasure": 0.3389361888586281, "rougeL_fmeasure_stderr": 0.001994011964068714, "rougeL_precision": 0.3875589106822081, "rougeL_precision_stderr": 0.0029960409984381296, "rougeL_recall": 0.3362068824396353, "rougeL_recall_stderr": 0.0024065124976756567, "rougeLsum_fmeasure": 0.38104681490559605, "rougeLsum_fmeasure_stderr": 0.0021875307111738898, "rougeLsum_precision": 0.43414987277433165, "rougeLsum_precision_stderr": 0.0032063239226803007, "rougeLsum_recall": 0.37817721348532046, "rougeLsum_recall_stderr": 0.0026544745921995615}}, "3": {"generate_text_restaurant": {"bleu": 12.129694716562593, "bleu_stderr": 0.09885740494020588, "rouge1_fmeasure": 0.4414312727012384, "rouge1_fmeasure_stderr": 0.0019519907059499023, "rouge1_precision": 0.4445157890248481, "rouge1_precision_stderr": 0.002595665567685936, "rouge1_recall": 0.47798126521143697, "rouge1_recall_stderr": 0.0027344918481641326, "rouge2_fmeasure": 0.2107633646828048, "rouge2_fmeasure_stderr": 0.0018036725966383619, "rouge2_precision": 0.2128182501314406, "rouge2_precision_stderr": 0.002080514621594728, "rouge2_recall": 0.23033986601501272, "rouge2_recall_stderr": 0.002220133805877886, "rougeL_fmeasure": 0.32903441642513187, "rougeL_fmeasure_stderr": 0.001780398769078088, "rougeL_precision": 0.33200437713670644, "rougeL_precision_stderr": 0.002293852098406482, "rougeL_recall": 0.35658301284722854, "rougeL_recall_stderr": 0.0023733016537168627, "rougeLsum_fmeasure": 0.3753007198038583, "rougeLsum_fmeasure_stderr": 0.0020106738190462125, "rougeLsum_precision": 0.37782185980378685, "rougeLsum_precision_stderr": 0.0025010018735451525, "rougeLsum_recall": 0.40662395947064806, "rougeLsum_recall_stderr": 0.002656543475373511}}, "4": {"generate_text_restaurant": {"bleu": 12.132825433584408, "bleu_stderr": 0.16624627774955542, "rouge1_fmeasure": 0.44537146771645886, "rouge1_fmeasure_stderr": 0.001904249537543325, "rouge1_precision": 0.43551787708171735, "rouge1_precision_stderr": 0.0022984268679554208, "rouge1_recall": 0.488774946659327, "rouge1_recall_stderr": 0.0026403071353862067, "rouge2_fmeasure": 0.2120679639683205, "rouge2_fmeasure_stderr": 0.0017947484063169713, "rouge2_precision": 0.20679648264384795, "rouge2_precision_stderr": 0.0018808563087133726, "rouge2_recall": 0.23542355545577054, "rouge2_recall_stderr": 0.0022374175074990257, "rougeL_fmeasure": 0.33096010620007504, "rougeL_fmeasure_stderr": 0.0017733714402514843, "rougeL_precision": 0.32327382970798735, "rougeL_precision_stderr": 0.001995377079294585, "rougeL_recall": 0.36425119832827263, "rougeL_recall_stderr": 0.0023824504483212824, "rougeLsum_fmeasure": 0.380150071138794, "rougeLsum_fmeasure_stderr": 0.0019990851143011548, "rougeLsum_precision": 0.37161856664153076, "rougeLsum_precision_stderr": 0.0022688211821483505, "rougeLsum_recall": 0.41744652285901757, "rougeLsum_recall_stderr": 0.0026213051295942776}}, "5": {"generate_text_restaurant": {"bleu": 12.150501863631494, "bleu_stderr": 0.11314994370401227, "rouge1_fmeasure": 0.44709276979411555, "rouge1_fmeasure_stderr": 0.001910905514583041, "rouge1_precision": 0.43384350876692923, "rouge1_precision_stderr": 0.0022430721979742672, "rouge1_recall": 0.4930603001034525, "rouge1_recall_stderr": 0.002670829206562973, "rouge2_fmeasure": 0.2132756026241378, "rouge2_fmeasure_stderr": 0.001789068514228881, "rouge2_precision": 0.20616106117256064, "rouge2_precision_stderr": 0.001830057336865641, "rouge2_recall": 0.23792096807821955, "rouge2_recall_stderr": 0.00223350281305114, "rougeL_fmeasure": 0.3325234854628361, "rougeL_fmeasure_stderr": 0.0017707439403097452, "rougeL_precision": 0.3221029481308322, "rougeL_precision_stderr": 0.0019290523867159137, "rougeL_recall": 0.36806957352620984, "rougeL_recall_stderr": 0.0024290518235640574, "rougeLsum_fmeasure": 0.38137613302372186, "rougeLsum_fmeasure_stderr": 0.0020158755209571493, "rougeLsum_precision": 0.36995123008018044, "rougeLsum_precision_stderr": 0.002227439242864291, "rougeLsum_recall": 0.42090674888926755, "rougeLsum_recall_stderr": 0.002665490051406233}}}, "gem_xsum": {"0": {"article_DOC_summary": {"bleu": 2.3861113355807007, "bleu_stderr": 0.11074519195435138, "rouge1_fmeasure": 0.22169655207824404, "rouge1_fmeasure_stderr": 0.002737165165866136, "rouge1_precision": 0.16949773638289, "rouge1_precision_stderr": 0.0025008930161999152, "rouge1_recall": 0.35927434904922223, "rouge1_recall_stderr": 0.004560400461326097, "rouge2_fmeasure": 0.056907827559785344, "rouge2_fmeasure_stderr": 0.0018251232736631654, "rouge2_precision": 0.0431701596864316, "rouge2_precision_stderr": 0.001534312955547038, "rouge2_recall": 0.09474053242204084, "rouge2_recall_stderr": 0.002989222654082048, "rougeL_fmeasure": 0.168504331059963, "rougeL_fmeasure_stderr": 0.0021699742342189397, "rougeL_precision": 0.1290524889805869, "rougeL_precision_stderr": 0.0020543657036148173, "rougeL_recall": 0.27361967658141045, "rougeL_recall_stderr": 0.0035963924946506493, "rougeLsum_fmeasure": 0.1751085620216996, "rougeLsum_fmeasure_stderr": 0.0024047356803931223, "rougeLsum_precision": 0.13370844006346885, "rougeLsum_precision_stderr": 0.0021670339989317035, "rougeLsum_recall": 0.285256434682157, "rougeLsum_recall_stderr": 0.00408399090358691}}, "1": {"article_DOC_summary": {"bleu": 2.1599927233517997, "bleu_stderr": 0.11630676231683935, "rouge1_fmeasure": 0.20562256846157667, "rouge1_fmeasure_stderr": 0.0025917247878476176, "rouge1_precision": 0.1463713881635103, "rouge1_precision_stderr": 0.001933537484388361, "rouge1_recall": 0.35985532344291576, "rouge1_recall_stderr": 0.0044711381442348866, "rouge2_fmeasure": 0.052109640269165904, "rouge2_fmeasure_stderr": 0.0016499123215979108, "rouge2_precision": 0.036703622860321694, "rouge2_precision_stderr": 0.001172772206888684, "rouge2_recall": 0.0939485415027206, "rouge2_recall_stderr": 0.003047610569508944, "rougeL_fmeasure": 0.15866900668787276, "rougeL_fmeasure_stderr": 0.0019458892417091485, "rougeL_precision": 0.1126929429063383, "rougeL_precision_stderr": 0.0014352356833621214, "rougeL_recall": 0.27967026507009923, "rougeL_recall_stderr": 0.0035535952255309837, "rougeLsum_fmeasure": 0.16374652691863595, "rougeLsum_fmeasure_stderr": 0.0021813353055902, "rougeLsum_precision": 0.1163220909216439, "rougeLsum_precision_stderr": 0.001603962253257027, "rougeLsum_recall": 0.2884084692973325, "rougeLsum_recall_stderr": 0.003919667134306644}}, "2": {"article_DOC_summary": {"bleu": 2.258614670093732, "bleu_stderr": 0.08951840120004514, "rouge1_fmeasure": 0.20934999828708714, "rouge1_fmeasure_stderr": 0.0026521179445819754, "rouge1_precision": 0.14912207031164892, "rouge1_precision_stderr": 0.001973097149015836, "rouge1_recall": 0.3654183781592464, "rouge1_recall_stderr": 0.004588246988437046, "rouge2_fmeasure": 0.0552385842587779, "rouge2_fmeasure_stderr": 0.0017598952748467285, "rouge2_precision": 0.038943395782983094, "rouge2_precision_stderr": 0.0012528357050940226, "rouge2_recall": 0.09918868504865098, "rouge2_recall_stderr": 0.003233414024371685, "rougeL_fmeasure": 0.162664466797653, "rougeL_fmeasure_stderr": 0.002068423484247533, "rougeL_precision": 0.1156734461385958, "rougeL_precision_stderr": 0.001526111534509325, "rougeL_recall": 0.28548150411787737, "rougeL_recall_stderr": 0.003702367860147114, "rougeLsum_fmeasure": 0.16589005254411232, "rougeLsum_fmeasure_stderr": 0.0022566042044053773, "rougeLsum_precision": 0.11782158647690419, "rougeLsum_precision_stderr": 0.001648802010987179, "rougeLsum_recall": 0.29187107619025976, "rougeLsum_recall_stderr": 0.004071548917864099}}, "3": {"article_DOC_summary": {"bleu": 2.2258566055479094, "bleu_stderr": 0.13278688909462125, "rouge1_fmeasure": 0.2009780831532814, "rouge1_fmeasure_stderr": 0.002806726765718572, "rouge1_precision": 0.14621341287651227, "rouge1_precision_stderr": 0.0022083149046151504, "rouge1_recall": 0.3455642084346473, "rouge1_recall_stderr": 0.004873293934425135, "rouge2_fmeasure": 0.05215230425231278, "rouge2_fmeasure_stderr": 0.0017120956588686437, "rouge2_precision": 0.037135604961774385, "rouge2_precision_stderr": 0.0012274885414975227, "rouge2_recall": 0.09277441654545833, "rouge2_recall_stderr": 0.0031426558683045865, "rougeL_fmeasure": 0.15645205789193842, "rougeL_fmeasure_stderr": 0.0021779473947538264, "rougeL_precision": 0.11361322830742238, "rougeL_precision_stderr": 0.0016918706245087672, "rougeL_recall": 0.27017363415694445, "rougeL_recall_stderr": 0.003905391020509053, "rougeLsum_fmeasure": 0.16002294003908046, "rougeLsum_fmeasure_stderr": 0.002408602292236863, "rougeLsum_precision": 0.11619780916522449, "rougeLsum_precision_stderr": 0.001872558794638193, "rougeLsum_recall": 0.2770186544920654, "rougeLsum_recall_stderr": 0.004312222731166786}}, "4": {"article_DOC_summary": {"bleu": 1.1689695560959992, "bleu_stderr": 0.14941170439296517, "rouge1_fmeasure": 0.05602682791591825, "rouge1_fmeasure_stderr": 0.0030566032233541435, "rouge1_precision": 0.04540495134964114, "rouge1_precision_stderr": 0.002577404539511274, "rouge1_recall": 0.08944999300372532, "rouge1_recall_stderr": 0.005043063336771766, "rouge2_fmeasure": 0.014711826789814367, "rouge2_fmeasure_stderr": 0.001150153366023636, "rouge2_precision": 0.011337811755364056, "rouge2_precision_stderr": 0.000979022200716812, "rouge2_recall": 0.02507829492852627, "rouge2_recall_stderr": 0.002014742970966847, "rougeL_fmeasure": 0.04340501623577573, "rougeL_fmeasure_stderr": 0.002382694314714795, "rougeL_precision": 0.03552240669275928, "rougeL_precision_stderr": 0.0020775346300726987, "rougeL_recall": 0.0694647286645038, "rougeL_recall_stderr": 0.003953679220478554, "rougeLsum_fmeasure": 0.045785794288580685, "rougeLsum_fmeasure_stderr": 0.002531815611533499, "rougeLsum_precision": 0.037416239535642694, "rougeLsum_precision_stderr": 0.002189640562314706, "rougeLsum_recall": 0.07349320517885673, "rougeLsum_recall_stderr": 0.004238026627054986}}, "5": {"article_DOC_summary": {"bleu": 3.968509960352518e-38, "bleu_stderr": 9.071697715642431e-34, "rouge1_fmeasure": 0.0031078634832113075, "rouge1_fmeasure_stderr": 0.0008672375952429783, "rouge1_precision": 0.0033252126043761066, "rouge1_precision_stderr": 0.0009227377103489034, "rouge1_recall": 0.0030093268798964366, "rouge1_recall_stderr": 0.0008438210949622407, "rouge2_fmeasure": 0.0006713467768799879, "rouge2_fmeasure_stderr": 0.0003135528125707898, "rouge2_precision": 0.0007101797265504257, "rouge2_precision_stderr": 0.0003230925998744655, "rouge2_recall": 0.0006426199586576944, "rouge2_recall_stderr": 0.0003070058829967824, "rougeL_fmeasure": 0.002288473742428132, "rougeL_fmeasure_stderr": 0.0006642689228610262, "rougeL_precision": 0.0024626201177109525, "rougeL_precision_stderr": 0.0007048985126880111, "rougeL_recall": 0.0021932876500475765, "rougeL_recall_stderr": 0.0006418079510766518, "rougeLsum_fmeasure": 0.0024871269676956433, "rougeLsum_fmeasure_stderr": 0.0007048637473097949, "rougeLsum_precision": 0.0026697560249461646, "rougeLsum_precision_stderr": 0.0007461825026075466, "rougeLsum_recall": 0.0023870797070471815, "rougeLsum_recall_stderr": 0.0006822657353438714}}}} |