{"GEM/web_nlg_en": {"0": {"PALM_prompt": {"bleu": 0.4522375218061915, "bleu_stderr": 0.04842537846111568, "rouge1_fmeasure": 0.10639641446726286, "rouge1_fmeasure_stderr": 0.002372783014156511, "rouge1_precision": 0.09405156373772382, "rouge1_precision_stderr": 0.0036589357455526954, "rouge1_recall": 0.2623187491640316, "rouge1_recall_stderr": 0.0054853417994958405, "rouge2_fmeasure": 0.047608492095606206, "rouge2_fmeasure_stderr": 0.001384256918874843, "rouge2_precision": 0.04001471903798784, "rouge2_precision_stderr": 0.002167193193860632, "rouge2_recall": 0.12482367655474384, "rouge2_recall_stderr": 0.003329638916496446, "rougeL_fmeasure": 0.09811489729413486, "rougeL_fmeasure_stderr": 0.002141247906215953, "rougeL_precision": 0.08735958257324784, "rougeL_precision_stderr": 0.0035013157983101876, "rougeL_recall": 0.2450465857818092, "rougeL_recall_stderr": 0.005156857986010396, "rougeLsum_fmeasure": 0.0992851030641096, "rougeLsum_fmeasure_stderr": 0.0022026560740801633, "rougeLsum_precision": 0.08882938411931994, "rougeLsum_precision_stderr": 0.0035668764760974714, "rougeLsum_recall": 0.24452754279908495, "rougeLsum_recall_stderr": 0.005065510424462396}}, "1": {"PALM_prompt": {"bleu": 0.650629434960658, "bleu_stderr": 0.04811417898690189, "rouge1_fmeasure": 0.16281032775122675, "rouge1_fmeasure_stderr": 0.003905335709899557, "rouge1_precision": 0.15916782201345867, "rouge1_precision_stderr": 0.005131870879954661, "rouge1_recall": 0.29665725707782414, "rouge1_recall_stderr": 0.005228319001095806, "rouge2_fmeasure": 0.08120001213349398, "rouge2_fmeasure_stderr": 0.0026664765201647343, "rouge2_precision": 0.07819648278455865, "rouge2_precision_stderr": 0.0034063589997107026, "rouge2_recall": 0.15070155918572603, "rouge2_recall_stderr": 0.003623729048520002, "rougeL_fmeasure": 0.14574992383080743, "rougeL_fmeasure_stderr": 0.003397730356308293, "rougeL_precision": 0.14191196636841233, "rougeL_precision_stderr": 0.004635280920281775, "rougeL_recall": 0.2736224046058516, "rougeL_recall_stderr": 0.004816339822450663, "rougeLsum_fmeasure": 0.14966591828719222, "rougeLsum_fmeasure_stderr": 0.003504137587849123, "rougeLsum_precision": 0.14648404402072937, "rougeLsum_precision_stderr": 0.004776844963861229, "rougeLsum_recall": 0.2774966849512831, "rougeLsum_recall_stderr": 0.004834496186187873}}, "2": {"PALM_prompt": {"bleu": 0.9046528025555703, "bleu_stderr": 0.04317473166983863, "rouge1_fmeasure": 0.2126025964717363, "rouge1_fmeasure_stderr": 0.004487229116514054, "rouge1_precision": 0.21014915270499354, "rouge1_precision_stderr": 0.005813053226743566, "rouge1_recall": 0.35653672883727167, "rouge1_recall_stderr": 0.0051494656409290275, "rouge2_fmeasure": 0.11056055329882854, "rouge2_fmeasure_stderr": 0.0031590233571128605, "rouge2_precision": 0.11091162929767316, "rouge2_precision_stderr": 0.003989043309470051, "rouge2_recall": 0.18668399640135247, "rouge2_recall_stderr": 0.0039177512048306565, "rougeL_fmeasure": 0.18634690018126043, "rougeL_fmeasure_stderr": 0.0038448807973693925, "rougeL_precision": 0.1825110333764981, "rougeL_precision_stderr": 0.005070346564582974, "rougeL_recall": 0.32304322748014636, "rougeL_recall_stderr": 0.004678142532303707, "rougeLsum_fmeasure": 0.19202573601368517, "rougeLsum_fmeasure_stderr": 0.003952591052036519, "rougeLsum_precision": 0.18939634311269352, "rougeLsum_precision_stderr": 0.005258445068941222, "rougeLsum_recall": 0.32966626591290826, "rougeLsum_recall_stderr": 0.004724502434373412}}, "3": {"PALM_prompt": {"bleu": 1.1442800703272336, "bleu_stderr": 0.05161996592570338, "rouge1_fmeasure": 0.23508991254207284, "rouge1_fmeasure_stderr": 0.004629614568550998, "rouge1_precision": 0.23213625362665477, "rouge1_precision_stderr": 0.0059610834558063595, "rouge1_recall": 0.38062292481677, "rouge1_recall_stderr": 0.005078282219671234, "rouge2_fmeasure": 0.12608234413935157, "rouge2_fmeasure_stderr": 0.003256601130342381, "rouge2_precision": 0.12811335412630678, "rouge2_precision_stderr": 0.004200144761611546, "rouge2_recall": 0.20379204157806646, "rouge2_recall_stderr": 0.00386170912683119, "rougeL_fmeasure": 0.20320672155464048, "rougeL_fmeasure_stderr": 0.003882337416765662, "rougeL_precision": 0.1997394107463207, "rougeL_precision_stderr": 0.005153079376868987, "rougeL_recall": 0.3397942315323993, "rougeL_recall_stderr": 0.004538527029075319, "rougeLsum_fmeasure": 0.21069756332821474, "rougeLsum_fmeasure_stderr": 0.004028196190821567, "rougeLsum_precision": 0.2083043346123531, "rougeLsum_precision_stderr": 0.005363455263356501, "rougeLsum_recall": 0.347929987856493, "rougeLsum_recall_stderr": 0.0045764471921679985}}, "4": {"PALM_prompt": {"bleu": 1.3793783786539846, "bleu_stderr": 0.08292725693632953, "rouge1_fmeasure": 0.25107613979636906, "rouge1_fmeasure_stderr": 0.00476323540590602, "rouge1_precision": 0.25146617993410997, "rouge1_precision_stderr": 0.006199020027337637, "rouge1_recall": 0.3925026283739189, "rouge1_recall_stderr": 0.005116605241451321, "rouge2_fmeasure": 0.1354322190391961, "rouge2_fmeasure_stderr": 0.003385535533668589, "rouge2_precision": 0.1385226844845104, "rouge2_precision_stderr": 0.004282956786141916, "rouge2_recall": 0.21131194271802842, "rouge2_recall_stderr": 0.0040385627196912076, "rougeL_fmeasure": 0.2160535699510597, "rougeL_fmeasure_stderr": 0.003987483818543123, "rougeL_precision": 0.21425855000222013, "rougeL_precision_stderr": 0.005261027090142587, "rougeL_recall": 0.34988090714764264, "rougeL_recall_stderr": 0.004590444333954342, "rougeLsum_fmeasure": 0.22537108240785111, "rougeLsum_fmeasure_stderr": 0.004170782290413772, "rougeLsum_precision": 0.22545655976991655, "rougeLsum_precision_stderr": 0.0055589913005229, "rougeLsum_recall": 0.36010176303537716, "rougeLsum_recall_stderr": 0.0046603281582664625}}, "5": {"PALM_prompt": {"bleu": 1.4145829791141218, "bleu_stderr": 0.06756850302725374, "rouge1_fmeasure": 0.25726246836968625, "rouge1_fmeasure_stderr": 0.004880864665323261, "rouge1_precision": 0.25559388874117145, "rouge1_precision_stderr": 0.006265188037282814, "rouge1_recall": 0.4014517195417289, "rouge1_recall_stderr": 0.0052097160639095145, "rouge2_fmeasure": 0.1419903076188946, "rouge2_fmeasure_stderr": 0.003491421839159055, "rouge2_precision": 0.1462902529413211, "rouge2_precision_stderr": 0.004502888503688928, "rouge2_recall": 0.22067604236758182, "rouge2_recall_stderr": 0.0041554431177298085, "rougeL_fmeasure": 0.22145748379950564, "rougeL_fmeasure_stderr": 0.004104691248611666, "rougeL_precision": 0.21838534521953784, "rougeL_precision_stderr": 0.005386484846358847, "rougeL_recall": 0.35807492888309944, "rougeL_recall_stderr": 0.004713215605602484, "rougeLsum_fmeasure": 0.2308946484376556, "rougeLsum_fmeasure_stderr": 0.004281312884008834, "rougeLsum_precision": 0.22909884605448813, "rougeLsum_precision_stderr": 0.00564116547513353, "rougeLsum_recall": 0.3686456415754311, "rougeLsum_recall_stderr": 0.004784333349134369}}}, "GEM/wiki_lingua_en": {"0": {"tldr_en": {"bleu": 2.5768645983512664, "bleu_stderr": 0.10390732312462625, "rouge1_fmeasure": 0.1810278543145764, "rouge1_fmeasure_stderr": 0.002359129908964426, "rouge1_precision": 0.1631004447259747, "rouge1_precision_stderr": 0.0025140049334374266, "rouge1_recall": 0.24869580468026348, "rouge1_recall_stderr": 0.0032277820635021014, "rouge2_fmeasure": 0.04284409748743667, "rouge2_fmeasure_stderr": 0.001036773633130634, "rouge2_precision": 0.0385111191751266, "rouge2_precision_stderr": 0.0009986244610694906, "rouge2_recall": 0.05950986614858929, "rouge2_recall_stderr": 0.0015515657908224004, "rougeL_fmeasure": 0.1323060407446597, "rougeL_fmeasure_stderr": 0.001666744596513707, "rougeL_precision": 0.11812150163422086, "rougeL_precision_stderr": 0.0017909292945280444, "rougeL_recall": 0.18668011105548613, "rougeL_recall_stderr": 0.002526858332113489, "rougeLsum_fmeasure": 0.16822692441451978, "rougeLsum_fmeasure_stderr": 0.0021965424695315023, "rougeLsum_precision": 0.15149118025181801, "rougeLsum_precision_stderr": 0.0023436532932745767, "rougeLsum_recall": 0.23193053314919995, "rougeLsum_recall_stderr": 0.003047509010443981}}, "1": {"tldr_en": {"bleu": 3.2805418289148096, "bleu_stderr": 0.06930736886640082, "rouge1_fmeasure": 0.20446918503496525, "rouge1_fmeasure_stderr": 0.0022069372036890365, "rouge1_precision": 0.24381809168774637, "rouge1_precision_stderr": 0.0033022582237546634, "rouge1_recall": 0.23017687741596388, "rouge1_recall_stderr": 0.0028624354435880044, "rouge2_fmeasure": 0.05107550928141819, "rouge2_fmeasure_stderr": 0.0012372719079850197, "rouge2_precision": 0.064059693409422, "rouge2_precision_stderr": 0.0018318331544901892, "rouge2_recall": 0.05717654707897076, "rouge2_recall_stderr": 0.0015139726468610508, "rougeL_fmeasure": 0.15417240714255895, "rougeL_fmeasure_stderr": 0.001662532523275427, "rougeL_precision": 0.18545125118813593, "rougeL_precision_stderr": 0.0026173569724847225, "rougeL_recall": 0.1747030421481033, "rougeL_recall_stderr": 0.0022396644779822898, "rougeLsum_fmeasure": 0.19083537889844354, "rougeLsum_fmeasure_stderr": 0.002054035558945731, "rougeLsum_precision": 0.2280337645476899, "rougeLsum_precision_stderr": 0.003112015382305472, "rougeLsum_recall": 0.21469429192649783, "rougeLsum_recall_stderr": 0.0026546326180329014}}, "2": {"tldr_en": {"bleu": 4.071985313483549, "bleu_stderr": 0.07738970826466988, "rouge1_fmeasure": 0.23794097030152866, "rouge1_fmeasure_stderr": 0.002188642411213601, "rouge1_precision": 0.29175676576014364, "rouge1_precision_stderr": 0.0034471150363075184, "rouge1_recall": 0.2607907068748222, "rouge1_recall_stderr": 0.002898135289732422, "rouge2_fmeasure": 0.06574644928335649, "rouge2_fmeasure_stderr": 0.0013625725128389179, "rouge2_precision": 0.08536913371644045, "rouge2_precision_stderr": 0.0020895235460299017, "rouge2_recall": 0.0713925019948092, "rouge2_recall_stderr": 0.001635476891768791, "rougeL_fmeasure": 0.1789951285071888, "rougeL_fmeasure_stderr": 0.001673666200127008, "rougeL_precision": 0.22160256648226004, "rougeL_precision_stderr": 0.0027745204374263316, "rougeL_recall": 0.19691795695851566, "rougeL_recall_stderr": 0.002270661716223799, "rougeLsum_fmeasure": 0.22300315725329103, "rougeLsum_fmeasure_stderr": 0.0020678687486032563, "rougeLsum_precision": 0.27421900185303183, "rougeLsum_precision_stderr": 0.003293382529360642, "rougeLsum_recall": 0.24426464874342324, "rougeLsum_recall_stderr": 0.002735802329870702}}, "3": {"tldr_en": {"bleu": 3.256877193820952, "bleu_stderr": 0.07385158775345343, "rouge1_fmeasure": 0.20409132873325006, "rouge1_fmeasure_stderr": 0.0026059526618525918, "rouge1_precision": 0.2571754504445173, "rouge1_precision_stderr": 0.0037874180373320154, "rouge1_recall": 0.22046706474081984, "rouge1_recall_stderr": 0.0032483649489955437, "rouge2_fmeasure": 0.05803958336813696, "rouge2_fmeasure_stderr": 0.0013905246714186119, "rouge2_precision": 0.07716310931244513, "rouge2_precision_stderr": 0.0021423793043653955, "rouge2_recall": 0.06255207307386669, "rouge2_recall_stderr": 0.001665836586847627, "rougeL_fmeasure": 0.1557150280292743, "rougeL_fmeasure_stderr": 0.0020175919818759087, "rougeL_precision": 0.19917050763282695, "rougeL_precision_stderr": 0.0031058368371087975, "rougeL_recall": 0.16863998232504207, "rougeL_recall_stderr": 0.0025563859107073333, "rougeLsum_fmeasure": 0.19198507442281348, "rougeLsum_fmeasure_stderr": 0.002473123474513908, "rougeLsum_precision": 0.24286851428671166, "rougeLsum_precision_stderr": 0.003627579238772214, "rougeLsum_recall": 0.2070808578907387, "rougeLsum_recall_stderr": 0.003069864948055298}}, "4": {"tldr_en": {"bleu": 0.11803096947131637, "bleu_stderr": 0.018616113127493047, "rouge1_fmeasure": 0.06754366655458334, "rouge1_fmeasure_stderr": 0.00231821642571142, "rouge1_precision": 0.08608412704276916, "rouge1_precision_stderr": 0.0031073010197710128, "rouge1_recall": 0.07306085845324418, "rouge1_recall_stderr": 0.0026739004311174368, "rouge2_fmeasure": 0.01891360756998624, "rouge2_fmeasure_stderr": 0.0009547131510927643, "rouge2_precision": 0.02477632495929693, "rouge2_precision_stderr": 0.0013952242546163309, "rouge2_recall": 0.020963360092888926, "rouge2_recall_stderr": 0.0011677531292808372, "rougeL_fmeasure": 0.05180637434259422, "rougeL_fmeasure_stderr": 0.0017937325092342497, "rougeL_precision": 0.06705402166283986, "rougeL_precision_stderr": 0.0024891810743964266, "rougeL_recall": 0.05633331544121819, "rougeL_recall_stderr": 0.0021123430958068772, "rougeLsum_fmeasure": 0.06316340092042942, "rougeLsum_fmeasure_stderr": 0.0021760431723604587, "rougeLsum_precision": 0.08098856968063572, "rougeLsum_precision_stderr": 0.002946288914451725, "rougeLsum_recall": 0.06822240197436494, "rougeLsum_recall_stderr": 0.002506023867308553}}, "5": {"tldr_en": {"bleu": 5.860100637257344e-12, "bleu_stderr": 1.0205550894986597e-10, "rouge1_fmeasure": 0.01167038909001005, "rouge1_fmeasure_stderr": 0.0010944129890059014, "rouge1_precision": 0.014929032882940911, "rouge1_precision_stderr": 0.001437252981426829, "rouge1_recall": 0.012605454696432882, "rouge1_recall_stderr": 0.0012515184538477262, "rouge2_fmeasure": 0.003203820995720566, "rouge2_fmeasure_stderr": 0.00042103771194584703, "rouge2_precision": 0.0041010832248453595, "rouge2_precision_stderr": 0.0005815077800226312, "rouge2_recall": 0.0034469110258534192, "rouge2_recall_stderr": 0.0004725161504235943, "rougeL_fmeasure": 0.009059396220908112, "rougeL_fmeasure_stderr": 0.0008608509358819988, "rougeL_precision": 0.011742235186401492, "rougeL_precision_stderr": 0.0011661092630625284, "rougeL_recall": 0.009919184883424567, "rougeL_recall_stderr": 0.0010141555758155579, "rougeLsum_fmeasure": 0.011096298465596519, "rougeLsum_fmeasure_stderr": 0.0010440702662319144, "rougeLsum_precision": 0.014255925532109718, "rougeLsum_precision_stderr": 0.001380098431266019, "rougeLsum_recall": 0.012021925711305772, "rougeLsum_recall_stderr": 0.001202720217240228}}}, "e2e_nlg_cleaned": {"0": {"generate_text_restaurant": {"bleu": 7.518228772851459, "bleu_stderr": 0.07988589142118296, "rouge1_fmeasure": 0.30892622395914193, "rouge1_fmeasure_stderr": 0.002362726614809891, "rouge1_precision": 0.2527585937479932, "rouge1_precision_stderr": 0.0019586691047001085, "rouge1_recall": 0.4532685157753863, "rouge1_recall_stderr": 0.0036911339160002263, "rouge2_fmeasure": 0.13957033665597848, "rouge2_fmeasure_stderr": 0.001587978757027655, "rouge2_precision": 0.10827294752994317, "rouge2_precision_stderr": 0.0013193546727602984, "rouge2_recall": 0.21206177532278597, "rouge2_recall_stderr": 0.0024697648114498094, "rougeL_fmeasure": 0.25201104517465034, "rougeL_fmeasure_stderr": 0.0018344182759923726, "rougeL_precision": 0.2074761734719538, "rougeL_precision_stderr": 0.0015484435087844478, "rougeL_recall": 0.3707049758227277, "rougeL_recall_stderr": 0.002992917144452656, "rougeLsum_fmeasure": 0.2721367746591264, "rougeLsum_fmeasure_stderr": 0.002175228967316158, "rougeLsum_precision": 0.22367271169207667, "rougeLsum_precision_stderr": 0.0018161195853035582, "rougeLsum_recall": 0.3994503148641263, "rougeLsum_recall_stderr": 0.0034245642845668594}}, "1": {"generate_text_restaurant": {"bleu": 11.762713013802438, "bleu_stderr": 0.09382576543199773, "rouge1_fmeasure": 0.4698359144705449, "rouge1_fmeasure_stderr": 0.0023428195562317463, "rouge1_precision": 0.5758411505584643, "rouge1_precision_stderr": 0.0032641614095776606, "rouge1_recall": 0.43699974124480134, "rouge1_recall_stderr": 0.0030360517355224794, "rouge2_fmeasure": 0.21971297989413593, "rouge2_fmeasure_stderr": 0.0020517231278393165, "rouge2_precision": 0.27339290904893143, "rouge2_precision_stderr": 0.0027333405330301377, "rouge2_recall": 0.20425825992656632, "rouge2_recall_stderr": 0.0021962926617281136, "rougeL_fmeasure": 0.3397129377482095, "rougeL_fmeasure_stderr": 0.0020808579737579473, "rougeL_precision": 0.4200242586753886, "rougeL_precision_stderr": 0.0030278428531837543, "rougeL_recall": 0.31470569352158173, "rougeL_recall_stderr": 0.002441278894908242, "rougeLsum_fmeasure": 0.3826629288347234, "rougeLsum_fmeasure_stderr": 0.0023388359390624446, "rougeLsum_precision": 0.4702024862705025, "rougeLsum_precision_stderr": 0.0032151475190549403, "rougeLsum_recall": 0.3555458059380285, "rougeLsum_recall_stderr": 0.0027838026083691135}}, "2": {"generate_text_restaurant": {"bleu": 14.028619911508963, "bleu_stderr": 0.17673898243267264, "rouge1_fmeasure": 0.4982696315856735, "rouge1_fmeasure_stderr": 0.002277178664730148, "rouge1_precision": 0.5880328986485642, "rouge1_precision_stderr": 0.0031633644314478966, "rouge1_recall": 0.4720615710167169, "rouge1_recall_stderr": 0.0030042579734499103, "rouge2_fmeasure": 0.2436824998963185, "rouge2_fmeasure_stderr": 0.0021479952999434505, "rouge2_precision": 0.2905416018050732, "rouge2_precision_stderr": 0.0027458331588556565, "rouge2_recall": 0.2313719045642725, "rouge2_recall_stderr": 0.002349650773654754, "rougeL_fmeasure": 0.36315580245879386, "rougeL_fmeasure_stderr": 0.0021103667472393136, "rougeL_precision": 0.4304826242102334, "rougeL_precision_stderr": 0.002921537898047091, "rougeL_recall": 0.34359634632916913, "rougeL_recall_stderr": 0.002538014950574236, "rougeLsum_fmeasure": 0.41230819320152157, "rougeLsum_fmeasure_stderr": 0.0023628359694983633, "rougeLsum_precision": 0.4866663175226494, "rougeLsum_precision_stderr": 0.003134734940667762, "rougeLsum_recall": 0.39070560600420967, "rougeLsum_recall_stderr": 0.002859660656155989}}, "3": {"generate_text_restaurant": {"bleu": 14.824429124321526, "bleu_stderr": 0.1257638219512965, "rouge1_fmeasure": 0.5070937995389966, "rouge1_fmeasure_stderr": 0.0021993659376666874, "rouge1_precision": 0.5903839264246126, "rouge1_precision_stderr": 0.003096593178519806, "rouge1_recall": 0.48303754455261133, "rouge1_recall_stderr": 0.0029313776925495253, "rouge2_fmeasure": 0.2526618416523279, "rouge2_fmeasure_stderr": 0.0021298129637362085, "rouge2_precision": 0.2971819596009762, "rouge2_precision_stderr": 0.0027204840509740583, "rouge2_recall": 0.24110048435208156, "rouge2_recall_stderr": 0.002348630487706421, "rougeL_fmeasure": 0.37097982222923104, "rougeL_fmeasure_stderr": 0.00214061071940383, "rougeL_precision": 0.43347382731719464, "rougeL_precision_stderr": 0.0029257357889719074, "rougeL_recall": 0.3529852168172252, "rougeL_recall_stderr": 0.002550242635255893, "rougeLsum_fmeasure": 0.42203281188344766, "rougeLsum_fmeasure_stderr": 0.0023652228936698657, "rougeLsum_precision": 0.49123394352656125, "rougeLsum_precision_stderr": 0.0031248395828196904, "rougeLsum_recall": 0.4020764458847546, "rougeLsum_recall_stderr": 0.0028446825862533704}}, "4": {"generate_text_restaurant": {"bleu": 15.1456115809235, "bleu_stderr": 0.1628753687758124, "rouge1_fmeasure": 0.5145793651843434, "rouge1_fmeasure_stderr": 0.002244489356919281, "rouge1_precision": 0.5945998345487046, "rouge1_precision_stderr": 0.003074613754297493, "rouge1_recall": 0.48854055206810637, "rouge1_recall_stderr": 0.0028822641580179367, "rouge2_fmeasure": 0.2559926229244319, "rouge2_fmeasure_stderr": 0.002186356460577112, "rouge2_precision": 0.29784097926829245, "rouge2_precision_stderr": 0.0026941678409656135, "rouge2_recall": 0.2436337287979087, "rouge2_recall_stderr": 0.0023716503152493335, "rougeL_fmeasure": 0.3747326640922719, "rougeL_fmeasure_stderr": 0.002148508706418628, "rougeL_precision": 0.433653082379793, "rougeL_precision_stderr": 0.002833488672483008, "rougeL_recall": 0.3558030676746678, "rougeL_recall_stderr": 0.0025159494686373797, "rougeLsum_fmeasure": 0.42740717670424816, "rougeLsum_fmeasure_stderr": 0.0023775373903584217, "rougeLsum_precision": 0.49357503577481815, "rougeLsum_precision_stderr": 0.0030663612183832903, "rougeLsum_recall": 0.4058018094790397, "rougeLsum_recall_stderr": 0.002791634703514705}}, "5": {"generate_text_restaurant": {"bleu": 15.184590176560544, "bleu_stderr": 0.17570671649096134, "rouge1_fmeasure": 0.5172310679190623, "rouge1_fmeasure_stderr": 0.002187662941341786, "rouge1_precision": 0.5980619294865127, "rouge1_precision_stderr": 0.003055147702862821, "rouge1_recall": 0.4899430329979205, "rouge1_recall_stderr": 0.002838541142993511, "rouge2_fmeasure": 0.259556048619835, "rouge2_fmeasure_stderr": 0.002143271876534031, "rouge2_precision": 0.3029600136699186, "rouge2_precision_stderr": 0.002703515351522382, "rouge2_recall": 0.24620276831802643, "rouge2_recall_stderr": 0.0023264378571411816, "rougeL_fmeasure": 0.37807698267399703, "rougeL_fmeasure_stderr": 0.002126725638562394, "rougeL_precision": 0.4380103729999666, "rougeL_precision_stderr": 0.0028424300466825983, "rougeL_recall": 0.35795640195755224, "rougeL_recall_stderr": 0.0024826420662082673, "rougeLsum_fmeasure": 0.4311732922825964, "rougeLsum_fmeasure_stderr": 0.0023482937755900097, "rougeLsum_precision": 0.4982942932710782, "rougeLsum_precision_stderr": 0.0030594319184573462, "rougeLsum_recall": 0.40852131422574206, "rougeLsum_recall_stderr": 0.0027745302682206834}}}, "gem_xsum": {"0": {"article_DOC_summary": {"bleu": 1.0840616150366835, "bleu_stderr": 0.10220605780455636, "rouge1_fmeasure": 0.12067679782231505, "rouge1_fmeasure_stderr": 0.003015872334492621, "rouge1_precision": 0.09160247708817207, "rouge1_precision_stderr": 0.002375172469912284, "rouge1_recall": 0.19613476599918667, "rouge1_recall_stderr": 0.005073318605110471, "rouge2_fmeasure": 0.021176795907655737, "rouge2_fmeasure_stderr": 0.0011603757977784665, "rouge2_precision": 0.015487063309988504, "rouge2_precision_stderr": 0.000848981732321504, "rouge2_recall": 0.0363837944571209, "rouge2_recall_stderr": 0.0020790710888273895, "rougeL_fmeasure": 0.09086726074181874, "rougeL_fmeasure_stderr": 0.0022256142858678965, "rougeL_precision": 0.06937634282139736, "rougeL_precision_stderr": 0.001813605739492327, "rougeL_recall": 0.1479963053053532, "rougeL_recall_stderr": 0.0038099944087791725, "rougeLsum_fmeasure": 0.09880097411831448, "rougeLsum_fmeasure_stderr": 0.0024614730448775535, "rougeLsum_precision": 0.07512656050190324, "rougeLsum_precision_stderr": 0.001959507720128778, "rougeLsum_recall": 0.1612082948452722, "rougeLsum_recall_stderr": 0.004219489865399336}}, "1": {"article_DOC_summary": {"bleu": 2.1144830791719307, "bleu_stderr": 0.11445499213864452, "rouge1_fmeasure": 0.22223912621847974, "rouge1_fmeasure_stderr": 0.003038126692025604, "rouge1_precision": 0.2003179694226108, "rouge1_precision_stderr": 0.003646294986793581, "rouge1_recall": 0.3082326819925303, "rouge1_recall_stderr": 0.004421626418186149, "rouge2_fmeasure": 0.050641256552544464, "rouge2_fmeasure_stderr": 0.002016315458850625, "rouge2_precision": 0.04617082546967428, "rouge2_precision_stderr": 0.0021567164563758494, "rouge2_recall": 0.07074171325045796, "rouge2_recall_stderr": 0.0026782882522819163, "rougeL_fmeasure": 0.16589957489115423, "rougeL_fmeasure_stderr": 0.0024349153804753905, "rougeL_precision": 0.15020466828774898, "rougeL_precision_stderr": 0.002974138334891651, "rougeL_recall": 0.23037723268498672, "rougeL_recall_stderr": 0.0034903634923284257, "rougeLsum_fmeasure": 0.17413975005815832, "rougeLsum_fmeasure_stderr": 0.0025334465295397523, "rougeLsum_precision": 0.156190697593295, "rougeLsum_precision_stderr": 0.0029737943854797597, "rougeLsum_recall": 0.2443326358730322, "rougeLsum_recall_stderr": 0.003851152935036917}}, "2": {"article_DOC_summary": {"bleu": 2.2306956500254795, "bleu_stderr": 0.1534426529740081, "rouge1_fmeasure": 0.22874247828238384, "rouge1_fmeasure_stderr": 0.003191868132841587, "rouge1_precision": 0.2167785998186487, "rouge1_precision_stderr": 0.0038703703581663036, "rouge1_recall": 0.29079354607238944, "rouge1_recall_stderr": 0.0042086230091149205, "rouge2_fmeasure": 0.05359901469303583, "rouge2_fmeasure_stderr": 0.002063273466751458, "rouge2_precision": 0.05175962394844965, "rouge2_precision_stderr": 0.002262457698273439, "rouge2_recall": 0.06767519675126271, "rouge2_recall_stderr": 0.002531468931801855, "rougeL_fmeasure": 0.17116883513373068, "rougeL_fmeasure_stderr": 0.002601631095778569, "rougeL_precision": 0.1626685190790419, "rougeL_precision_stderr": 0.003181540362928691, "rougeL_recall": 0.2176434055764335, "rougeL_recall_stderr": 0.0033468188991687773, "rougeLsum_fmeasure": 0.17781283216267912, "rougeLsum_fmeasure_stderr": 0.0026319963165001175, "rougeLsum_precision": 0.16752103628195428, "rougeLsum_precision_stderr": 0.0031476246457933605, "rougeLsum_recall": 0.2286412427632142, "rougeLsum_recall_stderr": 0.003582394216085152}}, "3": {"article_DOC_summary": {"bleu": 2.4283658434676942, "bleu_stderr": 0.1084231496409544, "rouge1_fmeasure": 0.22044943741927525, "rouge1_fmeasure_stderr": 0.003500198780987625, "rouge1_precision": 0.21592444335846092, "rouge1_precision_stderr": 0.004246983520225218, "rouge1_recall": 0.27255737663479357, "rouge1_recall_stderr": 0.00447437166346409, "rouge2_fmeasure": 0.05351615652078515, "rouge2_fmeasure_stderr": 0.0022197484992897607, "rouge2_precision": 0.05330214126583765, "rouge2_precision_stderr": 0.0025012370800294183, "rouge2_recall": 0.06515904722605939, "rouge2_recall_stderr": 0.0025535061286592504, "rougeL_fmeasure": 0.16421475353571632, "rougeL_fmeasure_stderr": 0.0028136325952485735, "rougeL_precision": 0.16172792138960806, "rougeL_precision_stderr": 0.003474612361597086, "rougeL_recall": 0.20248110828398325, "rougeL_recall_stderr": 0.0034801799909718704, "rougeLsum_fmeasure": 0.17052032174118803, "rougeLsum_fmeasure_stderr": 0.002883605135295133, "rougeLsum_precision": 0.16634670992387487, "rougeLsum_precision_stderr": 0.0034675307885691244, "rougeLsum_recall": 0.21304752670955557, "rougeLsum_recall_stderr": 0.003802772338811888}}, "4": {"article_DOC_summary": {"bleu": 0.40228156399700404, "bleu_stderr": 0.0795066489605694, "rouge1_fmeasure": 0.05798370899016291, "rouge1_fmeasure_stderr": 0.003309673469340258, "rouge1_precision": 0.06147088600466444, "rouge1_precision_stderr": 0.003807688121301648, "rouge1_recall": 0.06919835565602203, "rouge1_recall_stderr": 0.004080878740872531, "rouge2_fmeasure": 0.013641962174467587, "rouge2_fmeasure_stderr": 0.0012106481387976049, "rouge2_precision": 0.014228533929974868, "rouge2_precision_stderr": 0.0014047860954449383, "rouge2_recall": 0.0166314025722418, "rouge2_recall_stderr": 0.0014602317545186565, "rougeL_fmeasure": 0.043392440237132235, "rougeL_fmeasure_stderr": 0.002526920635642375, "rougeL_precision": 0.04649724897774529, "rougeL_precision_stderr": 0.0029768758298026627, "rougeL_recall": 0.05168291535676844, "rougeL_recall_stderr": 0.003094715210052394, "rougeLsum_fmeasure": 0.04537985187674532, "rougeLsum_fmeasure_stderr": 0.0026361408489140024, "rougeLsum_precision": 0.048035895047127686, "rougeLsum_precision_stderr": 0.003028118969042768, "rougeLsum_recall": 0.05464177271239397, "rougeLsum_recall_stderr": 0.0033104672738008553}}, "5": {"article_DOC_summary": {"bleu": 1.2194816597556972e-29, "bleu_stderr": 1.9673150803997765e-21, "rouge1_fmeasure": 0.0022410464211047414, "rouge1_fmeasure_stderr": 0.0006379815102748624, "rouge1_precision": 0.002305114359249611, "rouge1_precision_stderr": 0.0006855365150103617, "rouge1_recall": 0.002688750909485673, "rouge1_recall_stderr": 0.0008419301936781596, "rouge2_fmeasure": 0.0002428157678792438, "rouge2_fmeasure_stderr": 0.00010121603253679161, "rouge2_precision": 0.00023662681974673803, "rouge2_precision_stderr": 0.00010805221445763836, "rouge2_recall": 0.0003191847290509596, "rouge2_recall_stderr": 0.00013624996945101362, "rougeL_fmeasure": 0.001480383954453164, "rougeL_fmeasure_stderr": 0.0004335775279500401, "rougeL_precision": 0.0014967981731443785, "rougeL_precision_stderr": 0.00044282917196946015, "rougeL_recall": 0.0018089244853048499, "rougeL_recall_stderr": 0.0005955143349649119, "rougeLsum_fmeasure": 0.0014592568247182058, "rougeLsum_fmeasure_stderr": 0.00042833093506174205, "rougeLsum_precision": 0.0014611359517881007, "rougeLsum_precision_stderr": 0.0004268628859757995, "rougeLsum_recall": 0.0017987055420995693, "rougeLsum_recall_stderr": 0.0005977174922462606}}}}