{"GEM/web_nlg_en": {"0": {"PALM_prompt": {"bleu": 0.23336285971913792, "bleu_stderr": 0.026831547216034552, "rouge1_fmeasure": 0.08446571459891085, "rouge1_fmeasure_stderr": 0.0015824965912950772, "rouge1_precision": 0.05439865962968967, "rouge1_precision_stderr": 0.0011092434568872975, "rouge1_recall": 0.24374100837448018, "rouge1_recall_stderr": 0.004154005834452381, "rouge2_fmeasure": 0.03996425304915668, "rouge2_fmeasure_stderr": 0.000989713007421649, "rouge2_precision": 0.02550841626771464, "rouge2_precision_stderr": 0.0006691581780940698, "rouge2_recall": 0.12014632144828626, "rouge2_recall_stderr": 0.002861946551453886, "rougeL_fmeasure": 0.08265416866191247, "rougeL_fmeasure_stderr": 0.0015305727288322003, "rougeL_precision": 0.0531129917083209, "rougeL_precision_stderr": 0.0010634389473944373, "rougeL_recall": 0.23984830582926353, "rougeL_recall_stderr": 0.004111595583702724, "rougeLsum_fmeasure": 0.08134464486582038, "rougeLsum_fmeasure_stderr": 0.0015093395667322115, "rougeLsum_precision": 0.052377103781293156, "rougeLsum_precision_stderr": 0.0010589109148837366, "rougeLsum_recall": 0.23522556317101853, "rougeLsum_recall_stderr": 0.003942690776656362}}, "1": {"PALM_prompt": {"bleu": 0.149999320100551, "bleu_stderr": 0.01648600857868501, "rouge1_fmeasure": 0.0783024499591439, "rouge1_fmeasure_stderr": 0.0015115599781434076, "rouge1_precision": 0.05039389233407519, "rouge1_precision_stderr": 0.0010678479734785133, "rouge1_recall": 0.23911605188763663, "rouge1_recall_stderr": 0.004217097544169996, "rouge2_fmeasure": 0.03533421218479914, "rouge2_fmeasure_stderr": 0.0009441723878638388, "rouge2_precision": 0.022689565244003423, "rouge2_precision_stderr": 0.0006492234607511071, "rouge2_recall": 0.10804796123371856, "rouge2_recall_stderr": 0.002772425440915182, "rougeL_fmeasure": 0.0765840417258607, "rougeL_fmeasure_stderr": 0.0014686631424978348, "rougeL_precision": 0.049215318671431786, "rougeL_precision_stderr": 0.0010308225696802156, "rougeL_recall": 0.23439123752368696, "rougeL_recall_stderr": 0.004133972873584638, "rougeLsum_fmeasure": 0.07550976829415487, "rougeLsum_fmeasure_stderr": 0.0014525784885102127, "rougeLsum_precision": 0.048623672915347575, "rougeLsum_precision_stderr": 0.0010273102967872621, "rougeLsum_recall": 0.22915163434854377, "rougeLsum_recall_stderr": 0.00394130010753112}}, "2": {"PALM_prompt": {"bleu": 0.13305791271479062, "bleu_stderr": 0.011210726963048447, "rouge1_fmeasure": 0.07604718629625555, "rouge1_fmeasure_stderr": 0.0014484478235269312, "rouge1_precision": 0.04874142647590828, "rouge1_precision_stderr": 0.001024411277927112, "rouge1_recall": 0.23418663847997345, "rouge1_recall_stderr": 0.0038675109072007405, "rouge2_fmeasure": 0.034017897932799156, "rouge2_fmeasure_stderr": 0.0009135473678299833, "rouge2_precision": 0.02178125656158737, "rouge2_precision_stderr": 0.0006229612925274444, "rouge2_recall": 0.10462775115881133, "rouge2_recall_stderr": 0.0026242942688188046, "rougeL_fmeasure": 0.07445958002040497, "rougeL_fmeasure_stderr": 0.00141287468923303, "rougeL_precision": 0.047663521069835214, "rougeL_precision_stderr": 0.0009922323810451167, "rougeL_recall": 0.22896434652678516, "rougeL_recall_stderr": 0.003766547321885562, "rougeLsum_fmeasure": 0.0737768400907496, "rougeLsum_fmeasure_stderr": 0.0014096194296899693, "rougeLsum_precision": 0.04730394599720064, "rougeLsum_precision_stderr": 0.000995041687823415, "rougeLsum_recall": 0.22603927988076686, "rougeLsum_recall_stderr": 0.0036652559910908635}}, "3": {"PALM_prompt": {"bleu": 0.10368475460486865, "bleu_stderr": 0.011060778041099317, "rouge1_fmeasure": 0.07485950515286233, "rouge1_fmeasure_stderr": 0.0014144928012380664, "rouge1_precision": 0.048322862828509484, "rouge1_precision_stderr": 0.001091294602922774, "rouge1_recall": 0.2281459683846524, "rouge1_recall_stderr": 0.003630469769192213, "rouge2_fmeasure": 0.033414173983495055, "rouge2_fmeasure_stderr": 0.0008989911483642444, "rouge2_precision": 0.021765575511902755, "rouge2_precision_stderr": 0.0007376999524486791, "rouge2_recall": 0.10112935517460186, "rouge2_recall_stderr": 0.0025273038118034915, "rougeL_fmeasure": 0.0733042353653659, "rougeL_fmeasure_stderr": 0.0013877940713480257, "rougeL_precision": 0.047310277561040476, "rougeL_precision_stderr": 0.0010701645225700237, "rougeL_recall": 0.22271748235416333, "rougeL_recall_stderr": 0.0035317693762082583, "rougeLsum_fmeasure": 0.07279776055251803, "rougeLsum_fmeasure_stderr": 0.0013786706937308762, "rougeLsum_precision": 0.04700153630836809, "rougeLsum_precision_stderr": 0.0010655951813045416, "rougeLsum_recall": 0.22158687380299466, "rougeLsum_recall_stderr": 0.0035274636245185057}}, "4": {"PALM_prompt": {"bleu": 0.12643210930285223, "bleu_stderr": 0.017689451259510113, "rouge1_fmeasure": 0.07550620564282749, "rouge1_fmeasure_stderr": 0.0014275424158662932, "rouge1_precision": 0.048546496122212304, "rouge1_precision_stderr": 0.0010917543766011267, "rouge1_recall": 0.23329777643622032, "rouge1_recall_stderr": 0.00377927308236942, "rouge2_fmeasure": 0.03361031713979665, "rouge2_fmeasure_stderr": 0.0009094774573230576, "rouge2_precision": 0.021812470526869524, "rouge2_precision_stderr": 0.0007410163805045418, "rouge2_recall": 0.10384870030998751, "rouge2_recall_stderr": 0.002559034716018191, "rougeL_fmeasure": 0.0737633812147375, "rougeL_fmeasure_stderr": 0.001396840481575515, "rougeL_precision": 0.047406756420334914, "rougeL_precision_stderr": 0.0010669755185219207, "rougeL_recall": 0.22692062870092394, "rougeL_recall_stderr": 0.003637107260174285, "rougeLsum_fmeasure": 0.07343239839440881, "rougeLsum_fmeasure_stderr": 0.001390175033514176, "rougeLsum_precision": 0.04722034321153461, "rougeLsum_precision_stderr": 0.0010651409333852174, "rougeLsum_recall": 0.22637726105546893, "rougeLsum_recall_stderr": 0.0036450661129995517}}, "5": {"PALM_prompt": {"bleu": 0.14580784113904285, "bleu_stderr": 0.02169837835551737, "rouge1_fmeasure": 0.07635558897011635, "rouge1_fmeasure_stderr": 0.0014067473320664224, "rouge1_precision": 0.04858688695146614, "rouge1_precision_stderr": 0.0009919570128492023, "rouge1_recall": 0.23936897854801265, "rouge1_recall_stderr": 0.003809570838617069, "rouge2_fmeasure": 0.0336482487712469, "rouge2_fmeasure_stderr": 0.0008809384464421846, "rouge2_precision": 0.021403300583302882, "rouge2_precision_stderr": 0.0005992879742971646, "rouge2_recall": 0.10635401405034506, "rouge2_recall_stderr": 0.0026320301985926294, "rougeL_fmeasure": 0.07457995007202929, "rougeL_fmeasure_stderr": 0.0013717292986929117, "rougeL_precision": 0.04743074568047055, "rougeL_precision_stderr": 0.0009628261081974606, "rougeL_recall": 0.23310511154456653, "rougeL_recall_stderr": 0.003667912499413062, "rougeLsum_fmeasure": 0.07413039496102994, "rougeLsum_fmeasure_stderr": 0.0013645157195961873, "rougeLsum_precision": 0.04717939159930382, "rougeLsum_precision_stderr": 0.0009611612661616537, "rougeLsum_recall": 0.23214615779014944, "rougeLsum_recall_stderr": 0.0036745231846563382}}}, "GEM/wiki_lingua_en": {"0": {"tldr_en": {"bleu": 0.5430730295333313, "bleu_stderr": 0.0365815466590515, "rouge1_fmeasure": 0.10422675836754251, "rouge1_fmeasure_stderr": 0.001600341131106392, "rouge1_precision": 0.09363473178880811, "rouge1_precision_stderr": 0.0016796809875309112, "rouge1_recall": 0.14418256512962083, "rouge1_recall_stderr": 0.002167398392749155, "rouge2_fmeasure": 0.013569083806173431, "rouge2_fmeasure_stderr": 0.000536933125563704, "rouge2_precision": 0.012160392139666808, "rouge2_precision_stderr": 0.0005105463730603428, "rouge2_recall": 0.019121459317877912, "rouge2_recall_stderr": 0.0008232714019808441, "rougeL_fmeasure": 0.09199729526410924, "rougeL_fmeasure_stderr": 0.0013200459901581483, "rougeL_precision": 0.0820107922443091, "rougeL_precision_stderr": 0.0013749923256347872, "rougeL_recall": 0.12893888139963622, "rougeL_recall_stderr": 0.0018862133214712646, "rougeLsum_fmeasure": 0.09659833472928117, "rougeLsum_fmeasure_stderr": 0.0014598821948214504, "rougeLsum_precision": 0.08652832387527064, "rougeLsum_precision_stderr": 0.0015294411673741832, "rougeLsum_recall": 0.1344951570087262, "rougeLsum_recall_stderr": 0.0020253753831603227}}, "1": {"tldr_en": {"bleu": 0.7631030821901151, "bleu_stderr": 0.03637126016426104, "rouge1_fmeasure": 0.12944623984650427, "rouge1_fmeasure_stderr": 0.0015508995745003894, "rouge1_precision": 0.113864402018691, "rouge1_precision_stderr": 0.0015404538134881224, "rouge1_recall": 0.1838117919523142, "rouge1_recall_stderr": 0.0023514998715679107, "rouge2_fmeasure": 0.014839503603430174, "rouge2_fmeasure_stderr": 0.0005401931668179484, "rouge2_precision": 0.012715360202877583, "rouge2_precision_stderr": 0.0004729696535287597, "rouge2_recall": 0.022779782580969615, "rouge2_recall_stderr": 0.0010072688122998766, "rougeL_fmeasure": 0.09507660161625574, "rougeL_fmeasure_stderr": 0.0010200141214599331, "rougeL_precision": 0.08328579570968432, "rougeL_precision_stderr": 0.0010324983906124013, "rougeL_recall": 0.1380185552697111, "rougeL_recall_stderr": 0.001751171256108266, "rougeLsum_fmeasure": 0.12204763022142331, "rougeLsum_fmeasure_stderr": 0.0014376576746715666, "rougeLsum_precision": 0.10740807503883001, "rougeLsum_precision_stderr": 0.0014382706335826095, "rougeLsum_recall": 0.17373508082119807, "rougeLsum_recall_stderr": 0.0022092321023785564}}, "2": {"tldr_en": {"bleu": 0.745302789030922, "bleu_stderr": 0.041165212986491714, "rouge1_fmeasure": 0.125968585192418, "rouge1_fmeasure_stderr": 0.001567482533109581, "rouge1_precision": 0.11393029559700361, "rouge1_precision_stderr": 0.0016763730882923063, "rouge1_recall": 0.1769694736700524, "rouge1_recall_stderr": 0.0023424150386553723, "rouge2_fmeasure": 0.014779019287405309, "rouge2_fmeasure_stderr": 0.0005575381148601111, "rouge2_precision": 0.01301367400947571, "rouge2_precision_stderr": 0.0005143488258905196, "rouge2_recall": 0.021873142006066014, "rouge2_recall_stderr": 0.000934130847859976, "rougeL_fmeasure": 0.09713467955259053, "rougeL_fmeasure_stderr": 0.0011252807281427579, "rougeL_precision": 0.0874972075486996, "rougeL_precision_stderr": 0.001231137532979079, "rougeL_recall": 0.13892758321292495, "rougeL_recall_stderr": 0.001814780335285223, "rougeLsum_fmeasure": 0.11827617802959285, "rougeLsum_fmeasure_stderr": 0.0014395913434439003, "rougeLsum_precision": 0.10695613459471714, "rougeLsum_precision_stderr": 0.0015471539643745647, "rougeLsum_recall": 0.16645890967746207, "rougeLsum_recall_stderr": 0.00217354070441736}}, "3": {"tldr_en": {"bleu": 0.9375524807033079, "bleu_stderr": 0.05076091375311075, "rouge1_fmeasure": 0.1080907737092221, "rouge1_fmeasure_stderr": 0.0017189902209006306, "rouge1_precision": 0.10517912682002659, "rouge1_precision_stderr": 0.0020169944192517456, "rouge1_recall": 0.14986203056954372, "rouge1_recall_stderr": 0.002553781810198287, "rouge2_fmeasure": 0.015116060561354339, "rouge2_fmeasure_stderr": 0.0005706720135531178, "rouge2_precision": 0.01411384967174985, "rouge2_precision_stderr": 0.0005796594561779423, "rouge2_recall": 0.022758512637964766, "rouge2_recall_stderr": 0.0010268466428699436, "rougeL_fmeasure": 0.08717745912804374, "rougeL_fmeasure_stderr": 0.0013335661136481402, "rougeL_precision": 0.08500267190413809, "rougeL_precision_stderr": 0.0016364237998568027, "rougeL_recall": 0.12241576028305143, "rougeL_recall_stderr": 0.0020787177316311327, "rougeLsum_fmeasure": 0.10075080145793731, "rougeLsum_fmeasure_stderr": 0.0015788401832700393, "rougeLsum_precision": 0.09826602680946438, "rougeLsum_precision_stderr": 0.0018880997129709805, "rougeLsum_recall": 0.13990265269905022, "rougeLsum_recall_stderr": 0.0023636459311459136}}, "4": {"tldr_en": {"bleu": 0.2455685388768164, "bleu_stderr": 0.023312196201743386, "rouge1_fmeasure": 0.038297790163100025, "rouge1_fmeasure_stderr": 0.001450936870070239, "rouge1_precision": 0.04021891620427611, "rouge1_precision_stderr": 0.00179527122100358, "rouge1_recall": 0.05458669351809771, "rouge1_recall_stderr": 0.0021686949760662015, "rouge2_fmeasure": 0.006564722152989603, "rouge2_fmeasure_stderr": 0.00044826882706775823, "rouge2_precision": 0.007175083221520411, "rouge2_precision_stderr": 0.0006861959426040823, "rouge2_recall": 0.010377039775321539, "rouge2_recall_stderr": 0.0008398548385378956, "rougeL_fmeasure": 0.03193814381233648, "rougeL_fmeasure_stderr": 0.0011842243614109398, "rougeL_precision": 0.03365949856690121, "rougeL_precision_stderr": 0.001518451427611522, "rougeL_recall": 0.046270525077678676, "rougeL_recall_stderr": 0.0018467375730547731, "rougeLsum_fmeasure": 0.03543698761206124, "rougeLsum_fmeasure_stderr": 0.0013366330300040165, "rougeLsum_precision": 0.03743305339041787, "rougeLsum_precision_stderr": 0.0016843420360592007, "rougeLsum_recall": 0.0506510365437872, "rougeLsum_recall_stderr": 0.002014009342396866}}, "5": {"tldr_en": {"bleu": 5.018187832788465e-07, "bleu_stderr": 9.001238569701927e-07, "rouge1_fmeasure": 0.006452133253476872, "rouge1_fmeasure_stderr": 0.0006426391950933609, "rouge1_precision": 0.00666688354748637, "rouge1_precision_stderr": 0.0007557736630150564, "rouge1_recall": 0.009539134461787335, "rouge1_recall_stderr": 0.0010266547706396002, "rouge2_fmeasure": 0.001256549559807457, "rouge2_fmeasure_stderr": 0.00021119936913661453, "rouge2_precision": 0.001389249823684832, "rouge2_precision_stderr": 0.0003303542509473268, "rouge2_recall": 0.002107899216680717, "rouge2_recall_stderr": 0.000406297855701019, "rougeL_fmeasure": 0.005351282375182499, "rougeL_fmeasure_stderr": 0.0005270601162356447, "rougeL_precision": 0.0055221266380235945, "rougeL_precision_stderr": 0.0006252483839771813, "rougeL_recall": 0.00798094708260653, "rougeL_recall_stderr": 0.0008641648642621242, "rougeLsum_fmeasure": 0.0059470818044703435, "rougeLsum_fmeasure_stderr": 0.0005945085971730911, "rougeLsum_precision": 0.006186563146749757, "rougeLsum_precision_stderr": 0.0007119271694803169, "rougeLsum_recall": 0.008778707261151484, "rougeLsum_recall_stderr": 0.0009486499053541579}}}, "e2e_nlg_cleaned": {"0": {"generate_text_restaurant": {"bleu": 0.0, "bleu_stderr": 0.0, "rouge1_fmeasure": 0.0, "rouge1_fmeasure_stderr": 0.0, "rouge1_precision": 0.0, "rouge1_precision_stderr": 0.0, "rouge1_recall": 0.0, "rouge1_recall_stderr": 0.0, "rouge2_fmeasure": 0.0, "rouge2_fmeasure_stderr": 0.0, "rouge2_precision": 0.0, "rouge2_precision_stderr": 0.0, "rouge2_recall": 0.0, "rouge2_recall_stderr": 0.0, "rougeL_fmeasure": 0.0, "rougeL_fmeasure_stderr": 0.0, "rougeL_precision": 0.0, "rougeL_precision_stderr": 0.0, "rougeL_recall": 0.0, "rougeL_recall_stderr": 0.0, "rougeLsum_fmeasure": 0.0, "rougeLsum_fmeasure_stderr": 0.0, "rougeLsum_precision": 0.0, "rougeLsum_precision_stderr": 0.0, "rougeLsum_recall": 0.0, "rougeLsum_recall_stderr": 0.0}}, "1": {"generate_text_restaurant": {"bleu": 4.009859551325065, "bleu_stderr": 0.13278046275335678, "rouge1_fmeasure": 0.2740595010030775, "rouge1_fmeasure_stderr": 0.002385396193975501, "rouge1_precision": 0.3578229387593085, "rouge1_precision_stderr": 0.003856721380827842, "rouge1_recall": 0.25948739086059736, "rouge1_recall_stderr": 0.002640226000794725, "rouge2_fmeasure": 0.0790458842297352, "rouge2_fmeasure_stderr": 0.001445148755996047, "rouge2_precision": 0.13054044528410688, "rouge2_precision_stderr": 0.0037429245675078405, "rouge2_recall": 0.07406180042426694, "rouge2_recall_stderr": 0.0014501941041824516, "rougeL_fmeasure": 0.2018458460713563, "rougeL_fmeasure_stderr": 0.0018101367404328157, "rougeL_precision": 0.2735828328272949, "rougeL_precision_stderr": 0.0036193449495243797, "rougeL_recall": 0.1900509586663965, "rougeL_recall_stderr": 0.001986984907305974, "rougeLsum_fmeasure": 0.22766636955410458, "rougeLsum_fmeasure_stderr": 0.002095153498100042, "rougeLsum_precision": 0.30371799193520876, "rougeLsum_precision_stderr": 0.003752209403616017, "rougeLsum_recall": 0.21475934437687166, "rougeLsum_recall_stderr": 0.0022815651046262236}}, "2": {"generate_text_restaurant": {"bleu": 4.7806427294993, "bleu_stderr": 0.1310832353636796, "rouge1_fmeasure": 0.2720615139154822, "rouge1_fmeasure_stderr": 0.0027687783144970625, "rouge1_precision": 0.4023615733786828, "rouge1_precision_stderr": 0.0050997654220666, "rouge1_recall": 0.2604859328757677, "rouge1_recall_stderr": 0.003124610081613822, "rouge2_fmeasure": 0.09494958872823868, "rouge2_fmeasure_stderr": 0.0016238555093460345, "rouge2_precision": 0.20471652877426683, "rouge2_precision_stderr": 0.0053699474888414716, "rouge2_recall": 0.08914356908095893, "rouge2_recall_stderr": 0.0017253335935271583, "rougeL_fmeasure": 0.20383717565040163, "rougeL_fmeasure_stderr": 0.002104411024247141, "rougeL_precision": 0.324312305309799, "rougeL_precision_stderr": 0.005059911825690109, "rougeL_recall": 0.19325765142384435, "rougeL_recall_stderr": 0.002374927639383697, "rougeLsum_fmeasure": 0.2287941438454128, "rougeLsum_fmeasure_stderr": 0.0024025488670924725, "rougeLsum_precision": 0.35265257546958945, "rougeLsum_precision_stderr": 0.005084624220690631, "rougeLsum_recall": 0.21792408382120357, "rougeLsum_recall_stderr": 0.002710638175002805}}, "3": {"generate_text_restaurant": {"bleu": 5.379158787794686, "bleu_stderr": 0.17424945572147568, "rouge1_fmeasure": 0.2739605028454004, "rouge1_fmeasure_stderr": 0.0028626358837710963, "rouge1_precision": 0.4200250914129759, "rouge1_precision_stderr": 0.0053484767449253675, "rouge1_recall": 0.2597005038015286, "rouge1_recall_stderr": 0.0031776678746421685, "rouge2_fmeasure": 0.10541398390697426, "rouge2_fmeasure_stderr": 0.0017164566544297254, "rouge2_precision": 0.2324625707379104, "rouge2_precision_stderr": 0.005656196308354222, "rouge2_recall": 0.09787654675007354, "rouge2_recall_stderr": 0.00178618058095944, "rougeL_fmeasure": 0.20932493009842154, "rougeL_fmeasure_stderr": 0.002213566067169264, "rougeL_precision": 0.3452442707098063, "rougeL_precision_stderr": 0.005326530824347986, "rougeL_recall": 0.19634967424253236, "rougeL_recall_stderr": 0.002444802090072814, "rougeLsum_fmeasure": 0.23343576076206798, "rougeLsum_fmeasure_stderr": 0.0025054329416814864, "rougeLsum_precision": 0.3730608496140118, "rougeLsum_precision_stderr": 0.0053445330283940886, "rougeLsum_recall": 0.21983351464384387, "rougeLsum_recall_stderr": 0.0027657542997588506}}, "4": {"generate_text_restaurant": {"bleu": 5.84362787810031, "bleu_stderr": 0.1914395641675779, "rouge1_fmeasure": 0.28912203831106437, "rouge1_fmeasure_stderr": 0.0028684342474448, "rouge1_precision": 0.44142915899786084, "rouge1_precision_stderr": 0.005252644410011952, "rouge1_recall": 0.27293406189445324, "rouge1_recall_stderr": 0.003231606561873733, "rouge2_fmeasure": 0.11600779243298241, "rouge2_fmeasure_stderr": 0.0017448325124731262, "rouge2_precision": 0.24580187764860698, "rouge2_precision_stderr": 0.005582820891133567, "rouge2_recall": 0.10804855284127729, "rouge2_recall_stderr": 0.0018386317913512528, "rougeL_fmeasure": 0.22136695075479842, "rougeL_fmeasure_stderr": 0.002213265282685222, "rougeL_precision": 0.36278920910440526, "rougeL_precision_stderr": 0.005259330590831443, "rougeL_recall": 0.20655546999122476, "rougeL_recall_stderr": 0.0024658407342331543, "rougeLsum_fmeasure": 0.24635463422951365, "rougeLsum_fmeasure_stderr": 0.002518259186545489, "rougeLsum_precision": 0.39113354412345547, "rougeLsum_precision_stderr": 0.005259888245133616, "rougeLsum_recall": 0.23109513502236428, "rougeLsum_recall_stderr": 0.0028128632311166086}}, "5": {"generate_text_restaurant": {"bleu": 6.294657081635081, "bleu_stderr": 0.1191423611800128, "rouge1_fmeasure": 0.30818385424543937, "rouge1_fmeasure_stderr": 0.002812315846665837, "rouge1_precision": 0.45758123798499606, "rouge1_precision_stderr": 0.005027609714045855, "rouge1_recall": 0.2870117768804813, "rouge1_recall_stderr": 0.0031304392663814677, "rouge2_fmeasure": 0.1273300920831121, "rouge2_fmeasure_stderr": 0.0017849338112142722, "rouge2_precision": 0.2503889688775632, "rouge2_precision_stderr": 0.00532362565564733, "rouge2_recall": 0.11655912503614715, "rouge2_recall_stderr": 0.0018305152372365434, "rougeL_fmeasure": 0.23900514298098396, "rougeL_fmeasure_stderr": 0.0022097628891594285, "rougeL_precision": 0.37623432283720026, "rougeL_precision_stderr": 0.005027601070585646, "rougeL_recall": 0.22058281726854637, "rougeL_recall_stderr": 0.0024416343969262534, "rougeLsum_fmeasure": 0.2631784707358199, "rougeLsum_fmeasure_stderr": 0.002487054103176312, "rougeLsum_precision": 0.40434981140634907, "rougeLsum_precision_stderr": 0.005043898533403243, "rougeLsum_recall": 0.24370773833649576, "rougeLsum_recall_stderr": 0.002739699465790519}}}, "gem_xsum": {"0": {"article_DOC_summary": {"bleu": 0.7848159984641091, "bleu_stderr": 0.0846489540307912, "rouge1_fmeasure": 0.13822546470552896, "rouge1_fmeasure_stderr": 0.0020817271615335853, "rouge1_precision": 0.09869862910594125, "rouge1_precision_stderr": 0.0015754263415516496, "rouge1_recall": 0.2425997427212717, "rouge1_recall_stderr": 0.0035498618411088337, "rouge2_fmeasure": 0.023697282994221247, "rouge2_fmeasure_stderr": 0.0009611791067872703, "rouge2_precision": 0.016787743878533688, "rouge2_precision_stderr": 0.0007005319097605839, "rouge2_recall": 0.0425780543002491, "rouge2_recall_stderr": 0.0017220443443167939, "rougeL_fmeasure": 0.12098743849059979, "rougeL_fmeasure_stderr": 0.001680519826816699, "rougeL_precision": 0.08626521539341878, "rougeL_precision_stderr": 0.0012705285495719658, "rougeL_recall": 0.21327598743091675, "rougeL_recall_stderr": 0.0029459890547047195, "rougeLsum_fmeasure": 0.1053525696001833, "rougeLsum_fmeasure_stderr": 0.001600085618320443, "rougeLsum_precision": 0.07499548048418175, "rougeLsum_precision_stderr": 0.0011973587779807702, "rougeLsum_recall": 0.18673351936586377, "rougeLsum_recall_stderr": 0.002877930418991892}}, "1": {"article_DOC_summary": {"bleu": 0.6629456628355466, "bleu_stderr": 0.08774497677853796, "rouge1_fmeasure": 0.12866565250951, "rouge1_fmeasure_stderr": 0.0019918374752407302, "rouge1_precision": 0.09124145037680485, "rouge1_precision_stderr": 0.0014659607841345699, "rouge1_recall": 0.22757570030500165, "rouge1_recall_stderr": 0.0034586902105503583, "rouge2_fmeasure": 0.018497303697898898, "rouge2_fmeasure_stderr": 0.0008688724913792904, "rouge2_precision": 0.012967504798466119, "rouge2_precision_stderr": 0.0006125196007516605, "rouge2_recall": 0.03365509386476815, "rouge2_recall_stderr": 0.0015985879929148613, "rougeL_fmeasure": 0.11258738658901131, "rougeL_fmeasure_stderr": 0.001654534085681258, "rougeL_precision": 0.07973413334544867, "rougeL_precision_stderr": 0.0012126850079835258, "rougeL_recall": 0.1999503525963445, "rougeL_recall_stderr": 0.0029346063767394658, "rougeLsum_fmeasure": 0.09952018094863402, "rougeLsum_fmeasure_stderr": 0.0015543045742524805, "rougeLsum_precision": 0.07040045782230749, "rougeLsum_precision_stderr": 0.0011336127776379584, "rougeLsum_recall": 0.17735154114603943, "rougeLsum_recall_stderr": 0.002793790877961365}}, "2": {"article_DOC_summary": {"bleu": 0.6581479118355196, "bleu_stderr": 0.07454636170059836, "rouge1_fmeasure": 0.1275054327542126, "rouge1_fmeasure_stderr": 0.001936094417525703, "rouge1_precision": 0.09013053440861082, "rouge1_precision_stderr": 0.0014220128061208542, "rouge1_recall": 0.2273610167464681, "rouge1_recall_stderr": 0.0034008282640079156, "rouge2_fmeasure": 0.019662620850184154, "rouge2_fmeasure_stderr": 0.0008838457269276937, "rouge2_precision": 0.013685249717276669, "rouge2_precision_stderr": 0.0006153358129211847, "rouge2_recall": 0.03651263650932684, "rouge2_recall_stderr": 0.0016893088610047168, "rougeL_fmeasure": 0.11364996341359528, "rougeL_fmeasure_stderr": 0.0016363233390032223, "rougeL_precision": 0.08023430784844289, "rougeL_precision_stderr": 0.0011971788003166785, "rougeL_recall": 0.20334042051960866, "rougeL_recall_stderr": 0.0029270688857344516, "rougeLsum_fmeasure": 0.09766604816138601, "rougeLsum_fmeasure_stderr": 0.001494448373327452, "rougeLsum_precision": 0.06885212236096724, "rougeLsum_precision_stderr": 0.0010822260185504432, "rougeLsum_recall": 0.17558641489646157, "rougeLsum_recall_stderr": 0.0027535532125502033}}, "3": {"article_DOC_summary": {"bleu": 0.6487530237798568, "bleu_stderr": 0.07015562797768161, "rouge1_fmeasure": 0.12223643758741752, "rouge1_fmeasure_stderr": 0.002043267213282596, "rouge1_precision": 0.08887731112301472, "rouge1_precision_stderr": 0.0016693801787118184, "rouge1_recall": 0.2137238957435145, "rouge1_recall_stderr": 0.0035351437827021116, "rouge2_fmeasure": 0.018803041332499517, "rouge2_fmeasure_stderr": 0.0009204376153200208, "rouge2_precision": 0.01336910380993121, "rouge2_precision_stderr": 0.0006644057446671918, "rouge2_recall": 0.034200003110033475, "rouge2_recall_stderr": 0.001715535153457774, "rougeL_fmeasure": 0.10976787111848983, "rougeL_fmeasure_stderr": 0.001747164342136605, "rougeL_precision": 0.07951277816840352, "rougeL_precision_stderr": 0.0013813570731518456, "rougeL_recall": 0.1929746396810042, "rougeL_recall_stderr": 0.0031195403408695475, "rougeLsum_fmeasure": 0.09547379870346774, "rougeLsum_fmeasure_stderr": 0.0015781898824613876, "rougeLsum_precision": 0.0692667028628289, "rougeLsum_precision_stderr": 0.0012719926110399762, "rougeLsum_recall": 0.16841312507750444, "rougeLsum_recall_stderr": 0.0028632604489444353}}, "4": {"article_DOC_summary": {"bleu": 0.31677978361218245, "bleu_stderr": 0.11491101515831749, "rouge1_fmeasure": 0.0352935136087583, "rouge1_fmeasure_stderr": 0.002067265021549025, "rouge1_precision": 0.030778909853395358, "rouge1_precision_stderr": 0.0020706771099415055, "rouge1_recall": 0.05446169618855107, "rouge1_recall_stderr": 0.0031240949944244803, "rouge2_fmeasure": 0.005563844272859168, "rouge2_fmeasure_stderr": 0.0005736273252218394, "rouge2_precision": 0.004626594678435454, "rouge2_precision_stderr": 0.0005432919775929613, "rouge2_recall": 0.008754579533738186, "rouge2_recall_stderr": 0.0008926051691577739, "rougeL_fmeasure": 0.030796858749521736, "rougeL_fmeasure_stderr": 0.0017427639473783613, "rougeL_precision": 0.026771846295171677, "rougeL_precision_stderr": 0.001757008435057672, "rougeL_recall": 0.04820099757783116, "rougeL_recall_stderr": 0.002741549258464254, "rougeLsum_fmeasure": 0.02795059198035774, "rougeLsum_fmeasure_stderr": 0.0016496415851520105, "rougeLsum_precision": 0.024799039714845435, "rougeLsum_precision_stderr": 0.0017459449627102337, "rougeLsum_recall": 0.043284204930067245, "rougeLsum_recall_stderr": 0.0025292545975519414}}, "5": {"article_DOC_summary": {"bleu": 5.0129268480742525e-39, "bleu_stderr": 2.561058897904247e-33, "rouge1_fmeasure": 0.0022773127753522747, "rouge1_fmeasure_stderr": 0.00063421295615357, "rouge1_precision": 0.0024889331628189042, "rouge1_precision_stderr": 0.0006815397373640728, "rouge1_recall": 0.002181607723763231, "rouge1_recall_stderr": 0.0006183413432850734, "rouge2_fmeasure": 0.00043251733980451243, "rouge2_fmeasure_stderr": 0.0001624532835097625, "rouge2_precision": 0.0005040504428810351, "rouge2_precision_stderr": 0.00018325075012185258, "rouge2_recall": 0.0003980023860711985, "rouge2_recall_stderr": 0.00015801551672316093, "rougeL_fmeasure": 0.001966631793324211, "rougeL_fmeasure_stderr": 0.0005373577051134612, "rougeL_precision": 0.002154819197651723, "rougeL_precision_stderr": 0.0005785407429483231, "rougeL_recall": 0.00188617310535414, "rougeL_recall_stderr": 0.0005267417519795776, "rougeLsum_fmeasure": 0.0019792726415445738, "rougeLsum_fmeasure_stderr": 0.0005523755455290908, "rougeLsum_precision": 0.002154819197651723, "rougeLsum_precision_stderr": 0.000586342779903712, "rougeLsum_recall": 0.0019061538009282621, "rougeLsum_recall_stderr": 0.0005449980000845078}}}} |