{"GEM/web_nlg_en": {"0": {"PALM_prompt": {"bleu": 0.4255419689866024, "bleu_stderr": 0.04553671379431864, "rouge1_fmeasure": 0.11709985442438758, "rouge1_fmeasure_stderr": 0.0019235811070200824, "rouge1_precision": 0.07691162970808266, "rouge1_precision_stderr": 0.0015499735187471276, "rouge1_recall": 0.3361349423128226, "rouge1_recall_stderr": 0.004717900225751208, "rouge2_fmeasure": 0.05502825027290272, "rouge2_fmeasure_stderr": 0.0012188176771805944, "rouge2_precision": 0.03634094203430491, "rouge2_precision_stderr": 0.0010568736203451017, "rouge2_recall": 0.16382279258438331, "rouge2_recall_stderr": 0.0032641856127605708, "rougeL_fmeasure": 0.11222201441152387, "rougeL_fmeasure_stderr": 0.0017898759559440783, "rougeL_precision": 0.07347783656701605, "rougeL_precision_stderr": 0.0014400832686900517, "rougeL_recall": 0.325262737431151, "rougeL_recall_stderr": 0.0046026209075170806, "rougeLsum_fmeasure": 0.1102576752933881, "rougeLsum_fmeasure_stderr": 0.0017934408668905857, "rougeLsum_precision": 0.07247687306153981, "rougeLsum_precision_stderr": 0.0014666193171867594, "rougeLsum_recall": 0.31667827309434965, "rougeLsum_recall_stderr": 0.004394255465374989}}, "1": {"PALM_prompt": {"bleu": 0.4375148581871164, "bleu_stderr": 0.043362378909165875, "rouge1_fmeasure": 0.12097522483010485, "rouge1_fmeasure_stderr": 0.002202684090770471, "rouge1_precision": 0.084573986124589, "rouge1_precision_stderr": 0.0022156458659289445, "rouge1_recall": 0.32974434511651185, "rouge1_recall_stderr": 0.004760360381005011, "rouge2_fmeasure": 0.05811058513302895, "rouge2_fmeasure_stderr": 0.0014298876541859705, "rouge2_precision": 0.040740790020171655, "rouge2_precision_stderr": 0.0014239356080917533, "rouge2_recall": 0.16249675831000945, "rouge2_recall_stderr": 0.003343995882368083, "rougeL_fmeasure": 0.11484527988661357, "rougeL_fmeasure_stderr": 0.0020020380133125328, "rougeL_precision": 0.07979616615847458, "rougeL_precision_stderr": 0.0020050186616118407, "rougeL_recall": 0.31708796648649956, "rougeL_recall_stderr": 0.004617552099836135, "rougeLsum_fmeasure": 0.11394268478061556, "rougeLsum_fmeasure_stderr": 0.0020477402089164776, "rougeLsum_precision": 0.07967262232949184, "rougeLsum_precision_stderr": 0.002074014298894367, "rougeLsum_recall": 0.3110596157987853, "rougeLsum_recall_stderr": 0.004435869800526469}}, "2": {"PALM_prompt": {"bleu": 0.43895421656508316, "bleu_stderr": 0.03560314454345476, "rouge1_fmeasure": 0.11837525964996032, "rouge1_fmeasure_stderr": 0.0020736790107389433, "rouge1_precision": 0.07893892499245164, "rouge1_precision_stderr": 0.0017559781579577936, "rouge1_recall": 0.33147399394577687, "rouge1_recall_stderr": 0.004792853072557146, "rouge2_fmeasure": 0.05685211598675336, "rouge2_fmeasure_stderr": 0.0013242460972892624, "rouge2_precision": 0.03778130469895934, "rouge2_precision_stderr": 0.0011220289463223655, "rouge2_recall": 0.16607823925825196, "rouge2_recall_stderr": 0.003428415308098998, "rougeL_fmeasure": 0.11305526526705706, "rougeL_fmeasure_stderr": 0.0019076101565052952, "rougeL_precision": 0.0751384880267446, "rougeL_precision_stderr": 0.0016250699836019358, "rougeL_recall": 0.31955459951422993, "rougeL_recall_stderr": 0.004633747457550051, "rougeLsum_fmeasure": 0.11212261864528106, "rougeLsum_fmeasure_stderr": 0.0019332204600801869, "rougeLsum_precision": 0.07484212840598793, "rougeLsum_precision_stderr": 0.0016673128268097014, "rougeLsum_recall": 0.31478623106918857, "rougeLsum_recall_stderr": 0.004462671481456754}}, "3": {"PALM_prompt": {"bleu": 0.4055173976621406, "bleu_stderr": 0.03388942315369854, "rouge1_fmeasure": 0.11521270106633405, "rouge1_fmeasure_stderr": 0.0020223822680663353, "rouge1_precision": 0.07564013742377862, "rouge1_precision_stderr": 0.001624130926371493, "rouge1_recall": 0.32832027029775396, "rouge1_recall_stderr": 0.004754946563417434, "rouge2_fmeasure": 0.054818451753863656, "rouge2_fmeasure_stderr": 0.0012891162497869618, "rouge2_precision": 0.03600203329160531, "rouge2_precision_stderr": 0.0010611943954759993, "rouge2_recall": 0.16248350820338053, "rouge2_recall_stderr": 0.003392520543251839, "rougeL_fmeasure": 0.11001628031350326, "rougeL_fmeasure_stderr": 0.0018702505486722842, "rougeL_precision": 0.07201677299268112, "rougeL_precision_stderr": 0.0015006281609086204, "rougeL_recall": 0.31619306971917027, "rougeL_recall_stderr": 0.004595788592278942, "rougeLsum_fmeasure": 0.10876033036378392, "rougeLsum_fmeasure_stderr": 0.00187477057348602, "rougeLsum_precision": 0.07139551984673621, "rougeLsum_precision_stderr": 0.001521052983920996, "rougeLsum_recall": 0.3106722185590567, "rougeLsum_recall_stderr": 0.004410951996082152}}, "4": {"PALM_prompt": {"bleu": 0.4219802204390914, "bleu_stderr": 0.035062189637818944, "rouge1_fmeasure": 0.11435782016646073, "rouge1_fmeasure_stderr": 0.0019930832962392476, "rouge1_precision": 0.07604999251191036, "rouge1_precision_stderr": 0.001694487867306116, "rouge1_recall": 0.32739311904589957, "rouge1_recall_stderr": 0.004733990565227727, "rouge2_fmeasure": 0.05493385212823661, "rouge2_fmeasure_stderr": 0.0012747653539780157, "rouge2_precision": 0.03608787195276645, "rouge2_precision_stderr": 0.0009682458617317419, "rouge2_recall": 0.16298585196913531, "rouge2_recall_stderr": 0.0033617720441310407, "rougeL_fmeasure": 0.1087646065353738, "rougeL_fmeasure_stderr": 0.0018365048381652636, "rougeL_precision": 0.0719402479836372, "rougeL_precision_stderr": 0.0015114912843032233, "rougeL_recall": 0.3140568060068406, "rougeL_recall_stderr": 0.004584266596245509, "rougeLsum_fmeasure": 0.10814461597064734, "rougeLsum_fmeasure_stderr": 0.0018690945883989335, "rougeLsum_precision": 0.0717813619994629, "rougeLsum_precision_stderr": 0.0015531796251007297, "rougeLsum_recall": 0.30959297417269843, "rougeLsum_recall_stderr": 0.004389147529346589}}, "5": {"PALM_prompt": {"bleu": 0.41421236223783364, "bleu_stderr": 0.03144881485668538, "rouge1_fmeasure": 0.11235776546508958, "rouge1_fmeasure_stderr": 0.0019443755895376892, "rouge1_precision": 0.07376815882972376, "rouge1_precision_stderr": 0.0015413873275619697, "rouge1_recall": 0.3269107430349855, "rouge1_recall_stderr": 0.004768390550563892, "rouge2_fmeasure": 0.05370114479085305, "rouge2_fmeasure_stderr": 0.0012337413746734015, "rouge2_precision": 0.03507239155053733, "rouge2_precision_stderr": 0.000919535201162236, "rouge2_recall": 0.16374442513917464, "rouge2_recall_stderr": 0.003472789622253923, "rougeL_fmeasure": 0.10679593308879384, "rougeL_fmeasure_stderr": 0.0017931240322613966, "rougeL_precision": 0.06977608287770509, "rougeL_precision_stderr": 0.001374956676465801, "rougeL_recall": 0.31368077194090394, "rougeL_recall_stderr": 0.004624757562111944, "rougeLsum_fmeasure": 0.1058735384538628, "rougeLsum_fmeasure_stderr": 0.001807570321110346, "rougeLsum_precision": 0.06944197659188452, "rougeLsum_precision_stderr": 0.001414266115795263, "rougeLsum_recall": 0.30880609903141404, "rougeLsum_recall_stderr": 0.004454929611901481}}}, "GEM/wiki_lingua_en": {"0": {"tldr_en": {"bleu": 0.0489790785966099, "bleu_stderr": 0.006779339030578523, "rouge1_fmeasure": 0.070437989859743, "rouge1_fmeasure_stderr": 0.0010312902668252013, "rouge1_precision": 0.06498870832691263, "rouge1_precision_stderr": 0.0010723261619156347, "rouge1_recall": 0.09208329086891458, "rouge1_recall_stderr": 0.0014107679511711905, "rouge2_fmeasure": 0.0032754676506289828, "rouge2_fmeasure_stderr": 0.00018463100249520333, "rouge2_precision": 0.0031259330192821917, "rouge2_precision_stderr": 0.0001792020567470567, "rouge2_recall": 0.0041562592064827136, "rouge2_recall_stderr": 0.0002654234746028053, "rougeL_fmeasure": 0.0638808755302006, "rougeL_fmeasure_stderr": 0.0008731247333910541, "rougeL_precision": 0.058599346602679785, "rougeL_precision_stderr": 0.0008924974727175551, "rougeL_recall": 0.08428848354699885, "rougeL_recall_stderr": 0.001258671638105778, "rougeLsum_fmeasure": 0.06702516127871343, "rougeLsum_fmeasure_stderr": 0.0009693030073720331, "rougeLsum_precision": 0.06184900174439773, "rougeLsum_precision_stderr": 0.001011647200269575, "rougeLsum_recall": 0.0878197954616511, "rougeLsum_recall_stderr": 0.0013420548769352185}}, "1": {"tldr_en": {"bleu": 0.19435530388407438, "bleu_stderr": 0.027474135486464886, "rouge1_fmeasure": 0.08534345009310793, "rouge1_fmeasure_stderr": 0.0012180416276689969, "rouge1_precision": 0.07527407433133869, "rouge1_precision_stderr": 0.0012353167292243439, "rouge1_recall": 0.11879070038037605, "rouge1_recall_stderr": 0.001666703743793988, "rouge2_fmeasure": 0.004199685382427501, "rouge2_fmeasure_stderr": 0.0002477120467452383, "rouge2_precision": 0.0037334174812980337, "rouge2_precision_stderr": 0.00022288691443581962, "rouge2_recall": 0.005917125245253962, "rouge2_recall_stderr": 0.0003984864275118756, "rougeL_fmeasure": 0.0779496715247138, "rougeL_fmeasure_stderr": 0.00102035551714523, "rougeL_precision": 0.06809342794848382, "rougeL_precision_stderr": 0.0010182876153051106, "rougeL_recall": 0.11003512325420707, "rougeL_recall_stderr": 0.0014770539784070803, "rougeLsum_fmeasure": 0.08013661978467537, "rougeLsum_fmeasure_stderr": 0.0011236586288798575, "rougeLsum_precision": 0.07054606286211522, "rougeLsum_precision_stderr": 0.001139963924498013, "rougeLsum_recall": 0.11204758740190628, "rougeLsum_recall_stderr": 0.0015572733289150008}}, "2": {"tldr_en": {"bleu": 0.26166447349576716, "bleu_stderr": 0.02664531207793444, "rouge1_fmeasure": 0.09264326558315315, "rouge1_fmeasure_stderr": 0.0012341782878536826, "rouge1_precision": 0.08188916742697006, "rouge1_precision_stderr": 0.0012604740470487253, "rouge1_recall": 0.12863501946937672, "rouge1_recall_stderr": 0.0017306118753458995, "rouge2_fmeasure": 0.004799135265562465, "rouge2_fmeasure_stderr": 0.0003258383358742087, "rouge2_precision": 0.00417689519312021, "rouge2_precision_stderr": 0.00027799524088823336, "rouge2_recall": 0.0070394381668830155, "rouge2_recall_stderr": 0.000549533007866243, "rougeL_fmeasure": 0.08530978440523501, "rougeL_fmeasure_stderr": 0.0010419970840251892, "rougeL_precision": 0.07469229492018686, "rougeL_precision_stderr": 0.0010462849454463273, "rougeL_recall": 0.11996588099996168, "rougeL_recall_stderr": 0.0015431639618236344, "rougeLsum_fmeasure": 0.08652135177894667, "rougeLsum_fmeasure_stderr": 0.0011347677035999774, "rougeLsum_precision": 0.07637785471073269, "rougeLsum_precision_stderr": 0.0011637595201347114, "rougeLsum_recall": 0.12067856570386956, "rougeLsum_recall_stderr": 0.0016119906969829974}}, "3": {"tldr_en": {"bleu": 0.35676801434287403, "bleu_stderr": 0.04322442294335073, "rouge1_fmeasure": 0.08496018846964883, "rouge1_fmeasure_stderr": 0.0013534144382857925, "rouge1_precision": 0.07918559281464797, "rouge1_precision_stderr": 0.0015732102907079421, "rouge1_recall": 0.11713311231879246, "rouge1_recall_stderr": 0.0018694365480156567, "rouge2_fmeasure": 0.005617198716065193, "rouge2_fmeasure_stderr": 0.0003504250975971709, "rouge2_precision": 0.005450855204647191, "rouge2_precision_stderr": 0.00042451344437272563, "rouge2_recall": 0.00786801734624306, "rouge2_recall_stderr": 0.0005418684959080103, "rougeL_fmeasure": 0.07686453493425864, "rougeL_fmeasure_stderr": 0.0011252346058277117, "rougeL_precision": 0.07101336043004314, "rougeL_precision_stderr": 0.001347924853763445, "rougeL_recall": 0.10774352434928229, "rougeL_recall_stderr": 0.0016488819148997246, "rougeLsum_fmeasure": 0.07875700339703082, "rougeLsum_fmeasure_stderr": 0.0012486260433925756, "rougeLsum_precision": 0.07334057105853452, "rougeLsum_precision_stderr": 0.00146993475075726, "rougeLsum_recall": 0.108988272664584, "rougeLsum_recall_stderr": 0.0017377582372509691}}, "4": {"tldr_en": {"bleu": 0.1251055397122511, "bleu_stderr": 0.014484092743724803, "rouge1_fmeasure": 0.03139283202672829, "rouge1_fmeasure_stderr": 0.0012003402420825678, "rouge1_precision": 0.030329065224279812, "rouge1_precision_stderr": 0.001330278405910414, "rouge1_recall": 0.04517297214250825, "rouge1_recall_stderr": 0.001758818657887946, "rouge2_fmeasure": 0.0029260675465866874, "rouge2_fmeasure_stderr": 0.00030134314126436455, "rouge2_precision": 0.002783763831604278, "rouge2_precision_stderr": 0.0003242150810229513, "rouge2_recall": 0.0044964737985171525, "rouge2_recall_stderr": 0.0005138289413575867, "rougeL_fmeasure": 0.02785801817001536, "rougeL_fmeasure_stderr": 0.0010086311227078628, "rougeL_precision": 0.02657200435528566, "rougeL_precision_stderr": 0.0011035850530213228, "rougeL_recall": 0.04083946585151625, "rougeL_recall_stderr": 0.001540836819231046, "rougeLsum_fmeasure": 0.028747368698632404, "rougeLsum_fmeasure_stderr": 0.0010989439749250103, "rougeLsum_precision": 0.027847356181606008, "rougeLsum_precision_stderr": 0.0012301635576539068, "rougeLsum_recall": 0.041473623387033184, "rougeLsum_recall_stderr": 0.0016278414776434958}}, "5": {"tldr_en": {"bleu": 1.608658724355054e-07, "bleu_stderr": 4.1367178740967643e-07, "rouge1_fmeasure": 0.005312217579045015, "rouge1_fmeasure_stderr": 0.0005447805558351684, "rouge1_precision": 0.00546467811919465, "rouge1_precision_stderr": 0.0006252571429574801, "rouge1_recall": 0.007588094977815991, "rouge1_recall_stderr": 0.0007854778326407263, "rouge2_fmeasure": 0.0004573993622119604, "rouge2_fmeasure_stderr": 9.93009701272525e-05, "rouge2_precision": 0.00044339189228553947, "rouge2_precision_stderr": 9.961401108641653e-05, "rouge2_recall": 0.0006655482990875535, "rouge2_recall_stderr": 0.0001814575634003083, "rougeL_fmeasure": 0.0045916498026018614, "rougeL_fmeasure_stderr": 0.0004489570697479766, "rougeL_precision": 0.00461981647245416, "rougeL_precision_stderr": 0.0005033099668854365, "rougeL_recall": 0.006788021218410852, "rougeL_recall_stderr": 0.0006881154075077389, "rougeLsum_fmeasure": 0.004852566252508574, "rougeLsum_fmeasure_stderr": 0.0004994751682757694, "rougeLsum_precision": 0.004946550238006405, "rougeLsum_precision_stderr": 0.0005649935199743343, "rougeLsum_recall": 0.007016292908843859, "rougeLsum_recall_stderr": 0.0007337348506316745}}}, "e2e_nlg_cleaned": {"0": {"generate_text_restaurant": {"bleu": 0.06113312558172764, "bleu_stderr": 0.01575172189851365, "rouge1_fmeasure": 0.018526574610266466, "rouge1_fmeasure_stderr": 0.0004491583645956695, "rouge1_precision": 0.014710592817317623, "rouge1_precision_stderr": 0.0003529315721245975, "rouge1_recall": 0.026426487712639557, "rouge1_recall_stderr": 0.0006726265968105224, "rouge2_fmeasure": 0.0006359667540750598, "rouge2_fmeasure_stderr": 0.0001041733500992725, "rouge2_precision": 0.0004867368803311285, "rouge2_precision_stderr": 7.864693694964923e-05, "rouge2_recall": 0.0009789004289938045, "rouge2_recall_stderr": 0.0001645546445630159, "rougeL_fmeasure": 0.018499794220557017, "rougeL_fmeasure_stderr": 0.00044650709340406276, "rougeL_precision": 0.014689240988132256, "rougeL_precision_stderr": 0.00035074403880002916, "rougeL_recall": 0.026390402516371297, "rougeL_recall_stderr": 0.0006695145672545542, "rougeLsum_fmeasure": 0.017471035147790994, "rougeLsum_fmeasure_stderr": 0.0003971392931020627, "rougeLsum_precision": 0.013873433046158122, "rougeLsum_precision_stderr": 0.0003117470202763751, "rougeLsum_recall": 0.024938658187947462, "rougeLsum_recall_stderr": 0.0005998309209761277}}, "1": {"generate_text_restaurant": {"bleu": 5.8201208498355745, "bleu_stderr": 0.07918003623517482, "rouge1_fmeasure": 0.2978972679324119, "rouge1_fmeasure_stderr": 0.001938270939643692, "rouge1_precision": 0.25691930916492756, "rouge1_precision_stderr": 0.002584112631865945, "rouge1_recall": 0.4396823419994151, "rouge1_recall_stderr": 0.002924006390564013, "rouge2_fmeasure": 0.12463514115806919, "rouge2_fmeasure_stderr": 0.001299783869728999, "rouge2_precision": 0.10986735481075849, "rouge2_precision_stderr": 0.0016737706226266926, "rouge2_recall": 0.18795573844856492, "rouge2_recall_stderr": 0.0020345189689034695, "rougeL_fmeasure": 0.24464314098146767, "rougeL_fmeasure_stderr": 0.0014611191185898375, "rougeL_precision": 0.2108434140927592, "rougeL_precision_stderr": 0.0021087197045539206, "rougeL_recall": 0.3655838393962915, "rougeL_recall_stderr": 0.0025164390500460707, "rougeLsum_fmeasure": 0.2473804112744828, "rougeLsum_fmeasure_stderr": 0.0017953159637369525, "rougeLsum_precision": 0.2157653393823411, "rougeLsum_precision_stderr": 0.0024335105491588797, "rougeLsum_recall": 0.36407468797098697, "rougeLsum_recall_stderr": 0.0026761965498774284}}, "2": {"generate_text_restaurant": {"bleu": 6.8213920736753035, "bleu_stderr": 0.09269849650267996, "rouge1_fmeasure": 0.3268772449979945, "rouge1_fmeasure_stderr": 0.002037185940562139, "rouge1_precision": 0.29394430959429885, "rouge1_precision_stderr": 0.0029349960483685197, "rouge1_recall": 0.44889829988946167, "rouge1_recall_stderr": 0.0026008346109833076, "rouge2_fmeasure": 0.1463066245452882, "rouge2_fmeasure_stderr": 0.0014390553252013872, "rouge2_precision": 0.1343978103369073, "rouge2_precision_stderr": 0.0019313519405930251, "rouge2_recall": 0.20303674980966369, "rouge2_recall_stderr": 0.0019154842806783233, "rougeL_fmeasure": 0.25892225643390154, "rougeL_fmeasure_stderr": 0.00149376807780425, "rougeL_precision": 0.2299825363481501, "rougeL_precision_stderr": 0.0021765504098611448, "rougeL_recall": 0.36308738357631903, "rougeL_recall_stderr": 0.0023177876330520717, "rougeLsum_fmeasure": 0.2738908855936707, "rougeLsum_fmeasure_stderr": 0.0019355452082937584, "rougeLsum_precision": 0.24820013238470168, "rougeLsum_precision_stderr": 0.0027165241805849048, "rougeLsum_recall": 0.37474754473838195, "rougeLsum_recall_stderr": 0.0024667758421094027}}, "3": {"generate_text_restaurant": {"bleu": 6.942009450714699, "bleu_stderr": 0.04290812234950382, "rouge1_fmeasure": 0.33114374289634996, "rouge1_fmeasure_stderr": 0.0019963064576782263, "rouge1_precision": 0.30906162515100283, "rouge1_precision_stderr": 0.0030674030901339717, "rouge1_recall": 0.44080702325897825, "rouge1_recall_stderr": 0.0026014559705604258, "rouge2_fmeasure": 0.14999298186863755, "rouge2_fmeasure_stderr": 0.0014464336948624026, "rouge2_precision": 0.14318958988373076, "rouge2_precision_stderr": 0.0020155780018855157, "rouge2_recall": 0.2013842488461, "rouge2_recall_stderr": 0.0019010681475652355, "rougeL_fmeasure": 0.26265901338393766, "rougeL_fmeasure_stderr": 0.0014797491179515284, "rougeL_precision": 0.24226611193261477, "rougeL_precision_stderr": 0.002287690467824282, "rougeL_recall": 0.35660966290964163, "rougeL_recall_stderr": 0.002307251432723998, "rougeLsum_fmeasure": 0.27712766233037806, "rougeLsum_fmeasure_stderr": 0.0019244037043805748, "rougeLsum_precision": 0.26123456663930006, "rougeLsum_precision_stderr": 0.0028608851643456765, "rougeLsum_recall": 0.3668591988145458, "rougeLsum_recall_stderr": 0.0024536597226958376}}, "4": {"generate_text_restaurant": {"bleu": 7.50519306139533, "bleu_stderr": 0.12141535391721209, "rouge1_fmeasure": 0.35014858130045096, "rouge1_fmeasure_stderr": 0.0020798805965393467, "rouge1_precision": 0.3382900801328086, "rouge1_precision_stderr": 0.0031870177107722864, "rouge1_recall": 0.43823825667258115, "rouge1_recall_stderr": 0.0025150913221159833, "rouge2_fmeasure": 0.1583408367591379, "rouge2_fmeasure_stderr": 0.0015305939174917813, "rouge2_precision": 0.1562658891246859, "rouge2_precision_stderr": 0.002090506730559318, "rouge2_recall": 0.199427975848365, "rouge2_recall_stderr": 0.0018891086525461194, "rougeL_fmeasure": 0.26748399521207994, "rougeL_fmeasure_stderr": 0.001534553168600716, "rougeL_precision": 0.25544052575853743, "rougeL_precision_stderr": 0.0023438446152810907, "rougeL_recall": 0.34203035767325535, "rougeL_recall_stderr": 0.0022562591465260075, "rougeLsum_fmeasure": 0.2924671515205407, "rougeLsum_fmeasure_stderr": 0.001988178356101477, "rougeLsum_precision": 0.2842748733336647, "rougeLsum_precision_stderr": 0.002916261382644648, "rougeLsum_recall": 0.36471610019410694, "rougeLsum_recall_stderr": 0.002385680406071139}}, "5": {"generate_text_restaurant": {"bleu": 8.909934598498245, "bleu_stderr": 0.11355686792329017, "rouge1_fmeasure": 0.3791546852434602, "rouge1_fmeasure_stderr": 0.0020200693077103015, "rouge1_precision": 0.37588510027488736, "rouge1_precision_stderr": 0.0028779178551135293, "rouge1_recall": 0.43674914985883706, "rouge1_recall_stderr": 0.0024638439091214433, "rouge2_fmeasure": 0.1726081857656977, "rouge2_fmeasure_stderr": 0.0015716694288982242, "rouge2_precision": 0.17238666817345458, "rouge2_precision_stderr": 0.0019278848044138694, "rouge2_recall": 0.19980355257879728, "rouge2_recall_stderr": 0.0018510324254879687, "rougeL_fmeasure": 0.28073901470903295, "rougeL_fmeasure_stderr": 0.001614330726795435, "rougeL_precision": 0.2762695240145616, "rougeL_precision_stderr": 0.0021890512735288354, "rougeL_recall": 0.3283605962966383, "rougeL_recall_stderr": 0.002209924055940966, "rougeLsum_fmeasure": 0.32085059046180675, "rougeLsum_fmeasure_stderr": 0.0019675465538199436, "rougeLsum_precision": 0.3186956691262859, "rougeLsum_precision_stderr": 0.0026612676205351017, "rougeLsum_recall": 0.36923270586040546, "rougeLsum_recall_stderr": 0.0023640716126389163}}}, "gem_xsum": {"0": {"article_DOC_summary": {"bleu": 0.06212804417145812, "bleu_stderr": 0.011971318709799528, "rouge1_fmeasure": 0.10102973537775274, "rouge1_fmeasure_stderr": 0.0014355102738807643, "rouge1_precision": 0.07192798210581976, "rouge1_precision_stderr": 0.0010917008658073372, "rouge1_recall": 0.17738230504867103, "rouge1_recall_stderr": 0.0023612645642943995, "rouge2_fmeasure": 0.006073255625355645, "rouge2_fmeasure_stderr": 0.0003809878915466881, "rouge2_precision": 0.004288158761745872, "rouge2_precision_stderr": 0.0002700287405913071, "rouge2_recall": 0.010847911832547128, "rouge2_recall_stderr": 0.0006940494564969847, "rougeL_fmeasure": 0.08708997150339674, "rougeL_fmeasure_stderr": 0.0011768137916529835, "rougeL_precision": 0.061860157155504046, "rougeL_precision_stderr": 0.0008875877382502058, "rougeL_recall": 0.15379181870207026, "rougeL_recall_stderr": 0.0019969008216420697, "rougeLsum_fmeasure": 0.08656040328674863, "rougeLsum_fmeasure_stderr": 0.001216757422923546, "rougeLsum_precision": 0.061491345289910605, "rougeLsum_precision_stderr": 0.0009161557912449834, "rougeLsum_recall": 0.15291182401919987, "rougeLsum_recall_stderr": 0.0020815555284572295}}, "1": {"article_DOC_summary": {"bleu": 0.07413849235928043, "bleu_stderr": 0.01976351303187912, "rouge1_fmeasure": 0.09194088936961643, "rouge1_fmeasure_stderr": 0.0013783104926480619, "rouge1_precision": 0.06505394396909397, "rouge1_precision_stderr": 0.0010345000379844767, "rouge1_recall": 0.16367528098007583, "rouge1_recall_stderr": 0.002310164884000985, "rouge2_fmeasure": 0.005968104627521815, "rouge2_fmeasure_stderr": 0.0003824456236105915, "rouge2_precision": 0.004211301109017673, "rouge2_precision_stderr": 0.0002712127686911097, "rouge2_recall": 0.010640558564493393, "rouge2_recall_stderr": 0.0006925012884316564, "rougeL_fmeasure": 0.08242443142898405, "rougeL_fmeasure_stderr": 0.0011823524939069798, "rougeL_precision": 0.05824585599255965, "rougeL_precision_stderr": 0.0008851968023125635, "rougeL_recall": 0.14716783464641015, "rougeL_recall_stderr": 0.0020015127545039207, "rougeLsum_fmeasure": 0.07935310191197463, "rougeLsum_fmeasure_stderr": 0.0011428193509701132, "rougeLsum_precision": 0.05601648748687626, "rougeLsum_precision_stderr": 0.0008514365416564917, "rougeLsum_recall": 0.14220135901573897, "rougeLsum_recall_stderr": 0.001984633594195078}}, "2": {"article_DOC_summary": {"bleu": 0.10304318645626095, "bleu_stderr": 0.02590406105837305, "rouge1_fmeasure": 0.08444066513722136, "rouge1_fmeasure_stderr": 0.0014657483966925, "rouge1_precision": 0.05970144726407935, "rouge1_precision_stderr": 0.0010808131881698626, "rouge1_recall": 0.15032918128991743, "rouge1_recall_stderr": 0.0025278263617417337, "rouge2_fmeasure": 0.00672052705909708, "rouge2_fmeasure_stderr": 0.0004405404886083871, "rouge2_precision": 0.004734886121730911, "rouge2_precision_stderr": 0.00030986275466350464, "rouge2_recall": 0.012150770146827796, "rouge2_recall_stderr": 0.0008496354899205403, "rougeL_fmeasure": 0.07722118221070728, "rougeL_fmeasure_stderr": 0.0012763559941414496, "rougeL_precision": 0.0545565395708172, "rougeL_precision_stderr": 0.0009399168505439712, "rougeL_recall": 0.13773639312565078, "rougeL_recall_stderr": 0.0022148411509370623, "rougeLsum_fmeasure": 0.07391840483447609, "rougeLsum_fmeasure_stderr": 0.0012190936937503734, "rougeLsum_precision": 0.05216833775619172, "rougeLsum_precision_stderr": 0.0008929985372574541, "rougeLsum_recall": 0.1322606270465344, "rougeLsum_recall_stderr": 0.002157181329873677}}, "3": {"article_DOC_summary": {"bleu": 0.22427754093829802, "bleu_stderr": 0.034552127103896886, "rouge1_fmeasure": 0.07896539889705549, "rouge1_fmeasure_stderr": 0.0016540196570312491, "rouge1_precision": 0.05815946761165747, "rouge1_precision_stderr": 0.001380812200134281, "rouge1_recall": 0.13549250184452813, "rouge1_recall_stderr": 0.0027208611626966957, "rouge2_fmeasure": 0.006943244163002554, "rouge2_fmeasure_stderr": 0.0005154856926939987, "rouge2_precision": 0.0051386914240500875, "rouge2_precision_stderr": 0.00040605626704506864, "rouge2_recall": 0.01205042518636505, "rouge2_recall_stderr": 0.0008745757698404825, "rougeL_fmeasure": 0.07314249899760741, "rougeL_fmeasure_stderr": 0.0014324655345679602, "rougeL_precision": 0.05358406774115243, "rougeL_precision_stderr": 0.0011716163642417996, "rougeL_recall": 0.1260775001189485, "rougeL_recall_stderr": 0.0023957295090012844, "rougeLsum_fmeasure": 0.06851629797589617, "rougeLsum_fmeasure_stderr": 0.0013679563501104437, "rougeLsum_precision": 0.050377295082503465, "rougeLsum_precision_stderr": 0.0011611779272879762, "rougeLsum_recall": 0.11809508568654702, "rougeLsum_recall_stderr": 0.0022806675190111193}}, "4": {"article_DOC_summary": {"bleu": 0.20252486202824954, "bleu_stderr": 0.0451733186712267, "rouge1_fmeasure": 0.024599325309196316, "rouge1_fmeasure_stderr": 0.0015226073238554963, "rouge1_precision": 0.02214933884629678, "rouge1_precision_stderr": 0.0016410873850719364, "rouge1_recall": 0.03772298255486349, "rouge1_recall_stderr": 0.0023501327317525427, "rouge2_fmeasure": 0.0026139422307253986, "rouge2_fmeasure_stderr": 0.00037040229047969556, "rouge2_precision": 0.0020692193883074857, "rouge2_precision_stderr": 0.0003062075285410719, "rouge2_recall": 0.004199075477211875, "rouge2_recall_stderr": 0.0006094344180167119, "rougeL_fmeasure": 0.022646617016988464, "rougeL_fmeasure_stderr": 0.0013512159194685597, "rougeL_precision": 0.020330750956918043, "rougeL_precision_stderr": 0.001451030088641699, "rougeL_recall": 0.03484763177326402, "rougeL_recall_stderr": 0.0020977393818014333, "rougeLsum_fmeasure": 0.020880117459677255, "rougeLsum_fmeasure_stderr": 0.0012684304431225134, "rougeLsum_precision": 0.01900606349570929, "rougeLsum_precision_stderr": 0.0014097333664542056, "rougeLsum_recall": 0.031891578587321945, "rougeLsum_recall_stderr": 0.0019321769969979038}}, "5": {"article_DOC_summary": {"bleu": 1.6165965257139506e-38, "bleu_stderr": 3.022588684192216e-34, "rouge1_fmeasure": 0.0018102133465432942, "rouge1_fmeasure_stderr": 0.0004995256780505414, "rouge1_precision": 0.0019620307874586742, "rouge1_precision_stderr": 0.0005451730856114239, "rouge1_recall": 0.0017379629055225318, "rouge1_recall_stderr": 0.0004813113588013356, "rouge2_fmeasure": 0.00010730891049598514, "rouge2_fmeasure_stderr": 7.588337415201644e-05, "rouge2_precision": 0.00010762452493862039, "rouge2_precision_stderr": 7.62180455261845e-05, "rouge2_recall": 0.0001072041166380789, "rouge2_recall_stderr": 7.577221663047183e-05, "rougeL_fmeasure": 0.0016046615232249279, "rougeL_fmeasure_stderr": 0.0004323354423624825, "rougeL_precision": 0.0017313225130562591, "rougeL_precision_stderr": 0.0004677255640486146, "rougeL_recall": 0.0015468066285396214, "rougeL_recall_stderr": 0.0004190027142908825, "rougeLsum_fmeasure": 0.0016046615232249279, "rougeLsum_fmeasure_stderr": 0.0004323354423624825, "rougeLsum_precision": 0.0017313225130562591, "rougeLsum_precision_stderr": 0.0004677255640486146, "rougeLsum_recall": 0.0015468066285396214, "rougeLsum_recall_stderr": 0.0004190027142908825}}}}