| { |
| "STSBenchmark": { |
| "train": { |
| "pearson": [ |
| 0.7593357300138104, |
| 0.0 |
| ], |
| "spearman": [ |
| 0.7363780516874698, |
| 0.0 |
| ], |
| "nsamples": 5749 |
| }, |
| "dev": { |
| "pearson": [ |
| 0.7708717320377951, |
| 1.0423163280003215e-295 |
| ], |
| "spearman": [ |
| 0.7786676025109732, |
| 1.5214906511814883e-305 |
| ], |
| "nsamples": 1500 |
| }, |
| "test": { |
| "pearson": [ |
| 0.7501376173451568, |
| 1.3467040400624944e-249 |
| ], |
| "spearman": [ |
| 0.750824400583584, |
| 2.649603496637417e-250 |
| ], |
| "nsamples": 1379 |
| }, |
| "all": { |
| "pearson": { |
| "all": 0.7604793924665235, |
| "mean": 0.7601150264655875, |
| "wmean": 0.759871173415051 |
| }, |
| "spearman": { |
| "all": 0.7504771603185239, |
| "mean": 0.7552900182606758, |
| "wmean": 0.7460391366854991 |
| } |
| } |
| }, |
| "SICKRelatedness": { |
| "train": { |
| "pearson": [ |
| 0.7662304008155296, |
| 0.0 |
| ], |
| "spearman": [ |
| 0.6902538404584456, |
| 0.0 |
| ], |
| "nsamples": 4500 |
| }, |
| "dev": { |
| "pearson": [ |
| 0.7821571234476052, |
| 2.2004576953729478e-104 |
| ], |
| "spearman": [ |
| 0.7166329672415084, |
| 5.843294318811089e-80 |
| ], |
| "nsamples": 500 |
| }, |
| "test": { |
| "pearson": [ |
| 0.7611310123704713, |
| 0.0 |
| ], |
| "spearman": [ |
| 0.6832295457395683, |
| 0.0 |
| ], |
| "nsamples": 4927 |
| }, |
| "all": { |
| "pearson": { |
| "all": 0.7644308360476054, |
| "mean": 0.7698395122112021, |
| "wmean": 0.7645016483673817 |
| }, |
| "spearman": { |
| "all": 0.6882116860582081, |
| "mean": 0.6967054511465074, |
| "wmean": 0.6880961758378777 |
| } |
| } |
| }, |
| "MR": { |
| "devacc": 81.02, |
| "acc": 80.82, |
| "ndev": 10662, |
| "ntest": 10662 |
| }, |
| "CR": { |
| "devacc": 87.16, |
| "acc": 86.17, |
| "ndev": 3775, |
| "ntest": 3775 |
| }, |
| "SUBJ": { |
| "devacc": 95.33, |
| "acc": 95.17, |
| "ndev": 10000, |
| "ntest": 10000 |
| }, |
| "MPQA": { |
| "devacc": 88.77, |
| "acc": 88.46, |
| "ndev": 10606, |
| "ntest": 10606 |
| }, |
| "SST2": { |
| "devacc": 83.6, |
| "acc": 84.24, |
| "ndev": 872, |
| "ntest": 1821 |
| }, |
| "TREC": { |
| "devacc": 80.56, |
| "acc": 87.0, |
| "ndev": 5452, |
| "ntest": 500 |
| }, |
| "MRPC": { |
| "devacc": 71.25, |
| "acc": 66.43, |
| "f1": 73.81, |
| "ndev": 4076, |
| "ntest": 1725 |
| }, |
| "STS12": { |
| "MSRpar": { |
| "pearson": [ |
| 0.45819524702782494, |
| 3.3567257088683594e-40 |
| ], |
| "spearman": [ |
| 0.4593149663142957, |
| 2.05835385149266e-40 |
| ], |
| "nsamples": 750 |
| }, |
| "MSRvid": { |
| "pearson": [ |
| 0.8388090235284806, |
| 1.054550172202713e-199 |
| ], |
| "spearman": [ |
| 0.8432194111992578, |
| 8.013026933052888e-204 |
| ], |
| "nsamples": 750 |
| }, |
| "SMTeuroparl": { |
| "pearson": [ |
| 0.470351077258895, |
| 1.2107115646660248e-26 |
| ], |
| "spearman": [ |
| 0.6116364642263132, |
| 1.9283950091627855e-48 |
| ], |
| "nsamples": 459 |
| }, |
| "surprise.OnWN": { |
| "pearson": [ |
| 0.7292994210321798, |
| 2.0693714792033592e-125 |
| ], |
| "spearman": [ |
| 0.6793850402850111, |
| 1.1917760852007569e-102 |
| ], |
| "nsamples": 750 |
| }, |
| "surprise.SMTnews": { |
| "pearson": [ |
| 0.6158664224403251, |
| 5.00305459526196e-43 |
| ], |
| "spearman": [ |
| 0.6265829727855505, |
| 6.644877973235503e-45 |
| ], |
| "nsamples": 399 |
| }, |
| "all": { |
| "pearson": { |
| "all": 0.6192684721893607, |
| "mean": 0.6225042382575411, |
| "wmean": 0.6374998763535671 |
| }, |
| "spearman": { |
| "all": 0.6088736294798399, |
| "mean": 0.6440277709620856, |
| "wmean": 0.6490306649196383 |
| } |
| } |
| }, |
| "STS13": { |
| "FNWN": { |
| "pearson": [ |
| 0.583088480042761, |
| 1.327977547862688e-18 |
| ], |
| "spearman": [ |
| 0.6168511381245143, |
| 3.3659450542010867e-21 |
| ], |
| "nsamples": 189 |
| }, |
| "headlines": { |
| "pearson": [ |
| 0.7836352201651423, |
| 8.29090382007377e-157 |
| ], |
| "spearman": [ |
| 0.7912489023898507, |
| 6.132894366499125e-162 |
| ], |
| "nsamples": 750 |
| }, |
| "OnWN": { |
| "pearson": [ |
| 0.780543451496936, |
| 3.728301808843133e-116 |
| ], |
| "spearman": [ |
| 0.7793841137341169, |
| 1.357231018729112e-115 |
| ], |
| "nsamples": 561 |
| }, |
| "all": { |
| "pearson": { |
| "all": 0.7340966173896293, |
| "mean": 0.7157557172349464, |
| "wmean": 0.7572100094278131 |
| }, |
| "spearman": { |
| "all": 0.7464064251943163, |
| "mean": 0.729161384749494, |
| "wmean": 0.7648373531351739 |
| } |
| } |
| }, |
| "STS14": { |
| "deft-forum": { |
| "pearson": [ |
| 0.5150502046211937, |
| 7.469786116455553e-32 |
| ], |
| "spearman": [ |
| 0.5042903667454042, |
| 2.107735033794951e-30 |
| ], |
| "nsamples": 450 |
| }, |
| "deft-news": { |
| "pearson": [ |
| 0.7600035052077184, |
| 1.0342986858741787e-57 |
| ], |
| "spearman": [ |
| 0.7070770213855571, |
| 9.237233248984215e-47 |
| ], |
| "nsamples": 300 |
| }, |
| "headlines": { |
| "pearson": [ |
| 0.7515597656390764, |
| 2.769317861251421e-137 |
| ], |
| "spearman": [ |
| 0.710516196158219, |
| 2.816764517801126e-116 |
| ], |
| "nsamples": 750 |
| }, |
| "images": { |
| "pearson": [ |
| 0.8347923636843458, |
| 4.653585389753753e-196 |
| ], |
| "spearman": [ |
| 0.798702780526685, |
| 3.566785098036202e-167 |
| ], |
| "nsamples": 750 |
| }, |
| "OnWN": { |
| "pearson": [ |
| 0.8223992201835943, |
| 2.1015626328917216e-185 |
| ], |
| "spearman": [ |
| 0.8224155107847296, |
| 2.0374470429214015e-185 |
| ], |
| "nsamples": 750 |
| }, |
| "tweet-news": { |
| "pearson": [ |
| 0.7274746788547437, |
| 1.7244493909147402e-124 |
| ], |
| "spearman": [ |
| 0.6538374727391042, |
| 1.1367362632519397e-92 |
| ], |
| "nsamples": 750 |
| }, |
| "all": { |
| "pearson": { |
| "all": 0.71492412302263, |
| "mean": 0.7352132896984455, |
| "wmean": 0.7498515106435127 |
| }, |
| "spearman": { |
| "all": 0.6678913458222988, |
| "mean": 0.6994732247232832, |
| "wmean": 0.7141753977620406 |
| } |
| } |
| }, |
| "STS15": { |
| "answers-forums": { |
| "pearson": [ |
| 0.7002911272139638, |
| 1.4668626470340174e-56 |
| ], |
| "spearman": [ |
| 0.7074764931313253, |
| 3.452041596266955e-58 |
| ], |
| "nsamples": 375 |
| }, |
| "answers-students": { |
| "pearson": [ |
| 0.6961950797823471, |
| 8.627896068129647e-110 |
| ], |
| "spearman": [ |
| 0.7027206344100234, |
| 1.0683742151679606e-112 |
| ], |
| "nsamples": 750 |
| }, |
| "belief": { |
| "pearson": [ |
| 0.7511423508124785, |
| 2.9073242437504715e-69 |
| ], |
| "spearman": [ |
| 0.7681133432498, |
| 3.266864742884551e-74 |
| ], |
| "nsamples": 375 |
| }, |
| "headlines": { |
| "pearson": [ |
| 0.8082307946809506, |
| 3.382538701221207e-174 |
| ], |
| "spearman": [ |
| 0.8104468033796624, |
| 6.90448241889555e-176 |
| ], |
| "nsamples": 750 |
| }, |
| "images": { |
| "pearson": [ |
| 0.8630054770339048, |
| 5.19656132014683e-224 |
| ], |
| "spearman": [ |
| 0.8698390459870816, |
| 9.903518997473141e-232 |
| ], |
| "nsamples": 750 |
| }, |
| "all": { |
| "pearson": { |
| "all": 0.7760986095295432, |
| "mean": 0.763772965904729, |
| "wmean": 0.7732870226276058 |
| }, |
| "spearman": { |
| "all": 0.7877087174315147, |
| "mean": 0.7717192640315785, |
| "wmean": 0.7802003504918326 |
| } |
| } |
| }, |
| "STS16": { |
| "answer-answer": { |
| "pearson": [ |
| 0.704831607499444, |
| 1.869291788174742e-39 |
| ], |
| "spearman": [ |
| 0.7140359945974517, |
| 6.717461236070393e-41 |
| ], |
| "nsamples": 254 |
| }, |
| "headlines": { |
| "pearson": [ |
| 0.7743109142972283, |
| 5.355550075397995e-51 |
| ], |
| "spearman": [ |
| 0.7864573637543575, |
| 1.320835283986403e-53 |
| ], |
| "nsamples": 249 |
| }, |
| "plagiarism": { |
| "pearson": [ |
| 0.8083151449572638, |
| 2.281279804429395e-54 |
| ], |
| "spearman": [ |
| 0.8212766679880286, |
| 1.732281708935307e-57 |
| ], |
| "nsamples": 230 |
| }, |
| "postediting": { |
| "pearson": [ |
| 0.8095639982798739, |
| 6.553674295846512e-58 |
| ], |
| "spearman": [ |
| 0.8300889112265731, |
| 2.5446199724900693e-63 |
| ], |
| "nsamples": 244 |
| }, |
| "question-question": { |
| "pearson": [ |
| 0.7760744103300035, |
| 2.5534707326738296e-43 |
| ], |
| "spearman": [ |
| 0.7821915474702287, |
| 2.0574127115194e-44 |
| ], |
| "nsamples": 209 |
| }, |
| "all": { |
| "pearson": { |
| "all": 0.7729055802161551, |
| "mean": 0.7746192150727627, |
| "wmean": 0.7735887830053114 |
| }, |
| "spearman": { |
| "all": 0.7885672061699577, |
| "mean": 0.786810097007328, |
| "wmean": 0.7859244414843136 |
| } |
| } |
| }, |
| "eval_senteval-STS12": 0.6088736294798399, |
| "eval_senteval-STS13": 0.7464064251943163, |
| "eval_senteval-STS14": 0.6678913458222988, |
| "eval_senteval-STS15": 0.7877087174315147, |
| "eval_senteval-STS16": 0.7885672061699577, |
| "eval_senteval-STSBenchmark": 0.7504771603185239, |
| "eval_senteval-SICKRelatedness": 0.6882116860582081, |
| "eval_senteval-avg_sts_7": 0.7197337386392372, |
| "eval_senteval-MR": 81.02, |
| "eval_senteval-CR": 87.16, |
| "eval_senteval-SUBJ": 95.33, |
| "eval_senteval-MPQA": 88.77, |
| "eval_senteval-SST2": 83.6, |
| "eval_senteval-TREC": 80.56, |
| "eval_senteval-MRPC": 71.25, |
| "eval_senteval-avg_transfer": 83.9557142857143 |
| } |
|
|