{ "STSBenchmark": { "train": { "pearson": [ 0.7671625496286432, 0.0 ], "spearman": [ 0.7407051823403011, 0.0 ], "nsamples": 5749 }, "dev": { "pearson": [ 0.7813083270941137, 5.741719519093736e-309 ], "spearman": [ 0.7888860081302335, 4.6194e-319 ], "nsamples": 1500 }, "test": { "pearson": [ 0.7624448096598531, 1.3012886054724166e-262 ], "spearman": [ 0.7602771570534436, 2.908594263406545e-260 ], "nsamples": 1379 }, "all": { "pearson": { "all": 0.7695053681260078, "mean": 0.7703052287942033, "wmean": 0.7688678002986993 }, "spearman": { "all": 0.7564014032837215, "mean": 0.7632894491746595, "wmean": 0.7522097015584654 } } }, "SICKRelatedness": { "train": { "pearson": [ 0.7772208691267224, 0.0 ], "spearman": [ 0.6978066630711928, 0.0 ], "nsamples": 4500 }, "dev": { "pearson": [ 0.7909750341980787, 2.5296588439552555e-108 ], "spearman": [ 0.7277741174377886, 1.3244056458147093e-83 ], "nsamples": 500 }, "test": { "pearson": [ 0.771314072761317, 0.0 ], "spearman": [ 0.6895861583188468, 0.0 ], "nsamples": 4927 }, "all": { "pearson": { "all": 0.7749070438706636, "mean": 0.7798366586953728, "wmean": 0.7749819547360027 }, "spearman": { "all": 0.6952695805138401, "mean": 0.7050556462759427, "wmean": 0.6952360274580659 } } }, "MR": { "devacc": 80.83, "acc": 80.73, "ndev": 10662, "ntest": 10662 }, "CR": { "devacc": 88.1, "acc": 86.04, "ndev": 3775, "ntest": 3775 }, "SUBJ": { "devacc": 95.32, "acc": 94.97, "ndev": 10000, "ntest": 10000 }, "MPQA": { "devacc": 89.04, "acc": 88.84, "ndev": 10606, "ntest": 10606 }, "SST2": { "devacc": 84.06, "acc": 85.45, "ndev": 872, "ntest": 1821 }, "TREC": { "devacc": 81.07, "acc": 88.0, "ndev": 5452, "ntest": 500 }, "MRPC": { "devacc": 70.68, "acc": 69.28, "f1": 80.87, "ndev": 4076, "ntest": 1725 }, "STS12": { "MSRpar": { "pearson": [ 0.44444679689851435, 1.1761912553301756e-37 ], "spearman": [ 0.44300447101923845, 2.1416387542051887e-37 ], "nsamples": 750 }, "MSRvid": { "pearson": [ 0.8646599853522132, 7.68208333670891e-226 ], "spearman": [ 0.8699014177629724, 8.381559996022476e-232 ], "nsamples": 750 }, "SMTeuroparl": { "pearson": [ 0.47046175638197285, 1.1740073098461771e-26 ], "spearman": [ 0.6114586792865501, 2.0882913296724147e-48 ], "nsamples": 459 }, "surprise.OnWN": { "pearson": [ 0.7178639582155328, 9.237684853571945e-120 ], "spearman": [ 0.6658532948970585, 3.0576891351321453e-97 ], "nsamples": 750 }, "surprise.SMTnews": { "pearson": [ 0.611621280135737, 2.647843518922555e-42 ], "spearman": [ 0.6250107076256665, 1.2659259057241255e-44 ], "nsamples": 399 }, "all": { "pearson": { "all": 0.6378431863774492, "mean": 0.6218107553967942, "wmean": 0.6371322047307528 }, "spearman": { "all": 0.6163833612367604, "mean": 0.6430457141182971, "wmean": 0.6480399594255531 } } }, "STS13": { "FNWN": { "pearson": [ 0.5562805069869132, 9.550380482948488e-17 ], "spearman": [ 0.5837123125601075, 1.19655468411138e-18 ], "nsamples": 189 }, "headlines": { "pearson": [ 0.7823638193897661, 5.690320525335935e-156 ], "spearman": [ 0.7917891963332858, 2.60264998377283e-162 ], "nsamples": 750 }, "OnWN": { "pearson": [ 0.7816458183409305, 1.083315842299476e-116 ], "spearman": [ 0.7796359177798075, 1.0258079303272485e-115 ], "nsamples": 561 }, "all": { "pearson": { "all": 0.7255022107614845, "mean": 0.7067633815725367, "wmean": 0.7536087896347422 }, "spearman": { "all": 0.7419430794508367, "mean": 0.7183791422244002, "wmean": 0.7610261827988645 } } }, "STS14": { "deft-forum": { "pearson": [ 0.5089575374073992, 5.023172357070916e-31 ], "spearman": [ 0.4963233135417476, 2.317944450085771e-29 ], "nsamples": 450 }, "deft-news": { "pearson": [ 0.7651252415822635, 6.366264844550544e-59 ], "spearman": [ 0.7127419493226671, 8.180911780133503e-48 ], "nsamples": 300 }, "headlines": { "pearson": [ 0.749244660243113, 5.438116092767328e-136 ], "spearman": [ 0.7099163551457461, 5.362434306324602e-116 ], "nsamples": 750 }, "images": { "pearson": [ 0.8463923099739724, 7.255366412502392e-207 ], "spearman": [ 0.8037324760119565, 7.818229780597217e-171 ], "nsamples": 750 }, "OnWN": { "pearson": [ 0.8194865773850172, 5.086803489175948e-183 ], "spearman": [ 0.8214740885641392, 1.2146288498994132e-184 ], "nsamples": 750 }, "tweet-news": { "pearson": [ 0.7298695292458673, 1.0631684722321918e-125 ], "spearman": [ 0.6599928354527725, 5.5057855924436005e-95 ], "nsamples": 750 }, "all": { "pearson": { "all": 0.7165932905627189, "mean": 0.7365126426396054, "wmean": 0.7512835391850631 }, "spearman": { "all": 0.6677462039090557, "mean": 0.7006968363398381, "wmean": 0.7156013046057461 } } }, "STS15": { "answers-forums": { "pearson": [ 0.7110270112832033, 5.18878369534419e-59 ], "spearman": [ 0.7180037029082824, 1.1507346620419953e-60 ], "nsamples": 375 }, "answers-students": { "pearson": [ 0.685403182699777, 3.763475670820268e-105 ], "spearman": [ 0.6892806170636011, 8.551548507203923e-107 ], "nsamples": 750 }, "belief": { "pearson": [ 0.7406221526966811, 2.1633293082135999e-66 ], "spearman": [ 0.7616812212998276, 2.7456783665122726e-72 ], "nsamples": 375 }, "headlines": { "pearson": [ 0.8065884284038872, 5.856919545907542e-173 ], "spearman": [ 0.8065628750527286, 6.121300087095471e-173 ], "nsamples": 750 }, "images": { "pearson": [ 0.8734727058865335, 5.133694173289855e-236 ], "spearman": [ 0.8800760762065849, 3.7371804165528405e-244 ], "nsamples": 750 }, "all": { "pearson": { "all": 0.7786729190560969, "mean": 0.7634226961940165, "wmean": 0.7728222247450349 }, "spearman": { "all": 0.7899640319998164, "mean": 0.7711208985062049, "wmean": 0.7789405076067425 } } }, "STS16": { "answer-answer": { "pearson": [ 0.6932635451048339, 1.0228592987318116e-37 ], "spearman": [ 0.7021547155024479, 4.8011478191297344e-39 ], "nsamples": 254 }, "headlines": { "pearson": [ 0.7691218196080909, 6.220546451256778e-50 ], "spearman": [ 0.779843578127762, 3.643403874299668e-52 ], "nsamples": 249 }, "plagiarism": { "pearson": [ 0.8038816275257141, 2.350047547816728e-53 ], "spearman": [ 0.8153039508029369, 5.088887617848758e-56 ], "nsamples": 230 }, "postediting": { "pearson": [ 0.8113538363870572, 2.3510310736845822e-58 ], "spearman": [ 0.8303201531350315, 2.1906668671246972e-63 ], "nsamples": 244 }, "question-question": { "pearson": [ 0.7802351353605056, 4.64479928094145e-44 ], "spearman": [ 0.7884164498209355, 1.4564689988934998e-45 ], "nsamples": 209 }, "all": { "pearson": { "all": 0.7704350276676698, "mean": 0.7715711927972403, "wmean": 0.7702635136920273 }, "spearman": { "all": 0.7846388532549995, "mean": 0.7832077694778227, "wmean": 0.7819775824229623 } } }, "eval_senteval-STS12": 0.6163833612367604, "eval_senteval-STS13": 0.7419430794508367, "eval_senteval-STS14": 0.6677462039090557, "eval_senteval-STS15": 0.7899640319998164, "eval_senteval-STS16": 0.7846388532549995, "eval_senteval-STSBenchmark": 0.7564014032837215, "eval_senteval-SICKRelatedness": 0.6952695805138401, "eval_senteval-avg_sts_7": 0.7217637876641472, "eval_senteval-MR": 80.83, "eval_senteval-CR": 88.1, "eval_senteval-SUBJ": 95.32, "eval_senteval-MPQA": 89.04, "eval_senteval-SST2": 84.06, "eval_senteval-TREC": 81.07, "eval_senteval-MRPC": 70.68, "eval_senteval-avg_transfer": 84.15714285714287 }