|
{ |
|
"STSBenchmark": { |
|
"train": { |
|
"pearson": [ |
|
0.7681082386326152, |
|
0.0 |
|
], |
|
"spearman": [ |
|
0.7398280920285996, |
|
0.0 |
|
], |
|
"nsamples": 5749 |
|
}, |
|
"dev": { |
|
"pearson": [ |
|
0.7871260331908001, |
|
1.11150867e-316 |
|
], |
|
"spearman": [ |
|
0.792474398503786, |
|
0.0 |
|
], |
|
"nsamples": 1500 |
|
}, |
|
"test": { |
|
"pearson": [ |
|
0.7651683167764847, |
|
1.338574321582192e-265 |
|
], |
|
"spearman": [ |
|
0.7613108217890912, |
|
2.22088758431869e-261 |
|
], |
|
"nsamples": 1379 |
|
}, |
|
"all": { |
|
"pearson": { |
|
"all": 0.7717571144826049, |
|
"mean": 0.7734675295333, |
|
"wmean": 0.7709446479508435 |
|
}, |
|
"spearman": { |
|
"all": 0.7568905857914078, |
|
"mean": 0.7645377707738256, |
|
"wmean": 0.7524143396007481 |
|
} |
|
} |
|
}, |
|
"SICKRelatedness": { |
|
"train": { |
|
"pearson": [ |
|
0.7686547151919503, |
|
0.0 |
|
], |
|
"spearman": [ |
|
0.686670691209585, |
|
0.0 |
|
], |
|
"nsamples": 4500 |
|
}, |
|
"dev": { |
|
"pearson": [ |
|
0.7902400028051256, |
|
5.478669559071821e-108 |
|
], |
|
"spearman": [ |
|
0.7241117459531325, |
|
2.1871273476832277e-82 |
|
], |
|
"nsamples": 500 |
|
}, |
|
"test": { |
|
"pearson": [ |
|
0.7603205521880406, |
|
0.0 |
|
], |
|
"spearman": [ |
|
0.677217475345889, |
|
0.0 |
|
], |
|
"nsamples": 4927 |
|
}, |
|
"all": { |
|
"pearson": { |
|
"all": 0.7655429200754945, |
|
"mean": 0.7730717567283723, |
|
"wmean": 0.7656054780292953 |
|
}, |
|
"spearman": { |
|
"all": 0.6838845953897259, |
|
"mean": 0.6959999708362021, |
|
"wmean": 0.6838646604662934 |
|
} |
|
} |
|
}, |
|
"MR": { |
|
"devacc": 80.71, |
|
"acc": 80.16, |
|
"ndev": 10662, |
|
"ntest": 10662 |
|
}, |
|
"CR": { |
|
"devacc": 87.05, |
|
"acc": 86.01, |
|
"ndev": 3775, |
|
"ntest": 3775 |
|
}, |
|
"SUBJ": { |
|
"devacc": 95.04, |
|
"acc": 94.71, |
|
"ndev": 10000, |
|
"ntest": 10000 |
|
}, |
|
"MPQA": { |
|
"devacc": 89.21, |
|
"acc": 89.07, |
|
"ndev": 10606, |
|
"ntest": 10606 |
|
}, |
|
"SST2": { |
|
"devacc": 84.06, |
|
"acc": 85.12, |
|
"ndev": 872, |
|
"ntest": 1821 |
|
}, |
|
"TREC": { |
|
"devacc": 80.61, |
|
"acc": 86.6, |
|
"ndev": 5452, |
|
"ntest": 500 |
|
}, |
|
"MRPC": { |
|
"devacc": 70.58, |
|
"acc": 65.51, |
|
"f1": 72.42, |
|
"ndev": 4076, |
|
"ntest": 1725 |
|
}, |
|
"STS12": { |
|
"MSRpar": { |
|
"pearson": [ |
|
0.4590340421521655, |
|
2.3274572346703796e-40 |
|
], |
|
"spearman": [ |
|
0.45385589375614366, |
|
2.1959530521625813e-39 |
|
], |
|
"nsamples": 750 |
|
}, |
|
"MSRvid": { |
|
"pearson": [ |
|
0.8528310967725129, |
|
2.9347357918307595e-213 |
|
], |
|
"spearman": [ |
|
0.854220777715675, |
|
1.1158473252287983e-214 |
|
], |
|
"nsamples": 750 |
|
}, |
|
"SMTeuroparl": { |
|
"pearson": [ |
|
0.4943065992119092, |
|
1.1819222066299774e-29 |
|
], |
|
"spearman": [ |
|
0.6119562407045409, |
|
1.670765662223567e-48 |
|
], |
|
"nsamples": 459 |
|
}, |
|
"surprise.OnWN": { |
|
"pearson": [ |
|
0.7373027197906938, |
|
1.5365117817869742e-129 |
|
], |
|
"spearman": [ |
|
0.6745662466490533, |
|
1.0854552176152885e-100 |
|
], |
|
"nsamples": 750 |
|
}, |
|
"surprise.SMTnews": { |
|
"pearson": [ |
|
0.6071798135532868, |
|
1.4735857118756226e-41 |
|
], |
|
"spearman": [ |
|
0.6088785137011317, |
|
7.667348467856033e-42 |
|
], |
|
"nsamples": 399 |
|
}, |
|
"all": { |
|
"pearson": { |
|
"all": 0.6623608523114471, |
|
"mean": 0.6301308542961137, |
|
"wmean": 0.645439951313564 |
|
}, |
|
"spearman": { |
|
"all": 0.6274520092064783, |
|
"mean": 0.6406955345053089, |
|
"wmean": 0.6469796106952348 |
|
} |
|
} |
|
}, |
|
"STS13": { |
|
"FNWN": { |
|
"pearson": [ |
|
0.6104407298501328, |
|
1.1065428255812799e-20 |
|
], |
|
"spearman": [ |
|
0.6416446744357271, |
|
2.5814733335245812e-23 |
|
], |
|
"nsamples": 189 |
|
}, |
|
"headlines": { |
|
"pearson": [ |
|
0.7850124142146208, |
|
1.0139977037812637e-157 |
|
], |
|
"spearman": [ |
|
0.793315510943691, |
|
2.2793688891679397e-163 |
|
], |
|
"nsamples": 750 |
|
}, |
|
"OnWN": { |
|
"pearson": [ |
|
0.7766707271490412, |
|
2.7086108094896696e-114 |
|
], |
|
"spearman": [ |
|
0.764681188348543, |
|
9.231297843026176e-109 |
|
], |
|
"nsamples": 561 |
|
}, |
|
"all": { |
|
"pearson": { |
|
"all": 0.741621137420334, |
|
"mean": 0.7240412904045982, |
|
"wmean": 0.7598965910221684 |
|
}, |
|
"spearman": { |
|
"all": 0.7537361964068123, |
|
"mean": 0.7332137912426537, |
|
"wmean": 0.7634957488931022 |
|
} |
|
} |
|
}, |
|
"STS14": { |
|
"deft-forum": { |
|
"pearson": [ |
|
0.49892982440741956, |
|
1.0652261555598016e-29 |
|
], |
|
"spearman": [ |
|
0.4865545802805047, |
|
4.028109290574198e-28 |
|
], |
|
"nsamples": 450 |
|
}, |
|
"deft-news": { |
|
"pearson": [ |
|
0.7661538564791797, |
|
3.605720461784356e-59 |
|
], |
|
"spearman": [ |
|
0.7240898336096998, |
|
5.311081186778723e-50 |
|
], |
|
"nsamples": 300 |
|
}, |
|
"headlines": { |
|
"pearson": [ |
|
0.7510342724250237, |
|
5.45925815985743e-137 |
|
], |
|
"spearman": [ |
|
0.7127027118216717, |
|
2.657235544077791e-117 |
|
], |
|
"nsamples": 750 |
|
}, |
|
"images": { |
|
"pearson": [ |
|
0.8457064177556566, |
|
3.3443785854353087e-206 |
|
], |
|
"spearman": [ |
|
0.8049272327834235, |
|
1.0191671573943109e-171 |
|
], |
|
"nsamples": 750 |
|
}, |
|
"OnWN": { |
|
"pearson": [ |
|
0.8241300010910765, |
|
7.676405298271845e-187 |
|
], |
|
"spearman": [ |
|
0.8223616193261, |
|
2.2573313609528353e-185 |
|
], |
|
"nsamples": 750 |
|
}, |
|
"tweet-news": { |
|
"pearson": [ |
|
0.7181193562444603, |
|
6.957548479833527e-120 |
|
], |
|
"spearman": [ |
|
0.6469747801580121, |
|
3.7447154677630655e-90 |
|
], |
|
"nsamples": 750 |
|
}, |
|
"all": { |
|
"pearson": { |
|
"all": 0.7207630295977413, |
|
"mean": 0.7340122880671359, |
|
"wmean": 0.7489618969504681 |
|
}, |
|
"spearman": { |
|
"all": 0.6776154802540348, |
|
"mean": 0.6996017929965687, |
|
"wmean": 0.713707005140278 |
|
} |
|
} |
|
}, |
|
"STS15": { |
|
"answers-forums": { |
|
"pearson": [ |
|
0.7104221785245369, |
|
7.180350548638676e-59 |
|
], |
|
"spearman": [ |
|
0.7157297042374495, |
|
4.032601594392119e-60 |
|
], |
|
"nsamples": 375 |
|
}, |
|
"answers-students": { |
|
"pearson": [ |
|
0.6841750672458253, |
|
1.2325511825986507e-104 |
|
], |
|
"spearman": [ |
|
0.6893747601179209, |
|
7.795024410550969e-107 |
|
], |
|
"nsamples": 750 |
|
}, |
|
"belief": { |
|
"pearson": [ |
|
0.749669412292463, |
|
7.484565874638222e-69 |
|
], |
|
"spearman": [ |
|
0.7689611847810851, |
|
1.80218707214869e-74 |
|
], |
|
"nsamples": 375 |
|
}, |
|
"headlines": { |
|
"pearson": [ |
|
0.8103746195832492, |
|
7.843957651748014e-176 |
|
], |
|
"spearman": [ |
|
0.8082136911038486, |
|
3.484989273824295e-174 |
|
], |
|
"nsamples": 750 |
|
}, |
|
"images": { |
|
"pearson": [ |
|
0.8764187325324918, |
|
1.372705232924295e-239 |
|
], |
|
"spearman": [ |
|
0.8823684545353031, |
|
4.309886303233611e-247 |
|
], |
|
"nsamples": 750 |
|
}, |
|
"all": { |
|
"pearson": { |
|
"all": 0.784979164135427, |
|
"mean": 0.7662120020357133, |
|
"wmean": 0.7752535536925166 |
|
}, |
|
"spearman": { |
|
"all": 0.7953840242507239, |
|
"mean": 0.7729295589551215, |
|
"wmean": 0.780575587566585 |
|
} |
|
} |
|
}, |
|
"STS16": { |
|
"answer-answer": { |
|
"pearson": [ |
|
0.7062392803273457, |
|
1.1334345573551127e-39 |
|
], |
|
"spearman": [ |
|
0.7160237031906911, |
|
3.2192023033831215e-41 |
|
], |
|
"nsamples": 254 |
|
}, |
|
"headlines": { |
|
"pearson": [ |
|
0.7684075132132632, |
|
8.674627222788605e-50 |
|
], |
|
"spearman": [ |
|
0.7792317750235211, |
|
4.923195475618921e-52 |
|
], |
|
"nsamples": 249 |
|
}, |
|
"plagiarism": { |
|
"pearson": [ |
|
0.814329742038296, |
|
8.73007637868767e-56 |
|
], |
|
"spearman": [ |
|
0.8315423069613309, |
|
3.8270415984455366e-60 |
|
], |
|
"nsamples": 230 |
|
}, |
|
"postediting": { |
|
"pearson": [ |
|
0.805735873745958, |
|
5.663717248324878e-57 |
|
], |
|
"spearman": [ |
|
0.8273031164960505, |
|
1.5191782859949922e-62 |
|
], |
|
"nsamples": 244 |
|
}, |
|
"question-question": { |
|
"pearson": [ |
|
0.7827391505554354, |
|
1.635608527236305e-44 |
|
], |
|
"spearman": [ |
|
0.7928031349595721, |
|
2.1346612440747243e-46 |
|
], |
|
"nsamples": 209 |
|
}, |
|
"all": { |
|
"pearson": { |
|
"all": 0.7742750560870418, |
|
"mean": 0.7754903119760597, |
|
"wmean": 0.7742041520422902 |
|
}, |
|
"spearman": { |
|
"all": 0.7904588398710303, |
|
"mean": 0.7893808073262332, |
|
"wmean": 0.7881208084519268 |
|
} |
|
} |
|
}, |
|
"eval_senteval-STS12": 0.6274520092064783, |
|
"eval_senteval-STS13": 0.7537361964068123, |
|
"eval_senteval-STS14": 0.6776154802540348, |
|
"eval_senteval-STS15": 0.7953840242507239, |
|
"eval_senteval-STS16": 0.7904588398710303, |
|
"eval_senteval-STSBenchmark": 0.7568905857914078, |
|
"eval_senteval-SICKRelatedness": 0.6838845953897259, |
|
"eval_senteval-avg_sts_7": 0.7264888187386019, |
|
"eval_senteval-MR": 80.71, |
|
"eval_senteval-CR": 87.05, |
|
"eval_senteval-SUBJ": 95.04, |
|
"eval_senteval-MPQA": 89.21, |
|
"eval_senteval-SST2": 84.06, |
|
"eval_senteval-TREC": 80.61, |
|
"eval_senteval-MRPC": 70.58, |
|
"eval_senteval-avg_transfer": 83.89428571428572 |
|
} |
|
|