|
{ |
|
"STSBenchmark": { |
|
"train": { |
|
"pearson": [ |
|
0.700217766857111, |
|
0.0 |
|
], |
|
"spearman": [ |
|
0.694596243514894, |
|
0.0 |
|
], |
|
"nsamples": 5749 |
|
}, |
|
"dev": { |
|
"pearson": [ |
|
0.7188725565702827, |
|
7.642460243707613e-239 |
|
], |
|
"spearman": [ |
|
0.7430861317995934, |
|
1.3229042265692801e-263 |
|
], |
|
"nsamples": 1500 |
|
}, |
|
"test": { |
|
"pearson": [ |
|
0.6697149917661123, |
|
3.5510311886663796e-180 |
|
], |
|
"spearman": [ |
|
0.7028355722100523, |
|
6.396511507534624e-206 |
|
], |
|
"nsamples": 1379 |
|
}, |
|
"all": { |
|
"pearson": { |
|
"all": 0.7003515412165919, |
|
"mean": 0.6962684383978353, |
|
"wmean": 0.698585738312752 |
|
}, |
|
"spearman": { |
|
"all": 0.708944371429387, |
|
"mean": 0.7135059825081799, |
|
"wmean": 0.7043432146203266 |
|
} |
|
} |
|
}, |
|
"SICKRelatedness": { |
|
"train": { |
|
"pearson": [ |
|
0.7900787687078513, |
|
0.0 |
|
], |
|
"spearman": [ |
|
0.7162798220982042, |
|
0.0 |
|
], |
|
"nsamples": 4500 |
|
}, |
|
"dev": { |
|
"pearson": [ |
|
0.7941456305052318, |
|
8.704175570070149e-110 |
|
], |
|
"spearman": [ |
|
0.7323591663810709, |
|
3.70700656086251e-85 |
|
], |
|
"nsamples": 500 |
|
}, |
|
"test": { |
|
"pearson": [ |
|
0.7827901659487767, |
|
0.0 |
|
], |
|
"spearman": [ |
|
0.7066436772359563, |
|
0.0 |
|
], |
|
"nsamples": 4927 |
|
}, |
|
"all": { |
|
"pearson": { |
|
"all": 0.7866207722959027, |
|
"mean": 0.7890048550539532, |
|
"wmean": 0.7866661047715896 |
|
}, |
|
"spearman": { |
|
"all": 0.7122486034563766, |
|
"mean": 0.7184275552384105, |
|
"wmean": 0.7123070595722788 |
|
} |
|
} |
|
}, |
|
"MR": { |
|
"devacc": 80.75, |
|
"acc": 80.52, |
|
"ndev": 10662, |
|
"ntest": 10662 |
|
}, |
|
"CR": { |
|
"devacc": 87.02, |
|
"acc": 86.41, |
|
"ndev": 3775, |
|
"ntest": 3775 |
|
}, |
|
"SUBJ": { |
|
"devacc": 95.02, |
|
"acc": 94.49, |
|
"ndev": 10000, |
|
"ntest": 10000 |
|
}, |
|
"MPQA": { |
|
"devacc": 88.67, |
|
"acc": 88.53, |
|
"ndev": 10606, |
|
"ntest": 10606 |
|
}, |
|
"SST2": { |
|
"devacc": 82.8, |
|
"acc": 85.89, |
|
"ndev": 872, |
|
"ntest": 1821 |
|
}, |
|
"TREC": { |
|
"devacc": 78.63, |
|
"acc": 88.6, |
|
"ndev": 5452, |
|
"ntest": 500 |
|
}, |
|
"MRPC": { |
|
"devacc": 70.17, |
|
"acc": 62.55, |
|
"f1": 68.4, |
|
"ndev": 4076, |
|
"ntest": 1725 |
|
}, |
|
"STS12": { |
|
"MSRpar": { |
|
"pearson": [ |
|
0.3279591431665635, |
|
2.8934198828902823e-20 |
|
], |
|
"spearman": [ |
|
0.37151182527291027, |
|
5.848988168730171e-26 |
|
], |
|
"nsamples": 750 |
|
}, |
|
"MSRvid": { |
|
"pearson": [ |
|
0.8600914351071427, |
|
7.615361092408985e-221 |
|
], |
|
"spearman": [ |
|
0.8710479889820992, |
|
3.841468226701095e-233 |
|
], |
|
"nsamples": 750 |
|
}, |
|
"SMTeuroparl": { |
|
"pearson": [ |
|
0.49106075103459146, |
|
3.1227262696721795e-29 |
|
], |
|
"spearman": [ |
|
0.5976234583132141, |
|
8.832799021137483e-46 |
|
], |
|
"nsamples": 459 |
|
}, |
|
"surprise.OnWN": { |
|
"pearson": [ |
|
0.6903453132676263, |
|
2.993644573897565e-107 |
|
], |
|
"spearman": [ |
|
0.6522049690471122, |
|
4.576466079694001e-92 |
|
], |
|
"nsamples": 750 |
|
}, |
|
"surprise.SMTnews": { |
|
"pearson": [ |
|
0.5747570138816134, |
|
1.8705693938405458e-36 |
|
], |
|
"spearman": [ |
|
0.6161895683302498, |
|
4.402482065232814e-43 |
|
], |
|
"nsamples": 399 |
|
}, |
|
"all": { |
|
"pearson": { |
|
"all": 0.6532360047609772, |
|
"mean": 0.5888427312915075, |
|
"wmean": 0.5995887554438998 |
|
}, |
|
"spearman": { |
|
"all": 0.6520942930121344, |
|
"mean": 0.6217155619891171, |
|
"wmean": 0.6245953644163854 |
|
} |
|
} |
|
}, |
|
"STS13": { |
|
"FNWN": { |
|
"pearson": [ |
|
0.5455691661756268, |
|
4.746052411411139e-16 |
|
], |
|
"spearman": [ |
|
0.5552285672079286, |
|
1.1207604310221007e-16 |
|
], |
|
"nsamples": 189 |
|
}, |
|
"headlines": { |
|
"pearson": [ |
|
0.7376364893975698, |
|
1.0257488464328715e-129 |
|
], |
|
"spearman": [ |
|
0.7584758247313932, |
|
3.1099800660504727e-141 |
|
], |
|
"nsamples": 750 |
|
}, |
|
"OnWN": { |
|
"pearson": [ |
|
0.8062599488981587, |
|
1.4758922804276925e-129 |
|
], |
|
"spearman": [ |
|
0.791620979725446, |
|
1.0741113505197788e-121 |
|
], |
|
"nsamples": 561 |
|
}, |
|
"all": { |
|
"pearson": { |
|
"all": 0.7161952323138701, |
|
"mean": 0.6964885348237851, |
|
"wmean": 0.7391011805248252 |
|
}, |
|
"spearman": { |
|
"all": 0.7489808796663362, |
|
"mean": 0.701775123888256, |
|
"wmean": 0.7452629582512124 |
|
} |
|
} |
|
}, |
|
"STS14": { |
|
"deft-forum": { |
|
"pearson": [ |
|
0.4539905158613596, |
|
2.8973755391032382e-24 |
|
], |
|
"spearman": [ |
|
0.4539149626420418, |
|
2.954477747813041e-24 |
|
], |
|
"nsamples": 450 |
|
}, |
|
"deft-news": { |
|
"pearson": [ |
|
0.6909565157190697, |
|
6.731301106701071e-44 |
|
], |
|
"spearman": [ |
|
0.654918374815774, |
|
3.9304042018460903e-38 |
|
], |
|
"nsamples": 300 |
|
}, |
|
"headlines": { |
|
"pearson": [ |
|
0.7163249206179311, |
|
5.064372905060631e-119 |
|
], |
|
"spearman": [ |
|
0.6890244755927888, |
|
1.1000588945875164e-106 |
|
], |
|
"nsamples": 750 |
|
}, |
|
"images": { |
|
"pearson": [ |
|
0.8341976013585205, |
|
1.581737521468821e-195 |
|
], |
|
"spearman": [ |
|
0.8009087778380325, |
|
9.127029827171149e-169 |
|
], |
|
"nsamples": 750 |
|
}, |
|
"OnWN": { |
|
"pearson": [ |
|
0.8416372752913062, |
|
2.488984870540694e-202 |
|
], |
|
"spearman": [ |
|
0.835891574935076, |
|
4.7883053518051054e-197 |
|
], |
|
"nsamples": 750 |
|
}, |
|
"tweet-news": { |
|
"pearson": [ |
|
0.5893351545919092, |
|
2.4679056644216343e-71 |
|
], |
|
"spearman": [ |
|
0.5523429250762462, |
|
4.020802928899476e-61 |
|
], |
|
"nsamples": 750 |
|
}, |
|
"all": { |
|
"pearson": { |
|
"all": 0.6458742493245161, |
|
"mean": 0.6877403305733494, |
|
"wmean": 0.7060543735328222 |
|
}, |
|
"spearman": { |
|
"all": 0.6214541243526541, |
|
"mean": 0.6645001818166599, |
|
"wmean": 0.6824968161907357 |
|
} |
|
} |
|
}, |
|
"STS15": { |
|
"answers-forums": { |
|
"pearson": [ |
|
0.5843871869461419, |
|
1.0151032193286744e-35 |
|
], |
|
"spearman": [ |
|
0.6084659043667563, |
|
2.3820444508668996e-39 |
|
], |
|
"nsamples": 375 |
|
}, |
|
"answers-students": { |
|
"pearson": [ |
|
0.6152132265657764, |
|
2.6617778013870566e-79 |
|
], |
|
"spearman": [ |
|
0.6302561398409405, |
|
2.773969605891675e-84 |
|
], |
|
"nsamples": 750 |
|
}, |
|
"belief": { |
|
"pearson": [ |
|
0.6392710473707196, |
|
1.799179528686185e-44 |
|
], |
|
"spearman": [ |
|
0.686875976718544, |
|
1.2015551469859737e-53 |
|
], |
|
"nsamples": 375 |
|
}, |
|
"headlines": { |
|
"pearson": [ |
|
0.7734487150038147, |
|
2.927357789667028e-150 |
|
], |
|
"spearman": [ |
|
0.7896018531226366, |
|
8.23498473346381e-161 |
|
], |
|
"nsamples": 750 |
|
}, |
|
"images": { |
|
"pearson": [ |
|
0.864344989852659, |
|
1.7210495814828955e-225 |
|
], |
|
"spearman": [ |
|
0.8824596984841369, |
|
3.2828816211446655e-247 |
|
], |
|
"nsamples": 750 |
|
}, |
|
"all": { |
|
"pearson": { |
|
"all": 0.7203379074291151, |
|
"mean": 0.6953330331478222, |
|
"wmean": 0.7162090121451702 |
|
}, |
|
"spearman": { |
|
"all": 0.7497940183329284, |
|
"mean": 0.7195319145066028, |
|
"wmean": 0.7374971579975911 |
|
} |
|
} |
|
}, |
|
"STS16": { |
|
"answer-answer": { |
|
"pearson": [ |
|
0.6368696070010881, |
|
2.678858858103159e-30 |
|
], |
|
"spearman": [ |
|
0.6921912704278468, |
|
1.4681538672067537e-37 |
|
], |
|
"nsamples": 254 |
|
}, |
|
"headlines": { |
|
"pearson": [ |
|
0.7289776103151235, |
|
1.5277023512508603e-42 |
|
], |
|
"spearman": [ |
|
0.7621038994295888, |
|
1.551008215103711e-48 |
|
], |
|
"nsamples": 249 |
|
}, |
|
"plagiarism": { |
|
"pearson": [ |
|
0.7702063765670754, |
|
2.003814813962993e-46 |
|
], |
|
"spearman": [ |
|
0.7911510680474892, |
|
1.3837761303567582e-50 |
|
], |
|
"nsamples": 230 |
|
}, |
|
"postediting": { |
|
"pearson": [ |
|
0.719837823485291, |
|
3.0286294416646686e-40 |
|
], |
|
"spearman": [ |
|
0.7566461459669797, |
|
1.4825051882045699e-46 |
|
], |
|
"nsamples": 244 |
|
}, |
|
"question-question": { |
|
"pearson": [ |
|
0.7625392869659763, |
|
5.114455019237254e-41 |
|
], |
|
"spearman": [ |
|
0.7800407128371691, |
|
5.033994633121257e-44 |
|
], |
|
"nsamples": 209 |
|
}, |
|
"all": { |
|
"pearson": { |
|
"all": 0.7140924962133864, |
|
"mean": 0.7236861408669109, |
|
"wmean": 0.721280701233954 |
|
}, |
|
"spearman": { |
|
"all": 0.7490972681198437, |
|
"mean": 0.7564266193418148, |
|
"wmean": 0.7548021651740933 |
|
} |
|
} |
|
}, |
|
"eval_senteval-STS12": 0.6520942930121344, |
|
"eval_senteval-STS13": 0.7489808796663362, |
|
"eval_senteval-STS14": 0.6214541243526541, |
|
"eval_senteval-STS15": 0.7497940183329284, |
|
"eval_senteval-STS16": 0.7490972681198437, |
|
"eval_senteval-STSBenchmark": 0.708944371429387, |
|
"eval_senteval-SICKRelatedness": 0.7122486034563766, |
|
"eval_senteval-avg_sts_7": 0.7060876511956659, |
|
"eval_senteval-MR": 80.75, |
|
"eval_senteval-CR": 87.02, |
|
"eval_senteval-SUBJ": 95.02, |
|
"eval_senteval-MPQA": 88.67, |
|
"eval_senteval-SST2": 82.8, |
|
"eval_senteval-TREC": 78.63, |
|
"eval_senteval-MRPC": 70.17, |
|
"eval_senteval-avg_transfer": 83.2942857142857 |
|
} |
|
|