|
{ |
|
"STSBenchmark": { |
|
"train": { |
|
"pearson": [ |
|
0.73125161607048, |
|
0.0 |
|
], |
|
"spearman": [ |
|
0.7150765613453124, |
|
0.0 |
|
], |
|
"nsamples": 5749 |
|
}, |
|
"dev": { |
|
"pearson": [ |
|
0.7443000568532008, |
|
6.40691279840157e-265 |
|
], |
|
"spearman": [ |
|
0.759890982808152, |
|
1.6901750172343795e-282 |
|
], |
|
"nsamples": 1500 |
|
}, |
|
"test": { |
|
"pearson": [ |
|
0.7216210553290073, |
|
3.539646733532031e-222 |
|
], |
|
"spearman": [ |
|
0.7304939228930519, |
|
2.4834600870262812e-230 |
|
], |
|
"nsamples": 1379 |
|
}, |
|
"all": { |
|
"pearson": { |
|
"all": 0.7322719424112719, |
|
"mean": 0.7323909094175627, |
|
"wmean": 0.7319808833295888 |
|
}, |
|
"spearman": { |
|
"all": 0.7295849518142924, |
|
"mean": 0.7351538223488387, |
|
"wmean": 0.7253317970625808 |
|
} |
|
} |
|
}, |
|
"SICKRelatedness": { |
|
"train": { |
|
"pearson": [ |
|
0.7596859741218331, |
|
0.0 |
|
], |
|
"spearman": [ |
|
0.7018231072465838, |
|
0.0 |
|
], |
|
"nsamples": 4500 |
|
}, |
|
"dev": { |
|
"pearson": [ |
|
0.777647576791967, |
|
1.9353259230163057e-102 |
|
], |
|
"spearman": [ |
|
0.7337127308506983, |
|
1.2717377929862408e-85 |
|
], |
|
"nsamples": 500 |
|
}, |
|
"test": { |
|
"pearson": [ |
|
0.7566490759566877, |
|
0.0 |
|
], |
|
"spearman": [ |
|
0.6936198984184592, |
|
0.0 |
|
], |
|
"nsamples": 4927 |
|
}, |
|
"all": { |
|
"pearson": { |
|
"all": 0.7589921709943909, |
|
"mean": 0.7646608756234959, |
|
"wmean": 0.7590833755598704 |
|
}, |
|
"spearman": { |
|
"all": 0.6992260214830822, |
|
"mean": 0.7097185788385804, |
|
"wmean": 0.6993578712141356 |
|
} |
|
} |
|
}, |
|
"MR": { |
|
"devacc": 81.81, |
|
"acc": 81.41, |
|
"ndev": 10662, |
|
"ntest": 10662 |
|
}, |
|
"CR": { |
|
"devacc": 87.87, |
|
"acc": 87.23, |
|
"ndev": 3775, |
|
"ntest": 3775 |
|
}, |
|
"SUBJ": { |
|
"devacc": 95.31, |
|
"acc": 95.0, |
|
"ndev": 10000, |
|
"ntest": 10000 |
|
}, |
|
"MPQA": { |
|
"devacc": 89.07, |
|
"acc": 89.01, |
|
"ndev": 10606, |
|
"ntest": 10606 |
|
}, |
|
"SST2": { |
|
"devacc": 84.4, |
|
"acc": 86.27, |
|
"ndev": 872, |
|
"ntest": 1821 |
|
}, |
|
"TREC": { |
|
"devacc": 80.43, |
|
"acc": 87.6, |
|
"ndev": 5452, |
|
"ntest": 500 |
|
}, |
|
"MRPC": { |
|
"devacc": 70.39, |
|
"acc": 67.07, |
|
"f1": 74.82, |
|
"ndev": 4076, |
|
"ntest": 1725 |
|
}, |
|
"STS12": { |
|
"MSRpar": { |
|
"pearson": [ |
|
0.44512999156378674, |
|
8.846234223022077e-38 |
|
], |
|
"spearman": [ |
|
0.4509834995822136, |
|
7.501496598491026e-39 |
|
], |
|
"nsamples": 750 |
|
}, |
|
"MSRvid": { |
|
"pearson": [ |
|
0.8158138179672533, |
|
4.485078256906633e-180 |
|
], |
|
"spearman": [ |
|
0.8238805942224864, |
|
1.2395324040896922e-186 |
|
], |
|
"nsamples": 750 |
|
}, |
|
"SMTeuroparl": { |
|
"pearson": [ |
|
0.5025777230618875, |
|
9.478558829456811e-31 |
|
], |
|
"spearman": [ |
|
0.6028335206096967, |
|
9.378736061336642e-47 |
|
], |
|
"nsamples": 459 |
|
}, |
|
"surprise.OnWN": { |
|
"pearson": [ |
|
0.7075050481901065, |
|
7.017744961203796e-115 |
|
], |
|
"spearman": [ |
|
0.6550259208484078, |
|
4.101580378925782e-93 |
|
], |
|
"nsamples": 750 |
|
}, |
|
"surprise.SMTnews": { |
|
"pearson": [ |
|
0.6149709443544354, |
|
7.125268059032375e-43 |
|
], |
|
"spearman": [ |
|
0.6179122177365513, |
|
2.2209746905791215e-43 |
|
], |
|
"nsamples": 399 |
|
}, |
|
"all": { |
|
"pearson": { |
|
"all": 0.5765393545095476, |
|
"mean": 0.617199505027494, |
|
"wmean": 0.6281831483184317 |
|
}, |
|
"spearman": { |
|
"all": 0.5812709943392725, |
|
"mean": 0.6301271505998711, |
|
"wmean": 0.6340621209223184 |
|
} |
|
} |
|
}, |
|
"STS13": { |
|
"FNWN": { |
|
"pearson": [ |
|
0.5404400970895422, |
|
1.0024601828505787e-15 |
|
], |
|
"spearman": [ |
|
0.5700597864027528, |
|
1.1134900500394056e-17 |
|
], |
|
"nsamples": 189 |
|
}, |
|
"headlines": { |
|
"pearson": [ |
|
0.7696057345254828, |
|
7.053396385656569e-148 |
|
], |
|
"spearman": [ |
|
0.7771493600170609, |
|
1.3424669074971778e-152 |
|
], |
|
"nsamples": 750 |
|
}, |
|
"OnWN": { |
|
"pearson": [ |
|
0.770711585062639, |
|
1.6777951910420866e-111 |
|
], |
|
"spearman": [ |
|
0.7682009295399416, |
|
2.3759249362431374e-110 |
|
], |
|
"nsamples": 561 |
|
}, |
|
"all": { |
|
"pearson": { |
|
"all": 0.7077401152320973, |
|
"mean": 0.6935858055592213, |
|
"wmean": 0.7411444523094507 |
|
}, |
|
"spearman": { |
|
"all": 0.7340343966035406, |
|
"mean": 0.705136691986585, |
|
"wmean": 0.7477093607432154 |
|
} |
|
} |
|
}, |
|
"STS14": { |
|
"deft-forum": { |
|
"pearson": [ |
|
0.5050347882312676, |
|
1.6792481128963397e-30 |
|
], |
|
"spearman": [ |
|
0.5006511549237668, |
|
6.351186067873574e-30 |
|
], |
|
"nsamples": 450 |
|
}, |
|
"deft-news": { |
|
"pearson": [ |
|
0.7505543283782676, |
|
1.480995559109095e-55 |
|
], |
|
"spearman": [ |
|
0.7172316918319939, |
|
1.1485152196025994e-48 |
|
], |
|
"nsamples": 300 |
|
}, |
|
"headlines": { |
|
"pearson": [ |
|
0.7381665393126864, |
|
5.392499213485816e-130 |
|
], |
|
"spearman": [ |
|
0.6987173657276973, |
|
6.630592581022267e-111 |
|
], |
|
"nsamples": 750 |
|
}, |
|
"images": { |
|
"pearson": [ |
|
0.8184796221575482, |
|
3.315905577355896e-182 |
|
], |
|
"spearman": [ |
|
0.7800399098279688, |
|
1.8607695353393358e-154 |
|
], |
|
"nsamples": 750 |
|
}, |
|
"OnWN": { |
|
"pearson": [ |
|
0.8151737890413434, |
|
1.4397424024788037e-179 |
|
], |
|
"spearman": [ |
|
0.8163228192853189, |
|
1.7682187396229704e-180 |
|
], |
|
"nsamples": 750 |
|
}, |
|
"tweet-news": { |
|
"pearson": [ |
|
0.6920222067407532, |
|
5.678306228875661e-108 |
|
], |
|
"spearman": [ |
|
0.6388729139230673, |
|
2.906642337192504e-87 |
|
], |
|
"nsamples": 750 |
|
}, |
|
"all": { |
|
"pearson": { |
|
"all": 0.6768936191011258, |
|
"mean": 0.719905212310311, |
|
"wmean": 0.7334169523084798 |
|
}, |
|
"spearman": { |
|
"all": 0.6371047443411619, |
|
"mean": 0.6919726425866354, |
|
"wmean": 0.704247275690222 |
|
} |
|
} |
|
}, |
|
"STS15": { |
|
"answers-forums": { |
|
"pearson": [ |
|
0.6715484368711376, |
|
1.6630650795173534e-50 |
|
], |
|
"spearman": [ |
|
0.6791768037991774, |
|
4.803053709588311e-52 |
|
], |
|
"nsamples": 375 |
|
}, |
|
"answers-students": { |
|
"pearson": [ |
|
0.6752231441950838, |
|
5.897966571800042e-101 |
|
], |
|
"spearman": [ |
|
0.6804903297262569, |
|
4.1825635033521844e-103 |
|
], |
|
"nsamples": 750 |
|
}, |
|
"belief": { |
|
"pearson": [ |
|
0.7171089394500281, |
|
1.8875842940680164e-60 |
|
], |
|
"spearman": [ |
|
0.7340838023228742, |
|
1.1234078020923912e-64 |
|
], |
|
"nsamples": 375 |
|
}, |
|
"headlines": { |
|
"pearson": [ |
|
0.7957787507836831, |
|
4.2857031841813906e-165 |
|
], |
|
"spearman": [ |
|
0.7959923201180171, |
|
3.028810020400643e-165 |
|
], |
|
"nsamples": 750 |
|
}, |
|
"images": { |
|
"pearson": [ |
|
0.847852285173722, |
|
2.736037311458429e-208 |
|
], |
|
"spearman": [ |
|
0.8592562196355571, |
|
5.9692336633848975e-220 |
|
], |
|
"nsamples": 750 |
|
}, |
|
"all": { |
|
"pearson": { |
|
"all": 0.7528553221562304, |
|
"mean": 0.7415023112947309, |
|
"wmean": 0.753295717078268 |
|
}, |
|
"spearman": { |
|
"all": 0.7672378740860561, |
|
"mean": 0.7497998951203765, |
|
"wmean": 0.7605922931352141 |
|
} |
|
} |
|
}, |
|
"STS16": { |
|
"answer-answer": { |
|
"pearson": [ |
|
0.6932025545095016, |
|
1.0441476948753323e-37 |
|
], |
|
"spearman": [ |
|
0.716984850240451, |
|
2.2505666854089843e-41 |
|
], |
|
"nsamples": 254 |
|
}, |
|
"headlines": { |
|
"pearson": [ |
|
0.7647140202671684, |
|
4.751336314867901e-49 |
|
], |
|
"spearman": [ |
|
0.7735811184492498, |
|
7.591019148208835e-51 |
|
], |
|
"nsamples": 249 |
|
}, |
|
"plagiarism": { |
|
"pearson": [ |
|
0.8094434845489986, |
|
1.2478658754392033e-54 |
|
], |
|
"spearman": [ |
|
0.8231197837843675, |
|
5.9498794720031536e-58 |
|
], |
|
"nsamples": 230 |
|
}, |
|
"postediting": { |
|
"pearson": [ |
|
0.7946011230206756, |
|
2.306149833128848e-54 |
|
], |
|
"spearman": [ |
|
0.8178716303963535, |
|
5.115171930640644e-60 |
|
], |
|
"nsamples": 244 |
|
}, |
|
"question-question": { |
|
"pearson": [ |
|
0.7803307090745555, |
|
4.4645254931736274e-44 |
|
], |
|
"spearman": [ |
|
0.7927716723925775, |
|
2.1646221593031153e-46 |
|
], |
|
"nsamples": 209 |
|
}, |
|
"all": { |
|
"pearson": { |
|
"all": 0.7636230650001257, |
|
"mean": 0.7684583782841801, |
|
"wmean": 0.7669738900099788 |
|
}, |
|
"spearman": { |
|
"all": 0.7833717936510003, |
|
"mean": 0.7848658110525999, |
|
"wmean": 0.7835610101788375 |
|
} |
|
} |
|
}, |
|
"eval_senteval-STS12": 0.5812709943392725, |
|
"eval_senteval-STS13": 0.7340343966035406, |
|
"eval_senteval-STS14": 0.6371047443411619, |
|
"eval_senteval-STS15": 0.7672378740860561, |
|
"eval_senteval-STS16": 0.7833717936510003, |
|
"eval_senteval-STSBenchmark": 0.7295849518142924, |
|
"eval_senteval-SICKRelatedness": 0.6992260214830822, |
|
"eval_senteval-avg_sts_7": 0.7045472537597723, |
|
"eval_senteval-MR": 81.81, |
|
"eval_senteval-CR": 87.87, |
|
"eval_senteval-SUBJ": 95.31, |
|
"eval_senteval-MPQA": 89.07, |
|
"eval_senteval-SST2": 84.4, |
|
"eval_senteval-TREC": 80.43, |
|
"eval_senteval-MRPC": 70.39, |
|
"eval_senteval-avg_transfer": 84.18285714285716 |
|
} |
|
|