遇到哪个加哪个
可以通过 paperswithcode 查看很多数据集的最好结果,且均有开源
NLP
STS
STS中的训练、测试、验证集的数量,语义文本相似性基准数据集,常用于无监督模型训练的测试集,使用Spearman correlation作为评价指标。
STS-B
main-captions | MSRvid | 2012test | 0000 | 5.000 | A man with a hard hat is dancing. | A man wearing a hard hat is dancing. |
main-captions | MSRvid | 2012test | 0002 | 4.750 | A young child is riding a horse. | A child is riding a horse. |
pair_ID | sentence_A | sentence_B | entailment_label | relatedness_score | entailment_AB | entailment_BA | sentence_A_original | sentence_B_original | sentence_A_dataset | sentenc |
---|