arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 1608.05014cs.CL
收藏

基于路径信息与分布信息的词汇语义关系识别

Path-based vs. Distributional Information in Recognizing Lexical Semantic Relations

Bar-Ilan University(巴伊兰大学)

Vered Shwartz, Ido Dagan

摘要:

识别术语之间的各种语义关系对于许多NLP任务是有益的。虽然基于路径和分布式信息源被认为是这项任务的补充,但后者最近显示的优越结果表明,前者的贡献可能已经过时。我们遵循最近成功的用于上位性检测的集成神经方法(Shwartz等人,2016年),并将其扩展到识别多种关系。实验结果表明,该方法在多类情况下也是有效的。我们进一步表明,基于路径的信息源总是有助于分类,并分析的情况下,它主要是补充的分布信息。

英文摘要:

Recognizing various semantic relations between terms is beneficial for many NLP tasks. While path-based and distributional information sources are considered complementary for this task, the superior results the latter showed recently suggested that the former's contribution might have become obsolete. We follow the recent success of an integrated neural method for hypernymy detection (Shwartz et al., 2016) and extend it to recognize multiple relations. The empirical results show that this method is effective in the multiclass setting as well. We further show that the path-based information source always contributes to the classification, and analyze the cases in which it mostly complements the distributional information.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑