arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2109.04787cs.CL
收藏

基于话题规则化的对话中的外指代词消解

Exophoric Pronoun Resolution in Dialogues with Topic Regularization

Tsinghua University(清华大学);The Hong Kong University of Science and Technology(香港科技大学);Tecent AI lab(腾讯AI实验室)

Xintong Yu, Hongming Zhang, Yangqiu Song, Changshui Zhang, Kun Xu, Dong Yu

摘要:

代词的指称问题一直是自然语言理解中的一个基本问题。以往关于代词共指消解的研究主要集中在代词与语篇中提及的消解上,而忽略了语篇中的外指情景。外指代词在日常交际中很常见,说话者可以直接使用代词来指称环境中的某些对象,而不必先介绍这些对象。虽然这些对象在对话文本中没有提到,但它们通常可以通过对话的一般主题来消除歧义。基于此,我们建议共同利用本地背景和全球对话主题来解决文本外PCR问题。大量的实验证明了添加主题正则化对解决外指代词的有效性。

英文摘要:

Resolving pronouns to their referents has long been studied as a fundamental natural language understanding problem. Previous works on pronoun coreference resolution (PCR) mostly focus on resolving pronouns to mentions in text while ignoring the exophoric scenario. Exophoric pronouns are common in daily communications, where speakers may directly use pronouns to refer to some objects present in the environment without introducing the objects first. Although such objects are not mentioned in the dialogue text, they can often be disambiguated by the general topics of the dialogue. Motivated by this, we propose to jointly leverage the local context and global topics of dialogues to solve the out-of-text PCR problem. Extensive experiments demonstrate the effectiveness of adding topic regularization for resolving exophoric pronouns.

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。

↑