arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1704.08387cs.CL
收藏

学习用于语义解析的结构化自然语言表示

Learning Structured Natural Language Representations for Semantic Parsing

University of Edinburgh(爱丁堡大学);IBM T.J. Watson Research(IBM T.J. Watson研究院)

Jianpeng Cheng, Siva Reddy, Vijay Saraswat, Mirella Lapata

摘要:

我们介绍了一个神经语义解析器,转换自然语言的话语中间表示形式的谓词参数结构,这是诱导与过渡系统,随后映射到目标域。语义解析器使用带注释的逻辑形式或它们的表示进行端到端的训练。我们在各种数据集上获得了有竞争力的结果。归纳的谓词-论元结构揭示了用于语义解析的表征类型,以及这些表征与语言动机表征的不同之处。

英文摘要:

We introduce a neural semantic parser that converts natural language utterances to intermediate representations in the form of predicate-argument structures, which are induced with a transition system and subsequently mapped to target domains. The semantic parser is trained end-to-end using annotated logical forms or their denotations. We obtain competitive results on various datasets. The induced predicate-argument structures shed light on the types of representations useful for semantic parsing and how these are different from linguistically motivated ones.

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。

↑