arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1601.01280cs.CL
收藏

语言到逻辑形式的神经注意

Language to Logical Form with Neural Attention

Institute for Language, Cognition and Computation(语言、认知与计算研究所);School of Informatics, University of Edinburgh(爱丁堡大学信息学院)

Li Dong, Mirella Lapata

摘要:

语义解析旨在将自然语言映射到机器可解释的语义表示。传统的方法依赖于高质量的词典,手动构建的模板,以及特定于域或表示的语言特征。在本文中,我们提出了一个一般的方法的基础上,注意力增强的编码器-解码器模型。我们将输入话语编码成向量表示,并通过将输出序列或树调节到编码向量上来生成它们的逻辑形式。在四个数据集上的实验结果表明,我们的方法在不使用手工设计的特征的情况下具有竞争力,并且易于跨域和意义表示进行适应。

英文摘要:

Semantic parsing aims at mapping natural language to machine interpretable meaning representations. Traditional approaches rely on high-quality lexicons, manually-built templates, and linguistic features which are either domain- or representation-specific. In this paper we present a general method based on an attention-enhanced encoder-decoder model. We encode input utterances into vector representations, and generate their logical forms by conditioning the output sequences or trees on the encoding vectors. Experimental results on four datasets show that our approach performs competitively without using hand-engineered features and is easy to adapt across domains and meaning representations.

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。

↑