DIM Reader:Dual Interaction Model for Machine Comprehension

摘要：

　　Enabling a computer to understand a document so that itcan answer comprehension questions is a central,yet unsolved goal of Natural Language Processing,so reading comprehension of text is an important problem in NLP research.In this paper,we propose a nov-el dual interaction model(called DIM Reader)1,which constructs dual iterative alternating attention mechanism over multiple hops.The pro-posed DIM Reader continually refines its view of the query and document while aggregating the information required to answer a query,aiming to compute the attentions not only for the document but also the query side,which will benefit from the mutual information.DIM Reader makes use of multiple turns to effectively exploit and perform deeper inference among queries,documents.We conduct extensive experiments on CN-N/DailyMail News datasets,and our model achieves the best results on both machine comprehension datasets among almost published results.

关键词： machine comprehension bi-directional attention dual in-teraction model Cloze-style

作者: Liu Zhuang Huang Degen Huang Kaiyu Zhang Jing

作者单位: School of Computer Science and Technology,Dalian University of Technology

会议类型: 国内会议

会议名称: 第十六届全国计算语言学学术会议暨第五届基于自然标注大数据的自然语言处理国际学术研讨会

会议地点: 南京

会议语种:英文

页码: 1-11

在线出版日期: 2017-10-13（万方平台首次上网日期，不代表论文的发表时间）