黄德根Huang Degen

(教授)

 博士生导师  硕士生导师
学位:博士
性别:男
毕业院校:大连理工大学
所在单位:计算机科学与技术学院
电子邮箱:huangdg@dlut.edu.cn

论文成果

DIM Reader: Dual Interaction Model for Machine Comprehension

发表时间:2019-03-11 点击次数:

论文名称:DIM Reader: Dual Interaction Model for Machine Comprehension
论文类型:会议论文
收录刊物:EI、CPCI-S
卷号:10565
页面范围:387-397
关键字:Machine comprehension; Bi-directional attention; Dual interaction model; Cloze-style
摘要:Enabling a computer to understand a document so that it can 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 novel dual interaction model (called DIM Reader) (Our code is available at https://github.com/dlt/mrc-dim), which constructs dual iterative alternating attention mechanism over multiple hops. The proposed 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 CNN/DailyMail News datasets, and our model achieves the best results on both machine comprehension datasets among almost published results.
发表时间:2017-01-01