Effective Character-Augmented Word Embedding for Machine Reading Comprehension

摘要：

　　Machine reading comprehension is a task to model relationship between passage and query.In terms of deep learning framework,most of state-of-the-art models simply concatenate word and character level representations,which has been shown suboptimal for the concerned task.In this paper,we empirically explore different integration strategies of word and character embeddings and propose a characteraugmented reader which attends character-level representation to augment word embedding with a short list to improve word representations,especially for rare words.Experimental results show that the proposed approach helps the baseline model significantly outperform state-of-theart baselines on various public benchmarks.

关键词： Question answering Reading comprehension Character-augmented embedding

作者: Zhuosheng Zhang Yafang Huang Pengfei Zhu Hai Zhao

作者单位: Department of Computer Science and Engineering,Shanghai Jiao Tong University,Shanghai,China;Key Labo Department of Computer Science and Engineering,Shanghai Jiao Tong University,Shanghai,China;Key Labo

会议类型: 国际会议

会议名称: 2018自然语言处理与中文计算国际会议(NLPCC2018)

会议地点: 呼和浩特

会议语种:英文

页码: 27-39

在线出版日期: 2018-08-26（万方平台首次上网日期，不代表论文的发表时间）