Neural recovery machine for Chinese dropped pronoun

作     者：Weinan ZHANG Ting LIU Qingyu YIN Yu ZHANG 

作者机构：Research Center for Social Computing and Information RetrievalSchool of Computer Science and Technology Harbin Institute of TechnologyHarbin 150001China 

出 版 物：《Frontiers of Computer Science》 (中国计算机科学前沿（英文版）)

年 卷 期：2019年第13卷第5期

页      面：1023-1033页

核心收录：

学科分类：12[管理学] 1201[管理学-管理科学与工程(可授管理学、工学学位)] 08[工学] 

基　　金：This paper was supported by the National Natural Science Foundation of China (Grant Nos. 61502120, 61472105, 61772153) Heilongjiang philosophy and social science research project (16TQD03) Young research foundation of Harbin University (HUYF2013-002) the project of university library work committee of Heilongjiang (2013-B-065) 

主　　题：neural network Chinese dropped pronoun re-covery Chinese zero pronoun resolution 

摘      要：Dropped pronouns (DPs) are ubiquitous in pro-drop languages like Chinese, Japanese etc. Previous work mainly focused on painstakingly exploring the empirical features for DPs recovery. In this paper, we propose a neural recovery machine (NRM) to model and recover DPs in Chinese to avoid the non-trivial feature engineering process. The experimental results show that the proposed NRM significantly outperforms the state-of-the-art approaches on two heterogeneous datasets. Further experimental results of Chinese zero pronoun (ZP) resolution show that the performance of ZP resolution can also be improved by recovering the ZPs to DPs.