Neural Chinese Word Segmentation as Sequence to Sequence Translation

被引:3
作者
Shi, Xuewen [1 ]
Huang, Heyan [1 ]
Jian, Ping [1 ]
Guo, Yuhang [1 ]
Wei, Xiaochi [1 ]
Tang, Yi-Kun [1 ]
机构
[1] Beijing Inst Technol, Sch Comp Sci & Technol, Beijing Engn Res Ctr High Volume Language Informa, Beijing 100081, Peoples R China
来源
SOCIAL MEDIA PROCESSING, SMP 2017 | 2017年 / 774卷
基金
中国国家自然科学基金;
关键词
Chinese word segmentation; Sequence-to-sequence; Chinese spelling correction; Natural language processing;
D O I
10.1007/978-981-10-6805-8_8
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Recently, Chinese word segmentation (CWS) methods using neural networks have made impressive progress. Most of them regard the CWS as a sequence labeling problem which construct models based on local features rather than considering global information of input sequence. In this paper, we cast the CWS as a sequence translation problem and propose a novel sequence-to-sequence CWS model with an attention-based encoder-decoder framework. The model captures the global information from the input and directly outputs the segmented sequence. It can also tackle other NLP tasks with CWS jointly in an end-to-end mode. Experiments on Weibo, PKU and MSRA benchmark datasets show that our approach has achieved competitive performances compared with state-of-the-art methods. Meanwhile, we successfully applied our proposed model to jointly learning CWS and Chinese spelling correction, which demonstrates its applicability of multi-task fusion.
引用
收藏
页码:91 / 103
页数:13
相关论文
共 26 条
[1]  
[Anonymous], P 10 INT C LANG RES
[2]  
[Anonymous], 2016, P C ASS MACH TRANSL
[3]  
[Anonymous], 2010, Proceedings of the Coling 2010: Demonstrations
[4]  
[Anonymous], ARXIV E PRINTS
[5]  
[Anonymous], 2010, ACM T ASIAN LANGUAGE
[6]  
[Anonymous], ARXIV160604300
[7]  
[Anonymous], 2001, P 18 INT C MACHINE L
[8]  
Bahdanau Dzmitry, 2015, 3 INT C LEARNING REP
[9]  
Chen X., 2015, P 2015 C EMP METH NA, P1197
[10]  
Chen XC, 2015, PROCEEDINGS OF THE 53RD ANNUAL MEETING OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS AND THE 7TH INTERNATIONAL JOINT CONFERENCE ON NATURAL LANGUAGE PROCESSING, VOL 1, P1744