Chinese-Vietnamese Word Alignment Method Based on Bidirectional RNN and Linguistic Features

被引：0

作者：

Gao, Shengxiang ^{[1
]}

Zhu, Haodong ^{[1
]}

Wang, Zhuo ^{[1
]}

Yu, Zhengtao ^{[1
]}

Wang, Xiaohan ^{[1
]}

机构：

[1] Kunming Univ Sci & Technol, Sch Informat Engn & Automat, 727 South Jingming Rd, Kunming 650500, Yunnan, Peoples R China

来源：

COMPUTER SUPPORTED COOPERATIVE WORK AND SOCIAL COMPUTING, CHINESECSCW 2018 | 2019年 / 917卷

基金：

中国国家自然科学基金;

关键词：

Word alignment; Chinese-Vietnamese; Bidirectional recurrent neural network; Linguistic features;

D O I：

10.1007/978-981-13-3044-5_33

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

We propose an automatically word alignment method of Chinese-Vietnamese based on bidirectional RNN and linguistic features. With the bidirectional RNN, we can obtain the context information of both forward and backward direction. Moreover, some bilingual features are also integrated. In the process of training model. The experiments show that the approach proposed outperform the previous method, and suggests that linguistic features and context information can effectively enhance the effect of word alignment.

引用

页码：454 / 465

页数：12

共 13 条

[1] [Anonymous], 1996, Proceedings of the 16th conference on Computational linguistics, DOI [DOI 10.3115/993268.993313, 10.3115/993268.993313]
[2] AULI M, 2013, P 2013 C EMP METH NA, P1044, DOI DOI 10.1057/AJP.2014.10
[3] Brown P. F., 1993, Computational Linguistics, V19, P263
[4] Dyer Chris., 2011, Proceedings of the 49th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies-Volume 1, P409
[5] Gutmann M., 2010, P 13 INT C ARTIFICIA, P297
[6] Kalchbrenner N., 2013, Proceedings of the ACL Conference on Empirical Methods in Natural Language Processing (EMNLP), P1700
[7] Mikolov T, 2012, IEEE W SP LANG TECH, P234, DOI 10.1109/SLT.2012.6424228
[8] Mikolov T, 2010, 11TH ANNUAL CONFERENCE OF THE INTERNATIONAL SPEECH COMMUNICATION ASSOCIATION 2010 (INTERSPEECH 2010), VOLS 1-2, P1045
[9] Mnih A., 2012, P 29 INT C INT C MAC, P419
[10] [莫媛媛 Mo Yuanyuan], 2016, [山东大学学报. 理学版, Journal of Shandong University. Natural Science], V51, P77

← 1 2 →