Construct chunk-level templates for improving rule-based machine translation

被引：0

作者：

Yin, Dechun ^{[1
]}

Zhang, Dakui ^{[1
]}

机构：

[1] School of Computer Science and Technology, Beijing Institute of Technology

来源：

Journal of Computational Information Systems | 2013年 / 9卷 / 14期

关键词：

Machine translation; Template-based machine translation; Translation template;

D O I：

10.12733/jcis6299

中图分类号：

学科分类号：

摘要：

For improving the conventional rule-based machine translation by using translation templates, we propose a data-driven and semiautomatic method, which can semiautomatically extract translation templates at chunk level from the unannotated Chinese corpus. The method includes four steps: morphological analysis, chunk analysis, extract and refine. After extracting and preforming the preliminary templates, we manually add English translations for them and then get the ultimate templates, which are used in a template-based machine translation system. The experimental results show that the method is effective to improve the quality of machine translation, and that the template-based machine translation system outperforms the conventional rule-based machine translation system without templates. 1553-9105/Copyright © 2013 Binary Information Press.

引用

页码：5505 / 5512

页数：7

共 7 条

[1] Altay Guvenir H., Cicekli I., Learning translation templates from examples, Inform. Syst., 23, 6, pp. 353-363, (1998)
[2] Cicekli I., Altay Guvenir H., Learning translation templates from bilingual translation examples, Appl. Intell., 15, 1, pp. 57-76, (2001)
[3] Watanabe H., Kurohashi S., Aramaki E., Finding structural correspondences from bilingual parsed corpus for corpus-based translation, Proc. 18th Int. Conf. Computational Linguistics, pp. 906-912, (2000)
[4] Imamura K., Hierarchical phrase alignment harmonized with parsing, Proc. 6th Natural Language Processing Pacific Rim Symp, pp. 377-384, (2001)
[5] Hu R., Zong C., Xu B., Semiautomatic acquisition of translation templates from monolingual unannotated corpora, Proceedings of International Conference on Natural Language Processing and Knowledge Engineering, pp. 63-167, (2003)
[6] Imamura K., Sumita E., Matsumoto Y., Feedback cleaning of machine translation rules using automatic evaluation, The 4lst Annual Meeting of the Association for Computational Linguistics, pp. 447-454, (2003)
[7] Zhang C.-X., Li S., Yang M.-Y., Zhao T.-J., Shi X.-S., A method of rule-base optimization based on evaluation, Journal of Harbin Institute of Technology (New Series), 16, 5, pp. 708-712, (2009)

← 1 →