期刊文献+

基于混合策略的汉英双向机器翻译系统的设计 被引量:2

Design of Bi-directional English-Chinese Machine Translation Systems Based on Hybrid Strategy
下载PDF
导出
摘要 本文对于机器翻译方法中的基于规则的方法、基于模板的方法及基于实例的方法进行了比较;对于完全句法分析和浅层句法分析方法也进行了分析。然后介绍了将上述方法结合起来的汉英双向机器翻译系统的设计思想及工作流程。基于混合策略的目的是为了提高汉英双向机器翻译系统的译文质量。实验结果表明,本文提出的设计思想对于机器翻译译文质量的提高具有良好的效果。基于模板及实例方法对于译文质量提高的贡献率为:口语为15%,篇章翻译为10%。 This paper compares role-based methods, template-based methods and example-based methods in machine translation, as well as comparing complete parsing methods and shallow parsing methods. The design and workflow of combining the above methods in bi-directional Chinese-English machine translation systems are also introduced in this paper. The purpose of the hybrid strategy is to improve the output quality of bi-directional Chinese-English machine ~ranslation systems. The empirical result shows that this design approach has resulted in significant improvement on the translation quality of the machine translation s^stems. The contribution rate for improving MT output by using the template-based method and the example-based method is 15% for oral English and 10% for written English respectively.
出处 《中文信息学报》 CSCD 北大核心 2006年第B03期25-30,共6页 Journal of Chinese Information Processing
基金 国家863高技术研究发展计划资助项目(2004AA117010-04) 国家自然科学基金资助项目(60572132 60372106)
关键词 翻译模板 浅层分析 混合策略 机器翻译 translation template shallow parsing hybrid strategy machine translation
  • 相关文献

参考文献2

  • 1冯志伟.机器翻译的现状和问题[A].徐波,孙茂松,靳光瑾主编.中文信息处理若干重要问题[C].北京:科学出版社,2003,353—377.
  • 2孙宏林,俞士汶.浅层句法分析方法概述[J].当代语言学,2000,2(2):74-83. 被引量:38

二级参考文献29

  • 1周强.一个汉语短语自动界定模型[J].软件学报,1996,7(A00):315-322. 被引量:9
  • 2Abney, 1996b. Partial parsing via finite-state cascades. In Proceedings of the ESSLLI '96 Robust Parsing Workshop.
  • 3Argamon, S., I. Dagon and Y. Krymolowsky. 1998. A memory-based approach to learning shallow natural language patterns. In Proceedings of COLING-ACL '98. Pp. 67-73.
  • 4Brill, Eric. 1995. Unsupervised learning of Disambiguation Rules for part of speech tagging. In Proceedings of the 3rd Workshop on Very Large Corpora. Pp. 1-13.
  • 5Cardie, Claire and David Pierce. 1998. Error-driven pruning of treebank grammars for base noun phrase identification. In Proceedings of COLING-ACL '98. Pp. 218-224.
  • 6Chen, Kuang-hua and Chen, Hsin-Hsi. 1994. Extracting noun phrases from large-scale texts: a hybrid approach and its automatic evaluation. In Proceedings of the 32nd Annual Meeting of the Association for Computational binguistics. Pp. 234-241.
  • 7Chen, Hsin-Hsi and Lee, Yue-Shi. 1995. Development of a partially bracketed corpus with part-of- speech information only. In Proceedings of the 3rd Workshop on Very Large Corpora. Pp. 162-172.
  • 8Church, K. 1988. A stochastic parts program and noun phrase parser for unrestricted text. In Proceedings of the Second Conference on Applied Natural Language Processing. Pp. 136-143.
  • 9Collins, M. 1996. A new statistical parser based on bigram lexical dependencies. In Proceedings of the 34th Annual Meeting of the Association for Computational Linguistics. Pp. 184-191.
  • 10Fano, R. M. 1961. Transmission of lnformation, A Statistical Theory of Communication. MIT Press.

共引文献38

同被引文献19

引证文献2

二级引证文献7

相关作者

内容加载中请稍等...

相关机构

内容加载中请稍等...

相关主题

内容加载中请稍等...

浏览历史

内容加载中请稍等...
;
使用帮助 返回顶部