计算机工程与应用 ›› 2009, Vol. 45 ›› Issue (24): 125-129.DOI: 10.3778/j.issn.1002-8331.2009.24.037

• 数据库、信息处理 • 上一篇    下一篇

专利文献翻译中并列结构的处理

赵 然,晋耀红   

  1. 中国科学院 声学研究所,北京 100190

  • 收稿日期:2008-10-17 修回日期:2009-02-17 出版日期:2009-08-21 发布日期:2009-08-21
  • 通讯作者: 赵 然

Processing of parallel structures in patent articles translation

ZHAO Ran,JIN Yao-hong   

  1. Institute of Acoustics,Chinese Academy of Sciences,Beijing 100190,China

  • Received:2008-10-17 Revised:2009-02-17 Online:2009-08-21 Published:2009-08-21
  • Contact: ZHAO Ran

摘要:

针对专利文献翻译中的复杂并列结构的处理,提出了一种预处理和后处理的方法——拆分合并法。它弥补了统计翻译系统在复杂结构方面的劣势,同时保留统计翻译在经验句式、人力成本等方面优于规则系统的特点。实验表明,这种方法稳定地提高了翻译系统的准确率。此外,它独立于具体的统计翻译系统,可以方便地移植到不同的统计翻译系统上。

关键词: 机器翻译, 语法结构, 专利文献

Abstract: In order to process parallel structures during translating patent articles,a pre-processing and post-processing method (Separating-combining Method) is proposed.It fixes disadvantages of the statistical translation system in processing complex structures,while maintains advantages in processing idioms and saving cost of human labor.Experiments show that this method consistently improves the accuracy of translation system.Besides,it is independent of the particularity of statistical translation system,and can be conveniently applied on different systems.

Key words: machine translation, syntactic structure, patent article

中图分类号: