首页 | 本学科首页   官方微博 | 高级检索  
     

基于错误驱动的翻译模板自动获取
引用本文:张春祥,梁颖红,于林森.基于错误驱动的翻译模板自动获取[J].计算机科学,2010,37(7):229-232.
作者姓名:张春祥  梁颖红  于林森
作者单位:1. 哈尔滨理工大学软件学院,哈尔滨,150080
2. 苏州市职业大学计算机系,苏州,215104
3. 哈尔滨理工大学计算机科学与技术学院,哈尔滨,150080
基金项目:国家自然科学基金,黑龙江省教育厅科学技术研究项目基金,哈尔滨理工大学青年科学研究基金,江苏省现代企业信息化应用支撑软件工程技术研究开发中心项目 
摘    要:翻译模板自动获取是提高MT系统译文输出质量和领域快速移植能力的关键性因素.利用Tree-to-String方法来抽取等价对,使用错误驱动的学习方法来获取翻译模板.将获取的模板用于MTS2005中,同时对其译文质量进行开放测试.实验结果表明:所提出的模板获取方法的性能要好于传统方法,当新模板加入系统原模板库后,开放测试语料的3元Nist评测分数提高了3.41%.

关 键 词:翻译模板  错误驱动  Nist评测
收稿时间:2009/8/18 0:00:00
修稿时间:2009/10/26 0:00:00

Automatic Acquisition of Translation Templates Based on Error-driven
ZHANG Chun-xiang,LIANG Ying-hong,YU Lin-sen.Automatic Acquisition of Translation Templates Based on Error-driven[J].Computer Science,2010,37(7):229-232.
Authors:ZHANG Chun-xiang  LIANG Ying-hong  YU Lin-sen
Affiliation:(School of Software, Harbin University of Science and Technology, Harbin 150080, China),(School of Computer Engineering,Suzhou Vocational University,Suzhou 215104,China),(College of Computer Science and Technology, Harbin University of Science and Technology, Harbin 150080, China)
Abstract:Automatic acquisition of translation templates is important for MT system to improve its translation quality and its ability of adapting to new domain. In this pap}r,hrecto-String method was applied to extract translation equivalents. Error-driven learning method was used to acctuire templates. These templates were applied to MTS2005 , and open test experiments were conducted for its translation quality. The experiment results show that the performance of new method in this paper is better than that of old method. Combination of new acquired templates and original ones makes assessment score of open test corpus improved by 3. 41 0 o under 3-gram Nist assessment metric.
Keywords:Translation templates  Error-driven  Nist assessment
本文献已被 万方数据 等数据库收录!
点击此处可从《计算机科学》浏览原始摘要信息
点击此处可从《计算机科学》下载全文
设为首页 | 免责声明 | 关于勤云 | 加入收藏

Copyright©北京勤云科技发展有限公司  京ICP备09084417号