版权所有:内蒙古大学图书馆 技术提供:维普资讯• 智图
内蒙古自治区呼和浩特市赛罕区大学西街235号 邮编: 010021
作者机构:NLP Lab College of Information Science and Engineering Northeastern University Shenyang 110819 China Key Laboratory of Medical Image Computing Northeastern University Shenyang Liaoning China
出 版 物:《Journal of Computational Information Systems》 (J. Comput. Inf. Syst.)
年 卷 期:2010年第6卷第5期
页 面:1483-1494页
核心收录:
主 题:Websites
摘 要:In this paper, we propose a web assistant based approach to translate organization name from Chinese to English. Firstly, all the OOV terms in the input are recognized by a CRFs model. And the input is then partially translated without considering these recognized OOV terms. Secondly, we construct some efficient queries to help search engines find some web pages that contain both the original input and its correct translation. We construct queries from different aspects and correlative words information is used during query construction. At last, a similarity matching and limited expansion based translation identification approach is proposed to identify the correct translation from the returned web pages. Experimental results show that our method can handle Chinese-English organization name translation well and can improve performance of organization name translation substantially. Copyright © 2010 Binary Information Press May, 2010.