基于英汉机译实现跨语言信息检索  

Implementing Cross-Language Information Retrieval Based on English-Chinese Machine Translation

作　　者：张玥杰[1] 郭依昆[1] 连理[1] 吴立德[1] 

机构地区：[1]复旦大学计算机科学与工程系,上海200433

出　　处：《小型微型计算机系统》2004年第7期1135-1140,共6页Journal of Chinese Computer Systems

基　　金：国家自然科学基金 (60 2 0 3 0 10 )资助;国家 863基金(2001AA114 12 0 )资助;复旦大学青年科学基金资助

摘　　要：随着日益增长的大量信息成为可利用的、用户面对查询一个多语种文本集合的情形 ,变得越来越普遍 .这就产生一个非常重要的问题—以一种语言描述的用户查询与以不同语言书写的文本之间的匹配问题 ,也就是一种如何跨越语言界限的问题 ,即跨语言信息检索 (Cross- L anguage Information Retrieval,CL IR) .针对该项任务建立了一个面向英汉的跨语言信息检索系统 ,并以此为基础提交了相关的几组运行结果 .同时 ,结合所构建的汉语 IR系统 ,实现完整的英—汉 CLWith the ever growing amount of information available to us all, situations when a user of an information retrieval system is faced with the task of querying a multilingual document collection are becoming increasingly common. Thus a very important problem is formed, which is the matching of user queries specified in one language against documents written in a different language crossing the language boundary, namely Cross Language Information Retrieval (CLIR). have established an English Chinese Oriented Cross Language Information Retrieval System for this task, and submitted several related runs. So combining the Chinese Information Retrieval System established by us, the complete English Chinese CLIR process can be implemented successfully.

关 键 词：信息检索 跨语言信息检索 机器翻译 语料库 语言学资源 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]