基于文本挖掘的搭配词典自动架构探讨  

Automatic Construction of CollocationsDictionary Based on Text Mining

作　　者：张辉[1] 薛贵荣[2] 

机构地区：[1]上海工程技术大学电子电气工程学院,上海200065 [2]扬州大学计算机科学系,扬州225009

出　　处：《上海工程技术大学学报》2004年第4期323-326,共4页Journal of Shanghai University of Engineering Science

基　　金：上海工程技术大学青年基金资助项目(2003Q03)

摘　　要：研究词语搭配的关系对于自然语言处理有很大的帮助。目前对计算机用的搭配词典是用人工方法实现的,它由人工进行维护,有更新慢、收藏的词少等缺点。为此,利用文本挖掘技术对大规模语料库进行分析,挖掘词语搭配的深层关系,在此基础上自动建立词语搭配词典,实验结果显示该方法是有效的。A collocations dictionary is the useful component to many natural language and spoken language processing application such as grammar checking, text-speech conversion and machine translation. Currently The collocations dictionary is constructed artificially, firstly it may not be updated frequently and many lexicon entries may be not available. Secondly to construct a dictionary may need lots of human resources. In this paper, text-mining approach for constructing a collocations dictionary is surveyed. The main purpose is to enable cheap and quick acquisition of a collocations dictionary from a large text corpus. Experimental results show that the approach is effective and suitable.

关 键 词：文本挖掘 互信息 关联规则挖掘 搭配词典 

分 类 号：H085.5[语言文字—语言学]