摘要
针对信息检索中存在的词语排除关系问题,给出排除词的定义并说明排除词在信息检索中的作用。指出排除词实质上是最大准交集型歧义切分字段的伪歧义切分所导致的,描述排除词的识别方法,并给出识别的结果,并在实际的信息检索平台上对排除词词库进行应用测评。
This paper introduces the phenomenon of mutually exclusive words and poses the role of mutually exclusive words identification in information retrieval system. The authors indicate that mutually exclusive words can be identified from the pseudo - ambiguity results after segmentation of maximal quasi overlapping ambiguity string, then present the method and result of the mutually exclusive words identification. Also the application of mutually exclusive words is provided.
出处
《现代图书情报技术》
CSSCI
北大核心
2007年第2期44-48,共5页
New Technology of Library and Information Service
关键词
信息检索
中文信息处理
交集型歧义
除词识别
伪歧义
Information retrieval Chinese information processing Overlapping ambiguity Mutually exclu- sive words recognition Pseudo -ambiguity
