摘要
词义排歧在自然语言处理领域占有重要地位。词义排歧的精确率依赖于排歧知识的完备性。但是目前使用基于词典的和基于语料库的词义排歧方法来获取排歧知识的效果都不令人满意。文章将介绍了一个汉语词义自动标注系统，该系统实现了基于语料库的无指导的词义排歧模型，比较成功地解决了排歧知识的获取瓶颈问题。文章将给出系统的总体设计和具体实现，并给出系统测试结果。
： Word Sense Disambiguation has always been important in Natural Language Processing．The precision rate of word sense disambiguation depends on the completeness of disambiguation knowledge．Main methods currently in use，which are based on dictionary and on corpora，to disambiguate word sense are not satisfiable．This paper introduces an automatic system of Chinese word sense tagging．It implements an untutorial word sense disambiguation model based on corpora and solves the disambiguation knowledge acquisition bottleneck successfully．The paper also describes the whole design and concrete implementation and gives the performance evaluation．
出处
《计算机工程与应用》
CSCD
北大核心
2001年第17期170-173,共4页
Computer Engineering and Applications
基金
国家重点自然科学基金项目--语料库语言学研究的理论
方法和工具
关键词
自然语言处理
词义排歧
汉语词义
自动标准系统
设计
： Natural Language Processing，word sense disambiguation，disambiguation knowledge
