摘要
语义歧义大量存在于自然语言中,其排歧成功率是衡量机器翻译、信息检索、文本分类等自然语言处理软件性能的重要指标.对语义消歧这一自然语言理解领域的难点技术问题进行了探讨,分析了统计学习方法在语义消歧中的应用,阐述了统计语义消歧的有关技术,并给出一个基于贝叶斯与机读词典的语义消歧实例,取得了较高的语义消歧成功率.
The senmantic ambiguity widly exists in natural language.The accuracy rate of sense ambiguation is the most important target of a software in the fields of machine translation,information search and text classification.In this paper we probe into the techniques of senmantic disambiguation,which is the most difficult problem in the natural language understanding field.We analyse the application of statistical learning methods in the senmantic disambigution and expatiate the correlative technologies.Finally w...
出处
《西南民族大学学报（自然科学版）》
CAS
2007年第1期193-196,共4页
Journal of Southwest Minzu University(Natural Science Edition)
关键词
歧义
自然语言理解
语义消歧
统计学习方法
语料库
ambiguity
natural language understanding
senmantic disambigution
statistical learning method
corpus
