一种基于知网的中文词义消歧算法  

An Approach to Chinese Word Sense Disambiguation Based on HowNet

作　　者：张明宝[1] 马静[1] 

机构地区：[1]南京航空航天大学经济与管理学院信息管理与电子商务系,江苏南京210016

出　　处：《计算机技术与发展》2009年第2期9-11,15,共4页Computer Technology and Development

基　　金：国防技术基础项目(1009-234039)

摘　　要：词义消歧对自然语言处理领域许多问题的研究具有重要的理论和实践价值。针对该问题,提出了一种基于知网的中文词义消歧算法。为了考虑上下文词汇对词义消歧的不同影响,以语义相似度计算为基础,设计了三种语义联系强度计算方法,并且制定了四条词义消歧规则,依此实现中文词义消歧。实验数据显示该方法可获得65%左右的召回率和75%左右的准确率。The automatic disambiguation of word senses has great theeretical and practical significance in many fields of natural language processing. Presents an approach to Chinese word sense disambiguation based on HowNet. In order to take into account different effects of context to word sense disambiguation, three methods of calculating sense relation strength and four related rules are designed based on semantic similarity computing. The recall/accuracy rate of experiment are respective about 65% and 75%.

关 键 词：词义消歧 语义相似度 知网 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]