基于语义扩展度的中文分词交叉歧义处理方法  

A Chinese overlapping ambiguity resolution method based on semantic expansion

作　　者：尹倩[1] 

机构地区：[1]安徽体育运动职业技术学院,安徽合肥230051

出　　处：《南昌工程学院学报》2016年第1期56-60,共5页Journal of Nanchang Institute of Technology

基　　金：安徽省高校优秀青年人才基金重点项目(2013SQRW125ZD);安徽省高校人文社科重点项目(SK2015A659)

摘　　要：提出一种歧义字段与其所在句子语义联系为依据的中文分词交叉歧义处理方法。该方法模拟人浏览句子按照语义和词语相关度寻找消歧证据的经验,通过比较计算歧义字段与整个句子的语义相似度和语义相关度,提出基于语义扩展度的中文分词交叉歧义处理算法,进而提高分词准确率,与经典的ICTCLAS分词系统相比,切分准确率和召回率均有很大提高。This paper proposes a novel approach to overlapping ambiguity resolution in Chinese word segmentation,based on semantic correlation between overlapping ambiguity and its sentence. It simulates the habit of using semantic correlation to browse the sentences. Our experimental results show that compared with the classical ICTCLAS segmentation method,our COARSE algorithm has an obvious advantage on overlapping ambiguity resolution： the accuracy rate is increased by 3. 18 percent on average,and the average recall rate is increased by 3. 33%.

关 键 词：中文自动分词 交叉歧义 语义扩展度 

分 类 号：TP391.1[自动化与计算机技术—计算机应用技术]