利用上下文信息解决汉语组合型歧义  

Solving Combinatorial Ambiguities in Chinese Word Segmentation Using Contextual Information

作　　者：冯素琴[1] 陈惠明[1] 

机构地区：[1]忻州师范学院,忻州034000

出　　处：《电脑开发与应用》2007年第1期23-25,共3页Computer Development & Applications

基　　金：山西省忻州师范学院基金资助项目(编号:200307)

摘　　要：汉语自动分词问题是制约中文信息处理发展的瓶颈之一,歧义切分又是影响分词系统切分精度的重要因素。在对已有方法深入分析的基础上,提出利用上下文信息的消歧策略。结果显示,经多次学习后搭配信息显示的消歧参数逐渐趋于稳定,且消歧准确率有大幅度提高。The disambiguation of combinatorial ambiguities in Chinese word segmentation is still an unsolved problem till now. On the basis of the analysis the methods,this thesis puts forwards solving combinatorial ambiguity using contextual information. The following is for the main steps ：get the original information from larger corpus ,study and form the dynamic information ,use the reformed rules to disambiguate the combinatorial ambiguities. The results of the test are：The average accuracies of colsing test are improved and contextual information are stabilized ,so this method is simple and valid to combinatorial ambiguities.

关 键 词：汉语自动分词 组合歧义 消歧 

分 类 号：TP391.1[自动化与计算机技术—计算机应用技术]