基于主题模型的中文词义归纳  

Chinese word sense induction based on topic model

作　　者：高章敏 何祥[1] 刘嘉勇[1,2] 汤殿华 GAO Zhang-Min HE Xiang LIU Jia-Yong TANG Dian-Hua(College of Electronics and Information, Sichuan University, Chengdu 610065, China Science and Technology on communication Security Laboratory, Chengdu, China)

机构地区：[1]四川大学电子信息学院,成都610065 [2]保密通信重点实验室,成都610041

出　　处：《四川大学学报（自然科学版）》2016年第6期1269-1272,共4页Journal of Sichuan University(Natural Science Edition)

基　　金：保密通信重点实验室基金(9140C110401140C11053)

摘　　要：词义归纳是在给定包含多义词语料的条件下,识别出多义词词义的过程,通常是采用聚类的方法.本文提出了基于主题模型的方法来解决中文词义归纳问题,基于主题模型的词义归纳方法关键之处在于使用文档的主题概率分布来推断多义词的词义分布.实验结果表明,本文方法在测试数据上获得了77.58%FScore值.Sense Induction is the process of identifying the word sense given its context, often treated as a clustering task. In this paper, the authors present a approach to Chinese word sense induction which is based on topic modeling. Key to the methodology in this paper is the use of probabilistic assignment of topics distributions to documents to estimate sense distributions. Experimental results show that the method in the paper could achieve 77.58% scores of Fscore on the development data set.

关 键 词：词义归纳 主题模型 隐含狄利克雷分布 词义消歧 

分 类 号：TP391.1[自动化与计算机技术—计算机应用技术]