计算机与数字工程2018，Vol.46Issue(5)：933-935,1067,4.DOI:10.3969/j.issn.1672-9722.2018.05.017
基于句法结构分析的中文文本聚类方法研究
Research on Chinese Text Clustering Based on Sentence Structure Analysis
摘要
Abstract
Most of the existing K-means clustering algorithms are based on the data carriers,they are difficult to apply to Chi-nese text clustering analysis.In this paper,a new text clustering method based on sentence structure analysis is introduced,which can accurately calculate the senmantic similarity and cluster texts.The method combines the advantages of the improved K-means, the sentence structure analysis is defined for reducing the complexity of the text set to improve the accuracy of the calculation of the semantic similarity between texts. Experimental results show that the method can gain a higher precision(0.96)than some widely used clustering methods.关键词
文本聚类/K-means/句法结构分析Key words
text clustering/K-means/sentence structure analysis分类
信息技术与安全科学引用本文复制引用
尹积栋,谢茶花,彭崧,刘红,曾昭虎..基于句法结构分析的中文文本聚类方法研究[J].计算机与数字工程,2018,46(5):933-935,1067,4.基金项目
江西省教育厅科学技术研究项目"基于句法结构分析的文本聚类方法及应用研究"(编号:GJJ151492)资助. （编号:GJJ151492）
