基于隐喻词扩展的短文本聚类算法

Short-Text Clustering Algorithm Based on Extension of Metaphorical Words

针对目前短文本词汇量少、表达形式多样,导致同种类文本聚类方法无效的问题,提出一种利用中文维基百科的丰富词汇间关系对短文本的隐喻词进行扩充的方法,以解决短文本包含信息少、词汇表达形式多样的不足.实验结果表明,该算法可有效提升短文本的聚类效果.

Aiming at the problem that short text contained small words and various expressions,which led to ineffective clustering of the same category of text,we proposed a method to extend metaphorical words in short texts by using the rich lexical relationships in Chinese Wikipedia,which solved the shortages of the short text withless information and various lexical expressions.Experimental results show that the algorithm can effectivelyenhance the clustering effect of short text.