摘要
短文本聚类研究广泛应用在不同领域,而短文本呈现的稀疏性、歧义与噪声多的特点,要求聚类处理过程中短文本的向量表示能够充分编码其有效特征,本文从短文本聚类的两个关键步骤,即文本的向量化表示与聚类效果评价进行研究。据此对短文本聚类方法的演化过程与优化方法进行了总结,并针对现有研究对未来的发展方向进行展望。
The clustering research of short texts is widely used in different fields.The sparseness,ambiguity and noise of short texts require that the vector representation of short texts in the clustering process can fully encode its effective features.Therefore,this article starts from two key steps of the short texts clustering,namely the vectorized representation of the text and the clustering effect evaluation are studied.Based on this,the evolution process and optimization method of the short text clustering method are summarized,and the future development direction of the existing research is prospected.
作者
和志强
王梦雪
马宁
陈萌
HE Zhi-qiang;WANG Meng-xue;MA Ning;CHEN Meng(School of Information Technology, Hebei University of Economics and Business, Shijiazhuang Hebei 050061, China)
出处
《河北省科学院学报》
CAS
2021年第5期34-40,共7页
Journal of The Hebei Academy of Sciences
基金
河北省科技研发平台建设专项(199676256D)。
关键词
短文本聚类
文本表示
聚类评价
Short text clustering
Text representation
Clustering evaluation
