Study on Chinese person name disambiguation based on multi-stage strategy

Namesake is a very common phenomenon both in real world and in the Internet. This paper combines the problem of name disambiguation with clustering technique and attempts to achieve the purpose of person name disambiguation through clustering technique by putting different texts pointing to the same person to one cluster. In this paper, we propose a multi-stage strategy for text clustering. In the first stage, the bias classifier is used to generate the initial categories. The second stage is a re-clustering process of agglomerative hierarchical clustering to achieve the name disambiguation. Experimental results show that the method proposed in this paper can effectively improve the accuracy of person name disambiguation.