Using sense recognition to resolve the problem of polysemy in building a taxonomic hierarchy

Abstract

Hyponymy is used to build a taxonomic hierarchy. But the terms in hyponymy may have multiple senses. It will cause the problem of polysemy and affect the building of taxonomic hierarchy. In order to solve the problem, we present a method of sense recognition of hyponymy based on vector space model. Firstly we acquire the contexts of hyponymy from Chinese free corpus. Secondly we use Cilin to construct a relation-word vector space. Then we use latent semantic analysis to reduce the dimension of the vector space. In the final phase, we recognize the senses of hyponymy using average-group clustering. Experimental results show that the method can provide adequate discrimination of the different senses. © 2008 Springer-Verlag Berlin Heidelberg.