A Kind of Vector Space Representation Model Based on Semantic in the Field of English Standard Information

Abstract

Through the Study of English semantic similarity, based on the previous, we designed the method of calculating English semantic similarity by Word Net. We proposed a vector space representation model of English standard information based on semantic similarity and applied the model on text clustering. This model resolves the problem of semantic correlation between the characteristics which is ignored by vector space model and reduces the semantic loss of practical application systems. Finally, by the experimentation we prove that this method improve the accuracy of text clustering.