Graph-based text representation model and its realization

Abstract

In this paper, on the foundation of summarizing several common used text representation models, such as Boolean model, probability model, vector space model and so on, mainly according to the defects of the vector space model, the word semantic space is proposed. And in the word semantic space, a graph-based text representation model is designed. Some properties of this type of text representation model have been given, and this model can describe the words semantic constraints in the text. At the same time, this model can also solve the defects of vector space model, such as the order or words, the boundary between sentences and phrases, etc. And at last the method of computing the text similarity is put forward.