Semantic similarity measure for graph-based sentences

Graphical text representation method attempts to capture the syntactical structure and semantics of documents. As such, they are the preferred text representation approach for a wide range of problems namely in natural language processing, information retrieval and text mining. In a number of these applications, it is necessary to measure the similarity between knowledge represented in the graphs. In this paper, we present semantic similarity measure to compare graph based representation of sentences. The proposed method incorporates computational linguistic method to obtain syntactical information prior to representation with graph. Word synonyms are embedded in the graph representation to support semantic matching. In this paper, we present our idea and initial results on the feasibility of the proposed similarity measurement method.