Semantic Network Based Approach to Compute Term Semantic Similarity

Abstract

Measuring semantic similarity between two terms is essential for a variety of text analytics and understanding applications.This paper presents a approach for measuring the semantic similarity between terms. Previous work on semantic similarity methods have focused on either the structure of the semantic network between terms, or only on the Information Content (IC) of terms. However, existing approaches are limited by the size of the knowledge base and corpus. We propose an efficient and effective approach for computing semantic similarity using a large scale semantic network. This approach base on Probase, which is a big graph of concepts. Knowledge in Probase is harnessed from billions of web pages and years' worth of search logs. Through experiments performed on well known word similarity datasets, we show that our approach is much more efficient than all competing algorithms.