Measuring the Sentence Level Similarity

Abstract

This article describes a method used to calculate the similarity between short English texts, specifically of sentence length. The described algorithm calculates semantic and word order similarities of two sentences. In order to do so, it uses a structured lexical knowledge base and statistical information from a corpus. The described method works well in determining sentence similarity for most sentence pairs, consequently the implemented method can be used in computer automated sentence similarity measurements and other text based mining problems. We encapsulated the implemented algorithm in a .NET library, to simplify the task of calculating sentence similarity for end users.