Word Sense Disambiguation-based Sentence Similarity

摘要

Previous works tend to compute the similarity between two sentences based on the comparison of their nearest meanings. However, the nearest meanings do not always represent their actual meanings. This paper presents a method which computes the similarity between two sentences based on a com- parison of their actual meanings. This is achieved by transforming an existing most-outstanding corpus-based measure into a knowledge-based measure, which is then integrated with word sense dis- ambiguation. The experimental results on a standard data set show that the pro- posed method outperforms the baseline and the improvement achieved is statisti- cally significant at 0.025 levels.