Subjective Bayes Method for Word Semantic Similarity Measurement

Measuring semantic similarity between words is a classical problem in nature language processing, the result of which can promote many applications such as machine translation, word sense disambiguation, ontology mapping, computational linguistics, etc. This paper combines knowledge-based methods with statistical methods in measuring words similarity, the novel aspect of which is that subjective Bayes method is employed. Firstly, extract evidences based on Word Net; secondly, analyze reasonableness of candidate evidence using scatter plot; thirdly, generate sufficiency measure by statistics and piecewise linear interpolation technique; fourthly, obtain comprehensive posteriori by integrating uncertainty reasoning with conclusion uncertainty synthetic strategy; finally, we quantify word semantic similarity. On data set R&G (65), we conducted experiment through 5-fold cross validation, and the correlation of our experimental results with human judgment is 0.912, with 0.4% improvements over existing best practice, which show that using subjective Bayes method to measure word semantic similarity is reasonable and effective.