Improving text categorization by resolving semantic ambiguity

In this investigation, we propose a new method for text categorization (TC) based on Bayesian approach by resolving ambiguity. The TC assumes weights to words of which meanings are ambiguous in a sense of synonymy and polysemy. We give weights to articles by examining dictionaries of thesaurus and of dimensionality reduction to improve the quality of TC. Also we show some experiments to illustrate how well our approach goes.