Heshaam Faili - School of Electrical and Computer Engineering, College of Engineering, University of Tehran, Tehran, Iran
Mohammad Azadnia - Information Technology Department Iran Telecom Research Center Tehran, Iran

In this article an attempt to introduce the first Persian context sensitive spell checker, which tries to detect and correct the :eat-word spelling error of Persian text is presented. The proposed method is a statistical approach which uses Bayesian framework as its probabilistic model and also uses mutual information metric as a semantic relatedness measure between different Persian words. Our experiments on sample test data, shows that accuracy of correction method is about ۸۰% with respect to Fl-measure.

Persian language, real-word error, Bayesian framework, mutual information