Statistical Machine Translation as a Grammar Checker for Persian Language

Existence of automatic writing assistance tools such as spell and grammar checker/corrector can help in increasing electronic texts with higher quality by removing noises and cleaning the sentences. Different kinds of errors in a text can be categorized into spelling, grammatical and real-word errors. In this article, the concepts of an automatic grammar checker for Persian (Farsi) language, is explained. A statistical grammar checker based on phrasal statistical machine translation (SMT) framework is proposed and a hybrid model is suggested by merging it with an existing rule-based grammar checker. The results indicate that these two approaches are complimentary in detecting and correcting syntactic errors, although statistical approach is able to correct more probable errors. The state-ofthe-art results on Persian grammar checking are achieved by using the hybrid model. The obtained recall is about 0.5 for correction and about 0.57 for detection with precision about 0.63.