Towards grammar checker development for Persian language

Abstract

With improvements in industry and information technology, large volumes of electronic texts such as newspapers, emails, weblogs, books and thesis are produced daily. Producing electrical documents has considerable benefits such as easy organizing and data management. Therefore, existence of automatic systems such as spell and grammar checker/corrector can help in reducing costs and increasing the electronic texts and it will improve the quality of electronic texts. You can input your text and the computer program will point out to you the spelling errors. It may also help with your grammar. Grammatical errors are described as wrong relation between words like subject-verb disagreement or wrong sequence of words like using plural noun where a single noun is needed. Grammar checking phase starts after spell checking is finished. This paper briefly describes the concepts and definition of grammar checkers in general followed by developing the first Persian (Farsi) grammar checker leading to an overview of the error types of Persian language. The proposed system detects and corrects about 20 frequent Persian grammar errors and tested on a sample dataset, retrieved about 70% and 83% accuracy respect to precision and recall metrics.