Bangla Spell Checking and Correction Using Edit Distance

Automatic spelling correction for Bangla language is a very important thing as the modern world is almost completely dependent on digital devices where electronic keyboards are used. Bangla is a largely used language (3.05% of world population), worldwide securing the 7^th most spoken language. But concerning the natural language processing it is still in its initial stage. Automatic spelling correction of Bangla language is just crossing its primitive stage. A few works have been done on automated Bangla spelling correction but those numbers are not still adequate. This research work is based on correct word prediction of typed Bangla sentences by using edit distance method and fractional accuracy. The results are promising. So, there is a high chance that the proposed model will help and have a great impact on automated Bangla spelling correction.

I. Introduction

Written form of a language is a very important factor in communication; whether it is handwritten or typed. When speaking it is not important to know proper spelling of a word and even without proper maintenance of grammar communications can be conducted, but when writing it is very important to have correct spelling. Spelling mistake is a common issue especially if it is a complex language such as Bangla. In aspect of most spoken language, Bangla stands 6^th in the world [1]. It has complex word construction, so it is common to have spelling error while writing. It is not necessary that the reasons for spelling mistakes are only because of its complexity, it might also occur due to fast typing or lack of knowledge. As it is a common phenomenon to make spelling mistakes, automatic spelling correction processes are a must. There are lots of work on this issue but when considering Bangla there aren’t many notable works. The main focus of this research work is checking the spelling of Bangla word following by the correction of it using fractional accuracy. Direct dictionary lookup and edit distance method will be used to check correctness and gain possible corrections of the word then the accuracy will be calculated. There are some works that used the edit distance method but, in this research, a much larger dictionary and new method to calculate accuracy are used which will give better results.