• Anita A. Patil
• Priti R. Sharma
• Sandip S. Patil

Spelling correction is a process of detecting and providing corrections for misspelled words in a text. Marathi is the official language of Maharashtra and Goa states, the fourth most widely spoken language in India. Marathi language is still in its early stage of research and development regarding natural language processing applications in comparison to other languages. Spelling detection and correction for Marathi language is an important task of natural language processing (NLP) which has not get sufficient attention till date. The main challenge while working with such regional languages is first needs to learn its char set and convert it into Unicode’s. Thus the existing techniques that are being used to check the errors in English language are not used for Marathi Language. The proposed approach is combination of three techniques, which are dictionary lookup, string similarity function LCS and N- gram. Each approach has a particular purpose and task. Finding the misspelled words from given text is corrected by using Hybrid approach. The proposed mechanism gives accurate error detection and suggestion for correction of Marathi misspelled words.

Longest Common Subsequence, Natural Language Processing.

" Design and Implementation of Marathi Spell Checker Using Hybrid Approach", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.6, Issue 6, page no.668-674, June 2019, Available :http://www.jetir.org/papers/JETIR1907J85.pdf

" Design and Implementation of Marathi Spell Checker Using Hybrid Approach", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.6, Issue 6, page no. pp668-674, June 2019, Available at : http://www.jetir.org/papers/JETIR1907J85.pdf