Missing word detection and correction based on context of Tamil sentences using n-grams

Abstract

The main function of a spell checker is to detect and correct erroneous words, missing words and grammatical mistakes in text documents. Erroneous words and grammatical mistakes can occur in sentences due to various reasons. Missing words can occur in sentences when typing a document or converting printed or handwritten documents into editable form. An efficient approach to detecting missing words in Tamil sentences and providing suggestions for them is proposed in this paper. The proposed approach uses word-level unigram, bigram and trigram techniques. Test results show that the proposed approach detects all missing words in Tamil sentences. Test results also show that the suggestions generated are of more than 99% accuracy as approved by a Scholar in Tamil.