Multilingual Machine Translation with Semantic and Disambiguation

Machine Translation is the process of translating one natural language into another using automated and computerized means. The proposed system is a rule based multilingual unidirectional translation system which translates English sentences into corresponding Malayalam and Hindi sentences. During translation it incorporates morphological and syntactic information present in the working pair of languages. And it also performs word sense disambiguation, semantic analysis and morphological processing of the generated target sentence. Machine learning based word sense disambiguation and First Order Predicate Logic(FOPL) based semantic checking are the two main features of this paper. The word arrangement in dictionary with POS tags and word sense is an other important factor that can contribute to the efficiency of the translation system. Hence the system can achieve 74% accuracy for both translation which includes all the tenses and different type of sentences in English.