Evaluation of machine translation approaches to translate English to Bengali

Abstract

This paper describes the different types of machine translation (MT) approaches, where MT refers to the use of computers for the task of translating automatically from one language to another. It is highly challenging to build up a proper MT system which will works with full accuracy for translating foreign languages to native languages but this paper aims at providing a solution that could be helpful for building a MT system which will convert the English sentences into Bengali. Moreover, total 12 tenses such as-present indefinite, continuous, perfect, perfect continuous; past indefinite, continuous, perfect, perfect continuous; future indefinite, continuous, perfect and perfect continuous are used for the purpose of translating English sentence into Bengali that will require finding out the meaning from our own database. After comparing the experimental results based on different machine translation approaches with Google translator, it is found that one of our investigated as well as implemented methods, Corpus approach, provides higher accuracy in comparison with Google translator and other implemented methods.