Independent study Report : Improving example based English to Bengali machine translation using WordNet

Abstract

The goal of this research topic is to develop efficient machine translation system for English to Bengali language by improving my Thesis work “Example Based English to Bengali Machine Translation”. Due to relevance of this work I kept the most of the texts of my thesis. To develop an efficient machine translation system is very important but it is really expensive as it requires a huge amount of time and resources. In all languages there are many words that may have multiple meanings and also some sentence may have multiple grammar structure to express the same meaning, it is a great challenge to do the right semantic analysis. But it is very important to have a machine translation system which can compute all possible outputs in reasonable time and able to choose the best option. We can dramatically improve the performance of English to Bengali Example Based Machine Translation using WordNet. For example the ‘have’ verb has more than ten different meaningful uses during English to Bengali translation. Using the word senses given by WordNet we can dramatically improve the performance of Example Based Machine Translation (EBMT) Depending on various characteristics of words. The proposed EBMT system has five steps: 1) Tagging 2) Parsing 3) Prepare the chunks of the sentence using sub-sentential EBMT 4) Using an efficient adapting scheme match the sentence rule 5) Translate from Source Language (English) to Target Language (Bengali) in the chunk and generate with morphological analysis with the help of WordNet.