Assamese WordNet based Quality Enhancement of Bilingual Machine Translation System

Abstract

Machine Translation is a task to trans-late the text from a source language to a target language in an automatic man-ner. Here, we describe a system that trans-late the English language to Assamese lan-guage text which is based on Phrase based statistical translation technique. To over-come the translation problem related with highly open word class like Proper Noun or the Out Of Vocabulary words we de-velop a transliteration system which is also embedded with our translation sys-tem. We enhance the translation output by replacing words with their most appro-priate synonymous word for that particular context with the help of Assamese Word-Net Synset. This Machine Translation sys-tem outcomes with a reasonable transla-tion output when analyzed by linguist for Assamese language which is a less com-putationally aware language among the In-dian languages. 1