Bodo to English Machine Translation through Transliteration

Abstract

Machine Translation (MT) is a technique that automatically translates text from one natural language to another using machine like computer. Machine Transliteration (MTn) is also a technique that converts the script of text from source language to target language without changing the pronunciation of the source text. Both the MT and MTn are the challenging research task in the field of Natural Language Processing (NLP) and Computational Linguistics (CL) globally. English is a high resource natural language, whereas Bodo is a low resource natural language. Though Bodo is a recognized language of India; still not much research work has been done on MT and MTn systems due to the low resources. The primary objective of this paper is to develop Bodo to English Machine Translation system with the help of Bodo to English Machine Transliteration system. The Bodo to English MT system has been developed using the Phrase-based Statistical Machine Translation technique for General and News domains of Bodo-English parallel text corpus. The Bodo to English MTn system has been developed using the Hybrid technique for General and News domains of Bodo-English parallel transliterated words/terms. The translation accuracy of the MT system has been evaluated using BLEU technique.