A Hybrid Approach to Example based Machine Translation for Indian Languages
Vamshi Ambati, U. Rohini · 2007
Corpus based approaches to machine translation namely Example based ma-chine translation and Statistical machine translation have received wide focus in the recent years. Hybrid approaches combin-ing the two further improved the perfor-mance. Indian language machine transla-tion has mostly focussed on rule based ma-chine translation. We propose a hybrid ap-proach to Example based machine trans-lation making use of statistical machine translation methods and minimal linguis-tic resources. Our motive in this paper is to obtain a ’good enough ’ translation as opposed to a perfect translation aimed by earlier machine translation efforts. Our ap-proach can be used for translation of en-glish to any indian language. In this paper, we perform experiments for translation of english to hindi and report BLEU scores. 1