English to Myanmar Machine Translation System with Numerical Particle Identification

Abstract

Myanmar is the morphologically rich and highly agglutinative language. The morphologi-cal synthesizer and analyzer are required for machine translation of English to Myanmar language. This paper the development of English to Myanmar machine translation system is implemented applying Rule based machine translation approach. Stanford parser is used for preprocessing step. From this step, the parser generates parse tree structure of input sentence. This parser generates corresponding CFG rules which are collected and created as synchronous context free grammar SCFG rules. CFG rules are required for reordering the structure of English languages. After that tree to tree transformation is carried on the English tree structure which corresponds with used Stanford parser. When English parse tree is transformed as Myanmar parse tree, it is changed according to the SCFG rules. And then system carries out the morphological synthesis. Particles or classifiers (ခ ) က ၊ ကင))၊ ကfယorက M) yanmar language can be solved in this system by proposed classifier identification algorithm. After finishing morphological synthesis, this system generates meaningful and appropriate smoothing sentences.