Reordering System Implementation for Myanmar-English-Myanmar Machine Translation

Abstract

Reordering is one of the most challenging and important problems in Statistical Machine Translation. Without reordering capabilities, sentences can be translated correctly only in the case when both languages implied in translation have a similar word order. When translating is between language pairs with high disparity in word order, word reordering is extremely desirable for translation accuracy improvement. Our Language, Myanmar is a verb final language and reordering is needed when our language is translated from other languages with different word orders. In this paper, hierarchical rule-based reordering approach is used. This work is intended to be incorporated into Myanmar-English-Myanmar machine translation. Proposed reordering system also serves as a pre-translation reordering system and gain the accuracy (94.23%) in Myanmar-English reordering and (90.99%) in English-Myanmar reordering.