Developing Word to Phrase Alignment for Myanmar-English Machine Translation

Abstract

Efficient estimation and alignment procedures for word and phrase alignment are developed for the alignment of parallel text, and this is shown in Myanmar-English translation. Word alignment based on the combination of corpus based approach and dictionary lookup approach. This word alignment process is based on the IBM model 1 to 3. For the dictionary lookup approach, the proposed system uses the bilingual Myanmar-English Dictionary. The system also uses a list of cognates and morphological analysis to get better alignment accuracy. After word alignment, phrase alignment is extended using PoS Pattern. Phrase alignment for machine translation is to improve quality in translation using PoS Filtering. Phrase alignment uses English Partof- Speech (PoS).