Sentence and Word Alignment System for Myanmar-English Machine Translation

Abstract

This paper describes an alignment system that aligns Myanmar-English texts at the sentence and word level in parallel text. Sentence and word level alignment is the identification of the corresponding sentence and word in the parallel text. The paper is also to construct word-aligned parallel corpus to be able in Myanmar-English machine translation. It is also resource for machine translation. This paper describes a simple sentence length approach to sentence alignment and a combination of corpus based approach and dictionary lookup approach to perform word alignment. Corpus based approach is based on the first three IBM models and dictionary lookup approach uses Myanmar-English dictionary. The system also uses a list of cognates and morphological analysis to get better alignment accuracy.