Abstract:
Factored machine translation models extend
traditionalPhrase Based Statistical Machine
Translation (PB-SMT) by taking into account notonly
the surface form of the words, but also linguistic
knowledge such as the dictionary form (lemma), partof-
speech (POS) and morphological tags. In this
paper, we used POS tagsas a factor and built
factored machine translation models with various
translation configurations for Myanmar to English,
Japanese translation and vice versa.The experimental
results show an improvement in translation quality
for Myanmar to English and Myanmar to Japanese language pairs.
