Factored Machine Translation for Myanmar to English, Japanese and Vice Versa

Factored machine translation models extendtraditionalPhrase Based Statistical MachineTranslation (PB-SMT) by taking into account notonlythe surface form of the words, but also linguisticknowledge such as the dictionary form (lemma), partof-speech (POS) and morphological tags. In thispaper, we used POS tagsas a factor and builtfactored machine translation models with varioustranslation configurations for Myanmar to English,Japanese translation and vice versa.The experimentalresults show an improvement in translation qualityfor Myanmar to English and Myanmar to Japanese language pairs