Minang and Indonesian Pharase-Based Statistical Machine Translation

Abstract

This research focuses on making a phrase based statistical machine translation for Minang – Indonesian language as well as seeing how well the machine translation results. The source of training and test data in the form of parallel corpus and monolingual corpus that taken from Minang Wikipedia language and Indonesian news website. Two test case scenario were tested in this research that based on the language model and translation model. To see how well the translation will be seen by using Bilingual Evaluation Understudy (BLEU). The result showed that the testing for the first scenario have a significant impact compare to the second scenario in terms of translation. The lack of corpus resources is a problem in building phrase-based statistical machine translation.