Abstract:
This paper contributes the first evaluation of the quality of machine translation between Myanmar (Burmese) and Rakhine (Arakanese). We also developed a Myanmar-Rakhine parallel corpus (around 18K sentences) based on the Myanmar language of ASEAN MT corpus. The 10 folds cross-validation experiments were carried out using three different statistical machine translation approaches: phrase-based, hierarchical phrase-based, and the operation sequence model (OSM). The results show that all three statistical machine translation approaches give higher and comparable BLEU and RIBES scores for both Myanmar to Rakhine and Rakhine to Myanmar machine translations. OSM approach achieved the highest BLEU and RIBES scores among three approaches.
Description:
We would like to express our gratitude to U Oo Hla Kyaw (Ba Gyi Kyaw), Editor of the Rakhine Newspaper for valuable advices. We also thank Mg Than Htun Soe (Computer University Sittwe Students Union), Mg Htet Myart Kyaw (Computer University Sittwe Students' Union) and Ma Oo Moe Wai (Computer University Sittwe) for their translation of Myanmar language corpus into Rakhine and answering our various questions.
