2024-03-29T08:20:35Z
https://meral.edu.mm/oai
oai:meral.edu.mm:recid/4586
2021-12-13T06:19:13Z
1582963302567:1597824175385
user-ucsy
Statistical Machine Translation between Myanmar and Myeik
Oo, Thazin Myint
Thu, Ye Kyaw
Soe, Khin Mar
Supnithi, Thepchai
This paper contributes the first evaluation of the quality of machine translation betweenMyanmar and Myeik (also known as Beik) . We also developed a Myanmar-Myeik parallel corpus (around10K sentences) based on the Myanmar language of ASEAN MT corpus. In addition, two types ofsegmentation were studied word and syllable segmentation. The 10 folds cross-validation experiments werecarried out using three different statistical machine translation approaches: phrase-based, hierarchical phrasebased, and the operation sequence model (OSM). The results show that all three statistical machinetranslation approaches give higher and comparable BLEU and RIBES scores for both Myanmar to Myeik andMyeik to Myanmar machine translations. OSM approach achieved the highest BLEU and RIBES scoresamong three approaches. We also found that syllable segmentation is appropriate for translation qualitycomparing with word level segmentation results.
2020-02-28
http://hdl.handle.net/20.500.12678/0000004586
https://meral.edu.mm/records/4586