Supervised and Unsupervised Machine Translation for Myanmar-English and Khmer-English

Benjamin Marie, Hour Kaing, Aye Myat Mon, Chenchen Ding, Atsushi Fujita, Masao Utiyama, Eiichiro Sumita


Abstract
This paper presents the NICT’s supervised and unsupervised machine translation systems for the WAT2019 Myanmar-English and Khmer-English translation tasks. For all the translation directions, we built state-of-the-art supervised neural (NMT) and statistical (SMT) machine translation systems, using monolingual data cleaned and normalized. Our combination of NMT and SMT performed among the best systems for the four translation directions. We also investigated the feasibility of unsupervised machine translation for low-resource and distant language pairs and confirmed observations of previous work showing that unsupervised MT is still largely unable to deal with them.
Anthology ID:
D19-5206
Volume:
Proceedings of the 6th Workshop on Asian Translation
Month:
November
Year:
2019
Address:
Hong Kong, China
Venues:
EMNLP | WAT | WS
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
68–75
Language:
URL:
https://aclanthology.org/D19-5206
DOI:
10.18653/v1/D19-5206
Bibkey:
Cite (ACL):
Benjamin Marie, Hour Kaing, Aye Myat Mon, Chenchen Ding, Atsushi Fujita, Masao Utiyama, and Eiichiro Sumita. 2019. Supervised and Unsupervised Machine Translation for Myanmar-English and Khmer-English. In Proceedings of the 6th Workshop on Asian Translation, pages 68–75, Hong Kong, China. Association for Computational Linguistics.
Cite (Informal):
Supervised and Unsupervised Machine Translation for Myanmar-English and Khmer-English (Marie et al., EMNLP 2019)
Copy Citation:
PDF:
https://preview.aclanthology.org/update-css-js/D19-5206.pdf