LTRC-MT Simple & Effective Hindi-English Neural Machine Translation Systems at WAT 2019

Vikrant Goyal, Dipti Misra Sharma


Abstract
This paper describes the Neural Machine Translation systems of IIIT-Hyderabad (LTRC-MT) for WAT 2019 Hindi-English shared task. We experimented with both Recurrent Neural Networks & Transformer architectures. We also show the results of our experiments of training NMT models using additional data via backtranslation.
Anthology ID:
D19-5216
Volume:
Proceedings of the 6th Workshop on Asian Translation
Month:
November
Year:
2019
Address:
Hong Kong, China
Editors:
Toshiaki Nakazawa, Chenchen Ding, Raj Dabre, Anoop Kunchukuttan, Nobushige Doi, Yusuke Oda, Ondřej Bojar, Shantipriya Parida, Isao Goto, Hidaya Mino
Venue:
WAT
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
137–140
Language:
URL:
https://aclanthology.org/D19-5216
DOI:
10.18653/v1/D19-5216
Bibkey:
Cite (ACL):
Vikrant Goyal and Dipti Misra Sharma. 2019. LTRC-MT Simple & Effective Hindi-English Neural Machine Translation Systems at WAT 2019. In Proceedings of the 6th Workshop on Asian Translation, pages 137–140, Hong Kong, China. Association for Computational Linguistics.
Cite (Informal):
LTRC-MT Simple & Effective Hindi-English Neural Machine Translation Systems at WAT 2019 (Goyal & Sharma, WAT 2019)
Copy Citation:
PDF:
https://preview.aclanthology.org/nschneid-patch-4/D19-5216.pdf