Utilizing Monolingual Data in NMT for Similar Languages: Submission to Similar Language Translation Task

Jyotsana Khatri, Pushpak Bhattacharyya


Abstract
This paper describes our submission to Shared Task on Similar Language Translation in Fourth Conference on Machine Translation (WMT 2019). We submitted three systems for Hindi -> Nepali direction in which we have examined the performance of a RNN based NMT system, a semi-supervised NMT system where monolingual data of both languages is utilized using the architecture by and a system trained with extra synthetic sentences generated using copy of source and target sentences without using any additional monolingual data.
Anthology ID:
W19-5426
Volume:
Proceedings of the Fourth Conference on Machine Translation (Volume 3: Shared Task Papers, Day 2)
Month:
August
Year:
2019
Address:
Florence, Italy
Editors:
Ondřej Bojar, Rajen Chatterjee, Christian Federmann, Mark Fishel, Yvette Graham, Barry Haddow, Matthias Huck, Antonio Jimeno Yepes, Philipp Koehn, André Martins, Christof Monz, Matteo Negri, Aurélie Névéol, Mariana Neves, Matt Post, Marco Turchi, Karin Verspoor
Venue:
WMT
SIG:
SIGMT
Publisher:
Association for Computational Linguistics
Note:
Pages:
197–201
Language:
URL:
https://aclanthology.org/W19-5426
DOI:
10.18653/v1/W19-5426
Bibkey:
Cite (ACL):
Jyotsana Khatri and Pushpak Bhattacharyya. 2019. Utilizing Monolingual Data in NMT for Similar Languages: Submission to Similar Language Translation Task. In Proceedings of the Fourth Conference on Machine Translation (Volume 3: Shared Task Papers, Day 2), pages 197–201, Florence, Italy. Association for Computational Linguistics.
Cite (Informal):
Utilizing Monolingual Data in NMT for Similar Languages: Submission to Similar Language Translation Task (Khatri & Bhattacharyya, WMT 2019)
Copy Citation:
PDF:
https://aclanthology.org/W19-5426.pdf