Multilingual Neural Machine Translation: Case-study for Catalan, Spanish and Portuguese Romance Languages

Pere Vergés Boncompte, Marta R. Costa-jussà


Abstract
In this paper, we describe the TALP-UPC participation in the WMT Similar Language Translation task between Catalan, Spanish, and Portuguese, all of them, Romance languages. We made use of different techniques to improve the translation between these languages. The multilingual shared encoder/decoder has been used for all of them. Additionally, we applied back-translation to take advantage of the monolingual data. Finally, we have applied fine-tuning to improve the in-domain data. Each of these techniques brings improvements over the previous one. In the official evaluation, our system was ranked 1st in the Portuguese-to-Spanish direction, 2nd in the opposite direction, and 3rd in the Catalan-Spanish pair.
Anthology ID:
2020.wmt-1.54
Volume:
Proceedings of the Fifth Conference on Machine Translation
Month:
November
Year:
2020
Address:
Online
Venue:
WMT
SIG:
SIGMT
Publisher:
Association for Computational Linguistics
Note:
Pages:
447–450
Language:
URL:
https://aclanthology.org/2020.wmt-1.54
DOI:
Bibkey:
Cite (ACL):
Pere Vergés Boncompte and Marta R. Costa-jussà. 2020. Multilingual Neural Machine Translation: Case-study for Catalan, Spanish and Portuguese Romance Languages. In Proceedings of the Fifth Conference on Machine Translation, pages 447–450, Online. Association for Computational Linguistics.
Cite (Informal):
Multilingual Neural Machine Translation: Case-study for Catalan, Spanish and Portuguese Romance Languages (Vergés Boncompte & R. Costa-jussà, WMT 2020)
Copy Citation:
PDF:
https://preview.aclanthology.org/ingestion-script-update/2020.wmt-1.54.pdf
Video:
 https://slideslive.com/38939555