Multilingual Machine Translation: Closing the Gap between Shared and Language-specific Encoder-Decoders

Carlos Escolano, Marta R. Costa-jussà, José A. R. Fonollosa, Mikel Artetxe


Abstract
State-of-the-art multilingual machine translation relies on a universal encoder-decoder, which requires retraining the entire system to add new languages. In this paper, we propose an alternative approach that is based on language-specific encoder-decoders, and can thus be more easily extended to new languages by learning their corresponding modules. So as to encourage a common interlingua representation, we simultaneously train the N initial languages. Our experiments show that the proposed approach outperforms the universal encoder-decoder by 3.28 BLEU points on average, while allowing to add new languages without the need to retrain the rest of the modules. All in all, our work closes the gap between shared and language-specific encoderdecoders, advancing toward modular multilingual machine translation systems that can be flexibly extended in lifelong learning settings.
Anthology ID:
2021.eacl-main.80
Volume:
Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume
Month:
April
Year:
2021
Address:
Online
Editors:
Paola Merlo, Jorg Tiedemann, Reut Tsarfaty
Venue:
EACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
944–948
Language:
URL:
https://aclanthology.org/2021.eacl-main.80
DOI:
10.18653/v1/2021.eacl-main.80
Bibkey:
Cite (ACL):
Carlos Escolano, Marta R. Costa-jussà, José A. R. Fonollosa, and Mikel Artetxe. 2021. Multilingual Machine Translation: Closing the Gap between Shared and Language-specific Encoder-Decoders. In Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume, pages 944–948, Online. Association for Computational Linguistics.
Cite (Informal):
Multilingual Machine Translation: Closing the Gap between Shared and Language-specific Encoder-Decoders (Escolano et al., EACL 2021)
Copy Citation:
PDF:
https://aclanthology.org/2021.eacl-main.80.pdf