Knowledge Transfer in Incremental Learning for Multilingual Neural Machine Translation

Kaiyu Huang, Peng Li, Jin Ma, Ting Yao, Yang Liu

Abstract
In the real-world scenario, a longstanding goal of multilingual neural machine translation (MNMT) is that a single model can incrementally adapt to new language pairs without accessing previous training data. In this scenario, previous studies concentrate on overcoming catastrophic forgetting while lacking encouragement to learn new knowledge from incremental language pairs, especially when the incremental language is not related to the set of original languages. To better acquire new knowledge, we propose a knowledge transfer method that can efficiently adapt original MNMT models to diverse incremental language pairs. The method flexibly introduces the knowledge from an external model into original models, which encourages the models to learn new language pairs, completing the procedure of knowledge transfer. Moreover, all original parameters are frozen to ensure that translation qualities on original language pairs are not degraded. Experimental results show that our method can learn new knowledge from diverse language pairs incrementally meanwhile maintaining performance on original language pairs, outperforming various strong baselines in incremental learning for MNMT.
Anthology ID:
2023.acl-long.852
Volume:
Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
Month:
July
Year:
2023
Address:
Toronto, Canada
Editors:
Anna Rogers, Jordan Boyd-Graber, Naoaki Okazaki
Venue:
ACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
15286–15304
Language:
URL:
https://aclanthology.org/2023.acl-long.852
DOI:
10.18653/v1/2023.acl-long.852
Bibkey:
Cite (ACL):
Kaiyu Huang, Peng Li, Jin Ma, Ting Yao, and Yang Liu. 2023. Knowledge Transfer in Incremental Learning for Multilingual Neural Machine Translation. In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 15286–15304, Toronto, Canada. Association for Computational Linguistics.
Cite (Informal):
Knowledge Transfer in Incremental Learning for Multilingual Neural Machine Translation (Huang et al., ACL 2023)
Copy Citation:
PDF:
https://preview.aclanthology.org/ingest-acl-2023-videos/2023.acl-long.852.pdf
PDF Search