Overcoming Catastrophic Forgetting in Massively Multilingual Continual Learning

Genta Winata, Lingjue Xie, Karthik Radhakrishnan, Shijie Wu, Xisen Jin, Pengxiang Cheng, Mayank Kulkarni, Daniel Preotiuc-Pietro


Abstract
Real-life multilingual systems should be able to efficiently incorporate new languages as data distributions fed to the system evolve and shift over time. To do this, systems need to handle the issue of catastrophic forgetting, where the model performance drops for languages or tasks seen further in its past. In this paper, we study catastrophic forgetting, as well as methods to minimize this, in a massively multilingual continual learning framework involving up to 51 languages and covering both classification and sequence labeling tasks. We present LR ADJUST, a learning rate scheduling method that is simple, yet effective in preserving new information without strongly overwriting past knowledge. Furthermore, we show that this method is effective across multiple continual learning approaches. Finally, we provide further insights into the dynamics of catastrophic forgetting in this massively multilingual setup.
Anthology ID:
2023.findings-acl.48
Volume:
Findings of the Association for Computational Linguistics: ACL 2023
Month:
July
Year:
2023
Address:
Toronto, Canada
Editors:
Anna Rogers, Jordan Boyd-Graber, Naoaki Okazaki
Venue:
Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
768–777
Language:
URL:
https://aclanthology.org/2023.findings-acl.48
DOI:
10.18653/v1/2023.findings-acl.48
Bibkey:
Cite (ACL):
Genta Winata, Lingjue Xie, Karthik Radhakrishnan, Shijie Wu, Xisen Jin, Pengxiang Cheng, Mayank Kulkarni, and Daniel Preotiuc-Pietro. 2023. Overcoming Catastrophic Forgetting in Massively Multilingual Continual Learning. In Findings of the Association for Computational Linguistics: ACL 2023, pages 768–777, Toronto, Canada. Association for Computational Linguistics.
Cite (Informal):
Overcoming Catastrophic Forgetting in Massively Multilingual Continual Learning (Winata et al., Findings 2023)
Copy Citation:
PDF:
https://aclanthology.org/2023.findings-acl.48.pdf
Video:
 https://aclanthology.org/2023.findings-acl.48.mp4