ICL: Iterative Continual Learning for Multi-domain Neural Machine Translation

Zhibo Man, Kaiyu Huang, Yujie Zhang, Yuanmeng Chen, Yufeng Chen, Jinan Xu


Abstract
In a practical scenario, multi-domain neural machine translation (MDNMT) aims to continuously acquire knowledge from new domain data while retaining old knowledge. Previous work separately learns each new domain knowledge based on parameter isolation methods, which effectively capture the new knowledge. However, task-specific parameters lead to isolation between models, which hinders the mutual transfer of knowledge between new domains. Given the scarcity of domain-specific corpora, we consider making full use of the data from multiple new domains. Therefore, our work aims to leverage previously acquired domain knowledge when modeling subsequent domains. To this end, we propose an Iterative Continual Learning (ICL) framework for multi-domain neural machine translation. Specifically, when each new domain arrives, (1) we first build a pluggable incremental learning model, (2) then we design an iterative updating algorithm to continuously update the original model, which can be used flexibly for constructing subsequent domain models. Furthermore, we design a domain knowledge transfer mechanism to enhance the fine-grained domain-specific representation, thereby solving the word ambiguity caused by mixing domain data. Experimental results on the UM-Corpus and OPUS multi-domain datasets show the superior performance of our proposed model compared to representative baselines.
Anthology ID:
2024.findings-emnlp.455
Volume:
Findings of the Association for Computational Linguistics: EMNLP 2024
Month:
November
Year:
2024
Address:
Miami, Florida, USA
Editors:
Yaser Al-Onaizan, Mohit Bansal, Yun-Nung Chen
Venue:
Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
7732–7743
Language:
URL:
https://aclanthology.org/2024.findings-emnlp.455
DOI:
Bibkey:
Cite (ACL):
Zhibo Man, Kaiyu Huang, Yujie Zhang, Yuanmeng Chen, Yufeng Chen, and Jinan Xu. 2024. ICL: Iterative Continual Learning for Multi-domain Neural Machine Translation. In Findings of the Association for Computational Linguistics: EMNLP 2024, pages 7732–7743, Miami, Florida, USA. Association for Computational Linguistics.
Cite (Informal):
ICL: Iterative Continual Learning for Multi-domain Neural Machine Translation (Man et al., Findings 2024)
Copy Citation:
PDF:
https://aclanthology.org/2024.findings-emnlp.455.pdf