Abstract
Multilingual neural machine translation models (MNMT) yield state-of-the-art performance when evaluated on data from a domain and language pair seen at training time. However, when a MNMT model is used to translate under domain shift or to a new language pair, performance drops dramatically. We consider a very challenging scenario: adapting the MNMT model both to a new domain and to a new language pair at the same time. In this paper, we propose m^4Adapter (Multilingual Multi-Domain Adaptation for Machine Translation with a Meta-Adapter), which combines domain and language knowledge using meta-learning with adapters. We present results showing that our approach is a parameter-efficient solution which effectively adapts a model to both a new language pair and a new domain, while outperforming other adapter methods. An ablation study also shows that our approach more effectively transfers domain knowledge across different languages and language information across different domains.- Anthology ID:
- 2022.findings-emnlp.315
- Volume:
- Findings of the Association for Computational Linguistics: EMNLP 2022
- Month:
- December
- Year:
- 2022
- Address:
- Abu Dhabi, United Arab Emirates
- Editors:
- Yoav Goldberg, Zornitsa Kozareva, Yue Zhang
- Venue:
- Findings
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 4282–4296
- Language:
- URL:
- https://aclanthology.org/2022.findings-emnlp.315
- DOI:
- 10.18653/v1/2022.findings-emnlp.315
- Cite (ACL):
- Wen Lai, Alexandra Chronopoulou, and Alexander Fraser. 2022. m^4 Adapter: Multilingual Multi-Domain Adaptation for Machine Translation with a Meta-Adapter. In Findings of the Association for Computational Linguistics: EMNLP 2022, pages 4282–4296, Abu Dhabi, United Arab Emirates. Association for Computational Linguistics.
- Cite (Informal):
- m^4 Adapter: Multilingual Multi-Domain Adaptation for Machine Translation with a Meta-Adapter (Lai et al., Findings 2022)
- PDF:
- https://preview.aclanthology.org/ingest-acl-2023-videos/2022.findings-emnlp.315.pdf