M4 Adapter: Multilingual Multi-Domain Adaptation for Machine Translation With a Meta-Adapter
MCML Authors
Alexandra Chronopoulou
Dr.
* Former Member
Alexander Fraser
Prof. Dr.
Core PI
Abstract
Alexandra Chronopoulou
Dr.
* Former Member
Alexander Fraser
Prof. Dr.
Core PI
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 m4Adapter (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.
inproceedings LCF22
Findings @EMNLP 2022
Findings of the Conference on Empirical Methods in Natural Language Processing. Abu Dhabi, United Arab Emirates, Nov 07-11, 2022.
Authors
W. Lai • A. Chronopoulou • A. FraserLinks
DOIResearch Area
BibTeXKey: LCF22