$m^4Adapter$: Multilingual Multi-Domain Adaptation for Machine Translation with a Meta-Adapter
This addresses performance drops in machine translation under domain and language shifts, offering an incremental improvement for multilingual adaptation.
The paper tackles the problem of adapting multilingual neural machine translation models to new domains and language pairs simultaneously, proposing m^4Adapter, a parameter-efficient meta-learning approach that outperforms other adapter methods in this challenging scenario.
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.