{
  "id": "2210.11912",
  "version": "v1",
  "published": "2022-10-21T12:25:05.000Z",
  "updated": "2022-10-21T12:25:05.000Z",
  "title": "$m^4Adapter$: Multilingual Multi-Domain Adaptation for Machine Translation with a Meta-Adapter",
  "authors": [
    "Wen Lai",
    "Alexandra Chronopoulou",
    "Alexander Fraser"
  ],
  "comment": "Accepted to Findings of EMNLP 2022",
  "categories": [
    "cs.CL"
  ],
  "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.",
  "revisions": [
    {
      "version": "v1",
      "updated": "2022-10-21T12:25:05.000Z"
    }
  ],
  "analyses": {
    "keywords": [
      "multilingual multi-domain adaptation",
      "language pair",
      "multilingual neural machine translation models",
      "meta-adapter",
      "mnmt model"
    ],
    "note": {
      "typesetting": "TeX",
      "pages": 0,
      "language": "en",
      "license": "arXiv",
      "status": "editable"
    }
  }
}