$m^4Adapter$: Multilingual Multi-Domain Adaptation for Machine Translation with a Meta-Adapter

• URL: http://arxiv.org/abs/2210.11912v1
• Date: Fri, 21 Oct 2022 12:25:05 GMT
• Title: $m^4Adapter$: Multilingual Multi-Domain Adaptation for Machine Translation with a Meta-Adapter
• Authors: Wen Lai, Alexandra Chronopoulou, Alexander Fraser
• Abstract summary: Multilingual neural machine translation models (MNMT) yield state-of-the-art performance when evaluated on data from a domain and language pair. When a MNMT model is used to translate under domain shift or to a new language pair, performance drops dramatically. We propose $m4Adapter$, which combines domain and language knowledge using meta-learning with adapters.
• Score: 128.69723410769586
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• 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.

Related papers

• $k$NN-Adapter: Efficient Domain Adaptation for Black-Box Language Models [18.969047541720123]
  $k$NN-Adapter is a method to adapt large language models to a new domain. Experiments on four different domains demonstrate that $k$NN-Adapter significantly improves perplexity.
  arXiv  Detail & Related papers  (2023-02-21T18:54:21Z)
• AdapterSoup: Weight Averaging to Improve Generalization of Pretrained Language Models [127.04370753583261]
  Pretrained language models (PLMs) are trained on massive corpora, but often need to specialize to specific domains. A solution is to use a related-domain adapter for the novel domain at test time. We introduce AdapterSoup, an approach that performs weight-space averaging of adapters trained on different domains.
  arXiv  Detail & Related papers  (2023-02-14T13:09:23Z)
• Language-Family Adapters for Low-Resource Multilingual Neural Machine Translation [129.99918589405675]
  Large multilingual models trained with self-supervision achieve state-of-the-art results in a wide range of natural language processing tasks. Multilingual fine-tuning improves performance on low-resource languages but requires modifying the entire model and can be prohibitively expensive. We propose training language-family adapters on top of mBART-50 to facilitate cross-lingual transfer.
  arXiv  Detail & Related papers  (2022-09-30T05:02:42Z)
• Multilingual Domain Adaptation for NMT: Decoupling Language and Domain Information with Adapters [66.7986513246294]
  We study the compositionality of language and domain adapters in the context of Machine Translation. We find that in the partial resource scenario a naive combination of domain-specific and language-specific adapters often results in catastrophic forgetting' of the missing languages.
  arXiv  Detail & Related papers  (2021-10-18T18:55:23Z)
• Non-Parametric Unsupervised Domain Adaptation for Neural Machine Translation [61.27321597981737]
  $k$NN-MT has shown the promising capability of directly incorporating the pre-trained neural machine translation (NMT) model with domain-specific token-level $k$-nearest-neighbor retrieval. We propose a novel framework that directly uses in-domain monolingual sentences in the target language to construct an effective datastore for $k$-nearest-neighbor retrieval.
  arXiv  Detail & Related papers  (2021-09-14T11:50:01Z)
• Efficient Test Time Adapter Ensembling for Low-resource Language Varieties [115.12997212870962]
  Specialized language and task adapters have been proposed to facilitate cross-lingual transfer of multilingual pretrained models. An intuitive solution is to use a related language adapter for the new language variety, but we observe that this solution can lead to sub-optimal performance. In this paper, we aim to improve the robustness of language adapters to uncovered languages without training new adapters.
  arXiv  Detail & Related papers  (2021-09-10T13:44:46Z)
• Domain Adaptation and Multi-Domain Adaptation for Neural Machine Translation: A Survey [9.645196221785694]
  We focus on robust approaches to domain adaptation for Neural Machine Translation (NMT) models. In particular, we look at the case where a system may need to translate sentences from multiple domains. We highlight the benefits of domain adaptation and multi-domain adaptation techniques to other lines of NMT research.
  arXiv  Detail & Related papers  (2021-04-14T16:21:37Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.