# Multilingual Multi-Domain Adaptation Approaches for Neural Machine Translation

arXiv: https://arxiv.org/abs/1906.07978 · HTML: https://mlsanity.com/paper/1906.07978/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 19 Jun 2019.

## Built on by (most cited first, 8 of 8)

- [Contrastive Learning for Many-to-many Multilingual Neural Machine Translation](https://mlsanity.com/paper/2105.09501/) (2021)
- [Domain Adaptation and Multi-Domain Adaptation for Neural Machine Translation: A Survey](https://mlsanity.com/paper/2104.06951/) (2021)
- [Back-translation for Large-Scale Multilingual Machine Translation](https://mlsanity.com/paper/2109.08712/) (2021)
- [YANMTT: Yet Another Neural Machine Translation Toolkit](https://mlsanity.com/paper/2108.11126/) (2021)
- [Tailoring Domain Adaptation for Machine Translation Quality Estimation](https://mlsanity.com/paper/2304.08891/) (2023)
- [m4Adapter: Multilingual Multi-Domain Adaptation for Machine Translation with a Meta-Adapter](https://mlsanity.com/paper/2210.11912/) (2022)
- [F-MALLOC: Feed-forward Memory Allocation for Continual Learning in Neural Machine Translation](https://mlsanity.com/paper/2404.04846/) (2024)
- [Contrastive Token Learning with Similarity Decay for Repetition Suppression in Machine Translation](https://mlsanity.com/paper/2409.19877/) (2024)

## Abstract (arXiv)

In this paper, we propose two novel methods for domain adaptation for the attention-only neural machine translation (NMT) model, i.e., the Transformer. Our methods focus on training a single translation model for multiple domains by either learning domain specialized hidden state representations or predictor biases for each domain. We combine our methods with a previously proposed black-box method called mixed fine tuning, which is known to be highly effective for domain adaptation. In addition, we incorporate multilingualism into the domain adaptation framework. Experiments show that multilingual multi-domain adaptation can significantly improve both resource-poor in-domain and resource-rich out-of-domain translations, and the combination of our methods with mixed fine tuning achieves the best performance.