# Multi-Domain Neural Machine Translation

arXiv: https://arxiv.org/abs/1805.02282 · HTML: https://mlsanity.com/paper/1805.02282/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 6 May 2018.

## Built on by (most cited first, 11 of 11)

- [Domain Adaptation and Multi-Domain Adaptation for Neural Machine Translation: A Survey](https://mlsanity.com/paper/2104.06951/) (2021)
- [Uncertainty-Aware Balancing for Multilingual and Multi-Domain Neural Machine Translation Training](https://mlsanity.com/paper/2109.02284/) (2021)
- [Extremely low-resource machine translation for closely related languages](https://mlsanity.com/paper/2105.13065/) (2021)
- [CAMERO: Consistency Regularized Ensemble of Perturbed Language Models with Weight Sharing](https://mlsanity.com/paper/2204.06625/) (2022)
- [DMDTEval: An Evaluation and Analysis of LLMs on Disambiguation in Multi-domain Translation](https://mlsanity.com/paper/2504.20371/) (2025)
- [Translation Transformers Rediscover Inherent Data Domains](https://mlsanity.com/paper/2109.07864/) (2021)
- [Elastic Multi-Gradient Descent for Parallel Continual Learning](https://mlsanity.com/paper/2401.01054/) (2024)
- [Label-Free Multi-Domain Machine Translation with Stage-wise Training](https://mlsanity.com/paper/2305.03949/) (2023)
- [Optimal Corpus Aware Training for Neural Machine Translation](https://mlsanity.com/paper/2508.05364/) (2025)
- [Efficient Continual Learning in Neural Machine Translation: A Low-Rank Adaptation Approach](https://mlsanity.com/paper/2512.09910/) (2025)
- [MUTEX: Leveraging Multilingual Transformers and Conditional Random Fields for Enhanced Urdu Toxic Span Detection](https://mlsanity.com/paper/2603.05057/) (2026)

## Abstract (arXiv)

We present an approach to neural machine translation (NMT) that supports multiple domains in a single model and allows switching between the domains when translating. The core idea is to treat text domains as distinct languages and use multilingual NMT methods to create multi-domain translation systems, we show that this approach results in significant translation quality gains over fine-tuning. We also explore whether the knowledge of pre-specified text domains is necessary, turns out that it is after all, but also that when it is not known quite high translation quality can be reached.