# Go From the General to the Particular: Multi-Domain Translation with Domain Transformation Networks

arXiv: https://arxiv.org/abs/1911.09912 · HTML: https://mlsanity.com/paper/1911.09912/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 22 Nov 2019.

## Built on by (most cited first, 12 of 12)

- [Domain Adaptation and Multi-Domain Adaptation for Neural Machine Translation: A Survey](https://mlsanity.com/paper/2104.06951/) (2021)
- [Importance-based Neuron Allocation for Multilingual Neural Machine Translation](https://mlsanity.com/paper/2107.06569/) (2021)
- [Hallucination Detection and Hallucination Mitigation: An Investigation](https://mlsanity.com/paper/2401.08358/) (2024)
- [Salute the Classic: Revisiting Challenges of Machine Translation in the Age of Large Language Models](https://mlsanity.com/paper/2401.08350/) (2024)
- [Pruning-then-Expanding Model for Domain Adaptation of Neural Machine Translation](https://mlsanity.com/paper/2103.13678/) (2021)
- [Large Language Model for Multi-Domain Translation: Benchmarking and Domain CoT Fine-tuning](https://mlsanity.com/paper/2410.02631/) (2024)
- [Self-Teaching Machines to Read and Comprehend with Large-Scale Multi-Subject Question-Answering Data](https://mlsanity.com/paper/2102.01226/) (2021)
- [Pay Better Attention to Attention: Head Selection in Multilingual and Multi-Domain Sequence Modeling](https://mlsanity.com/paper/2106.10840/) (2021)
- [AutoMixer: Checkpoint Artifacts as Automatic Data Mixers](https://mlsanity.com/paper/2506.21910/) (2025)
- [Pairwise Distance Distillation for Unsupervised Real-World Image Super-Resolution](https://mlsanity.com/paper/2407.07302/) (2024)
- [Can Domains Be Transferred Across Languages in Multi-Domain Multilingual Neural Machine Translation?](https://mlsanity.com/paper/2210.11628/) (2022)
- [Neuron-Guided Fine-Tuning: Unlocking Efficient Alignment Mechanisms for Large Language Models](https://mlsanity.com/paper/2609.05913/) (2026)

## Abstract (arXiv)

The key challenge of multi-domain translation lies in simultaneously encoding both the general knowledge shared across domains and the particular knowledge distinctive to each domain in a unified model. Previous work shows that the standard neural machine translation (NMT) model, trained on mixed-domain data, generally captures the general knowledge, but misses the domain-specific knowledge. In response to this problem, we augment NMT model with additional domain transformation networks to transform the general representations to domain-specific representations, which are subsequently fed to the NMT decoder. To guarantee the knowledge transformation, we also propose two complementary supervision signals by leveraging the power of knowledge distillation and adversarial learning. Experimental results on several language pairs, covering both balanced and unbalanced multi-domain translation, demonstrate the effectiveness and universality of the proposed approach. Encouragingly, the proposed unified model achieves comparable results with the fine-tuning approach that requires multiple models to preserve the particular knowledge. Further analyses reveal that the domain transformation networks successfully capture the domain-specific knowledge as expected.