# Improving Domain Adaptation Translation with Domain Invariant and Specific Information

arXiv: https://arxiv.org/abs/1904.03879 · HTML: https://mlsanity.com/paper/1904.03879/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 8 Apr 2019.

## Built on by (most cited first, 7 of 7)

- [Domain Adaptation and Multi-Domain Adaptation for Neural Machine Translation: A Survey](https://mlsanity.com/paper/2104.06951/) (2021)
- [Overcoming Catastrophic Forgetting beyond Continual Learning: Balanced Training for Neural Machine Translation](https://mlsanity.com/paper/2203.03910/) (2022)
- [Pruning-then-Expanding Model for Domain Adaptation of Neural Machine Translation](https://mlsanity.com/paper/2103.13678/) (2021)
- [Guiding Teacher Forcing with Seer Forcing for Neural Machine Translation](https://mlsanity.com/paper/2106.06751/) (2021)
- [Continual Learning of Neural Machine Translation within Low Forgetting Risk Regions](https://mlsanity.com/paper/2211.01542/) (2022)
- [Powering Comparative Classification with Sentiment Analysis via Domain Adaptive Knowledge Transfer](https://mlsanity.com/paper/2109.03819/) (2021)
- [Can Domains Be Transferred Across Languages in Multi-Domain Multilingual Neural Machine Translation?](https://mlsanity.com/paper/2210.11628/) (2022)

## Abstract (arXiv)

In domain adaptation for neural machine translation, translation performance can benefit from separating features into domain-specific features and common features. In this paper, we propose a method to explicitly model the two kinds of information in the encoder-decoder framework so as to exploit out-of-domain data in in-domain training. In our method, we maintain a private encoder and a private decoder for each domain which are used to model domain-specific information. In the meantime, we introduce a common encoder and a common decoder shared by all the domains which can only have domain-independent information flow through. Besides, we add a discriminator to the shared encoder and employ adversarial training for the whole model to reinforce the performance of information separation and machine translation simultaneously. Experiment results show that our method can outperform competitive baselines greatly on multiple data sets.