DeepAI AI Chat
Log In Sign Up

Domain Differential Adaptation for Neural Machine Translation

by   Zi-Yi Dou, et al.
Carnegie Mellon University

Neural networks are known to be data hungry and domain sensitive, but it is nearly impossible to obtain large quantities of labeled data for every domain we are interested in. This necessitates the use of domain adaptation strategies. One common strategy encourages generalization by aligning the global distribution statistics between source and target domains, but one drawback is that the statistics of different domains or tasks are inherently divergent, and smoothing over these differences can lead to sub-optimal performance. In this paper, we propose the framework of Domain Differential Adaptation (DDA), where instead of smoothing over these differences we embrace them, directly modeling the difference between domains using models in a related task. We then use these learned domain differentials to adapt models for the target task accordingly. Experimental results on domain adaptation for neural machine translation demonstrate the effectiveness of this strategy, achieving consistent improvements over other alternative adaptation strategies in multiple experimental settings.


page 1

page 2

page 3

page 4


Unsupervised Domain Adaptation for Neural Machine Translation with Domain-Aware Feature Embeddings

The recent success of neural machine translation models relies on the av...

Domain Control for Neural Machine Translation

Machine translation systems are very sensitive to the domains they were ...

Iterative Dual Domain Adaptation for Neural Machine Translation

Previous studies on the domain adaptation for neural machine translation...

Curriculum Learning for Domain Adaptation in Neural Machine Translation

We introduce a curriculum learning approach to adapt generic neural mach...

Domain Adaptation with L2 constraints for classifying images from different endoscope systems

This paper proposes a method for domain adaptation that extends the maxi...

Unsupervised Neural Domain Adaptation for Document Image Binarization

Binarization is a well-known image processing task, whose objective is t...

Label-Free Multi-Domain Machine Translation with Stage-wise Training

Most multi-domain machine translation models rely on domain-annotated da...