DeepAI AI Chat
Log In Sign Up

Domain Adaptation and Multi-Domain Adaptation for Neural Machine Translation: A Survey

by   Danielle Saunders, et al.

The development of deep learning techniques has allowed Neural Machine Translation (NMT) models to become extremely powerful, given sufficient training data and training time. However, systems struggle when translating text from a new domain with a distinct style or vocabulary. Tuning on a representative training corpus allows good in-domain translation, but such data-centric approaches can cause over-fitting to new data and `catastrophic forgetting' of previously learned behaviour. We concentrate on more robust approaches to domain adaptation for NMT, particularly the case where a system may need to translate sentences from multiple domains. We divide techniques into those relating to data selection, model architecture, parameter adaptation procedure, and inference procedure. We finally highlight the benefits of domain adaptation and multi-domain adaptation techniques to other lines of NMT research.


page 1

page 2

page 3

page 4


Domain specialization: a post-training domain adaptation for Neural Machine Translation

Domain adaptation is a key feature in Machine Translation. It generally ...

CrossTrainer: Practical Domain Adaptation with Loss Reweighting

Domain adaptation provides a powerful set of model training techniques g...

Revisiting the Weaknesses of Reinforcement Learning for Neural Machine Translation

Policy gradient algorithms have found wide adoption in NLP, but have rec...

Multi-Domain Adaptation in Neural Machine Translation Through Multidimensional Tagging

Many modern Neural Machine Translation (NMT) systems are trained on nonh...

Fast Domain Adaptation for Neural Machine Translation

Neural Machine Translation (NMT) is a new approach for automatic transla...

Investigating Catastrophic Forgetting During Continual Training for Neural Machine Translation

Neural machine translation (NMT) models usually suffer from catastrophic...

FDMT: A Benchmark Dataset for Fine-grained Domain Adaptation in Machine Translation

Previous domain adaptation research usually neglect the diversity in tra...