Multilingual Multi-Domain Adaptation Approaches for Neural Machine Translation
arXiv:1906.07978
Abstract
In this paper, we propose two novel methods for domain adaptation for the attention-only neural machine translation (NMT) model, i.e., the Transformer. Our methods focus on training a single translation model for multiple domains by either learning domain specialized hidden state representations or predictor biases for each domain. We combine our methods with a previously proposed black-box method called mixed fine tuning, which is known to be highly effective for domain adaptation. In addition, we incorporate multilingualism into the domain adaptation framework. Experiments show that multilingual multi-domain adaptation can significantly improve both resource-poor in-domain and resource-rich out-of-domain translations, and the combination of our methods with mixed fine tuning achieves the best performance.
References in corpus (7)
- Sequence to Sequence Learning with Neural Networks
- Frustratingly Easy Domain Adaptation
- Fast Domain Adaptation for Neural Machine Translation
- Freezing Subnetworks to Analyze Domain Adaptation in Neural Machine Translation
- Neural Machine Translation Training in a Multi-Domain Scenario
- Domain specialization: a post-training domain adaptation for Neural Machine Translation
- Domain Control for Neural Machine Translation