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

Zi-Yi Dou, Junjie Hu, Antonios Anastasopoulos, Graham Neubig


Abstract
The recent success of neural machine translation models relies on the availability of high quality, in-domain data. Domain adaptation is required when domain-specific data is scarce or nonexistent. Previous unsupervised domain adaptation strategies include training the model with in-domain copied monolingual or back-translated data. However, these methods use generic representations for text regardless of domain shift, which makes it infeasible for translation models to control outputs conditional on a specific domain. In this work, we propose an approach that adapts models with domain-aware feature embeddings, which are learned via an auxiliary language modeling task. Our approach allows the model to assign domain-specific representations to words and output sentences in the desired domain. Our empirical results demonstrate the effectiveness of the proposed strategy, achieving consistent improvements in multiple experimental settings. In addition, we show that combining our method with back translation can further improve the performance of the model.
Anthology ID:
D19-1147
Volume:
Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)
Month:
November
Year:
2019
Address:
Hong Kong, China
Venues:
EMNLP | IJCNLP
SIG:
SIGDAT
Publisher:
Association for Computational Linguistics
Note:
Pages:
1417–1422
Language:
URL:
https://aclanthology.org/D19-1147
DOI:
10.18653/v1/D19-1147
Bibkey:
Cite (ACL):
Zi-Yi Dou, Junjie Hu, Antonios Anastasopoulos, and Graham Neubig. 2019. Unsupervised Domain Adaptation for Neural Machine Translation with Domain-Aware Feature Embeddings. In Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP), pages 1417–1422, Hong Kong, China. Association for Computational Linguistics.
Cite (Informal):
Unsupervised Domain Adaptation for Neural Machine Translation with Domain-Aware Feature Embeddings (Dou et al., EMNLP-IJCNLP 2019)
Copy Citation:
PDF:
https://preview.aclanthology.org/paclic-22-ingestion/D19-1147.pdf
Code
 zdou0830/DAFE