Efficient Machine Translation Domain Adaptation

Pedro Martins, Zita Marinho, Andre Martins


Abstract
Machine translation models struggle when translating out-of-domain text, which makes domain adaptation a topic of critical importance. However, most domain adaptation methods focus on fine-tuning or training the entire or part of the model on every new domain, which can be costly. On the other hand, semi-parametric models have been shown to successfully perform domain adaptation by retrieving examples from an in-domain datastore (Khandelwal et al., 2021). A drawback of these retrieval-augmented models, however, is that they tend to be substantially slower. In this paper, we explore several approaches to speed up nearest neighbors machine translation. We adapt the methods recently proposed by He et al. (2021) for language modeling, and introduce a simple but effective caching strategy that avoids performing retrieval when similar contexts have been seen before. Translation quality and runtimes for several domains show the effectiveness of the proposed solutions.
Anthology ID:
2022.spanlp-1.3
Volume:
Proceedings of the 1st Workshop on Semiparametric Methods in NLP: Decoupling Logic from Knowledge
Month:
May
Year:
2022
Address:
Dublin, Ireland and Online
Editors:
Rajarshi Das, Patrick Lewis, Sewon Min, June Thai, Manzil Zaheer
Venue:
SpaNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
23–29
Language:
URL:
https://aclanthology.org/2022.spanlp-1.3
DOI:
10.18653/v1/2022.spanlp-1.3
Bibkey:
Cite (ACL):
Pedro Martins, Zita Marinho, and Andre Martins. 2022. Efficient Machine Translation Domain Adaptation. In Proceedings of the 1st Workshop on Semiparametric Methods in NLP: Decoupling Logic from Knowledge, pages 23–29, Dublin, Ireland and Online. Association for Computational Linguistics.
Cite (Informal):
Efficient Machine Translation Domain Adaptation (Martins et al., SpaNLP 2022)
Copy Citation:
PDF:
https://aclanthology.org/2022.spanlp-1.3.pdf
Video:
 https://aclanthology.org/2022.spanlp-1.3.mp4
Code
 deep-spin/efficient_knn_mt