Evaluation of Terminology Translation in Instance-Based Neural MT Adaptation

M. Amin Farajian, Nicola Bertoldi, Matteo Negri, Marco Turchi, Marcello Federico


Abstract
We address the issues arising when a neural machine translation engine trained on generic data receives requests from a new domain that contains many specific technical terms. Given training data of the new domain, we consider two alternative methods to adapt the generic system: corpus-based and instance-based adaptation. While the first approach is computationally more intensive in generating a domain-customized network, the latter operates more efficiently at translation time and can handle on-the-fly adaptation to multiple domains. Besides evaluating the generic and the adapted networks with conventional translation quality metrics, in this paper we focus on their ability to properly handle domain-specific terms. We show that instance-based adaptation, by fine-tuning the model on-the-fly, is capable to significantly boost the accuracy of translated terms, producing translations of quality comparable to the expensive corpusbased method.
Anthology ID:
2018.eamt-main.15
Volume:
Proceedings of the 21st Annual Conference of the European Association for Machine Translation
Month:
May
Year:
2018
Address:
Alicante, Spain
Editors:
Juan Antonio Pérez-Ortiz, Felipe Sánchez-Martínez, Miquel Esplà-Gomis, Maja Popović, Celia Rico, André Martins, Joachim Van den Bogaert, Mikel L. Forcada
Venue:
EAMT
SIG:
Publisher:
Note:
Pages:
169–178
Language:
URL:
https://aclanthology.org/2018.eamt-main.15
DOI:
Bibkey:
Cite (ACL):
M. Amin Farajian, Nicola Bertoldi, Matteo Negri, Marco Turchi, and Marcello Federico. 2018. Evaluation of Terminology Translation in Instance-Based Neural MT Adaptation. In Proceedings of the 21st Annual Conference of the European Association for Machine Translation, pages 169–178, Alicante, Spain.
Cite (Informal):
Evaluation of Terminology Translation in Instance-Based Neural MT Adaptation (Farajian et al., EAMT 2018)
Copy Citation:
PDF:
https://aclanthology.org/2018.eamt-main.15.pdf