Learning Hidden Unit Contribution for Adapting Neural Machine Translation Models

David Vilar


Abstract
In this paper we explore the use of Learning Hidden Unit Contribution for the task of neural machine translation. The method was initially proposed in the context of speech recognition for adapting a general system to the specific acoustic characteristics of each speaker. Similar in spirit, in a machine translation framework we want to adapt a general system to a specific domain. We show that the proposed method achieves improvements of up to 2.6 BLEU points over a general system, and up to 6 BLEU points if the initial system has only been trained on out-of-domain data, a situation which may easily happen in practice. The good performance together with its short training time and small memory footprint make it a very attractive solution for domain adaptation.
Anthology ID:
N18-2080
Volume:
Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 2 (Short Papers)
Month:
June
Year:
2018
Address:
New Orleans, Louisiana
Editors:
Marilyn Walker, Heng Ji, Amanda Stent
Venue:
NAACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
500–505
Language:
URL:
https://aclanthology.org/N18-2080
DOI:
10.18653/v1/N18-2080
Bibkey:
Cite (ACL):
David Vilar. 2018. Learning Hidden Unit Contribution for Adapting Neural Machine Translation Models. In Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 2 (Short Papers), pages 500–505, New Orleans, Louisiana. Association for Computational Linguistics.
Cite (Informal):
Learning Hidden Unit Contribution for Adapting Neural Machine Translation Models (Vilar, NAACL 2018)
Copy Citation:
PDF:
https://aclanthology.org/N18-2080.pdf