Extreme Adaptation for Personalized Neural Machine Translation

Paul Michel, Graham Neubig


Abstract
Every person speaks or writes their own flavor of their native language, influenced by a number of factors: the content they tend to talk about, their gender, their social status, or their geographical origin. When attempting to perform Machine Translation (MT), these variations have a significant effect on how the system should perform translation, but this is not captured well by standard one-size-fits-all models. In this paper, we propose a simple and parameter-efficient adaptation technique that only requires adapting the bias of the output softmax to each particular user of the MT system, either directly or through a factored approximation. Experiments on TED talks in three languages demonstrate improvements in translation accuracy, and better reflection of speaker traits in the target text.
Anthology ID:
P18-2050
Volume:
Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)
Month:
July
Year:
2018
Address:
Melbourne, Australia
Editors:
Iryna Gurevych, Yusuke Miyao
Venue:
ACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
312–318
Language:
URL:
https://aclanthology.org/P18-2050
DOI:
10.18653/v1/P18-2050
Bibkey:
Cite (ACL):
Paul Michel and Graham Neubig. 2018. Extreme Adaptation for Personalized Neural Machine Translation. In Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers), pages 312–318, Melbourne, Australia. Association for Computational Linguistics.
Cite (Informal):
Extreme Adaptation for Personalized Neural Machine Translation (Michel & Neubig, ACL 2018)
Copy Citation:
PDF:
https://aclanthology.org/P18-2050.pdf
Note:
 P18-2050.Notes.pdf
Code
 neulab/extreme-adaptation-for-personalized-translation