Sockeye 2: A Toolkit for Neural Machine Translation

Felix Hieber, Tobias Domhan, Michael Denkowski, David Vilar


Abstract
We present Sockeye 2, a modernized and streamlined version of the Sockeye neural machine translation (NMT) toolkit. New features include a simplified code base through the use of MXNet’s Gluon API, a focus on state of the art model architectures, and distributed mixed precision training. These improvements result in faster training and inference, higher automatic metric scores, and a shorter path from research to production.
Anthology ID:
2020.eamt-1.50
Volume:
Proceedings of the 22nd Annual Conference of the European Association for Machine Translation
Month:
November
Year:
2020
Address:
Lisboa, Portugal
Venue:
EAMT
SIG:
Publisher:
European Association for Machine Translation
Note:
Pages:
457–458
Language:
URL:
https://aclanthology.org/2020.eamt-1.50
DOI:
Bibkey:
Cite (ACL):
Felix Hieber, Tobias Domhan, Michael Denkowski, and David Vilar. 2020. Sockeye 2: A Toolkit for Neural Machine Translation. In Proceedings of the 22nd Annual Conference of the European Association for Machine Translation, pages 457–458, Lisboa, Portugal. European Association for Machine Translation.
Cite (Informal):
Sockeye 2: A Toolkit for Neural Machine Translation (Hieber et al., EAMT 2020)
Copy Citation:
PDF:
https://preview.aclanthology.org/update-css-js/2020.eamt-1.50.pdf
Code
 awslabs/sockeye