The Sockeye 2 Neural Machine Translation Toolkit at AMTA 2020

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, distributed mixed precision training, and effici...

Full description

Saved in:
Bibliographic Details
Published inarXiv.org
Main Authors Domhan, Tobias, Denkowski, Michael, Vilar, David, Niu, Xing, Hieber, Felix, Heafield, Kenneth
Format Paper
LanguageEnglish
Published Ithaca Cornell University Library, arXiv.org 11.08.2020
Subjects
Decoding
Gluons
Machine translation
Modernization
Toolkits
Training
Online AccessGet full text

Cover

More Information
Summary: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, distributed mixed precision training, and efficient CPU decoding with 8-bit quantization. These improvements result in faster training and inference, higher automatic metric scores, and a shorter path from research to production.
ISSN:2331-8422