ResearchTrend.AI
  • Papers
  • Communities
  • Events
  • Blog
  • Pricing
Papers
Communities
Social Events
Terms and Conditions
Pricing
Parameter LabParameter LabTwitterGitHubLinkedInBlueskyYoutube

© 2025 ResearchTrend.AI, All rights reserved.

  1. Home
  2. Papers
  3. 2008.04885
6
52

The Sockeye 2 Neural Machine Translation Toolkit at AMTA 2020

11 August 2020
Tobias Domhan
Michael J. Denkowski
David Vilar
Xing Niu
F. Hieber
Kenneth Heafield
ArXivPDFHTML
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, 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.

View on arXiv
Comments on this paper