Papers › Sockeye: A Toolkit for Neural Machine Translation

Sockeye: A Toolkit for Neural Machine Translation

15 Dec 2017arXiv:1712.05690archive 2025-07-28

Felix Hieber, Tobias Domhan, Michael Denkowski, David Vilar, Artem Sokolov, Ann Clifton, Matt Post

We describe Sockeye (version 1.12), an open-source sequence-to-sequence toolkit for Neural Machine Translation (NMT). Sockeye is a production-ready framework for training and applying models as well as an experimental platform for researchers. Written in Python and built on MXNet, the toolkit offers scalable training and inference for the three most prominent encoder-decoder architectures: attentional recurrent neural networks, self-attentional transformers, and fully convolutional networks. Sockeye also supports a wide range of optimizers, normalization and regularization techniques, and inference improvements from current NMT literature. Users can easily run standard training recipes, explore different model settings, and incorporate new ideas. In this paper, we highlight Sockeye's features and benchmark it against other NMT toolkits on two language arcs from the 2017 Conference on Machine Translation (WMT): English-German and Latvian-English. We report competitive BLEU scores across all three architectures, including an overall best score for Sockeye's transformer implementation. To facilitate further comparison, we release all system outputs and training scripts used in our experiments. The Sockeye toolkit is free software released under the Apache 2.0 license.

PaperPDFCode

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

16 repositories listed; official and paper-mentioned ones first.

awslabs/sockeye officialmentioned in papermentioned on GitHubmxnetApache-2.0 report
Izecson/saml-nmt mentioned on GitHubmxnet report
Izecson/sockeye-1.16.6 mentioned on GitHubtf report
StatNLP/joeynmt mentioned on GitHubpytorchApache-2.0 report
ZurichNLP/sockeye mentioned on GitHubmxnetApache-2.0 report
ducthanhtran/sockeye_document_context mentioned on GitHubmxnetApache-2.0 report
jarl93/joeynmt-modified mentioned on GitHubpytorchMIT report
joeynmt/joeynmt mentioned on GitHubpytorchApache-2.0 report
juliakreutzer/joeynmt mentioned on GitHubpytorchMIT report
nrc-cnrc/sockeye-multisource mentioned on GitHubmxnet report
penny9287/sockeye mentioned on GitHubmxnet report
songchujun/joeynmt mentioned on GitHubpytorchApache-2.0 report
xingniu/sockeye mentioned on GitHubmxnet report
yunsukim86/sockeye-noise mentioned on GitHubmxnet report
yunsukim86/sockeye-transfer mentioned on GitHubmxnet report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

DecoderMachine TranslationNMTTranslation

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

Absolute Position EncodingsAdamAttentionBPEDense ConnectionsDropoutLabel SmoothingLayer NormalizationLinear LayerMulti-Head AttentionPosition-Wise Feed-Forward LayerReLUResidual ConnectionSoftmaxTransformer

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections