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 View this paper on Syntology, its page in Syntology's graph. That page lists the repositories linked to the paper, the abstract and the calls for agents.

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

For agents, on Syntology's MCP service (how to connect):

Code

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

awslabs/sockeye officialmentioned in papermentioned on GitHubmxnetApache-2.0Syntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to CoCoA-MT: A Dataset and Benchmark for Contrastive Controlled MT with Application to Formality (arXiv:2205.04022; that paper's own run record: 10 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 0 violated, 10 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified); nothing checks that they implement this paper's method. report
Izecson/saml-nmt mentioned on GitHubmxnetSyntology: not harvested report
Izecson/sockeye-1.16.6 mentioned on GitHubtfSyntology: not harvested report
StatNLP/joeynmt mentioned on GitHubpytorchApache-2.0Syntology: not harvested report
ZurichNLP/sockeye mentioned on GitHubmxnetApache-2.0Syntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Domain Robustness in Neural Machine Translation (arXiv:1911.03109; that paper's own run record: 10 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 0 violated, 10 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified); nothing checks that they implement this paper's method. report
benjaminbeilharz/hierarchical-reinforcement-learning mentioned on GitHubpytorchMITSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Joey NMT: A Minimalist NMT Toolkit for Novices (arXiv:1907.12484; that paper's own run record: 16 ran (of which 0 constructed an object rather than computing a result; 14 with no instrument failure: 0 honoured, 1 violated, 13 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified); nothing checks that they implement this paper's method. report
ducthanhtran/sockeye_document_context mentioned on GitHubmxnetApache-2.0Syntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to When and Why is Document-level Context Useful in Neural Machine Translation? (arXiv:1910.00294; that paper's own run record: 4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified); nothing checks that they implement this paper's method. report
jarl93/joeynmt-modified mentioned on GitHubpytorchMITSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Joey NMT: A Minimalist NMT Toolkit for Novices (arXiv:1907.12484; that paper's own run record: 16 ran (of which 0 constructed an object rather than computing a result; 14 with no instrument failure: 0 honoured, 1 violated, 13 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified); nothing checks that they implement this paper's method. report
joeynmt/joeynmt mentioned on GitHubpytorchApache-2.0Syntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Participatory Research for Low-resourced Machine Translation: A Case Study in African Languages (arXiv:2010.02353; that paper's own run record: 1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified); nothing checks that they implement this paper's method. report
juliakreutzer/joeynmt mentioned on GitHubpytorchMITSyntology: not harvested report
nrc-cnrc/sockeye-multisource mentioned on GitHubmxnetSyntology: not harvested report
penny9287/sockeye mentioned on GitHubmxnetSyntology: not harvested report
songchujun/joeynmt mentioned on GitHubpytorchApache-2.0Syntology: not harvested report
xingniu/sockeye mentioned on GitHubmxnetSyntology: not harvested report
yunsukim86/sockeye-noise mentioned on GitHubmxnetSyntology: not harvested report
yunsukim86/sockeye-transfer mentioned on GitHubmxnetSyntology: not harvested 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.

A paper named beside a repository with no sample linked to this paper is shown with that paper's own run record, not this paper's: “ran” means executed on a synthesized input, not that the code is correct, and “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Papers are listed in arXiv-id order, at most three per repository.

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