/sockeye

Sequence-to-sequence framework with a focus on Neural Machine Translation based on Apache MXNet

Primary LanguagePythonApache License 2.0Apache-2.0

Sockeye

PyPI version GitHub license GitHub issues Build Status Documentation Status

This package contains the Sockeye project, a sequence-to-sequence framework for Neural Machine Translation based on Apache MXNet (Incubating). It implements state-of-the-art encoder-decoder architectures, such as:

In addition, it provides an experimental image-to-description module that can be used for image captioning. Recent developments and changes are tracked in our CHANGELOG.

If you have any questions or discover problems, please file an issue. You can also send questions to sockeye-dev-at-amazon-dot-com.

Documentation

For information on how to use Sockeye, please visit our documentation. Developers may be interested in our developer guidelines.

Citation

For technical information about Sockeye, see our paper on the arXiv (BibTeX):

Felix Hieber, Tobias Domhan, Michael Denkowski, David Vilar, Artem Sokolov, Ann Clifton and Matt Post. 2017. Sockeye: A Toolkit for Neural Machine Translation. ArXiv e-prints.