论文信息 - Sockeye 2: A Toolkit for Neural Machine Translation

Sockeye 2: A Toolkit for Neural Machine Translation

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, and distributed mixed precision training. These improvements result in faster training and inference, higher automatic metric scores, and a shorter path from research to production.

[1] Michael J. Denkowski,et al. Sockeye: A Toolkit for Neural Machine Translation , 2017, ArXiv.

[2] Myle Ott,et al. Scaling Neural Machine Translation , 2018, WMT.

[3] Alexander Sergeev,et al. Horovod: fast and easy distributed deep learning in TensorFlow , 2018, ArXiv.

[4] Lukasz Kaiser,et al. Attention is All you Need , 2017, NIPS.

[5] Zheng Zhang,et al. MXNet: A Flexible and Efficient Machine Learning Library for Heterogeneous Distributed Systems , 2015, ArXiv.

[6] Marta R. Costa-jussà,et al. Findings of the 2019 Conference on Machine Translation (WMT19) , 2019, WMT.

[7] Matt Post,et al. A Call for Clarity in Reporting BLEU Scores , 2018, WMT.

[8] Hermann Ney,et al. The RWTH Aachen University Supervised Machine Translation Systems for WMT 2018 , 2018, WMT.