The Sockeye 2 Neural Machine Translation Toolkit at AMTA 2020
This is an incremental update to a toolkit for researchers and practitioners in machine translation, improving usability and performance.
The authors tackled the need for an efficient and modern neural machine translation toolkit by presenting Sockeye 2, which resulted in faster training and inference, higher automatic metric scores, and a shorter path from research to production.
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.