The Sockeye 2 Neural Machine Translation Toolkit at AMTA 2020
arXiv:2008.04885
Abstract
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.
References in corpus (4)
- Sequence to Sequence Learning with Neural Networks
- Google's Neural Machine Translation System: Bridging the Gap between Human and Machine Translation
- Regularizing Neural Networks by Penalizing Confident Output Distributions
- Is Neural Machine Translation Ready for Deployment? A Case Study on 30 Translation Directions
Cited by in corpus (6)
- GluonTS: Probabilistic Time Series Models in Python
- Subword Segmentation and a Single Bridge Language Affect Zero-Shot Neural Machine Translation
- When and Why is Document-level Context Useful in Neural Machine Translation?
- Faithful Target Attribute Prediction in Neural Machine Translation
- XFORMAL: A Benchmark for Multilingual Formality Style Transfer
- Segmenting Subtitles for Correcting ASR Segmentation Errors