@inproceedings{ott-etal-2018-scaling,
title = "Scaling Neural Machine Translation",
author = "Ott, Myle and
Edunov, Sergey and
Grangier, David and
Auli, Michael",
editor = "Bojar, Ond{\v{r}}ej and
Chatterjee, Rajen and
Federmann, Christian and
Fishel, Mark and
Graham, Yvette and
Haddow, Barry and
Huck, Matthias and
Yepes, Antonio Jimeno and
Koehn, Philipp and
Monz, Christof and
Negri, Matteo and
N{\'e}v{\'e}ol, Aur{\'e}lie and
Neves, Mariana and
Post, Matt and
Specia, Lucia and
Turchi, Marco and
Verspoor, Karin",
booktitle = "Proceedings of the Third Conference on Machine Translation: Research Papers",
month = oct,
year = "2018",
address = "Brussels, Belgium",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/W18-6301",
doi = "10.18653/v1/W18-6301",
pages = "1--9",
abstract = "Sequence to sequence learning models still require several days to reach state of the art performance on large benchmark datasets using a single machine. This paper shows that reduced precision and large batch training can speedup training by nearly 5x on a single 8-GPU machine with careful tuning and implementation. On WMT{'}14 English-German translation, we match the accuracy of Vaswani et al. (2017) in under 5 hours when training on 8 GPUs and we obtain a new state of the art of 29.3 BLEU after training for 85 minutes on 128 GPUs. We further improve these results to 29.8 BLEU by training on the much larger Paracrawl dataset. On the WMT{'}14 English-French task, we obtain a state-of-the-art BLEU of 43.2 in 8.5 hours on 128 GPUs.",
}
Markdown (Informal)
[Scaling Neural Machine Translation](https://aclanthology.org/W18-6301) (Ott et al., WMT 2018)
ACL
- Myle Ott, Sergey Edunov, David Grangier, and Michael Auli. 2018. Scaling Neural Machine Translation. In Proceedings of the Third Conference on Machine Translation: Research Papers, pages 1–9, Brussels, Belgium. Association for Computational Linguistics.