Alek Andreev
2020
The DeepMind Chinese–English Document Translation System at WMT2020
Lei Yu
|
Laurent Sartran
|
Po-Sen Huang
|
Wojciech Stokowiec
|
Domenic Donato
|
Srivatsan Srinivasan
|
Alek Andreev
|
Wang Ling
|
Sona Mokra
|
Agustin Dal Lago
|
Yotam Doron
|
Susannah Young
|
Phil Blunsom
|
Chris Dyer
Proceedings of the Fifth Conference on Machine Translation
This paper describes the DeepMind submission to the Chinese→English constrained data track of the WMT2020 Shared Task on News Translation. The submission employs a noisy channel factorization as the backbone of a document translation system. This approach allows the flexible combination of a number of independent component models which are further augmented with back-translation, distillation, fine-tuning with in-domain data, Monte-Carlo Tree Search decoding, and improved uncertainty estimation. In order to address persistent issues with the premature truncation of long sequences we included specialized length models and sentence segmentation techniques. Our final system provides a 9.9 BLEU points improvement over a baseline Transformer on our test set (newstest 2019).
Search
Co-authors
- Lei Yu 1
- Laurent Sartran 1
- Po-Sen Huang 1
- Wojciech Stokowiec 1
- Domenic Donato 1
- show all...
Venues
- wmt1