Abstract
This paper describes the University of Sydney’s submission of the WMT 2019 shared news translation task. We participated in the Finnish->English direction and got the best BLEU(33.0) score among all the participants. Our system is based on the self-attentional Transformer networks, into which we integrated the most recent effective strategies from academic research (e.g., BPE, back translation, multi-features data selection, data augmentation, greedy model ensemble, reranking, ConMBR system combination, and postprocessing). Furthermore, we propose a novel augmentation method Cycle Translation and a data mixture strategy Big/Small parallel construction to entirely exploit the synthetic corpus. Extensive experiments show that adding the above techniques can make continuous improvements of the BLEU scores, and the best result outperforms the baseline (Transformer ensemble model trained with the original parallel corpus) by approximately 5.3 BLEU score, achieving the state-of-the-art performance.- Anthology ID:
- W19-5314
- Volume:
- Proceedings of the Fourth Conference on Machine Translation (Volume 2: Shared Task Papers, Day 1)
- Month:
- August
- Year:
- 2019
- Address:
- Florence, Italy
- Editors:
- Ondřej Bojar, Rajen Chatterjee, Christian Federmann, Mark Fishel, Yvette Graham, Barry Haddow, Matthias Huck, Antonio Jimeno Yepes, Philipp Koehn, André Martins, Christof Monz, Matteo Negri, Aurélie Névéol, Mariana Neves, Matt Post, Marco Turchi, Karin Verspoor
- Venue:
- WMT
- SIG:
- SIGMT
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 175–182
- Language:
- URL:
- https://aclanthology.org/W19-5314
- DOI:
- 10.18653/v1/W19-5314
- Cite (ACL):
- Liang Ding and Dacheng Tao. 2019. The University of Sydney’s Machine Translation System for WMT19. In Proceedings of the Fourth Conference on Machine Translation (Volume 2: Shared Task Papers, Day 1), pages 175–182, Florence, Italy. Association for Computational Linguistics.
- Cite (Informal):
- The University of Sydney’s Machine Translation System for WMT19 (Ding & Tao, WMT 2019)
- PDF:
- https://preview.aclanthology.org/dois-2013-emnlp/W19-5314.pdf
- Data
- WMT 2016, WMT 2016 News, WMT 2018