The AFRL WMT18 Systems: Ensembling, Continuation and Combination
Jeremy Gwinnup, Tim Anderson, Grant Erdmann, Katherine Young
Abstract
This paper describes the Air Force Research Laboratory (AFRL) machine translation systems and the improvements that were developed during the WMT18 evaluation campaign. This year, we examined the developments and additions to popular neural machine translation toolkits and measure improvements in performance on the Russian–English language pair.- Anthology ID:
- W18-6411
- Volume:
- Proceedings of the Third Conference on Machine Translation: Shared Task Papers
- Month:
- October
- Year:
- 2018
- Address:
- Belgium, Brussels
- Editors:
- Ondřej Bojar, Rajen Chatterjee, Christian Federmann, Mark Fishel, Yvette Graham, Barry Haddow, Matthias Huck, Antonio Jimeno Yepes, Philipp Koehn, Christof Monz, Matteo Negri, Aurélie Névéol, Mariana Neves, Matt Post, Lucia Specia, Marco Turchi, Karin Verspoor
- Venue:
- WMT
- SIG:
- SIGMT
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 394–398
- Language:
- URL:
- https://aclanthology.org/W18-6411
- DOI:
- 10.18653/v1/W18-6411
- Cite (ACL):
- Jeremy Gwinnup, Tim Anderson, Grant Erdmann, and Katherine Young. 2018. The AFRL WMT18 Systems: Ensembling, Continuation and Combination. In Proceedings of the Third Conference on Machine Translation: Shared Task Papers, pages 394–398, Belgium, Brussels. Association for Computational Linguistics.
- Cite (Informal):
- The AFRL WMT18 Systems: Ensembling, Continuation and Combination (Gwinnup et al., WMT 2018)
- PDF:
- https://preview.aclanthology.org/emnlp-22-attachments/W18-6411.pdf