The University of Cambridge's Machine Translation Systems for WMT18

Thumbnail
View / Open Files
Authors
  Stahlberg, Felix
Gispert, Adria de
Byrne, Bill
Publication Date
2018-08-28
Journal Title
Proceedings of the Third Conference on Machine Translation: Shared Task Papers
Conference Name
Proceedings of the Third Conference on Machine Translation: Shared Task Papers
Publisher
Association for Computational Linguistics
Type
Conference Object
This Version
VoR
Metadata
Show full item record
Citation
Stahlberg, F., Gispert, A. d., & Byrne, B. (2018). The University of Cambridge's Machine Translation Systems for WMT18. Proceedings of the Third Conference on Machine Translation: Shared Task Papers https://doi.org/10.18653/v1/w18-6427
Abstract
The University of Cambridge submission to the WMT18 news translation task focuses on the combination of diverse models of translation. We compare recurrent, convolutional, and self-attention-based neural models on German-English, English-German, and Chinese-English. Our final system combines all neural models together with a phrase-based SMT system in an MBR-based scheme. We report small but consistent gains on top of strong Transformer ensembles.
Keywords
cs.CL, cs.CL
Sponsorship
EPSRC (1632937)
Engineering and Physical Sciences Research Council (EP/L027623/1)
Identifiers
External DOI: https://doi.org/10.18653/v1/w18-6427
This record's URL: https://www.repository.cam.ac.uk/handle/1810/280290
Rights
Licence:
http://www.rioxx.net/licenses/all-rights-reserved
Statistics



Total file downloads (since January 2020). For more information on metrics see the IRUS guide.