Location via proxy:   [ UP ]  
[Report a bug]   [Manage cookies]                

Samsung and University of Edinburgh’s System for the IWSLT 2018 Low Resource MT Task

Philip Williams, Marcin Chochowski, Pawel Przybysz, Rico Sennrich, Barry Haddow, Alexandra Birch


Abstract
This paper describes the joint submission to the IWSLT 2018 Low Resource MT task by Samsung R&D Institute, Poland, and the University of Edinburgh. We focused on supplementing the very limited in-domain Basque-English training data with out-of-domain data, with synthetic data, and with data for other language pairs. We also experimented with a variety of model architectures and features, which included the development of extensions to the Nematus toolkit. Our submission was ultimately produced by a system combination in which we reranked translations from our strongest individual system using multiple weaker systems.
Anthology ID:
2018.iwslt-1.17
Volume:
Proceedings of the 15th International Conference on Spoken Language Translation
Month:
October 29-30
Year:
2018
Address:
Brussels
Editors:
Marco Turchi, Jan Niehues, Marcello Frederico
Venue:
IWSLT
SIG:
SIGSLT
Publisher:
International Conference on Spoken Language Translation
Note:
Pages:
118–123
Language:
URL:
https://aclanthology.org/2018.iwslt-1.17
DOI:
Bibkey:
Cite (ACL):
Philip Williams, Marcin Chochowski, Pawel Przybysz, Rico Sennrich, Barry Haddow, and Alexandra Birch. 2018. Samsung and University of Edinburgh’s System for the IWSLT 2018 Low Resource MT Task. In Proceedings of the 15th International Conference on Spoken Language Translation, pages 118–123, Brussels. International Conference on Spoken Language Translation.
Cite (Informal):
Samsung and University of Edinburgh’s System for the IWSLT 2018 Low Resource MT Task (Williams et al., IWSLT 2018)
Copy Citation:
PDF:
https://aclanthology.org/2018.iwslt-1.17.pdf