UCAM Biomedical Translation at WMT19: Transfer Learning Multi-domain Ensembles

Danielle Saunders, Felix Stahlberg, Bill Byrne


Abstract
The 2019 WMT Biomedical translation task involved translating Medline abstracts. We approached this using transfer learning to obtain a series of strong neural models on distinct domains, and combining them into multi-domain ensembles. We further experimented with an adaptive language-model ensemble weighting scheme. Our submission achieved the best submitted results on both directions of English-Spanish.
Anthology ID:
W19-5421
Volume:
Proceedings of the Fourth Conference on Machine Translation (Volume 3: Shared Task Papers, Day 2)
Month:
August
Year:
2019
Address:
Florence, Italy
Venue:
WMT
SIG:
SIGMT
Publisher:
Association for Computational Linguistics
Note:
Pages:
169–174
Language:
URL:
https://aclanthology.org/W19-5421
DOI:
10.18653/v1/W19-5421
Bibkey:
Cite (ACL):
Danielle Saunders, Felix Stahlberg, and Bill Byrne. 2019. UCAM Biomedical Translation at WMT19: Transfer Learning Multi-domain Ensembles. In Proceedings of the Fourth Conference on Machine Translation (Volume 3: Shared Task Papers, Day 2), pages 169–174, Florence, Italy. Association for Computational Linguistics.
Cite (Informal):
UCAM Biomedical Translation at WMT19: Transfer Learning Multi-domain Ensembles (Saunders et al., WMT 2019)
Copy Citation:
PDF:
https://aclanthology.org/W19-5421.pdf