UCAM Biomedical Translation at WMT19: Transfer Learning Multi-domain Ensembles
Published version
Peer-reviewed
Repository URI
Repository DOI
Change log
Authors
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 experiment with an adaptive language-model ensemble weighting scheme. Our submission achieved the best submitted results on both directions of English-Spanish.
Description
Keywords
Journal Title
Proceedings of the Fourth Conference on Machine Translation (Volume 3: Shared Task Papers, Day 2)
Conference Name
Proceedings of the Fourth Conference on Machine Translation (Volume 3: Shared Task Papers, Day 2)
Journal ISSN
Volume Title
Publisher
Association for Computational Linguistics
Publisher DOI
Sponsorship
EPSRC (1750003)