UCAM Biomedical Translation at WMT19: Transfer Learning Multi-domain Ensembles
The result's identifiers
Result code in IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216208%3A11320%2F19%3A10427148" target="_blank" >RIV/00216208:11320/19:10427148 - isvavai.cz</a>
Result on the web
<a href="https://www.aclweb.org/anthology/W19-5421" target="_blank" >https://www.aclweb.org/anthology/W19-5421</a>
DOI - Digital Object Identifier
—
Alternative languages
Result language
angličtina
Original language name
UCAM Biomedical Translation at WMT19: Transfer Learning Multi-domain Ensembles
Original language description
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.
Czech name
—
Czech description
—
Classification
Type
O - Miscellaneous
CEP classification
—
OECD FORD branch
10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)
Result continuities
Project
—
Continuities
—
Others
Publication year
2019
Confidentiality
S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů