Speed-optimized, Compact Student Models that Distill Knowledge from a Larger Teacher Model: the UEDIN-CUNI Submission to the WMT 2020 News Translation Task
The result's identifiers
Result code in IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216208%3A11320%2F20%3A10424446" target="_blank" >RIV/00216208:11320/20:10424446 - isvavai.cz</a>
Result on the web
<a href="https://www.aclweb.org/anthology/2020.wmt-1.17.pdf" target="_blank" >https://www.aclweb.org/anthology/2020.wmt-1.17.pdf</a>
DOI - Digital Object Identifier
—
Alternative languages
Result language
angličtina
Original language name
Speed-optimized, Compact Student Models that Distill Knowledge from a Larger Teacher Model: the UEDIN-CUNI Submission to the WMT 2020 News Translation Task
Original language description
We describe the joint submission of the University of Edinburgh and Charles University, Prague, to the Czech/English track in the WMT 2020 Shared Task on News Translation. Our fast and compact student models distill knowledge from a larger, slower teacher. They are designed to offer a good trade-off between translation quality and inference efficiency. On the WMT 2020 Czech-English test sets, they achieve translation speeds of over 700 whitespace-delimited source words per second on a single CPU thread, thus making neural translation feasible on consumer hardware without a GPU.
Czech name
—
Czech description
—
Classification
Type
D - Article in proceedings
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
<a href="/en/project/LM2018101" target="_blank" >LM2018101: Digital Research Infrastructure for the Language Technologies, Arts and Humanities</a><br>
Continuities
P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)
Others
Publication year
2020
Confidentiality
S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů
Data specific for result type
Article name in the collection
Fifth Conference on Machine Translation - Proceedings of the Conference
ISBN
978-1-948087-81-0
ISSN
—
e-ISSN
—
Number of pages
6
Pages from-to
191-196
Publisher name
Association for Computational Linguistics
Place of publication
Stroudsburg, PA, USA
Event location
Online
Event date
Nov 19, 2020
Type of event by nationality
WRD - Celosvětová akce
UT code for WoS article
—