The LMU Munich System for the WMT20 Very Low Resource Supervised MT Task
The result's identifiers
Result code in IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216208%3A11320%2F20%3A10424469" target="_blank" >RIV/00216208:11320/20:10424469 - isvavai.cz</a>
Result on the web
<a href="http://www.statmt.org/wmt20/bib/2020.wmt-1.131.pdf" target="_blank" >http://www.statmt.org/wmt20/bib/2020.wmt-1.131.pdf</a>
DOI - Digital Object Identifier
—
Alternative languages
Result language
angličtina
Original language name
The LMU Munich System for the WMT20 Very Low Resource Supervised MT Task
Original language description
We present our systems for the WMT20 Very Low Resource MT Task for translation between German and Upper Sorbian. For training our systems, we generate synthetic data by both back- and forward-translation. Additionally, we enrich the training data with German-Czech translated from Czech to Upper Sorbian by an unsupervised statistical MT system incorporating orthographically similar word pairs and transliterations of OOV words. Our best translation system between German and Sorbian is based on transfer learning from a Czech-German system and scores 12 to 13 BLEU higher than a baseline system built using the available parallel data only.
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
—
Continuities
I - Institucionalni podpora na dlouhodoby koncepcni rozvoj vyzkumne organizace
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
8
Pages from-to
1102-1109
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
—