Backtranslation in Neural Morphological Inflection
The result's identifiers
Result code in IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216208%3A11320%2F21%3A10442314" target="_blank" >RIV/00216208:11320/21:10442314 - isvavai.cz</a>
Result on the web
—
DOI - Digital Object Identifier
—
Alternative languages
Result language
angličtina
Original language name
Backtranslation in Neural Morphological Inflection
Original language description
Backtranslation is a common technique for leveraging unlabeled data in low-resource scenarios in machine translation. The method is directly applicable to morphological inflection generation if unlabeled word forms are available. This paper evaluates the potential of backtranslation for morphological inflection using data from six languages with labeled data drawn from the SIGMORPHON shared task resource and unlabeled data from different sources. Our core finding is that backtranslation can offer modest improvements in low-resource scenarios, but only if the unlabeled data is very clean and has been filtered by the same annotation standards as the labeled data.
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
—
Others
Publication year
2021
Confidentiality
S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů
Data specific for result type
Article name in the collection
Proceedings of the Second Workshop on Insights from Negative Results in NLP
ISBN
978-1-954085-93-0
ISSN
—
e-ISSN
—
Number of pages
8
Pages from-to
81-88
Publisher name
Association for Computational Linguistics
Place of publication
Stroudsburg
Event location
Punta Cana
Event date
Nov 10, 2021
Type of event by nationality
WRD - Celosvětová akce
UT code for WoS article
—