A systematic comparison of methods for low-resource dependency parsing on genuinely low-resource languages

Result code in IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216208%3A11320%2F19%3A10427101" target="_blank" >RIV/00216208:11320/19:10427101 - isvavai.cz</a>
Result on the web
<a href="https://www.aclweb.org/anthology/D19-1102" target="_blank" >https://www.aclweb.org/anthology/D19-1102</a>
DOI - Digital Object Identifier
—

Result language
angličtina
Original language name
A systematic comparison of methods for low-resource dependency parsing on genuinely low-resource languages
Original language description
Parsers are available for only a handful of the world's languages, since they require lots of training data. How far can we get with just a small amount of training data? We systematically compare a set of simple strategies for improving low-resource parsers: data augmentation, which has not been tested before; cross-lingual training; and transliteration. Experimenting on three typologically diverse low-resource languages—North Sámi, Galician, and Kazah—We find that (1) when only the low-resource treebank is available, data augmentation is very helpful; (2) when a related high-resource treebank is available, cross-lingual training is helpful and complements data augmentation; and (3) when the high-resource treebank uses a different writing system, transliteration into a shared orthographic spaces is also very helpful.
Czech name
—
Czech description
—

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)

Publication year
2019
Confidentiality
S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Similar results(10)