On the Frailty of Universal POS Tags for Neural UD Parsers
The result's identifiers
Result code in IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216208%3A11320%2F20%3A10426968" target="_blank" >RIV/00216208:11320/20:10426968 - isvavai.cz</a>
Result on the web
<a href="https://www.aclweb.org/anthology/2020.conll-1.6" target="_blank" >https://www.aclweb.org/anthology/2020.conll-1.6</a>
DOI - Digital Object Identifier
—
Alternative languages
Result language
angličtina
Original language name
On the Frailty of Universal POS Tags for Neural UD Parsers
Original language description
We present an analysis on the effect UPOS accuracy has on parsing performance. Results suggest that leveraging UPOS tags as fea-tures for neural parsers requires a prohibitively high tagging accuracy and that the use of gold tags offers a non-linear increase in performance, suggesting some sort of exceptionality. We also investigate what aspects of predicted UPOS tags impact parsing accuracy the most, highlighting some potentially meaningful linguistic facets of the problem.
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
2020
Confidentiality
S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů