On the Frailty of Universal POS Tags for Neural UD Parsers

Mark Anderson, Carlos Gómez-Rodríguez


Abstract
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.
Anthology ID:
2020.conll-1.6
Volume:
Proceedings of the 24th Conference on Computational Natural Language Learning
Month:
November
Year:
2020
Address:
Online
Editors:
Raquel Fernández, Tal Linzen
Venue:
CoNLL
SIG:
SIGNLL
Publisher:
Association for Computational Linguistics
Note:
Pages:
69–96
Language:
URL:
https://aclanthology.org/2020.conll-1.6
DOI:
10.18653/v1/2020.conll-1.6
Bibkey:
Cite (ACL):
Mark Anderson and Carlos Gómez-Rodríguez. 2020. On the Frailty of Universal POS Tags for Neural UD Parsers. In Proceedings of the 24th Conference on Computational Natural Language Learning, pages 69–96, Online. Association for Computational Linguistics.
Cite (Informal):
On the Frailty of Universal POS Tags for Neural UD Parsers (Anderson & Gómez-Rodríguez, CoNLL 2020)
Copy Citation:
PDF:
https://aclanthology.org/2020.conll-1.6.pdf