A Falta de Pan, Buenas Son Tortas: The Efficacy of Predicted UPOS Tags for Low Resource UD Parsing

Mark Anderson, Mathieu Dehouck, Carlos Gómez-Rodríguez


Abstract
We evaluate the efficacy of predicted UPOS tags as input features for dependency parsers in lower resource settings to evaluate how treebank size affects the impact tagging accuracy has on parsing performance. We do this for real low resource universal dependency treebanks, artificially low resource data with varying treebank sizes, and for very small treebanks with varying amounts of augmented data. We find that predicted UPOS tags are somewhat helpful for low resource treebanks, especially when fewer fully-annotated trees are available. We also find that this positive impact diminishes as the amount of data increases.
Anthology ID:
2021.iwpt-1.8
Volume:
Proceedings of the 17th International Conference on Parsing Technologies and the IWPT 2021 Shared Task on Parsing into Enhanced Universal Dependencies (IWPT 2021)
Month:
August
Year:
2021
Address:
Online
Editors:
Stephan Oepen, Kenji Sagae, Reut Tsarfaty, Gosse Bouma, Djamé Seddah, Daniel Zeman
Venue:
IWPT
SIG:
SIGPARSE
Publisher:
Association for Computational Linguistics
Note:
Pages:
78–83
Language:
URL:
https://aclanthology.org/2021.iwpt-1.8
DOI:
10.18653/v1/2021.iwpt-1.8
Bibkey:
Cite (ACL):
Mark Anderson, Mathieu Dehouck, and Carlos Gómez-Rodríguez. 2021. A Falta de Pan, Buenas Son Tortas: The Efficacy of Predicted UPOS Tags for Low Resource UD Parsing. In Proceedings of the 17th International Conference on Parsing Technologies and the IWPT 2021 Shared Task on Parsing into Enhanced Universal Dependencies (IWPT 2021), pages 78–83, Online. Association for Computational Linguistics.
Cite (Informal):
A Falta de Pan, Buenas Son Tortas: The Efficacy of Predicted UPOS Tags for Low Resource UD Parsing (Anderson et al., IWPT 2021)
Copy Citation:
PDF:
https://aclanthology.org/2021.iwpt-1.8.pdf