New syntactic insights for automated Wolof Universal Dependency parsing

Bill Dyer


Abstract
Focus on language-specific properties with insights from formal minimalist syntax can improve universal dependency (UD) parsing. Such improvements are especially sensitive for low-resource African languages, like Wolof, which have fewer UD treebanks in number and amount of annotations, and fewer contributing annotators. For two different UD parser pipelines, one parser model was trained on the original Wolof treebank, and one was trained on an edited treebank. For each parser pipeline, the accuracy of the edited treebank was higher than the original for both the dependency relations and dependency labels. Accuracy for universal dependency relations improved as much as 2.90%, while accuracy for universal dependency labels increased as much as 3.38%. An annotation scheme that better fits a language’s distinct syntax results in better parsing accuracy.
Anthology ID:
2022.computel-1.2
Volume:
Proceedings of the Fifth Workshop on the Use of Computational Methods in the Study of Endangered Languages
Month:
May
Year:
2022
Address:
Dublin, Ireland
Editors:
Sarah Moeller, Antonios Anastasopoulos, Antti Arppe, Aditi Chaudhary, Atticus Harrigan, Josh Holden, Jordan Lachler, Alexis Palmer, Shruti Rijhwani, Lane Schwartz
Venue:
ComputEL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
5–12
Language:
URL:
https://aclanthology.org/2022.computel-1.2
DOI:
10.18653/v1/2022.computel-1.2
Bibkey:
Cite (ACL):
Bill Dyer. 2022. New syntactic insights for automated Wolof Universal Dependency parsing. In Proceedings of the Fifth Workshop on the Use of Computational Methods in the Study of Endangered Languages, pages 5–12, Dublin, Ireland. Association for Computational Linguistics.
Cite (Informal):
New syntactic insights for automated Wolof Universal Dependency parsing (Dyer, ComputEL 2022)
Copy Citation:
PDF:
https://aclanthology.org/2022.computel-1.2.pdf
Video:
 https://aclanthology.org/2022.computel-1.2.mp4