Comparing learnability of two dependency schemes: ‘semantic’ (UD) and ‘syntactic’ (SUD)

Ryszard Tuora, Adam Przepiórkowski, Aleksander Leczkowski


Abstract
This paper contributes to the thread of research on the learnability of different dependency annotation schemes: one (‘semantic’) favouring content words as heads of dependency relations and the other (‘syntactic’) favouring syntactic heads. Several studies have lent support to the idea that choosing syntactic criteria for assigning heads in dependency trees improves the performance of dependency parsers. This may be explained by postulating that syntactic approaches are generally more learnable. In this study, we test this hypothesis by comparing the performance of five parsing systems (both transition- and graph-based) on a selection of 21 treebanks, each in a ‘semantic’ variant, represented by standard UD (Universal Dependencies), and a ‘syntactic’ variant, represented by SUD (Surface-syntactic Universal Dependencies): unlike previously reported experiments, which considered learnability of ‘semantic’ and ‘syntactic’ annotations of particular constructions in vitro, the experiments reported here consider whole annotation schemes in vivo. Additionally, we compare these annotation schemes using a range of quantitative syntactic properties, which may also reflect their learnability. The results of the experiments show that SUD tends to be more learnable than UD, but the advantage of one or the other scheme depends on the parser and the corpus in question.
Anthology ID:
2021.findings-emnlp.256
Volume:
Findings of the Association for Computational Linguistics: EMNLP 2021
Month:
November
Year:
2021
Address:
Punta Cana, Dominican Republic
Editors:
Marie-Francine Moens, Xuanjing Huang, Lucia Specia, Scott Wen-tau Yih
Venue:
Findings
SIG:
SIGDAT
Publisher:
Association for Computational Linguistics
Note:
Pages:
2987–2996
Language:
URL:
https://aclanthology.org/2021.findings-emnlp.256
DOI:
10.18653/v1/2021.findings-emnlp.256
Bibkey:
Cite (ACL):
Ryszard Tuora, Adam Przepiórkowski, and Aleksander Leczkowski. 2021. Comparing learnability of two dependency schemes: ‘semantic’ (UD) and ‘syntactic’ (SUD). In Findings of the Association for Computational Linguistics: EMNLP 2021, pages 2987–2996, Punta Cana, Dominican Republic. Association for Computational Linguistics.
Cite (Informal):
Comparing learnability of two dependency schemes: ‘semantic’ (UD) and ‘syntactic’ (SUD) (Tuora et al., Findings 2021)
Copy Citation:
PDF:
https://aclanthology.org/2021.findings-emnlp.256.pdf
Video:
 https://aclanthology.org/2021.findings-emnlp.256.mp4
Data
Universal Dependencies