Syntactic Nuclei in Dependency Parsing – A Multilingual Exploration

Ali Basirat, Joakim Nivre


Abstract
Standard models for syntactic dependency parsing take words to be the elementary units that enter into dependency relations. In this paper, we investigate whether there are any benefits from enriching these models with the more abstract notion of nucleus proposed by Tesnière. We do this by showing how the concept of nucleus can be defined in the framework of Universal Dependencies and how we can use composition functions to make a transition-based dependency parser aware of this concept. Experiments on 12 languages show that nucleus composition gives small but significant improvements in parsing accuracy. Further analysis reveals that the improvement mainly concerns a small number of dependency relations, including nominal modifiers, relations of coordination, main predicates, and direct objects.
Anthology ID:
2021.eacl-main.117
Original:
2021.eacl-main.117v1
Version 2:
2021.eacl-main.117v2
Version 3:
2021.eacl-main.117v3
Volume:
Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume
Month:
April
Year:
2021
Address:
Online
Editors:
Paola Merlo, Jorg Tiedemann, Reut Tsarfaty
Venue:
EACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
1376–1387
Language:
URL:
https://aclanthology.org/2021.eacl-main.117
DOI:
10.18653/v1/2021.eacl-main.117
Bibkey:
Cite (ACL):
Ali Basirat and Joakim Nivre. 2021. Syntactic Nuclei in Dependency Parsing – A Multilingual Exploration. In Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume, pages 1376–1387, Online. Association for Computational Linguistics.
Cite (Informal):
Syntactic Nuclei in Dependency Parsing – A Multilingual Exploration (Basirat & Nivre, EACL 2021)
Copy Citation:
PDF:
https://aclanthology.org/2021.eacl-main.117.pdf
Data
Universal Dependencies