Syntactic nuclei in dependency parsing - A multilingual exploration
Research output: Chapter in Book/Report/Conference proceeding › Article in proceedings › Research › peer-review
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.
Original language | English |
---|---|
Title of host publication | EACL 2021 - 16th Conference of the European Chapter of the Association for Computational Linguistics, Proceedings of the Conference |
Number of pages | 12 |
Publisher | Association for Computational Linguistics (ACL) |
Publication date | 2021 |
Pages | 1376-1387 |
ISBN (Electronic) | 9781954085022 |
Publication status | Published - 2021 |
Externally published | Yes |
Event | 16th Conference of the European Chapter of the Associationfor Computational Linguistics, EACL 2021 - Virtual, Online Duration: 19 Apr 2021 → 23 Apr 2021 |
Conference
Conference | 16th Conference of the European Chapter of the Associationfor Computational Linguistics, EACL 2021 |
---|---|
By | Virtual, Online |
Periode | 19/04/2021 → 23/04/2021 |
Sponsor | Babelscape, Bloomberg Engineering, Facebook AI, Grammarly, LegalForce |
Series | EACL 2021 - 16th Conference of the European Chapter of the Association for Computational Linguistics, Proceedings of the Conference |
---|
Bibliographical note
Funding Information:
We thank Daniel Dakota, Artur Kulmizev, Sara Stymne and Gongbo Tang for useful discussions and the EACL reviewers for constructive criticism. We acknowledge the computational resources provided by CSC in Helsinki and Sigma2 in Oslo through NeIC-NLPL (www.nlpl.eu).
Publisher Copyright:
© 2021 Association for Computational Linguistics
ID: 366045841