Auxiliary tasks to boost Biaffine Semantic Dependency Parsing

Marie Candito


Abstract
The biaffine parser of (CITATION) was successfully extended to semantic dependency parsing (SDP) (CITATION). Its performance on graphs is surprisingly high given that, without the constraint of producing a tree, all arcs for a given sentence are predicted independently from each other (modulo a shared representation of tokens).To circumvent such an independence of decision, while retaining the O(n2) complexity and highly parallelizable architecture, we propose to use simple auxiliary tasks that introduce some form of interdependence between arcs. Experiments on the three English acyclic datasets of SemEval-2015 task 18 (CITATION), and on French deep syntactic cyclic graphs (CITATION) show modest but systematic performance gains on a near-state-of-the-art baseline using transformer-based contextualized representations. This provides a simple and robust method to boost SDP performance.
Anthology ID:
2022.findings-acl.190
Volume:
Findings of the Association for Computational Linguistics: ACL 2022
Month:
May
Year:
2022
Address:
Dublin, Ireland
Editors:
Smaranda Muresan, Preslav Nakov, Aline Villavicencio
Venue:
Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
2422–2429
Language:
URL:
https://aclanthology.org/2022.findings-acl.190
DOI:
10.18653/v1/2022.findings-acl.190
Bibkey:
Cite (ACL):
Marie Candito. 2022. Auxiliary tasks to boost Biaffine Semantic Dependency Parsing. In Findings of the Association for Computational Linguistics: ACL 2022, pages 2422–2429, Dublin, Ireland. Association for Computational Linguistics.
Cite (Informal):
Auxiliary tasks to boost Biaffine Semantic Dependency Parsing (Candito, Findings 2022)
Copy Citation:
PDF:
https://aclanthology.org/2022.findings-acl.190.pdf
Software:
 2022.findings-acl.190.software.tgz
Code
 mcandito/aux-tasks-biaffine-graph-parser-findingsacl22