Easy-First Bottom-Up Discourse Parsing via Sequence Labelling

Andrew Shen, Fajri Koto, Jey Han Lau, Timothy Baldwin


Abstract
We propose a novel unconstrained bottom-up approach for rhetorical discourse parsing based on sequence labelling of adjacent pairs of discourse units (DUs), based on the framework of Koto et al. (2021). We describe the unique training requirements of an unconstrained parser, and explore two different training procedures: (1) fixed left-to-right; and (2) random order in tree construction. Additionally, we introduce a novel dynamic oracle for unconstrained bottom-up parsing. Our proposed parser achieves competitive results for bottom-up rhetorical discourse parsing.
Anthology ID:
2022.codi-1.5
Volume:
Proceedings of the 3rd Workshop on Computational Approaches to Discourse
Month:
October
Year:
2022
Address:
Gyeongju, Republic of Korea and Online
Venue:
CODI
SIG:
Publisher:
International Conference on Computational Linguistics
Note:
Pages:
35–41
Language:
URL:
https://aclanthology.org/2022.codi-1.5
DOI:
Bibkey:
Cite (ACL):
Andrew Shen, Fajri Koto, Jey Han Lau, and Timothy Baldwin. 2022. Easy-First Bottom-Up Discourse Parsing via Sequence Labelling. In Proceedings of the 3rd Workshop on Computational Approaches to Discourse, pages 35–41, Gyeongju, Republic of Korea and Online. International Conference on Computational Linguistics.
Cite (Informal):
Easy-First Bottom-Up Discourse Parsing via Sequence Labelling (Shen et al., CODI 2022)
Copy Citation:
PDF:
https://preview.aclanthology.org/ingestion-script-update/2022.codi-1.5.pdf