Towards an Implementation of Rhetorical Structure Theory in Discourse Coherence Modelling

Michael Lambropoulos, Shunichi Ishihara


Abstract
In this paper, we combine the discourse coherence principles of Elementary Discourse Unit segmentation and Rhetorical Structure Theory parsing to construct meaningful graph-based text representations. We then evaluate a Graph Convolutional Network and a Graph Attention Network on these representations. Our results establish a new benchmark in F1-score assessment for discourse coherence modelling while also showing that Graph Convolutional Network models are generally more computationally efficient and provide superior accuracy.
Anthology ID:
2024.alta-1.1
Volume:
Proceedings of the 22nd Annual Workshop of the Australasian Language Technology Association
Month:
December
Year:
2024
Address:
Canberra, Australia
Editors:
Tim Baldwin, Sergio José Rodríguez Méndez, Nicholas Kuo
Venue:
ALTA
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
1–11
Language:
URL:
https://aclanthology.org/2024.alta-1.1/
DOI:
Bibkey:
Cite (ACL):
Michael Lambropoulos and Shunichi Ishihara. 2024. Towards an Implementation of Rhetorical Structure Theory in Discourse Coherence Modelling. In Proceedings of the 22nd Annual Workshop of the Australasian Language Technology Association, pages 1–11, Canberra, Australia. Association for Computational Linguistics.
Cite (Informal):
Towards an Implementation of Rhetorical Structure Theory in Discourse Coherence Modelling (Lambropoulos & Ishihara, ALTA 2024)
Copy Citation:
PDF:
https://aclanthology.org/2024.alta-1.1.pdf