Towards an Implementation of Rhetorical Structure Theory in Discourse Coherence Modelling

Michael Lambropoulos; Shunichi Ishihara

Towards an Implementation of Rhetorical Structure Theory in Discourse Coherence Modelling

School of Culture, History & Language

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

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.

Original language	English
Title of host publication	Proceedings of the 22nd Annual Workshop of the Australasian Language Technology Association
Editors	Tim Baldwin, Sergio José Rodríguez Méndez, Nicholas Kuo
Place of Publication	Canberra, Australia
Publisher	Association for Computational Linguistics
Pages	1-11
Number of pages	11
Publication status	Published - 1 Dec 2024

Access to Document

https://aclanthology.org/2024.alta-1.1/

Cite this

Lambropoulos, M., & Ishihara, S. (2024). Towards an Implementation of Rhetorical Structure Theory in Discourse Coherence Modelling. In T. Baldwin, S. J. Rodríguez Méndez, & N. Kuo (Eds.), Proceedings of the 22nd Annual Workshop of the Australasian Language Technology Association (pp. 1-11). Association for Computational Linguistics. https://aclanthology.org/2024.alta-1.1/

Lambropoulos, Michael ; Ishihara, Shunichi. / Towards an Implementation of Rhetorical Structure Theory in Discourse Coherence Modelling. Proceedings of the 22nd Annual Workshop of the Australasian Language Technology Association. editor / Tim Baldwin ; Sergio José Rodríguez Méndez ; Nicholas Kuo. Canberra, Australia : Association for Computational Linguistics, 2024. pp. 1-11

@inproceedings{7157d7aeb92c45739d75545df4b6c19a,

title = "Towards an Implementation of Rhetorical Structure Theory in Discourse Coherence Modelling",

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.",

author = "Michael Lambropoulos and Shunichi Ishihara",

year = "2024",

month = dec,

day = "1",

language = "English",

pages = "1--11",

editor = "Tim Baldwin and {Rodr{\'i}guez M{\'e}ndez}, {Sergio Jos{\'e}} and Nicholas Kuo",

booktitle = "Proceedings of the 22nd Annual Workshop of the Australasian Language Technology Association",

publisher = "Association for Computational Linguistics",

}

Lambropoulos, M & Ishihara, S 2024, Towards an Implementation of Rhetorical Structure Theory in Discourse Coherence Modelling. in T Baldwin, SJ Rodríguez Méndez & N Kuo (eds), Proceedings of the 22nd Annual Workshop of the Australasian Language Technology Association. Association for Computational Linguistics, Canberra, Australia, pp. 1-11. <https://aclanthology.org/2024.alta-1.1/>

Towards an Implementation of Rhetorical Structure Theory in Discourse Coherence Modelling. / Lambropoulos, Michael ; Ishihara, Shunichi.
Proceedings of the 22nd Annual Workshop of the Australasian Language Technology Association. ed. / Tim Baldwin; Sergio José Rodríguez Méndez; Nicholas Kuo. Canberra, Australia: Association for Computational Linguistics, 2024. p. 1-11.

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Towards an Implementation of Rhetorical Structure Theory in Discourse Coherence Modelling

AU - Lambropoulos, Michael

AU - Ishihara, Shunichi

PY - 2024/12/1

Y1 - 2024/12/1

N2 - 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.

AB - 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.

M3 - Conference contribution

SP - 1

EP - 11

BT - Proceedings of the 22nd Annual Workshop of the Australasian Language Technology Association

A2 - Baldwin, Tim

A2 - Rodríguez Méndez, Sergio José

A2 - Kuo, Nicholas

PB - Association for Computational Linguistics

CY - Canberra, Australia

ER -

Towards an Implementation of Rhetorical Structure Theory in Discourse Coherence Modelling

Abstract

Access to Document

Fingerprint

Cite this