@inproceedings{fu-etal-2025-topicality,
title = "A Topicality-Driven {QUD} Model for Discourse Processing",
author = "Fu, Yingxue and
Nederhof, Mark-Jan and
Ollagnier, Anais",
editor = "B{\'e}chet, Fr{\'e}d{\'e}ric and
Lef{\`e}vre, Fabrice and
Asher, Nicholas and
Kim, Seokhwan and
Merlin, Teva",
booktitle = "Proceedings of the 26th Annual Meeting of the Special Interest Group on Discourse and Dialogue",
month = aug,
year = "2025",
address = "Avignon, France",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.sigdial-1.17/",
pages = "214--230",
abstract = "Question Under Discussion (QUD) is a discourse framework that has attracted growing interest in NLP in recent years. Among existing QUD models, the QUD tree approach (Riester, 2019) focuses on reconstructing QUDs and their hierarchical relationships, using a single tree to represent discourse structure. Prior implementation shows moderate inter-annotator agreement, highlighting the challenging nature of this task. In this paper, we propose a new QUD model for annotating hierarchical discourse structure. Our annotation achieves high inter-annotator agreement: 81.45{\%} for short files and 79.53{\%} for long files of Wall Street Journal articles. We show preliminary results on using GPT-4 for automatic annotation, which suggests that one of the best-performing LLMs still struggles with capturing hierarchical discourse structure. Moreover, we compare the annotations with RST annotations. Lastly, we present an approach for integrating hierarchical and local discourse relation annotations with the proposed model."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="fu-etal-2025-topicality">
<titleInfo>
<title>A Topicality-Driven QUD Model for Discourse Processing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yingxue</namePart>
<namePart type="family">Fu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mark-Jan</namePart>
<namePart type="family">Nederhof</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anais</namePart>
<namePart type="family">Ollagnier</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-08</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 26th Annual Meeting of the Special Interest Group on Discourse and Dialogue</title>
</titleInfo>
<name type="personal">
<namePart type="given">Frédéric</namePart>
<namePart type="family">Béchet</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Fabrice</namePart>
<namePart type="family">Lefèvre</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nicholas</namePart>
<namePart type="family">Asher</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Seokhwan</namePart>
<namePart type="family">Kim</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Teva</namePart>
<namePart type="family">Merlin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Avignon, France</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Question Under Discussion (QUD) is a discourse framework that has attracted growing interest in NLP in recent years. Among existing QUD models, the QUD tree approach (Riester, 2019) focuses on reconstructing QUDs and their hierarchical relationships, using a single tree to represent discourse structure. Prior implementation shows moderate inter-annotator agreement, highlighting the challenging nature of this task. In this paper, we propose a new QUD model for annotating hierarchical discourse structure. Our annotation achieves high inter-annotator agreement: 81.45% for short files and 79.53% for long files of Wall Street Journal articles. We show preliminary results on using GPT-4 for automatic annotation, which suggests that one of the best-performing LLMs still struggles with capturing hierarchical discourse structure. Moreover, we compare the annotations with RST annotations. Lastly, we present an approach for integrating hierarchical and local discourse relation annotations with the proposed model.</abstract>
<identifier type="citekey">fu-etal-2025-topicality</identifier>
<location>
<url>https://aclanthology.org/2025.sigdial-1.17/</url>
</location>
<part>
<date>2025-08</date>
<extent unit="page">
<start>214</start>
<end>230</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T A Topicality-Driven QUD Model for Discourse Processing
%A Fu, Yingxue
%A Nederhof, Mark-Jan
%A Ollagnier, Anais
%Y Béchet, Frédéric
%Y Lefèvre, Fabrice
%Y Asher, Nicholas
%Y Kim, Seokhwan
%Y Merlin, Teva
%S Proceedings of the 26th Annual Meeting of the Special Interest Group on Discourse and Dialogue
%D 2025
%8 August
%I Association for Computational Linguistics
%C Avignon, France
%F fu-etal-2025-topicality
%X Question Under Discussion (QUD) is a discourse framework that has attracted growing interest in NLP in recent years. Among existing QUD models, the QUD tree approach (Riester, 2019) focuses on reconstructing QUDs and their hierarchical relationships, using a single tree to represent discourse structure. Prior implementation shows moderate inter-annotator agreement, highlighting the challenging nature of this task. In this paper, we propose a new QUD model for annotating hierarchical discourse structure. Our annotation achieves high inter-annotator agreement: 81.45% for short files and 79.53% for long files of Wall Street Journal articles. We show preliminary results on using GPT-4 for automatic annotation, which suggests that one of the best-performing LLMs still struggles with capturing hierarchical discourse structure. Moreover, we compare the annotations with RST annotations. Lastly, we present an approach for integrating hierarchical and local discourse relation annotations with the proposed model.
%U https://aclanthology.org/2025.sigdial-1.17/
%P 214-230
Markdown (Informal)
[A Topicality-Driven QUD Model for Discourse Processing](https://aclanthology.org/2025.sigdial-1.17/) (Fu et al., SIGDIAL 2025)
ACL
- Yingxue Fu, Mark-Jan Nederhof, and Anais Ollagnier. 2025. A Topicality-Driven QUD Model for Discourse Processing. In Proceedings of the 26th Annual Meeting of the Special Interest Group on Discourse and Dialogue, pages 214–230, Avignon, France. Association for Computational Linguistics.