@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://preview.aclanthology.org/ingest-emnlp/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."
}