@inproceedings{inadumi-etal-2025-disambiguating, title = "Disambiguating Reference in Visually Grounded Dialogues through Joint Modeling of Textual and Multimodal Semantic Structures", author = "Inadumi, Shun and Ueda, Nobuhiro and Yoshino, Koichiro", editor = "Che, Wanxiang and Nabende, Joyce and Shutova, Ekaterina and Pilehvar, Mohammad Taher", booktitle = "Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)", month = jul, year = "2025", address = "Vienna, Austria", publisher = "Association for Computational Linguistics", url = "https://preview.aclanthology.org/ingestion-acl-25/2025.acl-long.547/", pages = "11183--11198", ISBN = "979-8-89176-251-0" }