@inproceedings{lam-yang-2025-revisiting,
    title = "Revisiting Pre-trained Language Models for Conversation Disentanglement",
    author = "Lam, Tung-Thien  and
      Yang, Cheng-Zen",
    editor = "Chang, Kai-Wei  and
      Lu, Ke-Han  and
      Yang, Chih-Kai  and
      Tam, Zhi-Rui  and
      Chang, Wen-Yu  and
      Wang, Chung-Che",
    booktitle = "Proceedings of the 37th Conference on Computational Linguistics and Speech Processing (ROCLING 2025)",
    month = nov,
    year = "2025",
    address = "National Taiwan University, Taipei City, Taiwan",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/dashboard/2025.rocling-main.31/",
    pages = "296--302",
    ISBN = "979-8-89176-379-1",
    abstract = "Multi-party conversation is a popular form in online group chatting. However, the interweaving of utterance threads complicates the understanding of the dialogues for participants. Many conversation disentanglement models have been proposed using transformer-based pre-trained language models (PrLMs). However, advanced transformer-based PrLMs have not been extensively studied. This paper investigates the effectiveness of five advanced PrLMs: BERT, XLNet, ELECTRA, RoBERTa, and ModernBERT. The experimental results show that ELECTRA and RoBERTa are two PrLMs with outstanding performance than other PrLMs for the conversation disentanglement task."
}