@inproceedings{vuong-etal-2025-hicot,
    title = "{H}i{COT}: Improving Neural Topic Models via Optimal Transport and Contrastive Learning",
    author = "Vuong, Hoang Tran  and
      Le, Tue  and
      Vu, Tu  and
      Nguyen, Tung  and
      Van, Linh Ngo  and
      Dinh, Sang  and
      Nguyen, Thien Huu",
    editor = "Che, Wanxiang  and
      Nabende, Joyce  and
      Shutova, Ekaterina  and
      Pilehvar, Mohammad Taher",
    booktitle = "Findings of the Association for Computational Linguistics: ACL 2025",
    month = jul,
    year = "2025",
    address = "Vienna, Austria",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingestion-acl-25/2025.findings-acl.715/",
    pages = "13894--13920",
    ISBN = "979-8-89176-256-5",
    abstract = "Recent advances in neural topic models (NTMs) have improved topic quality but still face challenges: weak document-topic alignment, high inference costs due to large pretrained language models (PLMs), and limited modeling of hierarchical topic structures. To address these issues, we introduce HiCOT (Hierarchical Clustering and Contrastive Learning with Optimal Transport for Neural Topic Modeling), a novel framework that enhances topic coherence and efficiency. HiCOT integrates Optimal Transport to refine document-topic relationships using compact PLM-based embeddings, captures semantic structure of the documents. Additionally, it employs hierarchical clustering combine with contrastive learning to disentangle topic-word and topic-topic relationships, ensuring clearer structure and better coherence. Experimental results on multiple benchmark datasets demonstrate HiCOT{'}s superior effectiveness over existing NTMs in topic coherence, topic performance, representation quality, and computational efficiency."
}