@inproceedings{yang-etal-2024-polclip,
    title = "{P}ol{CLIP}: A Unified Image-Text Word Sense Disambiguation Model via Generating Multimodal Complementary Representations",
    author = "Yang, Qihao  and
      Li, Yong  and
      Wang, Xuelin  and
      Wang, Fu Lee  and
      Hao, Tianyong",
    editor = "Ku, Lun-Wei  and
      Martins, Andre  and
      Srikumar, Vivek",
    booktitle = "Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)",
    month = aug,
    year = "2024",
    address = "Bangkok, Thailand",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/jlcl-multiple-ingestion/2024.acl-long.575/",
    doi = "10.18653/v1/2024.acl-long.575",
    pages = "10676--10690"
}