@inproceedings{bai-etal-2023-wukong,
    title = "Wukong-Reader: Multi-modal Pre-training for Fine-grained Visual Document Understanding",
    author = "Bai, Haoli  and
      Liu, Zhiguang  and
      Meng, Xiaojun  and
      Wentao, Li  and
      Liu, Shuang  and
      Luo, Yifeng  and
      Xie, Nian  and
      Zheng, Rongfu  and
      Wang, Liangwei  and
      Hou, Lu  and
      Wei, Jiansheng  and
      Jiang, Xin  and
      Liu, Qun",
    editor = "Rogers, Anna  and
      Boyd-Graber, Jordan  and
      Okazaki, Naoaki",
    booktitle = "Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)",
    month = jul,
    year = "2023",
    address = "Toronto, Canada",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/jlcl-multiple-ingestion/2023.acl-long.748/",
    doi = "10.18653/v1/2023.acl-long.748",
    pages = "13386--13401"
}