@inproceedings{wei-etal-2025-p2net,
    title = "{P}{\texttwosuperior}{N}et: Parallel Pointer-based Network for Key Information Extraction with Complex Layouts",
    author = "Wei, Kaiwen  and
      Yao, Jie  and
      Zhong, Jiang  and
      Kang, Yangyang  and
      Zhang, Jingyuan  and
      Sun, Changlong  and
      Zhang, Xin  and
      Lv, Fengmao  and
      Jin, Li",
    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.552/",
    pages = "10611--10626",
    ISBN = "979-8-89176-256-5",
    abstract = "Key Information Extraction (KIE) is a challenging multimodal task aimed at extracting structured value entities from visually rich documents. Despite recent advancements, two major challenges remain. First, existing datasets typically feature fixed layouts and a limited set of entity categories, while current methods are based on a full-shot setting that is difficult to apply in real-world scenarios, where new entity categories frequently emerge. Secondly, current methods often treat key entities simply as parts of the OCR-parsed context, neglecting the positive impact of the relationships between key-value entities. To address the first challenge, we introduce a new large-scale, human-annotated dataset, Complex Layout document for Key Information Extraction (CLEX). Comprising 5,860 images with 1,162 entity categories, CLEX is larger and more complex than existing datasets. It also primarily focuses on the zero-shot and few-shot KIE tasks, which are more aligned with real-world applications. To tackle the second challenge, we propose the Parallel Pointer-based Network (P{\texttwosuperior}Net). This model frames KIE as a pointer-based classification task and effectively leverages implicit relationships between key-value entities to enhance extraction. Its parallel extraction mechanism enables simultaneous and efficient extraction of multiple results. Experiments on widely-used datasets, including SROIE, CORD, and the newly introduced CLEX, demonstrate that P{\texttwosuperior}Net outperforms existing state-of-the-art methods (including GPT-4V) while maintaining fast inference speeds."
}