@inproceedings{zhang-etal-2025-document,
    title = "Document-Level Relation Extraction with Global Relations and Entity Pair Reasoning",
    author = "Zhang, Fu  and
      Yan, Yi  and
      Cheng, Jingwei",
    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/transition-to-people-yaml/2025.findings-acl.1002/",
    doi = "10.18653/v1/2025.findings-acl.1002",
    pages = "19556--19567",
    ISBN = "979-8-89176-256-5",
    abstract = "Document-level relation extraction (DocRE) aims to extract structured relational triples from unstructured text based on given entities. Existing methods are mainly categorized into transformer-based models and graph-based models. While transformer-based models capture global contextual information, they typically focus on individual entity pairs, making it challenging to capture complex interactions between multiple entity pairs. Graph-based models build document graphs using entities or sentences as nodes for reasoning but often lack explicit mechanisms to model fine-grained interactions between entity pairs, limiting their ability to handle complex relational reasoning tasks. Additionally, previous research has not considered predicting all possible relations in advance to assist with DocRE tasks. To address these issues, we propose a new framework namely **GREP** (**g**lobal **r**elations and **e**ntity **p**air reasoning) for DocRE tasks. GREP leverages the global interdependencies between entity pairs to capture fine-grained interactions and perform multi reasoning at the entity pair level. In addtion, GREP for the first time proposes an auxiliary task that predicts all possible relations in advance that exist in a document, which enables the model to filter out the most unlikely relations. Experimental results on widely-used datasets demonstrate that our model achieves state-of-the-art performance. Code is available at https://github.com/yanyi74/GREP."
}