@inproceedings{li-etal-2022-ji-yu,
    title = "基于平行交互注意力网络的中文电子病历实体及关系联合抽取(Parallel Interactive Attention Network for Joint Entity and Relation Extraction Based on {C}hinese Electronic Medical Record)",
    author = "Li, LiShuang  and
      Wang, Zehao  and
      Qin, Xueyang  and
      Guanghui, Yuan",
    booktitle = "Proceedings of the 21st Chinese National Conference on Computational Linguistics",
    month = oct,
    year = "2022",
    address = "Nanchang, China",
    publisher = "Chinese Information Processing Society of China",
    url = "https://aclanthology.org/2022.ccl-1.21",
    pages = "222--233",
    abstract = "{``}基于电子病历构建医学知识图谱对医疗技术的发展具有重要意义,实体和关系抽取是构建知识图谱的关键技术。本文针对目前实体关系联合抽取中存在的特征交互不充分的问题,提出了一种平行交互注意力网络(PIAN)以充分挖掘实体与关系的相关性,在多个标准的医学和通用数据集上取得最优结果;当前中文医学实体及关系标注数据集较少,本文基于中文电子病历构建了实体和关系抽取数据集(CEMRIE),与医学专家共同制定了语料标注规范,并基于所提出的模型实验得出基准结果。{''}",
    language = "Chinese",
}