@inproceedings{mengxi-etal-2024-yi,
    title = "意合图:中文多层次语义表示方法{\ensuremath{*}}(Parataxis Graph: Multi-level Semantic Representation Method for {C}hinese)",
    author = "Mengxi, Guo  and
      Endong, Xun  and
      Meng, Li  and
      Gaoqi, Rao",
    editor = "Sun, Maosong  and
      Liang, Jiye  and
      Han, Xianpei  and
      Liu, Zhiyuan  and
      He, Yulan",
    booktitle = "Proceedings of the 23rd Chinese National Conference on Computational Linguistics (Volume 1: Main Conference)",
    month = jul,
    year = "2024",
    address = "Taiyuan, China",
    publisher = "Chinese Information Processing Society of China",
    url = "https://preview.aclanthology.org/Ingest-2025-COMPUTEL/2024.ccl-1.58/",
    pages = "740--749",
    language = "zho",
    abstract = "{\textquotedblleft}基于参数的语义表示虽取得成就,但符号化的语义表示仍具有不可忽视的意义。我们在语义学基础上,充分考虑符号化语义表示在NLP领域落地中的需求,提出了一种兼具通用性与扩展性的多层次语义表示方法{---}{---}意合图。意合图以事件为核心,由事件结构与实体结构构成,通过多层次语义体系设计,提升与场景结合的能力,并力求对不同层级的语言单元作一贯式表示。在资源建设和相关分析实验中取得良好效果。本文将重点介绍意合图设计理念与多层次语义体系。{\textquotedblright}"
}