@inproceedings{hongying-etal-2024-ji,
    title = "基于关系抽取的中文意合图语义解析方法研究",
    author = "Hongying, Huo  and
      Shaoping, Huang  and
      Pengyuan, Liu",
    editor = "Lin, Hongfei  and
      Tan, Hongye  and
      Li, Bin",
    booktitle = "Proceedings of the 23rd Chinese National Conference on Computational Linguistics (Volume 3: Evaluations)",
    month = jul,
    year = "2024",
    address = "Taiyuan, China",
    publisher = "Chinese Information Processing Society of China",
    url = "https://preview.aclanthology.org/fix-sig-urls/2024.ccl-3.7/",
    pages = "62--71",
    language = "zho",
    abstract = "``意合图是以事件为中心的单根有向语义表征图,在语义计算与应用方面具有重要价值。在乃乃乌中串丰串临中文意合图语义解析评测任务中,为克服意合图为单根有向图、意合图包含隐性事件词以及意合图的语义关系类型十分丰富,导致关系类型过多等诸多方面的难点,本文提出一种将该任务转换为关系抽取的方法。该方法首先对标签进行扩充,分为正向标签和反向标签;其次,对输入进行扩充,将隐性事件词添加到输入中,无须额外对隐性事词进行预测;最后,细分为不带隐性事件词和带隐性事件词的关系抽取任务。实验结果表明,本文方法在官方盲测集上的F1值为64.44{\%},高出基线模型33.41{\%},证明了本文方法的有效性。''"
}