@inproceedings{yang-etal-2023-ccl23,
    title = "{CCL}23-Eval 任务2系统报告：基于大型语言模型的中文抽象语义表示解析(System Report for {CCL}23-Eval Task 2: Chinese Abstract Meaning Representation Parsing based on Large Language Models)",
    author = "Yang, Yifei  and
      Cheng, Ziming  and
      Zhao, Hai",
    editor = "Sun, Maosong  and
      Qin, Bing  and
      Qiu, Xipeng  and
      Jiang, Jing  and
      Han, Xianpei",
    booktitle = "Proceedings of the 22nd Chinese National Conference on Computational Linguistics (Volume 3: Evaluations)",
    month = aug,
    year = "2023",
    address = "Harbin, China",
    publisher = "Chinese Information Processing Society of China",
    url = "https://preview.aclanthology.org/more-markup/2023.ccl-3.5/",
    pages = "41--52",
    language = "zho",
    abstract = "中文抽象语义表示解析旨在将自然语句转换为抽象语义表示，是一个复杂的结构化预测任务。传统方法多利用抽象语义表示的图特征设计特殊模型或者多阶段解析来完成解析，而这类方法通常需要设计复杂的神经网络模型。目前，通用大型语言模型在已经多种自然语言处理任务上表现出惊人效果，我们在本次测评中尝试直接利用大型语言模型进行零样本学习、少样本学习以及用LoRA和全参数的方式微调大型语言模型来完成解析。我们得到了一个较好的评测结果，并对这些方案进行了讨论。"
}