@inproceedings{gao-etal-2023-ccl23,
    title = "{CCL}23-Eval 任务2系统报告:{W}estlake{NLP},基于生成式大语言模型的中文抽象语义表示解析(System Report for {CCL}23-Eval Task 2: {W}estlake{NLP}, Investigating Generative Large Language Models for {C}hinese {AMR} Parsing)",
    author = "Gao, Wenyang  and
      Bai, Xuefeng  and
      Zhang, Yue",
    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/fix-sig-urls/2023.ccl-3.6/",
    pages = "64--69",
    language = "zho",
    abstract = "``本文介绍了我们在第二十二届中文计算语言学大会中文抽象语义表示解析评测任务中提交的参赛系统。中文抽象语义表示(Chinese Abstract Meaning Representa-tion,CAMR)不仅以图的方式表示句子的语义,还保证了概念对齐和关系对齐。近期,生成式大规模语言模型在诸多自然语言处理任务上展现了优秀的生成能力和泛化能力。受此启发,我们选择微调Baichuan-7B模型来以端到端的形式从文本直接生成序列化的CAMR。实验结果表明,我们的系统能够在不依赖于词性、依存句法信息以及复杂规则的前提下取得了同现有方法可比的性能。''"
}