@inproceedings{gu-etal-2023-ccl23,
    title = "{CCL}23-Eval 任务2系统报告:基于图融合的自回归和非自回归中文{AMR}语义分析(System Report for {CCL}23-Eval Task 2: Autoregressive and Non-autoregressive {C}hinese {AMR} Semantic Parsing based on Graph Ensembling)",
    author = "Gu, Yanggan  and
      Zhou, Shilin  and
      Li, Zhenghua",
    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-3.5/",
    pages = "53--63",
    language = "zho",
    abstract = "``本文介绍了我们在第二十二届中国计算语言学大会中文抽象语义表示解析评测中提交的参赛系统。抽象语义表示(Abstract Meaning Representation,AMR)以有向无环图的形式表示一个句子的语义。本次评测任务针对中文抽象语义表示(Chinese AMR,CAMR),参赛系统不仅需要对常规的AMR图解析预测,还需要预测CAMR数据特有的概念节点对齐、虚词关系对齐、概念同指。我们同时使用多个自回归模型和多个非自回归模型,然后基于图融合的方法将多个模型输出结果融合起来。最终,我们在两个赛道共六个测试集上取得了五项第一名,一项第二名。''"
}