@inproceedings{chenyang-etal-2024-ji,
    title = "基于参数高效微调与半监督学习的空间语义理解",
    author = "Chenyang, Li  and
      Long, Zhang  and
      Qiusheng, Zheng",
    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-3.10/",
    pages = "87--94",
    language = "zho",
    abstract = "``本文介绍了我们在第二十三届中文计算语言大会的第四届中文空间语义理解评测任务中提交的参赛模型。该任务旨在测试机器的中文语义理解水平。现有研究显示,机器的中文语义理解水平与人类平均水平相比仍有较大差距。近年来,生成式大规模语言模型在自然语言处理任务中展现了出色的生成和泛化能力。在本次评测中,我们采用了对Qwen1.5-7b模型进行高效微调的方法,以端到端的形式实现空间语义的推理过程,并结合prompt优化和半监督学习提升推理表现。实验结果表明,我们的模型在该任务中取得了领先的效果。''"
}