@inproceedings{yang-etal-2024-jie,
    title = "结合{LLM}与3{D}动画技术的手语数字人系统",
    author = "Yang, Yang  and
      Ying, Zhang  and
      Kaiyu, Huang  and
      Jinan, Xu",
    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-3.44/",
    pages = "393--404",
    language = "zho",
    abstract = "``手语翻译(Sign Language Translation, SLT)系统作为一种重要的辅助技术,为听障人士提供了与他人沟通的有效途径。然而,传统手语翻译系统在准确性、流畅性差等方面存在问题。本文提出了一种结合大语言模型(Large Language Model, LLM)和3D动画技术(3D Animation Technology)的手语翻译系统,旨在克服这些局限,提高翻译的准确性和流畅性。本文详细介绍了系统的设计与实现过程,包括提示词设计、数据处理方法以及手语数字人翻译系统的实现。实验结果表明,采用LLM方法在手语翻译中能够生成较为自然和准确的结果。在标准评估和人工评估的两种评估方法下,本系统在大多数情况下能够较好地完成手语翻译任务,性能优于传统方法。本文的研究为进一步改进手语翻译系统提供了有益的参考和启示。''"
}