@inproceedings{cairang-etal-2024-rong,
    title = "融合多元特征表示的藏文命名实体识别方法赵小兵{\ensuremath{*}}2(Research on {T}ibetan Named Entity Recognition Using Multi-Feature Fusion Representation)",
    author = "Cairang, Ejian  and
      Maoke, Zhou  and
      Bo, Chen  and
      Xiaobing, Zhao",
    editor = "Sun, Maosong  and
      Liang, Jiye  and
      Han, Xianpei  and
      Liu, Zhiyuan  and
      He, Yulan",
    booktitle = "Proceedings of the 23rd Chinese National Conference on Computational Linguistics (Volume 1: Main Conference)",
    month = jul,
    year = "2024",
    address = "Taiyuan, China",
    publisher = "Chinese Information Processing Society of China",
    url = "https://preview.aclanthology.org/Ingest-2025-COMPUTEL/2024.ccl-1.26/",
    pages = "340--351",
    language = "zho",
    abstract = "{\textquotedblleft}本文针对基于音节嵌入方式的藏文命名实体识别(TNER)中词汇信息和音节部件信息忽略的问题,提出了基于交叉Transformer架构的MECT-TL模型,融合了藏文音节信息、词汇信息和音节部件信息的多元数据特征。MECT-TL通过平面网络结构将藏文音节与词汇信息结合,并整合音节部件信息,有效提升了藏文实体识别的准确性。实验结果显示,相较于主流的TNER基准模型BiLSTM-CRF,本文模型在F1值上提高了5.14个百分点,与基于Transformer架构的TENER模型相比提高了4.18个百分点。这表明,融合藏文词汇和音节部件信息的方法可以显著提高TNER任务的性能。{\textquotedblright}"
}