@inproceedings{wenjuan-etal-2024-ji,
    title = "基于隐性句逗号识别的汉语长句机器翻译(Machine translation of {C}hinese long sentences based on recognition of implicit period and comma)",
    author = "Wenjuan, Zhang  and
      Manjia, Li  and
      Wenhe, Feng",
    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/jlcl-multiple-ingestion/2024.ccl-1.14/",
    pages = "197--205",
    language = "zho",
    abstract = "{\textquotedblleft}长句翻译一直是机器翻译的难题。本文根据汉语中相当数量的逗号(句内标点)和句号(句间标点)可相互转化的特点,提出{\textquotedblright}隐性句号{\textquotedblright}(可转化为句号的逗号)和{\textquotedblright}隐性逗号{\textquotedblright}(可转化为逗号的句号)概念,并实现其自动识别,以将汉语长句变为短句用于汉英机器翻译。为此,首先通过人工与半监督学习结合方法构建了一个隐性句逗数据集,实现了基于预训练模型的隐性句逗识别方法,其中性能最好的HierarchicalBERT作为后续应用模型。进而,实现了基于隐性句逗识别的汉英机器翻译方法。在WMT2018(新闻)和WMT2023(文学)测试语料上基于预训练机器翻译模型的实验表明,对于汉语长句的英译,本文方法相比基准翻译的BLEU值整体有所提高,而且在相对稳健机器翻译模型上,呈现为句子越长本文方法效果越明显。{\textquotedblright}"
}