@inproceedings{wang-etal-2020-ji-yu,
    title = "基于强负采样的词嵌入优化算法(Word Embedding Optimization Based on Hard Negative Sampling)",
    author = "Wang, Yuchen  and
      Lin, Miaozhe  and
      Zhan, Jiefan",
    editor = "Sun, Maosong  and
      Li, Sujian  and
      Zhang, Yue  and
      Liu, Yang",
    booktitle = "Proceedings of the 19th Chinese National Conference on Computational Linguistics",
    month = oct,
    year = "2020",
    address = "Haikou, China",
    publisher = "Chinese Information Processing Society of China",
    url = "https://preview.aclanthology.org/add-emnlp-2024-awards/2020.ccl-1.20/",
    pages = "207--214",
    language = "zho",
    abstract = "word2vec是自然语言处理领域重要的词嵌入算法之一,为了解决随机负采样作为优化目标可能出现的样本贡献消失问题,提出了可以应用在CBOW和Skip-gram框架上的以余弦距离为度量的强负采样方法:HNS-CBOW和HNS-SG。将原随机负采样过程拆解为两个步骤,首先,计算随机负样本与目标词的余弦距离,然后,再使用距离较近的强负样本更新参数。以英文维基百科数据作为实验语料,在公开的语义-语法数据集上对优化算法的效果进行了定量分析,实验表明,优化后的词嵌入质量显著优于原方法。同时,与GloVe等公开发布的预训练词向量相比,可以在更小的语料库上获得更高的准确性。"
}