@inproceedings{yu-etal-2017-joint,
    title = "Joint Embeddings of {C}hinese Words, Characters, and Fine-grained Subcharacter Components",
    author = "Yu, Jinxing  and
      Jian, Xun  and
      Xin, Hao  and
      Song, Yangqiu",
    editor = "Palmer, Martha  and
      Hwa, Rebecca  and
      Riedel, Sebastian",
    booktitle = "Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing",
    month = sep,
    year = "2017",
    address = "Copenhagen, Denmark",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/jlcl-multiple-ingestion/D17-1027/",
    doi = "10.18653/v1/D17-1027",
    pages = "286--291",
    abstract = "Word embeddings have attracted much attention recently. Different from alphabetic writing systems, Chinese characters are often composed of subcharacter components which are also semantically informative. In this work, we propose an approach to jointly embed Chinese words as well as their characters and fine-grained subcharacter components. We use three likelihoods to evaluate whether the context words, characters, and components can predict the current target word, and collected 13,253 subcharacter components to demonstrate the existing approaches of decomposing Chinese characters are not enough. Evaluation on both word similarity and word analogy tasks demonstrates the superior performance of our model."
}