@inproceedings{tseng-hsieh-2019-eigencharacter,
    title = "{E}igencharacter: An Embedding of {C}hinese Character Orthography",
    author = "Tseng, Yu-Hsiang  and
      Hsieh, Shu-Kai",
    editor = "Mogadala, Aditya  and
      Klakow, Dietrich  and
      Pezzelle, Sandro  and
      Moens, Marie-Francine",
    booktitle = "Proceedings of the Beyond Vision and LANguage: inTEgrating Real-world kNowledge (LANTERN)",
    month = nov,
    year = "2019",
    address = "Hong Kong, China",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/fix-sig-urls/D19-6404/",
    doi = "10.18653/v1/D19-6404",
    pages = "24--28",
    abstract = "Chinese characters are unique in its logographic nature, which inherently encodes world knowledge through thousands of years evolution. This paper proposes an embedding approach, namely eigencharacter (EC) space, which helps NLP application easily access the knowledge encoded in Chinese orthography. These EC representations are automatically extracted, encode both structural and radical information, and easily integrate with other computational models. We built EC representations of 5,000 Chinese characters, investigated orthography knowledge encoded in ECs, and demonstrated how these ECs identified visually similar characters with both structural and radical information."
}