Corpus ID: 59336292

Glyce: Glyph-vectors for Chinese Character Representations

@article{Wu2019GlyceGF,
  title={Glyce: Glyph-vectors for Chinese Character Representations},
  author={Wei Wu and Yuxian Meng and Qinghong Han and Muyu Li and Xiaoya Li and Jie Mei and Ping Nie and Xiaofei Sun and Jiwei Li},
  journal={ArXiv},
  year={2019},
  volume={abs/1901.10125}
}
  • Wei Wu, Yuxian Meng, +6 authors Jiwei Li
  • Published 2019
  • Computer Science
  • ArXiv
  • It is intuitive that NLP tasks for logographic languages like Chinese should benefit from the use of the glyph information in those languages. [...] Key Method We make three major innovations: (1) We use historical Chinese scripts (e.g., bronzeware script, seal script, traditional Chinese, etc) to enrich the pictographic evidence in characters; (2) We design CNN structures (called tianzege-CNN) tailored to Chinese character image processing; and (3) We use image-classification as an auxiliary task in a multi…Expand Abstract

    Citations

    Publications citing this paper.
    SHOWING 1-10 OF 15 CITATIONS

    Using Chinese Glyphs for Named Entity Recognition

    VIEW 9 EXCERPTS
    CITES BACKGROUND, METHODS & RESULTS
    HIGHLY INFLUENCED

    Lattice LSTM for Chinese Sentence Representation

    • Yue Zhang, Yile Wang, Jie Yang
    • Computer Science
    • IEEE/ACM Transactions on Audio, Speech, and Language Processing
    • 2020

    Probing Contextualized Sentence Representations with Visual Awareness

    VIEW 1 EXCERPT
    CITES BACKGROUND

    Sentence-Level Semantic Features Guided Adversarial Network for Zhuang Language Part-of-Speech Tagging

    References

    Publications referenced by this paper.
    SHOWING 1-10 OF 85 REFERENCES

    Glyph-aware Embedding of Chinese Characters

    VIEW 2 EXCERPTS
    HIGHLY INFLUENTIAL

    Multi-Granularity Chinese Word Embedding

    VIEW 5 EXCERPTS
    HIGHLY INFLUENTIAL

    Subword Encoding in Lattice LSTM for Chinese Word Segmentation

    VIEW 11 EXCERPTS
    HIGHLY INFLUENTIAL