Corpus ID: 19168290

cw2vec: Learning Chinese Word Embeddings with Stroke n-gram Information

@inproceedings{Cao2018cw2vecLC,
  title={cw2vec: Learning Chinese Word Embeddings with Stroke n-gram Information},
  author={Shaosheng Cao and Wei Lu and Jun Zhou and Xiaolong Li},
  booktitle={AAAI},
  year={2018}
}
  • Shaosheng Cao, Wei Lu, +1 author Xiaolong Li
  • Published in AAAI 2018
  • Computer Science
  • Highlight Information
    We propose cw2vec, a novel method for learning Chinese word embeddings. [...] Key Result Empirical results on the word similarity, word analogy, text classification and named entity recognition tasks show that the proposed approach consistently outperforms state-of-the-art approaches such as word-based word2vec and GloVe, character-based CWE, component-based JWE and pixel-based GWE.Expand Abstract

    Create an AI-powered research feed to stay up to date with new papers like this posted to ArXiv

    Citations

    Publications citing this paper.
    SHOWING 1-10 OF 31 CITATIONS

    Enhanced Double-Carrier Word Embedding via Phonetics and Writing

    VIEW 4 EXCERPTS
    CITES BACKGROUND & METHODS
    HIGHLY INFLUENCED

    Chinese Embedding via Stroke and Glyph Information: A Dual-channel View

    VIEW 7 EXCERPTS
    CITES METHODS & BACKGROUND
    HIGHLY INFLUENCED

    Joint Fine-Grained Components Continuously Enhance Chinese Word Embeddings

    VIEW 4 EXCERPTS
    CITES METHODS & BACKGROUND
    HIGHLY INFLUENCED

    Learning Chinese Word Embeddings from Stroke, Structure and Pinyin of Characters

    VIEW 10 EXCERPTS
    CITES METHODS, RESULTS & BACKGROUND
    HIGHLY INFLUENCED

    SAC-Net: Stroke-Aware Copy Network for Chinese Neural Question Generation

    VIEW 6 EXCERPTS
    CITES BACKGROUND
    HIGHLY INFLUENCED

    The construction of Chinese microblog gender-specific thesauruses and user gender classification

    VIEW 5 EXCERPTS
    CITES BACKGROUND
    HIGHLY INFLUENCED

    An Adaptive Wordpiece Language Model for Learning Chinese Word Embeddings

    VIEW 5 EXCERPTS
    CITES BACKGROUND & METHODS
    HIGHLY INFLUENCED

    An Auxiliary Scheme for Automatic Marking of Chinese Reading Comprehension

    • Cheng-Hang Wang, Hong Wang
    • Computer Science
    • 2019 10th International Conference on Information Technology in Medicine and Education (ITME)
    • 2019
    VIEW 3 EXCERPTS
    CITES METHODS & BACKGROUND
    HIGHLY INFLUENCED

    Improving clinical named entity recognition in Chinese using the graphical and phonetic feature

    VIEW 11 EXCERPTS
    CITES METHODS
    HIGHLY INFLUENCED

    References

    Publications referenced by this paper.
    SHOWING 1-10 OF 49 REFERENCES

    Enriching Word Vectors with Subword Information

    VIEW 4 EXCERPTS
    HIGHLY INFLUENTIAL

    Multi-Granularity Chinese Word Embedding

    VIEW 4 EXCERPTS
    HIGHLY INFLUENTIAL

    How Does Word Length Evolve in Written Chinese?

    VIEW 19 EXCERPTS
    HIGHLY INFLUENTIAL

    Joint Learning of Character and Word Embeddings

    VIEW 10 EXCERPTS
    HIGHLY INFLUENTIAL