Character-based Embeddings

Character-Based Embeddings is a type of word representation in natural language processing that generates vectorized embeddings by modeling words as sequences of characters, thereby capturing subword morphological information through character-level composition.

178

Publications

14.6K

Citations

556

Authors

196

Institutions

Publications per year

2017–2026

145

Variants

Character-level Embeddings

Authors

556

  1. HZ
    Hai Zhao

    Shanghai Jiao Tong University, China

    4 publications · 202 citations

    4

    h-index

  2. CD
    Chris Dyer

    Carnegie Mellon University, United States

    4 publications · 5K citations

    4

    h-index

  3. MR
    Marek Rei

    University of Cambridge, United Kingdom

    3 publications · 230 citations

    3

    h-index

  4. KL
    Karen Livescu

    Toyota Technological Institute at Chicago, United States

    3 publications · 230 citations

    3

    h-index

  5. YB
    Yonatan Belinkov

    Technion – Israel Institute of Technology, Israel

    3 publications · 1K citations

    3

    h-index

1–5 of 556

Venues

  1. arXiv (Cornell University)

    Repository · 22 publications · 1.3K citations

    17

    h-index

  2. IEEE Access

    8 publications · 171 citations

    8

    h-index

  3. Proceedings of the AAAI Conference on Artificial Intelligence

    Conference · 7 publications · 661 citations

    7

    h-index

  4. International Conference on Computational Linguistics

    Conference · 5 publications · 1.1K citations

    5

    h-index

  5. Journal of Biomedical Informatics

    2 publications · 121 citations

    2

    h-index

1–5