Embedding Regularization

Embedding Regularization is a computational technique in natural language processing that belongs to the class of regularization methods, specifically designed to constrain the learned representations of words in a continuous vector space to improve generalization by reducing overfitting, enhancing semantic coherence, or enforcing desirable geometric properties.

60

Publications

4.7K

Citations

216

Authors

91

Institutions

Publications per year

2017–2026

49

Authors

216

  1. BW
    Byron Wallace

    Northeastern University, United States

    2 publications · 129 citations

    2

    h-index

  2. MF
    Minwei Feng

    IBM (United States), United States

    2 publications · 1.8K citations

    2

    h-index

  3. WD
    Weihong Deng

    Beijing University of Posts and Telecommunications, China

    2 publications · 73 citations

    2

    h-index

  4. LW
    Liwei Wang

    Peking University, China

    2 publications · 158 citations

    2

    h-index

  5. RI
    Ryutaro Ichise

    National Institute of Informatics, Japan

    2 publications · 202 citations

    2

    h-index

1–5 of 216

Venues

  1. arXiv (Cornell University)

    Repository · 13 publications · 2.2K citations

    11

    h-index

  2. Proceedings of the AAAI Conference on Artificial Intelligence

    Conference · 5 publications · 368 citations

    5

    h-index

  3. Pattern Recognition

    3 publications · 95 citations

    3

    h-index

  4. IEEE Transactions on Cybernetics

    2 publications · 48 citations

    2

    h-index

  5. 2

    h-index

1–5