Low-dimensional Embeddings

Low-Dimensional Embeddings is a type of word embedding that represents words as dense vectors in a continuous vector space with significantly reduced dimensionality compared to the vocabulary size, enabling efficient computation and capturing semantic relationships through proximity in the latent space.

1.3K

Publications

150.4K

Citations

3.9K

Authors

983

Institutions

Publications per year

2017–2026

820

Authors

3.9K

  1. ZL
    Zhiyuan Liu

    Tsinghua University, China

    12 publications · 2.1K citations

    12

    h-index

  2. MS
    Maosong Sun

    Tsinghua University, China

    10 publications · 1.9K citations

    10

    h-index

  3. PI
    Piotr Indyk

    Massachusetts Institute of Technology, United States

    9 publications · 670 citations

    9

    h-index

  4. PC
    Peng Cui

    Tsinghua University, China

    8 publications · 5.4K citations

    8

    h-index

  5. CS
    Chuan Shi

    Beijing University of Posts and Telecommunications, China

    8 publications · 805 citations

    8

    h-index

1–5 of 3.9K

Venues

  1. arXiv (Cornell University)

    Repository · 169 publications · 32.2K citations

    52

    h-index

  2. Proceedings of the AAAI Conference on Artificial Intelligence

    Conference · 40 publications · 4.2K citations

    24

    h-index

  3. Briefings in Bioinformatics

    19 publications · 1.2K citations

    16

    h-index

  4. IEEE Transactions on Knowledge and Data Engineering

    TKDE · 19 publications · 2.7K citations

    16

    h-index

  5. 15

    h-index

1–5