Neural Topic Models

Neural Topic Models is a class of probabilistic topic modeling frameworks that leverages deep neural networks to learn latent thematic structures from text corpora, distinguishing itself from classical topic models by replacing explicit generative assumptions with flexible neural architectures for inference.

350

Publications

17.6K

Citations

1.2K

Authors

388

Institutions

Publications per year

2017–2026

262

Authors

1.2K

  1. YH
    Yulan He

    Aston University, United Kingdom

    8 publications · 352 citations

    8

    h-index

  2. QX
    Qianqian Xie

    University of Manchester, United Kingdom

    7 publications · 251 citations

    7

    h-index

  3. YR
    Yanghui Rao

    Sun Yat-sen University, China

    6 publications · 114 citations

    6

    h-index

  4. MP
    Min Peng

    Wuhan University, China

    5 publications · 190 citations

    5

    h-index

  5. DZ
    Deyu Zhou

    Southeast University, China

    5 publications · 238 citations

    5

    h-index

1–5 of 1.2K

Venues

  1. arXiv (Cornell University)

    Repository · 31 publications · 2.8K citations

    18

    h-index

  2. Proceedings of the AAAI Conference on Artificial Intelligence

    Conference · 12 publications · 562 citations

    12

    h-index

  3. Information Processing & Management

    11 publications · 461 citations

    11

    h-index

  4. Neurocomputing

    10 publications · 325 citations

    10

    h-index

  5. IEEE Access

    9 publications · 223 citations

    9

    h-index

1–5