Markov Language Models

Markov Language Models is a type of probabilistic language model that assumes the probability of each word in a sequence depends only on a fixed number of preceding words, formalized through the Markov property to simplify joint probability estimation in natural language.

212

Publications

23K

Citations

503

Authors

182

Institutions

Publications per year

2017–2026

25

Variants

Markov Language Model

Authors

503

  1. CD
    Christopher D. Manning

    Stanford University, United States

    4 publications · 3.4K citations

    4

    h-index

  2. JB
    Jeff Bilmes

    University of Washington, United States

    4 publications · 134 citations

    4

    h-index

  3. RP
    Roberto Pieraccini

    AT&T (United States), United States

    3 publications · 151 citations

    3

    h-index

  4. HB
    Horst Bunke

    University of Bern, Switzerland

    3 publications · 365 citations

    3

    h-index

  5. HR
    Hae‐Chang Rim

    Korea University, South Korea

    3 publications · 57 citations

    3

    h-index

1–5 of 503

Venues

  1. Computer Speech & Language

    9 publications · 328 citations

    9

    h-index

  2. 4

    h-index

  3. Pattern Recognition

    4 publications · 154 citations

    4

    h-index

  4. arXiv (Cornell University)

    Repository · 3 publications · 177 citations

    3

    h-index

  5. Proceedings of the AAAI Conference on Artificial Intelligence

    Conference · 2 publications · 60 citations

    2

    h-index

1–5