N-gram Statistics

N-Gram Statistics is a computational linguistic metric that quantifies the frequency and distributional patterns of contiguous sequences of n items in a given text corpus, distinguishing itself by enabling probabilistic language modeling and empirical validation of syntactic and semantic regularities in natural language processing.

458

Publications

40K

Citations

1K

Authors

377

Institutions

Publications per year

2017–2026

55

Authors

1K

  1. AS
    Andreas Stolcke

    SRI International, United States

    8 publications · 599 citations

    8

    h-index

  2. HN
    Hermann Ney

    RWTH Aachen University, Germany

    6 publications · 442 citations

    6

    h-index

  3. LL
    Lori Lamel

    Laboratoire d'Informatique pour la Mécanique et les Sciences de l'Ingénieur, France

    5 publications · 122 citations

    5

    h-index

  4. SF
    Stanley F. Chen

    IBM (United States), United States

    5 publications · 3.6K citations

    5

    h-index

  5. OG
    Ondřej Glembek

    Brno University of Technology, Czechia

    4 publications · 168 citations

    4

    h-index

1–5 of 1K

Venues

  1. Computer Speech & Language

    8 publications · 2.5K citations

    8

    h-index

  2. ArXiv.org

    Repository · 7 publications · 930 citations

    7

    h-index

  3. arXiv (Cornell University)

    Repository · 6 publications · 109 citations

    6

    h-index

  4. International Journal of Corpus Linguistics

    IJCL · 5 publications · 382 citations

    5

    h-index

  5. Computational Linguistics

    5 publications · 292 citations

    5

    h-index

1–5