Character N-grams

Character N-Grams is a text feature engineering technique that represents contiguous sequences of characters of length n within a string, serving as a lexical-level representation to capture sub-word morphological patterns in natural language processing tasks.

183

Publications

12.1K

Citations

478

Authors

220

Institutions

Publications per year

2017–2026

78

Authors

478

  1. RT
    Radu Tudor Ionescu

    University of Bucharest, Romania

    6 publications · 158 citations

    6

    h-index

  2. GS
    Grigori Sidorov

    Instituto Politécnico Nacional, Mexico

    6 publications · 163 citations

    6

    h-index

  3. AG
    Alexander Gelbukh

    Instituto Politécnico Nacional, Mexico

    4 publications · 220 citations

    4

    h-index

  4. AM
    Andrei M. Butnaru

    University of Bucharest, Romania

    4 publications · 84 citations

    4

    h-index

  5. ES
    Efstathios Stamatatos

    University of the Aegean, Greece

    4 publications · 380 citations

    4

    h-index

1–5 of 478

Venues

  1. arXiv (Cornell University)

    Repository · 6 publications · 117 citations

    6

    h-index

  2. International Conference on Computational Linguistics

    Conference · 4 publications · 358 citations

    4

    h-index

  3. Digital Scholarship in the Humanities

    DSH · 3 publications · 54 citations

    3

    h-index

  4. 3

    h-index

  5. CLEF (Working Notes)

    2 publications · 43 citations

    2

    h-index

1–5