Rule-based Generation

Rule-Based Generation is a natural language generation approach that systematically produces text by applying predefined linguistic and syntactic rules, distinguished from statistical or neural methods through its reliance on explicitly encoded grammatical and semantic constraints.

324

Publications

14.6K

Citations

869

Authors

389

Institutions

Publications per year

2017–2026

81

Authors

869

  1. MN
    Michinori Nakata

    Josai International University, Japan

    6 publications · 155 citations

    6

    h-index

  2. HS
    Hiroshi Sakai

    High Energy Accelerator Research Organization, Japan

    6 publications · 155 citations

    6

    h-index

  3. KM
    Kathleen McKeown

    Columbia University, United States

    5 publications · 189 citations

    5

    h-index

  4. SK
    Sankar K. Pal

    Indian Statistical Institute, India

    5 publications · 303 citations

    5

    h-index

  5. AB
    Aditya Bhan

    University of Minnesota, United States

    4 publications · 266 citations

    4

    h-index

1–5 of 869

Venues

  1. IEEE Transactions on Knowledge and Data Engineering

    TKDE · 5 publications · 879 citations

    5

    h-index

  2. Fuzzy Sets and Systems

    4 publications · 138 citations

    4

    h-index

  3. arXiv (Cornell University)

    Repository · 4 publications · 83 citations

    4

    h-index

  4. Computers & Chemical Engineering

    3 publications · 187 citations

    3

    h-index

  5. 3

    h-index

1–5