Transformation-based Learning

Transformation-Based Learning is a supervised machine learning methodology within computational linguistics that iteratively applies rule-based transformations to annotate parts of speech, distinguished by its use of error-driven learning to refine tagging accuracy through successive rule application.

135

Publications

8.4K

Citations

331

Authors

141

Institutions

Publications per year

2017–2026

29

Authors

331

  1. RF
    Radu Florian

    IBM (United States), United States

    8 publications · 940 citations

    8

    h-index

  2. KS
    Ken Samuel

    University of Delaware, United States

    5 publications · 190 citations

    5

    h-index

  3. SC
    Sandra Carberry

    University of Delaware, United States

    4 publications · 180 citations

    4

    h-index

  4. DY
    David Yarowsky

    Johns Hopkins University, United States

    4 publications · 293 citations

    4

    h-index

  5. KV
    K. Vijay‐Shanker

    University of Delaware, United States

    4 publications · 180 citations

    4

    h-index

1–5 of 331

Venues

  1. arXiv (Cornell University)

    Repository · 10 publications · 303 citations

    10

    h-index

  2. ArXiv.org

    Repository · 7 publications · 833 citations

    7

    h-index

  3. Conference on Computational Natural Language Learning

    Conference · 4 publications · 69 citations

    4

    h-index

  4. Natural Language Engineering

    3 publications · 207 citations

    3

    h-index

  5. IEEE Transactions on Cybernetics

    2 publications · 31 citations

    2

    h-index

1–5