Stereotype Amplification

Stereotype Amplification is a systematic bias in machine translation whereby gender, racial, or cultural stereotypes present in training data are reinforced or intensified in translated outputs, leading to the propagation of distorted social representations.

26

Publications

3.9K

Citations

75

Authors

35

Institutions

Publications per year

2017–2026

20

Authors

75

  1. JZ
    James Zou

    Stanford University, United States

    4 publications · 1.7K citations

    4

    h-index

  2. AC
    Aylin Caliskan

    University of Washington, United States

    4 publications · 399 citations

    4

    h-index

  3. AW
    Alan W. Black

    Carnegie Mellon University, United States

    3 publications · 404 citations

    3

    h-index

  4. YT
    Yulia Tsvetkov

    Carnegie Mellon University, United States

    3 publications · 404 citations

    3

    h-index

  5. DN
    Debora Nozza

    Bocconi University, Italy

    3 publications · 377 citations

    3

    h-index

1–5 of 75

Venues

  1. arXiv (Cornell University)

    Repository · 7 publications · 1.6K citations

    7

    h-index

  2. Journal of Experimental Social Psychology

    2 publications · 384 citations

    2

    h-index

  3. American Journal of Epidemiology

    AJE · 1 publications · 11 citations

    1

    h-index

  4. The British Journal of Criminology

    1 publications · 15 citations

    1

    h-index

  5. International Conference on Machine Learning

    Conference · 1 publications · 58 citations

    1

    h-index

1–5