We Didn’t Prove Prejudice Is True: Why and When Machines Have Human Bias

Internal Event
16 November 2017
Begin time: 
End time: 
CITEC building, 1.204

In 2017, Dr. Joanna Bryson and two colleagues demonstrated that applying machine learning to ordinary human language results in human-like semantic biases. They replicated a spectrum of known biases, as measured by the Implicit Association Test, applying a widely used, purely statistical machine-learning model trained on a standard corpus of texts from the Internet. More informations: https://cit-ec.de/de/gender-diversit%C3%A4t/gender-gastprofessur