Aylin Caliskan
University of Washington associate professor studying bias, safety, and societal impacts of AI
- Associate Professor, The Information School; Paul G. Allen School of Computer Science & Engineering (courtesy), University of Washington1
Aylin Caliskan is an Associate Professor in the Information School at the University of Washington, with a courtesy appointment in the Paul G. Allen School of Computer Science & Engineering, and a co-director of the Tech Policy Lab. Caliskan's research covers technical and empirical AI ethics and safety in natural language processing, multimodal machine learning, and human-AI collaboration, developing methods to detect, quantify, and mitigate biases, errors, and potential harms of AI systems. Caliskan is first author, with Joanna J. Bryson and Arvind Narayanan, of Semantics derived automatically from language corpora contain human-like biases, which replicated standard human biases measured by the Implicit Association Test in GloVe word embeddings trained on web text.12
Work
Semantics derived automatically from language corpora contain human-like biases (external site: arxiv.org)Published research
First author of the 2016 paper showing that standard machine learning applied to ordinary language reproduces human-like semantic biases.2
This profile covers public professional work only, from the sources below. It is not an endorsement or a ranking. To correct or remove it, use the correction form.