Skip to content

Implementation of the POAT in order to identify implicit biases in word embeddings. Based on the IAT and WEAT.

License

Notifications You must be signed in to change notification settings

jellebosscher/POAT

Repository files navigation

POAT

https://scripties.uba.uva.nl/search?id=715755 Implementation of the Positive Operator Association Test that identifies implicit biases in words embeddings. Based on the IAT and WEAT.

First use: Possibly change directories in run_poat.py and download word embeddings from: https://nlp.stanford.edu/projects/glove/ (This project used the 'Common Crawl' embeddings with 300 dimensions)

WEAT: https://science.sciencemag.org/content/356/6334/183 IAT: https://psycnet.apa.org/fulltext/1998-02892-004.html

About

Implementation of the POAT in order to identify implicit biases in word embeddings. Based on the IAT and WEAT.

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages