Dear all, We are pleased to inform you that a new version of WEFE has been released: The Word Embeddings Fairness Evaluation Framework. WEFE is an open source library for measuring and mitigating bias in word embedding models. The main goal of the library is to provide a ready-to-use tool that allows the user to run bias measures and mitigation methods in a straightforward manner through well-designed and documented interfaces.

The new version implements of various debiasing algorithms (e.g., HardDebias, Repulsion Attraction Normalization, Half-Sibling Regression) in addition to various the already implemented fairness metrics (e.g., WEAT, RND, RNSB).

We invite you to try it out at: https://wefe.readthedocs.io/en/latest/index.html and "Star" the project on Github: https://github.com/dccuchile/wefe

We appreciate your feedback and suggestions.

Bests, Felipe Bravo-Marquez https://felipebravom.com/