Skip to content

Implementations and wrapper of bias scores for text embeddings.

License

Notifications You must be signed in to change notification settings

HammerLabML/EmbeddingBiasScores

Folders and files

NameName
Last commit message
Last commit date

Latest commit

5e72d36 · Apr 22, 2024

History

30 Commits
Apr 22, 2024
Oct 27, 2022
Oct 31, 2023
Mar 1, 2022
Apr 8, 2022
Dec 18, 2022
Nov 7, 2023
Apr 18, 2023
Aug 11, 2023
Aug 11, 2023

Repository files navigation

EmbeddingBiasScores

Implementations and wrapper of bias scores for text embeddings.

Requirements

All requirements are listed in requirements.txt.
In the notebooks, we use a wrapper for huggingface models. You can install the lib from source:
https://github.com/UBI-AGML-NLP/Embeddings

Installation

Download this repository and install via pip install .

Example

A minimalistic example for the usage of implemented bias scores can be found in example.ipynb.

Implemented Scores

So far, we implemented geometrical bias scores that measure the association of embeddings with protected groups. Other scores and bias test will follow.
Papers that introduced the scores are linked.

Geometrical Bias scores

Clustering based Bias Scores

Clustering, Classification and Neighbor Test

About

Implementations and wrapper of bias scores for text embeddings.

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published