microsoft/responsible-ai-toolbox-genbit

A tool for gender bias identification in text. Part of Microsoft's Responsible AI toolbox.

42
/ 100
Emerging

This tool helps data scientists and ML developers identify gender bias in the text datasets they use to train natural language processing (NLP) models. You provide a body of text, and it outputs scores indicating the strength of association between words in your corpus and various gender categories (male, female, non-binary, trans, cis). It's designed for anyone building or evaluating NLP systems to ensure fairness.

No commits in the last 6 months.

Use this if you need to measure how much your text data associates specific words with particular genders, helping you identify and mitigate bias before it impacts your AI models.

Not ideal if you're looking for a tool to fix bias directly in your models or if your dataset has fewer than 400 documents and 600 unique words.

AI-ethics NLP-data-preparation model-fairness text-corpus-analysis responsible-AI
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 8 / 25
Maturity 16 / 25
Community 18 / 25

How are scores calculated?

Stars

50

Forks

14

Language

Python

License

Last pushed

Aug 20, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/generative-ai/microsoft/responsible-ai-toolbox-genbit"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.