microsoft/responsible-ai-toolbox-genbit
A tool for gender bias identification in text. Part of Microsoft's Responsible AI toolbox.
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.
Stars
50
Forks
14
Language
Python
License
—
Category
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.