Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

Bias metrics for gender based on arXiv:1910.10872 paper #1262

Open
mariobrasil123 opened this issue Jul 22, 2023 · 2 comments
Open

Bias metrics for gender based on arXiv:1910.10872 paper #1262

mariobrasil123 opened this issue Jul 22, 2023 · 2 comments

Comments

@mariobrasil123
Copy link

mariobrasil123 commented Jul 22, 2023 •
edited
Loading

Is your feature request related to a problem? Please describe.

I want to create a library to get the metrics of arXiv:1910.10872 given a model o names entity recognition, but i think it would be good if its implemented on fairlearn instead of other library.

Describe the solution you'd like

Given a model of name entity recognition, templates according to the paper or created by the user and frequency of name in a region, I want to calculate all errors described in this paper for gender bias analysis,

Describe alternatives you've considered, if relevant

Additional context

example of a plot of the gender bias in many templates given the frequency of a names in Brazil according to IBGE(a Brazilian government association for Brazilian Statistics)
image
@mariobrasil123
Copy link
Author

I already created a class for this type of metrics, but i don't know if this specific metric for name entity recognition bias is outside of the scope of this library

@adrinjalali
Copy link
Member

Thanks for opening this issue @mariojose123 . It's indeed a good question weather it's too specific or not. I'm leaning towards being a +1 on having a general version of this in the library. But we'll need to discuss with other @fairlearn/fairlearn-maintainers

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees
No one assigned
Labels
None yet
Projects
None yet
Milestone
No milestone
Development

No branches or pull requests
2 participants
@adrinjalali @mariobrasil123