Let’s make gender neutral language open source!

A NLP resource to identify non-gender neutral terminology

For a recent project I was asked to create a set of Natural Language Processing (NLP) tools to check documents on upload to a server for several things, one of which being checking for non-gender neutral terminology.

For all the other requirements I was able to find out of the box solutions but I wasn’t able to find any definitive resources to identify said terminology.

So what can we do about this?

I spent a few hours cycling through the entire English dictionary and one massive headache later I put together a list of 1500+ terms that aren’t neutral.

This is by no means every single term but I believe it is a solid start.

So how can I help?

What I want your help with is adding to this list and suggesting gender neutral terminology for each word.

Together we can provide a resource for anyone developing NLP tools and help make the content we create more inclusive.

Head over to the GitHub repo and get collaborating, I’m looking forward to working with you all!