NuMind

Custom NLP models for Information Extraction

41 followers

Custom NLP models for Information Extraction

41 followers

•

•

Teach your AI to create classifiers, NER models, and Structured Extraction models tailored to your needs. These lightweight models extract information better & cheaper than generic models, and can be used in a private setting.

Free Options

Launch tags:Developer Tools•Artificial Intelligence•Data & Analytics

Launch Team / Built With

Render Sandboxes: a computer for every agentRun untrusted code safely. Idle sandboxes cost nothing

Promoted

Maker

📌

Hi Everyone! I am Co-Founder & CEO of NuMind (YC S22) We are launching our NLP tool after a (long!) R&D phase. Our overall idea is that the best way to customize an AI is to "teach it", which essentially means telling it what to do and iteratively correcting it until it "gets it". We chose to focus on the tasks of text information extraction first, but might adventure ourselves in other kind of tasks later. Practically speaking, this means that you can create custom classifiers, NER models, and soon Structured Extraction models that are lightweight and have strong performance. Under the hood, NuMind uses our foundation models (https://lnkd.in/drx4UA3n), some automatic machine learning, and an active learning strategy to reduce the amount of human effort. You can try it (for free) here: https://numind.ai/signup If you want to know more about it you can also watch the presentation video https://lnkd.in/enpYVaRg, read the release blog post https://lnkd.in/eWhdk6nD, and join our Discord server https://lnkd.in/ei-ahJ4q. I hope some of you will find this tool useful, and don't hesitate to give us feedback! :)

Report

2yr ago

Connector Catalog by Whaly

Very impressive demo! Seems awesome and well built! Will keep in mind if I need to execute a NLP project soon!

Report

2yr ago

Maker

Thanks @pierre_de_poulpiquet !

Report

2yr ago

Kuration AI

Great product! I had the chance to have a live demo when Etienne was still in stealth mode, 6 months ago. The product is very promising and has many good use cases. I haven't used it extensively but it's on my roadmap. Well done team!

Report

2yr ago

Maker

Thanks @aurelien_vasinis !

Report

2yr ago