Today we’re joined by return guest Francisco Webber, CEO & Co-founder of Cortical.io.
Subscribe: iTunes / Google Play / Spotify / RSS
Francisco was originally a guest over 4 years and 400 episodes ago, where we discussed his company Cortical.io, and their unique approach to natural language processing. In this conversation, Francisco gives us an update on Cortical, including their applications and toolkit, including semantic extraction, classifier, and search use cases. We also discuss GPT-3, and how it compares to semantic folding, the unreasonable amount of data needed to train these models, and the difference between the GPT approach and semantic modeling for language understanding.
Connect with Francisco!
Resources
- Statistics vs Semantics for Natural Language Processing Francisco Webber
- Turning Ideas into ML Powered Products with Emmanuel Ameisen
- Cortical.io
- Trends in Natural Language Processing with Sameer Singh
Join Forces!
- Check out our TWIML Presents: series page!
- Register for the TWIML Newsletter
- Check out the official TWIMLcon:AI Platform video packages here!
- Download our latest eBook, The Definitive Guide to AI Platforms!
“More On That Later” by Lee Rosevere licensed under CC By 4.0
Thomas E
I think his argument of why they can’t compare with benchmarks is incoherent. Why in the world would you not be able to at least measure the relative differences in real-world efficacy of different models/algorithms to a problem like entity or relation extraction, using academical benchmarks? It seems negligent to build any real-world predictive model without establishing a baseline at all, like did you at least try fine-tuning a random huggingface transformer?