The Data Exchange with Ben Lorica cover image

Efficient Methods for Natural Language Processing

The Data Exchange with Ben Lorica

00:00

Using Labeled Examples to Fine Tune Your Model

Roya: When you have a big model, then you realize it's not good enough to deploy because it's framed on internet data. You want to fine tune it for your domain. And in this case, this is where labeled examples come in. So maybe you could take doctor notes with no label whatsoever, but just this is medical text. This is helpful for adjusting the pre-trained model to your domain of interest. Another very active area of research along these lines is using Roya.

Transcript
Play full episode

The AI-powered Podcast Player

Save insights by tapping your headphones, chat with episodes, discover the best highlights - and more!
App store bannerPlay store banner
Get the app