Practical transfer learning for NLP with spaCy and Prodigy Scale

Transfer learning has been called “NLP’s ImageNet moment”. Recent work has shown that models can be initialized with detailed, contextualised linguistic knowledge, drawn from huge samples of data. In this talk, I’ll explain spaCy’s new support for efficient and easy transfer learning, and show you how it can kickstart new NLP projects with our new annotation tool, Prodigy Scale.