8: Deep Learning for Natural Language – Transformers, Self-Supervised Learning

Transcript

[SQUEAKING] RAMA RAMAKRISHNAN: OK, so we'll This is going to be a deeper it's potentially the So a quick review. Why do we want transformers? Because we want an architecture that has the same length and we want to take And so just a quick review. If you have a phrase like, or uncontextual embeddings. And then-- sometimes So if you're here, if we em... Read More