[27] Danqi Chen - Neural Reading Comprehension and Beyond
The Thesis Review
How to Build a Stronger Natural Language Understanding Systems
I'm very interested in basically almost everything that can actually help us build a stronger natural language understanding systems. I do think that yeah we can build a large model and then compress later but maybe if the goal is really to start with a smaller model maybe there could be a new ideas like that nearest neighbor approach. Yeah, I like to throw in some speculative questions that I don't think anyone knows the answer to so that's a good perspective though. So then after your PhD we talked about like some of your outgoing paths of work so even like working on this Roberta model working on dense passes retrieval this phrase based model.
00:00
Transcript
Play full episode
Remember Everything You Learn from Podcasts
Save insights instantly, chat with episodes, and build lasting knowledge - all powered by AI.
