
[27] Danqi Chen - Neural Reading Comprehension and Beyond
The Thesis Review
The Challenges of Generalization in Large Scale Neural Sequence Models
The problem is right now we just have a model that can actually feel in the distribution of one particular dataset. And then it's very hard to understand, okay, whether this type of reasoning can generalize to another. So it's a really difficult problem. That was really like a mind blowing like a moment to me. Like I was even joking that, okay, maybe I should just go back and do another PhD.
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.