Neural Architecture Search and Google’s New AutoML Zero with Quoc Le - #366
The TWIML AI Podcast (formerly This Week in Machine Learning & Artificial Intelligence)
00:00
Scaling Up NLP Models for Improved Human-Like Interaction
This chapter explores how scaling up natural language processing models enhances performance while addressing the challenges of evaluating the human-like quality of bot conversations. It highlights the correlation between model perplexity and human judgments, suggesting that improved predictive capabilities can foster more human-like interactions.
Transcript
Play full episode
