The Loop Asia podcast

"What's Not in Your Data?" — Karin Verspoor, RMIT University

11/2/2026
0:00
25:30
Retroceder 15 segundos
Avanzar 15 segundos
"What's not in your data?" is the question Karin Verspoor asks before trusting any model — because LLMs are excellent at aggregating what's been said thousands of times, and blind to the specific context you're actually working in. Karin Verspoor is Executive Dean of Computer Science at RMIT University, with over 20 years applying natural language processing to healthcare, from molecular biology literature to electronic health records. What we cover: • How a chance question at Los Alamos National Lab led a computational linguist into biomedical NLP • The Unified Medical Language System — 40 years of structured medical vocabulary • Why simple dictionary lookup fails on medical negation, and what it takes to get right • Why AI scribes still put a human in the loop to catch drift and complacency • The domain-knowledge argument: you need to know more than the LLM to catch when it's wrong The Loop Asia: www.theloop.asia

Otros episodios de "The Loop Asia"