
Episode 7: There Are Now 15 Competing Evaluation Metrics (ft. Dr. Jeremy Kahn). December 12, 2022
Mystery AI Hype Theater 3000
The Importance of Human Evaluation in Summarization
The notion of task itself is self-determined quite intensely by what the benchmark is. The people we need to be talking to are not the linguists, and they're definitely not the computer scientists. It's actually the sociologists and the anthropologists who are thinking about what do these data sets need to reflect in order to be a decent reflection of performance on some task.
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.