Watson apparently refines it’s notion of the kinds of answers that are expected under a given category as it accumulates previous answers. The human contestants could exploit this by starting with the higher dollar questions. I’ll be curious to see if they do.
There’s a detailed chart of the performance over time of the system here.
Here’s a better quality video. And this is another video in which the people at IBM talk about developing Watson and why they chose to do Jeopardy.
Watson apparently refines it’s notion of the kinds of answers that are expected under a given category as it accumulates previous answers. The human contestants could exploit this by starting with the higher dollar questions. I’ll be curious to see if they do.
There’s a detailed chart of the performance over time of the system here.