Hacker News new | past | comments | ask | show | jobs | submit login

The actual Watson program that performed on Jeopardy is pretty well described in publications. You can start here: http://www.aaai.org/ojs/index.php/aimagazine/article/view/23... for example.

The right way to answer "Can you help me with life insurance" is to start asking the user questions to learn more about their needs - that's one of the way we are currently trying to go beyond the Jeopardy use case.




Interesting.

I'm yet to see a good public implementation of conversational question answering. It's pretty clear Google is headed down that path with Google Now, and I guess Siri is going the same way.

Traditionally question refinement is done using filters and clustering, but of course this focuses the result sets, and is the opposite of what you need in conversational question answering.




Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: