News:

Help! We're trapped in the computer, and the computer is trapped in 2008! Someone call the time police!

Main Menu

TextRunner

Started by Sidoh, December 14, 2006, 12:40:03 AM

Previous topic - Next topic

0 Members and 1 Guest are viewing this topic.

Sidoh

This is a really neat development, I thought.  It's not really designed to compete with anything like Google, but the University of Washington is attempting to explore the "next generation of search engines."  There are still a few anomalous entries that don't really make sense, but it's fun to play around with!

For example, you could fill in the fields:

Arg1 -- Einstein
Predicate -- Born

and it would return a list of tuples that it thinks describes your specifications.

There was a lecture on this on TV today, which is where I heard about it.  I'm not sure how famous it is, but I found some of the details pretty interesting.  For example, it is a "self-sufficient" application.  It learns on its own.  It decides what to learn and how to learn it.  That's obviously a huge understatement of what it is actually doing, but none of these aspects were covered in much detail.

Anyway, I thought I'd share.

Towelie

how does this differ from modern day search engines?

Sidoh