Technology Review: Extracting Meaning from Millions of Pages - 0 views
www.technologyreview.com/...22773
artificial intelligence AI data mining Google search semantic semantic web software
shared by Graham Perrin on 08 Jul 09
- Cached
-
University of Washington software pulls facts from 500 million Web pages
- ...15 more annotations...
-
"It can discover and learn millions of relations, not just one at a time. With TextRunner, there is no human in the loop: it just finds relations on its own."
-
insights that "chlorine kills bacteria" or "ultraviolet light kills bacteria" or "heat kills bacteria"
-
"this work reflects a growing trend toward the design of search tools that actively combine the pieces of information they find on the Web into a larger synthesis."