Forum Moderators: open
Using a combination of statistical mathematics, heuristics, artificial intelligence and new computer languages, researchers are developing a "Semantic Web," as it is called, which responds to online queries more effectively. The new tools are enabling users -- now on internal corporate networks and, within a year, on the global Internet -- to search using more natural language queries.
And:
"Key word searching is common today," Wiener said. "But the next generation of the Web is making documents more contextually relevant.
Full Story [upi.com]
James Lester's comment was particularly telling, "People aren't doing this out of the goodness of their hearts. There is significant commercial potential". :)
Now, when they get AI around to the point of passing the AI test, we'll see a whole new type of search.
Have you ever looked into the Tritus project?
Pretty cool stuff. They train their system with loads of question-answer FAQ files so that it learns to find documents that might contain answers to questions that are searched.
Learning to Find Answers to Questions on the Web [cs.columbia.edu]