Wednesday, July 02, 2008
Microsoft Search Aims to Interpret Meaning
For most of us, Google is best way to find information on the Web. We have a question, we type in a keyword and up pops just about anything we want.
Provided we guess the right keywords.
By and large, though, keywords are a pretty good way to find your way around the Web. But search technologists -- and linguists -- have been trying to get beyond the one-step, guess-and-enter world of search. They want to better understand what you are trying to find instead of which keyword matches.
It's called "semantic search" and some of the smartest minds on the planet are trying to figure it out. We're not there yet. Not even close. But big companies are beginning to dip their toes in the water.
Microsoft is close to finalizing a deal with Powerset, a company that uses natural language (e.g. "find me the nearest swimming pool" instead of "pool, Cincinnati, public") to come up with better search results (theoretically).
On the surface, natural language search doesn't sound all that exciting (unless you're a mathematician or a chip designer), but the ability to develop contextual means would make it far easier to find information on the Web. Michael Arrington lays it out very well at Tech Crunch, where they also have an audio interview (with transcript) with the founders of Powerset:
A query such as “who wrote catcher in the rye” using normal keyword search will attempt to find those very words, while with Powerset and natural language search it will analyze what the user is actually looking for, even though there may not be a website that directly spells out “who wrote catcher in the rye”. The technology is all based on analyzing the users intention when searching based on the words they use.
Why the move?
Well as nice as it would be for you and I to have natural language searches, Microsoft has other designers. The company continues to lag behind Google and Yahoo in the search market and desperately needs to find the "new, new" thing if it wants to eclipse its rivals. Whichever company creates the best natural language search will have a leg up in the search wars.
By Brad at 05:26 PM | Comments (0)