Innovative search hits Wikipedia
Powerset has unveiled the first beta of its semantic search engine, allowing users to search by conversational phrasing instead of keywords.
The technology breaks down the meaning of words and sentences into related concepts, freeing users from always needing to type the exact words they want to find.
“Our system is a little more forgiving,” explains Scott Prevost, general manager of Powerset. “It is not looking for hard-word matches. We are not searching for exact words, but concepts.”
Currently the engine is limited to searching around two million Wikipedia pages, but its creators intend on broadening the service in coming months with the intention of leapfrogging keyword dependent services such as Google and Yahoo.
However, analysts have warned that forming a challenge to Google could take some time: “What I don’t know is how Powerset will perform on the wide open web. In a sense, this is a massive prototype using the relatively structured information of Wikipedia. It is difficult to compare to what Google has built,” says Reg Sterling, an internet analyst with Sterling Market Intelligence.
Sterling claims a bigger danger to Google would be if rival Microsoft was to acquire Powerset and incorporate it into its other search technologies.
Spokesmen for Microsoft and Powerset declined to comment on rumours of a potential tie-up between the two companies.