Semantic Search Wikipedia With Powerset

[engine]

Powerset on Sunday unveiled tools for searching Wikipedia that use conversational phrasing instead of keywords, marking the first step of its challenge to established Web search services such as Google.

Powerset's 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.

The closely watched Silicon Valley start-up is offering a way of searching millions of entries in Wikipedia's online encyclopedia, helping users find detailed answers to questions rather than isolated links that require further research.

Search Wikipedia With Powerset [uk.reuters.com]

[powerset.com...]

[AjiNIMC]

Looks good, did some searches and it gave me good results, don't know if better that google :)

[Tastatura]

interesting...but not sure that it's a G killer just yet.
I started easy and typed geographical query, asking for a capital of some country ( a la " What is capital of Widgetland?") - it gave correct answer, but so did same query on G.

I then asked 'How fast is (certain car make and model)?' and got mostly irrelavent results back - most of them weren't even about right car model. I was hoping result would be a number such as 'top speed is xyz mph' or something similar...It definitely did not get a meaning of speed and make a 'connection' between 'how fast' and 'speed'. For the same query G did not get the answer back either, but seemed to have more focused results....

[edited by: Tastatura at 2:53 pm (utc) on May 12, 2008]

[Receptional Andy]

IMO this has always been a good concept, but with less than satisfying implementations. Another startup trying similar things (that is worth a test or two) is Hakia.

[TheGuyAboveYou]

No big deal. Google is public. Just buy them up.
Not an issue.