Google Killer: Powerset Semantic Search Engine
by Muhammad on May 12, 2008
in Uncategorized
Having been long predicted as the shaping the next generation of search, Semantic Web Applications are now coming to the fore with Powerset leading the way. Powerset has released its beta version, allowing the public to finally try out the new key word technology. Ushering the new era of search, Powerset hopes to change people’s expectations of search by offering a far more intelligent and efficient form of searching, at least in theory.
“We’re changing the way information is searched by doing a much deeper analysis of the pages we index,” said Scott Prevost, Powerset’s product director.
Keyword engines treat pages as word bags, indexing their content without grasping its meaning, he said. Meanwhile, Powerset’s engine, applying technology developed in-house as well as licensed from Xerox’s PARC subsidiary, creates a semantic representation by parsing each sentence and extracting its meaning. “Meaning is what we index,” he said.
Google’s Marissa Mayer has even elaborated on the benefit of the semantic web…
“People should be able to ask questions and we should understand their meaning, or they should be able to talk about things at a conceptual level. We see a lot of concept-based questions — not about what words will appear on the page but more like ‘what is this about?’. A lot of people will turn to things like the semantic Web as a possible answer to that,” she said.
She also said that Google seems intelligent more through brute force because of the amount of data it crunches rather than it being really “smart” and working out what the user really means when they are searching for certain terms.
I can already see Google Scurrying to upgrade their system to incorporate this though… they certainly have the budget to do it. The current form of Powerset is limited, consisting only of millions of pages from Wikipedia and Metaweb Technologies’ Freebase, a Web-based structured database of information. Whatever it is, here’s to ushering in a new era in search, one that will ultimately provide a real challenge to the Google’s and Yahoo’s of our increasingly connected world.
Could this possibly be the beginning of a Web 3.0?
What is something that is worrisome (and kinda unrelated) is the extreme prevalence of the use of Wikipedia as an “authoritative” source. I see students producing tons of stuff where wiki’s been used because of the convenience, it’s like a mini-self contained-internet. Wiki is becoming the first stop of info for many searches.
I still feel also that there should be a 3-layered approach to search queries, Layer 1 for proper subject/specialist/academically related websites, Layer 2 (a sub directory) for wiki and the like and Layer 3 (as a sub-sub directory) for blogs, MySpace, FaceBook etc.
That way I guess the Internet will be used to find infomation without having searches “polluted” with junk.
Rah – I agree. But you must also agree that the stuff put up on wikipedia is generally trusted since not ALL of the users have malicious intent and most really have the urge to spread knowledge and ideas about a vast array of topics. That’s why it was spawned in the first place.
Your three layers make sense, but don’t they only relate to academically related queries? for example if you search for Cindy Crawford (I’m a guy, sue me)… you don’t want some academic article about the abuse of female models in the Beauty and Modelling Industry.
Hence, searching by popularity and searching by “Meaning”…Web 3.0