Powerset Revolutionizes The Web Semantic Search
San Francisco – Amid speculation that Microsoft is looking to make an acquisition, Powerset on Sunday launched tools for searching Wikipedia that use conversational phrasing instead of keywords, taking a significant step forward in its challenge to established Web search services such as Google.
“It offers an innovative, rich semantic dimension via natural language query processing to Wikipedia that greatly improves the search and reading experience.”
Powerset’s technology analyzes the meaning of words and sentences into correlated concepts, freeing users from always needing to type the exact words they want to find.
The company calls it a gateway in shifting the way users search and consume Web content. “It is a complete shift. You see this and you want to experience all content in this way,” Barney Pell, co-founder and CTO of Powerset, said in a statement. “And, as an introduction, it will drive huge investment in semantic and linguistic technology, just as investments were made in information retrieval and scalable databases in the past. People working in this space will be very marketable.”
Users can enter keywords, phrases, or simple questions in Powerset’s search box. Like many Web startups, Powerset is currently free of advertising.
The closely watched Silicon Valley start-up is providing a novel method 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. For example, a user who wants to know how many wives King Henry VIII had (six, or two, depending on your definition of marriage) can find an answer via Powerset’s service at tinyurl.com/5qpcr9/.
San Francisco-based Powerset is hoping to advance the current generation of services that rely on keyword searches such as Google Inc, Yahoo Inc, Microsoft Corp and IAC InterActiveCorp’s Ask.com.
“The Wikipedia is becoming a microcosm of the most useful parts of the Web,” said Greg Sterling, an Internet analyst with Sterling Market Intelligence. “This offers a powerful way to find what you are looking for against this subset of the Web.”
Powerset is part of a promising generation of startups including Hakia, Wikia Search, Cuill and Twine that propose to make inroads in search despite the overwhelming domination by industry leader Google Inc. It is an ambitious goal that many Web sites have adopted over the years, only to fail to make much of an impact.
Powerset also offers adequately annotated ways for searching inside Wikipedia entries to find related concepts. Called “Factz,” these related ideas generate outlines, summaries and automated answers to users’ questions.
“Our system is a little more forgiving,” Scott Prevost, general manager of Powerset, said in an interview on Sunday. “It is not looking for hard-word matches. We are not searching for exact words, but concepts,” he said.
Powerset has said that the longer term plan is to read, linguistically analyze and index 20 billion documents on the Web, which will be a costly and ambitious undertaking.
Pell said his search engine will focus on “high value” Web sites, at least in its early days, and added that “even nailing Wikipedia” is success enough, given the encyclopedia’s popularity.
The search engine will be limited to Web search at first, although Powerset has contemplated adding specialty engines for things like images and video later, as well as targeting verticals such as health, product reviews and travel, he said.
“We have only shown the tip of the iceberg in language analysis,” he said.