Powerset is offering a new way to search Wikipedia -- with natural-language technology and conversational phrasing instead of keywords like Google uses.
The Powerset tools unveiled Sunday are available in beta and based on patents licensed from PARC and Powerset's proprietary research. The technology, which can be applied to any topic and any domain, reads and extracts meaning from every sentence in Wikipedia.
Unlike traditional search engines, which look for words, Powerset matches the meaning of the user's query to the meaning of sentences. Powerset proclaimed the release is the first step in changing the way users search and use Web content.
"Powerset's understanding of content on pages and the way they are presenting results is interesting. Powerset is organizing context and content in helpful ways," said Greg Sterling, principal analyst at Sterling Market Intelligence. "But it only applies to Wikipedia -- Powerset is not indexing the broader Internet. So you can't really get an apples-to-apples comparison with broader search tools."
A Different Way to Search
While a direct comparison with Google may not be possible, Powerset offers some statistics to consider. The tool searches content from leading free-content providers, including more than 2.5 million Wikipedia topics in English. For many questions, Powerset returns answers from Freebase, an open, shared database of the world's information.
Powerset's search-results page includes a cadre of features, including Factz, dossiers, answers, semantic highlighting and a minibrowser. When users enter a topic query, Powerset assembles a summary of Factz extracted from pages across Wikipedia. Powerset also creates a summary of information found in Freebase and Wikipedia to give users a quick overview about a topic.
The most relevant search results are highlighted based on the meaning of a user's question, and a result can be expanded in a minibrowser to show the snippet in the context of the full Wikipedia article.
If...

More...