Powerset, a San Francisco-based company that pioneers natural language technology, announced Sunday the launch of its search engine that uses “natural language” to organize and search documents. Instead of searching the entire Web, the search engine initially will be confined to Wikipedia.

The service that adds a whole new dimension to searching for information from Wikipedia opened up to the masses on Monday.

Based on the patents licensed from PARC (formerly Xerox PARC) and Powerset’s proprietary research, Powerset claims the beta product will enable users reinvent the way they search and discover information from Wikipedia.

“We have focused on making Powerset able to read and understand documents on the web as part of a broader vision to change the way people interact with technology, Scott Prevost, general manager and director of Powerset's product, said in a statement. “This first product will make people’s search experiences on Wikipedia and Freebase easier, more natural and more relevant.”

By using language rather than keywords, Powerset’s demos suggest the company has developed powerful new capabilities, delivering query results based on meaning, rather than words, delivering valid answers and improving the search experience.

With the help of its natural language technology, Powerset has created an index of search results from Wikipedia and Metaweb Technologies' Freebase, a Web-based structured database of information, by studying the meaning of entire sentences rather than the relationship between words. It also allows users to type queries as fully formed questions like “Who did Henry VIII marry?” or “What did the FDA ban?” or “What did Bill Clinton sign?”

"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.

For now, Powerset's index is very limited, consisting only of millions of pages from Wikipedia and Freebase, but the company plans to increase its scope gradually by indexing other “data sets” beyond Wikipedia and Freebase. News articles and blog posts may be next to compliment its search engine, the company said.

“Our first product has only touched the surface of what our technology will allow,” Lorenzo Thione, co-founder and product architect, said in a statement. “Our team of computational linguists, computer scientists and engineers, together with the PARC technology we licensed, has allowed us to develop a solid platform to begin to change the way people consume content.”