Powerset has launched a public beta of its Wikipedia search engine that brings a new, rich semantic dimension via natural language query processing to Wikipedia, greatly improving the search and reading experience.

Powerset’s engine, based on techology licensed from PARC, has read 2.5 million Wikipedia pages and extracted “meaning” from the sentences, creating a navigation and semantic layer on top of the popular Web encyclopedia.

Powerset has also indexed Freebase, Metaweb’s evolving, open database of structured information. The search result page presents Factz, a summary of key information extracted from Wikipedia pages. It also shows a tag cloud of things and actions found by its linguistic analysis engine on the page.

Powerset has said that the longer term plan is to read, linguistically analyze and index 20 billion documents on the Web.