11
May
2008
|
02:45 AM
America/Los_Angeles

Search Engine Powerset Debuts Semantic Search/Navigation

I recently visited Powerset to get a look at the company's much buzzed-about search technology based on the semantic understanding of language. Powerset is not the next Google but it does have an interesting technology thanks to its dozens of noted academics in lingustics and artificial intelligence.

The first product is a hand-optimized use of its technology to search Wikipedia along with Freebase, an open-source database of information. The results are fascinating in that the search results provide a new way to navigate through subjects. You can see what Powerset calls "factz" similar to facts, which are terms drawn from the subject matter dispersed throughout the two databases, that highlight and summarize complex subjects.

It takes a lot of computing power and time for Powerset to process a web page and it generates a lot of metadata. Thanks to Moore's law and Powerset's computing architecture, this processing time will continue to shrink but right now it cannot be used to process the entire web in a similar way to that of the major search engines because of those constraints.

There are about 2.5m pages in Wikipedia which is a lot of information and a good size to demonstrate Powerset's technology. Wikipedia was chosen because of its open license.

I can think of many uses for Powerset's approach such as improved ad serving based on meaning rather than contextual keywords.

What will be Powerset's next product? I wonder how many types of searches require a semantic understanding? It'll be interesting to find out. In the meantime I encourage you to take Powerset for a spin.

Here is Powerset's news release:



Powerset, a company pioneering natural language technology, today announced the launch of its publicly available beta product that reinvents how users search and discover information from Wikipedia™.


Powerset’s breakthrough natural language technology is based on patents licensed from PARC (formerly Xerox 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.


This release is the first step in Powerset changing the way users search and consume web content. Unlike traditional search engines, which look for words, Powerset matches the meaning of the users’ query to the meaning of sentences.


Powerset currently searches content from leading free content providers:


Powerset searches over 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 the following helpful features:


Factz – When users enter a topic query, Powerset assembles a compact summary of interesting, and sometimes surprising Factz, extracted from pages across Wikipedia. (screenshot)


Dossiers – Powerset creates a summary of information found in Freebase and Wikipedia to give users a quick overview about a topic. (screenshot)


Answers – For many questions, Powerset automatically assembles an answer list from sentences in Wikipedia or data in Freebase. (screenshot)


Semantic Highlighting – The most relevant search results are highlighted based on the meaning of a users’ question. (screenshot)


Minibrowser – A result can be expanded to show the snippet in the context of the full Wikipedia article. (screenshot)


When consumers click on a search result, Powerset offers features that summarize long pages of content, allowing users to find and browse information quickly.


Article Outline – A navigational tool that follows users as they read Wikipedia articles (screenshot)


Summary of Factz – An automatically generated summary of the key Factz on the page, which often reads like the Cliff’s Notes™ for the article (screenshot)


Explore Factz – Offers a helpful guide of key relationships and topics in the page which can be clicked to highlight relevant Factz (screenshot)


Powerset’s technology improves the entire search and discovery experience by:


Allowing users to express themselves in the search box through keywords, phrases, or simple questions.


Providing more accurate search results on the page, often answering questions directly, and aggregating information from across multiple articles.


Offering a better way to digest and navigate content on Wikipedia quickly.


Quotes, attributable to Powerset executives:


“Wikipedia serves a fundamental human need – a single destination to find a broad range of information,” according to Barney Pell, Powerset co-founder and CTO. “This broad content base is a great way for us to showcase Powerset’s functionality while giving people a faster time to satisfaction.”


“Our first product has only touched the surface of what our technology will allow,” said Lorenzo Thione, co-founder and product architect. “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.”


“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,” said Scott Prevost, director of product. “This first product will make people’s search experiences on Wikipedia and Freebase easier, more natural and more relevant.”


Quote, attributable to Carla Thompson, senior analyst with Guidewire Group:


“Powerset’s new Wikipedia experience is an impressive achievement, and goes beyond what I expected to see from Powerset's first public product,” said Carla Thompson, senior analyst with Guidewire Group. “In many ways, it defines a new search category altogether and brings the power of semantics to mass consumers. Once users have experienced the usability and deep relevance of Powerset-enabled Wikipedia search, I imagine they’ll start demanding this level of intelligence from all content channels.”