Powerset just launched its publicly available beta product minutes ago.

Can’t wait to see it? Watch the Demo Video now!

This is the long-awaited debut of the search engine that reinvents how users search and discover information from Wikipedia™. Powerset’s breakthrough natural language technology is 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.

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.
We’ve been hearing about Powerset for a long time, so I thought that on this auspicious day a quick flash-back was in order.

Let’s go back to October 2nd, 2006.

Writing for Venture Beat, Matt Marshall makes this announcement:

Bold start-up, Powerset, about to raise $10M to take on Google

We’ve been hearing about a new Palo Alto start-up called Powerset, which says its search technology is better than Google’s. The start-up, led by artificial intelligence and natural language expert, Barney Pell, has been pitching its business idea aggressively to Silicon Valley venture firms. The company says its idea is so promising it merits an extremely high valuation from the get-go, according to several sources.

In the ensuing “blogstorm,” Pell posted an exhaustive summary of his vision on his blog:
“Powerset and Natural Language Search”

Just two days later, VB posts a lengthy update, too long to republish now.

Here is an excerpt: More on Powerset, the secretive search engine.

By Matt Marshall October 4th, 2006

We promised to bring you more on Powerset, that secretive company that wants to better Google with a new kind of search. Powerset is going after the holy grail. It is called “natural language” search, or understanding language as it is actually spoken — and that is something that has defied everyone until now, even the Google guys.Take, for example, if you type “Books by Children” into Google’s search box. Google essentially drops the word “by” and looks for all the pages that are relevant to “books” and “children.” That’s because the English language is so idiomatic that no engine has been able to understand meaning within sentences. Some companies, most famously Ask Jeeves, have tried. You prompted Ask Jeeves’ engine with a question ending with question mark, but as soon as your question got remotely complex, Ask Jeeves broke down because its engine could only answer specific questions its engineers had prepped it for.

Google, while acknowledging that natural language is a big goal, hasn’t made very big advances in the area. This makes sense, because people have become trained to use “a grunting pidgin language,” as Powerset’s Barney Pell puts it. Pell calls this “Keyword-ese.” Many search engines recognize some advanced query syntaxes — for example to find Web pages that don’t carry certain words, or that have two words within a certain number of words of each other, and so on.But people have a hard time remembering these advanced syntaxes, and each search engine has a different syntax. Finally, Google’s core engine has been built around this keyword-ese language, and it is hard to change all of the layers that have been built around it.

Which is where Pell comes in. Powerset is trying to solve the natural language problem, by making its core engine understand concepts of time, place, sentiment and other intent…They are also giving no dates about when it will be released.

So, is this so much hype?

The very next day, on October 5th, search expert Danny Sullivan became an official detractor with his response to the news:
“This is a rant. It’s a rant from over 10 years of watching people trot out natural language search as the “killer” solution to the current state of search, something that’s happening once again with Powerset. That’s a search engine you can’t even use at the moment, but the hype will no doubt continue. To counteract that, my thoughts on and some history about natural language search.”

There follows a very long rant going back in time to 1995, which we don’t need to republish here.

Now, fast forward to May 12, 2008

Houston, we have lift-off!

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.

Here it is - the new Powerset Homepage

Powerset currently searches content from these leading free content providers:

o Powerset searches over 2.5 million Wikipedia topics in English

o 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:

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

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

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

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

o Minibrowser – A result can be expanded to show the snippet in the context of the full Wikipedia article. When consumers click on a search result, Powerset offers features that summarize long pages of content, allowing users to find and browse information quickly.

o Article Outline – A navigational tool that follows users as they read Wikipedia articles

o 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

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

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

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

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

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

Congratulations on a successful launch!

Here are some Quick FAQs about Powerset:

Why is Powerset search limited to Wikipedia?

Wikipedia is a primary destination for millions of people worldwide who want to find high-quality, detailed information on a wide array of topics. By initially focusing on the Wikipedia collection, Powerset showcases how our technology not only improves search results, but provides new ways to aggregate, summarize and navigate information. Of course Wikipedia is only a starting point. In the coming months, Powerset will expand our product offerings with additional premium content and exciting new features.

What is Freebase?

In addition to Wikipedia, Powerset provides instant answers and dossiers from Freebase, an open, community developed database of the world’s information provided by Metaweb.

What does the name “Powerset” mean?

In mathematics, the powerset of a set S, usually written P(S), is the set of all possible subsets of S. You can read more on the powerset page.

What are Factz?

Factz are concise representations of information extracted from sentences. They are represented in three parts: the subject, relation and object (e.g. Oswald shot JFK). Factz are one way that Powerset represents the meaning of a sentence. Of course, Factz do not always represent truth, but rather propositions that are asserted in the text of Wikipedia.

On the search results page, you will often see Factz for general topic queries. These Factz are collected from pages across Wikipedia. Click a word in one of the three columns to see the sentences that support the selected fact.

On a particular topic page, you can see the Factz extracted from the given page in the outline. Click on one to scroll directly to the sentence from which the fact was derived.

And now, to wrap this post up, I have my own question for Powerset: 

This entry was posted on Sunday, May 11th, 2008 at 11:02 pm and is filed under News, Reviews. You can follow any responses to this entry through the RSS 2.0 feed. You can leave a response, or trackback from your own site.

Sphere: Related Content