12 Comments

Summary:

It has been a long time coming, but Powerset, a San Francisco-based contextual-semantic search engine has finally launched. I urge you to try it out, for this is quite an impressive search effort, despite the fact it is currently limited to searching Wikipedia along with some […]

It has been a long time coming, but Powerset, a San Francisco-based contextual-semantic search engine has finally launched. I urge you to try it out, for this is quite an impressive search effort, despite the fact it is currently limited to searching Wikipedia along with some supplementary results from Metaweb’s Freebase. I think it has made Wikipedia much easier to use. I like how you can do more topic-based searches and get a holistic view of the information you’re looking for. Danny Sullivan over on Search Engine Land has an elaborate and fantastic indepth review of Powerset, and that frankly obviates the need for any other review.

That said, Powerset faces an uphill climb, especially when it comes to consumer mindshare. I think Google has become so synonymous with search that it is virtually impossible for a newcomer to establish a toehold. Powerset’s approach is different, and its tactic of applying its technology to specific content repositories such as Wikipedia is smart. But will they (web searchers) come and use Powerset?

At our recent GigaOM PM event, Chad Walters, director of engineering, search and platform at Powerset, gave a talk about how his company was using Hadoop and other clever technologies to meet its immense infrastructure needs. Here are some bits from OStatic’s live blog coverage of the event:

Powerset applies deep natural language processing (based on technology licensed from Xerox PARC), which means the company needs 100 times more processing horsepower than a simple keyword searching and indexing. Powerset uses a distributed database system called HBase in tandem with Coral, its Document Processing System. Coral uses Hadoop as its job control machine. Powerset uses 92 eight-core machines to do processing.

  1. [...] do more topic-based searches and get a holistic view of the information you’re looking for.–Powerset Is Live – GigaOM There is no way to look at Powerset today and determine if it can be as disruptive to search as [...]

    Share
  2. A lot of people seem to mistake that new search companies need to index the entire web in order to have a viable business. This is obviously incorrect.

    Share
  3. Pwb you are right. many people submit thei websites into old search engines in the market. this is ok but they can try submitting in the new ones too.

    Share
  4. [...] So is Om Malik, who notes that Powerset performance is a bear [...]

    Share
  5. I tried: What is the longest lake in the world?
    If powerset understands semantics, why does it return so many unrelated results?

    Share
  6. First of, I have to agree Google is an ROI problem. But can someone be better it by providing a better search by Investing in search. I doubt it. But maybe they don’t want to do that.
    In any way it seems to try to be a better recognizing system, no understanding. No idea what information is and how it is processed in the brain to form understanding, same goes for Google.

    For someone interested in the topic try:
    http://psych.colorado.edu/~oreilly/

    While we have some disagreements it’s a good start to see where we stand today.

    But maybe it I need to relax, found some mistakes in the underlying articles, and have more coffee.

    Share
  7. @ Kumar,

    I agree with you. I have been doing some random searches this morning and well, things have not been coming back as I expected. I think this needs a couple of days of rapid testing before making a final judgement call.

    Share
  8. From a quick look at Powerset today, I think it has two problems: firstly, the kind of approach Powerset *appears* to be taking performs *worse* than keyword search; and secondly, Google is, in a low-key way, already implementing a “natural language” approach to search that works *better* than keyword search.

    For anyone interested, I’ve put some more details on my blog @

    http://www.psynixis.com/blog/2008/05/12/the-two-big-problems-for-powerset/

    Share
  9. Random searches indicate that it should be dead in a few months. Try, for instance, “American civil war death toll” with Powerset, then with Google.

    And I’m no SEO master, but every other search engine seems to find Daily Paws just fine. Powerset…. not so much.

    Share
  10. [...] article. It works quite well as an advanced search tool for a single site like Wikipedia. [via GigaOm] Bookmark this Post Now!   [?] Do you want to get daily computer tips and web 2.0 info? [...]

    Share

Comments have been disabled for this post