Extractiv: Content Provisioning

February 7, 2010

A happy quack to the reader who alerted me to Extractiv. The company is in the “content provisioning business”, and I did not know what this phrase meant. I know about “telecommunications provisioning”, but the “content” part threw me. I followed the links my reader sent me and located an interview (“Quick Q&A on Extractiv”) on the AndyHIckl.com blog. It took me about a half hour to figure out that the interviewer and the interview subject seemed to be the same person.

The key points that pierced the addled goose’s skull were:

  • The service “helps consumers ‘make sense’ of large amounts of unstructured text. The method is natural language processing
  • Unstructured text is transformed into structured text for sentiment tracking and semantic search
  • The technology is “unique distributed computing platform makes it possible for us to crawl — and extract content from — zillions of pages at the same time. (Our performance is pretty unbeatable, too: we’re currently able to download and extract content from 1 million pages in just under an hour.)”
  • “Extractiv’s a joint venture between two companies: 80Legs and Language Computer. It’s really a great match. 80Legs offers the world’s first truly scalable web crawling platform, while Language Computer provides some of the world’s best — and most scalable — natural language processing tools.”

The company says:

Extractiv is a new kind of content provisioning service which is making the Web truly actionable. Rather than simply passively “monitoring” the Web, our industry-leading data harvesting and content extraction goes out and delivers the information that really matters to you and your business. With Extractiv, it’s easy to build semantically-aware applications – regardless if you’re a newcomer to the Semantic Web or a deep believer in the power of semantic metadata.

For more information you will want to read “Learning More about Swinly and Extractiv”. The company’s Web site is at www.extractiv.com. The company is in its alpha stage. More information when it becomes available.

Stephen E Arnold, February 8, 2010

No one paid me to write this. I think this company is in Dallas, and I don’t go to Dallas. Texas makes me nervous. I will report this to the US House of Representatives with the “this” meaning money and my nervousness about the Lone Star State.

Comments

2 Responses to “Extractiv: Content Provisioning”

  1. Extractiv: Content Provisioning | Digital Asset Management on April 8th, 2010 1:51 am

    […] Extractiv: Content Provisioning : Beyond Search. […]

  2. sperky undernet on April 20th, 2010 3:43 am

    more about 80legs “web crawling as a market”
    http://venturebeat.com/2010/04/19/80legs-crawl-package/
    “The free version will cover up to 100,000 pages per job, and one job at a time. Beyond that, 80legs is also rolling out a new pricing model, based on a monthly subscription fee. Once you want to go past 100,000 pages per job, pricing starts at $99 per month; there’s a $299 plan too.”
    http://venturebeat.com/2009/12/21/80legs-web-crawler-free/

  • Archives

  • Recent Posts

  • Meta