Mind to Market

Monday, March 24, 2008

Killer Semantic Apps

Is coming up with a definitive application for demonstrating the utility of semantic analysis really that difficult? TextWise, a software development company in Rochester, New York, apparently thinks a good idea for this technology is worth at least the $1 million they are offering the winner of their SemanticHacker $1M Innovators Challenge.

The rules of this contest require the contestant to use, or propose to use, the SemanticHacker API, based on TextWise's Semantic Signatures® technology, to develop a software application for a specific industry vertical. Although it is up to the contestant to propose a vertical, TextWise suggests industries such as "healthcare or pharmaceuticals might be good places to start." Wonder who tipped them off?

As explained in TechCrunch, Semantic Signatures® uses natural-language processing to extract relevant terms from text then applies semantic analysis to automatically categorize Web pages. Not a bad idea, but the technology can be a bit flaky. Semantic Signatures® used Wikipedia as a reference; connecting the concepts extracted from the text and matching them to Wikipedia articles.

One of the cornerstones of the W3C specification for the Semantic Web is its use of Web Ontology Language (OWL), although OWL only specifies the format of the ontologies there is the assumption that human domain experts will be required to accurately develop an ontology. TextWise claims that ontologies developed in this way "do not align with customer needs and…rapidly become obsolete." Perhaps, but without some agreement on the ontology all you have is a folksonomy, which reduces its value in collaborative efforts.

The Holy Grail that drives the concept of semantic analysis is the ability for the software to do "connecting the dots" process that is normally done by humans. We humans can juggle a few thousand "dot" in our heads but connecting one to another, or maybe some complex combination of five to another twelve, gives most of us a headache. And when you start thinking about connecting a million or more dots, well, time to start thinking about a simpler project, like brain surgery.

Labels: , , ,


  • Hi Steve. Thanks for the comments on our Challenge and technology. I just wanted to elaborate on a few points.

    Our Semantic Signature technology at its core does not use Wikipedia data. In fact we indexed the entire Wikipedia database to demonstrate how Semantic Signatures work by returning Wikipedia related articles to a chunk of text.

    Also, we updated our technology page on www.semantichacker.com so the benefits, specifically as they relate to ontologies, are a little clearer. Our ontology is auto-generated, nothing is manual and therefore no agreement (as you mentioned in your post) would be necessary.

    Hope this helps clear any confusion.

    By Anonymous Rebecca, At 3:23 PM  

Post a Comment

Subscribe to Post Comments [Atom]


Create a Link

<< Home