When writing a blog post, we create links to Wikipedia articles because it is an easy and quick way to provide information to readers, without having to go into too many details. It is not always possible to find, link or even know about all the articles that might be related to the post's topic.
Zareen Syed, one of my colleagues, recently presented a paper at ICWSM on "Wikipedia as an Ontology for Describing Documents". This paper talks about how Wikipedia articles can be used to associate the concepts with a given document. Over at SemanticHacker a similar approach is taken to find the "Simplified Semantic Signatures" for a document. TextWise, is offering upto a Million Dollars in funding to any idea that can
Turn on the Power of Semantics
I liked their demo, API and tools they provide. Inspired by the effectiveness of Wikipedia in describing documents and my desire to play with widgets, I decided to mash these two goals together. If you look on the right column of this blog, you would find a small widget that displays the related Wikipedia entries for a given page/post and is powered by the SemanticHacker API. This was a quick hack and the system can be improved by
- focusing on the post content alone (right now I just pass the current page URL).
- Adding more features, like identifying people, places etc and highlighting them differently
While I dont think this by itself might qualify for a $1 Million challenge, I think there might be something interesting here. I have a couple of ideas around this and scant time to work on it. Finally, in true Web 2.0 spirit -- not sure what, if any, is the business model (I just built this for kicks; semantic hacker is looking for a bizplan from participants).
I dont think that the widget itself is ready for prime time -- it was an evening hack. But if you would like to play with it leave me a note in the comments and I shall provide a link to you so you can install it on your blog.