I started to work on a small project on my off time, its a semantic web project based on the use case below. I started looking into any applications that are currently available to the public and found 2 projects that currently attempt to do what I want to do but come short of it. The idea, if your too lazy to read the below post; A document parser that will highlight interesting items (‘interesting’ is defined by key words of places, people, and things) Once the “interesting” items are hihglighted he user can hover the highlighted word and see a short description of the item, or present the user with a list of links that might be of some use.
Since i see no point in reinventing the wheel, I found Gnosis and SemanticHacker.com. Gnosis has a great natural language processor and can accomplish the requirement to find “interesting” items but dosnt provide useful articles. Gnosis instead send you to a google result page (pretty lame but its a start). On the other hand SemanticHacker.com has come up with a API that basically does both the Natural Language Processing and the relevance articles but has two drawbacks. 1. The NLP sorta sucks, well its not as good as the Gnosis one. 2. Articles of interest are mined from Wikipedia which might not be up-to-date or might be misleading. 3. No FIrefox plugin.
So what am i going to do now? Easy. I will check out the API that SemanticHacker has released and work on two things. 1. Create a Firefox plugin for it. and 2. Expand on the Knowledge Base the system references. Move from a wikipedia setting to a flickr (look for tagged relevant images) and a news RSS feeds.