The DevX article on Classifier4J includes a good example of using Classifier4J for doing automatic text summary. I have to admit the example given makes it seem pretty impressive. I'm not sure everyone will get as good results as that (the summarising code is the ugliest in Classifier4J by far – I just wanted to see if it would work), but none the less summarising http://www.devx.com/xml/Article/16704/1954?pf=true
to:
The invention of database driver methodologies such as JDBC
and ODBC led to applications being loosely coupled with their back end databases,
allowing best-of-breed databases to be chosen—and swapped
out when necessary—without any ill-effect on the user interface.
Similarly, the decoupling of data and presentation in HTML—by using XML for the data and
XSLT for the presentation of data—has led to much innovation and flexibility,
not least of which is the ability to deliver a document as data in XML and deliver
custom styling for that document with different XSLTs.
A runtime engine would be present on the desktop, and servers would
be able to deliver the GUI to the browser with an XML document.
is pretty useful. It does demonstrate that the software might currently have a preference for using sentances too early in the article, though.