Jan Hein finished his Master thesis at the end of 2008 with the topic: ‘Specification and implementation of information units for qualifying knowledge modelling’ (Thesis in German). Automated extraction of text chunks out of Wikipedia without loosing structure and context is next to semantic annotation the main focus of his work.
The specification of information units can be found here: http://qkai.org/spec/2008/10/
The Wikipedia Extractor prototype is available under http://qkai.org/WikipediaExtractor
