I don't see many people recommending already-written papers about Wikimedia projects on this mailing list, so I thought I'd recommend one.

http://afflatus.ucd.ie/Papers/ecai2006.pdf

The paper is about "a system for dynamic lexicon growth that harvests and semantically analyses new lexical forms from Wikipedia, to automatically enrich WordNet as these new word forms are minted."

It's an interesting read about semantic information that can be extracted from Wikipedia as-is. A useful derivitive use of what we're putting together.

A second paper also covers the semantic extraction of a knowledge base of 5 million facts from Wikipedia. "The facts have been automatically extracted from Wikipedia and married with WordNet, using a carefully designed combination of rule-based and heuristic methods described in this paper." (http://www.mpi-inf.mpg.de/~suchanek/publications/www2007.pdf)

Credit to Chris Bizer for posting the former paper, and Sören Auer for the latter on the Dbpedia-discussion mailing list.