Hierarchies are becoming increasingly popular for the organization of text documents, particularly on the Web. Web directories, such as the Yahoo! Directory and the Dmoz Directory, are typical examples. Along with their widespread use, comes the need for automated classification of new documents to the categories in the hierarchy. The Software and Knowledge Engineering Laboratory of NCSR “Demokritos”, in the framework of the European Network of Excellence PASCAL, has co-organised with the University of Grenoble a challenge, in order to assess and promote the state-of-the-art in this research area. Participation in the challenge has exceeded the expectations of the organizers and has included research teams from many countries around the world. The competition was intensive and fruitful, judging from the results achieved by the top-scoring methods. In this presentation, we will describe the main aspects of challenge, we will provide an overview of the methods that participated and present a comparative analysis of the results.
Web site of the challengehttp://lshtc.iit.demokritos.gr/Talk slides in pdf [~1,4MB]http://www.iit.demokritos.gr/docs/seminars/iptseminars-2010-04-kosmopoulos.pdf