06070130

a

06070130 Ciesielski, Krzysztof Borkowski, Piotr K{\l}opotek, Mieczys{\l}aw A. Trojanowski, Krzysztof Wysocki, Kamil Wikipedia-based document categorization. Bouvry, Pascal (ed.) et al., Security and intelligent information systems. International joint conferences, SIIS 2011, Warsaw, Poland, June 13--14, 2011. Revised selected papers. Berlin: Springer (ISBN 978-3-642-25260-0/pbk). Lecture Notes in Computer Science 7053, 265-278 (2012). 2012 Berlin: Springer EN

doi:10.1007/978-3-642-25261-7_21

Summary: A novel method of text categorization for Polish language documents, based on Polish Wikipedia resources is presented. The distinctive feature of the approach is that document labelling can be performed with no additional categorized corpora. Experiments with two different types of document semantic disambiguation have been performed, and evaluated according to the several quality metrics.