Text categorization for Internet content filtering

Abstract

Text Filtering is one of the most challenging and useful tasks in the Multilingual Information Access field. In a number of filtering applications, Automated Text Categorization of documents plays a key role. In this paper, we present two of that applications (Hermes and POESIA), focused on personalized news delivery and Internet inappropriate content blocking, respectively. We are specifically concerned with the role of Automated Text Categorization in these applications, and how the task is approached in a multilingual environment. Apart from the details of the methods employed in our work, we envisage new solutions for a more complex task we have called Cross-Lingual Text Categorization.