Special-text corpora are characterized by the use of domain terminology to convey meaning. It is therefore natural to investigate ways of taking advantage of domain terms in tasks such as information retrieval, summarization, and more general knowledge management problems associated with document corpora, such as document clustering. The use of terms instead of words holds the promise of leading to low-dimensional document representations, which make clustering more feasible and summarization by extraction more effective. In this talk, I will discuss initial investigations on the use of automatically extracted terms in retrieval and summarization.

-------------------
Evangelos Milios received a diploma in Electrical Engineering from the National Technical University of Athens, Greece, and Master's and Ph.D. degrees in Electrical Engineering and Computer Science from the Massachusetts Institute of Technology, Cambridge, Massachusetts. Since July of 1998 he has been with the Faculty of Computer Science, Dalhousie University, Halifax, where he is Professor. He was Director of the Graduate Program (1999-2002). He is a Senior Member of the IEEE. His current research activity is centered on Networked Information Spaces, Web information retrieval, and aquatic robotics.