next up previous
Next: The Transition Point Technique Up: A Comparative Study of Previous: Clustering on Narrow Domain

Feature Selection Techniques

Up to now, different Feature Selection Techniques (FST) have been used in the clustering task; however, clustering abstracts for a narrow domain implies the well known problem of the lackness of training corpora. This led us to use unsupervised term selection techniques instead of supervised ones. In the next subsection we describe briefly the transition point technique. In the final subsection we explain all the other techniques used in our experiments.


David Pinto 2006-05-25