Exploration of Text Collections with Hierarchical Feature

Document classiication is one of the central issues in information retrieval research. The aim is to uncover similarities between text documents. In other words, classiication techniques are used to gain insight in the structure of the various data items contained in the text archive. In this paper we show the results from using a hierarchy of self-organizing maps to perform the text classiication task. Each of the individual self-organizing maps is trained independently and gets specialized to a subset of the input data. As a consequence , the choice of this particular artiicial neural network model enables the true establishment of a document taxon-omy. The beneet of this approach is a straightforward representation of document similarities combined with dramatically reduced training time. In particular, the hierarchical representation of document collections is appealing because it is the underlying organizational principle in use by librarians providing the necessary familiarity for the user. The massive reduction in the time needed to train the artiicial neural network together with its highly accurate clustering results makes it a challenging alternative to conventional approaches. 1 Introduction During the last years we witnessed an ever increasing ood of miscellaneous digital information originating from very diierent sources. Powerful methods for organizing, exploring , and searching collections of textual documents are thus needed to deal with that information. Classical methods do exist for searching documents by means of keywords. These methods may be enhanced with proximity search function-ality and keyword combination according to Boole's algebra. Other approaches rather rely on document similarity measures based on a vector representation of the various texts. What is still missing, however, are tools providing assistance for explorative search in text collections. Explorative search