Text mining in a digital library

Abstract

Digital library strive to add value to the collections they create and maintain. One way is through selectivity: a carefully chosen set of authoritative documents in a particular topic area is far more useful to those working in the area than a huge, unfocused collection (like the Web). Another is by augmenting the collection with high- quality metadata, which supports activities of searching and browsing in a uniform and useful way. A third way, and our topic here, is to enrich the documents by examining their content, extracting information, and using it to enhance the ways they can be located and presented.