An Automatic Intelligent System for Document Processing and Fruition

With the increasing amount of documents available on-line, the need for intelligent
\ndigital libraries, that allow to automatize the document processing tasks and to suitably
\norganize and make available the documents so as to provide personalized and focused access,
\nbecomes more and more pressing. This paper proposes an integrated system that merges
\nintelligent modules covering all the phases involved in a document lifecycle, from acquisition,
\nto processing, to information extraction, to personalized fruition for final users. The role and
\npossible cooperation of Machine Learning and Data Mining techniques in the system is
\nhighlighted and discussed, along with their importance to provide effective support to both the
\nbuilding and the fruition of the Digital Library and the underlying knowledge base.