Multimedia data integration and processing for E-Government

Knowledge management has become a challenge for almost all E-government based applications where one of the main problem is the efficient management of great amounts of data. In order to efficiently access the information embedded in very large document repositories, techniques for semantic document management are required. They ensure improvement for a large and intense process of dematerialization and aim at eliminating or at least reducing, the amount of paper documents. In this work, we present a novel model of digital documents for the improvement of the dematerialization effectiveness. This model represents the starting point for an information system that is able to manage the document streams in an efficient way. It takes into account E-government applications needs like the compliance with the laws and regulations in force and the adaptability to evolving technologies. At the best of our knowledge, the proposed model is one of the first attempts to give a single and unified characterization for the management of multimedia documents, pertaining to a bureaucratic domain as the E-government one, on which semantic procedures are used for the transformation of non structured documents (pertaining to specialized domain) into structured data, suitable for automatic processing. Furthermore, an architecture for the management of documents life cycle is proposed, which provides advanced functionalities for semantic processing, such as giving formal structure to document informative content, information extraction, semantic retrieval, indexing, storage, presentation, together with long-term preservation. Keywords-Ontology Learning, Ontology Population, Natural Languages Processing