The elaboration of an operational framework for the representation of concepts, their combinations and contextual meaning to improve the automated extraction of semantical information from unstructured documents

Due to the explosive increase of the number of documents on the internet, the available information for an internet user has grown enormously. However, retrieving the needed documents from the enormous quantity available is a problem of which its importance is recognized more and more. Since the majority of such added documents are unstructured, the question emerges of whether it is possible to extract in an automated way semantic or content sensitive information. To accomplish this, a computer should be able to understand the way in which concepts combine in a text. One of the deep problems which is mentioned often in the literature on concepts is the problem of the 'conjunction of concepts'. In classical logic and in the actual semantic web, combinations of concepts are seen as intersections of classes that represent two individual concepts. There are however many simple combinations of concepts that cannot be analyzed in this symplistic manner. The proposed project aims at elaborating a mathematically drastic new way of representing concepts starting from a structural generalization of quantum mechanics and with the purpose of facilitating the automatic extraction of information from unstructured documents.