Multi-aspect Document Content Analysis using Ontological Modelling

Existing methods of information extraction from web documents are usually based on a single aspect of the document or its contents such as the code, textual features or visual features. Due to the great variability of the available online documents, it seems reasonable to combine multiple kinds of analysis in order to use all the available knowledge for identifying a particular information in the document. In this paper, we propose an ontological document model that allows to integrate the results of the analysis of different document aspects. We propose a generic architecture of an information extraction system based on this model and we show its applicability on a practical example.