Models and technologies for the extraction of aggregated knowledge to control processes of the retrieval of non-structured information

To control the retrieval and to arrange the retrieval of non-structured information in large-scale collections of texts in natural languages, crucially new models of aggregated representation of knowledge about their topic and content (semiotic and semantic characteristics of the text) are proposed. Based on the proposed models, techniques of computational extraction and use of knowledge about the topic and content of text collections are developed. The proposed models and techniques are based on formation of secondary information resources characterizing the topic and content of particular texts in natural languages.