16 | 16 | The new three-years long project concentrates on named entity and relation extraction from large texts. The aim of the project is to create tools for natural language processing which will allow to extract information about entities (personal name, location or organization, time, email or telephone number) and relations between these entities and to mine information based on author's style (author's education and sex, origin of the text – if the text is a machine translation). All the text characteristics mentioned above will be acquired by text analysis with use of tools of language analysis, machine learning techniques and stylometry. |