Digital and algorithmic processing of text collections (in Greek)

The object of this work is the processing of text collections so that their contents, i.e. theirunstructured information are transformed into knowledge. More specifically, the processingof text collections has a dual dimension. The first dimension concerns declarativeknowledge, i.e. knowledge of entities (e.g. objects, events), and is related to the digitalprocessing of texts in order the unstructured data they contain to be transformed intostructured data. The second dimension concerns procedural knowledge, i.e. the knowledgeto perform a task and is related to the strict definition of a sequence of steps. In otherwords, creating an algorithm that explains a process. The implementation of the above willbe done by using digital tools: a) computational linguistics (e.g. Antconc) b) spreadsheets(e.g. excel) and c) graphical representation of knowledge (e.g. yEd).