The course introduces the student to the derivation of information and knowledge from the analysis of a collection of documents in natural language, which refers to almost all generated and stored data.
The student will be trained in content analysis on enriched document representation models to address specific applications in different domains.
Special attention will be paid to the extraction of relevant information, the determination of the contextual polarity (sentiment) of a content, and the automatic response to questions posed directly in natural language.
In short, the goal is to answer fundamental questions in the development of interfaces, decision support environments, and access to new knowledge.