Information Extraction from Text
Information extraction aims at the acquisition of structured knowledge that is buried in large amounts of natural language text. The main goal of our work in this area is to generate actionable knowledge to be exploited in real-world problems or business processes. Among other challenges, this requires knowledge aggregation in order to discover hidden structures and relations, and knowledge integration in order to guarantee interoperability with different knowledge sources.
We are mainly (not exclusively, though) dealing with text from the biomedical domain and social media. In our current research, we apply methods from probabilistic graphical modeling, deep learning, text mining and ontology learning.