Information Service Engineering

Information Service Engineering (ISE) focuses on researching, developing, and refining symbolic knowledge representations, sub-symbolic AI technologies, and their hybrid integration. Our goal is to advance state-of-the-art methodologies by exploring their applications in real-world contexts. A core focus is the interplay between symbolic and sub-symbolic AI, investigating how knowledge graphs and ontologies can enhance deep learning and language models, and vice versa. ISE conducts applied research in semantic indexing, aggregation, linking, and retrieval for comprehensive, heterogeneous, and distributed data sources. Solutions for knowledge extraction, semantic annotation, semantic and exploratory search, recommender systems, and question answering are developed within this context. Beyond methodological research, ISE engages in applied projects across cultural heritage, digital humanities, materials science, and research data management.

ISE is structured in two departments: Knowledge Graphs (ISE-KG) and Machine Learning (ISE-ML).