This line of work looks at the task of extracting various information from textual input. By identifying entities and the relations between them, it is possible to derive a structured ontology representation from these unstructured documents.

By integrating external knowledge originating from taxonomies, ontologies, or knowledge graphs into the information retrieval process, we aim to improve the outcomes in terms of relevance and completeness.

We investigate hybrid AI systems that incorporate both Semantic Web Technologies (SWe) and Machine Learning (ML). These “SWeML” systems are benefiting from both technologies by overcoming respective shortcomings in order to fulfill complex tasks.

We present our research on the development, deployment, and usage of collections of interdependent natural language processing services. We aim at the best quality of processing and robustness of the deployed services.

In this area of research, we are investigating approaches to address the Named Entity Recognition (NER) task as well as how Knowledge Graphs can be used to improve upon and circumvent the shortcomings of existing models.

This line of work looks into challenges related to recognizing words in a text as specific entities, understanding their types and linking them to a knowledge graph.