Data Management and Enrichment
The focus of the department is on the exploration and development of tools and systems alongside the data life cycle. The main areas of research are (1) the development of NLP methods for automated information extraction from documents, (2) the development of methods to simplify the automated exchange of heterogeneous data between different stake holders, (3) utilization of data outside of their initial acquisition context with the help of semantic metadata descriptions, (4) development of methods and systems to efficiently manage, visualize, and explore large volumes of raster data, timeseries data, and point cloud data in different execution environments and by leveraging modern hardware, and (5) the development of resource-efficient AI methods (i.e., Green AI) for resource-constrained execution environments.
The department is divided into three working groups:
- Metadata Management
- Information Extraction and Interoperability
- Data Access and Processing