Print

Information Extraction and Interoperability

Information and data exchange is essential for communication in a wide variety of areas; for example, between companies regarding production data or between research institutions regarding measurement and survey data.

This exchange is made more difficult by the fact that information and data are available in incompatible and sometimes not even machine-readable formats. For example, they are often stored in - from the computer's point of view - unstructured or semi-structured documents.

In order to simplify the exchange of information and to make unstructured data accessible for further automated processing, the working group is therefore pursuing two main research areas:

• Information extraction (primarily (further) development of natural language processing methods on documents)
• Interoperability, especially at the semantic level
  • Development of methods and tools for the (semi-)automatic creation and extension of semantic models as a basis for interoperability
  • Development of methods and tools for automatic matching of needs and capabilities/offers, for example along supply chains, recycling chains, etc.

Various projects of the group are presented in more detail on the subpages.