ExANT

The “ExANT: Extraction of Requirements from Natural Language Text” project aims to demonstrate whether and how natural language processing (NLP)—a subfield of AI—can be used to reliably automate this translation. The consortium consists of the Institute of Space Systems at the University of Stuttgart, the space systems company OHB System AG, the technology firm OHB Digital Services, and the software technology specialist BSSE, which also coordinates the consortium. Various NLP tools—including several open-source systems—will be applied to natural-language requirements from real-world space projects.

Among other things, the stakeholders want answers to the following questions: How much time and money can be saved? How can errors made by AI during translation be detected or avoided? Can NLP tools significantly improve the quality of requirements? This applies, for example, to requirements that are poorly worded or incompletely described, which can lead to delays and additional costs.

The project is funded by the Federal Ministry for Economic Affairs and Energy as part of the National Space and Innovation Program and is managed technically and administratively by the German Space Agency at the DLR. The work is scheduled to be completed by the end of November 2023.