Automatic Information Extraction from Text-Based Requirements

Requirements form the legal basis for many development pro-jects. They are usually exchanged between customer and supplier in the form of product and requirements specifications and re-quire a subsequent integration effort into the corresponding requirements management solutions. Especially for small and medium-sized enterprises (SME), which mainly use office solutions for the management of requirements, this involves a very high integration effort, which is why this is usually only partially managed or not managed at all. Software solutions available on the market already offer support, but they are too expensive or complex, especially for small companies. The project DAM4KMU, funded by German Federal Ministry for Education and Research (BMBF), addresses this challenge and by enabling SMEs from Germany to integrate requirement documents automatically into existing requirement structures with the help of NLP-based techniques. For this purpose, the documents to be processed are divided into semantic roles, which can then be transferred into a semantic data structure. This in turn enables an automatic linking of the requirements and system components, which reduces the manual effort and avoids possible errors.