Linguistically based requirements engineering - The NIBA-project

Usually, the development of an information system (or some part of it) starts with an requirements elicitation, collection and analysis phase that results in a set of natural language requirements specifications. These then serve as a source for the phase of conceptual design where a semantic model of the given universe of discourse is established using modeling and representation concepts like UML [1] or former approaches like OMT [6] or even the classical Entity-Relationship Model (or one of its numerous extensions). These approaches mainly are thought for enhancing the validation of the collected requirements as well as for providing a more formal basis for the subsequent system design and realization steps. Indeed, they form a considerable help for the designer, however they are no aid in collecting and cataloguing information. Moreover, these approaches require a level of abstraction end-users (i.e., the ‘requirement suppliers’) often are not willing or not able to cope with.