CORDULA – Com­pens­a­tion Of Re­quire­ments De­scrip­tions Us­ing Lin­guist­ic Ana­lys­is

CORDULA allows the indicator-based detection and compensation of inaccurate and incompletely described software requirements. Since the vision of OTF Computing is to have the software needs of end users in the future covered by an automatic composition of existing software services, we focus on natural language software requirements that end users formulate and submit to OTF providers as requirement specifications. These requirements serve as the sole foundation for the composition of software; but they can be inaccurate and incomplete. Up to now, software developers have identified and corrected these deficits by using a bidirectional consolidation process. However, this type of quality assurance is no longer included in OTF Computing – the classic consolidation process is dropped.

This is where CORDULA picks up, dealing with the inaccuracies of freely formulated software design requirements. The CORDULA system recognizes and compensates language deficiencies (e.g., ambiguity, vagueness and incompleteness) in requirements written by inexperienced end users. CORDULA supports the search for suitable software services that can be combined in a composition by transferring requirement specifications into canonical core functionalities. This way, CORDULA provides the first-ever method for holistically recording and improving language deficiencies in user-generated requirement specifications by dealing with ambiguity, incompleteness and vagueness in parallel and in sequence. Using linguistic indicators makes it possible to optimize the individual text quality in a data-driven and needs-oriented manner by deviating from the classical text analysis pipeline: Its distinguishing feature is the ad hoc configuration of the compensating pipeline, triggered by the deficiencies that On-The-Fly Computing detected in the requirement specifications of end users.


If you have any questions regarding CORDULA, please, contact the research staff from the Subproject B1