Lightweight validation of natural language requirements: a case study

The authors report on their experiences of using lightweight formal methods for the partial validation of natural language (NL) requirements documents. They describe a case study based on part of NASA's specification of the Node Control Software of the International Space Station, and apply to it their method of checking properties on models obtained by shallow parsing of natural language requirements. These experiences support the position that it is feasible and useful to perform automated analysis of requirements expressed in natural language. Indeed the authors identified a number of errors in their case study that were also independently discovered and corrected by NASA's IV and V Facility in a subsequent version of the same document. The paper describes the techniques used, the errors found, and reflects on the lessons learned.