Semiautomated Development of Textual Requirements: Combined NLP and Multidomain Semantic Modeling Approach

This paper presents a framework for the semiautomated development of textual requirements for the building construction industry, a domain in which quality of textual requirements has a direct bearing on the avoidance of unnecessary project losses and failures. The proposed framework is novel in three respects. First, it employs a combination of natural language processing (NLP) and template matching to restrict the range of ways in which textual requirements can be stated. Second, knowledge-based models work hand-in-hand with the NLP and templates to help designers fill in the details of a model that might be missing. Third, we envision the proposed approach being part of a multidomain semantic modeling and reasoning framework that includes the building construction domain and its connections to processes for project management and governance. To demonstrate the potential of the proposed approach to the practical development and construction of building systems, we developed a prototype software tool-the framework for linking ontology objects and textual requirements (FLOOR)-and procedures for the validation of individual textual requirements and groups of textual requirements related to construction tasks.