Ontology-Based Natural Language Processing for Process Compliance Management

Process compliance with relevant regulations and de-facto standards is a mandatory requirement for certifying critical systems. However, it is often carried out manually, and therefore perceived as complex and labour-intensive. Ontology-based Natural Language Processing (NLP) provides an efficient support for compliance management with critical software system engineering standards. This, however, has not been considered in the literature. Accordingly, the approach presented in this paper focuses on ontology-based NLP for compliance management of software engineering processes with standard documents. In the developed ontology, the process concerns, such as stakeholders, tasks and work products are captured for better interpretation. The rules are created for extracting and structuring information, in which both syntactic features (captured using NLP tasks) and semantic features (captured using ontology) are encoded. During the planning phase, we supported the generation of requirements, process models and compliance mappings in Eclipse Process Framework (EPF) Composer. In the context of reverse compliance, the gaps with standard documents are detected, potential measures for their resolution are provided, and adaptions are made after the process engineer approval. The applicability of the proposed approach is demonstrated by processing ECSS-E-ST-40C, a space software engineering standard, generating models and mappings, as well as reverse compliance management of extended process model.