Generating Natural-language Process Descriptions from Formal Process Models

Abstract. Process models are often used to support the understanding and analysis of complex systems. The accuracy of such process models usually requires that various stakeholders review, evaluate, correct, and propose improvements to these models. Some stakeholders, however, may not have the skills to understand the process models except at a relatively superficial level. To address this issue, we have developed an approach for automatically generating natural-language process descriptions based on formal process models. Unlike existing electronic process guides, these process descriptions are generated completely automatically and can de-scribe complex process features, such as exception handling, concurrency, and non-deterministic choice. The generated process descriptions have been well-received by domain experts from several fields and have also proven useful to process programmers. We describe our template-based approach, the resulting hypertext representation, and report on a user study that compares the understandability of the generated textual de-scription and a diagrammatic process representation