From Textual Scenarios to Message Sequence Charts: Inclusion of Condition Generation and Actor Extraction

Abstract

Natural language is the main presentation means in industrial requirements documents. In such documents, system behavior is specified in the form of scenarios, with every scenario written as a sequence of sentences in natural language. To translate scenarios to executable models, message sequence charts (MSCs), we proposed an approach that analyzes textual scenarios by means of computational linguistics by L. Kof (2007). The presented paper shows that (1) a more differentiated treatment of certain sentence types than in our previous work results in better precision of the text-to-MSC translation and (2) it is possible to automate agent identification, performed semiautomatically in our previous work.