Generating UML Diagrams from Natural Language Specifications

Abstract

This paper describes a case study on application of natural language processing in very early stages of software development. At this early stage it is very important for the domain expert (who is, most probably, the future user) and the software expert to define a common language, understood by both of them. To define such a common language, we extract terms from the text written by domain expert, classify these terms and build a domain ontology using them. In our previous work 11 we experimented with applicability of the approach to small requirements documents. It turned out that manual work is also necessary to extract information from requirements document. This gave rise to the question whether the same approach also works for larger documents. In this paper we present a case study on the extraction of the ontology from a larger document. The case study shows that the approach works for larger documents as well and the cost (in the sense of time consumption) is reasonable.