Generating Sequence Diagram from Natural Language Requirements

Model-driven requirements engineering is gaining enormous popularity in recent years. Unified Modeling Language (UML) is widely used in the software industry for specifying, visualizing, constructing, and documenting the software systems artifacts. UML models are helpful tools for portraying the structure and behavior of a software system. However, generating UML models like Sequence Diagrams from requirements documents often expressed in unstructured natural language, is time consuming and tedious. In this paper, we present an automated approach towards generating behavioral models as UML sequence diagrams from textual use cases written in natural language. The approach uses different Natural Language Processing (NLP) techniques combined with some rule based decision approaches to identify problem level objects and interactions. Additionally, different quality metrics are defined to assess the validity of generated sequence diagrams in terms of expected behaviour from a given use case. The criteria we established to assess the quality of analysis sequence diagrams can be applied to similar experiments. We evaluate our approach using different case studies concerning correctness and completeness of the generated sequence diagrams using those metrics. In most situations, we attained an average accuracy factor of over 85% and average completeness of over 90%, which is encouraging.