A natural language interface for automatic generation of data flow diagram using web extraction techniques
Sehrish Munawar Cheema, Saman Tariq, Ivan Miguel Pires
Abstract
To model the data and functions in various computer science applications, the researcher uses a Data Flow Diagram (DFD). DFD has been constructed using [open-source software tools that provide users with different shapes and environments. However, the existing approaches require substantial human effort, the validity of the generated output is still a loophole, and they have never gained traction in practice. Our research objective is to develop a semi-automated tool for drawing complex Data Flow Diagrams in the shortest time according to the specified features of the intended system. We developed a Natural Language Interface (NLI) that allows the user to compose a query and identify the system functionality and constraints for the composition of DFD. Natural Language Processing (NLP) techniques are applied to scrapped data to extract the keywords and develop a data repository. Also, we developed rule-based algorithms to map user queries onto respective token shapes to draw the required functionality into appropriate levels of DFD. For verification, output DFDs were converted into conceptual digraphs using adjacency and permutation matrices to evaluate isomorphism. The empirical results reflect that the DFDs generated by the system are correct, complete, and significant.