Automated Assistance for Data Modelers combining Natural Language Processing and Data Modeling Heuristics: A Prototype Demonstration
Ternes B
Rosenthal K
Strecker S
Beiträge in referierten Konferenzbänden
erschienen in:
Proceedings of the ER Demos and Posters Track co-located with 40th International Conference on Conceptual Modeling (ER 2021), St. John's, NL, Canada, October 18–21, 2021. [Link to Paper]

Identifiers of model elements convey semantics of conceptual models essential to interpretation by human viewers. Prior research shows that devising meaningful identifiers for model elements challenges data modelers from early learning stages to advanced levels of modeling expertise, constituting one of the most common difficulties data modelers face. We demonstrate the Automated Assistant, an integrated modeling tool support component combining natural language processing techniques and data modeling heuristics to provide data modelers with modeling-time feedback on identifying and signifying entity types, relationship types, and attributes with meaningful identifiers. Different from other approaches to automating assistance for data modelers, the Automated Assistant implementation does not rely on fixed reference solutions for modeling tasks as it processes (m)any natural language descriptions of modeling tasks. We report on the current state of prototype development, discuss the Automated Assistant implementation and outline future work.

Lehrstuhl EvIS | 17.10.2022