Minimal Data, Maximal Impact: Language Model-based Pipelines for the Automatic Generation of Use Case Diagrams from Requirements

Schleifer S, Lungu A, Kruse B, van Putten S, Götz S, Wartzack S (2024)

Publication Type: Conference contribution, Conference Contribution

Publication year: 2024

Publisher: Cambridge University Press

Series: Proceedings of the 35th Symposium Design for X (DFX2024)

Pages Range: 240-249

Event location: Bamberg DE

URI: https://www.designsociety.org/publication/47592/Minimal+Data,+Maximal+Impact:+Language+Model-based+Pipelines+for+the+Automatic+Generation+of+Use+Case+Diagrams+from+Requirements

DOI: 10.35199/dfx2024.25

Abstract

Striving for unique selling points leads to an increase in product requirements, which are prevalently written in natural language. In order to mitigate inherent ambiguities in these requirements specifications, methods of Model-Based Systems Engineering, like use case diagrams, can be utilized. However, creating model-based requirements is time-consuming. Thus, two novel pipelines for the automatic generation of use case diagrams are proposed and discussed with focus on reducing the amount of needed annotated training data. The first pipeline combines named entity recognition with active learning. The second pipeline utilizes generative large language models and prompt engineering. Both pipelines are exemplarily applied to a requirements specification from the automotive industry.

Authors with CRIS profile

Simon Schleifer Chair of Engineering Design Stefan Götz Chair of Engineering Design Sandro Wartzack Chair of Engineering Design

Involved external institutions

Audi AG DE Germany (DE)

How to cite

APA:

Schleifer, S., Lungu, A., Kruse, B., van Putten, S., Götz, S., & Wartzack, S. (2024). Minimal Data, Maximal Impact: Language Model-based Pipelines for the Automatic Generation of Use Case Diagrams from Requirements. In Dieter Krause; Kristin Paetzold-Byhain; Sandro Wartzack (Eds.), Proceedings of the 35. Symposium - Design for X (DfX) (pp. 240-249). Bamberg, DE: Cambridge University Press.

MLA:

Schleifer, Simon, et al. "Minimal Data, Maximal Impact: Language Model-based Pipelines for the Automatic Generation of Use Case Diagrams from Requirements." Proceedings of the 35. Symposium - Design for X (DfX), Bamberg Ed. Dieter Krause; Kristin Paetzold-Byhain; Sandro Wartzack, Cambridge University Press, 2024. 240-249.

BibTeX: Download