Logo des Repositoriums
 

Experiences with Using a Pre-Trained Programming Language Model for Reverse Engineering Sequence Diagrams

dc.contributor.authorGreiner, Sandra
dc.contributor.authorMaier, Nicolas
dc.contributor.authorKehrer, Timo
dc.contributor.editorHerrmann, Andrea
dc.date.accessioned2024-02-22T10:39:09Z
dc.date.available2024-02-22T10:39:09Z
dc.date.issued2023
dc.description.abstractReverse engineering software models from program source code has been extensively studied for decades. Still, most model-driven reverse engineering approaches cover only single programming languages and cannot be transferred to others easily. Large pre-trained AI transformer models which were trained on several programming languages promise to translate source code from one language into another (e.g., Java to Python). Thus, we fine-tuned such a pre-trained model (CodeT5) to extract sequence diagrams from Java code and examined whether it can perform the same task for Python without additional training.en
dc.identifier.issn0720-8928
dc.identifier.urihttps://dl.gi.de/handle/20.500.12116/43659
dc.language.isoen
dc.pubPlaceBonn
dc.publisherGesellschaft für Informatik e.V.
dc.relation.ispartofSoftwaretechnik-Trends Band 43, Heft 2
dc.relation.ispartofseriesSoftwaretechnik-Trends
dc.subjectartificial intelligence
dc.subjectPre-Trained Programming Language Model
dc.subjectReverse Engineering
dc.subjectSequence Diagram
dc.titleExperiences with Using a Pre-Trained Programming Language Model for Reverse Engineering Sequence Diagramsen
dc.typeText/Conference Paper
mci.conference.date44993
mci.conference.locationBad Honnef, Germany
mci.conference.sessiontitle25. Workshop Software-Reengineering und -Evolution der GI-Fachgruppe Software Reengineering (SRE)
mci.reference.pages26-27

Dateien

Originalbündel
1 - 1 von 1
Vorschaubild nicht verfügbar
Name:
08_Greiner.pdf
Größe:
226.41 KB
Format:
Adobe Portable Document Format