Experiences with Using a Pre-Trained Programming Language Model for Reverse Engineering Sequence Diagrams
| dc.contributor.author | Greiner, Sandra | |
| dc.contributor.author | Maier, Nicolas | |
| dc.contributor.author | Kehrer, Timo | |
| dc.contributor.editor | Herrmann, Andrea | |
| dc.date.accessioned | 2024-02-22T10:39:09Z | |
| dc.date.available | 2024-02-22T10:39:09Z | |
| dc.date.issued | 2023 | |
| dc.description.abstract | Reverse 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.issn | 0720-8928 | |
| dc.identifier.uri | https://dl.gi.de/handle/20.500.12116/43659 | |
| dc.language.iso | en | |
| dc.pubPlace | Bonn | |
| dc.publisher | Gesellschaft für Informatik e.V. | |
| dc.relation.ispartof | Softwaretechnik-Trends Band 43, Heft 2 | |
| dc.relation.ispartofseries | Softwaretechnik-Trends | |
| dc.subject | artificial intelligence | |
| dc.subject | Pre-Trained Programming Language Model | |
| dc.subject | Reverse Engineering | |
| dc.subject | Sequence Diagram | |
| dc.title | Experiences with Using a Pre-Trained Programming Language Model for Reverse Engineering Sequence Diagrams | en |
| dc.type | Text/Conference Paper | |
| mci.conference.date | 44993 | |
| mci.conference.location | Bad Honnef, Germany | |
| mci.conference.sessiontitle | 25. Workshop Software-Reengineering und -Evolution der GI-Fachgruppe Software Reengineering (SRE) | |
| mci.reference.pages | 26-27 |
Dateien
Originalbündel
1 - 1 von 1