Machine Learning for Software Engineering Research Group
Description of Activities
The core activities concern the application of machine learning, particularly deep learning, to software engineering: teaching machines to understand, write, and fix code. This relies on the naturalness of source code that makes it possible to apply the vast knowledge accumulated in the natural processing community to computer programs.
Research Interests
▶ Program code transformations
▶ Code idiomatizationa
Related publications:
☞ Szalontai et al., 2024
☞ Localizing and Idiomatizing Nonidiomatic Python Code with Deep Learning
▶ Automatic bugfixing
Related publications:
☞ Szalontai et al., 2024
▶ Neural decompilation
.png)
Related publications:
☞ Single-pass end-to-end neural decompilation using copying mechanism
▶ Requirements engineering
Research Methodology
- Recurrent neural networks
- Transformers
- Large language models
- Copying mechanism
Research Staff
- Balázs Pintér (research group leader, MTMT)
- Tibor Gregorics, associate professor
- Balázs Szalontai PhD student
- Gergő Szalay PhD student
- Silva Matti PhD student
- 15-20 MSc and BSc students
5 important publications in the field
- G. Szalay, M. B. Poór, B. Pintér, T. Gregorics (2024): Single-pass end-to-end neural decompilation using copying mechanism, Neural Computing and Applications [DOI]
- B. Szalontai, A. Vadász, T. Márton, B. Pintér, T. Gregorics (2024): Fine-tuning CodeLlama to fix bugs, Proceedings of International Conference on Recent Innovations in Computing [DOI]
- B. Szalontai, T. Márton, Á. Kukucska, B. Pintér, T. Gregorics (2024): Idiomatizing Python source code using different recurrent architectures, Intelligent Systems and Applications [DOI]
- B. Szalontai, Á. Kukucska, A. Vadász, B. Pintér, T. Gregorics (2023): Localizing and idiomatizing nonidiomatic Python code with deep learning, Intelligent Computing [DOI]
- B. Mucsányi, B. Gyarmathy, Á. Czapp, B. Pintér (2022): Flexible example-based program synthesis on tree-structured function compositions, SN Computer Science [DOI]
Contact
Balázs Pintér [pinter@inf.elte.hu]