An Empirical Study on Learning-based Techniques for Explicit and Implicit Commit Messages Generation
Zhiquan Huang, Yuan Huang, Xiangping Chen, Xiaocong Zhou, Changlin Yang, Zibin Zheng
2024Year
2Citations
Abstract
High-quality and appropriate commit messages help developers to quickly understand and track code evolution, which is crucial for the collaborative development and maintenance of software. To relieve developers of the burden of writing commit messages, researchers have proposed various techniques to generate commit messages automatically, among which learning-based techniques have proven to be promising.
Ask about this paper
Ask your agent about it.
Lune has read the top-tier papers around this one, so every answer names the papers it rests on.
Your agent calls
Lunesearch_papers
Free to start. No credit card required.
Terminal
Install the CLIlune papers get d52eed61-171c-4f46-8433-8458e2a4ceaaRelated papers
- FIRA: Fine-Grained Graph-Based Code Change Representation for Automated Commit Message GenerationJinhao Dong, Yiling Lou, Qihao Zhu, Zeyu Sun et al.ICSE 2022 · 50 citations
- Revisiting Learning-based Commit Message GenerationJinhao Dong, Yiling Lou, Dan Hao, Lin TanICSE 2023 · 8 citations
- What Makes a Good Commit Message?Yingchen Tian, Yuxia Zhang, Klaas-Jan Stol, Lin Jiang et al.ICSE 2022 · 90 citations
- Commit Message Matters: Investigating Impact and Evolution of Commit Message QualityJiawei Li, Iftekhar AhmedICSE 2023 · 26 citations
- RACE: Retrieval-augmented Commit Message GenerationEnsheng Shi, Yanlin Wang, Wei Tao, Lun Du et al.EMNLP 2022 · 36 citations
