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
2024年份
2被引次数
摘要
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.
问问这篇 Paper
问问你的智能体。
Lune 读过与它相关的顶会 Paper,每个回答都会注明依据哪几篇。
相关 Paper
- FIRA: Fine-Grained Graph-Based Code Change Representation for Automated Commit Message GenerationJinhao Dong, Yiling Lou, Qihao Zhu, Zeyu Sun 等ICSE 2022 · 被引用 50 次
- Revisiting Learning-based Commit Message GenerationJinhao Dong, Yiling Lou, Dan Hao, Lin TanICSE 2023 · 被引用 8 次
- What Makes a Good Commit Message?Yingchen Tian, Yuxia Zhang, Klaas-Jan Stol, Lin Jiang 等ICSE 2022 · 被引用 90 次
- Commit Message Matters: Investigating Impact and Evolution of Commit Message QualityJiawei Li, Iftekhar AhmedICSE 2023 · 被引用 26 次
- RACE: Retrieval-augmented Commit Message GenerationEnsheng Shi, Yanlin Wang, Wei Tao, Lun Du 等EMNLP 2022 · 被引用 36 次
