一句话:系统实证比较学习型方法在显式与隐式提交信息生成任务上的表现与适用性。
高质量的提交信息有助于开发者快速理解并追踪代码演化,对软件协作开发与维护至关重要。为减轻开发者撰写提交信息的负担,研究者提出了多种自动生成提交信息的技术,其中基于学习的技术被认为颇具前景。本文针对显式提交信息与隐式提交信息生成,对现有学习型技术开展实证研究,系统考察这些方法在两类生成场景中的表现、适用性与影响因素。该工作旨在为 commit message 自动生成技术的理解、选择与后续改进提供经验依据。
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.
DOI 原文 ·
@inproceedings{paperbot8408,
title = {An Empirical Study on Learning-based Techniques for Explicit and Implicit Commit Messages Generation},
author = {Zhiquan Huang and Yuan Huang and Xiangping Chen and Xiaocong Zhou and Changlin Yang and Zibin Zheng},
booktitle = {ASE},
year = {2024},
doi = {10.1145/3691620.3695025}
}