Context-Encoded Code Change Representation for Automated Commit Message Generation
Thanh Trong Vu, Thanh-Dat Do, and Hieu Dinh Vo

TL;DR
This paper introduces a novel code change representation that combines changed and unchanged code with program dependence, significantly enhancing automated commit message generation performance.
Contribution
It proposes a new representation method leveraging program dependence to improve automated commit message generation over existing approaches.
Findings
Improves METEOR score by up to 15%
Enhances ROUGE-L score by up to 14%
Boosts BLEU-4 score by up to 10%
Abstract
Changes in source code are an inevitable part of software development. They are the results of indispensable activities such as fixing bugs or improving functionality. Descriptions for code changes (commit messages) help people better understand the changes. However, due to a lack of motivation and time pressure, writing high-quality commit messages remains reluctantly considered. Several methods have been proposed with the aim of automated commit message generation. However, the existing methods are still limited because they only utilise either the changed code or the changed code combined with surrounding statements. This paper proposes a method to represent code changes by combining the changed code and the unchanged code which have program dependence on the changed code. This method overcomes the limitations of current representations while improving the performance of 5/6 of…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsSoftware System Performance and Reliability · Advanced Software Engineering Methodologies · Software Engineering Research
