RACE: Retrieval-Augmented Commit Message Generation

TL;DR

RACE is a retrieval-augmented neural method for commit message generation that uses similar past commits as exemplars and guides message generation based on semantic similarity, improving accuracy and outperforming baselines.

Contribution

The paper introduces RACE, a novel retrieval-augmented approach with an exemplar guider for more accurate commit message generation, outperforming existing models.

Findings

RACE outperforms all baseline models in experiments.

RACE enhances existing Seq2Seq models.

The method is effective across five programming languages.

Abstract

Commit messages are important for software development and maintenance. Many neural network-based approaches have been proposed and shown promising results on automatic commit message generation. However, the generated commit messages could be repetitive or redundant. In this paper, we propose RACE, a new retrieval-augmented neural commit message generation method, which treats the retrieved similar commit as an exemplar and leverages it to generate an accurate commit message. As the retrieved commit message may not always accurately describe the content/intent of the current code diff, we also propose an exemplar guider, which learns the semantic similarity between the retrieved and current code diff and then guides the generation of commit message based on the similarity. We conduct extensive experiments on a large public dataset with five programming languages. Experimental results show that RACE can outperform all baselines. Furthermore, RACE can boost the performance of existing Seq2Seq models in commit message generation.