Delving into Commit-Issue Correlation to Enhance Commit Message Generation Models

TL;DR

This paper introduces a new dataset and a training paradigm that leverage commit-issue correlations to significantly improve automated commit message generation models.

Contribution

It constructs the first dataset combining correlated commits and issues and proposes ool, a novel training paradigm that enhances models by incorporating commit-issue correlation.

Findings

ool-enhanced models outperform original models in experiments.

The dataset includes both unlabeled and human-annotated commit-issue pairs.

Significant performance improvements demonstrate the effectiveness of the approach.

Abstract

Commit message generation (CMG) is a challenging task in automated software engineering that aims to generate natural language descriptions of code changes for commits. Previous methods all start from the modified code snippets, outputting commit messages through template-based, retrieval-based, or learning-based models. While these methods can summarize what is modified from the perspective of code, they struggle to provide reasons for the commit. The correlation between commits and issues that could be a critical factor for generating rational commit messages is still unexplored. In this work, we delve into the correlation between commits and issues from the perspective of dataset and methodology. We construct the first dataset anchored on combining correlated commits and issues. The dataset consists of an unlabeled commit-issue parallel part and a labeled part in which each example is provided with human-annotated rational information in the issue. Furthermore, we propose \tool (\underline{Ex}traction, \underline{Gro}unding, \underline{Fi}ne-tuning), a novel paradigm that can introduce the correlation between commits and issues into the training phase of models. To evaluate whether it is effective, we perform comprehensive experiments with various state-of-the-art CMG models. The results show that compared with the original models, the performance of \tool-enhanced models is significantly improved.