Automatic Pull Request Title Generation

TL;DR

This paper introduces the task of automatically generating pull request titles using summarization techniques, constructs a large dataset, and demonstrates that BART outperforms other models in generating high-quality PR titles.

Contribution

It formulates PR title generation as a summarization task, creates a large dataset, and evaluates state-of-the-art models, showing BART's superior performance.

Findings

BART achieves ROUGE-1 of 47.22, ROUGE-2 of 25.27, ROUGE-L of 43.12.

Generated titles are preferred in manual evaluations.

The dataset contains 43,816 PRs from 495 repositories.

Abstract

Pull Requests (PRs) are a mechanism on modern collaborative coding platforms, such as GitHub. PRs allow developers to tell others that their code changes are available for merging into another branch in a repository. A PR needs to be reviewed and approved by the core team of the repository before the changes are merged into the branch. Usually, reviewers need to identify a PR that is in line with their interests before providing a review. By default, PRs are arranged in a list view that shows the titles of PRs. Therefore, it is desirable to have a precise and concise title, which is beneficial for both reviewers and other developers. However, it is often the case that developers do not provide good titles; we find that many existing PR titles are either inappropriate in length (i.e., too short or too long) or fail to convey useful information, which may result in PR being ignored or rejected. Therefore, there is a need for automatic techniques to help developers draft high-quality titles. In this paper, we introduce the task of automatic generation of PR titles. We formulate the task as a one-sentence summarization task. To facilitate the research on this task, we construct a dataset that consists of 43,816 PRs from 495 GitHub repositories. We evaluated the state-of-the-art summarization approaches for the automatic PR title generation task. We leverage ROUGE metrics to automatically evaluate the summarization approaches and conduct a manual evaluation. The experimental results indicate that BART is the best technique for generating satisfactory PR titles with ROUGE-1, ROUGE-2, and ROUGE-L F1-scores of 47.22, 25.27, and 43.12, respectively. The manual evaluation also shows that the titles generated by BART are preferred.