Resolving Code Review Comments with Machine Learning
Alexander Frömmgen, Jacob Austin, Peter Choy et al. · International Conference on Software Engineering: Software Engineering in Practice (ICSE-SEIP) · 2024
Code reviews are a critical part of the software development process, taking a significant amount of the code authors' and the code reviewers' time. As part of this process, the reviewer inspects the proposed code and asks the author for code changes through comments written in natural language. At Google, we see millions of reviewer comments per year, and authors require an average of ~60 minutes active shepherding time between sending changes for review and finally submitting the change. In our measurements, the required active work time that the code author must devote to address reviewer comments grows almost linearly with the number of comments. However, with machine learning (ML), we have an opportunity to automate and streamline the code-review process, e.g., by proposing code changes based on a comment's text.
Cited by 21 works. doi:10.1145/3639477.3639746
Authors
- Alexander Frömmgen
- Jacob Austin
- Nimesh Ghelani
- Lera Kharatyan
- Gabriela Surita
- Elena Khrapko
- Pascal Lamblin
- Pierre-Antoine Manzagol
- Marcus Revaj
- Maxim Tabachnyk
- Daniel Tarlow
- Kevin Villela
- Daniel Zheng
- Satish Chandra
- Petros Maniatis
References
- Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer
- A Direction-Aware Study of LLM-Based Code Translation Across Eight Programming Languages
- CodeT5: Identifier-aware Unified Pre-trained Encoder-Decoder Models for Code Understanding and Generation
- DeepFix: Fixing Common C Language Errors by Deep Learning
- Code Llama: Open Foundation Models for Code
- Convergent contemporary software peer review practices
- Why Google stores billions of lines of code in a single repository
- Automating code review activities by large-scale pre-training
- Towards Automating Code Review Activities
- LLaMA-Reviewer: Advancing Code Review Automation with Large Language Models through Parameter-Efficient Fine-Tuning