We propose a novel task of jointly repairing program codes and generating commit messages. Code repair and commit message generation are two essential and related tasks for software development. However, existing work usually performs the two tasks independently. We construct a multilingual triple dataset including buggy code, fixed code, and commit messages for this novel task. We provide the cascaded models as baseline, which are enhanced with different training approaches, including the teacher-student method, the multi-task method, and the back-translation method. To deal with the error propagation problem of the cascaded method, the joint model is proposed that can both repair the code and generate the commit message in a unified framework. Experimental results show that the enhanced cascaded model with teacher-student method and multitask-learning method achieves the best score on different metrics of automated code repair, and the joint model behaves better than the cascaded model on commit message generation.
CITATION STYLE
Bai, J., Zhou, L., Blanco, A., Liu, S., Wei, F., Zhou, M., & Li, Z. (2021). Jointly Learning to Repair Code and Generate Commit Message. In EMNLP 2021 - 2021 Conference on Empirical Methods in Natural Language Processing, Proceedings (pp. 9784–9795). Association for Computational Linguistics (ACL). https://doi.org/10.18653/v1/2021.emnlp-main.771
Mendeley helps you to discover research relevant for your work.