Using Developer Discussions to Guide Fixing Bugs in Software

Sheena Panthaplackel, Milos Gligoric, Junyi Jessy Li, Raymond Mooney


Abstract
Automatically fixing software bugs is a challenging task. While recent work showed that natural language context is useful in guiding bug-fixing models, the approach required prompting developers to provide this context, which was simulated through commit messages written after the bug-fixing code changes were made. We instead propose using bug report discussions, which are available before the task is performed and are also naturally occurring, avoiding the need for any additional information from developers. For this, we augment standard bug-fixing datasets with bug report discussions. Using these newly compiled datasets, we demonstrate that various forms of natural language context derived from such discussions can aid bug-fixing, even leading to improved performance over using commit messages corresponding to the oracle bug-fixing commits.
Anthology ID:
2022.findings-emnlp.169
Volume:
Findings of the Association for Computational Linguistics: EMNLP 2022
Month:
December
Year:
2022
Address:
Abu Dhabi, United Arab Emirates
Editors:
Yoav Goldberg, Zornitsa Kozareva, Yue Zhang
Venue:
Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
2292–2301
Language:
URL:
https://aclanthology.org/2022.findings-emnlp.169
DOI:
10.18653/v1/2022.findings-emnlp.169
Bibkey:
Cite (ACL):
Sheena Panthaplackel, Milos Gligoric, Junyi Jessy Li, and Raymond Mooney. 2022. Using Developer Discussions to Guide Fixing Bugs in Software. In Findings of the Association for Computational Linguistics: EMNLP 2022, pages 2292–2301, Abu Dhabi, United Arab Emirates. Association for Computational Linguistics.
Cite (Informal):
Using Developer Discussions to Guide Fixing Bugs in Software (Panthaplackel et al., Findings 2022)
Copy Citation:
PDF:
https://aclanthology.org/2022.findings-emnlp.169.pdf
Video:
 https://aclanthology.org/2022.findings-emnlp.169.mp4