Using Developer Discussions to Guide Fixing Bugs in Software
Using Developer Discussions to Guide Fixing Bugs in Software
复制标题
DOI：
10.48550/arxiv.2211.06335
复制
发表时间：
2022-11
期刊：
影响因子：
--
通讯作者：
Sheena Panthaplackel;Miloš Gligorić;Junyi Jessy Li;R. Mooney
中科院分区：
文献类型：
--
作者：
Sheena Panthaplackel;Miloš Gligorić;Junyi Jessy Li;R. Mooney
自动修复软件错误是一项具有挑战性的任务。虽然最近的工作表明自然语言上下文在指导bug修复模型方面很有用，但这种方法需要提示开发人员提供这种上下文，这是通过在bug修复代码更改后编写的提交消息来模拟的。相反，我们建议使用bug报告讨论，这在任务执行之前就可以使用，并且也是自然发生的，避免了对开发人员任何额外信息的需求。为此，我们用bug报告讨论来增加标准的bug修复数据集。使用这些新编译的数据集，我们证明了从这些讨论中派生的各种形式的自然语言上下文可以帮助修复错误，甚至可以提高使用与Oracle错误修复提交对应的提交消息的性能。
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.