arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2110.04353cs.CLcs.SE
收藏

基于开发人员讨论学习描述Bug报告的解决方案

Learning to Describe Solutions for Bug Reports Based on Developer Discussions

The University of Texas at Austin(德克萨斯大学奥斯汀分校)

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

摘要:

当一个软件错误被报告时,开发人员会参与讨论以协同解决它。虽然解决方案可能在讨论中制定,但它通常被隐藏在大量文本中,难以理解并延迟其实施。为了加快错误解决,我们建议通过综合讨论中的相关内容来生成解决方案的简洁自然语言描述,其中包括自然语言和源代码。我们建立了一个语料库,这项任务使用一种新的技术,从存储库的变化链接到错误报告,我们建立基准获得嘈杂的监督。我们还设计了两个系统,用于在正在进行的讨论中产生的描述进行分类时,有足够的上下文执行任务出现在实时。通过自动化和人工评估,我们发现这项任务可以在长时间的双峰对话背景下形成复杂推理的理想测试平台。

英文摘要:

When a software bug is reported, developers engage in a discussion to collaboratively resolve it. While the solution is likely formulated within the discussion, it is often buried in a large amount of text, making it difficult to comprehend and delaying its implementation. To expedite bug resolution, we propose generating a concise natural language description of the solution by synthesizing relevant content within the discussion, which encompasses both natural language and source code. We build a corpus for this task using a novel technique for obtaining noisy supervision from repository changes linked to bug reports, with which we establish benchmarks. We also design two systems for generating a description during an ongoing discussion by classifying when sufficient context for performing the task emerges in real-time. With automated and human evaluation, we find this task to form an ideal testbed for complex reasoning in long, bimodal dialogue context.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑