arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2106.09844cs.SE
收藏

基于自然语言的设计讨论挖掘的结论稳定性

Conclusion Stability for Natural Language Based Mining of Design Discussions

Alvi Mahadi, Neil A. Ernst, Karan Tongay

摘要:

开发人员的讨论范围从面对面的走廊聊天到bug报告的评论链。能够识别涉及软件设计的讨论将有助于文档和重构软件。设计挖掘是机器学习技术的应用,用于正确地标记给定的讨论工件,例如拉取请求,作为与设计相关(或不相关)。在本文中,我们演示了一个简单的例子,设计挖掘的工作原理。然后,我们展示了结论的稳定性是如何在不同的工件类型和不同的项目差。我们展示了两种技术--增强和上下文特异性--可以大大提高设计挖掘的结论稳定性和跨项目相关性。我们的新方法在数据集内分类上实现了0.88的AUC,在跨数据集分类任务上实现了0.80的AUC。

英文摘要:

Developer discussions range from in-person hallway chats to comment chains on bug reports. Being able to identify discussions that touch on software design would be helpful in documentation and refactoring software. Design mining is the application of machine learning techniques to correctly label a given discussion artifact, such as a pull request, as pertaining (or not) to design. In this paper we demonstrate a simple example of how design mining works. We then show how conclusion stability is poor on different artifact types and different projects. We show two techniques -- augmentation and context specificity -- that greatly improve the conclusion stability and cross-project relevance of design mining. Our new approach achieves AUC of 0.88 on within dataset classification and 0.80 on the cross-dataset classification task.

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。

↑