| 本文已被：浏览 1370次 下载 2619次 |
码上扫一扫！ |
|
|
| 深度学习在基于信息检索的缺陷定位中的应用综述 |
|
曹帅1,2, 牛菲菲1,2, 李传艺1,2, 陈俊洁3, 刘逵4, 葛季栋1,2, 骆斌1,2
|
|
1.计算机软件新技术国家重点实验室(南京大学), 江苏 南京 210093;2.南京大学 软件学院, 江苏 南京 210093;3.天津大学 智能与计算学部, 天津 300350;4.华为公司 软件工程应用技术实验室, 浙江 杭州 310007
|
|
| 摘要: |
| 缺陷自动定位方法可以极大程度减轻开发人员调试和维护软件程序的负担. 基于信息检索的缺陷定位方法是广泛研究的缺陷自动定位方法之一, 并已取得了较好的成果. 随着深度学习的普及, 将深度学习应用于基于信息检索的缺陷定位成为近年来的研究趋势之一. 系统梳理和总结了52篇近年来将深度学习引入基于信息检索缺陷定位的工作. 首先, 总结该类缺陷定位的数据集和评价指标, 接着从不同粒度和可迁移性分析了该类技术的定位效果, 随后着重梳理了相关工作中信息编码表征方法和特征提取方法. 最后总结对比分析了各领域最先进的定位方法, 并展望了使用深度学习的基于信息检索的缺陷定位方法的未来发展方向. |
| 关键词: 深度学习 缺陷定位 信息检索 特征编码 代码表示 |
| DOI：10.13328/j.cnki.jos.007288 |
| 分类号: |
| 基金项目:国家重点研发计划(2022YFF0711404); 江苏省自然科学基金(BK20201250, BK20210279) |
|
| Survey on Deep Learning Applications in Information Retrieval-based Bug Localization |
|
CAO Shuai1,2, NIU Fei-Fei1,2, LI Chuan-Yi1,2, CHEN Jun-Jie3, LIU Kui4, GE Ji-Dong1,2, LUO Bin1,2
|
|
1.State Key Laboratory for Novel Software Technology at Nanjing University, Nanjing 210093, China;2.Software Institute, Nanjing University, Nanjing 210093, China;3.College of Intelligence and Computing, Tianjin University, Tianjin 300350, China;4.Software Engineering Application Technology Lab, Huawei Technologies Co. Ltd., Hangzhou 310007, China
|
| Abstract: |
| Automatic bug localization technologies can significantly alleviate the burden of debugging and maintaining software programs for developers. As a widely studied automatic bug localization technology, information retrieval-based bug localization has yielded promising performance of bug localization. In recent years, the utilization of deep learning for information retrieval-based bug localization has emerged as a research trend due to the widespread adoption of deep learning. This study systematically categorizes and summarizes 52 studies that have introduced deep learning to information retrieval-based bug localization in recent years. Firstly, a summary of datasets and evaluation indexes in this kind of bug localization is provided. Then, the localization performance of these techniques is analyzed from the perspectives of different granularity and transportability. Subsequently, information coding characterization methods and feature extraction methods employed in related studies are summarized. Finally, this study summarizes and compares the most advanced bug localization methods, and provides insights into the future directions of utilizing deep learning in information retrieval-based bug localization methods. |
| Key words: deep learning bug localization information retrieval feature embedding code representation |
