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 2211.05286cs.SE
收藏

面向软件需求分类的深度学习方法:基于PURE数据集的性能研究

Deep Learning Methods for Software Requirement Classification: A Performance Study on the PURE dataset

Shiraz University of Technology(Shiraz理工大学)

Fatemeh Khayashi, Behnaz Jamasb, Reza Akbari, Pirooz Shamsinejadbabaki

AI总结:

针对软件需求中功能与非功能需求的分类难题,基于PURE构建含4661条需求的数据集,训练5种主流深度学习模型并结合2种投票算法构建集成分类器,验证了深度学习的分类效果及投票机制的性能提升作用。

摘要:

需求工程(RE)是软件生产与开发中首要且最为关键的步骤,其目标是明确软件需求。需求工程中的一项任务是将软件需求划分为功能需求与非功能需求:功能需求(FR)明确系统的职责,非功能需求则体现软件的质量属性。区分功能需求与非功能需求是一项具有挑战性的工作。如今,深度学习(DL)已渗透到工程的各个领域,在提升准确率的同时缩短了落地周期。本文将深度学习应用于软件需求分类任务:训练了5种主流深度学习算法用于需求分类,同时采用2种投票分类算法,基于这5种深度学习方法构建集成分类器。实验选用PURE——一个软件需求规格说明(SRS)文档仓库——作为数据来源,我们从中构建了包含4661条需求的数据集,其中2617条为功能需求,其余为非功能需求。我们将所提方法应用于该数据集并报告了性能分析结果。实验结果表明,深度学习模型的性能表现令人满意,且投票机制能带来更优的分类效果。

英文摘要:

Requirement engineering (RE) is the first and the most important step in software production and development. The RE is aimed to specify software requirements. One of the tasks in RE is the categorization of software requirements as functional and non-functional requirements. The functional requirements (FR) show the responsibilities of the system while non-functional requirements represent the quality factors of software. Discrimination between FR and NFR is a challenging task. Nowadays Deep Learning (DL) has entered all fields of engineering and has increased accuracy and reduced time in their implementation process. In this paper, we use deep learning for the classification of software requirements. Five prominent DL algorithms are trained for classifying requirements. Also, two voting classification algorithms are utilized for creating ensemble classifiers based on five DL methods. The PURE, a repository of Software Requirement Specification (SRS) documents, is selected for our experiments. We created a dataset from PURE which contains 4661 requirements where 2617 requirements are functional and the remaining are non-functional. Our methods are applied to the dataset and their performance analysis is reported. The results show that the performance of deep learning models is satisfactory and the voting mechanisms provide better results.

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。

↑