基于词嵌入和长短期记忆网络的非功能软件需求分类  

Classification of Non-Functional Software Requirements Using Word Embeddings and Long Short-Term Memory

作　　者：李冰 李智[1] 杨溢龙 LI Bing;LI Zhi;YANG Yilong(College of Computer Science and Engineering,Guangxi Normal University,Guilin Guangxi 541004,China;College of Software,Beihang University,Beijing 100191,China)

机构地区：[1]广西师范大学计算机科学与工程学院,广西桂林541004 [2]北京航空航天大学软件学院,北京100191

出　　处：《广西师范大学学报（自然科学版）》2021年第5期110-121,共12页Journal of Guangxi Normal University:Natural Science Edition

基　　金：国家自然科学基金(61862009);广西自然科学基金(2018GXNSFAA281314);广西研究生教育创新计划项目(JXXYYJSCXXM-001)。

摘　　要：非功能需求(non-functional requirements,NFR)描述了软件所需的一组质量属性,例如安全性、可靠性、性能等。为了开发高质量的软件产品,需要从软件需求规格说明书(software requirements specification,SRS)中提取NFR,如果此过程实现了自动化,不仅可以减少从大量需求中识别特定需求所涉及的人工、时间和精神疲劳,还可以帮助开发人员提供满足用户期望的高质量软件。针对此问题,本文采用深度学习特征提取和分类技术,提出一种基于预训练的BERT(bidirectional encoder representations from transformers)词嵌入和长短期记忆网络LSTM(long short-term memory)相结合的BERT-LSTM网络模型,用于质量软件开发的自动NFR分类。首先,通过BERT模型训练需求文本中的词向量,然后利用长短期记忆网络对词向量进行特征提取,最后使用Softmax分类器识别SRS中的NFR。实验表明,相比于其他算法,在由非功能需求和功能需求组成的PROMISE语料库中,BERT-LSTM网络模型在准确度、召回率、F_(1)得分等指标方面取得了最佳的效果。Non-functional requirements(NFR)describes a set of quality attributes required by the software,such as safety,reliability,performance,etc.In order to develop high-quality software products,it would be beneficial to automatically extract NFR from the Software Requirements Specification(SRS),which not only reduces the labor,time,and mental fatigue involved in identifying specific requirements from a large number of requirements,but also helps developers provide high-quality software that fully meets user expectations.In order to solve this problem,by adopting deep learning feature extraction and classification technology,a BERT-LSTM network model based on the combination of pre-trained BERT word embeddings and long short-term memory network LSTM is proposed,which is used for automatic NFR classification of quality software development.First,use the BERT model to train the word vectors in the sentence.Then use the Long Short-Term Memory network to further perform feature selection and dimensionality reduction.And finally use the Softmax classifier to identify NFR from SRS.Experiments show that in the PROMISE corpus composed of NFR,the BERT-LSTM network model has achieved the best results compared with other algorithms in terms of precision,recall,F_(1) score,and other indicators.

关 键 词：非功能需求 需求规格说明书 BERT 长短期记忆网络 

分 类 号：TP183[自动化与计算机技术—控制理论与控制工程]