Support for traceability management of software artefacts using Natural Language Processing
Support for traceability management of software artefacts using Natural Language Processing
复制标题
使用自然语言处理支持软件工件的可追溯性管理
DOI：
--
复制
发表时间：
2016
期刊：
影响因子：
--
通讯作者：
D. Balasubramaniam
中科院分区：
文献类型：
--
作者：
A. Arunthavanathan;Sobiga Shanmugathasan;S. Ratnavel;V. Thiyagarajah;I. Perera;D. Meedeniya;D. Balasubramaniam
软件开发过程中的主要问题之一是管理软件制品。随着软件的发展，人工制品之间的不一致也会随之发展。为了解决变更管理中的不一致问题，引入了一个名为“软件构件可跟踪性分析器(SAT-Analyzer)”的工具作为本研究的前期工作。在自然语言处理(NLP)的帮助下，通过创建这些文档的结构化格式，可以跟踪需求规范、统一建模语言(UML)图表和源代码中的软件人工产物的变化。因此，在本研究中，我们的目标是增加NLP支持，作为SAT-Analyzer的扩展。由于人工产物的不一致，增强在SAT分析器工具中创建的可追溯性链接是另一个重点。本文包括应用NLP改进可追溯性管理的研究方法和开展的相关研究。工具的多情景评估结果显示，平均准确率为72.22%，召回率为88.89%，F1测量值为78.89%，表明该领域具有较高的准确率。
One of the major problems in software development process is managing software artefacts. While software evolves, inconsistencies between the artefacts do evolve as well. To resolve the inconsistencies in change management, a tool named “Software Artefacts Traceability Analyzer (SAT-Analyzer)” was introduced as the previous work of this research. Changes in software artefacts in requirement specification, Unified Modelling Language (UML) diagrams and source codes can be tracked with the help of Natural Language Processing (NLP) by creating a structured format of those documents. Therefore, in this research we aim at adding an NLP support as an extension to SAT-Analyzer. Enhancing the traceability links created in the SAT-analyzer tool is another focus due to artefact inconsistencies. This paper includes the research methodology and relevant research carried out in applying NLP for improved traceability management. Tool evaluation with multiple scenarios resulted in average Precision 72.22%, Recall 88.89% and F1 measure of 78.89% suggesting high accuracy for the domain.