Cross-Domain Requirements Linking via Adversarial-based Domain Adaptation
Requirements linking is the core of software system maintenance and evolution, and it is critical to assuring software quality. In practice, however, the requirements links are frequently absent or incorrectly labeled, and reconstructing such ties is time-consuming and error-prone. Numerous learning-based approaches have been put forth to address the problem. However, these approaches will lose effectiveness for the Cold-Start projects with few labeled samples. To this end, we propose RADIATION, an adversarial-based domain adaptation approach for cross-domain requirements linking. Generally, RADIATION firstly adopts an IDF-based Masking strategy to filter the domain-specific features. Then it pre-trains a linking model in the source domain with sufficient labeled samples and adapts the model to target domains using a distance-enhanced adversarial technique without using any labeled target samples. Evaluation on five public datasets shows that RADIATION could achieve 66.4% precision, 89.2% recall, and significantly outperform state-of-the-art baselines by 13.4%-42.9% F1. In addition, the designed components, i.e., IDF-based Masking and Distance-enhanced Loss, could significantly improve performance.
Thu 18 MayDisplayed time zone: Hobart change
13:45 - 15:15 | Requirements engineeringDEMO - Demonstrations / Technical Track / NIER - New Ideas and Emerging Results / Showcase / Journal-First Papers / SEIP - Software Engineering in Practice at Meeting Room 105 Chair(s): Luciano Baresi Politecnico di Milano | ||
13:45 15mTalk | Demystifying Privacy Policy of Third-Party Libraries in Mobile Apps Technical Track Kaifa ZHAO The Hong Kong Polytechnic University, Xian Zhan The Hong Kong Polytechnic University, Le Yu The Hong Kong Polytechnic University, Shiyao Zhou The Hong Kong Polytechnic University, Hao Zhou Department of Computing, The Hong Kong Polytechnic University, Hong Kong, China, Xiapu Luo The Hong Kong Polytechnic University, Haoyu Wang Huazhong University of Science and Technology, Yepang Liu Southern University of Science and Technology Pre-print | ||
14:00 15mTalk | Cross-Domain Requirements Linking via Adversarial-based Domain Adaptation Technical Track Zhiyuan Chang Institute of Software at Chinese Academy of Sciences; University of Chinese Academy of Sciences, Mingyang Li Institute of Software at Chinese Academy of Sciences; University of Chinese Academy of Sciences, Qing Wang Institute of Software at Chinese Academy of Sciences; University of Chinese Academy of Sciences, Shoubin Li Institute of Software at Chinese Academy of Sciences; University of Chinese Academy of Sciences, Junjie Wang Institute of Software at Chinese Academy of Sciences; University of Chinese Academy of Sciences | ||
14:15 15mTalk | DocToModel: Automated Authoring of Models from Diverse Requirements Specification Documents SEIP - Software Engineering in Practice Asha Rajbhoj TCS Research, Padmalata Nistala TCS Research, Vinay Kulkarni Tata Consultancy Services Research, Shivani Soni TCS Research, Ajim Pathan TCS Research | ||
14:30 15mTalk | Environment-Driven Abstraction Identification for Requirements-Based Testing Showcase Zedong Peng , Prachi Rathod , Nan Niu University of Cincinnati, Tanmay Bhowmik Mississippi State University, Hui Liu Beijing Institute of Technology, Lin Shi ISCAS, Zhi Jin Peking University | ||
14:45 7mTalk | A Web-Based Tool for Using Storyboard of Android Apps DEMO - Demonstrations | ||
14:52 7mTalk | InputGen: A Tool for Automatic Generation of Prototype Inputs to Support Rapid Requirements Validation DEMO - Demonstrations Shuanglong Chang Northeast Petroleum University, Juntao Gao Northeast Petroleum University, Yilong Yang Beihang University | ||
15:00 7mTalk | A Software Requirements Ecosystem: Linking Forum, Issue Tracker, and FAQs for Requirements Management Journal-First Papers James Tizard University of Auckland, Peter Devine The University of Auckland, Hechen Wang University of Auckland, Kelly Blincoe University of Auckland | ||
15:07 7mTalk | Towards Human-Centred Crowd Computing: Software for Better Use of Computational Resources NIER - New Ideas and Emerging Results Niroshinie Fernando Deakin University, Chetan Arora Monash University, Seng W.Loke Deakin University, Lubna Alam Deakin University, Stephen La Macchia Deakin University, Helen Graesser Deakin University Pre-print |