Classifying requirements is crucial for automatically handling natural language requirements. The performance of existing automatic classification approaches diminishes when applied to unseen projects because requirements usually vary in wording and style. The main problem is poor generalization. We propose NoRBERT that fine-tunes BERT, a language model that has proven useful for transfer learning. We apply our approach to different tasks in the domain of requirements classification. We achieve similar or better results (F 1 -scores of up to 94%) on both seen and unseen projects for classifying functional and non-functional requirements on the PROMISE NFR dataset. NoRBERT outperforms recent approaches at classifying nonfunctional requirements subclasses. The most frequent classes are classified with an average F 1 -score of 87%. In an unseen project setup on a relabeled PROMISE NFR dataset, our approach achieves an improvement of 15 percentage points in average F 1score compared to recent approaches. Additionally, we propose to classify functional requirements according to the included concerns, i.e., function, data, and behavior. We labeled the functional requirements in the PROMISE NFR dataset and applied our approach. NoRBERT achieves an F 1 -score of up to 92%. Overall, NoRBERT improves requirements classification and can be applied to unseen projects with convincing results.
Marc Andreesen targets the disruptive change of business models enabled through software, it also describes a process ongoing over decades. Software already invaded basically all parts of our daily lives, at work as well as in private affairs. As a consequence, there is software in daily use to support critical processes in enterprises, machines, or production systems, which was initially developed decades ago. And still this software needs to be maintained and adopted to newly required functionality or modern information technology (IT) platforms. Estimations exist that assume that more than half of software budgets are spent in software maintenance [Gla01].
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.