NoRBERT: Transfer Learning for Requirements Classification
| Autor: | Tobias Hey, Jan Keim, Walter F. Tichy, Anne Koziolek |
|---|---|
| Jazyk: | angličtina |
| Rok vydání: | 2022 |
| Předmět: |
Generalization
Computer science media_common.quotation_subject 02 engineering and technology 010501 environmental sciences Language Model Machine learning computer.software_genre 01 natural sciences Domain (software engineering) Machine Learning 0202 electrical engineering electronic engineering information engineering Function (engineering) 0105 earth and related environmental sciences media_common Requirements Engineering Requirements engineering business.industry Requirements Classification DATA processing & computer science 020207 software engineering Percentage point Functional requirement Transfer Learning ComputingMethodologies_PATTERNRECOGNITION Artificial intelligence Language model ddc:004 business Transfer of learning computer BERT |
| Zdroj: | RE |
| DOI: | 10.5445/ir/1000150464 |
| Popis: | 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 $\text{F}_1$-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 non-functional requirements subclasses. The most frequent classes are classified with an average $\text{F}_1$-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 $\text{F}_1$-score 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 $\text{F}_1$-score of up to 92%. Overall, NoRBERT improves requirements classification and can be applied to unseen projects with convincing results. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|