Adaptive Fine-tuning for Multiclass Classification over Software Requirement Data

January 02, 2023 Β· Declared Dead Β· πŸ› Conference of the Centre for Advanced Studies on Collaborative Research

πŸ‘» CAUSE OF DEATH: Ghosted
No code link whatsoever

"No code URL or promise found in abstract"

Evidence collected by the PWNC Scanner

Authors Savas Yildirim, Mucahit Cevik, Devang Parikh, Ayse Basar arXiv ID 2301.00495 Category cs.SE: Software Engineering Citations 3 Venue Conference of the Centre for Advanced Studies on Collaborative Research Last Checked 4 months ago
Abstract
The analysis of software requirement specifications (SRS) using Natural Language Processing (NLP) methods has been an important study area in the software engineering field in recent years. Especially thanks to the advances brought by deep learning and transfer learning approaches in NLP, SRS data can be utilized for various learning tasks more easily. In this study, we employ a three-stage domain-adaptive fine-tuning approach for three prediction tasks regarding software requirements, which improve the model robustness on a real distribution shift. The multi-class classification tasks involve predicting the type, priority and severity of the requirement texts specified by the users. We compare our results with strong classification baselines such as word embedding pooling and Sentence BERT, and show that the adaptive fine-tuning leads to performance improvements across the tasks. We find that an adaptively fine-tuned model can be specialized to particular data distribution, which is able to generate accurate results and learns from abundantly available textual data in software engineering task management systems.
Community shame:
Not yet rated
Community Contributions

Found the code? Know the venue? Think something is wrong? Let us know!

πŸ“œ Similar Papers

In the same crypt β€” Software Engineering

Died the same way β€” πŸ‘» Ghosted