Transfer learning for conflict and duplicate detection in software requirement pairs

TL;DR

This paper introduces SR-BERT, a transformer-based model that improves automatic detection of conflicting and duplicate software requirements, enhancing software development efficiency through transfer learning and multi-stage fine-tuning.

Contribution

The study presents a novel SR-BERT architecture combining Sentence-BERT and Bi-encoders, with multi-stage fine-tuning, for effective conflict and duplicate detection in requirement pairs.

Findings

SR-BERT achieves top performance on larger datasets.

Sequential training improves model accuracy.

Cross-domain detection performance is promising.

Abstract

Consistent and holistic expression of software requirements is important for the success of software projects. In this study, we aim to enhance the efficiency of the software development processes by automatically identifying conflicting and duplicate software requirement specifications. We formulate the conflict and duplicate detection problem as a requirement pair classification task. We design a novel transformers-based architecture, SR-BERT, which incorporates Sentence-BERT and Bi-encoders for the conflict and duplicate identification task. Furthermore, we apply supervised multi-stage fine-tuning to the pre-trained transformer models. We test the performance of different transfer models using four different datasets. We find that sequentially trained and fine-tuned transformer models perform well across the datasets with SR-BERT achieving the best performance for larger datasets. We also explore the cross-domain performance of conflict detection models and adopt a rule-based filtering approach to validate the model classifications. Our analysis indicates that the sentence pair classification approach and the proposed transformer-based natural language processing strategies can contribute significantly to achieving automation in conflict and duplicate detection