Lessons from the Use of Natural Language Inference (NLI) in Requirements Engineering Tasks

arXiv:2405.05135v1 Announce Type: cross
Abstract: We investigate the use of Natural Language Inference (NLI) in automating requirements engineering tasks. In particular, we focus on three tasks: requirements classification, identification of requirements specification defects, and detection of conflicts in stakeholders' requirements. While previous research has demonstrated significant benefit in using NLI as a universal method for a broad spectrum of natural language processing tasks, these advantages have not been investigated within the context of software requirements engineering. Therefore, we design experiments …

abstract arxiv benefit classification cs.cl cs.lg cs.se defects detection engineering focus identification inference language natural natural language requirements research stakeholders tasks type while