Sentence Embedding Models for Similarity Detection of Software Requirements

Semantic similarity detection mainly relies on the availability of laboriously curated ontologies, as well supervised and unsupervised neural embedding models. In this paper, we present two domain-specific sentence models trained a natural language requirements dataset in order to derive embeddings specific software engineering domain. We use cosine-similarity measures both these The result experimental evaluation confirm that proposed enhance performance textual semantic over existing state-of-the-art models: reach an accuracy 88.35%—which improves by about 10% benchmarks.