Understanding the Challenges of Deploying Live-Traceability Solutions

TL;DR

This paper discusses the challenges in deploying automated software traceability solutions, especially in safety-critical projects, and explores future directions for commercializing NLP-based traceability tools.

Contribution

It highlights the key challenges in commercializing automated traceability and suggests future research directions for NLP-based solutions.

Findings

Identifies key challenges in deploying traceability solutions.

Emphasizes the importance of NLP techniques like transformer models.

Discusses future directions for commercialization and research.

Abstract

Software traceability is the process of establishing and maintaining relationships between artifacts in a software system. This process is crucial to many engineering processes, particularly for safety critical projects; however, it is labor-intensive and error-prone. Automated traceability has been a long awaited tool for project managers of these systems, and due to the semantic similarities between linked artifacts, NLP techniques, such as transformer models, may be leveraged to accomplish this task. SAFA.ai is a startup focusing on fine-tuning project-specific models that deliver automated traceability in a near real-time environment. The following paper describes the challenges that characterize commercializing software traceability and highlights possible future directions.