Workshop on Neuro-Symbolic Software Engineering

Software engineering has a successful history of evolving symbolic techniques like formal methods and programming languages to solve increasingly challenging problems, as for instance, providing safety and performance guarantees for autonomous intelligent and mission-critical systems. With the availability of machine learning (ML) techniques, software engineering expanded its set of problems to study how learning from data can enable various tasks, e.g., from code summarization and generation to automatic program repair and formal verification.
The integration of symbolic and machine learning techniques (coined neuro-symbolic methods) has opened novel methodological challenges that go beyond applying ML to build software (ML4SE) or applying software engineering to build ML (SE4ML). Neuro-Symbolic methods focus on problems of how to “reason while learning” and how to “learn while reasoning”.
This workshop aims to discuss these problems in the context of the various software engineering tasks that have been recently transformed by the adoption of machine learning techniques. We invite insights on merging symbolic and ML techniques across the software development life-cycle, its activities, artifacts, metrics, and tools. We welcome case studies, conceptual approaches, empirical research, and more formal or theoretical considerations.