Deep Learning Meets Software Engineering: A Survey on Pre-Trained Models of Source Code
Changan Niu, C. Li, Bin Luo, Vincent Ng
2022Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence34 citationsDOIOpen Access PDF
Abstract
Recent years have seen the successful application of deep learning to software engineering (SE). In particular, the development and use of pre-trained models of source code has enabled state-of-the-art results to be achieved on a wide variety of SE tasks. This paper provides an overview of this rapidly advancing field of research and reflects on future research directions.
Topics & Concepts
Computer scienceVariety (cybernetics)Software engineeringSource codeField (mathematics)Code (set theory)Deep learningSoftwareData scienceSoftware developmentArtificial intelligenceProgramming languageSet (abstract data type)Pure mathematicsMathematicsSoftware Engineering ResearchTopic ModelingSoftware Testing and Debugging Techniques