Deep Learning Meets Software Engineering: A Survey on Pre-Trained Models of Source Code

Changan Niu, Chuanyi Li, Bin Luo, and Vincent Ng.
Proceedings of the 31st International Joint Conference on Artificial Intelligence and the 25th European Conference on Artificial Intelligence, pp. 5546-5555, 2022.

Click here for the PDF version.

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.

BibTeX entry

@InProceedings{Niu+etal:22a,
  author = {Changan Niu and Chuanyi Li and Vincent Ng},
  title = {Deep Learning Meets Software Engineering: A Survey on Pre-Trained Models of Source Code},
  booktitle = {Proceedings of the 31st International Joint Conference on Artificial Intelligence and the 25th European Conference on Artificial Intelligence},
  pages = {5546--5555}, 
  year = 2022}