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

Changan Niu; Chuanyi Li; Bin Luo; Vincent Ng

IJCAI 2022poster54 citations

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

Changan Niu, Chuanyi Li, Bin Luo, Vincent Ng

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.

Survey Track: Knowledge Representation and Reasoning

BibTeX

@inproceedings{ijcai2022p775,
  title     = {Deep Learning Meets Software Engineering: A Survey on Pre-Trained Models of Source Code},
  author    = {Niu, Changan and Li, Chuanyi and Luo, Bin and Ng, Vincent},
  booktitle = {Proceedings of the Thirty-First International Joint Conference on
               Artificial Intelligence, {IJCAI-22}},
  publisher = {International Joint Conferences on Artificial Intelligence Organization},
  editor    = {Lud De Raedt},
  pages     = {5546--5555},
  year      = {2022},
  month     = {7},
  note      = {Survey Track},
  doi       = {10.24963/ijcai.2022/775},
  url       = {https://doi.org/10.24963/ijcai.2022/775},
}