CodeStylist: A System for Performing Code Style Transfer Using Neural Networks

Authors

  • Chih-Kai Ting University of California Santa Cruz
  • Karl Munson University of California Santa Cruz
  • Serenity Wade University of California Santa Cruz
  • Anish Savla University of California Santa Cruz
  • Kiran Kate IBM Research
  • Kavitha Srinivas IBM Research

DOI:

https://doi.org/10.1609/aaai.v37i13.27087

Keywords:

Language Model Probing, Code Style, Generation, CodeT5, Pre-Trained Language Model, Python

Abstract

Code style refers to attributes of computer programs that affect their readability, maintainability, and performance. Enterprises consider code style as important and enforce style requirements during code commits. Tools that assist in coding style compliance and transformations are highly valuable. However, many key aspects of programming style transfer are difficult to automate, as it can be challenging to specify the patterns required to perform the transfer algorithmically. In this paper, we describe a system called CodeStylist which uses neural methods to perform style transfer on code.

Downloads

Published

2024-07-15

How to Cite

Ting, C.-K., Munson, K., Wade, S., Savla, A., Kate, K., & Srinivas, K. (2024). CodeStylist: A System for Performing Code Style Transfer Using Neural Networks. Proceedings of the AAAI Conference on Artificial Intelligence, 37(13), 16485-16487. https://doi.org/10.1609/aaai.v37i13.27087