English

Inferring Javascript types using Graph Neural Networks

Machine Learning 2019-05-17 v1 Programming Languages Software Engineering Machine Learning

Abstract

The recent use of `Big Code' with state-of-the-art deep learning methods offers promising avenues to ease program source code writing and correction. As a first step towards automatic code repair, we implemented a graph neural network model that predicts token types for Javascript programs. The predictions achieve an accuracy above 90%90\%, which improves on previous similar work.

Keywords

Cite

@article{arxiv.1905.06707,
  title  = {Inferring Javascript types using Graph Neural Networks},
  author = {Jessica Schrouff and Kai Wohlfahrt and Bruno Marnette and Liam Atkinson},
  journal= {arXiv preprint arXiv:1905.06707},
  year   = {2019}
}

Comments

Published at the Representation Learning on Graphs and Manifolds ICLR 2019 workshop (https://rlgm.github.io/papers/)