Inferring Javascript types using Graph Neural Networks

J. Schrouff, K. Wohlfahrt, B. Marnette, L. Atkinson. Representation Learning on Graphs and Manifolds ICLR 2019 workshop 2019

     

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%, which improves on previous similar work.