Generative Code Modeling with Graphs
Machine Learning
2019-04-18 v2 Programming Languages
Machine Learning
Abstract
Generative models for source code are an interesting structured prediction problem, requiring to reason about both hard syntactic and semantic constraints as well as about natural, likely programs. We present a novel model for this problem that uses a graph to represent the intermediate state of the generated output. The generative procedure interleaves grammar-driven expansion steps with graph augmentation and neural message passing steps. An experimental evaluation shows that our new model can generate semantically meaningful expressions, outperforming a range of strong baselines.
Cite
@article{arxiv.1805.08490,
title = {Generative Code Modeling with Graphs},
author = {Marc Brockschmidt and Miltiadis Allamanis and Alexander L. Gaunt and Oleksandr Polozov},
journal= {arXiv preprint arXiv:1805.08490},
year = {2019}
}