Skip to yearly menu bar Skip to main content


Poster

Generative Code Modeling with Graphs

Marc Brockschmidt · Miltiadis Allamanis · Alexander Gaunt · Oleksandr Polozov

Great Hall BC #20

Keywords: [ source code ] [ generative model ] [ graph learning ]


Abstract:

Generative models forsource 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. Our model generates code by interleaving 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.

Live content is unavailable. Log in and register to view live content