2018/05/22 by Marc Brockschmidt, Miltiadis Allamanis, Brockschmidt, Marc +5 · 2 citations
Computer Science · #FOS: Computer and information sciences #Machine Learning (cs.LG) #Machine Learning (stat.ML) #Natural Language Processing Techniques #Programming Languages (cs.PL) #Software Engineering Research #Topic Modeling
paper · pdf · doi:10.48550/arxiv.1805.08490
openalex publication_date 2018/05/22 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
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.