# Neural Sketch Learning for Conditional Program Generation

arXiv: https://arxiv.org/abs/1703.05698 · HTML: https://mlsanity.com/paper/1703.05698/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 16 Mar 2017.

## Built on by (most cited first, 3 of 3)

- [CodeXGLUE: A Machine Learning Benchmark Dataset for Code Understanding and Generation](https://mlsanity.com/paper/2102.04664/) (2021)
- [Natural Language-Guided Programming](https://mlsanity.com/paper/2108.05198/) (2021)
- [Addressing Leakage in Self-Supervised Contextualized Code Retrieval](https://mlsanity.com/paper/2204.11594/) (2022)

## Abstract (arXiv)

We study the problem of generating source code in a strongly typed, Java-like programming language, given a label (for example a set of API calls or types) carrying a small amount of information about the code that is desired. The generated programs are expected to respect a "realistic" relationship between programs and labels, as exemplified by a corpus of labeled programs available during training. Two challenges in such conditional program generation are that the generated programs must satisfy a rich set of syntactic and semantic constraints, and that source code contains many low-level features that impede learning. We address these problems by training a neural generator not on code but on program sketches, or models of program syntax that abstract out names and operations that do not generalize across programs. During generation, we infer a posterior distribution over sketches, then concretize samples from this distribution into type-safe programs using combinatorial techniques. We implement our ideas in a system for generating API-heavy Java code, and show that it can often predict the entire body of a method given just a few API calls or data types that appear in the method.