---
title: "Compositional Program Synthesis from Natural Language and Examples"
authors:
  - "Mohammad Raza"
  - "Sumit Gulwani"
  - "Natasa Milic-Frayling"
doi: ""
url: "https://ijcai.org/proceedings/2015/117"
pdf: "https://ijcai.org/proceedings/2015/0117.pdf"
venue: "Proceedings of the Twenty-Fourth International Joint Conference on Artificial Intelligence"
year: 2015
pages: "792-799"
track: "Main Track"
keywords:
---

# Compositional Program Synthesis from Natural Language and Examples

Mohammad Raza, Sumit Gulwani, Natasa Milic-Frayling

*Proceedings of the Twenty-Fourth International Joint Conference on Artificial Intelligence*, pages 792-799.

## Abstract

Compositionality is a fundamental notion in computation whereby complex abstractions can be constructed from simpler ones, but this property has so far escaped the paradigm of end-user programming from examples or natural language. Existing approaches restrict end users to only give holistic end-to-end specifications, which limits the expressivity and scalability of these approaches to relatively simple programs in very restricted domains. In this paper we propose a new approach to end-user program synthesis in which input can be given in a compositional manner through a combination of natural language and examples. We present a domain-agnostic program synthesis algorithm and demonstrate its application to an expressive string manipulation language. We evaluate on a range of complex examples from help forums that are beyond the scope of previous systems.