Program synthesis using natural language

Aditya Desai, Sumit Gulwani, Vineet Hingorani, Nidhi Jain, Amey Karkare, Mark Marron, R. Sailesh, Subhajit Roy

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

83 Scopus citations


Interacting with computers is a ubiquitous activity for millions of people. Repetitive or specialized tasks often require creation of small, often one-off, programs. End-users struggle with learning and using the myriad of domain-specific languages (DSLs) to effectively accomplish these tasks. We present a general framework for constructing program synthesizers that take natural language (NL) inputs and produce expressions in a target DSL. The framework takes as input a DSL definition and training data consisting of NL/DSL pairs. From these it constructs a synthesizer by learning optimal weights and classifiers (using NLP features) that rank the outputs of a keywordprogramming based translation. We applied our framework to three domains: repetitive text editing, an intelligent tutoring system, and flight information queries. On 1200+ English descriptions, the respective synthesizers rank the desired program as the top-1 and top-3 for 80% and 90% descriptions respectively.

Original languageEnglish
Title of host publicationProceedings - 2016 IEEE/ACM 38th IEEE International Conference on Software Engineering Companion, ICSE 2016
Number of pages12
ISBN (Electronic)9781450339001, 9781450342056
StatePublished - May 14 2016
Event2016 IEEE/ACM 38th IEEE International Conference on Software Engineering, ICSE 2016 - Austin, United States
Duration: May 14 2016May 22 2016

Publication series

NameProceedings - International Conference on Software Engineering
ISSN (Print)0270-5257


Conference2016 IEEE/ACM 38th IEEE International Conference on Software Engineering, ICSE 2016
Country/TerritoryUnited States

Bibliographical note

Publisher Copyright:
© 2016 ACM.

ASJC Scopus subject areas

  • Software


Dive into the research topics of 'Program synthesis using natural language'. Together they form a unique fingerprint.

Cite this