Year: 2015
Type: preprint
Abstract: 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 keyword-programming 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.
Source: arXiv (Cornell University)
Authors: Desai, Aditya, Gulwani, Sumit, Hingorani, Vineet, Jain, Nidhi, Karkare, Amey, Marron, Mark, R, Sailesh, Roy, Subhajit
Institution: Indian Institute of Technology Kanpur
Language: English
Subfield: Information Systems
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W2952115883
