Guided code synthesis using deep neural networks
Author:
Open Access
- 1 November 2016
- conference paper
- Published by Association for Computing Machinery (ACM)
- p. 1068-1070
Abstract
Can we teach computers how to program? Recent advances in neural network research reveal that certain neural networks are able not only to learn the syntax, grammar and semantics of arbitrary character sequences, but also synthesize new samples `in the style of' the original training data. We explore the adaptation of these techniques to code classification, comprehension and completion.Keywords
This publication has 11 references indexed in Scilit:
- Exploring the use of deep learning for feature location2015
- CACHECA: A Cache Language Model Based Code Suggestion Tool2015
- Toward Deep Learning Software Repositories2015
- Predicting Program Properties from "Big Code"2015
- Code completion with statistical language models2014
- Code completion with statistical language modelsACM SIGPLAN Notices, 2014
- Mining StackOverflow to turn the IDE into a self-confident programming prompter2014
- Hybrid speech recognition with Deep Bidirectional LSTM2013
- Statistical parametric speech synthesis using deep neural networks2013
- Learning from examples to improve code completion systems2009