On End-to-End Program Generation from User Intention by Deep Neural Networks

2015/10/25 by Lili Mou, Rui Men, Mou, Lili +7 · 1 voice
Computer Science · #Advanced Neural Network Applications #Parallel Computing and Optimization Techniques #Reinforcement Learning in Robotics #cs.LG #cs.SE

paper · pdf · doi:10.48550/arxiv.1510.07211

openalex publication_date 2015/10/25 · openalex created_date 2016/06/24 · openalex updated_date 2026/07/28

Abstract

This paper envisions an end-to-end program generation scenario using recurrent neural networks (RNNs): Users can express their intention in natural language; an RNN then automatically generates corresponding code in a characterby-by-character fashion. We demonstrate its feasibility through a case study and empirical analysis. To fully make such technique useful in practice, we also point out several cross-disciplinary challenges, including modeling user intention, providing datasets, improving model architectures, etc. Although much long-term research shall be addressed in this new field, we believe end-to-end program generation would become a reality in future decades, and we are looking forward to its practice.

Citations

• On the difficulty of training Recurrent Neural Networks
• Long Short-Term Memory
• Sequence to Sequence Learning with Neural Networks

Discussions

• On End-To-End Program Generation from User Intention by Deep Neural Networks [hn, 20 points, 1 comments]

Related

• Automated Source Code Generation and Auto-completion Using Deep Learning: Comparing and Discussing Current Language-Model-Related Approaches
• Towards Machine-Generated Code for the Resolution of User Intentions
• Recent Advances in Neural Program Synthesis
• Neural Models for Source Code Synthesis and Completion
• EgoCoder: Intelligent Program Synthesis with Hierarchical Sequential Neural Network Model