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

TL;DR

This paper explores using recurrent neural networks for end-to-end program generation from natural language, demonstrating feasibility through a case study and discussing practical challenges for future development.

Contribution

It introduces a novel approach of character-by-character code generation from user intentions using RNNs and discusses key challenges for practical application.

Findings

Feasibility demonstrated via case study

Identified challenges in modeling and datasets

Future potential of end-to-end program generation

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.