On End-to-End Program Generation from User Intention by Deep Neural Networks
This work addresses the challenge of automating program generation for users, but it is incremental as it points out unresolved cross-disciplinary issues.
The paper tackles the problem of generating code from natural language user intentions using recurrent neural networks, demonstrating feasibility through a case study and empirical analysis.
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.