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

arXiv: https://arxiv.org/abs/1510.07211 · HTML: https://mlsanity.com/paper/1510.07211/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 25 Oct 2015.

## Built on by (most cited first, 6 of 6)

- [CodeGeeX: A Pre-Trained Model for Code Generation with Multilingual Benchmarking on HumanEval-X](https://mlsanity.com/paper/2303.17568/) (2023)
- [Large Language Model-Aware In-Context Learning for Code Generation](https://mlsanity.com/paper/2310.09748/) (2023)
- [Hot or Cold? Adaptive Temperature Sampling for Code Generation with Large Language Models](https://mlsanity.com/paper/2309.02772/) (2023)
- [Embedding API Dependency Graph for Neural Code Generation](https://mlsanity.com/paper/2103.15361/) (2021)
- [A Comprehensive Review of State-of-The-Art Methods for Java Code Generation from Natural Language Text](https://mlsanity.com/paper/2306.06371/) (2023)
- [Convolutional Neural Networks Exploiting Attributes of Biological Neurons](https://mlsanity.com/paper/2311.08314/) (2023)

## Abstract (arXiv)

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.