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

By Lili Mou, Rui Men, Ge Li, Lu Zhang, Zhi Jin. 2015

48 citations recorded by the source corpus.

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.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition, Hardware and Architecture, Code Generation & Program Synthesis

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. Mohit Bansal
2. Graham Neubig
3. Luke S. Zettlemoyer
4. Jianfeng Gao
5. Yoshua Bengio
6. Kyunghyun Cho
7. Phil Blunsom
8. Quoc V. Le

In Computer Vision and Pattern Recognition

1. Mohit Bansal
2. Luc Van Gool
3. Andrew Zisserman
4. Dacheng Tao
5. Trevor Darrell
6. Jianfeng Gao
7. Yi Yang
8. Jitendra Malik

In Hardware and Architecture

1. Sunghun Kim
2. Hongyu Zhang
3. Xiaodong Gu
4. Ge Li
5. David Lo
6. Phil Blunsom
7. Zhi Jin
8. Edward Grefenstette

In Code Generation & Program Synthesis

1. Ge Li
2. Zhi Jin
3. Hongyu Zhang
4. Sunghun Kim
5. Xiaodong Gu
6. Dongmei Zhang
7. Xin Xia
8. David Lo

Citations in the corpus

• CodeGeeX: A Pre-Trained Model for Code Generation with Multilingual Benchmarking on HumanEval-X (2023, background): “By treating programs as language sequences, neural sequential architectures, such as recurrent neural networks and trans-former [36], can be naturally applied to code generation.”
• Latent Predictor Networks for Code Generation (2016, methodology): “Character-based sequence-to-sequence models have previously been used to generate code from natural language in (Mou et al., 2015).”
• Deep API learning (2016, methodology): “[34] proposed to generate code from natural language user intentions using an RNN Encoder-Decoder model.”
• Deep Code Search (2018, methodology): “A typical use of deep learning is code generation [42, 54].”
• Deep Code Comment Generation (2018, background): “, fault detection [32], code completion [27, 29], code clone [38] and code summarization [19].”
• CodeGeeX: A Pre-Trained Model for Code Generation with Multilingual Evaluations on HumanEval-X (2023, methodology): “…1977) to modern program synthesis systems (Solar-Lezama, 2008; Polozov and Gulwani, 2015), to end-to-end code generation via deep neural networks (Mou et al., 2015; Svyatkovskiy et al., 2020; Sun et al., 2020), tremendous efforts have been made to enable machines to automatically write correct…”
• CoCoNuT: combining context-aware neural translation models using ensemble for program repair (2020, methodology): “Deep Learning in Software Engineering: The software engineering community had applied deep learning to perform various tasks such as defects prediction [40, 79, 81], source code representation [6, 7, 66, 80], source code summarization [4, 22] source code modeling [5, 11, 26, 83], code clone detectio”
• CodeGen-Test: An Automatic Code Generation Model Integrating Program Test Information (2022, background): “However, in the early stage, only simple code vocabulary sequence can be generated [13], [14], which can not meet the requirements of correct code grammar.”