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

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.

Submitted to 2016 International Conference of Software Engineering "Vision of 2025 and Beyond" track

References in corpus (3)

• Sequence to Sequence Learning with Neural Networks
• Show, Attend and Tell: Neural Image Caption Generation with Visual Attention
• On the difficulty of training Recurrent Neural Networks

Cited by in corpus (8)

• Latent Predictor Networks for Code Generation
• A Comprehensive Review of State-of-The-Art Methods for Java Code Generation from Natural Language Text
• Embedding API Dependency Graph for Neural Code Generation
• Dataset for a Neural Natural Language Interface for Databases (NNLIDB)
• ENCORE: Ensemble Learning using Convolution Neural Machine Translation for Automatic Program Repair
• Holistic Combination of Structural and Textual Code Information for Context based API Recommendation
• Type I Attack for Generative Models
• Augmenting Machine Learning with Information Retrieval to Recommend Real Cloned Code Methods for Code Completion