Deep Learning for Source Code Modeling and Generation: Models, Applications and Challenges
arXiv:2002.05442 · doi:10.1145/3383458
Abstract
Deep Learning (DL) techniques for Natural Language Processing have been evolving remarkably fast. Recently, the DL advances in language modeling, machine translation and paragraph understanding are so prominent that the potential of DL in Software Engineering cannot be overlooked, especially in the field of program learning. To facilitate further research and applications of DL in this field, we provide a comprehensive review to categorize and investigate existing DL methods for source code modeling and generation. To address the limitations of the traditional source code models, we formulate common program learning tasks under an encoder-decoder framework. After that, we introduce recent DL mechanisms suitable to solve such problems. Then, we present the state-of-the-art practices and discuss their challenges with some recommendations for practitioners and researchers as well.
References in corpus (3)
Cited by in corpus (22)
- A Survey on Data-driven Software Vulnerability Assessment and Prioritization
- Review: Deep Learning in Electron Microscopy
- Deep Learning-based Software Engineering: Progress, Challenges, and Opportunities
- Machine Learning for Software Engineering: A Tertiary Study
- PromSec: Prompt Optimization for Secure Generation of Functional Source Code with Large Language Models (LLMs)
- Memorization and Generalization in Neural Code Intelligence Models
- SALLM: Security Assessment of Generated Code
- Misty: UI Prototyping Through Interactive Conceptual Blending
- A Survey on Machine Learning Techniques for Source Code Analysis
- Multi-task Learning based Pre-trained Language Model for Code Completion
- CoT-TL: Low-Resource Temporal Knowledge Representation of Planning Instructions Using Chain-of-Thought Reasoning
- Improving Code Summarization with Block-wise Abstract Syntax Tree Splitting
- Contextualized Data-Wrangling Code Generation in Computational Notebooks
- Automated Code-centric Software Vulnerability Assessment: How Far Are We? An Empirical Study in C/C++
- MalCodeAI: Autonomous Vulnerability Detection and Remediation via Language Agnostic Code Reasoning
- Automated Source Code Generation and Auto-completion Using Deep Learning: Comparing and Discussing Current Language-Model-Related Approaches
- Learning to generate Reliable Broadcast Algorithms
- Intent Preserving Generation of Diverse and Idiomatic (Code-)Artifacts
- PromCopilot: Simplifying Prometheus Metric Querying in Cloud Native Online Service Systems via Large Language Models
- Automated Security Assessment for the Internet of Things
- Mining Program Properties From Neural Networks Trained on Source Code Embeddings
- Towards Top-Down Automated Development in Limited Scopes: A Neuro-Symbolic Framework from Expressibles to Executables