Toward Code Generation: A Survey and Lessons from Semantic Parsing

2021/04/26 by Celine Lee, Justin Gottschlich, Lee, Celine +3 · 9 citations
Computer Science · #Artificial intelligence #Computation and Language (cs.CL) #Computer science #Domain (mathematical analysis) #FOS: Computer and information sciences #Machine Learning (cs.LG) #Natural Language Processing Techniques #Natural language #Natural language processing #Parallels #Parsing #Perspective (graphical) #Programming Languages (cs.PL) #Programming language #Software Engineering (cs.SE) #Software Engineering Research #Software Testing and Debugging Techniques #cs.CL #cs.LG #cs.PL #cs.SE

paper · pdf · doi:10.48550/arxiv.2105.03317

published in arXiv (Cornell University) (Cornell University) · 12 pages, 6 figures

arxiv created 2021/04/26 · openalex publication_date 2021/04/26 · arxiv updated 2021/05/19 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

With the growth of natural language processing techniques and demand for improved software engineering efficiency, there is an emerging interest in translating intention from human languages to programming languages. In this survey paper, we attempt to provide an overview of the growing body of research in this space. We begin by reviewing natural language semantic parsing techniques and draw parallels with program synthesis efforts. We then consider semantic parsing works from an evolutionary perspective, with specific analyses on neuro-symbolic methods, architecture, and supervision. We then analyze advancements in frameworks for semantic parsing for code generation. In closing, we present what we believe are some of the emerging open challenges in this domain.

Citations

• Learning to Map Sentences to Logical Form: Structured Classification\n with Probabilistic Categorial Grammars
• Language to Logical Form with Neural Attention
• Incorporating Copying Mechanism in Sequence-to-Sequence Learning
• Latent Predictor Networks for Code Generation
• DeepCoder: Learning to Write Programs
• A Syntactic Neural Model for General-Purpose Code Generation
• Seq2SQL: Generating Structured Queries from Natural Language using Reinforcement Learning
• Coarse-to-Fine Decoding for Neural Semantic Parsing
• Learning Dependency-Based Compositional Semantics
• Neo: A Learned Query Optimizer

Cited by

• MISIM: A Neural Code Semantics Similarity System Using the Context-Aware Semantics Structure

Related

• A Syntactic Neural Model for General-Purpose Code Generation
• Program Synthesis and Semantic Parsing with Learned Code Idioms
• A Survey on Semantic Parsing
• Neural Models for Source Code Synthesis and Completion
• Bridging Code Semantic and LLMs: Semantic Chain-of-Thought Prompting for Code Generation