Toward Code Generation: A Survey and Lessons from Semantic Parsing
arXiv:2105.03317
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.
arXiv comment12 pages, 6 figures
References in corpus (18)
- Learning to Map Sentences to Logical Form: Structured Classification with Probabilistic Categorial Grammars
- Seq2SQL: Generating Structured Queries from Natural Language using Reinforcement Learning
- Snorkel: Rapid Training Data Creation with Weak Supervision
- Neo: A Learned Query Optimizer
- Incorporating Copying Mechanism in Sequence-to-Sequence Learning
- DeepCoder: Learning to Write Programs
- Language to Logical Form with Neural Attention
- A Syntactic Neural Model for General-Purpose Code Generation
- Latent Predictor Networks for Code Generation
- Neural Code Comprehension: A Learnable Representation of Code Semantics
- Learning Dependency-Based Compositional Semantics
- Neural Module Networks for Reasoning over Text
- Program Synthesis and Semantic Parsing with Learned Code Idioms
- Coarse-to-Fine Decoding for Neural Semantic Parsing
- Selecting Representative Examples for Program Synthesis
- Inferring Logical Forms From Denotations
- The Three Pillars of Machine Programming
- Confidence Modeling for Neural Semantic Parsing