# Towards Top-Down Automated Development in Limited Scopes: A Neuro-Symbolic Framework from Expressibles to Executables

arXiv: https://arxiv.org/abs/2209.01566 · HTML: https://mlsanity.com/paper/2209.01566/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 25 of its 46 references that are in the map.
- First posted on arXiv 4 Sep 2022.

## Builds on (most cited first, 25 of 25)

- [ImageNet Large Scale Visual Recognition Challenge](https://mlsanity.com/paper/1409.0575/) (2014)
- [Competition-Level Code Generation with AlphaCode](https://mlsanity.com/paper/2203.07814/) (2022)
- [CodeT5: Identifier-aware Unified Pre-trained Encoder-Decoder Models for Code Understanding and Generation](https://mlsanity.com/paper/2109.00859/) (2021)
- [CodeGen: An Open Large Language Model for Code with Multi-Turn Program Synthesis](https://mlsanity.com/paper/2203.13474/) (2022)
- [A Survey on Knowledge Graphs: Representation, Acquisition and Applications](https://mlsanity.com/paper/2002.00388/) (2020)
- [Unsupervised Translation of Programming Languages](https://mlsanity.com/paper/2006.03511/) (2020)
- [Text Generation from Knowledge Graphs with Graph Transformers](https://mlsanity.com/paper/1904.02342/) (2019)
- [Data Collection and Quality Challenges in Deep Learning: A Data-Centric AI Perspective](https://mlsanity.com/paper/2112.06409/) (2021)
- [Taxonomy of Real Faults in Deep Learning Systems](https://mlsanity.com/paper/1910.11015/) (2019)
- [TRANX: A Transition-based Neural Abstract Syntax Parser for Semantic Parsing and Code Generation](https://mlsanity.com/paper/1810.02720/) (2018)
- [Leveraging Automated Unit Tests for Unsupervised Code Translation](https://mlsanity.com/paper/2110.06773/) (2021)
- [Deep Learning for Source Code Modeling and Generation: Models, Applications and Challenges](https://mlsanity.com/paper/2002.05442/) (2020)
- [Deep API Learning](https://mlsanity.com/paper/1605.08535/) (2016)
- [A Systematic Literature Review on the Use of Deep Learning in Software Engineering Research](https://mlsanity.com/paper/2009.06520/) (2020)
- [CodeQA: A Question Answering Dataset for Source Code Comprehension](https://mlsanity.com/paper/2109.08365/) (2021)
- [Aroma: Code Recommendation via Structural Code Search](https://mlsanity.com/paper/1812.01158/) (2018)
- [Assemble Foundation Models for Automatic Code Summarization](https://mlsanity.com/paper/2201.05222/) (2022)
- [Context2Name: A Deep Learning-Based Approach to Infer Natural Variable Names from Usage Contexts](https://mlsanity.com/paper/1809.05193/) (2018)
- [StoryDroid: Automated Generation of Storyboard for Android Apps](https://mlsanity.com/paper/1902.00476/) (2019)
- [Toward Code Generation: A Survey and Lessons from Semantic Parsing](https://mlsanity.com/paper/2105.03317/) (2021)
- [PyART: Python API Recommendation in Real-Time](https://mlsanity.com/paper/2102.04706/) (2021)
- [Semantic Scaffolds for Pseudocode-to-Code Generation](https://mlsanity.com/paper/2005.05927/) (2020)
- [CSRS: Code Search with Relevance Matching and Semantic Matching](https://mlsanity.com/paper/2203.07736/) (2022)
- [The Development and Prospect of Code Clone](https://mlsanity.com/paper/2202.08497/) (2022)
- [Lupa: A Framework for Large Scale Analysis of the Programming Language Usage](https://mlsanity.com/paper/2203.09658/) (2022)

## Built on by (most cited first, 2 of 2)

- [Neuron Patching: Semantic-based Neuron-level Language Model Repair for Code Generation](https://mlsanity.com/paper/2312.05356/) (2023)
- [A Semantic-based Optimization Approach for Repairing LLMs: Case Study on Code Generation](https://mlsanity.com/paper/2503.12899/) (2025)

## Abstract (arXiv)

Deep code generation is a topic of deep learning for software engineering (DL4SE), which adopts neural models to generate code for the intended functions. Since end-to-end neural methods lack domain knowledge and software hierarchy awareness, they tend to perform poorly w.r.t project-level tasks. To systematically explore the potential improvements of code generation, we let it participate in the whole top-down development from expressibles to executables, which is possible in limited scopes. In the process, it benefits from massive samples, features, and knowledge. As the foundation, we suggest building a taxonomy on code data, namely code taxonomy, leveraging the categorization of code information. Moreover, we introduce a three-layer semantic pyramid (SP) to associate text data and code data. It identifies the information of different abstraction levels, and thus introduces the domain knowledge on development and reveals the hierarchy of software. Furthermore, we propose a semantic pyramid framework (SPF) as the approach, focusing on software of high modularity and low complexity. SPF divides the code generation process into stages and reserves spots for potential interactions. In addition, we conceived preliminary applications in software development to confirm the neuro-symbolic framework.