# Abstract Syntax Networks for Code Generation and Semantic Parsing

arXiv: https://arxiv.org/abs/1704.07535 · HTML: https://mlsanity.com/paper/1704.07535/

## Key facts

- Cited by 92 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 25 Apr 2017.

## Built on by (most cited first, 30 of 92)

- [LEVER: Learning to Verify Language-to-Code Generation with Execution](https://mlsanity.com/paper/2302.08468/) (2023)
- [Efficient Guided Generation for Large Language Models](https://mlsanity.com/paper/2307.09702/) (2023)
- [MapCoder: Multi-Agent Code Generation for Competitive Problem Solving](https://mlsanity.com/paper/2405.11403/) (2024)
- [DocPrompting: Generating Code by Retrieving the Docs](https://mlsanity.com/paper/2207.05987/) (2022)
- [Retrieval Augmented Code Generation and Summarization](https://mlsanity.com/paper/2108.11601/) (2021)
- [Natural Language to Code Translation with Execution](https://mlsanity.com/paper/2204.11454/) (2022)
- [Execution-based Code Generation using Deep Reinforcement Learning](https://mlsanity.com/paper/2301.13816/) (2023)
- [RnG-KBQA: Generation Augmented Iterative Ranking for Knowledge Base Question Answering](https://mlsanity.com/paper/2109.08678/) (2021)
- [Tool Documentation Enables Zero-Shot Tool-Usage with Large Language Models](https://mlsanity.com/paper/2308.00675/) (2023)
- [Out of the BLEU: how should we assess quality of the Code Generation models?](https://mlsanity.com/paper/2208.03133/) (2022)
- [AI-Generated Content (AIGC): A Survey](https://mlsanity.com/paper/2304.06632/) (2023)
- [A Syntax-Guided Edit Decoder for Neural Program Repair](https://mlsanity.com/paper/2106.08253/) (2021)
- [Compilable Neural Code Generation with Compiler Feedback](https://mlsanity.com/paper/2203.05132/) (2022)
- [TreeBERT: A Tree-Based Pre-Trained Model for Programming Language](https://mlsanity.com/paper/2105.12485/) (2021)
- [MCoNaLa: A Benchmark for Code Generation from Multiple Natural Languages](https://mlsanity.com/paper/2203.08388/) (2022)
- [Automatic Programming: Large Language Models and Beyond](https://mlsanity.com/paper/2405.02213/) (2024)
- [StructCoder: Structure-Aware Transformer for Code Generation](https://mlsanity.com/paper/2206.05239/) (2022)
- [AST-T5: Structure-Aware Pretraining for Code Generation and Understanding](https://mlsanity.com/paper/2401.03003/) (2024)
- [CODESIM: Multi-Agent Code Generation and Problem Solving through Simulation-Driven Planning and Debugging](https://mlsanity.com/paper/2502.05664/) (2025)
- [Sequence-to-Sequence Learning with Latent Neural Grammars](https://mlsanity.com/paper/2109.01135/) (2021)
- [How could Neural Networks understand Programs?](https://mlsanity.com/paper/2105.04297/) (2021)
- [HumanEvalComm: Benchmarking the Communication Competence of Code Generation for LLMs and LLM Agent](https://mlsanity.com/paper/2406.00215/) (2024)
- [Deep Learning for Code Intelligence: Survey, Benchmark and Toolkit](https://mlsanity.com/paper/2401.00288/) (2023)
- [An Empirical Study of Retrieval-Augmented Code Generation: Challenges and Opportunities](https://mlsanity.com/paper/2501.13742/) (2025)
- [B-Coder: Value-Based Deep Reinforcement Learning for Program Synthesis](https://mlsanity.com/paper/2310.03173/) (2023)
- [Learning Structural Edits via Incremental Tree Transformations](https://mlsanity.com/paper/2101.12087/) (2021)
- [Shellcode_IA32: A Dataset for Automatic Shellcode Generation](https://mlsanity.com/paper/2104.13100/) (2021)
- [KNOD: Domain Knowledge Distilled Tree Decoder for Automated Program Repair](https://mlsanity.com/paper/2302.01857/) (2023)
- [Sequence to General Tree: Knowledge-Guided Geometry Word Problem Solving](https://mlsanity.com/paper/2106.00990/) (2021)
- [Incorporating Domain Knowledge through Task Augmentation for Front-End JavaScript Code Generation](https://mlsanity.com/paper/2208.10091/) (2022)

## Abstract (arXiv)

Tasks like code generation and semantic parsing require mapping unstructured (or partially structured) inputs to well-formed, executable outputs. We introduce abstract syntax networks, a modeling framework for these problems. The outputs are represented as abstract syntax trees (ASTs) and constructed by a decoder with a dynamically-determined modular structure paralleling the structure of the output tree. On the benchmark Hearthstone dataset for code generation, our model obtains 79.2 BLEU and 22.7% exact match accuracy, compared to previous state-of-the-art values of 67.1 and 6.1%. Furthermore, we perform competitively on the Atis, Jobs, and Geo semantic parsing datasets with no task-specific engineering.