# CAST: Enhancing Code Summarization with Hierarchical Splitting and Reconstruction of Abstract Syntax Trees

arXiv: https://arxiv.org/abs/2108.12987 · HTML: https://mlsanity.com/paper/2108.12987/

## Key facts

- Cited by 32 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 30 Aug 2021.

## Built on by (most cited first, 30 of 32)

- [Agents in Software Engineering: Survey, Landscape, and Vision](https://mlsanity.com/paper/2409.09030/) (2024)
- [RACE: Retrieval-Augmented Commit Message Generation](https://mlsanity.com/paper/2203.02700/) (2022)
- [CoCoSoDa: Effective Contrastive Learning for Code Search](https://mlsanity.com/paper/2204.03293/) (2022)
- [Deep Learning for Code Intelligence: Survey, Benchmark and Toolkit](https://mlsanity.com/paper/2401.00288/) (2023)
- [An Extractive-and-Abstractive Framework for Source Code Summarization](https://mlsanity.com/paper/2206.07245/) (2022)
- [Nova: Generative Language Models for Assembly Code with Hierarchical Attention and Contrastive Learning](https://mlsanity.com/paper/2311.13721/) (2023)
- [CP-BCS: Binary Code Summarization Guided by Control Flow Graph and Pseudo Code](https://mlsanity.com/paper/2310.16853/) (2023)
- [Towards an Understanding of Context Utilization in Code Intelligence](https://mlsanity.com/paper/2504.08734/) (2025)
- [HierarchyNet: Learning to Summarize Source Code with Heterogeneous Representations](https://mlsanity.com/paper/2205.15479/) (2022)
- [EyeTrans: Merging Human and Machine Attention for Neural Code Summarization](https://mlsanity.com/paper/2402.14096/) (2024)
- [SoTaNa: The Open-Source Software Development Assistant](https://mlsanity.com/paper/2308.13416/) (2023)
- [ESALE: Enhancing Code-Summary Alignment Learning for Source Code Summarization](https://mlsanity.com/paper/2407.01646/) (2024)
- [ShieldedCode: Learning Robust Representations for Virtual Machine Protected Code](https://mlsanity.com/paper/2601.20679/) (2026)
- [AlignCoder: Aligning Retrieval with Target Intent for Repository-Level Code Completion](https://mlsanity.com/paper/2601.19697/) (2026)
- [Tram: A Token-level Retrieval-augmented Mechanism for Source Code Summarization](https://mlsanity.com/paper/2305.11074/) (2023)
- [GypSum: Learning Hybrid Representations for Code Summarization](https://mlsanity.com/paper/2204.12916/) (2022)
- [Abstract Syntax Tree for Programming Language Understanding and Representation: How Far Are We?](https://mlsanity.com/paper/2312.00413/) (2023)
- [WAFFLE: Finetuning Multi-Modal Models for Automated Front-End Development](https://mlsanity.com/paper/2410.18362/) (2024)
- [EffiReasonTrans: RL-Optimized Reasoning for Code Translation](https://mlsanity.com/paper/2510.18863/) (2025)
- [A Survey of Deep Learning Models for Structural Code Understanding](https://mlsanity.com/paper/2205.01293/) (2022)
- [NS3: Neuro-Symbolic Semantic Code Search](https://mlsanity.com/paper/2205.10674/) (2022)
- [A Survey on Natural Language Processing for Programming](https://mlsanity.com/paper/2212.05773/) (2022)
- [ShortCoder: Knowledge-Augmented Syntax Optimization for Token-Efficient Code Generation](https://mlsanity.com/paper/2601.09703/) (2026)
- [DRAINCODE: Stealthy Energy Consumption Attacks on Retrieval-Augmented Code Generation via Context Poisoning](https://mlsanity.com/paper/2601.20615/) (2026)
- [Diverse Title Generation for Stack Overflow Posts with Multiple Sampling Enhanced Transformer](https://mlsanity.com/paper/2208.11523/) (2022)
- [PhoenixRepair: Rethinking Repair Strategy Exploration in Software Agents](https://mlsanity.com/paper/2607.18859/) (2026)
- [Learning Rate Perturbation: A Generic Plugin of Learning Rate Schedule towards Flatter Local Minima](https://mlsanity.com/paper/2208.11873/) (2022)
- [Knowledge Transfer for Pseudo-code Generation from Low Resource Programming Language](https://mlsanity.com/paper/2303.09062/) (2023)
- [An Exploratory Literature Study on Sharing and Energy Use of Language Models for Source Code](https://mlsanity.com/paper/2307.02443/) (2023)
- [Backdoors in Code Summarizers: How Bad Is It?](https://mlsanity.com/paper/2506.01825/) (2025)

## Abstract (arXiv)

Code summarization aims to generate concise natural language descriptions of source code, which can help improve program comprehension and maintenance. Recent studies show that syntactic and structural information extracted from abstract syntax trees (ASTs) is conducive to summary generation. However, existing approaches fail to fully capture the rich information in ASTs because of the large size/depth of ASTs. In this paper, we propose a novel model CAST that hierarchically splits and reconstructs ASTs. First, we hierarchically split a large AST into a set of subtrees and utilize a recursive neural network to encode the subtrees. Then, we aggregate the embeddings of subtrees by reconstructing the split ASTs to get the representation of the complete AST. Finally, AST representation, together with source code embedding obtained by a vanilla code token encoder, is used for code summarization. Extensive experiments, including the ablation study and the human evaluation, on benchmarks have demonstrated the power of CAST. To facilitate reproducibility, our code and data are available at https://anonymous.4open.science/r/CAST/.