# Convolutional Neural Networks over Tree Structures for Programming Language Processing

arXiv: https://arxiv.org/abs/1409.5718 · HTML: https://mlsanity.com/paper/1409.5718/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 18 Sep 2014.

## Built on by (most cited first, 10 of 10)

- [A Survey on Large Language Models for Code Generation](https://mlsanity.com/paper/2406.00515/) (2024)
- [Cross-Language Binary-Source Code Matching with Intermediate Representations](https://mlsanity.com/paper/2201.07420/) (2022)
- [SLOTH: Structured Learning and Task-based Optimization for Time Series Forecasting on Hierarchies](https://mlsanity.com/paper/2302.05650/) (2023)
- [A Survey of Deep Learning Models for Structural Code Understanding](https://mlsanity.com/paper/2205.01293/) (2022)
- [Malicious Source Code Detection Using Transformer](https://mlsanity.com/paper/2209.07957/) (2022)
- [Comparative Code Structure Analysis using Deep Learning for Performance Prediction](https://mlsanity.com/paper/2102.07660/) (2021)
- [Region4Web: Rethinking Observation Space Granularity for Web Agents](https://mlsanity.com/paper/2605.07134/) (2026)
- [Exploring Representation of Horn Clauses using GNNs (Extended Technical Report)](https://mlsanity.com/paper/2206.06986/) (2022)
- [Automated Vulnerability Detection in Source Code Using Deep Representation Learning](https://mlsanity.com/paper/2602.23121/) (2026)
- [All-In-One: Artificial Association Neural Networks](https://mlsanity.com/paper/2111.00424/) (2021)

## Abstract (arXiv)

Programming language processing (similar to natural language processing) is a hot research topic in the field of software engineering; it has also aroused growing interest in the artificial intelligence community. However, different from a natural language sentence, a program contains rich, explicit, and complicated structural information. Hence, traditional NLP models may be inappropriate for programs. In this paper, we propose a novel tree-based convolutional neural network (TBCNN) for programming language processing, in which a convolution kernel is designed over programs' abstract syntax trees to capture structural information. TBCNN is a generic architecture for programming language processing; our experiments show its effectiveness in two different program analysis tasks: classifying programs according to functionality, and detecting code snippets of certain patterns. TBCNN outperforms baseline methods, including several neural models for NLP.