# Code Generation as a Dual Task of Code Summarization

arXiv: https://arxiv.org/abs/1910.05923 · HTML: https://mlsanity.com/paper/1910.05923/

## Key facts

- Cited by 62 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 14 Oct 2019.

## Built on by (most cited first, 30 of 62)

- [CodeXGLUE: A Machine Learning Benchmark Dataset for Code Understanding and Generation](https://mlsanity.com/paper/2102.04664/) (2021)
- [Retrieval Augmented Code Generation and Summarization](https://mlsanity.com/paper/2108.11601/) (2021)
- [KaggleDBQA: Realistic Evaluation of Text-to-SQL Parsers](https://mlsanity.com/paper/2106.11455/) (2021)
- [Retrieval-Augmented Generation for Code Summarization via Hybrid GNN](https://mlsanity.com/paper/2006.05405/) (2020)
- [Is ChatGPT the Ultimate Programming Assistant -- How far is it?](https://mlsanity.com/paper/2304.11938/) (2023)
- [Automatic Semantic Augmentation of Language Model Prompts (for Code Summarization)](https://mlsanity.com/paper/2304.06815/) (2023)
- [Out of the BLEU: how should we assess quality of the Code Generation models?](https://mlsanity.com/paper/2208.03133/) (2022)
- [On the Evaluation of Neural Code Summarization](https://mlsanity.com/paper/2107.07112/) (2021)
- [Compilable Neural Code Generation with Compiler Feedback](https://mlsanity.com/paper/2203.05132/) (2022)
- [Multilingual training for Software Engineering](https://mlsanity.com/paper/2112.02043/) (2021)
- [Neural-Symbolic Solver for Math Word Problems with Auxiliary Tasks](https://mlsanity.com/paper/2107.01431/) (2021)
- [Learning Deep Semantics for Test Completion](https://mlsanity.com/paper/2302.10166/) (2023)
- [Code Structure Guided Transformer for Source Code Summarization](https://mlsanity.com/paper/2104.09340/) (2021)
- [CodeQA: A Question Answering Dataset for Source Code Comprehension](https://mlsanity.com/paper/2109.08365/) (2021)
- [On Multi-Modal Learning of Editing Source Code](https://mlsanity.com/paper/2108.06645/) (2021)
- [Automatically Generating UI Code from Screenshot: A Divide-and-Conquer-Based Approach](https://mlsanity.com/paper/2406.16386/) (2024)
- [CoDesc: A Large Code-Description Parallel Dataset](https://mlsanity.com/paper/2105.14220/) (2021)
- [Unsupervised Evaluation of Code LLMs with Round-Trip Correctness](https://mlsanity.com/paper/2402.08699/) (2024)
- [Deep Learning for Code Intelligence: Survey, Benchmark and Toolkit](https://mlsanity.com/paper/2401.00288/) (2023)
- [Improving Code Summarization with Block-wise Abstract Syntax Tree Splitting](https://mlsanity.com/paper/2103.07845/) (2021)
- [An Extractive-and-Abstractive Framework for Source Code Summarization](https://mlsanity.com/paper/2206.07245/) (2022)
- [Exploring the Robustness of Large Language Models for Solving Programming Problems](https://mlsanity.com/paper/2306.14583/) (2023)
- [Prompt-based Code Completion via Multi-Retrieval Augmented Generation](https://mlsanity.com/paper/2405.07530/) (2024)
- [Benchmarking and Explaining Large Language Model-based Code Generation: A Causality-Centric Approach](https://mlsanity.com/paper/2310.06680/) (2023)
- [Source Code Summarization with Structural Relative Position Guided Transformer](https://mlsanity.com/paper/2202.06521/) (2022)
- [AST-Transformer: Encoding Abstract Syntax Trees Efficiently for Code Summarization](https://mlsanity.com/paper/2112.01184/) (2021)
- [API2Com: On the Improvement of Automatically Generated Code Comments Using API Documentations](https://mlsanity.com/paper/2103.10668/) (2021)
- [Improving Tree-Structured Decoder Training for Code Generation via Mutual Learning](https://mlsanity.com/paper/2105.14796/) (2021)
- [Exploring Dynamic Selection of Branch Expansion Orders for Code Generation](https://mlsanity.com/paper/2106.00261/) (2021)
- [HierarchyNet: Learning to Summarize Source Code with Heterogeneous Representations](https://mlsanity.com/paper/2205.15479/) (2022)

## Abstract (arXiv)

Code summarization (CS) and code generation (CG) are two crucial tasks in the field of automatic software development. Various neural network-based approaches are proposed to solve these two tasks separately. However, there exists a specific intuitive correlation between CS and CG, which have not been exploited in previous work. In this paper, we apply the relations between two tasks to improve the performance of both tasks. In other words, exploiting the duality between the two tasks, we propose a dual training framework to train the two tasks simultaneously. In this framework, we consider the dualities on probability and attention weights, and design corresponding regularization terms to constrain the duality. We evaluate our approach on two datasets collected from GitHub, and experimental results show that our dual framework can improve the performance of CS and CG tasks over baselines.