# Retrieve and Refine: Exemplar-based Neural Comment Generation

arXiv: https://arxiv.org/abs/1910.10419 · HTML: https://mlsanity.com/paper/1910.10419/

## Key facts

- Cited by 36 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 23 Oct 2019.

## Built on by (most cited first, 30 of 36)

- [Retrieval-Augmented Generation for AI-Generated Content: A Survey](https://mlsanity.com/paper/2402.19473/) (2024)
- [ReACC: A Retrieval-Augmented Code Completion Framework](https://mlsanity.com/paper/2203.07722/) (2022)
- [On the Evaluation of Neural Code Summarization](https://mlsanity.com/paper/2107.07112/) (2021)
- [Multilingual training for Software Engineering](https://mlsanity.com/paper/2112.02043/) (2021)
- [Automatic Code Summarization via ChatGPT: How Far Are We?](https://mlsanity.com/paper/2305.12865/) (2023)
- [Code Structure Guided Transformer for Source Code Summarization](https://mlsanity.com/paper/2104.09340/) (2021)
- [RACE: Retrieval-Augmented Commit Message Generation](https://mlsanity.com/paper/2203.02700/) (2022)
- [AceCoder: Utilizing Existing Code to Enhance Code Generation](https://mlsanity.com/paper/2303.17780/) (2023)
- [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)
- [EditSum: A Retrieve-and-Edit Framework for Source Code Summarization](https://mlsanity.com/paper/2308.13775/) (2023)
- [Source Code Summarization with Structural Relative Position Guided Transformer](https://mlsanity.com/paper/2202.06521/) (2022)
- [M2TS: Multi-Scale Multi-Modal Approach Based on Transformer for Source Code Summarization](https://mlsanity.com/paper/2203.09707/) (2022)
- [API2Com: On the Improvement of Automatically Generated Code Comments Using API Documentations](https://mlsanity.com/paper/2103.10668/) (2021)
- [BashExplainer: Retrieval-Augmented Bash Code Comment Generation based on Fine-tuned CodeBERT](https://mlsanity.com/paper/2206.13325/) (2022)
- [A Prompt Learning Framework for Source Code Summarization](https://mlsanity.com/paper/2312.16066/) (2023)
- [Expository Text Generation: Imitate, Retrieve, Paraphrase](https://mlsanity.com/paper/2305.03276/) (2023)
- [ESALE: Enhancing Code-Summary Alignment Learning for Source Code Summarization](https://mlsanity.com/paper/2407.01646/) (2024)
- [Keeping Deep Learning Models in Check: A History-Based Approach to Mitigate Overfitting](https://mlsanity.com/paper/2401.10359/) (2024)
- [Retrieval-Augmented Code Review Comment Generation](https://mlsanity.com/paper/2506.11591/) (2025)
- [Improving Stack Overflow question title generation with copying enhanced CodeBERT model and bi-modal information](https://mlsanity.com/paper/2109.13073/) (2021)
- [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)
- [A Survey of Deep Learning Models for Structural Code Understanding](https://mlsanity.com/paper/2205.01293/) (2022)
- [Automatic Comment Generation via Multi-Pass Deliberation](https://mlsanity.com/paper/2209.06634/) (2022)
- [Revisiting File Context for Source Code Summarization](https://mlsanity.com/paper/2309.02326/) (2023)
- [The Role of Transformer Models in Advancing Blockchain Technology: A Systematic Survey](https://mlsanity.com/paper/2409.02139/) (2024)
- [APIContext2Com: Code Comment Generation by Incorporating Pre-Defined API Documentation](https://mlsanity.com/paper/2303.01645/) (2023)
- [MESIA: Understanding and Leveraging Supplementary Nature of Method-level Comments for Automatic Comment Generation](https://mlsanity.com/paper/2403.17357/) (2024)
- [LAMNER: Code Comment Generation Using Character Language Model and Named Entity Recognition](https://mlsanity.com/paper/2204.09654/) (2022)

## Abstract (arXiv)

Code comment generation is a crucial task in the field of automatic software development. Most previous neural comment generation systems used an encoder-decoder neural network and encoded only information from source code as input. Software reuse is common in software development. However, this feature has not been introduced to existing systems. Inspired by the traditional IR-based approaches, we propose to use the existing comments of similar source code as exemplars to guide the comment generation process. Based on an open source search engine, we first retrieve a similar code and treat its comment as an exemplar. Then we applied a seq2seq neural network to conduct an exemplar-based comment generation. We evaluate our approach on a large-scale Java corpus, and experimental results demonstrate that our model significantly outperforms the state-of-the-art methods.