BashExplainer: Retrieval-Augmented Bash Code Comment Generation based on Fine-tuned CodeBERT

Chen, Yu; Yang, Guang; Chen, Xiang; Liu, Ke; Zhou, Yanlin

doi:10.1109/icsme55016.2022.00016

Cited by 17 publications

(25 citation statements)

References 41 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Motivated by the neural machine translation research domain, one intuitive way is to model this problem as the automatic generation task, which can generate the required API for the developer's query directly. Although the popular generation models perform well in software engineering generation tasks (such as source code summarization [1,20,21,45,49], issue title generation [5,22], code generation [44,47], Stack Overflow title generation [23,51]), we find that the performance of this intuitive way is not promising after our preliminary investigation. Figure 1 shows two examples of generating incorrect APIs by using this intuitive generation approach.…”

Section: Introductionmentioning

confidence: 82%

APICom: Automatic API Completion via Prompt Learning and Adversarial Training-based Data Augmentation

Gu,

Shen,

Chen

et al. 2023

Proceedings of the 14th Asia-Pacific Symposium on Internetware

Self Cite

View full text Add to dashboard Cite

Based on developer needs and usage scenarios, API (Application Programming Interface) recommendation is the process of assisting developers in finding the required API among numerous candidate APIs. Previous studies mainly modeled API recommendation as the recommendation task, which can recommend multiple candidate APIs for the given query, and developers may not yet be able to find what they need. Motivated by the neural machine translation research domain, we can model this problem as the generation task, which aims to directly generate the required API for the developer query. After our preliminary investigation, we find the performance of this intuitive approach is not promising. The reason is that there exists an error when generating the prefixes of the API. However, developers may know certain API prefix information during actual development in most cases. Therefore, we model this problem as the automatic completion task and propose a novel approach API-Com based on prompt learning, which can generate API related to the query according to the prompts (i.e., API prefix information). Moreover, the effectiveness of APICom highly depends on the quality of the training dataset. In this study, we further design a novel gradient-based adversarial training method ATCom for data augmentation, which can improve the normalized stability when generating adversarial examples. To evaluate the effectiveness of APICom, we consider a corpus of 33k developer queries and corresponding APIs. Compared with the state-of-the-art baselines, our experimental results show that APICom can outperform all baselines by at least 40.02%, 13.20%, and 16.31% in terms of the performance measures EM@1, MRR, and MAP. Finally, our ablation studies confirm the effectiveness of our component setting (such as our designed adversarial training method, our used pre-trained model, and prompt learning) in APICom.

show abstract

Section: Introductionmentioning

confidence: 82%

APICom: Automatic API Completion via Prompt Learning and Adversarial Training-based Data Augmentation

Gu,

Shen,

Chen

et al. 2023

Proceedings of the 14th Asia-Pacific Symposium on Internetware

Self Cite

View full text Add to dashboard Cite

show abstract

“…The second group is deep learning approaches, including CodeBert [12], UniXcoder [13], and CodeT5 [14]. The last group is hybrid approaches, including Rencos [15] and BashExplainer [30].…”

Section: Baselinesmentioning

confidence: 99%

CCGRA: Smart Contract Code Comment Generation with Retrieval-enhanced Approach

Zhang,

Chen,

Fan

et al. 2023

International Conferences on Software Engineering and Knowledge Engineering

View full text Add to dashboard Cite

Smart contracts are self-executing programs on the blockchain that are critical to a range of industries, including finance, supply chain management, and healthcare. However, comprehending smart contracts can be challenging due to a lack of effective comments in most user-defined code. To address this challenge, we propose a novel retrieval-enhanced approach CC-GRA that leverages retrieval knowledge to generate high-quality comments for Solidity language code. Our approach carefully eliminates duplicated data and template data in the widely-used smart contract dataset to ensure a high-quality corpus. Extensive experiments and comprehensive analysis demonstrate the effectiveness applicability of our approach after being compared with eight state-of-the-art baselines. Finally, we conduct a human study and find the comment quality generated by our approach is better than baselines in terms of similarity, naturalness, and informativeness.

show abstract

“…Li et al [20] combined the code comments obtained by information retrieval with the semantic information of the input code to generate code comments. Recently, Yu et al [16] proposed a hybrid method of two-stage training, which generates Bash comments through one-stage information retrieval and twostage CodeBERT fine-tuning.…”

Section: A Code Comment Generationmentioning

confidence: 99%

“…Motivation. The classical deep learning model is a highly recognized model in earlier studies, and it is often used as a baseline in current studies [16], [28]. We consider them as experimental objects, which can better reflect the rigor of our experiments.…”

Section: Research Questionsmentioning

confidence: 99%

See 1 more Smart Citation

An Empirical Study of Adversarial Training in Code Comment Generation

Shen,

Ju,

Chen

et al. 2023

International Conferences on Software Engineering and Knowledge Engineering

View full text Add to dashboard Cite

The code comment generation task is designed for developers to understand programs more quickly during development and maintenance. However, the existing automatic code comment generation models can not generate valuable comments for developers. It is necessary to explore a technology that can optimize the performance of code comment generation models without changing the model. We consider adversarial training as the experimental object, which can improve the robustness and generalization of the model. We present a large-scale study to experimentally validate the performance of gradient-based adversarial training methods in the code comment generation task. The results show that adversarial training can improve the model performance by generating adversarial examples without changing the model. Our empirical study can provide a new perspective for researchers to improve the performance of code comment generation models.

show abstract

BashExplainer: Retrieval-Augmented Bash Code Comment Generation based on Fine-tuned CodeBERT

Cited by 17 publications

References 41 publications

APICom: Automatic API Completion via Prompt Learning and Adversarial Training-based Data Augmentation

APICom: Automatic API Completion via Prompt Learning and Adversarial Training-based Data Augmentation

CCGRA: Smart Contract Code Comment Generation with Retrieval-enhanced Approach

An Empirical Study of Adversarial Training in Code Comment Generation

Contact Info

Product

Resources

About