Retrieve and Refine: Exemplar-Based Neural Comment Generation

Wei, Bolin; Li, Yongmin; Li, Ge; Xia, Xin; Jin, Zhi

doi:10.1109/ase.2019.00152

Cited by 34 publications

(37 citation statements)

References 45 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To complement the above objective metrics, we also conduct a human evaluation to further assess the quality of the comments generated by the masked training method, data augmentation and normal training method. Generally, we follow the evaluation settings from the previous work [17,46]. Particularly, the comments are examined from three aspects, i.e., similarity, naturalness, and informativeness [46].…”

Section: Human Evaluationmentioning

confidence: 99%

“…Generally, we follow the evaluation settings from the previous work [17,46]. Particularly, the comments are examined from three aspects, i.e., similarity, naturalness, and informativeness [46]. Similarity refers to how similar the generated comment is to the reference comment; naturalness measures the grammaticality and luency; informativeness focuses on the content delivery from code snippet to the generated comments.…”

Section: Human Evaluationmentioning

confidence: 99%

See 1 more Smart Citation

Adversarial Robustness of Deep Code Comment Generation

Zhou

Zhang

Shen

et al. 2022

ACM Trans. Softw. Eng. Methodol.

View full text Add to dashboard Cite

Deep neural networks (DNNs) have shown remarkable performance in a variety of domains such as computer vision, speech recognition, and natural language processing. Recently they also have been applied to various software engineering tasks, typically involving processing source code. DNNs are well-known to be vulnerable to adversarial examples, i.e., fabricated inputs that could lead to various misbehaviors of the DNN model while being perceived as benign by humans. In this paper, we focus on the code comment generation task in software engineering and study the robustness issue of the DNNs when they are applied to this task. We propose ACCENT ( A dversarial C ode C omment g EN era T or), an identifier substitution approach to craft adversarial code snippets, which are syntactically correct and semantically close to the original code snippet, but may mislead the DNNs to produce completely irrelevant code comments. In order to improve the robustness, ACCENT also incorporates a novel training method, which can be applied to existing code comment generation models. We conduct comprehensive experiments to evaluate our approach by attacking the mainstream encoder-decoder architectures on two large-scale publicly available datasets. The results show that ACCENT efficiently produces stable attacks with functionality-preserving adversarial examples, and the generated examples have better transferability compared with the baselines. We also confirm, via experiments, the effectiveness in improving model robustness with our training method.

show abstract

Section: Human Evaluationmentioning

confidence: 99%

Section: Human Evaluationmentioning

confidence: 99%

Adversarial Robustness of Deep Code Comment Generation

Zhou

Zhang

Shen

et al. 2022

ACM Trans. Softw. Eng. Methodol.

View full text Add to dashboard Cite

show abstract

“…We note that the ideas similar to our approach for automated log generation have been already applied and proven to be effective in adjacent software engineering tasks such as automated commit message [71] and comment [73] generation. For example, Wei et al [73] used comments of similar code snippets as 'exemplars' to assist in generating comments for new code snippets. Both papers' ideas and application scenarios are analogous to a large extent to those of our work.…”

Section: Practicality In Software Engineeringmentioning

confidence: 99%

“…Both papers' ideas and application scenarios are analogous to a large extent to those of our work. Similarly, both approaches utilize BLEU [73,73] and ROUGE-L [73] scores for evaluating the quality of the auto-generated text.…”

Section: Practicality In Software Engineeringmentioning

confidence: 99%

Borrowing from Similar Code: A Deep Learning NLP-Based Approach for Log Statement Automation

Gholamian¹,

Ward²

2021

Preprint

View full text Add to dashboard Cite

Software developers embed logging statements inside the source code as an imperative duty in modern software development as log files are necessary for tracking down runtime system issues and troubleshooting system management tasks. Prior research has emphasized the importance of logging statements in the operation and debugging of software systems. However, the current logging process is mostly manual, and thus, proper placement and content of logging statements remain as challenges. To overcome these challenges, methods that aim to automate log placement and predict its content, i.e., 'where and what to log', are of high interest. Thus, we focus on predicting the location (i.e., where) and description (i.e., what) for log statements by utilizing source code clones and natural language processing (NLP), as these approaches provide additional context and advantage for log prediction. Specifically, we guide our research with three research questions (RQs): (RQ1) how similar code snippets, i.e., code clones, can be leveraged for log statements prediction? (RQ2) how the approach can be extended to automate log statements' descriptions? and (RQ3) how effective the proposed methods are for log location and description prediction? To pursue our RQs, we perform an experimental study on seven open-source Java projects. We introduce an updated and improved log-aware code-clone detection method to predict the location of logging statements (RQ1). Then, we incorporate natural language processing (NLP) and deep learning methods to automate the log statements' description prediction (RQ2). Our analysis shows that our hybrid NLP and code-clone detection approach (NLP CC'd) outperforms conventional clone detectors in finding log statement locations on average by 15.60% and achieves 40.86% higher performance on BLEU and ROUGE scores for predicting the description of logging statements when compared to prior research (RQ3). Our work demonstrates the effectiveness of borrowing context from similar code snippets for automated log location and description prediction.CCS Concepts: • Software and its engineering → Software libraries and repositories; Software configuration management and version control systems; Software maintenance tools; Maintaining software; System administration.

show abstract

“…To complement the above objective metrics, we also conduct a human evaluation to further assess the quality of the comments generated by the masked training method and data augmentation. Generally, we follow the evaluation settings from the previous work [17,45]. Particularly, the comments are examined from three aspects, i.e., similarity, naturalness, and informativeness [45].…”

Section: Human Evaluationmentioning

confidence: 99%

Adversarial Robustness of Deep Code Comment Generation

Zhou¹,

Zhang²,

Shen³

et al. 2021

Preprint

View full text Add to dashboard Cite

Deep neural networks (DNNs) have shown remarkable performance in a variety of domains such as computer vision, speech recognition, or natural language processing. Recently they also have been applied to various software engineering tasks, typically involving processing source code. DNNs are well-known to be vulnerable to adversarial examples, i.e., fabricated inputs that could lead to various misbehaviors of the DNN model while being perceived as benign by humans. In this paper, we focus on the code comment generation task in software engineering and study the robustness issue of the DNNs when they are applied to this task. We propose ACCENT, an identifier substitution approach to craft adversarial code snippets, which are syntactically correct and functionality-preserving with respect to the original code snippet, but may mislead the DNNs to produce completely irrelevant code comments. In order to improve the robustness, ACCENT also incorporates a novel training method, which can be applied to existing code comment generation models. We conduct comprehensive experiments to evaluate our approach by attacking the mainstream encoder-decoder architectures on two large-scale publicly available datasets. The results show that ACCENT efficiently produces stable attacks with functionality-preserving adversarial examples, and the generated examples have better transferability compared with baselines. We also confirm, via experiments, the effectiveness in improving model robustness with our training method.

show abstract

Retrieve and Refine: Exemplar-Based Neural Comment Generation

Cited by 34 publications

References 45 publications

Adversarial Robustness of Deep Code Comment Generation

Adversarial Robustness of Deep Code Comment Generation

Borrowing from Similar Code: A Deep Learning NLP-Based Approach for Log Statement Automation

Adversarial Robustness of Deep Code Comment Generation

Contact Info

Product

Resources

About