检索结果-内蒙古大学图书馆

Improve code summarization via Prompt-Tuning codeT5

Wuhan University Journal of Natural Sciences 2023年第6期28卷 474-482页

作者： LI Huanzhen College of Information Engineering Jiangxi University of TechnologyNanchang 330022JiangxiChina

code comments are crucial in software engineering, aiding in program maintenance and code reuse. The process of generating clear and descriptive code comments, outlining code functionality, is called code summarization. Existing code summarization methods are typically trained using transformer-based models. However, these trained models often possess limited parameters and lack specific training tasks, hindering their ability to capture code semantics effectively. This paper uses a high-capacity pre-trained model, codeT5, for code summarization. codeT5 is designed with an encoder-decoder architecture that excels in code summarization tasks. Furthermore, we adopt a novel paradigm, "pre-train, prompt, predict", to unlock the knowledge embedded within codeT5. We devise a prompt template to convert input code into code prompts and fine-tune codeT5 with these prompts—a process we term prompt tuning. Our effectiveness experiments demonstrate that prompt tuning codeT5 with only 40% of the dataset can achieve comparable performance to fine-tuning codeT5 with 100% of the dataset. This means our approach is applicable in few-shot learning scenarios. Additionally, our prompt learning method is not sensitive to the size of the tuning dataset. Our practicality experiments show that the performance of prompt-tuned codeT5 far surpasses that of transformer-based models trained on code-comment datasets collected from Stack Overflow.

关键词： code summarization transformer-based model prompt learning codeT5 few-shot learning

来源：评论

学校读者我要写书评

暂无评论

Adversarial Attack and Robustness Improvement on code summarization 24

Adversarial Attack and Robustness Improvement on Code Summar...

引用

28th International Conference on Evaluation and Assessment in Software Engineering (EASE)

作者： Ding, Xi Huang, Yuan Chen, Xiangping Bian, Jing Sun Yat Sen Univ Sch Comp Sci & Engn Guangzhou Peoples R China Sun Yat Sen Univ Sch Software Engn Zhuhai Peoples R China Sun Yat Sen Univ China Sch Software Engn Guangzhou Peoples R China Sun Yat Sen Univ Sch Journalism & Commun Guangzhou Peoples R China

ISBN: (纸本)9798400717017

Automatic code summarization, also known as code comment generation, has been proven beneficial for developers to understand better and maintain software projects. However, few research works have investigated the robustness of such models. Robustness requires that the model sustains the quality of the output summaries in the presence of perturbations to the inputs. In this paper, we provide an in-depth study of the robustness of code summarization models. We propose CREATE (code summarization modEl's Adversarial aTtackEr), an approach for performing adversarial attacks against the model. This approach can generate adversarial samples to mislead the model and explore its robustness while ensuring these samples are compilable and semantically similar. We attack mainstream code summarization models with a large-scale available Java dataset to evaluate the effectiveness and efficiency of our approach. The experimental results indicate that CREATE's attack effectiveness and efficiency surpasses other baselines, causing a decrease in the quality of generated comments by at least 40%. Furthermore, we investigate the magnitude of perturbation caused by CREATE during adversarial attacks, and the results show that the similarity between the adversarial samples generated by CREATE and the input code is approximately 0.8, demonstrating that it induces more minor perturbations compared to other baselines. Finally, we utilize CREATE for adversarial training of the model. Through experimentation, this approach indeed effectively enhances the model's robustness.

关键词： code summarization Adversarial Attack Robustness

来源：评论

学校读者我要写书评

暂无评论

Low-Resources Project-Specific code summarization 7

Low-Resources Project-Specific Code Summarization

引用

37th IEEE/ACM International Conference on Automated Software Engineering (ASE)

作者： Xie, Rui Hu, Tianxiang Ye, Wei Zhang, Shikun Peking Univ Natl Engn Res Ctr Software Engn Beijing Peoples R China

ISBN: (纸本)9781450394758

code summarization generates brief natural language descriptions of source code pieces, which can assist developers in understanding code and reduce documentation workload. Recent neural models on code summarization are trained and evaluated on large-scale multiproject datasets consisting of independent code-summary pairs. Despite the technical advances, their effectiveness on a specific project is rarely explored. In practical scenarios, however, developers are more concerned with generating high-quality summaries for their working projects. And these projects may not maintain sufficient documentation, hence having few historical code-summary pairs. To this end, we investigate low-resource project-specific code summarization, a novel task more consistent with the developers' requirements. To better characterize project-specific knowledge with limited training samples, we propose a meta transfer learning method by incorporating a lightweight fine-tuning mechanism into a meta-learning framework. Experimental results on nine realworld projects verify the superiority of our method over alternative ones and reveal how the project-specific knowledge is learned.

关键词： code summarization parameter efficient transfer learning meta learning

来源：评论

学校读者我要写书评

暂无评论

MMF3: Neural code summarization Based on Multi-Modal Fine-Grained Feature Fusion 22

MMF3: Neural Code Summarization Based on Multi-Modal Fine-Gr...

引用

16th ACM/IEEE International Symposium on Empirical Software Engineering and Measurement (ESEM)

作者： Ma, Zheng Gao, Yuexiu Lyu, Lei Lyu, Chen Shandong Normal Univ Jinan Peoples R China

ISBN: (纸本)9781450394277

Background: code summarization automatically generates the corresponding natural language descriptions according to the input code to characterize the function implemented by source code. Comprehensiveness of code representation is critical to code summarization task. However, most existing approaches typically use coarse-grained fusion methods to integrate multi-modal features. They generally represent different modalities of a piece of code, such as an Abstract Syntax Tree (AST) and a token sequence, as two embeddings and then fuse the two ones at the AST/code levels. Such a coarse integration makes it difficult to learn the correlations between fine-grained code elements across modalities effectively. Aims: This study intends to improve the model's prediction performance for high-quality code summarization by accurately aligning and fully fusing semantic and syntactic structure information of source code at node/token levels. Method: This paper proposes a Multi-Modal Fine-grained Feature Fusion approach (MMF3) for neural code summarization. The method uses the Transformer architecture. In particular, we introduce a novel fine-grained fusion method, which allows fine-grained fusion of multiple code modalities at the token and node levels. Specifically, we use this method to fuse information from both token and AST modalities and apply the fused features to code summarization. Results: We conduct experiments on one Java and one Python datasets, and evaluate generated summaries using four metrics. The results show that: 1) the performance of our model outperforms the current state-of-the-art models, and 2) the ablation experiments show that our proposed fine-grained fusion method can effectively improve the accuracy of generated summaries. Conclusion: MMF3 can mine the relationships between cross-modal elements and perform accurate fine-grained element-level alignment fusion accordingly. As a result, more clues can be provided to improve the accuracy of the generate

关键词： code summarization Multi-modal Features Transformer Finegrained Fusion

来源：评论

学校读者我要写书评

暂无评论

Are We Building on the Rock? On the Importance of Data Preprocessing for code summarization 2022

Are We Building on the Rock? On the Importance of Data Prepr...

引用

30th ACM Joint European Software Engineering Conference / Symposium on the Foundations of Software Engineering (ESEC/FSE)

作者： Shi, Lin Mu, Fangwen Chen, Xiao Wang, Song Wang, Junjie Yang, Ye Li, Ge Xia, Xin Wang, Qing Chinese Acad Sci Inst Software Beijing Peoples R China York Univ Lassonde Sch Engn Toronto ON Canada Stevens Inst Technol Sch Syst & Enterprises Hoboken NJ USA Peking Univ Key Lab High Confidence Software Technol Beijing Peoples R China Huawei Software Engn Applicat Technol Lab Beijing Peoples R China Chinese Acad Sci Inst Software Lab Internet Software Technol Beijing Peoples R China Univ Chinese Acad Sci Beijing Peoples R China Chinese Acad Sci Inst Software Sci Technol Integrated Informat Syst Lab Beijing Peoples R China

ISBN: (纸本)9781450394130

code summarization, the task of generating useful comments given the code, has long been of interest. Most of the existing code summarization models are trained and validated on widely-used code comment benchmark datasets. However, little is known about the quality of the benchmark datasets built from real-world projects. Are the benchmark datasets as good as expected? To bridge the gap, we conduct a systematic research to assess and improve the quality of four benchmark datasets widely used for code summarization tasks. First, we propose an automated code-comment cleaning tool that can accurately detect noisy data caused by inappropriate data preprocessing operations from existing benchmark datasets. Then, we apply the tool to further assess the data quality of the four benchmark datasets, based on the detected noises. Finally, we conduct comparative experiments to investigate the impact of noisy data on the performance of code summarization models. The results show that these data preprocessing noises widely exist in all four benchmark datasets, and removing these noisy data leads to a significant improvement on the performance of code summarization. We believe that the findings and insights will enable a better understanding of data quality in code summarization tasks, and pave the way for relevant research and practice.

关键词： code summarization Data Quality Empirical Study

来源：评论

学校读者我要写书评

暂无评论

A code summarization Approach for Object Oriented Programs

A Code Summarization Approach for Object Oriented Programs

引用

International Conference on Innovation and Intelligence for Informatics, Computing, and Technologies (3ICT)

作者： Mohsin, Ali Hameed Hammad, Mustafa Univ Bahrain Coll IT Sukhair Bahrain

ISBN: (纸本)9781728130125

The software maintenance process is not an easy job, especially when the source code becomes more complex and less documented. Software developers and engineers may spend plenty of time to understand the structures and features of the source code in order to maintain their software projects. Using an automated code summarization technique is a key factor to save time and cost of the maintenance process. Generating descriptive documents from the source code helps the software developers to understand their software. In this paper, a code summarization framework is proposed to document the source code. A set of software features are extracted and displayed to the developers based on mapping the target source code segments to an XML representation. The proposed framework has been conducted on an open source project to evaluate its effectiveness. The generated results showed that the proposed approach is useful in understanding the different structural aspects of the source code.

关键词： code summarization software documentation method summarization Reverse engineering

来源：评论

学校读者我要写书评

暂无评论

On the Evaluation of Neural code summarization 22

On the Evaluation of Neural Code Summarization

引用

ACM/IEEE 44th International Conference on Software Engineering (ICSE)

作者： Shi, Ensheng Wang, Yanlin Du, Lun Chen, Junjie Han, Shi Zhang, Hongyu Zhang, Dongmei Sun, Hongbin Xi An Jiao Tong Univ Xian Peoples R China Microsoft Res Beijing Peoples R China Tianjin Univ Tianjin Peoples R China Univ Newcastle Callaghan NSW Australia Microsoft Res Asia Beijing Peoples R China

ISBN: (纸本)9781450392211

Source code summaries are important for program comprehension and maintenance. However, there are plenty of programs with missing, outdated, or mismatched summaries. Recently, deep learning techniques have been exploited to automatically generate summaries for given code snippets. To achieve a profound understanding of how far we are from solving this problem and provide suggestions to future research, in this paper, we conduct a systematic and in-depth analysis of 5 state-of-the-art neural code summarization models on 6 widely used BLEU variants, 4 pre-processing operations and their combinations, and 3 widely used datasets. The evaluation results show that some important factors have a great influence on the model evaluation, especially on the performance of models and the ranking among the models. However, these factors might be easily overlooked. Specifically, (1) the BLEU metric widely used in existing work of evaluating code summarization models has many variants. Ignoring the differences among these variants could greatly affect the validity of the claimed results. Besides, we discover and resolve an important and previously unknown bug in BLEU calculation in a commonly-used software package. Furthermore, we conduct human evaluations and find that the metric BLEU-DC is most correlated to human perception;(2) code preprocessing choices can have a large (from -18% to +25%) impact on the summarization performance and should not be neglected. We also explore the aggregation of pre-processing combinations and boost the performance of models;(3) some important characteristics of datasets (corpus sizes, data splitting methods, and duplication ratios) have a significant impact on model evaluation. Based on the experimental results, we give actionable suggestions for evaluating code summarization and choosing the best method in different scenarios. We also build a shared code summarization toolbox to facilitate future research.

关键词： code summarization Empirical study Deep learning Evaluation

来源：评论

学校读者我要写书评

暂无评论

Exploiting Method Names to Improve code summarization: A Deliberation Multi-Task Learning Approach 29

Exploiting Method Names to Improve Code Summarization: A Del...

引用

29th IEEE/ACM International Conference on Program Comprehension (ICPC) / 18th IEEE/ACM International Conference on Mining Software Repositories (MSR)

作者： Xie, Rui Ye, Wei Sun, Jinan Zhang, Shikun Peking Univ Natl Engn Res Ctr Software Engn Beijing Peoples R China Peking Univ Sch Software & Microelect Beijing Peoples R China

ISBN: (纸本)9781665414036

code summaries are brief natural language descriptions of source code pieces. The main purpose of code summarization is to assist developers in understanding code and to reduce documentation workload. In this paper, we design a novel multi-task learning (MTL) approach for code summarization through mining the relationship between method code summaries and method names. More specifically, since a method's name can be considered as a shorter version of its code summary, we first introduce the tasks of generation and informativeness prediction of method names as two auxiliary training objectives for code summarization. A novel two-pass deliberation mechanism is then incorporated into our MTL architecture to generate more consistent intermediate states fed into a summary decoder, especially when informative method names do not exist. To evaluate our deliberation MTL approach, we carried out a large-scale experiment on two existing datasets for Java and Python. The experiment results show that our technique can be easily applied to many state-of-the-art neural models for code summarization and improve their performance. Meanwhile, our approach shows significant superiority when generating summaries for methods with non-informative names.

关键词： code summarization method name prediction multi-task learning deliberation network

来源：评论

学校读者我要写书评

暂无评论

GypSum: Learning Hybrid Representations for code summarization 30

GypSum: Learning Hybrid Representations for Code Summarizati...

引用

30th IEEE/ACM International Conference on Program Comprehension (ICPC)

作者： Wang, Yu Dong, Yu Lu, Xuesong Zhou, Aoying East China Normal Univ Shanghai Peoples R China

ISBN: (纸本)9781450392983

code summarization with deep learning has been widely studied in recent years. Current deep learning models for code summarization generally follow the principle in neural machine translation and adopt the encoder-decoder framework, where the encoder learns the semantic representations from source code and the decoder transforms the learnt representations into human-readable text that describes the functionality of code snippets. Despite they achieve the new state-of-the-art performance, we notice that current models often either generate less fluent summaries, or fail to capture the core functionality, since they usually focus on a single type of code representations. As such we propose GypSum, a new deep learning model that learns hybrid representations using graph attention neural networks and a pre-trained programming and natural language model. We introduce particular edges related to the control flow of a code snippet into the abstract syntax tree for graph construction, and design two encoders to learn from the graph and the token sequence of source code, respectively. We modify the encoder-decoder sublayer in the Transformer's decoder to fuse the representations and propose a dual-copy mechanism to facilitate summary generation. Experimental results demonstrate the superior performance of GypSum over existing code summarization models.

关键词： code summarization deep neural networks graph attention neural networks copy mechanisms

来源：评论

学校读者我要写书评

暂无评论

Revisiting Information Retrieval and Deep Learning Approaches for code summarization 23

Revisiting Information Retrieval and Deep Learning Approache...

引用

45th IEEE/ACM International Conference on Software Engineering (ICSE)

作者： Zhu, Tingwei Li, Zhong Pan, Minxue Shi, Chaoxuan Zhang, Tian Pei, Yu Li, Xuandong Nanjing Univ Nanjing Peoples R China Hong Kong Polytech Univ Hong Kong Peoples R China

ISBN: (纸本)9798350322637

code summarization refers to the procedure of creating short descriptions that outline the semantics of source code snippets. Existing code summarization approaches can be broadly classified into Information Retrieval (IR)-based and Deep Learning (DL)-based approaches. However, their effectiveness, and especially their strengths and weaknesses, remain largely understudied. Existing evaluations use different benchmarks and metrics, making performance comparisons of these approaches susceptible to bias and potentially yielding misleading results. For example, the DL-based approaches typically show better code summarization performance in their original papers [1], [2]. However, Gros et al. [3] report that a naive IR approach could achieve comparable (or even better) performance to the DL-based ones. In addition, some recent work [4], [5] suggests that incorporating IR techniques can improve the DL-based approaches. To further advance code summarization techniques, it is critical that we have a good understanding of how IR-based and DL-based approaches perform on different datasets and in terms of different metrics. Prior works have studied some aspects of code summarization, such as the factors affecting performance evaluation [6] and the importance of data preprocessing [7], etc. In this paper, we focus on the study of the IR-based and DL-based code summarization approaches to enhance the understanding and design of more advanced techniques. We first compare the IRbased and DL-based approaches under the same experimental settings and benchmarks, then study their strengths and limitations through quantitative and qualitative analyses. Finally, we propose a simpler but effective strategy to combine IR and DL to further improve code summarization. Four IR-based approaches and two DL-based approaches are investigated with regard to representativeness and diversity. For IR-based approaches, we select three BM25-based approaches (i.e., BM25-spl, BM25-ast, BM25-alpha) and o

关键词： code summarization deep learning empirical study information retrieval

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：