检索结果-内蒙古大学图书馆

41st IEEE/ACM International Conference on Software Engineering (ICSE)

作者： Abid, Nahla J. Sharif, Bonita Dragan, Natalia Alrasheed, Hend Maletic, Jonathan I. Taibah Univ Dept Comp Sci Madinah Saudi Arabia Univ Nebraska Lincoln Dept Comp Sci & Engn Lincoln NE 68588 USA King Saud Univ Dept Informat Technol Riyadh Saudi Arabia Kent State Univ Dept Comp Sci Kent OH 44242 USA

ISBN: (纸本)9781728108698

An eye-tracking study of 18 developers reading and summarizing Java methods is presented. The developers provide a written summary for methods assigned to them. In total, 63 methods are used from five different systems. Previous studies on this topic use only short methods presented in isolation usually as images. In contrast, this work presents the study in the Eclipse IDE allowing access to all the source code in the system. The developer can navigate via scrolling and switching files while writing the summary. New eye-tracking infrastructure allows for this improvement in the study environment. Data collected includes eye gazes on source code, written summaries, and time to complete each summary. Unlike prior work that concluded developers focus on the signature the most, these results indicate that they tend to focus on the method body more than the signature. Moreover, both experts and novices tend to revisit control flow terms rather than reading them for a long period. They also spend a significant amount of gaze time and have higher gaze visits when they read call terms. Experts tend to revisit the body of the method significantly more frequently than its signature as the size of the method increases. Moreover, experts tend to write their summaries from source code lines that they read the most.

关键词： source code summarization eye tracking program comprehension empirical study

来源：评论

学校读者我要写书评

暂无评论

JSummarizer: An Automatic Generator of Natural Language Summaries for Java Classes

JSummarizer: An Automatic Generator of Natural Language Summ...

引用

IEEE 21st International Conference on Program Comprehension (ICPC)

作者： Moreno, Laura Marcus, Andrian Pollock, Lori Vijay-Shanker, K. Wayne State Univ Dept Comp Sci Detroit MI 48202 USA Univ Delaware Comp & Inf Sci Dept Newark DE USA

ISBN: (纸本)9781467330923

JSummarizer is an Eclipse plug-in for automatically generating natural language summaries of Java classes. The summary is based on the stereotype of the class, which implicitly encodes the design intent of the class and is automatically inferred by JSummarizer. The tool uses a set of predefined heuristics to determine what information will be reflected in the summary, and it uses natural language processing and generation techniques to form the summary. The generated summaries can be used to re-document the code and to help developers to easier understand large and complex classes.

关键词： source code summarization program comprehension documentation generation

来源：评论

学校读者我要写书评

暂无评论

A Neural Model for Generating Natural Language Summaries of Program Subroutines 19

A Neural Model for Generating Natural Language Summaries of ...

引用

41st IEEE/ACM International Conference on Software Engineering (ICSE)

作者： LeClair, Alexander Jiang, Siyuan McMillan, Collin Univ Notre Dame Dept Comp Sci & Engn Notre Dame IN 46556 USA Eastern Michigan Univ Dept Comp Sci Ypsilanti MI 48197 USA

ISBN: (纸本)9781728108698

source code summarization - creating natural language descriptions of source code behavior - is a rapidly-growing research topic with applications to automatic documentation generation, program comprehension, and software maintenance. Traditional techniques relied on heuristics and templates built manually by human experts. Recently, data-driven approaches based on neural machine translation have largely overtaken template-based systems. But nearly all of these techniques rely almost entirely on programs having good internal documentation;without clear identifier names, the models fail to create good summaries. In this paper, we present a neural model that combines words from code with code structure from an AST. Unlike previous approaches, our model processes each data source as a separate input, which allows the model to learn code structure independent of the text in code. This process helps our approach provide coherent summaries in many cases even when zero internal documentation is provided. We evaluate our technique with a dataset we created from 2.1m Java methods. We find improvement over two baseline techniques from SE literature and one from NLP literature.

关键词： automatic documentation generation source code summarization code comment generation

来源：评论

学校读者我要写书评

暂无评论

Neural Comment Generation for source code with Auxiliary code Classification Task 26

Neural Comment Generation for Source Code with Auxiliary Cod...

引用

26th Asia-Pacific Software Engineering Conference (APSEC)

作者： Chen, Minghao Wan, Xiaojun Peking Univ Ctr Data Sci Wangxuan Inst Comp Technol MOE Key Lab Computat Linguist Beijing Peoples R China

ISBN: (纸本)9781728146485

code comments help program developers understand programs, read and navigate source code, thus resulting in more efficient software maintenance. Unfortunately, many codes are not commented adequately, or the code comments are missing. So developers have to spend additional time in reading source code. In this paper, we propose a new approach to automatically generating comments for source codes. Following the intuition behind the traditional sequence-to-sequence (Seq2Seq) model for machine translation, we propose a tree-to-sequence (Tree2Seq) model for code comment generation, which leverages an encoder to capture the structure information of source code. More importantly, code classification is involved as an auxiliary task for aiding the Tree2Seq model. We build a multi-task learning model to achieve this goal. We evaluate our models on a benchmark dataset with automatic metrics like BLEU, ROUGE, and METEOR. Experimental results show that our proposed Tree2Seq model outperforms traditional Seq2Seq model with attention, and our proposed multi-task learning model outperforms the state-of-the-art approaches by a substantial margin.

关键词： program comprehension source code summarization deep learning multi task learning

来源：评论

学校读者我要写书评

暂无评论

On the Effectiveness of Large Language Models in Statement-level code summarization 24

On the Effectiveness of Large Language Models in Statement-l...

引用

24th IEEE International Conference on Software Quality, Reliability and Security (QRS)

作者： Zhu, Jie Miao, Yun Xu, Tingting Zhu, Junwu Sun, Xiaolei Yangzhou Univ Yangzhou Jiangsu Peoples R China Nanjing Univ State Key Lab Novel Software Technol Nanjing Peoples R China Anhui Commun Vocat & Tech Coll Hefei Anhui Peoples R China

ISBN: (纸本)9798350365634

code comments are crucial for program comprehension, and the automated generation of comments greatly enhances the efficiency of code commenting. Statement-level code summarization represents the finest granularity of code summarization, typically encompassing explanations of the purpose and functionality of code statements. Large Language Models (LLMs) are deep learning models trained on massive text data. They possess not only the capability to generate natural language text but also to deeply understand the meaning of text, applicable to various natural language processing tasks such as text summarization, question answering, and translation. Currently, LLMs have demonstrated the ability to generate summaries for code. In this paper, we systematically investigate the capability of LLMs to generate statement-level code summaries. we construct a dataset for statement-level code summarization and evaluate the ability of large language models on statement-level code summarization. For further research, we investigate the impact of different prompting techniques. We also study the effect of the temperature parameter on the quality of generated summaries. Additionally, we compare large language models with the state-of-the-art pretrained model codeT5 and find out that large language models have great potential to replace pre-trained models and become the new state-of-the-art models on statement-level code summarization. To ensure the reliability of automatic evaluation, we also conduct human evaluation. Our findings emphasize the transformative potential of LLMs on statement-level code summarization and the challenges yet to be overcome.

关键词： Large Language Models Statement-Level code summarization source code summarization

来源：评论

学校读者我要写书评

暂无评论

Improved Automatic summarization of Subroutines via Attention to File Context 17

Improved Automatic Summarization of Subroutines via Attentio...

引用

IEEE/ACM 17th International Conference on Mining Software Repositories (MSR)

作者： Haque, Sakib LeClair, Alexander Wu, Lingfei McMillan, Collin Univ Notre Dame Dept Comp Sci Notre Dame IN 46556 USA IBM Res Yorktown Hts NY USA

ISBN: (纸本)9781450375177

Software documentation largely consists of short, natural language summaries of the subroutines in the software. These summaries help programmers quickly understand what a subroutine does without having to read the source code him or herself. The task of writing these descriptions is called "source code summarization" and has been a target of research for several years. Recently, AI-based approaches have superseded older, heuristic-based approaches. Yet, to date these AI-based approaches assume that all the content needed to predict summaries is inside subroutine itself. This assumption limits performance because many subroutines cannot be understood without surrounding context. In this paper, we present an approach that models the file context of subroutines (i.e. other subroutines in the same file) and uses an attention mechanism to find words and concepts to use in summaries. We show in an experiment that our approach extends and improves several recent baselines.

关键词： source code summarization neural networks documentation generation artificial intelligence natural language processing

来源：评论

学校读者我要写书评

暂无评论

AST-Trans: code summarization with Efficient Tree-Structured Attention 22

AST-Trans: Code Summarization with Efficient Tree-Structured...

引用

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

作者： Tang, Ze Shen, Xiaoyu Li, Chuanyi Ge, Jidong Huang, Liguo Zhu, Zhelin Luo, Bin Nanjing Univ State Key Lab Novel Software Technol Nanjing Peoples R China Amazon Alexa AI Berlin Germany Southern Methodist Univ Dept Comp Sci Dallas TX USA

ISBN: (纸本)9781450392211

code summarization aims to generate brief natural language descriptions for source codes. The state-of-the-art approaches follow a transformer-based encoder-decoder architecture. As the source code is highly structured and follows strict grammars, its Abstract Syntax Tree (AST) is widely used for encoding structural information. However, ASTs are much longer than the corresponding source code. Existing approaches ignore the size constraint and simply feed the whole linearized AST into the encoders. We argue that such a simple process makes it difficult to extract the truly useful dependency relations from the overlong input sequence. It also incurs significant computational overhead since each node needs to apply self-attention to all other nodes in the AST. To encode the AST more effectively and efficiently, we propose AST-Trans in this paper which exploits two types of node relationships in the AST: ancestor-descendant and sibling relationships. It applies the tree-structured attention to dynamically allocate weights for relevant nodes and exclude irrelevant nodes based on these two relationships. We further propose an efficient implementation to support fast parallel computation for tree-structure attention. On the two code summarization datasets, experimental results show that AST-Trans significantly outperforms the state-of-the-arts while being times more efficient than standard transformers (1).

关键词： tree-based neural network source code summarization

来源：评论

学校读者我要写书评

暂无评论

Keyword-guided abstractive code summarization via incorporating structural and contextual information

引用

INFORMATION AND SOFTWARE TECHNOLOGY 2022年第0期150卷

作者： Cheng, Wuyan Hu, Po Wei, Shaozhi Mo, Ran Cent China Normal Univ Hubei Prov Key Lab Artificial Intelligence & Smart Wuhan Hubei Peoples R China Cent China Normal Univ Sch Comp Wuhan Hubei Peoples R China Cent China Normal Univ Natl Language Resources Monitoring & Res Ctr Netwo Wuhan Hubei Peoples R China

Context: source code summarization is a crucial yet far from settled task for describing structured code snippets in natural language. High-quality code summaries could effectively facilitate program comprehension and software maintenance. A good code summary is supposed to have the following characteristics: complete information, correct meaning, and consistent description. In recent years, numerous approaches have been proposed for code summarization, but it is still very challenging for developers to automatically learn the complex semantics from the source code and generate complete, correct and consistent code summaries. Objective: In this paper, we propose KGcodeSum, a novel keyword-guided abstractive code summarization approach that incorporates structural and contextual ***: To improve summaries' quality, we leverage both the structural information embedded in code itself and the contextual information from related code snippets. Meanwhile, we make use of keywords to guide summaries' generation to guarantee the code summaries contain key information. Finally, we propose a new dynamic vocabulary strategy which can effectively resolve the UNK problems in code ***: Through our evaluation on the large-scale benchmark datasets with 2.1 million java method-comment pairs and 1.1 million C/C++ function-summary pairs, We have observed that our approach could generate better code summaries than existing state-of-the-art approaches in terms of completeness, correctness and consistency. In addition, we also find that incorporating the dynamic vocabulary strategy into our approach could significantly save time and space in the model training ***: Our KGcodeSum approach could effectively generate code summaries.

关键词： source code summarization Encoder-decoder Information incorporation Dynamic vocabulary Deep learning

来源：评论

学校读者我要写书评

暂无评论

Towards automatically generating block comments for code snippets

引用

INFORMATION AND SOFTWARE TECHNOLOGY 2020年 127卷 106373-106373页

作者： Huang, Yuan Huang, Shaohao Chen, Huanchao Chen, Xiangping Zheng, Zibin Luo, Xiapu Jia, Nan Hu, Xinyu Zhou, Xiaocong Sun Yat Sen Univ Natl Engn Res Ctr Digital Life Sch Data & Comp Sci Guangzhou Peoples R China Sun Yat Sen Univ Sch Commun & Design Guangdong Key Lab Big Data Anal & Simulat Publ Op Guangzhou Peoples R China Hong Kong Polytech Univ Dept Comp Hong Kong Peoples R China Hebei GEO Univ Sch Management Sci & Engn Shijiazhuang Hebei Peoples R China

code commenting is a common programming practice of practical importance to help developers review and comprehend source code. There are two main types of code comments for a method: header comments that summarize the method functionality located before a method, and block comments that describe the functionality of the code snippets within a method. Inspired by the effectiveness of deep learning techniques in the NLP field, many studies focus on using the machine translation model to automatically generate comment for the source code. Because the data set of block comments is difficult to collect, current studies focus more on the automatic generation of header comments than that of block comments. However, block comments are important for program comprehension due to their explanation role for the code snippets in a method. To fill the gap, we have proposed an approach that combines heuristic rules and learning-based method to collect a large number of comment-code pairs from 1,032 open source projects in our previous study. In this paper, we propose a reinforcement learning-based method, RL-BlockCom, to automatically generate block comments for code snippets based on the collected comment-code pairs. Specifically, we utilize the abstract syntax tree (i.e., AST) of a code snippet to generate a token sequence with a statement-based traversal way. Then we propose a composite learning model, which combines the actor-critic algorithm of reinforcement learning with the encoder-decoder algorithm, to generate block comments. On the data set of the comment-code pairs, the BLEU-4 score of our method is 24.28, which outperforms the baselines and state-of-the-art in comment generation.

关键词： Automatic comment generation source code summarization code comment scope Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Fret: Functional Reinforced Transformer With BERT for code summarization

引用

IEEE ACCESS 2020年 8卷 135591-135604页

作者： Wang, Ruyun Zhang, Hanwen Lu, Guoliang Lyu, Lei Lyu, Chen Shandong Normal Univ Sch Informat Sci & Engn Jinan 250014 Shandong Peoples R China Shandong Univ Sch Mech Engn Jinan 250061 Shandong Peoples R China

code summarization has long been viewed as a challenge in software engineering because of the difficulties of understanding source code and generating natural language. Some mainstream methods combine abstract syntax trees with language models to capture the structural information of the source code and generate relatively satisfactory comments. However, these methods are still deficient in code understanding and limited by the long dependency problem. In this paper, we propose a novel model called Fret, which stands for Functional REinforced Transformer with BERT. The model provides a new way to generate code comments by learning code functionalities and deepening code understanding while alleviating the problem of long dependency. For this purpose, a novel reinforcer is proposed for learning the functional contents of code so that more accurate summaries to describe the code functionalities can be generated. In addition, a more efficient algorithm is newly designed to capture the source code structure. The experimental results show that the effectiveness of our model is remarkable. Fret significantly outperforms all the state-of-the-art methods we examine. It pushes the BLEU-4 score to 24.32 for Java code summarization (14.23% absolute improvement) and the ROUGE-L score to 40.12 for Python. An ablation test is also conducted to further explore the impact of each component of our method.

关键词： Bit error rate Neural networks Task analysis Semantics Software engineering Natural languages Syntactics BERT language representation model software engineering source code summarization transformer network

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：