检索结果-内蒙古大学图书馆

A Multi-Module Based Method for Generating Natural Language Descriptions of code Fragments

IEEE ACCESS 2021年 9卷 21579-21592页

作者： Gao, Xuejian Jiang, Xue Wu, Qiong Wang, Xiao Lyu, Lei Lyu, Chen Shandong Normal Univ Sch Informat Sci & Engn Jinan 250014 Peoples R China

code fragment natural language description generation, also known as code summarization, refers to obtaining a natural language sequence describing a given code fragment's functionality. It is broadly agreed that applying code summarization into production can significantly improve the efficiency of software development and maintenance. In recent years, syntactic analysis (SA) technology and Latent Dirichlet Allocation (LDA) has been widely used in code summarization and has achieved good results. However, most of the existing techniques focus on core code statements, and thus their generated code summarization lacks a logical description of the code fragment's holistic information. To this end, we propose a code summarization method based on multiple modules to generate natural language for each code statement by constructing a new type of natural language template. Meanwhile, to utilize the code fragment's holistic information, we adopt the code statement partition rules and cosine similarity measure to rank and optimize the weight of the overall information of the code fragment, and finally generate the holistic natural language description of the code fragment. The experimental results demonstrate that our method can generate more concise and logical natural language descriptions than existing models.

关键词： Natural languages Software Semantics Task analysis Java Standards Resource management source code summarization program comprehension program description

来源：评论

学校读者我要写书评

暂无评论

An empirical study of the textual similarity between source code and source code summaries

引用

EMPIRICAL SOFTWARE ENGINEERING 2016年第1期21卷 17-42页

作者： McBurney, Paul W. McMillan, Collin Univ Notre Dame Dept Comp Sci & Engn Notre Dame IN 46556 USA

source code documentation often contains summaries of source code written by authors. Recently, automatic source code summarization tools have emerged that generate summaries without requiring author intervention. These summaries are designed for readers to be able to understand the high-level concepts of the source code. Unfortunately, there is no agreed upon understanding of what makes up a "good summary." This paper presents an empirical study examining summaries of source code written by authors, readers, and automatic source code summarization tools. This empirical study examines the textual similarity between source code and summaries of source code using Short Text Semantic Similarity metrics. We found that readers use source code in their summaries more than authors do. Additionally, this study finds that accuracy of a human written summary can be estimated by the textual similarity of that summary to the source code.

关键词： source code summarization Documentation Textual similarity Automatic documentation generation

来源：评论

学校读者我要写书评

暂无评论

Grading Programming Assignments by summarization 24

Grading Programming Assignments by Summarization

引用

ACM Turing Award Celebration Conference (ACM-TURC)

作者： Dong, Dong Liang, Yue Hebei Normal Univ Coll Comp & Cyber Secur Shijiazhuang Peoples R China

ISBN: (纸本)9798400710117

Grading programming assignments manually is a big burden for instructors who teach programming languages for university students due to complexity and subjectivity. The black test approach adopted by online judge systems can only outputs either an answer is correct or incorrect. This study proposes a Large Language Model (LLM) approach to automatically grade answers from students for programming assignments. A LLM mode formed by coder-decoder architecture is utilized to generate summarization from source code, then the summarization is compared to the textual assignment description by semantic similarity. Finally, the output is converted to five-score rating. codeBERT and a Transformer model serve as coder and decoder respectively. The semantic similarity is computed by MiniLM-L6. The validation test shows that the accuracy of the suggested approach reaches 0.92.

关键词： automatic grading codeBERT source code summarization programming assignment assessment

来源：评论

学校读者我要写书评

暂无评论

Automatically Generating code Comment Using Heterogeneous Graph Neural Networks 29

Automatically Generating Code Comment Using Heterogeneous Gr...

引用

29th IEEE International Conference on Software Analysis, Evolution and Reengineering (SANER)

作者： Jin, Dun Liu, Peiyu Zhu, Zhenfang Shandong Normal Univ Sch Informat Sci & Engn Jinan Peoples R China Shandong Jiao Tong Univ Sch Informat Sci & Elect Engn Jinan Peoples R China

ISBN: (纸本)9781665437868

code summarization aims to generate readable summaries that describe the functionality of source code pieces. The main purpose of the code summarization is to help software developers understand the code and save their precious time. However, since programming languages are highly structured, it is challenging to generate high-quality code summaries. For this reason, this paper proposes a new approach named CCHG to automatically generate code comments. Compared to recent models that use additional information such as Abstract Syntax Trees as input, our proposed method only uses the most original code as input. We believe that programming languages are the same as natural languages. Each line of code is equivalent to a sentence, representing an independent meaning. Therefore, we split the entire code snippet into several sentence-level code. Coupled with token-level code, there are two types of code that need to be processed. So we propose heterogeneous graph networks to process the sentence-level and token-level code. Even though we do not introduce additional structural knowledge, the experimental results show that our model has a considerable performance, which indicates that our model can fully learn structural information and sequence information from code snippets.

关键词： source code summarization neural networks heterogeneous graph networks AI in SE

来源：评论

学校读者我要写书评

暂无评论

Creating Important Statement Type Comments in Autocomment: Automatic Comment Generation Framework 3

Creating Important Statement Type Comments in Autocomment: A...

引用

3rd International Conference on Computer Science and Engineering (UBMK)

作者： Yildiz, Eren Ekin, Emine Huawei Huawei Turkcy R&D Ctr Istanbul Turkey Isik Univ Dept Comp Engn Istanbul Turkey

ISBN: (纸本)9781538678930

This study explains important statement comments generated by Autocomment, which is an automatic comment generation framework described in [1]. To create the comments, the source code is not expected to be runnable, but to conliffm to the syntax rules of the Java programming language. Two types of comments are created: summary comments and important statement comments. How the important statements are extracted in a given Java source, how they are classified, how comments are generated for each type of important statement have been explained in this work.

关键词： source code summarization documentation generation program comprehension

来源：评论

学校读者我要写书评

暂无评论

Automatic Comment Generation using only source code 25

Automatic Comment Generation using only Source Code

引用

25th Signal Processing and Communications Applications Conference (SIU)

作者： Yildiz, Eren Ekin, Emine Isik Univ Bilgisayar Muhendisligi Bolumu Istanbul Turkey

ISBN: (纸本)9781509064946

In this study, automatic comment generation for Java methods is described. It is sufficient that the codes conform to the syntax rules of the Java programming language, and it is not expected to be runnable. In order to generate comments, source code is examined syntactically. At this stage, only the method signature and its return type is needed. By working on open source Java projects, different templates have been developed for different method types. Using the compiled information which is the result of the examining source code that is currently being developed, the most suitable template is chosen and texts arc created. These texts explain the aim of the method. Created texts are added to source code as a comment.

关键词： source code summarization documentation generation program comprehension

来源：评论

学校读者我要写书评

暂无评论

A Simple Retrieval-based Method for code Comment Generation 29

A Simple Retrieval-based Method for Code Comment Generation

引用

29th IEEE International Conference on Software Analysis, Evolution and Reengineering (SANER)

作者： Zhu, Xiaoning Sha, Chaofeng Niu, Junyu Fudan Univ Sch Comp Sci Shanghai Peoples R China Fudan Univ Shanghai Key Lab Data Sci Shanghai Peoples R China

ISBN: (纸本)9781665437868

code comments can effectively help developers comprehend programs. However, it is a challenging and time consuming task to write good comments for source code. Therefore, automatic generation of code comments is a promising research direction. Recently, researchers have leveraged neural machine translation to generate comments from source code and achieved impressive results. Another line of work has tried to exploit information retrieval (IR) techniques and showed excellent performance improvement on this task. However, current retrieval-based methods usually involve complex retrieval and editing operations, which are difficult to implement. To tackle the problems, we propose kNN-Transformer, a simple end-to-end retrieval-based code comment generation method. Our method combines a simple nearest neighbor retrieval module and a powerful transformer-based model. When generating each token, the retrieval module estimates a probability distribution depending on the current translation context rather than obtaining the retrieved samples in advance. The experiment results on four widely used public datasets (two Java datasets and two Python datasets) demonstrate that our method outperforms all the baselines, and our kNN retrieval module brings significant improvement when similar code snippets are available.

关键词： code comment generation source code summarization deep learning information retrieval

来源：评论

学校读者我要写书评

暂无评论

Evaluating code summarization with Improved Correlation with Human Assessment 21

Evaluating Code Summarization with Improved Correlation with...

引用

21st IEEE International Conference on Software Quality, Reliability and Security (QRS)

作者： Shen, Juanjuan Zhou, Yu Wang, Yongchao Chen, Xiang Han, Tingting Chen, Taolue Nanjing Univ Aeronaut & Astronaut Coll Comp Sci & Technol Nanjing Peoples R China Nantong Univ Sch Informat Sci & Technol Nantong Peoples R China Birkbeck Univ London Dept Comp Sci London England Nanjing Univ State Key Lab Novel Software Technol Nanjing Peoples R China

ISBN: (纸本)9781665458139

code summarization aims to automatically generate functionality descriptions of code snippets. Faithful metrics are needed to measure to which degree the machine generated summaries capture the semantics of the code snippets. Most commonly used metrics in code summarization, such as BLEU-4, METEOR, and ROUGE-L, originate from machine translation and text summarization, and have constantly been found to be inconsistent with human assessment. In this paper, we propose a novel evaluation metric, Consensus-based code summarization Evaluation (CCSE), which assigns different semantic weights to the n-grams of the summary. We also provide an algorithm to match the n-gram pairs from the reference and candidate based on the similarities. To validate the effectiveness of our proposed metric, we collect summary pairs from two public Java datasets and calculate the correlation coefficients between CCSE and the human evaluations. The experiment results show that, compared with BLEU-4, METEOR, and ROUGE-L, CCSE is more consistent with the scores assessed by human developers.

关键词： source code summarization Deep neural networks Automatic evaluation

来源：评论

学校读者我要写书评

暂无评论

AST-Transformer: Encoding Abstract Syntax Trees Efficiently for code summarization 36

AST-Transformer: Encoding Abstract Syntax Trees Efficiently ...

引用

36th IEEE/ACM International Conference on Automated Software Engineering (ASE)

作者： Tang, Ze Li, Chuanyi Ge, Jidong Shen, Xiaoyu Zhu, Zheling Luo, Bin Nanjing Univ State Key Lab Novel Software Technol Nanjing Jiangsu Peoples R China Saarland Informat Campus Saarbrucken Germany

ISBN: (纸本)9781665403375

code summarization aims to generate brief natural language descriptions for source code. As source code is highly structured and follows strict programming language grammars, its Abstract Syntax Tree (AST) is often leveraged to inform the encoder about the structural information. However, ASTs are usually much longer than the source code. Current approaches ignore the size limit and simply feed the whole linearized AST into the encoder. To address this problem, we propose AST-Transformer to efficiently encode tree-structured ASTs. Experiments show that AST-Transformer outperforms the state-of-arts by a substantial margin while being able to reduce 90 similar to 95% of the computational complexity in the encoding process.

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

Automatic Generation of Natural Language Summaries for Java Classes

Automatic Generation of Natural Language Summaries for Java ...

引用

IEEE 21st International Conference on Program Comprehension (ICPC)

作者： Moreno, Laura Aponte, Jairo Sridhara, Giriprasad Marcus, Andrian Pollock, Lori Vijay-Shanker, K. Wayne State Univ Detroit MI 48202 USA Univ Nacl Colombia Bogota Colombia IBM Res India Bangalore Karnataka India Univ Delaware Newark DE 19716 USA

ISBN: (纸本)9781467330923

Most software engineering tasks require developers to understand parts of the source code. When faced with unfamiliar code, developers often rely on (internal or external) documentation to gain an overall understanding of the code and determine whether it is relevant for the current task. Unfortunately, the documentation is often absent or outdated. This paper presents a technique to automatically generate human readable summaries for Java classes, assuming no documentation exists. The summaries allow developers to understand the main goal and structure of the class. The focus of the summaries is on the content and responsibilities of the classes, rather than their relationships with other classes. The summarization tool determines the class and method stereotypes and uses them, in conjunction with heuristics, to select the information to be included in the summaries. Then it generates the summaries using existing lexicalization tools. A group of programmers judged a set of generated summaries for Java classes and determined that they are readable and understandable, they do not include extraneous information, and, in most cases, they are not missing essential information.

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

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：