检索结果-内蒙古大学图书馆

Project-Level Encoding for Neural source code summarization of Subroutines 29

Project-Level Encoding for Neural Source Code Summarization ...

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

作者： Bansal, Aakash Haque, Sakib McMillan, Collin Univ Notre Dame Dept Comp Sci & Engn Notre Dame IN 46556 USA

ISBN: (纸本)9781665414036

source code summarization of a subroutine is the task of writing a short, natural language description of that subroutine. The description usually serves in documentation aimed at programmers, where even brief phrase (e.g. "compresses data to a zip file") can help readers rapidly comprehend what a subroutine does without resorting to reading the code itself. Techniques based on neural networks (and encoder-decoder model designs in particular) have established themselves as the state-of-the-art. Yet a problem widely recognized with these models is that they assume the information needed to create a summary is present within the code being summarized itself - an assumption which is at odds with program comprehension literature. Thus a current research frontier lies in the question of encoding source code context into neural models of summarization. In this paper, we present a project-level encoder to improve models of code summarization. By project-level, we mean that we create a vectorized representation of selected code files in a software project, and use that representation to augment the encoder of state-of-the-art neural code summarization techniques. We demonstrate how our encoder improves several existing models, and provide guidelines for maximizing improvement while controlling time and resource costs in model size.

关键词： source code summarization automatic documentation generation neural networks

来源：评论

学校读者我要写书评

暂无评论

Retrieval-based Neural source code summarization 20

Retrieval-based Neural Source Code Summarization

引用

42nd ACM/IEEE International Conference on Software Engineering - Companion Proceedings (ICSE-Companion) / 42nd ACM/IEEE International Conference on Software Engineering - Software Engineering in Practice (ICSE-SEIP)

作者： Zhang, Jian Wang, Xu Zhang, Hongyu Sun, Hailong Liu, Xudong Beihang Univ SKLSDE Lab Beijing Peoples R China Univ Newcastle Callaghan NSW Australia

ISBN: (纸本)9781450371216

source code summarization aims to automatically generate concise summaries of source code in natural language texts, in order to help developers better understand and maintain source code. Traditional work generates a source code summary by utilizing information retrieval techniques, which select terms from original source code or adapt summaries of similar code snippets. Recent studies adopt Neural Machine Translation techniques and generate summaries from code snippets using encoder-decoder neural networks. The neural-based approaches prefer the high-frequency words in the corpus and have trouble with the low-frequency ones. In this paper, we propose a retrieval-based neural source code summarization approach where we enhance the neural model with the most similar code snippets retrieved from the training set. Our approach can take advantages of both neural and retrieval-based techniques. Specifically, we first train an attentional encoder-decoder model based on the code snippets and the summaries in the training set;Second, given one input code snippet for testing, we retrieve its two most similar code snippets in the training set from the aspects of syntax and semantics, respectively;Third, we encode the input and two retrieved code snippets, and predict the summary by fusing them during decoding. We conduct extensive experiments to evaluate our approach and the experimental results show that our proposed approach can improve the state-of-the-art methods.

关键词： source code summarization Information retrieval Deep neural network

来源：评论

学校读者我要写书评

暂无评论

Autofolding for source code summarization

引用

IEEE TRANSACTIONS ON SOFTWARE ENGINEERING 2017年第12期43卷 1095-1109页

作者： Fowkes, Jaroslav Chanthirasegaran, Pankajan Ranca, Razvan Allamanis, Miltiadis Lapata, Mirella Sutton, Charles Univ Edinburgh Sch Informat Edinburgh EH8 9AB Midlothian Scotland Tractable Oval Off 11-12 Oval London E2 9DT England

Developers spend much of their time reading and browsing source code, raising new opportunities for summarization methods. Indeed, modern code editors provide code folding, which allows one to selectively hide blocks of code. However this is impractical to use as folding decisions must be made manually or based on simple rules. We introduce the autofolding problem, which is to automatically create a code summary by folding less informative code regions. We present a novel solution by formulating the problem as a sequence of AST folding decisions, leveraging a scoped topic model for code tokens. On an annotated set of popular open source projects, we show that our summarizer outperforms simpler baselines, yielding a 28 percent error reduction. Furthermore, we find through a case study that our summarizer is strongly preferred by experienced developers. More broadly, we hope this work will aid program comprehension by turning code folding into a usable and valuable tool.

关键词： source code summarization program comprehension topic modelling

来源：评论

学校读者我要写书评

暂无评论

Automatic source code summarization of Context for Java Methods

引用

IEEE TRANSACTIONS ON SOFTWARE ENGINEERING 2016年第2期42卷 103-119页

作者： McBurney, Paul W. McMillan, Collin Univ Notre Dame Coll Comp Sci & Engn Notre Dame IN 46556 USA Univ Notre Dame Comp Sci South Bend VA USA

source code summarization is the task of creating readable summaries that describe the functionality of software. source code summarization is a critical component of documentation generation, for example as Javadocs formed from short paragraphs attached to each method in a Java program. At present, a majority of source code summarization is manual, in that the paragraphs are written by human experts. However, new automated technologies are becoming feasible. These automated techniques have been shown to be effective in select situations, though a key weakness is that they do not explain the source code's context. That is, they can describe the behavior of a Java method, but not why the method exists or what role it plays in the software. In this paper, we propose a source code summarization technique that writes English descriptions of Java methods by analyzing how those methods are invoked. We then performed two user studies to evaluate our approach. First, we compared our generated summaries to summaries written manually by experts. Then, we compared our summaries to summaries written by a state-of-the-art automatic summarization tool. We found that while our approach does not reach the quality of human-written summaries, we do improve over the state-of-the-art summarization tool in several dimensions by a statistically-significant margin.

关键词： source code summarization automatic documentation program comprehension

来源：评论

学校读者我要写书评

暂无评论

Automated feature discovery via sentence selection and source code summarization

引用

JOURNAL OF SOFTWARE-EVOLUTION AND PROCESS 2016年第2期28卷 120-145页

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

Programs are, in essence, a collection of implemented features. Feature discovery in software engineering is the task of identifying key functionalities that a program implements. Manual feature discovery can be time consuming and expensive, leading to automatic feature discovery tools being developed. However, these approaches typically only describe features using lists of keywords, which can be difficult for readers who are not already familiar with the source code. An alternative to keyword lists is sentence selection, in which one sentence is chosen from among the sentences in a text document to describe that document. Sentence selection has been widely studied in the context of natural language summarization but is only beginning to be explored as a solution to feature discovery. In this paper, we compare four sentence selection strategies for the purpose of feature discovery. Two are off-the-shelf approaches, while two are adaptations we propose. We present our findings as guidelines and recommendations to designers of feature discovery tools. Copyright (c) 2016 John Wiley & Sons, Ltd.

关键词： feature discovery sentence selection source code summarization

来源：评论

学校读者我要写书评

暂无评论

Automatic Documentation Generation via source code summarization 37

Automatic Documentation Generation via Source Code Summariza...

引用

IEEE/ACM 2nd International Workshop on Software Architecture and Metrics (SAM)

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

ISBN: (纸本)9781479919345

Programmers need software documentation. However, documentation is expensive to produce and maintain, and often becomes outdated over time. Programmers often lack the time and resources to write documentation. Therefore, automated solutions are desirable. Designers of automatic documentation tools are limited because there is not yet a clear understanding of what characteristics are important to generating high quality summaries. I propose three specific research objectives to improving automatic documentation generation. I propose to study the similarity between source code and summary. Second, I propose studying whether or not including contextual information about source code improves summary quality. Finally, I propose to study the problem of similarity in source code structure and source code documentation. This paper discusses my work on these three objectives towards my Ph.D. dissertation, including my preliminary and proposed work.

关键词： Automatic documentation Software engineering source code summarization

来源：评论

学校读者我要写书评

暂无评论

Context-aware code summarization with multi-relational graph neural network

引用

AUTOMATED SOFTWARE ENGINEERING 2025年第1期32卷 1-26页

作者： Wang, Yanlin Shi, Ensheng Du, Lun Yang, Xiaodi Hu, Yuxuan Wang, Yanli Guo, Daya Han, Shi Zhang, Hongyu Zhang, Dongmei Sun Yat Sen Univ Guangzhou Peoples R China Xi An Jiao Tong Univ Xian Peoples R China Microsoft Res Asia Beijing Peoples R China Univ Hong Kong Hong Kong Peoples R China Beijing Univ Technol Beijing Peoples R China Chongqing Univ Chongqing Peoples R China

source code summaries are short natural language descriptions of code snippets that help developers better understand and maintain source code. There has been a surge of work on automatic code summarization to reduce the burden of writing summaries manually. However, contemporary approaches only leverage the information within the boundary of the method being summarized (i.e., local context), and ignore the broader context that could assist with code summarization. This paper explores two global contexts, namely intra-class and inter-class contexts, and proposes CoCoSUM: Context-Aware code summarization with Multi-Relational Graph Neural Network. CoCoSUM first incorporates class names as the intra-class context to generate the class semantic embeddings. Then, relevant Unified Modeling Language (UML) class diagrams are extracted as inter-class context and are encoded into the class relational embeddings using a novel Multi-Relational Graph Neural Network (MRGNN). Class semantic embeddings and class relational embeddings, together with the outputs from code token encoder and AST encoder, are passed to a decoder armed with a two-level attention mechanism to generate high-quality, context-aware code summaries. Experimental results show that CoCoSUM outperforms state-of-the-art methods and the global contexts adopted in CoCoSUM can also strengthen existing code summarization models. Our replication package is anonymously available at https://***/DeepSoftwareAnalytics/cocosum.

关键词： source code summarization Unified modeling language Graph neural network Transformer

来源：评论

学校读者我要写书评

暂无评论

Leveraging meta-data of code for adapting prompt tuning for code summarization

引用

APPLIED INTELLIGENCE 2025年第2期55卷 1-15页

作者： Jiang, Zhihua Wang, Di Rao, Dongning Jinan Univ Dept Comp Sci 601 West Huangpu Ave Guangzhou 510632 Guangdong Peoples R China Guangdong Univ Technol Sch Comp 100 Waihuan West Rd Guangzhou 510006 Guangdong Peoples R China

Prompt tuning alleviates the gap between pre-training and fine-tuning and achieves promising results in various natural language processing (NLP) tasks. However, it is nontrivial for adapting prompt tuning in intelligent code tasks since code-specific knowledge such as abstract syntax tree is usually hierarchy-structured and therefore is hard to be converted into plain text. Recent works (e.g., PT4code) introduce simple task prompts along with a programming language indicator into prompt template, achieving improvement over non-prompting state-of-the-art code models (e.g., codeT5). Inspired by this, we propose a novel code-specific prompt paradigm, meta-data prompt, which introduces semi-structured code's meta-data (attribute-value pairs) into prompt template and facilitates the adaption of prompt tuning techniques into code tasks. Specifically, we find the usage of diverse meta-data attributes and their combinations and employ the OpenPrompt to implement a meta-data prompt based code model, PRIME (PRompt tunIng with MEta-data), via utilizing codeT5 as the backbone model. We experiment PRIME with the source code summarization task on the publicly available codeSearchNet benchmark. Results show that 1) using good meta-data can lead to an improvement on the model performance;2) the proposed meta-data prompt can be combined with traditional task prompt for further improvement;3) our best-performing model can consistently outperform codeT5 by an absolute score of 0.73 and PT4code by an absolute score of 0.48 regarding the averaged BLEU metric across six programming languages.

关键词： code intelligence source code summarization Prompt tuning Meta-data prompt

来源：评论

学校读者我要写书评

暂无评论

Programmer Visual Attention During Context-Aware code summarization

引用

IEEE TRANSACTIONS ON SOFTWARE ENGINEERING 2025年第5期51卷 1524-1537页

作者： Wallace, Robert Bansal, Aakash Karas, Zachary Tang, Ningzhi Huang, Yu Jia-Jun Li, Toby McMillan, Collin Univ Notre Dame Dept Comp Sci & Engn Notre Dame IN 46556 USA Vanderbilt Univ Dept Comp Sci Nashville TN 37235 USA

Programmer attention represents the visual focus of programmers on parts of the source code in pursuit of programming tasks. The focus of current research in modeling this programmer attention has been on using mouse cursors, keystrokes, or eye tracking equipment to map areas in a snippet of code. These approaches have traditionally only mapped attention for a single method. However, there is a knowledge gap in the literature because programming tasks such as source code summarization require programmers to use contextual knowledge that can only be found in other parts of the project, not only in a single method. To address this knowledge gap, we conducted an in-depth human study with 10 Java programmers, where each programmer generated summaries for 40 methods from five large Java projects over five one-hour sessions. We used eye tracking equipment to map the visual attention of programmers while they wrote the summaries. We also rate the quality of each summary. We found eye-gaze patterns and metrics that define common behaviors between programmer attention during context-aware code summarization. Specifically, we found that programmers need to read up to 35% fewer words (p < 0.01) over the whole session, and revisit 13% fewer words (p < 0.03) as they summarize each method during a session, while maintaining the quality of summaries. We also found that the amount of source code a participant looks at correlates with a higher quality summary, but this trend follows a bell-shaped curve, such that after a threshold reading more source code leads to a significant decrease (p < 0.01) in the quality of summaries. We also gathered insight into the type of methods in the project that provide the most contextual information for code summarization based on programmer attention. Specifically, we observed that programmers spent a majority of their time looking at methods inside the same class as the target method to be summarized. Surprisingly, we found that programmers spent

关键词： codes Visualization source coding Gaze tracking Unified modeling language Java Context modeling Cognitive science Algorithms Programming Automatic documentation generation source code summarization neural networks context-aware models

来源：评论

学校读者我要写书评

暂无评论

Evaluating source code summarization Techniques: Replication and Expansion

Evaluating Source Code Summarization Techniques: Replication...

引用

IEEE 21st International Conference on Program Comprehension (ICPC)

作者： Eddy, Brian P. Robinson, Jeffrey A. Kraft, Nicholas A. Carver, Jeffrey C. Univ Alabama Dept Comp Sci Tuscaloosa AL 35487 USA

ISBN: (纸本)9781467330923

During software evolution a developer must investigate source code to locate then understand the entities that must be modified to complete a change task. To help developers in this task, Haiduc et al. proposed text summarization based approaches to the automatic generation of class and method summaries, and via a study of four developers, they evaluated source code summaries generated using their techniques. In this paper we propose a new topic modeling based approach to source code summarization, and via a study of 14 developers, we evaluate source code summaries generated using the proposed technique. Our study partially replicates the original study by Haiduc et al. in that it uses the objects, the instruments, and a subset of the summaries from the original study, but it also expands the original study in that it includes more subjects and new summaries. The results of our study both support the findings of the original and provide new insights into the processes and criteria that developers use to evaluate source code summaries. Based on our results, we suggest future directions for research on source code summarization.

关键词： Program comprehension text summarization topic modeling source code summarization replication study

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：