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

Enhancing source code summarization from structure and semantics

Enhancing source code summarization from structure and seman...

引用

International Joint Conference on Neural Networks (IJCNN)

作者： Lu, Xurong Niu, Jun Ningbo Univ Fac Elect Engn & Comp Sci Ningbo Peoples R China Zhejiang Key Lab Mobile Network Applicat Technol Ningbo Peoples R China Zhejiang Engn Res Ctr Adv Mass Spectrometry & Cli Ningbo Peoples R China

ISBN: (纸本)9781665488679

source code summarization aims to generate concise and high-quality natural language descriptions for code snippets. High-quality code summaries can help developers better understand source codes. Researchers have made great efforts to generate more accurate summaries;however, due to the lack of preservation of source code structure and semantics, previous approaches have struggled to generate summaries that accurately describe the functionality or other major characteristics of codes. In this paper, we propose a novel approach called code Structure and Semantic Fusion (CSSF) for automatically generating summaries for source code. CSSF can utilize both the structural and semantic information of source codes. To achieve this, we extract the overall structure of the Abstract Syntax Tree (AST) by expanding the AST and using a heterogeneous graph attention network. Furthermore, we use an additional sequence model to obtain the semantic information of the code fragment. Finally, we fuse the two kinds of information through a novel modality fusion method. We evaluate our approach on a widely used Java dataset;experimental results confirm that our approach outperforms existing methods.

关键词： source code summarization Deep learning Graph neural network

来源：评论

学校读者我要写书评

暂无评论

Distilled GPT for source code summarization

引用

AUTOMATED SOFTWARE ENGINEERING 2024年第1期31卷 22-22页

作者： Su, Chia-Yi McMillan, Collin Univ Notre Dame Dept Comp Sci Holy Cross Dr Notre Dame IN 46556 USA

A code summary is a brief natural language description of source code. Summaries are usually only a single sentence long, and yet form the backbone of developer documentation. A short descriptions such as "changes all visible polygons to the color blue" can give a programmer a high-level idea of what code does without the effort of reading the code itself. Recently, products based on Large Language Models such as ChatGPT have demonstrated a strong ability to write these descriptions automatically. However, to use these tools, programmers must send their code to untrusted third parties for processing (e.g., via an API call). This loss of custody is not acceptable to many organizations. In this paper, we present an alternative: we train an open source model using sample output generated by GPT-\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$-$$\end{document}3.5 in a process related to knowledge distillation. Our model is small enough (350 m parameters) to be run on a single 16gb GPU, yet we show in our evaluation that it is large enough to mimic GPT-\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$-$$\end{document}3.5 on this task.

关键词： source code summarization Software documentation generation Language model

来源：评论

学校读者我要写书评

暂无评论

Automatic source code summarization with graph attention networks

引用

JOURNAL OF SYSTEMS AND SOFTWARE 2022年 188卷

作者： Zhou, Yu Shen, Juanjuan Zhang, Xiaoqing Yang, Wenhua Han, Tingting Chen, Taolue Nanjing Univ Aeronaut & Astronaut Coll Comp Sci & Technol Nanjing Peoples R China Birkbeck Univ London Dept Comp Sci London England Nanjing Univ State Key Lab Novel Software Technol Nanjing Peoples R China

source code summarization aims to generate concise descriptions for code snippets in a natural language, thereby facilitates program comprehension and software maintenance. In this paper, we propose a novel approach-GSCS-to automatically generate summaries for Java methods, which leverages both semantic and structural information of the code snippets. To this end, GSCS utilizes Graph Attention Networks to process the tokenized abstract syntax tree of the program, which employ a multi-head attention mechanism to learn node features in diverse representation sub-spaces, and aggregate features by assigning different weights to its neighbor nodes. GSCS further harnesses an additional RNN-based sequence model to obtain the semantic features and optimizes the structure by combining its output with a transformed embedding layer. We evaluate our approach on two widely adopted Java datasets;the experiment results confirm that GSCS outperforms the state-of-the-art baselines. (c) 2022 Elsevier Inc. All rights reserved.

关键词： source code summarization Recurrent neural network Graph neural network

来源：评论

学校读者我要写书评

暂无评论

Revisiting file context for source code summarization

引用

AUTOMATED SOFTWARE ENGINEERING 2024年第2期31卷 62-62页

作者： Su, Chia-Yi Bansal, Aakash McMillan, Collin Univ Notre Dame Dept Comp Sci Holy Cross Dr Notre Dame IN 46556 USA Louisiana State Univ Div Comp Sci Baton Rouge LA 70803 USA

source code summarization is the task of writing natural language descriptions of source code. A typical use case is generating short summaries of subroutines for use in API documentation. The heart of almost all current research into code summarization is the encoder-decoder neural architecture, and the encoder input is almost always a single subroutine or other short code snippet. The problem with this setup is that the information needed to describe the code is often not present in the code itself-that information often resides in other nearby code. In this paper, we revisit the idea of "file context" for code summarization. File context is the idea of encoding select information from other subroutines in the same file. We propose a novel modification of the Transformer architecture that is purpose-built to encode file context and demonstrate its improvement over several baselines. We find that file context helps on a subset of challenging examples where traditional approaches struggle.

关键词： source code summarization Program comprehension Software and its documentation Information systems Natural language processing Machine translation

来源：评论

学校读者我要写书评

暂无评论

FMCF: A fusing multiple code features approach based on Transformer for Solidity smart contracts source code summarization

引用

APPLIED SOFT COMPUTING 2024年 166卷

作者： Lei, Gang Zhang, Donghua Xiao, Jianmao Fan, Guodong Cao, Yuanlong Feng, Zhiyong Jiangxi Normal Univ Sch Software Nanchang 330022 Peoples R China Jiangxi Normal Univ Sch Digital Ind Shangrao 334000 Peoples R China Tianjin Univ Coll Intelligence & Comp Tianjin 300350 Peoples R China

A smart contract is a software program executed on a blockchain, designed to facilitate functionalities such as contract execution, asset administration, and identity validation within a secure and decentralized ecosystem. Summarizing the code of Solidity smart contracts aids developers in promptly grasping essential functionalities, thereby enhancing the security posture of Ethereum-based projects. Existing smart contract code summarization works mainly use traditional information retrieval and single code features, resulting in suboptimal performance. In this study, we propose a fusing multiple code features (FMCF) approach based on Transformer for Solidity summarization. First, FMCF created contract integrity modeling and state immutability modeling in the data preprocessing stage to process and filter data that meets security conditions. At the same time, FMCF retains the self-attention mechanism to construct the Graph Attention Network (GAT) encoder and codeBERT encoder, which respectively extract multiple feature vectors of the code to ensure the integrity of the source code information. Furthermore, the FMCF uses a weighted summation method to input these two types of feature vectors into the feature fusion module for fusion and inputs the fused feature vectors into the Transformer decoder to obtain the final smart contract code summarization. The experimental results show that FMCF outperforms the standard baseline methods by 12.45% in the BLEU score and maximally preserves the semantic information and syntax structures of the source code. The results demonstrate that the FMCF can provide a good direction for future research on smart contract code summarization, thereby helping developers enhance the security of development projects.

关键词： Solidity smart contracts source code summarization Feature fusion Transformer Structure-based traversal Manual evaluation

来源：评论

学校读者我要写书评

暂无评论

引用

JOURNAL OF SOFTWARE-EVOLUTION AND PROCESS 2024年第11期36卷

作者： Su, Chia-Yi McMillan, Collin Univ Notre Dame Dept Comp Sci & Engn Notre Dame IN USA Holy Cross Dr Notre Dame IN 46556 USA

This paper presents a procedure for and evaluation of using a semantic similarity metric as a loss function for neural source code summarization. code summarization is the task of writing natural language descriptions of source code. Neural code summarization refers to automated techniques for generating these descriptions using neural networks. Almost all current approaches involve neural networks as either standalone models or as part of a pretrained large language models, for example, GPT, codex, and LLaMA. Yet almost all also use a categorical cross-entropy (CCE) loss function for network optimization. Two problems with CCE are that (1) it computes loss over each word prediction one-at-a-time, rather than evaluating a whole sentence, and (2) it requires a perfect prediction, leaving no room for partial credit for synonyms. In this paper, we extend our previous work on semantic similarity metrics to show a procedure for using semantic similarity as a loss function to alleviate this problem, and we evaluate this procedure in several settings in both metrics-driven and human studies. In essence, we propose to use a semantic similarity metric to calculate loss over the whole output sentence prediction per training batch, rather than just loss for each word. We also propose to combine our loss with CCE for each word, which streamlines the training process compared to baselines. We evaluate our approach over several baselines and report improvement in the vast majority of conditions. We proposed a procedure for using semantic similarity as a loss function. We evaluated this loss function with both purpose-built models and large language model (LLM). The results in terms of human study and automatic metrics show that models trained with this loss function are better than models trained with categorical cross-entropy (CCE). image

关键词： human ratings and feedback loss functions neural models optimization 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

CrowdSummarizer Automated Generation of code Summaries for Java Programs through Crowdsourcing

引用

IEEE SOFTWARE 2017年第2期34卷 71-80页

作者： Badihi, Sahar Heydarnoori, Abbas Sharif Univ Technol Software Engn Tehran Iran Sharif Univ Technol Dept Comp Engn Tehran Iran

CrowdSummarizer exploits crowdsourcing, gamification, and natural-language processing to automatically generate high-level summaries of Java program methods. Researchers have implemented it as an Eclipse plug-in toget... 详细信息

关键词： Computer Games Crowdsourcing Java Natural Language Processing Software Maintenance source code Software Eclipse Plug In Software Engineering Web Based code summarization Game High Level Summaries Java Program Gamification Natural Language Processing Program source code Software Maintenance code Summary Automated Generation Crowd Summarizer Software Reliability Crowdsourcing Java Software Maintenance Software Engineering Software Measurement Crowd Summarizer Crowdsourcing Program Comprehension source code summarization Gamification Software Engineering Software Development

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：