检索结果-内蒙古大学图书馆

您好，读者！请登录

内蒙古大学图书馆

首页
概况
党建
资源
服务
科研支持
- 论文收录引用证明
- 科技查新
知识产权
档案馆
帮助

咨询与建议

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

您的常用邮箱：*

您的手机号码：*

问题描述：

当前已输入0个字，您还可以输入200个字

全部搜索
期刊论文
图书
学位论文
标准
纸本馆藏
外文资源发现
数据库导航
超星发现

高级检索

时间限定

出版年份：

文献类型

图书期刊文献学位论文多媒体

馆藏选择

电子馆藏纸本馆藏

核心期刊

全部期刊 SCI 收录期刊 SSCI 收录期刊 EI 收录期刊 CSCD 收录期刊 CSSCI 收录期刊

语言

中文英文

文献类型

期刊文献图书学位论文标准纸本馆藏

帮助

文字说明：

T=题名（书名、题名），A=作者（责任者），K=主题词，P=出版物名称，PU=出版社名称，O=机构（作者单位、学位授予单位、专利申请人），L=中图分类号，C=学科分类号，U=全部字段，Y=年（出版发行年、学位年度、标准发布年）

检索规则说明：

AND代表“并且”；OR代表“或者”；NOT代表“不包含”；(注意必须大写,运算符两边需空一格)

检索范例：

范例一：(K=图书馆学 OR K=情报学) AND A=范并思 AND Y=1982-2016
范例二：P=计算机应用与软件 AND (U=C++ OR U=Basic) NOT K=Visual AND Y=2011-2016

分类表

所选分类

>> <<

限定检索结果

文献类型

56 篇 会议
35 篇 期刊文献

馆藏范围

91 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

85 篇 工学
- 73 篇 计算机科学与技术...
- 66 篇 软件工程
- 11 篇 电气工程
- 6 篇 控制科学与工程
- 3 篇 信息与通信工程
- 1 篇 仪器科学与技术
- 1 篇 电子科学与技术（可...
2 篇 管理学
- 1 篇 管理科学与工程(可...
- 1 篇 图书情报与档案管...
1 篇 理学
- 1 篇 化学
1 篇 医学
- 1 篇 基础医学(可授医学...

主题

91 篇 code summarizati...
20 篇 deep learning
10 篇 transformer
9 篇 program comprehe...
8 篇 information retr...
5 篇 empirical study
5 篇 abstract syntax ...
4 篇 graph neural net...
4 篇 transfer learnin...
4 篇 contrastive lear...
3 篇 representation l...
3 篇 code representat...
3 篇 api
3 篇 code comment
3 篇 code retrieval
3 篇 clone detection
3 篇 reverse engineer...
3 篇 attention mechan...
3 篇 code comprehensi...
2 篇 ast

机构

7 篇 east china univ ...
4 篇 peking univ peop...
4 篇 shanghai engn re...
3 篇 sun yat sen univ...
3 篇 beihang univ sch...
3 篇 deakin univ sch ...
3 篇 univ chinese aca...
3 篇 wuhan univ sch c...
3 篇 peking univ natl...
3 篇 sun yat sen univ...
3 篇 chinese acad sci...
2 篇 peking univ key ...
2 篇 soochow univ sch...
2 篇 york univ lasson...
2 篇 sichuan univ col...
2 篇 china acad ind i...
2 篇 zhejiang univ pe...
2 篇 nanjing univ sta...
2 篇 chongqing univ s...
2 篇 univ calif davis...

作者

7 篇 yu huiqun
7 篇 fan guisheng
7 篇 zhou ziyi
4 篇 jin zhi
4 篇 zhang shikun
4 篇 hu tianxiang
4 篇 ye wei
4 篇 huang zijie
4 篇 li ge
4 篇 lyu chen
4 篇 xie rui
4 篇 chen qiuyuan
3 篇 li li
3 篇 li xuandong
3 篇 zhu tingwei
3 篇 wan yao
3 篇 ding xi
3 篇 liu xiao
3 篇 zhang tian
3 篇 guo juncai

语言

91 篇 英文
1 篇 德文
1 篇 法文
1 篇 意大利文

检索条件"主题词=code summarization"

共 91 条记录，以下是31-40 订阅

全选清除本页清除全部题录导出标记到"检索档案"

详细简洁

排序：

Interpretation-based code summarization 31

Interpretation-based Code Summarization

引用

31st IEEE/ACM International Conference on Program Comprehension (ICPC)

作者： Geng, Mingyang Wang, Shangwen Dong, Dezun Wang, Haotian Cao, Shaomeng Zhang, Kechi Jin, Zhi Natl Univ Def Technol Coll Comp Sci Changsha Peoples R China Peng Cheng Lab Shenzhen Peoples R China Peking Univ Key Lab High Confidence Software Technol Beijing Peoples R China

ISBN: (纸本)9798350337501

code comment, i.e., the natural language text to describe the semantic of a code snippet, is an important way for developers to comprehend the code. Recently, a number of approaches have been proposed to automatically generate the comment given a code snippet, aiming at facilitating the comprehension activities of developers. Despite that state-of-the-art approaches have already utilized advanced machine learning techniques such as the Transformer model, they often ignore critical information of the source code, leading to the inaccuracy of the generated summarization. In this paper, to boost the effectiveness of code summarization, we propose a two-stage paradigm, where in the first stage, we train an off-the-shelf model and then identify its focuses when generating the initial summarization, through a model interpretation approach, and in the second stage, we reinforce the model to generate more qualified summarization based on the source code and its focuses. Our intuition is that in such a manner the model could learn to identify what critical information in the code has been captured and what has been missed in its initial summarization, and thus revise its initial summarization accordingly, just like how a human student learns to write high-quality summarization for a natural language text. Extensive experiments on two large-scale datasets show that our approach can boost the effectiveness of five state-of-the-art code summarization approaches significantly. Specifically, for the well-known code summarizer, DeepCom, utilizing our two-stage paradigm can increase its BLEU-4 values by around 30% and 25% on the two datasets, respectively.

关键词： Automatic Comment Generation code summarization Model Interpretation

来源：评论

学校读者我要写书评

暂无评论

Improving code summarization with Block-wise Abstract Syntax Tree Splitting 29

Improving Code Summarization with Block-wise Abstract Syntax...

引用

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

作者： Lin, Chen Ouyang, Zhichao Zhuang, Junqing Chen, Jianqiang Li, Hui Wu, Rongxin Xiamen Univ Xiamen Peoples R China

ISBN: (纸本)9781665414036

Automatic code summarization frees software developers from the heavy burden of manual commenting and benefits software development and maintenance. Abstract Syntax Tree (AST), which depicts the source code's syntactic structure, has been incorporated to guide the generation of code summaries. However, existing AST based methods suffer from the difficulty of training and generate inadequate code summaries. In this paper, we present the Block-wise Abstract Syntax Tree Splitting method (BASTS for short), which fully utilizes the rich tree-form syntax structure in ASTs, for improving code summarization. BASTS splits the code of a method based on the blocks in the dominator tree of the Control Flow Graph, and generates a split AST for each code split. Each split AST is then modeled by a Tree-LSTM using a pre-training strategy to capture local non-linear syntax encoding. The learned syntax encoding is combined with code encoding, and fed into Transformer to generate high-quality code summaries. Comprehensive experiments on benchmarks have demonstrated that BASTS significantly outperforms state-of-the-art approaches in terms of various evaluation metrics. To facilitate reproducibility, our implementation is available at https://***/XMUDM/BASTS.

关键词： code summarization code Splitting Abstract Syntax Tree

来源：评论

学校读者我要写书评

暂无评论

Reassessing Automatic Evaluation Metrics for code summarization Tasks 2021

Reassessing Automatic Evaluation Metrics for Code Summarizat...

引用

29th ACM Joint Meeting on European Software Engineering Conference and Symposium on the Foundations of Software Engineering (ESEC/FSE)

作者： Roy, Devjeet Fakhoury, Sarah Arnaoudova, Venera Washington State Univ Pullman WA 99164 USA

ISBN: (纸本)9781450385626

In recent years, research in the domain of source code summarization has adopted data-driven techniques pioneered in machine translation (MT). Automatic evaluation metrics such as BLEU, METEOR, and ROUGE, are fundamental to the evaluation of MT systems and have been adopted as proxies of human evaluation in the code summarization domain. However, the extent to which automatic metrics agree with the gold standard of human evaluation has not been evaluated on code summarization tasks. Despite this, marginal improvements in metric scores are often used to discriminate between the performance of competing summarization models. In this paper, we present a critical exploration of the applicability and interpretation of automatic metrics as evaluation techniques for code summarization tasks. We conduct an empirical study with 226 human annotators to assess the degree to which automatic metrics reflect human evaluation. Results indicate that metric improvements of less than 2 points do not guarantee systematic improvements in summarization quality, and are unreliable as proxies of human evaluation. When the difference between metric scores for two summarization approaches increases but remains within 5 points, some metrics such as METEOR and chrF become highly reliable proxies, whereas others, such as corpus BLEU, remain unreliable. Based on these findings, we make several recommendations for the use of automatic metrics to discriminate model performance in code summarization.

关键词： automatic evaluation metrics code summarization machine translation

来源：评论

学校读者我要写书评

暂无评论

iiPCS: Intent-Based In-Context Learning for Project-Specific code summarization

iiPCS: Intent-Based In-Context Learning for Project-Specific...

引用

International Joint Conference on Neural Networks (IJCNN)

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

ISBN: (纸本)9798350359329;9798350359312

Recent years have witnessed growing research interest in automatic source code summarization due to its beneficial potential in software development and maintenance tasks. In the past few years, various deep learning models have been developed to leverage structural and textual features in the code for generating meaningful and succinct summaries. However, the summaries generated by traditional deep learning models often have syntax errors or are meaningless. The emergence of large language models provides an opportunity to overcome the problem. However, the quality of the summaries largely depends on the in-context learning examples of code-summary pairs. In this work, we develop iiPCS, an LLM-based method for code summarization. We retrieve relevant code-summary pairs as incontext learning examples from the same project of the target code, which ensures to generate more project-specific summaries, and use the predicted intent of the target code to pick few-shot examples, which ensures to generate summaries with the correct intent. Experimental results show that iiPCS can generate code summaries with higher quality compared to traditional methods using deep learning and recent methods using LLMs.

关键词： code summarization Large Language Models Project-specific Summaries In-context Learning Developer Intent

来源：评论

学校读者我要写书评

暂无评论

Leveraging Comment Retrieval for code summarization 1

引用

45th European Conference on Information Retrieval (ECIR)

作者： Hou, Shifu Chen, Lingwei Ju, Mingxuan Ye, Yanfang Univ Notre Dame Notre Dame IN 46556 USA Wright State Univ Dayton OH 45435 USA

ISBN: (数字)9783031282386

ISBN: (纸本)9783031282379;9783031282386

Open-source code often suffers from mismatched or missing comments, leading to difficult code comprehension, and burdening software development and maintenance. In this paper, we design a novel code summarization model codeFiD to address this laborious challenge. Inspired by retrieval-augmented methods for open-domain question answering, codeFiD first retrieves a set of relevant comments from code collections for a given code, and then aggregates presentations of code and these comments to produce a natural language sentence that summarizes the code behaviors. Different from current code summarization works that focus on improving code representations, our model resorts to external knowledge to enhance code summarizing performance. Extensive experiments on public code collections demonstrate the effectiveness of codeFiD by outperforming state-of-the-art counterparts across all programming languages.

关键词： code summarization Comment retrieval Heterogeneous graph neural network Fusion-in-Decoder

来源：评论

学校读者我要写书评

暂无评论

Leveraging In-and-Cross Project Pseudo-Summaries for Project-Specific code summarization

Leveraging In-and-Cross Project Pseudo-Summaries for Project...

引用

International Joint Conference on Neural Networks (IJCNN)

作者： Wu, Yupeng Hu, Tianxiang Liao, Ninglin Xie, Rui Zhang, Minghui Du, Dongdong Lin, Shujun Peking Univ Beijing Peoples R China Beijing Inst Control & Elect Technol Key Lab Informat Syst & Technol Beijing Peoples R China Peking Univ Handan Inst Innovat Handan Peoples R China China Acad Ind Internet Beijing Peoples R China Peking Univ Inst Global Hlth & Dev Beijing Peoples R China

ISBN: (纸本)9798350359329;9798350359312

code summarization is pivotal in software development, aiding developers in grasping the semantics of source code. However, existing research predominantly focuses on the general code summarization capabilities of models, neglecting project-specific summary characteristics. However, given the scarcity of project-internal code summary corpora, enhancing the model's performance for a specific project presents a significant challenge. To tackle this issue, we introduces the use of Inand-Cross project pseudo-summaries to improve Project-Specific code summarization. Specifically, we employ models trained on other projects to generate cross-project pseudo-summaries and learn the distinctions from target-project through contrastive learning. Simultaneously, we utilize in-project pseudo-summaries generated by the current model, harnessing these data through semi-supervised learning to enhance performance. The experiment results show that the proposed method can effectively improve the performance of the summarization task in practical scenarios, and can also enhance the coordination of the model.

关键词： matural language processing code summarization contrastive learning data augmentation.

来源：评论

学校读者我要写书评

暂无评论

A Multi-Modal Transformer-based code summarization Approach for Smart Contracts 29

A Multi-Modal Transformer-based Code Summarization Approach ...

引用

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

作者： Yang, Zhen Keung, Jacky Yu, Xiao Gu, Xiaodong Wei, Zhengyuan Ma, Xiaoxue Zhang, Miao City Univ Hong Kong Dept Comp Sci Hong Kong Peoples R China Wuhan Univ Technol Sch Comp Sci & Technol Wuhan Peoples R China Shanghai Jiao Tong Univ Sch Software Shanghai Peoples R China

ISBN: (纸本)9781665414036

code comment has been an important part of computer programs, greatly facilitating the understanding and maintenance of source code. However, high-quality code comments are often unavailable in smart contracts, the increasingly popular programs that run on the blockchain. In this paper, we propose a Multi-Modal Transformer-based (MMTrans) code summarization approach for smart contracts. Specifically, the MMTrans learns the representation of source code from the two heterogeneous modalities of the Abstract Syntax Tree (AST), i.e., Structure-based Traversal (SBT) sequences and graphs. The SBT sequence provides the global semantic information of AST, while the graph convolution focuses on the local details. The MMTrans uses two encoders to extract both global and local semantic information from the two modalities respectively, and then uses a joint decoder to generate code comments. Both the encoders and the decoder employ the multi-head attention structure of the Transformer to enhance the ability to capture the long-range dependencies between code tokens. We build a dataset with over 300K pairs of smart contracts, and evaluate the MMTrans on it. The experimental results demonstrate that the MMTrans outperforms the state-of-the-art baselines in terms of four evaluation metrics by a substantial margin, and can generate higher quality comments.

关键词： Smart Contracts code summarization Transformer Graph Convolution Structure-based Traversal

来源：评论

学校读者我要写书评

暂无评论

Improving code summarization Through Automated Quality Assurance 32

Improving Code Summarization Through Automated Quality Assur...

引用

32nd IEEE International Symposium on Software Reliability Engineering (ISSRE)

作者： Hu, Yuxing Yan, Meng Liu, Zhongxin Chen, Qiuyuan Wang, Bei Chongqing Univ Minist Educ Key Lab Dependable Serv Comp Cyber Phys Soc Chongqing Peoples R China Chongqing Univ Sch Big Data & Software Engn Chongqing Peoples R China Pengcheng Lab Shenzhen Peoples R China Zhejiang Univ Coll Comp Sci & Technol Hangzhou Peoples R China

ISBN: (纸本)9781665425872

The code summarization task aims to generate brief descriptions of source code automatically. It is beneficial for developers to understand source code. However, almost all of current code summarization approaches may generate low-quality (BLEU4<40) summaries, which will mislead developers. Previous work has shown that it is possible to conduct quality assurance for document generation (QA4DG) and improve the practicability of document generation approaches. code summarization can also be regarded as a document generation task. This work aims to investigate whether QA4DG approaches can be leveraged to improve code summarization. Specifically, we first investigate whether existing QA4DG approaches can be plugged in code summarization approaches. We find that an automated quality assurance framework for commit message generation named QACom performs best. Inspired by the idea behind QAcom, we propose an ensemble code summarization approach called Ensum. Precisely, given a code snippet, Ensum first uses current code summarization approaches to generate candidate summaries. Then, Ensum predicts the quality of each candidate summary using a collaborative filtering-based component and a retrieval-based component and selects the best candidate summary as the output. Experimental results on two public datasets show that Ensum outperforms three state-of-the-art single approaches and one ensemble approach for code summarization in terms of BLEU-4, METEOR, and ROUGE-L.

关键词： code summarization code Comment Quality Assurance

来源：评论

学校读者我要写书评

暂无评论

Multi-modal code summarization Fusing Local API Dependency Graph and AST 28th

Multi-modal Code Summarization Fusing Local API Dependency G...

引用

28th International Conference on Neural Information Processing

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

ISBN: (纸本)9783030923068;9783030923075

Automatically obtaining descriptions of the functions of code snippets in natural language, i.e., code summarization, is an important issue in software engineering. In recent years, abstract syntax tree (AST)-based code summarization models for modelling syntactic structures have continued to emerge. In addition to syntactics, the semantics of the code are gradually gaining attention. In this paper, we propose a code summarization approach that incorporates local-ADG and AST, called GTsum. In particular, we introduce a novel local-ADG-based approach that can effectively filter out irrelevant semantics in the modelling of the semantic structure of code. GTsum learns semantics and syntactics in the local-ADG and AST through graph convolutional networks (GCNs) and then fuses them using Transformer. We evaluate our model on two Java language datasets with several metrics. The results demonstrate that our model achieves state-of-the-art performance compared to the existing models.

关键词： code summarization Local API dependency graph Abstract syntax tree Graph convolutional network

来源：评论

学校读者我要写书评

暂无评论

EDITSUM: A Retrieve-and-Edit Framework for Source code summarization 36

EDITSUM: A Retrieve-and-Edit Framework for Source Code Summa...

引用

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

作者： Li, Jia Li, Yongmin Li, Ge Hu, Xing Xia, Xin Jin, Zhi Peking Univ MoE Key Lab High Confidence Software Technol Beijing Peoples R China Zhejiang Univ Sch Software Technol Ningbo Peoples R China Monash Univ Fac Informat Technol Melbourne Vic Australia

ISBN: (纸本)9781665403375

Existing studies show that code summaries help developers understand and maintain source code. Unfortunately, these summaries are often missing or outdated in software projects. code summarization aims to generate natural language descriptions automatically for source code. According to Gros et al., code summaries are highly structured and have repetitive patterns (e.g. "return true if..."). Besides the patternized words, a code summary also contains important keywords, which are the key to reflecting the functionality of the code. However, the state-of-the-art approaches perform poorly on predicting the keywords, which leads to the generated summaries suffer a loss in informativeness. To alleviate this problem, this paper proposes a novel retrieve-and-edit approach named EDIT Sum for code summarization. Specifically, EDITS um first retrieves a similar code snippet from a pre-defined corpus and treats its summary as a prototype summary to learn the pattern. Then, EDIT Sum edits the prototype automatically to combine the pattern in the prototype with the semantic information of input code. Our motivation is that the retrieved prototype provides a good startpoint for post-generation because the summaries of similar code snippets often have the same pattern. The post-editing process further reuses the patternized words in prototype and generates keywords based on the semantic information of input code. We conduct experiments on a large-scale Java corpus (2M) and experimental results demonstrate that EDITSum outperforms the state-of-the-art approaches by a substantial margin. The human evaluation also proves the summaries generated by EDIT Sum are more informative and useful. We also verify that EDIT Sum performs well on predicting the patternized words and keywords.

关键词： code summarization Information retrieval Deep learning

来源：评论

学校读者我要写书评

暂无评论

没有更多数据了...

全选清除本页清除全部题录导出标记到“检索档案”

共10页 << < 1 2 3 4 5 6 7 8 9 10 > >>

检索报告对象比较合并检索0

隐藏清空

合并搜索

回到顶部

执行限定条件

内容：

评分：

请选择保存的检索档案：

请选择收藏分类：

订阅名称：

通借通还

温馨提示：

图书名称：

借书校区：

取书校区：

手机号码：

邮箱地址：

一卡通帐号：

电话和邮箱必须正确填写，我们会与您联系确认。

联系人：

所在院系：

联系邮箱：

联系电话：

内蒙古自治区呼和浩特市赛罕区大学西街235号邮编: 010021

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：