检索结果-内蒙古大学图书馆

Revisiting file context for source code summarization

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

引用

30th IEEE/ACM International Conference on Program Comprehension (ICPC)

作者： Haque, Sakib Eberhart, Zachary Bansal, Aakash McMillan, Collin Univ Notre Dame Notre Dame IN 46556 USA

ISBN: (纸本)9781450392983

source code summarization involves creating brief descriptions of source code in natural language. These descriptions are a key component of software documentation such as JavaDocs. Automatic code summarization is a prized target of software engineering research, due to the high value summaries have to programmers and the simultaneously high cost of writing and maintaining documentation by hand. Current work is almost all based on machine models trained via big data input. Large datasets of examples of code and summaries of that code are used to train an e.g. encoder-decoder neural model. Then the output predictions of the model are evaluated against a set of reference summaries. The input is code not seen by the model, and the prediction is compared to a reference. The means by which a prediction is compared to a reference is essentially word overlap, calculated via a metric such as BLEU or ROUGE. The problem with using word overlap is that not all words in a sentence have the same importance, and many words have synonyms. The result is that calculated similarity may not match the perceived similarity by human readers. In this paper, we conduct an experiment to measure the degree to which various word overlap metrics correlate to human-rated similarity of predicted and reference summaries. We evaluate alternatives based on current work in semantic similarity metrics and propose recommendations for evaluation of source code summarization.

关键词： source code summarization automatic documentation generation evaluation metrics

来源：评论

学校读者我要写书评

暂无评论

M2TS: Multi-Scale Multi-Modal Approach Based on Transformer for source code summarization 30

M2TS: Multi-Scale Multi-Modal Approach Based on Transformer ...

引用

30th IEEE/ACM International Conference on Program Comprehension (ICPC)

作者： Gao, Yuexiu Lyu, Chen Shandong Normal Univ Jinan Peoples R China

ISBN: (纸本)9781450392983

source code summarization aims to generate natural language descriptions of code snippets. Many existing studies learn the syntactic and semantic knowledge of code snippets from their token sequences and Abstract Syntax Trees (ASTs). They use the learned code representations as input to code summarization models, which can accordingly generate summaries describing source code. Traditional models traverse ASTs as sequences or split ASTs into paths as input. However, the former loses the structural properties of ASTs, and the latter destroys the overall structure of ASTs. Therefore, comprehensively capturing the structural features of ASTs in learning code representations for source code summarization remains a challenging problem to be solved. In this paper, we propose M2TS, a Multi-scale Multi-modal approach based on Transformer for source code summarization. M2TS uses a multi-scale AST feature extraction method, which can extract the structures of ASTs more completely and accurately at multiple local and global levels. To complement missing semantic information in ASTs, we also obtain code token features, and further combine them with the extracted AST features using a cross modality fusion method that not only fuses the syntactic and contextual semantic information of source code, but also highlights the key features of each modality. We conduct experiments on two Java and one Python datasets, and the experimental results demonstrate that M2TS outperforms current state-of-the-art methods. We release our code at https://***/TranSMS/M2TS.

关键词： source code summarization Transformer Neural network Deep learning

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

source code summarization Using Attention-based Keyword Memory Networks

Source Code Summarization Using Attention-based Keyword Memo...

引用

IEEE International Conference on Big Data and Smart Computing (BigComp)

作者： Choi, YunSeok Kim, Suah Lee, Jee-Hyong Sungkyunkwan Univ Dept Software Suwon South Korea Sungkyunkwan Univ Dept Elect & Comp Engn Suwon South Korea

ISBN: (纸本)9781728160344

Recently, deep learning techniques have been developed for source code summarization. Most existing studies have simply adopted natural language processing techniques, because source code summarization can be considered as machine translation tasks from source code into descriptions. However, source code and its description are very different, not only in the languages of writing, but also in the purpose of writing. There is a large semantic gap between source codes in programming languages and their descriptions in natural languages. To respond to the semantic gap, we propose a two-phase model that consists of a keyword predictor and a description generator. The keyword predictor captures the natural language keywords semantically associated with the source code, and the generator generates a description by referring to the natural language keywords provided by the predictor. Using such keywords as scaffolding, we can effectively reduce the semantic gap and generate more accurate descriptions of source codes. To evaluate the proposed method, we use datasets collected from GitHub and StackOverflow. We perform various experiments with these datasets. Our methods show outstanding performance compared with baselines that include state-of-the-art methods, which concludes that keyword prediction is very helpful to the generation of accurate descriptions.

关键词： source code summarization Keyword Memory Networks

来源：评论

学校读者我要写书评

暂无评论

Ensemble Models for Neural source code summarization of Subroutines 37

Ensemble Models for Neural Source Code Summarization of Subr...

引用

37th IEEE International Conference on Software Maintenance and Evolution (ICSME)

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

ISBN: (纸本)9781665428828

A source code summary of a subroutine is a brief description of that subroutine. Summaries underpin a majority of documentation consumed by programmers, such as the method summaries in JavaDocs. source code summarization is the task of writing these summaries. At present, most state-of-the-art approaches for code summarization are neural network-based solutions akin to seq2seq, graph2seq, and other encoder-decoder architectures. The input to the encoder is source code, while the decoder helps predict the natural language summary. While these models tend to be similar in structure, evidence is emerging that different models make different contributions to prediction quality - differences in model performance are orthogonal and complementary rather than uniform over the entire dataset. In this paper, we explore the orthogonal nature of different neural code summarization approaches and propose ensemble models to exploit this orthogonality for better overall performance. We demonstrate that a simple ensemble strategy boosts performance by up to 14.8%, and provide an explanation for this boost. The takeaway from this work is that a relatively small change to the inference procedure in most neural code summarization techniques leads to outsized improvements in prediction quality.

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

Transformer-XL With Graph Neural Network for source code summarization

Transformer-XL With Graph Neural Network for Source Code Sum...

引用

IEEE International Conference on Systems, Man, and Cybernetics (SMC)

作者： Zhang, Xiaoling Yang, Shouguo Duan, Luqian Lang, Zhe Shi, Zhiqiang Sun, Limin Univ Chinese Acad Sci Sch Cyber Secur Beijing Peoples R China Inst Informat Engn Beijing Key Lab IOT Informat Secur Technol CAS Beijing Peoples R China Beijing Univ Technol Beijing Peoples R China

ISBN: (纸本)9781665442077

source code summarization is the task of generating a readable natural language to describe the functionality of source code. code summarization is rapidly expanding, especially as the research takes great advantage of advances in neural networks and artificial intelligence technologies. Some mainstream methods input the structural information (abstract syntax tree (AST)) of the source code into the language model to generate relatively satisfactory comments. However, existing methods can not capture code's long dependencies from AST for effective code summarization. In this paper, we provide a novel way to generate code summaries by combining a graph-based neural network and a Transformer-XL network. We utilize the graph-based neural network to better capture the structure information of AST, and the Transformer-XL network to learn important tokens in the AST and alleviate the problem of long dependency. We evaluate our technique on the standard Java dataset. The experimental results show that the effectiveness of our model is remarkable. It pushes the precision score to 60.73% (5.21% absolute improvement) and the F1 score to 51.06%.

关键词： source code summarization Neural networks Deep learning Transformer-XL network

来源：评论

学校读者我要写书评

暂无评论

Action Word Prediction for Neural source code summarization 28

Action Word Prediction for Neural Source Code Summarization

引用

28th IEEE International Conference on Software Analysis, Evolution and Reengineering (SANER)

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

ISBN: (纸本)9781728196305

source code summarization is the task of creating short, natural language descriptions of source code. code summarization is the backbone of much software documentation such as JavaDocs, in which very brief comments such as "adds the customer object" help programmers quickly understand a snippet of code. In recent years, automatic code summarization has become a high value target of research, with approaches based on neural networks making rapid progress. However, as we will show in this paper, the production of good summaries relies on the production of the action word in those summaries: the meaning of the example above would be completely changed if "removes" were substituted for "adds." In this paper, we advocate for a special emphasis on action word prediction as an important stepping stone problem towards better code summarization - current techniques try to predict the action word along with the whole summary, and yet action word prediction on its own is quite difficult. We show the value of the problem for code summaries, explore the performance of current baselines, and provide recommendations for future research.

关键词： neural networks source code summarization automatic documentation generation AI in SE

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

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：