检索结果-内蒙古大学图书馆

documentation Matters: Human-Centered AI System to Assist Data Science code documentation in Computational Notebooks

引用

ACM TRANSACTIONS ON COMPUTER-HUMAN INTERACTION 2022年第5期29卷 1-33页

作者： Wang, April Yi Wang, Dakuo Drozdal, Jaimie Muller, Michael Park, Soya Weisz, Justin D. Liu, Xuye Wu, Lingfei Dugan, Casey Univ Michigan 105 South State St Ann Arbor MI 48109 USA IBM Res 75 Binney St Cambridge MA 02142 USA Rensselaer Polytech Inst 110 Eighth St Troy NY 12180 USA MIT CSAIL 32 Vassar St Cambridge MA 02139 USA

Computational notebooks allow data scientists to express their ideas through a combination of code and documentation. However, data scientists often pay attention only to the code, and neglect creating or updating their documentation during quick iterations. Inspired by human documentation practices learned from 80 highly-voted Kaggle notebooks, we design and implement Themisto, an automated documentation generation system to explore how human-centered AI systems can support human data scientists in the machine learning code documentation scenario. Themisto facilitates the creation of documentation via three approaches: a deep-learning-based approach to generate documentation for source code, a query-based approach to retrieve online API documentation for source code, and a user prompt approach to nudge users to write documentation. We evaluated Themisto in a within-subjects experiment with 24 data science practitioners, and found that automated documentation generation techniques reduced the time for writing documentation, reminded participants to document code they would have ignored, and improved participants' satisfaction with their computational notebook.

关键词： code summarization computational notebooks code documentation

来源：评论

学校读者我要写书评

暂无评论

Automatic code documentation Generation Using GPT-3 7

Automatic Code Documentation Generation Using GPT-3

引用

37th IEEE/ACM International Conference on Automated Software Engineering (ASE)

作者： Khan, Junaed Younus Uddin, Gias Univ Calgary DISA Lab Calgary AB Canada

ISBN: (纸本)9781450394758

Source code documentation is an important artifact for efficient software development. code documentation could greatly benefit from automation since manual documentation is often labouring, resource and time-intensive. In this paper, we employed codex for automatic code documentation creation. codex is a GPT-3 based model pre-trained on both natural and programming languages. We find that codex outperforms existing techniques even with basic settings like one-shot learning (i.e., providing only one example for training). codex achieves an overall BLEU score of 20.6 for six different programming languages (11.2% improvement over earlier state-of-the-art techniques). Thus, codex shows promise and warrants in-depth future studies for automatic code documentation generation to support diverse development tasks.

关键词： code documentation GPT-3 Machine Learning

来源：评论

学校读者我要写书评

暂无评论

A Comparative Analysis of Large Language Models for code documentation Generation 1

A Comparative Analysis of Large Language Models for Code Doc...

引用

1st International Conference on AI-Powered Software (AIware)

作者： Dvivedi, Shubhang Shekhar Vijay, Vyshnav Pujari, Sai Leela Rahul Lodh, Shoumik Kumar, Dhruv IIIT Delhi New Delhi India

ISBN: (纸本)9798400706851

This paper presents a comprehensive comparative analysis of Large Language Models (LLMs) for generation of code documentation. code documentation is an essential part of the software writing process. The paper evaluates models such as GPT-3.5, GPT-4, Bard, Llama2, and StarChat on various parameters like Accuracy, Completeness, Relevance, Understandability, Readability and Time Taken for different levels of code documentation. Our evaluation employs a checklist-based system to minimize subjectivity, providing a more objective assessment. We find that, barring StarChat, all LLMs consistently outperform the original documentation. Notably, closedsource models GPT-3.5, GPT-4, and Bard exhibit superior performance across various parameters compared to open-source/sourceavailable LLMs, namely Llama 2 and StarChat. Considering the time taken for generation, GPT-4 demonstrated the longest duration by a significant margin, followed by Llama2, Bard, with GPT-3.5 and StarChat having comparable generation times. Additionally, file level documentation had a considerably worse performance across all parameters (except for time taken) as compared to inline and function level documentation.

关键词： code documentation Large Language Models

来源：评论

学校读者我要写书评

暂无评论

Prioritizing code documentation effort: Can we do it simpler but better?

引用

INFORMATION AND SOFTWARE TECHNOLOGY 2021年 140卷 106686-106686页

作者： Liu, Shiran Guo, Zhaoqiang Li, Yanhui Lu, Hongmin Chen, Lin Xu, Lei Zhou, Yuming Xu, Baowen Nanjing Univ State Key Lab Novel Software Technol Nanjing Jiangsu Peoples R China

Context: . Due to time or economic pressures, code developers are often unable to write documents for all modules in a project. Recently, a supervised artificial neural network (ANN) approach is proposed to prioritize documentation effort "to ensure that sections of code important to program comprehension are thoroughly explained". Objective: . However, as a supervised approach, there is a need to use labeled training data to train the prediction model, which may not easy to obtain in practice. Furthermore, it is unclear whether the ANN approach is generalizable, as it is only evaluated on several small data sets collected from API libraries. Method: . In this paper, we propose an unsupervised approach based on improved PageRank to prioritize documentation effort. This approach identifies "important" modules only based on the dependence relationships between modules in a project. As a result, the PageRank approach does not need any training data to build the prediction model. Results: . In order to evaluate the effectiveness of the PageRank approach, we use six additional large data sets collected from two larger libraries and four applications to conduct the experiment. The experimental results show that the PageRank approach is superior to the state-of-the-art ANN approach. Conclusion: . Due to the simplicity and effectiveness, we advocate that the PageRank approach should be used as an easy-to-implement baseline in future research on documentation effort prioritization, and any newly proposed approach should be compared with it to demonstrate its effectiveness.

关键词： code documentation Program comprehension PageRank Metrics

来源：评论

学校读者我要写书评

暂无评论

Automatic code documentation Generation Using GPT-3 22

Automatic Code Documentation Generation Using GPT-3

引用

Proceedings of the 37th IEEE/ACM International Conference on Automated Software Engineering

作者： Junaed Younus Khan Gias Uddin DISA Lab University of Calgary Canada

ISBN: (纸本)9781450394758

关键词： Machine Learning. code documentation GPT-3

来源：评论

学校读者我要写书评

暂无评论

Combining Contexts from Multiple Sources for documentation -Specific code Example Generation 30

Combining Contexts from Multiple Sources for Documentation -...

引用

30th IEEE International Conference on Software Analysis, Evolution and Reengineering (SANER)

作者： Khan, Junaed Younus Uddin, Gias Univ Calgary DISA Lab Calgary AB Canada

ISBN: (纸本)9781665452786

code example is a crucial part of good documentation. It helps the developers to understand the documentation easily and use the corresponding code unit (e.g., method) properly. However, many official documentation still lacks (good) code example and it is one of the common documentation issues as found by several studies. Hence in this paper, we consider automatic code example generation for documentation, a direction less explored by the existing research. We employ codex, a GPT3 based model, pre-trained on both natural and programming languages to generate code examples from source code and documentation given as input. Our preliminary investigation on 40 scikit-learn methods reveals that this approach is able to generate good code examples where 72.5% code examples were executed without error (passability) and 82.5% properly dealt with the target method and documentation (relevance). We also find that incorporation of error logs (produced by the compiler while executing a failed code example) in the input further improves the passability from 72.5% to 87.5%. Thus, our investigation sets the base of documentation-specific code example generation and warrants in-depth future studies.

关键词： code Example code documentation Machine Learning GPT-3 codex

来源：评论

学校读者我要写书评

暂无评论

PyScribe-Learning to describe python code

引用

SOFTWARE-PRACTICE & EXPERIENCE 2024年第3期54卷 501-527页

作者： Guo, Juncai Liu, Jin Liu, Xiao Wan, Yao Zhao, Yanjie Li, Li Liu, Kui Klein, Jacques Bissyande, Tegawende Wuhan Univ Sch Comp Sci Wuhan Peoples R China Chinese Acad Sci Inst Informat Engn Key Lab Network Assessment Technol Beijing Peoples R China Deakin Univ Sch Informat Technol Melbourne Australia Huazhong Univ Sci & Technol Sch Comp Sci & Technol Wuhan Peoples R China Monash Univ Fac Informat Technol Clayton Vic Australia Beihang Univ Sch Software Beijing Peoples R China Huawei Software Engn Applicat Technol LabHangzhou Hangzhou Peoples R China Univ Luxembourg SnT Ctr Esch Sur Alzette Luxembourg

code comment generation, which attempts to summarize the functionality of source code in textual descriptions, plays an important role in automatic software development research. Currently, several structural neural networks have been exploited to preserve the syntax structure of source code based on abstract syntax trees (ASTs). However, they can not well capture both the long-distance and local relations between nodes while retaining the overall structural information of AST. To mitigate this problem, we present a pro-to type tool titled PyScribe, which extends the Transformer model to a new encoder-decoder-based framework. Particularly, the triplet position is designed and integrated into the node-level and edge-level structural features of AST for producing Python code comments automatically. This paper, to the best of our knowledge, makes the first effort to model the edges of AST as an explicit component for improved code representation. By specifying triplet positions for each node and edge, the overall structural information can be well preserved in the learning process. Moreover, the captured node and edge features go through a two-stage decoding process to yield higher qualified comments. To evaluate the effectiveness of PyScribe, we resort to a large dataset of code-comment pairsby mining Jupyter Notebooks from GitHub, for which we have made it publicly available to support further studies. The experimental results reveal that PyScribe is indeed effective, outperforming the state-of the-art by achieving an average BLEU score (i.e., av-BLEU) of approximate to 0.28.

关键词： code comprehension code documentation code embedding code summarization deep learning representation learning

来源：评论

学校读者我要写书评

暂无评论

Pride: Prioritizing documentation Effort Based on a PageRank-Like Algorithm and Simple Filtering Rules

引用

IEEE TRANSACTIONS ON SOFTWARE ENGINEERING 2023年第3期49卷 1118-1151页

作者： Pan, Weifeng Ming, Hua Kim, Dae-Kyoo Yang, Zijiang Zhejiang Gongshang Univ Sch Comp Sci & Informat Engn Hangzhou 310018 Zhejiang Peoples R China Oakland Univ Sch Engn & Comp Sci Rochester MI 48309 USA Xi An Jiao Tong Univ Sch Comp Sci Xian 710049 Shaanxi Peoples R China Guard Strike Inc Xian 710049 Shaanxi Peoples R China

code documentation can be helpful in many software quality assurance tasks. However, due to resource constraints (e.g., time, human resources, and budget), programmers often cannot document their work completely and timely. In the literature, two approaches (one is supervised and the other is unsupervised) have been proposed to prioritize documentation effort to ensure the most important classes to be documented first. However, both of them contain several limitations. The supervised approach overly relies on a difficult-to-obtain labeled data set and has high computation cost. The unsupervised one depends on a graph representation of the software structure, which is inaccurate since it neglects many important couplings between classes. In this paper, we propose an improved approach, named Pride, to prioritize documentation effort. First, Pride uses a weighted directed class coupling network to precisely describe classes and their couplings. Second, we propose a PageRank-like algorithm to quantify the importance of classes in the whole class coupling network. Third, we use a set of software metrics to quantify source code complexity and further propose a simple but easy-to-operate filtering rule. Fourth, we sort all the classes according to their importance in descending order and use the filtering rule to filter out unimportant classes. Finally, a threshold k is utilized, and the top -k% ranked classes are the identified important classes to be documented first. Empirical results on a set of nine software systems show that, according to the average ranking of the Friedman test, Pride is superior to the existing approaches in the whole data set.

关键词： codes documentation Couplings Software Software metrics Java Task analysis code documentation program comprehension software maintenance PageRank software metrics

来源：评论

学校读者我要写书评

暂无评论

Generating Unit Tests for documentation

引用

IEEE TRANSACTIONS ON SOFTWARE ENGINEERING 2022年第9期48卷 3268-3279页

作者： Nassif, Mathieu Hernandez, Alexa Sridharan, Ashvitha Robillard, Martin P. McGill Univ Sch Comp Sci Montreal PQ H3A 0E9 Canada

Software projects capture redundant information in various kinds of artifacts, as specifications from the source code are also tested and documented. Such redundancy provides an opportunity to reduce development effort by supporting the joint generation of different types of artifacts. We introduce a tool-supported technique, called DScribe, that allows developers to combine unit test and documentation templates, and to invoke these templates to generate documentation and unit tests. DScribe supports the detection and replacement of outdated documentation, and the use of templates can encourage extensive test suites with a consistent style. Our evaluation of 835 specifications revealed that 85 percent were not tested or correctly documented, and DScribe could be used to automatically generate 97 percent of the tests and documentation. An additional study revealed that tests generated by DScribe are more focused and readable than those written by human testers or generated by state-of-the-art automated techniques.

关键词： documentation Testing Skeleton Java Software Redundancy Libraries code documentation testing testing tools test generation maintainability specification management

来源：评论

学校读者我要写书评

暂无评论

Towards Prioritizing documentation Effort

引用

IEEE TRANSACTIONS ON SOFTWARE ENGINEERING 2018年第9期44卷 897-913页

作者： McBurney, Paul W. Jiang, Siyuan Kessentini, Marouane Kraft, Nicholas A. Armaly, Ameer Mkaouer, Mohamed Wiem McMillan, Collin Univ Penn Dept Comp & Informat Sci 200 S 33Rd St Philadelphia PA 19104 USA Univ Notre Dame Dept Comp Sci & Engn Notre Dame IN 46556 USA Univ Michigan Dearborn Dept Comp & Informat Sci Dearborn MI 48128 USA ABB Corp Res Raleigh NC 27606 USA

Programmers need documentation to comprehend software, but they often lack the time to write it. Thus, programmers must prioritize their documentation effort to ensure that sections of code important to program comprehension are thoroughly explained. In this paper, we explore the possibility of automatically prioritizing documentation effort. We performed two user studies to evaluate the effectiveness of static source code attributes and textual analysis of source code towards prioritizing documentation effort. The first study used open-source API Libraries while the second study was conducted using closed-source industrial software from ABB. Our findings suggest that static source code attributes are poor predictors of documentation effort priority, whereas textual analysis of source code consistently performed well as a predictor of documentation effort priority.

关键词： code documentation program comprehension software maintenance

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：