检索结果-内蒙古大学图书馆

Towards an interface for translating natural language questions to SQL: A conceptual framework from a systematic review

引用

International Journal of Reasoning-based Intelligent systems 2020年第4期12卷 264-275页

作者： Ahkouk, Karam Machkour, Mustapha Team of Engineering and Information Systems Information Systems and Vision Laboratory Faculty of Sciences Ibn Zohr University Agadir Morocco

Querying relational databases using human language is a complex process that must take into consideration the lack of knowledge of SQL by the end users who use the content of these systems. Many studies published in the last decade are based on limited, unbalanced or even small datasets, thing that is by far not realistic for training and evaluating a model. The SQL structure is rich and the scale of complexity is very large. Moreover, the difference between the natural language, which is a language of communication, and the SQL language that contains details of implementation specific to relational databases, adds more complications to the problem. In this paper, we present a full systematic review of the existing approaches in the task of text to SQL and we introduce the details of our suggested architecture as well as our new approach to tackle the problem of nested queries. Copyright © 2020 Inderscience Enterprises Ltd.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

A novel hypergraph neural network combining multi-view learning with density awareness

引用

Pattern Recognition 2025年 168卷

作者： Liao, Jianpeng Yan, Jun Tao, Qian Zhang, Enze Zhang, Yanchao School of Software South China University of Technology Guangdong Guangzhou510006 China Concordia Institute for Information Systems Engineering Concordia University MontréalQuébecH3G 1M8 Canada Pazhou Lab Guangdong Guangzhou510335 China

Graph-based semi-supervised node classification has become a vital area in pattern recognition, with numerous applications of substantial research importance. However, existing approaches typically rely solely on either the intrinsic graph structure or artificially constructed graphs, potentially leading to inaccuracies in capturing the true data correlations, thus diminishing performance in downstream graph neural networks. Additionally, while current methods predominantly utilize explicit graph structures, there exists untapped potential in leveraging implicit information such as density for enhanced performance. To address these limitations, this paper introduces the Multi-view Density-aware Hypergraph Neural Network (MD-HGNN), a novel dual connection model that simultaneously integrates hypergraph structure and representation learning in a unified architecture. The MD-HGNN begins by utilizing a multi-view hypergraph learning (MVHL) network to explore the optimal hypergraph structure from multiple views, constrained by a consistency loss proposed to improve its generalization. Subsequently, it employs a density-aware hypergraph attention (DAHAT) network to explore the high-order semantic correlation among data points based on the density-aware attention mechanism. Extensive experiments across diverse benchmark datasets validate the efficacy of the proposed MD-HGNN approach, showcasing its superior performance in semi-supervised node classification tasks. © 2025 Elsevier Ltd

关键词： Graph neural networks

来源：评论

学校读者我要写书评

暂无评论

BOOM - A first step to an object-oriented fourth generation system

引用

JOURNAL OF systems AND software 1996年第2期33卷 171-177页

作者： Rumerstorfer, H Altmann, J Management Information Systems Software Engineering Department Johannes Kepler University A-4040 Linz Austria

This article describes BOOM, an object-oriented fourth-generation system. BOOM supports the powerful and elegant development of information systems in an object-oriented manner. By using object-oriented techniques, the complexities in building information systems can be handled more easily, and the development process in general can be improved and revived. BOOM decouples development from the physical environment. BOOM developers build a logical object-oriented data model that, after development, is automatically transferred into a relational database system. The toolset supplied for the construction of information systems includes components for the definition of structural object-oriented data models,for the generation of user interfaces, and the arrangement of application logic. Generic operations for manipulating user-defined objects are provided for every BOOM application. BOOM objects are stored in a relational database and are dynamically loaded on demand. Further, how the object model is transformed to relational tables is illustrated.

关键词： Object oriented programming

来源：评论

学校读者我要写书评

暂无评论

Architecture, Tools, and DSLs for Developing Conversational Agents: An Overview 14

Architecture, Tools, and DSLs for Developing Conversational ...

引用

14th International Conference on Emerging Ubiquitous systems and Pervasive Networks / 13th International Conference on Current and Future Trends of information and Communication Technologies in Healthcare, EUSPN/ICTH 2023

作者： Ouaddi, Charaf Benaddi, Lamya Jakimi, Abdeslam Software Engineering and Information Systems Engineering Team FST Errachidia University of Moulay Ismail Meknes50050 Morocco

Conversational agents (CA) are software programs that can converse with users using natural language. They are now widely used in various domains, such as tourism, healthcare, and others, to perform tasks and provide permanent assistance to users by interacting with them in natural language. The development of such applications is a task that requires expertise in several fields, such as software engineering, machine learning, deep learning, and natural language processing (NLP). However, several platforms and frameworks on the market facilitate the building of CA, such as Dialogflow, Rasa, and others. Recently, several research studies have proposed solutions to reduce the workload of developers and designers by offering their model-driven development approaches using domain-specific languages (DSLs), which facilitate the automation of the development of CA. This work aims to provide an Overview of CA to identify and describe their architecture and the details of its key components. and discuss the tools and technologies for their development. At the same time, discover the research topics that focus on using DSLs for model-driven development to automate and speed up the creation of these agents and discover approaches and technologies employed to implement each of these DSLs. © 2024 Elsevier B.V.. All rights reserved.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Towards A software Factory for Developing the Chatbots in Smart Tourism Mobile Applications 14

Towards A Software Factory for Developing the Chatbots in Sm...

引用

作者： Benaddi, Lamya Ouaddi, Charaf Jakimi, Abdeslam Ouchao, Brahim Software Engineering and Information Systems Engineering Team FST Errachidia University of Moulay Ismail Meknes50050 Morocco

Today, the tourism industry is significantly impacted by mobile applications leveraging Artificial Intelligence (AI) and Natural Language Processing (NLP) to enhance tourists' experiences before, during, and after their visits. This technological convergence has given rise to Smart Tourism Destinations (STDs). However, efficiently integrating these functionalities into mobile apps poses a major challenge, leading to the emergence of chatbots. Companies like IBM, Google, Microsoft, and Amazon offer tools such as Watson, Bot Framework, Dialogflow, and Amazon Lex for their development. Nevertheless, creating chatbots remains intricate, demanding expertise in software development and AI, along with associated costs related to NLP service providers. Additionally, employing an appropriate modeling language is crucial for designing a chatbot. At this juncture, the concepts of software factories and Domain-Specific Languages (DSLs) become indispensable. These innovative approaches provide solutions for addressing these complex challenges. software factories automate the development process, expediting chatbot creation while ensuring consistency. Simultaneously, DSLs furnish tools for accurately modeling and articulating the specific requirements of smart tourism, simplifying the development of tailor-made chatbots suited to this domain. This article introduces a model-driven approach for a DSL aimed at offering an abstract, high-level representation of the various aspects of chatbots within the context of an intelligent tourism mobile application. © 2024 Elsevier B.V.. All rights reserved.

关键词： Problem oriented languages

来源：评论

学校读者我要写书评

暂无评论

A Graphical DSL for Accelerating Chatbot Development 7

A Graphical DSL for Accelerating Chatbot Development

引用

7th International Conference on Advanced Communication Technologies and Networking, CommNet 2024

作者： Ouaddi, Charaf Benaddi, Lamya Naimi, Lahbib Bouziane, El Mahi Jakimi, Abdeslam Moulay Ismail University Software Engineering and Information Systems Engineering Team Faculty of Sciences and Technologies Errachidia Morocco

ISBN: (纸本)9798350367027

The development of chatbots utilizing artificial intelligence (AI) techniques represents a significant advancement in Natural Language Processing (NLP). Numerous studies employ deep learning and NLP methodologies to construct sophisticated chatbot systems. Additionally, developers and companies often utilize APIs provided by intent recognition services like Dialogflow and Amazon Lex to easily create chatbots using graphical forms, which enhance chatbot functionality. However, these APIs have limitations, such as potential dependency on specific NLP service providers and associated high costs. To address these limitations, the proposed work addresses critical gaps in chatbot development tools by constructing a Domain-Specific Language (DSL) for chatbot development. This DSL aims to simplify the chatbot development process and reduce costs. Specifically, the paper introduces a graphical DSL designed to accelerate chatbot development. We use code generation templates to easily generate the source code for chatbots of the Rasa framework, simplifying the development process and reducing the time spent on manual coding. © 2024 IEEE.

关键词： Bot (Internet)

来源：评论

学校读者我要写书评

暂无评论

Use Cases and Scenarios engineering in Smart software Application Development Services 7

Use Cases and Scenarios Engineering in Smart Software Applic...

引用

7th International Conference on Advanced Communication Technologies and Networking, CommNet 2024

作者： Bouziane, El Mahi Naimi, Lahbib Ouaddi, Charaf Benaddi, Lamya Jakimi, Abdeslam Moulay Ismail University Software Engineering and Information Systems Engineering Team Faculty of Sciences and Technologies Errachidia Morocco

ISBN: (纸本)9798350367027

Unified Modeling Language (UML) is a versatile tool for specifying, visualizing, and documenting software systems through diagrams. In the early stages of development, addressing design issues is critical to improving software quality and reducing costs. Use case modeling and UML scenario engineering are key techniques in requirements elicitation and specification development. This paper presents best practices for applying these techniques, highlighting their role in constructing accurate sequence diagrams and integrating formal specifications with user interface prototyping. Additionally, it explores extending scenarios to manage complex requirements like time and security constraints and offers a framework for visualizing business interactions in B2B environments to improve communication among stakeholders. © 2024 IEEE.

关键词： Requirements engineering

来源：评论

学校读者我要写书评

暂无评论

Code Generation Templates for Accelerating Chatbot Development in Smart Tourism 7

Code Generation Templates for Accelerating Chatbot Developme...

引用

7th International Conference on Advanced Communication Technologies and Networking, CommNet 2024

作者： Benaddi, Lamya Ouaddi, Charaf Souha, Adnane Jakimi, Abdeslam Ouchao, Brahim Moulay Ismail University Software Engineering and Information Systems Engineering Team Faculty of Sciences and Technologies Errachidia Morocco

ISBN: (纸本)9798350367027

The rapid advancement of Artificial Intelligence (AI) and Natural Language Processing (NLP) has positioned chatbots as essential tools across various industries, particularly in the tourism sector. These agents are computer programs designed to interact with users naturally. They can access services at any time, such as booking hotels, getting information about local attractions, or managing their travel itineraries. These chatbots enhance the customer experience by providing quick responses 24/7. However, developing chatbots tailored to specific tourism needs can be a time-consuming and complex process due to the use of a wide range of platforms like Dialogflow and *** providing NLP services, which can often be locked and require high costs for access. This paper proposes a solution using code generation templates and domain-specific language (DSL) that accelerates the development of chatbots in smart tourism. With this approach, both developers and non-Technical users can easily create chatbots, significantly reducing the need for manual coding efforts. © 2024 IEEE.

关键词： Chatbots

来源：评论

学校读者我要写书评

暂无评论

Fuzzy Granule Density-Based Outlier Detection with Multi-Scale Granular Balls

arXiv

引用

arXiv 2025年

作者： Gao, Can Tan, Xiaofeng Zhou, Jie Ding, Weiping Pedrycz, Witold The College of Computer Science and Software Engineering Shenzhen University Shenzhen518060 China Guangdong Key Laboratory of Intelligent Information Processing Shenzhen518060 China The National Engineering Laboratory for Big Data System Computing Technology Shenzhen University Shenzhen518060 China The School of Artificial Intelligence and Computer Science Nantong University Nantong226019 China The Faculty of Data Science City University of Macau Macau999078 China The Department of Electrical and Computer Engineering University of Alberta Edmonton Canada Systems Research Institute Polish Academy of Sciences Warsaw Poland The Department of Electrical and Computer Engineering King Abdulaziz University Jeddah Saudi Arabia The Department of Computer Engineering Istinye University Istanbul Turkey

Outlier detection refers to the identification of anomalous samples that deviate significantly from the distribution of normal data and has been extensively studied and used in a variety of practical tasks. However, most unsupervised outlier detection methods are carefully designed to detect specified outliers, while real-world data may be entangled with different types of outliers. In this study, we propose a fuzzy rough sets-based multi-scale outlier detection method to identify various types of outliers. Specifically, a novel fuzzy rough sets-based method that integrates relative fuzzy granule density is first introduced to improve the capability of detecting local outliers. Then, a multi-scale view generation method based on granular-ball computing is proposed to collaboratively identify group outliers at different levels of granularity. Moreover, reliable outliers and inliers determined by the three-way decision are used to train a weighted support vector machine to further improve the performance of outlier detection. The proposed method innovatively transforms unsupervised outlier detection into a semi-supervised classification problem and for the first time explores the fuzzy rough sets-based outlier detection from the perspective of multi-scale granular balls, allowing for high adaptability to different types of outliers. Extensive experiments carried out on both artificial and UCI datasets demonstrate that the proposed outlier detection method significantly outperforms the state-of-the-art methods, improving the results by at least 8.48% in terms of the Area Under the ROC Curve (AUROC) index. The source codes are released at https://***/Xiaofeng-Tan/MGBOD. © 2025, CC BY.

关键词： Granulation

来源：评论

学校读者我要写书评

暂无评论

Towards Label-Efficient Deep Learning-based Aging-related Bug Prediction with Spiking Convolutional Neural Networks

引用

IEEE Transactions on Emerging Topics in Computing 2025年

作者： Tian, Yunzhe Li, Yike Chen, Kang Zhang, Zhenguo Tong, Endong Liu, Jiqiang Qin, Fangyun Zheng, Zheng Niu, Wenjia Hebei Boshilin Technology Development Co. Ltd. Shijiazhuang050051 China Beijing Jiaotong University Beijing Key Laboratory of Security and Privacy in Intelligent Transportation Beijing100044 China Tangshan Research Institute of Beijing Jiaotong University Tangshan063000 China Capital Normal University College of Information Engineering Beijing100048 China Nanjing University State Key Laboratory for Novel Software Technology Nanjing210093 China Beihang University Laboratory of Dependable Intelligent Systems School of Automation Science and Electrical Engineering Beijing100191 China

Recent advances in Deep Learning (DL) have enhanced Aging-Related Bug (ARB) prediction for mitigating software aging. However, DL-based ARB prediction models face a dual challenge: overcoming overfitting to enhance generalization and managing the high labeling costs associated with extensive data requirements. To address the first issue, we utilize the sparse and binary nature of spiking communication in Spiking Neural Networks (SNNs), which inherently provides brain-inspired regularization to effectively alleviate overfitting. Therefore, we propose a Spiking Convolutional Neural Network (SCNN)-based ARB prediction model along with a training framework that handles the model's spatial-temporal dynamics and non-differentiable nature. To reduce labeling costs, we introduce a Bio-inspired and Diversity-aware Active Learning framework (BiDAL), which prioritizes highly informative and diverse samples, enabling more efficient usage of the limited labeling budget. This framework incorporates bio-inspired uncertainty to enhance informativeness measurement along with using a diversity-aware selection strategy based on clustering to prevent redundant labeling. Experiments on three ARB datasets show that ARB-SCNN effectively reduces overfitting, improving generalization performance by 6.65% over other DL-based classifiers. Additionally, BiDAL boosts label efficiency for ARB-SCNN training, outperforming four state-of-the-art active learning methods by 4.77% within limited labeling budgets. © 2013 IEEE.

关键词： Active learning

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：