检索结果-内蒙古大学图书馆

31st International Conference on Computational Linguistics, COLING 2025

作者： Lawan, Adamu Pu, Juhua Yunusa, Haruna Umar, Aliyu Lawan, Muhammad School of Computer Science and Technology Beihang University Beijing China National Research Institute for Teaching Materials in Information Science and Tech. China School of Automation Science and Electrical Engineering Beihang University Beijing China School of Computing University of Portsmouth Portsmouth United Kingdom Department of Information and Communication Technology Federal University Gusau Nigeria

ISBN: (纸本)9798891761964

Aspect-based Sentiment Analysis (ABSA) evaluates sentiments toward specific aspects of entities within the text. However, attention mechanisms and neural network models struggle with syntactic constraints. The quadratic complexity of attention mechanisms also limits their adoption for capturing long-range dependencies between aspect and opinion words in ABSA. This complexity can lead to the misinterpretation of irrelevant contextual words, restricting their effectiveness to short-range dependencies. To address the above problem, we present a novel approach to enhance long-range dependencies between aspect and opinion words in ABSA (MambaForGCN). This approach incorporates syntax-based Graph Convolutional Network (SynGCN) and MambaFormer (Mamba-Transformer) modules to encode input with dependency relations and semantic information. The Multihead Attention (MHA) and Selective State Space model (Mamba) blocks in the MambaFormer module serve as channels to enhance the model with short and long-range dependencies between aspect and opinion words. We also introduce the Kolmogorov-Arnold Networks (KANs) gated fusion, an adaptive feature representation system that integrates SynGCN and MambaFormer and captures non-linear, complex dependencies. Experimental results on three benchmark datasets demonstrate MambaForGCN's effectiveness, outperforming state-of-the-art (SOTA) baseline models. © 2025 Association for Computational Linguistics.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

LI4 : Label-Infused Iterative information Interacting based Fact Verification in Question-answering Dialogue 30

LI4 : Label-Infused Iterative Information Interacting based ...

引用

Joint 30th International Conference on Computational Linguistics and 14th International Conference on Language Resources and Evaluation, LREC-COLING 2024

作者： Zhang, Xiaocheng Wang, Chang Zhao, Guoping Su, Xiaohong Faculty of Computing Harbin Institute of Technology Harbin China School of Computer Science Engineering South China University of Technology Guangzhou China Zhengzhou Esunny Information Technology Co. Ltd. Zhengzhou China

ISBN: (纸本)9782493814104

Fact verification constitutes a pivotal application in the effort to combat the dissemination of disinformation, a concern that has recently garnered considerable attention. However, previous studies in the field of fact verification, particularly those focused on question-answering dialogue, have exhibited limitations, such as failing to fully exploit the potential of question structures and ignoring relevant label information during the verification process. In this paper, we introduce Label-Infused Iterative information Interacting (LI4), a novel approach designed for the task of question-answering dialogue based fact verification. LI4 consists of two meticulously designed components, namely the Iterative information Refining and Filtering Module (IIRF) and the Fact Label Embedding Module (FLEM). The IIRF uses the Interactive Gating Mechanism to iteratively filter out the noise of question and evidence, concurrently refining the claim information. The FLEM is conceived to strengthen the understanding ability of the model towards labels by injecting label knowledge. We evaluate the performance of the proposed LI4 on HEALTHVER, FAVIQ, and COLLOQUIAL. The experimental results confirm that our LI4 model attains remarkable progress, manifesting as a new state-of-the-art performance. © 2024 ELRA Language Resource Association: CC BY-NC 4.0.

关键词： Refining

来源：评论

学校读者我要写书评

暂无评论

Empirical Investigation of the Diverse Refactoring Effects on Software Quality: The Role of Refactoring Tools and Software Size 3

Empirical Investigation of the Diverse Refactoring Effects o...

引用

3rd International Conference on Emerging Smart Technologies and Applications, eSmarTA 2023

作者： Almogahed, Abdullah Mahdin, Hairulnizam Omar, Mazni Zakaria, Nur Haryani Alawadhi, Abdulwadood Barraood, Samera Obaid Universiti Tun Hussein Onn Malaysia Faculty of Computer Science and Information Technology Johor Malaysia School of Computing Universiti Utara Malaysia Sintok Malaysia University of Science and Technology Faculty of Engineering and Computing Yemen Hadhramout University Collage of Computers and Information Technology Department of Computer Science Hadhramout Yemen

ISBN: (纸本)9798350305333

Recent research has shown that various refactoring methods have very diverse, often opposing, and contradicting impacts on software quality characteristics. While using refactoring methods to enhance software quality, developers confront difficulties in choosing effective refactoring methods. To date, there is a lack of research that has studied factors that might explain conflicting or divergent findings about the influence of refactoring methods on software quality. As a result, two factors were identified, explored, and fully evaluated in this study: refactoring tools and software size. Four of the most regularly used refactoring methods (Add Parameter, Remove Parameter, Extract Class, and Extract Superclass) in practice were selected and independently implemented in five case studies of varied sizes (small, medium, and large). The results give solid evidence that these factors have a substantial role in determining the diverse impacts of refactoring methods on quality characteristics. These insights may help software engineers understand how to employ refactoring methods to enhance software quality while taking these factors into account. Moreover, the results may provide guidelines for software engineers to apply refactoring methods to enhance the quality of software systems, depending on the optimal situation for employing the refactoring methods. © 2023 IEEE.

关键词： Computer software maintenance

来源：评论

学校读者我要写书评

暂无评论

A Sentimental Analysis Approach for Personalized Drug Recommendations Using Machine Learning 1

A Sentimental Analysis Approach for Personalized Drug Recomm...

引用

1st IEEE International Conference on computing and Data science, ICCDS 2024

作者： Vijayaraj, A. Murugan, V.P. Jebakumar, R. Gaurav, N.V. Santhosh, V. Shai Kumar, R. R.M.K. Engineering College Department of Information Technology Chennai India Panimalar Engineering College Department of Mathematics Chennai India School of Computing SRM Institute of Science and Technology Department of Computing Technologies Chennai India

ISBN: (纸本)9798350365337

Since the virus that causes corona disease was discovered, it has gotten more difficult to find medical professionals with the appropriate licenses, including doctors, nurses, diagnostic equipment, and medications. Due to the intense grieving, a substantial number of people in the medical industry pass away. Because of the scarcity, a lot of individuals began self-medicating without first consulting a doctor, which made the health problem worse. There are numerous well-established applications for machine learning, and recent years have witnessed a growth in the pace and breadth of computerization-related research and development. The goal of this research is to develop a method for recommending medications that might greatly reduce the obligations of specialists. In this work, we built a drug recommendation system that makes estimations about the emotional of patient reviews using a variety of different vectorization techniques, such as using a Bow, The TF-ID Word 2 Vector, or Manually Feature Analysis. The predicted emotions were graded using accuracy, remembrance, flscore, exactness, and the area beneath the slope (AUC). The results show that, when weighed against the other models, the classification technique Linear SVC + The TF -I vector process has the greatest accuracy. © 2024 IEEE.

关键词： Recommender systems

来源：评论

学校读者我要写书评

暂无评论

Topic Modelling and Sentimental Analysis of Students’Reviews

引用

Computers, Materials & Continua 2023年第3期74卷 6835-6848页

作者： Omer S.Alkhnbashi Rasheed Mohammad Nassr Information and Computer Science Department King Fahd University of Petroleum and Minerals31261Kingdom Saudi Arabia Computer Science Department School of Computing and Digital TechnologyBirmingham City UniversityBirminghamB55JUUnited Kingdom

Globally,educational institutions have reported a dramatic shift to online learning in an effort to contain the COVID-19 *** fundamental concern has been the continuance of *** a result,several novel solutions have been developed to address technical and pedagogical ***,these were not the only difficulties that students *** implemented solutions involved the operation of the educational process with less regard for students’changing circumstances,which obliged them to study from *** should be asked to provide a full list of their *** a result,student reflections,including those from Saudi Arabia,have been analysed to identify obstacles encountered during the COVID-19 ***,most of the analyses relied on closed-ended questions,which limited student *** delve into students’responses,this study used open-ended questions,a qualitative method(content analysis),a quantitative method(topic modelling),and a sentimental *** study also looked at students’emotional states during and after the COVID-19 *** terms of determining trends in students’input,the results showed that quantitative and qualitative methods produced similar *** had unfavourable sentiments about studying during COVID-19 and positive sentiments about the face-to-face ***,topic modelling has revealed that the majority of difficulties are more related to the environment(home)and social *** were less accepting of online *** a result,it is possible to conclude that face-to-face study still attracts students and provides benefits that online study cannot,such as social interaction and effective eye-to-eye communication.

关键词： Topic modelling sentimental analysis COVID-19 students’input

来源：评论

学校读者我要写书评

暂无评论

ANN Based Fake Profile Detection and Categorization Using Premetric Paradigms On Instagram

ANN Based Fake Profile Detection and Categorization Using Pr...

引用

2023 Innovations in Power and Advanced computing Technologies, i-PACT 2023

作者： Fathima, Afifa Salsabil Reema, Syeda Ahmed, Syed Thouheed School of Computer Science and Engineering REVA University Bangalore India School of Computing and Information Technology REVA University Bangalore India Indian Institute of Technology Hyderabad India

ISBN: (纸本)9798350325188

This study, focused on the behavioral analysis for the identification of social media accounts, endeavors to discern counterfeit profiles within social media networks by employing machine learning methodologies. The investigation is underpinned by a comprehensive dataset encompassing various user behavior-related attributes, including but not limited to the count of followers, followings, posts, private account status, and other relevant factors. The data is subjected to rigorous preprocessing procedures, which involve feature scaling and the division of the dataset into distinct training and testing subsets. Subsequently, a neural network model is trained utilizing the training dataset and rigorously evaluated using performance metrics such as accuracy and loss on the testing dataset. Additionally, the study delves into an examination of the confusion matrix to provide insight into the classification performance and offers a visual representation of the distribution of genuine and counterfeit accounts. The experimental results substantiate the model's efficacy in successfully identifying fake accounts through an in-depth analysis of their behavioral patterns. © 2023 IEEE.

关键词： ANN Confusion Matrix data analysis data modelling Data preprocessing fake account Feature extraction Heatmap Instagram neural network

来源：评论

学校读者我要写书评

暂无评论

Joint Vehicle Pairing, Spectrum Assignment and Power Control for Sum-Rate Maximization in NOMA-Based V2X Underlaid Cellular Networks

引用

IEEE Internet of Things Journal 2025年第12期12卷 22337-22349页

作者： Xue, Tong Zhang, Haixia Ding, Hui Yuan, Dongfeng Shandong University of Science and Technology College of Electronic and Information Engineering Shandong Qingdao266590 China Shandong Key Laboratory of Intelligent Communication and Sensing-Computing Integration Shandong Jinan250061 China Shandong University School of Control Science and Engineering Shandong Jinan250061 China

Vehicle-to-everything (V2X) underlaid cellular networks in underlaid mode suffers catastrophic co-channel interference caused by spectrum sharing, results in a reduced system sum-rate. To cope with this, this work studies a social-mobility-aware non-orthogonal multiple access (NOMA)-enabled V2X underlaid cellular network to mitigate the co-channel interference and improve the sum-rate. By jointly optimizing vehicle pairing and resources, a sum-rate maximization problem is formulated under the diverse quality of service requirements of both cellular and vehicular users. The formulated problem is proved to be a non-deterministic polynomial-time (NP)-hard problem, and is difficult to solve. As an alternative, we propose a NOMA-based joint vehicle pairing, spectrum assignment and power control algorithm (NOMA-JVP-SA-PCA), with which the original problem is decomposed into two disjoint subproblems, i. e., 1) joint vehicle pairing and spectrum assignment subproblem, and 2) power control subproblem. Dealing the first subproblem, we propose a heuristic social-mobility-aware vehicle pairing algorithm (HSMA-VPA) and a revised Kuhn-munkres-based spectrum assignment algorithm (KM-SAA) to acquire the vehicle pairing and spectrum assignment solutions. Then, solving the second subproblem, a closed-form power solution is obtained utilizing a three-dimensional geometric power control approach (3D-PCA). Finally, we solve the original problem through an iterative method. Simulation results show that the proposed NOMA-JVP-SA-PCA effectively enhances the sum-rate and outperforms the baseline algorithms around 24%-53% within a specific range. © 2014 IEEE.

关键词： Polynomial approximation

来源：评论

学校读者我要写书评

暂无评论

Lithological Facies Classification Using Attention-Based Gated Recurrent Unit

引用

Tsinghua science and technology 2024年第4期29卷 1206-1218页

作者： Yuwen Liu Yulan Zhang Xingyuan Mao Xucheng Zhou Jingwen Chang Wenwei Wang Pan Wang Lianyong Qi College of Computer Science and Technology China University of Petroleum(East China)Qingdao 266580China Shandong Provincial University Laboratory for Protected Horticulture Weifang University of Science and TechnologyShouguang 262700China School of Mechanical Electrical and Information EngineeringShandong UniversityWeihai 264209China Shandong Provincial Key Laboratory of Network Based Intelligent Computing University of JinanJinan 250022China School of Modern Posts Nanjing University of Posts and TelecommunicationsNanjing 210023China

Lithological facies classification is a pivotal task in petroleum geology, underpinning reservoir characterization and influencing decision-making in exploration and production operations. Traditional classification methods, such as support vector machines and Gaussian process classifiers, often struggle with the complexity and nonlinearity of geological data, leading to suboptimal performance. Moreover, numerous prevalent approaches fail to adequately consider the inherent dependencies in the sequence of measurements from adjacent depths in a well. A novel approach leveraging an attention-based gated recurrent unit (AGRU) model is introduced in this paper to address these challenges. The AGRU model excels by exploiting the sequential nature of well-log data and capturing long-range dependencies through an attention mechanism. This model enables a flexible and context-dependent weighting of different parts of the sequence, enhancing the discernment of key features for classification. The proposed method was validated on two publicly available datasets. Results demonstrate a considerably improvement over traditional methods. Specifically, the AGRU model achieved superior performance metrics considering precision, recall, and F1-score.

关键词： attention mechanism facies classification GRU MLP(multilayer perceptron)

来源：评论

学校读者我要写书评

暂无评论

Reseed Skipping of Linear Congruential Generator for Multi-level Image Steganography Security of Financial Data

引用

SN Computer science 2023年第2期4卷 124页

作者： Danso, Juliana Mantebea Missah, Yaw Marfo Gyamfi, Enoch Opanin Dankwa, Stephen Kwabena, Sarpong Department of Computer Science Kwame Nkrumah University of Science and Technology (KNUST) Kumasi Ghana School of Computer Science and Engineering University of Electronic Science and Technology of China Chengdu China School of Information and Software Engineering University of Electronic Science and Technology of China Chengdu China Department of Cyber Security and Computer Engineering Technology School of Computing and Information Sciences C.K. Tedam University of Technology and Applied Sciences Upper East Region Navrongo Ghana School of Automation Engineering University of Electronic Science and Technology of China Chengdu China

This paper proposed a multi-level image steganography model that integrates with image and plaintext encryption schemes. The model starts by partitioning the cover-image pixel positions into two regions of respective purposes, one is reserved to hold the data, and through the implementation of the dynamic difference expansion principle, the other sloughs some parts to the reserved region in responsive to the size of the data to embed. Continuously reseeding and initializing the parameter values of a Linear Congruential Generator (LCG), generate a set of random pixel positions as members of the reserved region. Before data embedding, the region reserved to hold the data as well as the data bits to embed, are then encrypted using AES with respective keys. Encryption keys are randomly generated using a Cryptographically Secure Pseudo-Random Number Generator (CSPRNG), the Fortuna algorithm. Multiplex security nature of using a randomization generator to reserve image region for encryption and encrypting plaintext data before performing steganography still ensures stability in computational complexities better than a logarithmic O(n log n). A visual inspection by evaluators who made 3000 choices to correctly differentiate stego images from its cover-images shows that only 47 choices were correct, 1884 choices were wrong, while 1069 choices were uncertain. An experiment shows an average Embedding Rates (ERs) of 0.00109 bpp and an average PSNR of 72. This concludes, as our integrated steganography and image encryption which implements the dynamic difference expansion principle, outputs encrypted stego mages that can deceive the naked human eyes into identifying them as rather cover-images, its embedding rate is faster (i.e. ER < 0.1), suitably good, and ensures better imperceptibility of cover-image alterations. When comparing these experimental results with existing methods, our proposed model shows significant competitiveness. We even show real-life scenarios on how this

关键词： AES encryption scheme Dynamic difference expansion principle Linear congruential generator Pseudo-random number generator Reserving room before encryption Steganography

来源：评论

学校读者我要写书评

暂无评论

The Impact of CLIP Encoders and CNN Architectures on Model Efficiency: A Case Study on Hate Speech Detection 32

The Impact of CLIP Encoders and CNN Architectures on Model E...

引用

32nd Irish Conference on Artificial Intelligence and Cognitive science, AICS 2024

作者： Kälin, Christof Rushe, Ellen Kull, Stefan McCarren, Andrew School of Computing Dublin City University Dublin 9 Ireland Lucerne School of Computer Science and Information Technology Lucerne University of Applied Sciences and Arts Rotkreuz Switzerland

In this paper, the impact of model architecture, model size and overall efficiency of deep vision-language models is explored, focusing on the trade-off between performance and resource utilisation. Specifically, the effectiveness of Contrastive Language-Image Pre-training (CLIP) encoders combined with Convolutional Neural Networks (CNNs) are evaluated for this task. To this end, a study is performed using the Facebook Hateful Memes Dataset (HMD) to train and evaluate the Hate-CLIPper architecture and its variations, alongside smaller scale extentions using convolutional layers. Though the evaluation demonstrates that Hate-CLIPper shows the strongest performance, the reduced versions of Hate-CLIPper’s cross-fusion mechanism see a large decrease in parameters without a comparably large decrease in performance. This suggests that the addition of parameters to these models may ultimately lead to diminishing returns in terms of performance. We also show that downscaling a smaller version of HateCLIPper leads to a larger reduction in performance than its larger-scale counterparts, suggesting a non-linear relationship between the number of parameters and performance gains. The question of overparameterisation in Hate-CLIPper is therefore raised, highlighting the importance of balancing model complexity with training efficiency. Through this case study, this research contributes to the development of more efficient methods for automatic hateful meme detection which, in extension, can improve content moderation practices and reduce the spread of online hate speech. © 2024 Copyright for this paper by its authors.

关键词： Convolutional neural networks

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：