检索结果-内蒙古大学图书馆

An overview on visualization of ontology alignment and ontology entity 5th

学校读者我要写书评

暂无评论

An overview on visualization of ontology alignment and ontol...

5th Euro-China Conference on Intelligent data Analysis and Applications, ECC 2018

作者： Chen, Jie Xue, Xingsi Huang, Lili Ren, Aihong College of Information Science and Engineering Fujian University of Technology FuzhouFujian350118 China Intelligent Information Processing Research Center Fujian University of Technology FuzhouFujian350118 China Fujian Provincial Key Laboratory of Big Data Mining and Applications FuzhouFujian350118 China Fujian Key Lab for Automotive Electronics and Electric Drive Fujian University of Technology FuzhouFujian350118 China College of Humanities and Law Fujian Agriculture and Forestry University FuzhouFujian350002 China School of Mathematics and Information Science Baoji University of Arts and Sciences BaojiShaanxi721013 China

ISBN: (纸本)9783030037659

Visualization of ontology alignment and ontology entity is becoming a method to help Solve the problem of semantic heterogeneity. This paper first introduces the basic concepts of ontology and ontology matching, and then illustrates the importance of ontology visualization technique. The existing partial visualization tools are discussed respectively in two aspects of visualization of ontology alignment and visualization entity on ontology. Finally, four researching directions on ontology visualization technique are pointed out for the future work. © Springer Nature Switzerland AG 2019.

关键词： Ontology

A Dynamics Theory of Implicit Regularization in Deep Low-Rank Matrix Factorization

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Cao, Jian Qian, Chen Huang, Yihui Chen, Dicheng Gao, Yuncheng Dong, Jiyang Guo, Di Qu, Xiaobo Department of Electronic Science Biomedical Intelligent Cloud R&D Center Fujian Provincial Key Laboratory of Plasma and Magnetic Resonance Xiamen University Xiamen361005 China School of Computer and Information Engineering Fujian Engineering Research Center for Medical Data Mining and Application Xiamen University of Technology Xiamen361024 China

Implicit regularization is an important way to interpret neural networks. Recent theory starts to explain implicit regularization with the model of deep matrix factorization (DMF) and analyze the trajectory of discrete gradient dynamics in the optimization process. These discrete gradient dynamics are relatively small but not infinitesimal, thus fitting well with the practical implementation of neural networks. Currently, discrete gradient dynamics analysis has been successfully applied to shallow networks but encounters the difficulty of complex computation for deep networks. In this work, we introduce another discrete gradient dynamics approach to explain implicit regularization, i.e. landscape analysis. It mainly focuses on gradient regions, such as saddle points and local minima. We theoretically establish the connection between saddle point escaping (SPE) stages and the matrix rank in DMF. We prove that, for a rank-R matrix reconstruction, DMF will converge to a second-order critical point after R stages of SPE. This conclusion is further experimentally verified on a low-rank matrix reconstruction problem. This work provides a new theory to analyze implicit regularization in deep learning. Copyright © 2022, The Authors. All rights reserved.

关键词： Deep learning

Studies and implementation of the trusted process mechanism in a secure operating system

学校读者我要写书评

暂无评论

Qinghua Daxue Xuebao/Journal of Tsinghua University 2010年第SUPPL. 1期50卷 1547-1553页

作者： Zhang, Chongbin Li, Fengjuan Liang, Bin China Information Technology Security Evaluation Center Beijing 100085 China Key Laboratory of Data Engineering and Knowledge Engineering of Ministry of Education School of Information Renming University of China Beijing 100872 China

The trusted process mechanism is an important part of the operating system security mechanism, but there is no uniform definition of the trusted process and there are some limitations in understanding its fundamental properties. In this paper, the trustworthiness of a trusted process is discussed in terms of privilege, data-operated integrity, functional and logic correctness, self-integrity, availability and trusted interactions. A trusted process definition is then given which summarizes the fundamental properties of a trusted process as a theoretical foundation for researching and enforcing the trusted process mechanism. A prototype of a trusted process mechanism is implemented in a secure operating system based on Linux, with the trustworthiness of the trusted process assured in many ways to improve and extende the original trust mechanisms in Linux.

关键词： Linux

QGEval: Benchmarking Multi-dimensional Evaluation for Question Generation

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Fu, Weiping Wei, Bifan Hu, Jianxiang Cai, Zhongmin Liu, Jun School of Computer Science and Technology Xi’an Jiaotong University Xi’an China School of Continuing Education Xi’an Jiaotong University Xi’an China MOE KLINNS Lab School of Automation Science and Engineering Xi’an Jiaotong University Xi’an China Shaanxi Province Key Laboratory of Big Data Knowledge Engineering Xi’an Jiaotong University Xi’an China

Automatically generated questions often suffer from problems such as unclear expression or factual inaccuracies, requiring a reliable and comprehensive evaluation of their quality. Human evaluation is widely used in the field of question generation (QG) and serves as the gold standard for automatic metrics. However, there is a lack of unified human evaluation criteria, which hampers consistent and reliable evaluations of both QG models and automatic metrics. To address this, we propose QGEval, a multi-dimensional Evaluation benchmark for Question Generation, which evaluates both generated questions and existing automatic metrics across 7 dimensions: fluency, clarity, conciseness, relevance, consistency, answerability, and answer consistency. We demonstrate the appropriateness of these dimensions by examining their correlations and distinctions. Through consistent evaluations of QG models and automatic metrics with QGEval, we find that 1) most QG models perform unsatisfactorily in terms of answerability and answer consistency, and 2) existing metrics fail to align well with human judgments when evaluating generated questions across the 7 dimensions. We expect this work to foster the development of both QG technologies and their evaluation. Copyright © 2024, The Authors. All rights reserved.

关键词： Benchmarking

A Dynamics Theory of Implicit Regularization in Deep Low-Rank Matrix Factorization

学校读者我要写书评

暂无评论

SSRN

SSRN 2023年

Implicit regularization induced by gradient optimization is an important way to understand the generalization in neural networks. Recent theory explains implicit regularization over the model of deep matrix factorization (DMF) and analyzes the trajectory of discrete gradient dynamics in the optimization process. These discrete gradient dynamics can mathematically characterize the practical learning rate of adaptive gradient optimization such as RMSProp. Discrete gradient dynamics analysis has been successfully applied to shallow networks but encounters the difficulty of complex computation for deep networks. In this work, we introduce another discrete gradient dynamics approach to explain implicit regularization of RMSProp, i.e. landscape analysis. It mainly focuses on gradient regions like saddle points and local minima. We investigate that increasing learning rates benefit saddle point escaping (SPE) stages. In elucidating implicit regularization through the convergence of RMSProp, we prove that for a rank-R matrix reconstruction, DMF will converge to a second-order critical point after R stages of SPE. This conclusion is further experimentally verified on a low-rank matrix reconstruction problem. © 2023, The Authors. All rights reserved.

关键词： Deep learning

Prompt Tuning Pushes Farther, Contrastive Learning Pulls Closer: A Two-Stage Approach to Mitigate Social Biases

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Li, Yingji Du, Mengnan Wang, Xin Wang, Ying College of Computer Science and Technology Jilin University Changchun China Department of Data Science New Jersey Institute of Technology Newark United States School of Artificial Intelligence Jilin University Changchun China Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education Jilin University Changchun China

As the representation capability of Pre-trained Language Models (PLMs) improve, there is growing concern that they will inherit social biases from unprocessed corpora. Most previous debiasing techniques used Counterfactual data Augmentation (CDA) to balance the training corpus. However, CDA slightly modifies the original corpus, limiting the representation distance between different demographic groups to a narrow range. As a result, the debiasing model easily fits the differences between counterfactual pairs, which affects its debiasing performance with limited text resources. In this paper, we propose an adversarial training-inspired two-stage debiasing model using Contrastive learning with Continuous Prompt Augmentation (named CCPA) to mitigate social biases in PLMs’ encoding. In the first stage, we propose a data augmentation method based on continuous prompt tuning to push farther the representation distance between sample pairs along different demographic groups. In the second stage, we utilize contrastive learning to pull closer the representation distance between the augmented sample pairs and then fine-tune PLMs’ parameters to get debiased encoding. Our approach guides the model to achieve stronger debiasing performance by adding difficulty to the training process. Extensive experiments show that CCPA outperforms baselines in terms of debiasing performance. Meanwhile, experimental results on the GLUE benchmark show that CCPA retains the language modeling capability of PLMs. Copyright © 2023, The Authors. All rights reserved.

关键词： Encoding (symbols)

Automatically Labeling Aging Scenarios with a Machine Learning Approach 1

学校读者我要写书评

暂无评论

24th International Conference on Human-Computer Interaction, HCII 2022

作者： An, Ning Xu, Yang Gao, Qinglin Zhu, Wenjie Wu, Aoran Chen, Honglin School of Computer Science and Information Engineering Hefei University of Technology Hefei China Key Laboratory of Knowledge Engineering with Big Data of Ministry of Education Hefei University of Technology Hefei China National Smart Eldercare International S&T Cooperation Base Hefei University of Technology Hefei China Intelligent Interconnected Systems Laboratory of Anhui Province Hefei University of Technology Hefei China Shanghai Tianyu Senior Living Service Co. Ltd. Shanghai China School of Basic Courses Bengbu Medical College Bengbu China Management and Business Department Skidmore College Saratoga SpringsNY United States Department of Social Sciences University of Eastern Finland Kuopio70150 Finland

ISBN: (数字)9783031179020

ISBN: (纸本)9783031179013

Older adults have diversified needs often associated with particular aging scenarios. People started to use aging scenarios to provide better Smart Eldercare services and develop innovative solutions. The problem is how to manage these scenarios effectively. To our best knowledge, this study is the first to develop a model to provide a structured framework of aging scenarios for research and teaching of eldercare services. Labeling aging scenarios can facilitate their collection, classification, and consolidation within this model. This study uses the automatic labeling approach to manage and utilize aging scenarios. Under each class, there are labels with different numbers and smaller granularity to reflect the requirements in each scenario case. Since a scenario case often involves more than one label, properly labeling it becomes a multi-label text classification problem. We extend the multi-label text classification model LSAN for labeling aging scenario cases. For evaluation purposes, we collected 938 scenario cases as the dataset. Experimental results show that our proposed method can achieve an average accuracy of 61.66%, better than other classical methods. © 2022, Springer Nature Switzerland AG.

关键词： Classification (of information)

Semimetal Contacts to Monolayer Semiconductor: Weak Metalization as an Effective Mechanism to Schottky Barrier Lowering

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Su, Tong Li, Yueyan Wang, Qianqian Zhao, Weiwei Cao, Liemao Ang, Yee Sin Sauvage Laboratory for Smart Materials School of Materials Science and Engineering Harbin Institute of Technology Shenzhen518055 China Shenzhen Key Laboratory of Flexible Printed Electronics Technology Harbin Institute of Technology Shenzhen518055 China Science Mathematics and Technology Singapore University of Technology and Design Singapore487372 Singapore School of Information Management Nanjing University Nanjing210023 China Jiangsu Key Laboratory of Data Engineering and Knowledge Service Nanjing210023 China College of Physics and Electronic Engineering Hengyang Normal University Hengyang421002 China

Recent experiment has uncovered semimetal bismuth (Bi) as an excellent electrical contact to monolayer MoS2 with ultralow contact resistance. The contact physics of the broader semimetal/monolayer-semiconductor family beyond Bi/MoS2, however, remains largely unexplored thus far. Here we perform a comprehensive first-principle density functional theory investigation on the electrical contact properties between six archetypal two-dimensional (2D) transition metal dichalcogenide (TMDC) semiconductors, i.e. MoS2, WS2, MoSe2, WSe2, MoTe2 and WTe2, and two representative types of semimetals, Bi and antimony (Sb). As Bi and Sb work functions energetically aligns well with the TMDC conduction band edge, Ohmic or nearly-Ohmic n-type contacts are prevalent. The interlayer distance of semimetal/TMDC contacts are significantly larger than that of the metal/TMDC counterparts, which results in only weak metalization of TMDC upon contact formation. Intriguingly, such weak metalization generates semimetal-induced gap states (MIGS) that extends below the conduction band minimum, thus offering an effective mechanism to reduce or eliminate the n-type Schottky barrier height (SBH) while still preserving the electronic structures of 2D TMDC. A modified Schottky-Mott rule that takes into account SMIGS, interface dipole potential, and Fermi level shifting is proposed, which provides an improved agreement with the DFT-simulated SBH. We further show that the tunneling-specific resistivity of Sb/TMDC contacts are generally lower than the Bi counterparts, thus indicating a better charge injection efficiency can be achieved through Sb contacts. Our findings reveal the promising potential of Bi and Sb as excellent companion electrode materials for advancing 2D semiconductor device technology. Copyright © 2022, The Authors. All rights reserved.

关键词： Molybdenum compounds

Interactive Ontology Matching Based on Evolutionary Algorithm

学校读者我要写书评

暂无评论

Interactive Ontology Matching Based on Evolutionary Algorith...

International Conference on Computational Intelligence and Security

作者： Xingsi Xue Junfeng Chen Aihong Ren College of Information Science and Engineering Intelligent Information Processing Research Center Fujian Key Lab for Automotive Electronics and Electric Drive Fujian Provincial Key Laboratory of Big Data Mining and Applications Fujian University of Technology Fuzhou China College of IOT Engineering Hohai University ChanZhou China School of Mathematics and Information Science Baoji University of Arts and Sciences Baoji China

ISBN: (数字)9781728160924

ISBN: (纸本)9781728160931

Since different ontologies are mostly developed independently, establishing meaningful links between their entities, so-called ontology matching, is critical to ensure their communication. Due to the complexity of the ontology matching problem, Evolutionary Algorithm (EA) can present a good methodology for determining ontology alignments. However, since none of the similarity measure can distinguish all the identical ontology entities in any context, ontology alignments generated by the automatic matching tools should be validated by the users to ensure their qualities. To improve the quality of the ontology alignment, in this work, a similarity measure is first proposed to calculate the similarity value of two ontology entities; then, an optimal model for ontology matching problem is constructed; after that, an EA-based automatic matcher is presented to solve the ontology matching problem, which can also adaptively determine the timing of getting user involved; and finally, the ontology concept hierarchy graph based reasoning approaches are proposed to tradeoff the user's workload and his work's effect. The experiment is conducted on the Interactive track provided by the Ontology Alignment Evaluation Initiative (OAEI), and the comparisons with OAEI's participants show the effectiveness of our proposal.

关键词： Ontologies Graph theory Pattern matching Evolutionary computation