检索结果-内蒙古大学图书馆

DTGCN: a method combining dependency tree and graph convolutional networks for Chinese long-interval named entity relationship extraction

引用

Journal of Ambient Intelligence and Humanized Computing 2023年第10期14卷 13361-13373页

作者： Li, Taoyuan Ma, Liangli Qin, Jiwei Ren, Wei College of Electronic Engineering Naval University of Engineering Wuhan China School of Computer Science China University of Geosciences Wuhan China Key Laboratory of Network Assessment Technology CAS Institute of Information Engineering Chinese Academy of Sciences Beijing100093 China Henan Key Laboratory of Network Cryptography Technology Zhengzhou China

The extraction of relationships between military entities and descriptive entities is a key task for automated construction of military knowledge graphs. This category of text unstructured imposed problems such as unfixed entity length, possibly overlong intervals between entities, and excessive pronouns. Many studies rely on traditional pattern matching and statistical learning methods. Thanks to the expansion of data volume, deep learning methods are generally used to address similar problems. However, the traditional single neural network model lacks the ability to extract the relationship information of long-interval entities and cannot tackle the above problems well. To solve these problems, a new named entity relationship extraction model called DTGCN is proposed combining dependency tree and GCN (Graph Convolutional networks). By comparing with traditional models, the experimental results demonstrate that the method proposed in this paper can enhance F1-value by 2.28–11.11% and can provide support for the extraction of Chinese long-interval relationships. © 2022, The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature.

关键词： Knowledge graph

来源：评论

学校读者我要写书评

暂无评论

Target extraction through strong scattering disturbance using characteristic-enhanced pseudo-thermal ghost imaging

引用

Chinese Optics Letters 2024年第12期22卷 38-44页

作者： Xuanpengfan Zou Xianwei Huang Wei Tan Liyu Zhou Xiaohui Zhu Qin Fu Xiaoqian Liang Suqin Nan Yanfeng Bai Xiquan Fu College of Computer Science and Electronic Engineering Hunan UniversityChangsha 410082China Hunan Police Academy Changsha 410138China Hunan Provincial Key Laboratory of Network Investigational Technology Hunan Police AcademyChangsha 410138China School of Computer Science Hunan University of Technology and BusinessChangsha 410205China

It is difficult to extract targets under strong environmental disturbance in *** imaging(GI)is an innovative antiinterference imaging *** this paper,we propose a scheme for target extraction based on characteristicenhanced pseudo-thermal *** traditional GI which relies on training the detected signals or imaging results,our scheme trains the illuminating light fields using a deep learning network to enhance the target’s characteristic *** simulation and experimental results prove that our imaging scheme is sufficient to perform single-and multiple-target extraction at low *** addition,the effect of a strong scattering environment is discussed,and the results show that the scattering disturbance hardly affects the target extraction *** proposed scheme presents the potential application in target extraction through scattering media.

关键词： target extraction ghost imaging characteristic enhancement strong scattering environment

来源：评论

学校读者我要写书评

暂无评论

Multi-Label Open Set Recognition 38

Multi-Label Open Set Recognition

引用

38th Conference on Neural Information Processing Systems, NeurIPS 2024

作者： Wang, Yi-Bo Hang, Jun-Yi Zhang, Min-Ling School of Computer Science and Engineering Southeast University Nanjing210096 China Key Laboratory of Computer Network and Information Integration Southeast University Ministry of Education China

In multi-label learning, each training instance is associated with multiple labels simultaneously. Traditional multi-label learning studies primarily focus on closed set scenario, i.e. the class label set of test data is identical to those used in training phase. Nevertheless, in numerous real-world scenarios, the environment is open and dynamic where unknown labels may emerge gradually during testing. In this paper, the problem of multi-label open set recognition (MLOSR) is investigated, which poses significant challenges in classifying and recognizing instances with unknown labels in multi-label setting. To enable open set multi-label prediction, a novel approach named SLAN is proposed by leveraging sub-labeling information enriched by structural information in the feature space. Accordingly, unknown labels are recognized by differentiating the sub-labeling information from holistic supervision. Experimental results on various datasets validate the effectiveness of the proposed approach in dealing with the MLOSR problem. © 2024 Neural information processing systems foundation. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Binary Decomposition: A Problem Transformation Perspective for Open-Set Semi-Supervised Learning 41

Binary Decomposition: A Problem Transformation Perspective f...

引用

41st International Conference on Machine Learning, ICML 2024

作者： Hang, Jun-Yi Zhang, Min-Ling School of Computer Science and Engineering Southeast University Nanjing210096 China Key Laboratory of Computer Network and Information Integration Southeast University Ministry of Education China

Semi-supervised learning (SSL) is a classical machine learning paradigm dealing with labeled and unlabeled data. However, it often suffers performance degradation in real-world open-set scenarios, where unlabeled data contains outliers from novel categories that do not appear in labeled data. Existing studies commonly tackle this challenging open-set SSL problem with detect-and-filter strategy, which attempts to purify unlabeled data by detecting and filtering outliers. In this paper, we propose a novel binary decomposition strategy, which refrains from error-prone procedure of outlier detection by directly transforming the original open-set SSL problem into a number of standard binary SSL problems. Accordingly, a concise yet effective approach named BDMatch is presented. BDMatch confronts two attendant issues brought by binary decomposition, i.e. class-imbalance and representation-compromise, with adaptive logit adjustment and label-specific feature learning respectively. Comprehensive experiments on diversified benchmarks clearly validate the superiority of BDMatch as well as the effectiveness of our binary decomposition strategy. Copyright 2024 by the author(s)

关键词： Self-supervised learning

来源：评论

学校读者我要写书评

暂无评论

SEAVER: Attention Reallocation for Mitigating Distractions in Language Models for Conditional Semantic Textual Similarity Measurement

SEAVER: Attention Reallocation for Mitigating Distractions i...

引用

2024 Conference on Empirical Methods in Natural Language Processing, EMNLP 2024

作者： Li, Baixuan Fan, Yunlong Gao, Zhiqiang School of Computer Science and Engineering Southeast University Nanjing211189 China Key Laboratory of Computer Network and Information Integration Southeast University Ministry of Education China

ISBN: (纸本)9798891761681

Conditional Semantic Textual Similarity (C-STS) introduces specific limiting conditions to the traditional Semantic Textual Similarity (STS) task, posing challenges for STS models. Language models employing cross-encoding demonstrate satisfactory performance in STS, yet their effectiveness significantly diminishes in C-STS. In this work, we argue that the failure is due to the fact that the redundant information in the text distracts language models from the required condition-relevant information. To alleviate this, we propose SElf-Augmentation Via SElf-Reweighting (SEAVER), which, based solely on models' internal attention and without the need for external auxiliary information, adaptively reallocates the model's attention weights by emphasizing the importance of condition-relevant tokens. On the C-STS-2023 test set, SEAVER consistently improves performance of all million-scale fine-tuning baseline models (up to around 3 points), and even surpasses performance of billion-scale few-shot prompted large language models (such as GPT-4). Our code is available at https://***/BaixuanLi/SEAVER. © 2024 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

A blockchain-based framework for data quality in edge-computing-enabled crowdsensing

引用

Frontiers of computer Science 2023年第4期17卷 127-139页

作者： Jian AN Siyuan WU Xiaolin GUI Xin HE Xuejun ZHANG School of Computer Science and Technology Shaanxi Province Key Laboratory of Computer NetworkXi’an Jiaotong UniversityXi’an 710049China School of Software Henan UniversityKaifeng 475001China School of Electronic and Information Engineering Lanzhou Jiaotong UniversityLanzhou 730070China

With the rapid development of mobile technology and smart devices,crowdsensing has shown its large potential to collect massive *** the limitation of calculation power,edge computing is introduced to release unnecessary data *** edge-computing-enabled crowdsensing,massive data is required to be preliminary processed by edge computing devices(ECDs).Compared with the traditional central platform,these ECDs are limited by their own capability so they may only obtain part of relative factors and they can’t process data *** involved in one task are required to cooperate to process the task *** privacy of participants is important in crowdsensing,so blockchain is used due to its decentralization and *** crowdsensing tasks,it is usually difficult to obtain the assessment criteria in advance so reinforcement learning is *** mentioned before,ECDs can’t process task data comprehensively and they are required to cooperate quality ***,a blockchain-based framework for data quality in edge-computing-enabled crowdsensing(BFEC)is proposed in this ***(Delegated Proof of Reputation),which is proposed in our previous work,is improved to be suitable in ***,the final result is calculated without revealing the privacy of *** on the open datasets Adult,Blog,and Wine Quality show that our new framework outperforms existing methods in executing sensing tasks.

关键词： crowdsensing edge computing devices blockchain quality assessment reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

DP-GenFL: a local differentially private federated learning system through generative data

引用

Science China(Information Sciences) 2023年第8期66卷 275-276页

作者： Jun LI Kang WEI Chuan MA Feng SHU School of Electronic and Optical Engineering Nanjing University of Science and Technology Zhejiang Lab Key Laboratory of Computer Network and Information Integration (Southeast University) Ministry of Education School of Information and Communication Engineering Hainan University

With the rapid development of the Internet of Things(Io T),the amount of data from intelligent devices is propagating at unprecedented scales. Meanwhile, machine learning(ML),which relies heavily on such data, is revolutionizing many aspects of our lives [1]. However, conventional centralized ML offers little scalability for efficiently processing this huge amount of data.

关键词： Learning systems

来源：评论

学校读者我要写书评

暂无评论

Prompting Large Language Models with Knowledge-Injection for Knowledge-Based Visual Question Answering

引用

Big Data Mining and Analytics 2024年第3期7卷 843-857页

作者： Zhongjian Hu Peng Yang Fengyuan Liu Yuan Meng Xingyu Liu School of Computer Science and Engineering Southeast University the Key Laboratory of Computer Network and Information Integration(Southeast University) Ministry of Education of the People’s Republic of ChinaNanjing 211189China Southeast University-Monash University Joint Graduate School(Suzhou) Southeast UniversitySuzhou 215125China

Previous works employ the Large Language Model(LLM)like GPT-3 for knowledge-based Visual Question Answering(VQA).We argue that the inferential capacity of LLM can be enhanced through knowledge *** methods that utilize knowledge graphs to enhance LLM have been explored in various tasks,they may have some limitations,such as the possibility of not being able to retrieve the required *** this paper,we introduce a novel framework for knowledge-based VQA titled“Prompting Large Language Models with Knowledge-Injection”(PLLMKI).We use vanilla VQA model to inspire the LLM and further enhance the LLM with knowledge *** earlier approaches,we adopt the LLM for knowledge enhancement instead of relying on knowledge ***,we leverage open LLMs,incurring no additional *** comparison to existing baselines,our approach exhibits the accuracy improvement of over 1.3 and 1.7 on two knowledge-based VQA datasets,namely OK-VQA and A-OKVQA,respectively.

关键词： visual question answering knowledge-based visual question answering large language model knowledge injection

来源：评论

学校读者我要写书评

暂无评论

Probabilistic Reliability via Subsystem Structures of Arrangement Graph networks

引用

IEEE Transactions on Reliability 2024年第1期73卷 279-289页

作者： Huang, Yanze Lin, Limei Xu, Li Hsieh, Sun-Yuan Fujian University of Technology Fujian Provincial Key Laboratory of Big Data Mining and Applications School of Computer Science and Mathematics Fuzhou350118 China Fujian Normal University College of Computer and Cyber Security Key Laboratory of Network Security and Cryptology Fuzhou350117 China National Cheng Kung University Department of Computer Science and Information Engineering Tainan701 Taiwan

With the rapid growth of the number of processors in a multiprocessor system, faulty processors occur in it with a probability that rises quickly. The probability of a subsystem with an appropriate size being fault-free in a definite time interval is a significant and practical measure of the reliability for a multiprocessor system, which characterizes the functionality of a multiprocessor system well. Motivated by the study of subgraph reliability, as well as the attractive structure and fault tolerance properties of (n, k)-arrangement graph A n, k, we focus on the subgraph reliability for A n, k under the probabilistic fault model in this article. First, we investigate intersections of no more than four subgraphs in A n, k, and classify all the intersecting modes. Second, we focus on the probability P(q, A n, k n-1, k-1) with which at least one (n-1, k-1)-subarrangement graph is fault-free in A n, k, when given a uniform probability q with which a single vertex is fault-free, and we establish the P(q, A n, kn-1, k-1) by adopting the principle of inclusion-exclusion under the probabilistic fault model. Finally, we study the probabilistic fault model involving a nonuniform probability with which a single vertex is fault-free, and we prove that the P(q, A n, kn-1, k-1) under both models is very close to the asymptotic value by both theoretical arguments and experimental results. © 1963-2012 IEEE.

关键词： Fault tolerance

来源：评论

学校读者我要写书评

暂无评论

Textual Data De-Privatization Scheme Based on Generative Adversarial networks 24th

Textual Data De-Privatization Scheme Based on Generative Adv...

引用

24th International Conference on Algorithms and Architectures for Parallel Processing, ICA3PP 2024

作者： Du, Yanning Xu, Jinnan Zhang, Yaling Wang, Yichuan Wang, Zhoukai School of Computer Science and Engineering Xi’an University of Technology Xi’an China Shaanxi Key Laboratory for Network Computing and Security Technology Xi’an China

ISBN: (纸本)9789819615506

In many fields, such as healthcare, finance, and scientific research, data sharing and collaboration are critical to achieving better outcomes. However, the sharing of personal data often involves privacy risks, so privacy-preserving techniques are needed to ensure data security and privacy. The superior performance and flexibility of generative models in data representation have led to significant progress in the development of data privacy. This paper proposes a textual data de-privatization scheme based on generative adversarial networks that well combines generative adversarial networks with privacy protection. The generated de-privacy data retains the statistical properties of the original data and effectively removes sensitive information. Moreover, feature sorting and reshaping modules are introduced to enable the generator to better capture the relationships between features, thus improving the quality of synthetic data. In this paper, the utility of synthetic data is evaluated from three aspects, including similarity assessment, privacy assessment, and model utility assessment. Experimental results show that this method achieves a good trade-off in terms of textual data privacy protection and data quality maintenance. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Generative adversarial 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：