检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Huang, Peixin Zhao, Xiang Hu, Minghao Tan, Zhen Xiao, Weidong National Key Laboratory of Information Systems Engineering National University of Defense Technology China Laboratory for Big Data and Decision National University of Defense Technology China Information Research Center of Military Science China

To understand a document with multiple events, event-event relation extraction (ERE) emerges as a crucial task, aiming to discern how natural events temporally or structurally associate with each other. To achieve this goal, our work addresses the problems of temporal event relation extraction (TRE) and subevent relation extraction (SRE). The latest methods for such problems have commonly built document-level event graphs for global reasoning across sentences. However, the edges between events are usually derived from external tools heuristically, which are not always reliable and may introduce noise. Moreover, they are not capable of preserving logical constraints among event relations, e.g., coreference constraint, symmetry constraint and conjunction constraint. These constraints guarantee coherence between different relation types, enabling the generation of a unified event evolution graph. In this work, we propose a novel method named LogicERE, which performs high-order event relation reasoning through modeling logic constraints. Specifically, different from conventional event graphs, we design a logic constraint induced graph (LCG) without any external tools. LCG involves event nodes where the interactions among them can model the coreference constraint, and event pairs nodes where the interactions among them can retain the symmetry constraint and conjunction constraint. Then we perform high-order reasoning on LCG with relational graph transformer to obtain enhanced event and event pair embeddings. Finally, we further incorporate logic constraint information via a joint logic learning module. Extensive experiments demonstrate the effectiveness of the proposed method with state-of-the-art performance on benchmark datasets. Copyright © 2024, The Authors. All rights reserved.

关键词： Constraint theory

来源：评论

学校读者我要写书评

暂无评论

A Brief Survey of Vector databases

A Brief Survey of Vector Databases

引用

International Conference on big data and Information Analytics (bigDIA)

作者： Xingrui Xie Han Liu Wenzhe Hou Hongbin Huang College of Systems Engineering National University of Defense Technology Changsha China Laboratory for Big Data and Decision National University of Defense Technology Changsha China

The explosive growth of massive high-dimensional data requires capabilities for data processing, storing, and analyzing. This brings significant challenges to traditional databases due to the poor ability to handle high-dimensional data and its original design for stand-alone machines. Fortunately, vector databases have provided a practical solution for the management and analysis of high-dimensional data. Especially, they retrieve results related to the query efficiently after encoding various forms of data (e.g., text, image, and video) into vectors. The purpose of this paper is to offer insight into vector databases by presenting a brief survey. Firstly, the workflow of vector databases including indexing and querying, is detailed along with a specific case. Subsequently, we elaborate on the related methods applied in vector databases, which are the core techniques to enhance search efficiency and reduce computational overhead, particularly similarity search algorithms and similarity metrics. Further, we introduce widely used vector database products (e.g., Pinecone, Chroma, and Milvus) and compare them from multiple factors that should be taken into consideration. We also discuss potential avenues for future research in this domain. To conclude, this survey provides a comprehensive understanding of vector databases for retrieval from vast high-dimensional datasets.

关键词：

来源：评论

学校读者我要写书评

暂无评论

RuMEW-Rl: A Hybrid Framework for Sparse Knowledge Graph Explainable Reasoning

SSRN

引用

SSRN 2023年

作者： Zeng, Zefan Cheng, Qing Si, Yuehang Liu, Zhong Big Data and Decision Laboratory National University of Defense Technology No. 109 Deya Road Kaifu District Hunan Province Changsha City China

Knowledge Graph (KG) reasoning is an important technology for ensuring the accuracy and usefulness of KGs. However, due to the lack of information and truncated paths, accurate and explainable reasoning on sparse KGs is difficult. To address this challenge, we propose a hybrid reasoning framework called RuMER-RL. This framework includes three modules: rule mining (RM), embedding representation (ER), and reinforcement learning (RL). The ER and RM modules work together to improve the embedding models and the quality of rules, and generate additional triples to alleviate the sparsity of the KG. The RL module models KG reasoning as a Markov decision process and uses dynamic anticipation, action space expansion, and curiosity-driven strategies to provide more information for reasoning and reduce sparsity. We also reshape the reward function by adding embedding representation, rule matching, and curiosity rewards to guide the training and optimization of the policy network. Our experiments on six benchmark sparse KG datasets demonstrate that RuMER-RL outperforms state-of-the-art models in improving link prediction accuracy and interpretability. © 2023, The Authors. All rights reserved.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Rumer-Rl: A Hybrid Framework for Sparse Knowledge Graph Explainable Reasoning

SSRN

引用

SSRN 2023年

作者： Zeng, Zefan Cheng, Qing Si, Yuehang Liu, Zhong Big Data and Decision Laboratory National University of Defense Technology No. 109 Deya Road Kaifu District Hunan Province Changsha City China

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Research on Multi-UAV Path Planning and Modeling for Ship Search

Research on Multi-UAV Path Planning and Modeling for Ship Se...

引用

International Conference on big data and Information Analytics (bigDIA)

作者： Boyu Jia Zhimeng Li Chengming Zhang Yizheng Bao Xiang Lin Yutong Yuan Laboratory for Big Data and Decision National University of Defense Technology Changsha China College of Systems Engineering National University of Defense Technology Changsha China

A set of modeling method and optimization model for multi-UAV cooperative target searching at sea is proposed. First, a basic model is built according to the maneuvering rules of ships and drones. Then, on the basis of considering the load balance of each UAV, the historical discovery probability of sea area is used to update the target probability map information. Finally, the ant colony algorithm is used to optimize the search route of each UAV, considering both the energy supply demand of UAV and the maximum target discovery probability. The simulation results show that the proposed method has high search efficiency and can be effectively applied to the fast search task of Marine targets, which has important application value.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Causal Analysis of Bone Disease Risk Factors Based on Markov Boundary Discovery

Causal Analysis of Bone Disease Risk Factors Based on Markov...

引用

International Conference on big data and Information Analytics (bigDIA)

作者： Lihua Liu Haoran Wang Youdian Zhu Ningchao Ge Shengze Hu Laboratory for Big Data and Decision National University of Defense Technology Changsha China College of Systems Engineering National University of Defense Technology Changsha China

Bone diseases, affecting millions globally, necessitate a nuanced understanding of their underlying causal mechanisms for effective prevention and treatment. Traditional machine learning and deep learning methods, while powerful in identifying patterns and associations, often fall short in distinguishing correlation from causation. This paper addresses this gap by employing the Markov boundary discovery algorithm, a novel causal inference technique, to analyze risk factors associated with bone diseases. Utilizing a comprehensive dataset of patient information, including the occurrence of bone diseases and related factors, we identify the direct causes of bone disease presence, providing a clear and concise depiction of the causal relationships at play. Our results demonstrate a strong alignment with expert opinions, validating the efficacy of our approach and its potential to revolutionize bone disease research. By bridging the gap between data-driven insights and clinical expertise, this study contributes to the enhanced understanding of bone disease etiology, the development of targeted interventions, and the improvement of patient outcomes, marking a significant stride in the field of biomedical research.

关键词：

来源：评论

学校读者我要写书评

暂无评论

PD-Refiner: An Underlying Surface Inheritance Refiner with Adaptive Edge-Aware Supervision for Point Cloud Denoising 24

PD-Refiner: An Underlying Surface Inheritance Refiner with A...

引用

32nd ACM International Conference on Multimedia, MM 2024

作者： Zhang, Chengwei Zhang, Xueyi Yue, Xianghu Lao, Mingrui Jiang, Tao Wang, Jiawei Zhang, Fubo Chen, Longyong National Key Laboratory of Microwave Imaging Aerospace Information Research Institute Chinese Academy of Sciences Beijing China Laboratory for Big Data and Decision National University of Defense Technology Hunan Changsha China Department of Electrical and Computer and Engineering National University of Singapore Singapore Singapore National Key Laboratory of Information Systems Engineering National University of Defense Technology Hunan Changsha China School of Software Engineering Tongji University Shanghai China

ISBN: (纸本)9798400706868

Point clouds from real-world scenarios inevitably contain complex noise, significantly impairing the accuracy of downstream tasks. To tackle this challenge, cascading encoder-decoder architecture has become a conventional technical route to iterative denoise. However, circularly feeding the output of denoiser as its input again involves the re-extraction of underlying surface, leading to unstable denoising process and over-smoothed geometric details. To address these issues, we propose a novel denoising paradigm dubbed PD-Refiner that employs a single encoder to model the underlying surface. Then, we leverage several lightweight hierarchical Underlying Surface Inheritance Refiners (USIRs) to inherit and strengthen it, thereby avoiding the re-extraction from the intermediate point cloud. Furthermore, we design adaptive edge-aware supervision to improve the edge awareness of the USIRs, allowing for the adjustment of the denoising preferences from global structure to local details. The results demonstrate that our method not only achieves state-of-the-art performance in terms of denoising stability and efficacy, but also enhances edge clarity and point cloud uniformity. © 2024 ACM.

关键词： edge-aware supervision

来源：评论

学校读者我要写书评

暂无评论

MaxMin-L2-SVC-NCH: A Novel Approach for Support Vector Classifier Training and Parameter Selection

arXiv

引用

arXiv 2023年

作者： Luo, Linkai Yang, Qiaoling Peng, Hong Wang, Yiding Chen, Ziyang Department of Automation Xiamen University Xiamen361102 China Xiamen Key Laboratory of Big Data Intelligent Analysis and Decision-Making Xiamen361102 China

The selection of Gaussian kernel parameters plays an important role in the applications of support vector classification (SVC). A commonly used method is the k-fold cross validation with grid search (CV), which is extremely time-consuming because it needs to train a large number of SVC models. In this paper, a new approach is proposed to train SVC and optimize the selection of Gaussian kernel parameters. We first formulate the training and the parameter selection of SVC as a minimax optimization problem named as MaxMin-L2-SVC-NCH, in which the minimization problem is an optimization problem of finding the closest points between two normal convex hulls (L2-SVC-NCH) while the maximization problem is an optimization problem of finding the optimal Gaussian kernel parameters. A lower time complexity can be expected in MaxMin-L2-SVC-NCH because CV is not needed. We then propose a projected gradient algorithm (PGA) for the training of L2-SVC-NCH. It is revealed that the famous sequential minimal optimization (SMO) algorithm is a special case of the PGA. Thus, the PGA can provide more flexibility than the SMO. Furthermore, the solution of the maximization problem is done by a gradient ascent algorithm with dynamic learning rate. The comparative experiments between MaxMin-L2-SVC-NCH and the previous best approaches on public datasets show that MaxMin-L2-SVC-NCH greatly reduces the number of models to be trained while maintaining competitive test accuracy. These findings indicate that MaxMin-L2-SVC-NCH is a better choice for SVC tasks. © 2023, CC BY-NC-ND.

关键词： Convex optimization

来源：评论

学校读者我要写书评

暂无评论

EventSum: A Large-Scale Event-Centric Summarization dataset for Chinese Multi-News Documents

arXiv

引用

arXiv 2024年

作者： Zhu, Mengna Zeng, Kaisheng Wang, Mao Xiao, Kaiming Hou, Lei Huang, Hongbin Li, Juanzi Laboratory for Big Data and Decision National University of Defense Technology China Department of Computer Science and Technology Tsinghua University China College of Information and Communication National University of Defense Technology China

In real life, many dynamic events, such as major disasters and large-scale sports events, evolve continuously over time. Obtaining an overview of these events can help people quickly understand the situation and respond more effectively. This is challenging because the key information of the event is often scattered across multiple documents, involving complex event knowledge understanding and reasoning, which is under-explored in previous work. Therefore, we proposed the Event-Centric Multi-Document Summarization (ECS) task, which aims to generate concise and comprehensive summaries of a given event based on multiple related news documents. Based on this, we constructed the EventSum dataset, which was constructed using Baidu Baike entries and underwent extensive human annotation, to facilitate relevant research. It is the first large-scale Chinese multi-document summarization dataset, containing 5,100 events and a total of 57,984 news documents, with an average of 11.4 input news documents and 13,471 characters per event. To ensure data quality and mitigate potential data leakage, we adopted a multi-stage annotation approach for manually labeling the test set. Given the complexity of event-related information, existing metrics struggle to comprehensively assess the quality of generated summaries. We designed specific metrics including Event Recall, Argument Recall, Causal Recall, and Temporal Recall along with corresponding calculation methods for evaluation. We conducted comprehensive experiments on EventSum to evaluate the performance of advanced long-context Large Language Models (LLMs) on this task. Our experimental results indicate that: 1) The event-centric multi-document summarization task remains challenging for existing long-context LLMs;2) The recall metrics we designed are crucial for evaluating the comprehensiveness of the summary information. Our code and data can be obtained from https://***/Mzzzhu/EventSum. Copyright © 2024, The Authors. All r

关键词： Information leakage

来源：评论

学校读者我要写书评

暂无评论

Discriminative locality-constrained sparse representation for robust face recognition

Discriminative locality-constrained sparse representation fo...

引用

2020 International Symposium on Automation, Mechanical and Design Engineering, SAMDE 2020

作者： Huang, Meng Shao, Guifang Wang, Keqi Liu, Tundong Lu, Hao Department of Automation Xiamen University Xiamen Fujian China Xiamen Key Laboratory of Big Data Intelligent Analysis and Decision-making Fujian China

In this paper, a new joint sparse representation method called discriminative locality-constrained sparse representation (DLSR) is proposed for robust face recognition. DLSR incorporates locality and label information of training samples into the framework of sparse representation. Locality information can distinguish dissimilarity between samples and plays an important role in image classification. Compared with the existing methods, DLSR contains more discriminative information of samples and can obtain more discriminative recognition results. Due to the use of l2-norm regularization, DLSR can obtain a closed-form solution. This makes it computationally very efficient. Experimental results based on the benchmark face databases ORL have shown that DLSR can achieve more promising performance than some state-of-the-art methods. © Published under licence by IOP Publishing Ltd.

关键词： Face recognition

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：