检索结果-内蒙古大学图书馆

Unsupervised Statistical Text Simplification

IEEE Transactions on knowledge and data engineering 2021年第4期33卷 1802-1806页

作者： Qiang, Jipeng Wu, Xindong Department of Computer Science Yangzhou University Yangzhou Jiangsu225127 China Key Laboratory of Knowledge Engineering with Big Data Hefei University of Technology Ministry of Education Hefei Anhui10084 China

Most recent approaches for Text Simplification (TS) have drawn on insights from machine translation to learn simplification rewrites from the monolingual parallel corpus of complex and simple sentences, yet their effectiveness strongly relies on large amounts of parallel sentences. However, there has been a serious problem haunting TS for decades, that is, the availab.lity of parallel TS corpora is scarce or not fit for the learning task. In this paper, we will focus on one especially useful and challenging problem of unsupervised TS without a single parallel sentence. To the best of our knowledge, we present the first unsupervised text simplification system based on phrase-based machine translation system, which leverages a careful initialization of phrase tables and language models. On the widely used WikiLarge and WikiSmall benchmarks, our system respectively obtains 39.08 and 25.12 SARI points, even outperforms some supervised baselines. © 1989-2012 IEEE.

关键词： Machine translation

来源：评论

学校读者我要写书评

暂无评论

Semi-supervised Multi-lab.l Learning with Missing lab.ls via Correlation Information

Semi-supervised Multi-Label Learning with Missing Labels via...

引用

International Joint Conference on Neural Networks (IJCNN)

作者： Zexian Xie Peipei Li Jinling Jiang Xindong Wu Key Laboratory of Knowledge Engineering with Big Data (the Ministry of Education of China) Hefei University of Technology School of Computer Science and Information Engineering Hefei University of Technology Hefei Anhui China Knowledge Engineering Research Center Zhejiang Lab Hangzhou Zhejiang China

In multi-lab.l learning, each instance is associated with a set of lab.ls simultaneously. Most existing studies assume that the set of lab.ls for each instance is complete. However, it is generally difficult to obtain all the relevant lab.ls of each instance, and only a partial or even empty set of relevant lab.ls is availab.e, which is called semi-supervised multi-lab.l learning with missing lab.ls. To tackle this problem, we propose a novel framework that considers lab.l correlations and instance correlations to recover the missing lab.ls and utilizes a large amount of unlab.led data simultaneously to improve the classification performance. Specifically, a new supplementary lab.l matrix is firstly obtained by learning the lab.l correlation. Secondly, considering each class lab.l may be decided by some specific characteristics of its own, a lab.l-specific data representation is hence learned for each class lab.l. Thirdly, instance correlations are utilized not only to recover the missing lab.ls, but also to propagate the supervision information from lab.led instances to unlab.led ones. In addition, a united objective function is designed to facilitate the above processing and an accelerated proximal gradient method is adopted to solve the optimization problem. Finally, extensive experimental results conducted on several benchmark datasets demonstrate the effectiveness of the proposed method compared to competing ones.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Hyperbolic Geometric Latent Diffusion Model for Graph Generation 41

Hyperbolic Geometric Latent Diffusion Model for Graph Genera...

引用

41st International Conference on Machine Learning, ICML 2024

作者： Fu, Xingcheng Gao, Yisen Wei, Yuecen Sun, Qingyun Peng, Hao Li, Jianxin Li, Xianxian Key Lab of Education Blockchain and Intelligent Technology Ministry of Education Guangxi Normal University Guilin China Institute of Artificial Intelligence Beihang University Beijing China School of Software Beihang University Beijing China Beijing Advanced Innovation Center for Big Data and Brain Computing School of Computer Science and Engineering Beihang University Beijing China

Diffusion models have made significant contributions to computer vision, sparking a growing interest in the community recently regarding the application of them to graph generation. Existing discrete graph diffusion models exhibit heightened computational complexity and diminished training efficiency. A preferable and natural way is to directly diffuse the graph within the latent space. However, due to the non-Euclidean structure of graphs is not isotropic in the latent space, the existing latent diffusion models effectively make it difficult to capture and preserve the topological information of graphs. To address the above challenges, we propose a novel geometrically latent diffusion framework HypDiff. Specifically, we first establish a geometrically latent space with interpretability measures based on hyperbolic geometry, to define anisotropic latent diffusion processes for graphs. Then, we propose a geometrically latent diffusion process that is constrained by both radial and angular geometric properties, thereby ensuring the preservation of the original topological properties in the generative graphs. Extensive experimental results demonstrate the superior effectiveness of HypDiff for graph generation with various topologies. Copyright 2024 by the author(s)

关键词： Graph theory

来源：评论

学校读者我要写书评

暂无评论

A Dual-Broadband Circularly Polarized Shared-Aperture Array Antenna for C-/K-Band Application 15

A Dual-Broadband Circularly Polarized Shared-Aperture Array ...

引用

15th International Conference on Microwave and Millimeter Wave Technology, ICMMT 2023

作者： Li, Zhengting Ding, Kang Wu, Yanjie Li, Yujian Guangdong University of Technology School of Physics and Optoelectronic Engineering Guangzhou510006 China Beijing Jiaotong University Institute of Lightwave Technology The Key Lab. of All Optical Network Advanced Telecommunication Network of Ministry of Education Beijing100044 China

ISBN: (纸本)9798350338874

This paper presents a dual broadband circularly polarized (CP) array antenna with shared aperture for C- and K-band application. First, the CP operation for C-band element is generated by four square ring patches which are fed by an unequal cross slot. Second, a CP magnetoelectric (ME) dipole antenna with one pair of horizontal patches connected is used as the main radiator for K-band. The coupling slot etched on the ground is modified as cross-shaped to enhance the CP bandwidth. Last, a C-band 2×2 array and K-band 4×4 array are interlaced together at a shared aperture. The simulated results show the proposed antenna exhibits a -10-dB impedance bandwidth of 16.5% and 3-dB AR bandwidth of 16.2% at C-band, while has a -10-dB impedance bandwidth of 52.4% and 3-dB AR bandwidth of 33.7% at K-band. © 2023 IEEE.

关键词： Bandwidth

来源：评论

学校读者我要写书评

暂无评论

A knowledge Graph Completion Model with Path-Specific Learning

A Knowledge Graph Completion Model with Path-Specific Learni...

引用

Medical Artificial Intelligence (MedAI), IEEE International Conference on

作者： Xiulin Zheng Zan Zhang Rui Li Xindong Wu Key Laboratory of Knowledge Engineering with Big Data (the Ministry of Education of China) and also with the School of Computer Science and Information Engineering Hefei University of Technology Hefei Anhui China Inspur Academy of Science and Technology Shandong China

ISBN: (数字)9798350377613

ISBN: (纸本)9798350377620

knowledge graphs (KGs) play an increasingly im-portant role in many knowledge-aware tasks. However, existing KGs are struggle with incompleteness, which motivates knowledge graph completion (KGC), that is, predicting the lost links between entities based on observed triples. Reasoning over relation paths in incomplete KGs is popular. Nonetheless, some significant issues are still remained to be addressed, such as path noise and ambiguity of inferred relation. To address these problems, we propose a novel path augmented _Reasoning model with avoidance of Path noise and Disambiguation of inferred relation in this paper, referred to as RPD. In this model, we calculate the sum of resource allocation for each relation path to measure its reliability to avoid the inference of path noise. To address the ambiguity of an inferred relation, we introduce position embedding to denote the relation position along the path when learning path representation. Extensive experiments conducted on benchmark datasets demonstrate the effectiveness of our proposal RPD model in the handling of KGC tasks compared to SOTAs.

关键词： Heavily-tailed distribution Noise knowledge graphs Benchmark testing Transformers Cognition Reliability Resource management Proposals Noise measurement

来源：评论

学校读者我要写书评

暂无评论

A machine learning based solver for pressure Poisson equations

引用

Theoretical & Applied Mechanics Letters 2022年第5期12卷 315-321页

作者： Ruilin Chen Xiaowei Jin Hui Li Key Lab of Smart Prevention and Mitigation of Civil Engineering Disasters of the Ministry of Industry and Information Technology Harbin Institute of TechnologyHarbin 150090China Key Lab of Structures Dynamic Behavior and Control of the Ministry of Education Harbin Institute of TechnologyHarbin 150090China Guangdong-Hong Kong-Macao Joint Laboratory for Data-Driven Fluid Mechanics and Engineering Applications Harbin Institute of Technology(Shenzhen)Shenzhen 518055China

When using the projection method(or fractional step method)to solve the incompressible Navier-Stokes equations,the projection step involves solving a large-scale pressure Poisson equation(PPE),which is computationally expensive and *** this study,a machine learning based method is proposed to solve the large-scale *** machine learning(ML)-block is used to completely or partially(if not sufficiently accurate)replace the traditional PPE iterative solver thus accelerating the solution of the incompressible Navier-Stokes *** ML-block is designed as a multi-scale graph neural network(GNN)framework,in which the original high-resolution graph corresponds to the discrete grids of the solution domain,graphs with the same resolution are connected by graph convolution operation,and graphs with different resolutions are connected by down/up prolongation *** well trained MLblock will act as a general-purpose PPE solver for a certain kind of flow *** proposed method is verified via solving two-dimensional Kolmogorov flows(Re=1000 and Re=5000)with different source *** the premise of achieving a specified high precision(ML-block partially replaces the traditional iterative solver),the ML-block provides a better initial iteration value for the traditional iterative solver,which greatly reduces the number of iterations of the traditional iterative solver and speeds up the solution of the *** experiments show that the ML-block has great advantages in accelerating the solving of the Navier-Stokes equations while ensuring high accuracy.

关键词： Pressure Poisson equation Machine learning Projection method Multi-scale GNN

来源：评论

学校读者我要写书评

暂无评论

Prediction and analysis of uneven settlement of urban bridges and surrounding ground surface by combining GA-BP algorithm 4

Prediction and analysis of uneven settlement of urban bridge...

引用

4th International Conference on Geology, Mapping, and Remote Sensing, ICGMRS 2023

作者： Yuan, Tianyuge Liu, Xianglei Zhao, Yan Key Lab. for Urban Geomatics of National Administration of Surveying Mapping and Geoinformation Engineering Research Centre of Representative Building and Architectural Database Ministry of Education Beijing University of Civil Engineering and Architecture Beijing100044 China Shandong Provincial Land Survey and Mapping Institute No.9 East Alexandra Road Shandong Province Shandong Jinan250013 China

ISBN: (纸本)9781510672741

The aging of bridges, traffic congestion, and vehicle overloading have inevitably aggravated the damage of urban bridges in recent years, and it is extremely important to predict and analyze the settlement of urban bridges to monitor their safety conditions. The PS-InSAR (Permanent Scatterer Synthetic Aperture Radar) technique compensates for the drawbacks of the traditional InSAR technique such as atmospheric phase delay, and thus can obtain more accurate settlement information, which has unique advantages in long-term slow accumulation monitoring of surface deformation, and is especially suitable for this experiment to monitor and analyze the uneven settlement of urban bridges. In this paper, we obtain the uneven settlement of urban bridges based on PS-InSAR technique, and combine genetic algorithm and neural network algorithm (GA-BP) to achieve the prediction and analysis of uneven settlement of urban bridges. The method is also applied to the simulation experiment and analysis of uneven settlement prediction of Suzhou Bridge and the surrounding ground surface in Beijing. The experimental results show that the root mean squared error (RMSE, Root Mean Squared Error) of applying the GA-BP algorithm to predict the uneven settlement of urban bridges and the surrounding ground surface is 0.57500 mm, which has a good accuracy and proves that the method can effectively predict the uneven settlement of urban bridges and the surrounding ground surface, and with the increase of the number of experimental data. The best iteration the fewer the number of iterations, proving that its prediction performance will be better with the growth of the number of acquired data. © 2024 COPYRIGHT SPIE. Downloading of the abstract is permitted for personal use only.

关键词： Synthetic aperture radar

来源：评论

学校读者我要写书评

暂无评论

State Estimation for Discrete-Time Semi-Markovian Jump Piecewise-Affine Systems with Complex Semi-Markovian Kernel 63

State Estimation for Discrete-Time Semi-Markovian Jump Piece...

引用

63rd IEEE Conference on Decision and Control, CDC 2024

作者： Tang, Qi Liu, Tao Sun, Xi-Ming University of Hong Kong Department of Electrical and Electronic Engineering Hong Kong Shenzhen Institute of Research and Innovation The University of Hong Kong Hong Kong Dalian University of Technology Key Lab. of Intelligent Control and Optimization for Industrial Equipment of Ministry of Education Dalian116024 China Dalian University of Technology School of Control Science and Engineering Dalian116024 China

ISBN: (纸本)9798350316339

This paper addresses state estimation for discretetime semi-Markovian jump piecewise-affine (PWA) systems. To handle uncertainties caused by unknown disturbances, we propose an analysis method that considers all transfer paths between different regions within the same mode. We then examine the mean-square exponential stability and L∞ performance of the error dynamic system by constructing Lyapunov functions that depend on mode, region, and sojourn time. The related criteria are derived using ellipsoidal outer approximation. Based on these criteria, we design L∞ observers. Finally, we demonstrate the applicability of our method through a numerical example. © 2024 IEEE.

关键词： Lyapunov functions

来源：评论

学校读者我要写书评

暂无评论

Preparation and Characterization of Cpcm for Heating Accumulator

SSRN

引用

SSRN 2024年

作者： Zhou, Wenhe Cao, Hailan Zhao, Yun Zhang, Wenxiang Shen, Wei School of Environmental and Municipal Engineering Lanzhou Jiaotong University Lanzhou730070 China Key Lab. of Railway Vehicle Thermal Engineering Ministry of Education Lanzhou730070 China

In order to enhance the efficiency of air source heat pumps, the introduction of a heating accumulator is recommended. To address this application gap, 10 kinds of composite phase change materials (CPCM) suitable for this accumulator are prepared using the vacuum adsorption method and characterized. These CPCM consist of lauric acid (LA) as the phase change material and expanded graphite (EG) as the skeleton matrix. The results show that LA is effectively encapsulated, its maximum content in CPCM is 90% and its stability is satisfied. When the mass ratio of LA:EG is 8:2, the phase transition temperature of CPCM3 is 38.77-43.34°C, the latent heat is 164.34-168.28kJ/kg, and the thermal conductivity is 8.15-8.33 W/ (m• K). © 2024, The Authors. All rights reserved.

关键词： Phase change materials

来源：评论

学校读者我要写书评

暂无评论

Application Analysis of the Heat-Storage Electric Heating Floor System Powered by Pv System and Power Grid

SSRN

引用

SSRN 2024年

作者： Zhou, Wenhe Zhang, Wenxiang Shen, Wei Cao, Hailan Zhao, Yun School of Environmental and Municipal Engineering Lanzhou Jiaotong University Lanzhou730070 China Key Lab. of Railway Vehicle Thermal Engineering Ministry of Education Lanzhou730070 China

To meet the dual-carbon target, the power supply and demand contradiction during peak and valley periods in China and the clean heating problem in rural houses, the phase-change heat-storage electric heating floor system powered by the PV(photovoltaic) system and the power grid is proposed by this paper and its numerical model for a rural house in Lanzhou is built with the help of TRNSYS-Build software. Firstly, the hourly heating load of the house is analyzed. And then, in the operating mode of the floor system with 8-hour powered on and 4-hour off, the relationship between the heat-storage floor layer thickness and the indoor thermal comfort is revealed. The influence of the heating load rate undertaken by the PV system and its battery on the system economy and environmental impact is also indicated. The results show that the heat-storage layer with a 30mm thick is recommended in this paper condition, and the corresponding indoor temperature and PMV are 20.1~24.7℃ and -0.86~0.43, respectively. If the condition allows, more PV panel is encouraged to bear more heating load. The PV system with 70% heating load is recommended to match 30kWh battery and its investment payback period is 9.26 years. © 2024, The Authors. All rights reserved.

关键词： Floors

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：