检索结果-内蒙古大学图书馆

An Overview of Temporal Information Extraction

International Journal of Computer Processing of Languages 2005年第2期18卷 137-152页

作者： KAM-FAI WONG YUNQING XIA WENJIE LI CHUNFA YUAN Department of Systems Engineering and Engineering Management The Chinese University of Hong Kong Shatin Hong Kong China Department of Computing Hong Kong Polytechnic University Hong Hum Hong Kong China State Key Laboratory of Intelligent Technology and System Tsinghua University Beijing 100084 China

Research of temporal Information Extraction was regarded as a subtask of named entity recognition in 1990's. To date, the scope of this research is broadened, ranging from temporal expression extraction and annotation to temporal reasoning and understanding. This area of research is now a hot NLP topic and the results are applicable to question answering, information extraction, text summarization, etc. This paper presents the past, present and future research development in temporal information extraction.

关键词： Temporal information extraction Natural language processing Computational linguistics

来源：评论

学校读者我要写书评

暂无评论

Inconsistency measurement of software requirements specifications: an ontology-based approach

Inconsistency measurement of software requirements specifica...

引用

IEEE International Conference on Engineering of Complex Computer systems

作者： Xuefeng Zhu Zhi Jin Graduate School of Chinese Academy of Sciences Beijing China Key Laboratory of Intelligence Information Processing Institute of Computing Technology Chinese Academy and Sciences Beijing China Academy of Mathematics and System Sciences Chinese Academy and Sciences Beijing China

ISBN: (纸本)076952284X

Management of requirements inconsistency is key to the development of complex trustworthy software system, and precise measurement is precondition for the management of requirements inconsistency properly. But at present, although there are a lot of work on the detection of requirements inconsistency, most of them are limited in treating requirements inconsistency according to heuristic rules, we still lacks of promising method for handling requirements inconsistency properly. Based on an abstract requirements refinement process model, this paper takes domain ontology as infrastructure for the refinement of software requirements, the aim of which is to get requirements descriptions that are comparable. Thus we can measure requirements inconsistency based on tangent plane of requirements refinement tree, after we have detected inconsistent relations of leaf nodes at semantic level.

关键词： Software measurement Ontologies Software systems Software development management technology management Information processing Computers Mathematics Software quality Boundary conditions

来源：评论

学校读者我要写书评

暂无评论

Using fuzzy sets and genetic algorithm for Chinese verb classification

Using fuzzy sets and genetic algorithm for Chinese verb clas...

引用

World Congress on Intelligent Control and Automation (WCICA)

作者： Wei Li Chunfa Yuan Kam-Fai Wong Chun-Hung Cheng Wenjie Li State Key Laboratory of Intelligent Technology and System Tsinghua University Beijing China Department of SE&EM Chinese University of Hong Kong New Territories Hong Kong China Department of Computing Hong Kong Polytechnic University Hong Kong China

ISBN: (纸本)0780382730

Verb classification is very important for temporal information analysis and semantic understanding. In English, this topic has been fully studied. However, there are few works and no systematic approaches in Chinese up to now. We propose a new approach using fuzzy sets and genetic algorithm for Chinese verb classification. Its contribution lies in two aspects: it (a) provides a flexible and systematic framework for solving this problem; and (b) achieves high precision in experiments.

关键词： Fuzzy sets Genetic algorithms Information analysis Intelligent systems Laboratories Helium

来源：评论

学校读者我要写书评

暂无评论

Backlund Transformations for the Initial Problems of Nizhnich and Nizhnich-Novikov-Veselov Equations

引用

理论物理通讯(英文版) 2003年第7期40卷 15-18页

作者： SU Hong-Liang WANG Ming-Liang QIN Meng-Zhao State Key Laboratory of Scientific and Engineering Computing Institute of Computational Mathematics and Scien-tific/Engineering Computing Academy of Mathematics and System Science the Chinese Academy of Sciences Beijing 100080 China Mathematical Department Luoyang Institute of Technology Luoyang 471039 China

The homogeneous balance method is a method for solving general partial differential equations (PDEs). Inthis paper we solve a kind of initial problems of the PDEs by using the special Backlund transformations of the initialproblem. The basic Fourier transformation method and some variable-separation skill are used as auxiliaries. Two initialproblems of Nizhnich and the Nizhnich-Novikov-Veselov equations are solved by using this approach.

关键词： Backlund transformation initial problem Nizhnick equation Nizhnich Novikov-Veselov equation homogeneous balance method

来源：评论

学校读者我要写书评

暂无评论

Anaphora resolution in Chinese financial news for information extraction

Anaphora resolution in Chinese financial news for informatio...

引用

World Congress on Intelligent Control and Automation (WCICA)

作者： Ning Wang Chunfa Yuan K.F. Wong Wenjie Li Department of Computer Science & Technology State Key Laboratory of Intelligent Technology and System Tsinghua University Beijing China Department of System Engineering & Engineering Management Chinese University of Hong Kong Hong Kong China Department of Computing Hong Kong Polytechnic University Hong Kong China

Anaphora always appears in the text and it is a hot topic in linguistics and computational linguistics area. Anaphora resolution is an important part of the information extraction, and it is also important to discourse understanding, machine translation, abstract extraction and so on. After studying on the text in Chinese financial domain, an anaphora resolution system is proposed, which is built on a set of filtration rules and a set of evaluation rules. The experiment result shows the precision is 91.4%.

关键词： Data mining Laboratories Intelligent systems Computer science systems engineering and theory Research and development management Computational linguistics Filtration Intelligent control Automation

来源：评论

学校读者我要写书评

暂无评论

A comparative study of methodologies for designing IDSSs

引用

EUROPEAN JOURNAL OF OPERATIONAL RESEARCH 1997年第2期103卷 277-295页

作者： Blair, A Debenham, J Edwards, J Intelligent Decision Support System Laboratory Key Centre for Advanced Computing Studies School of Computing Sciences University of Technology P.O. Box 123 Broadway N.S.W. 2007 Australia

In this paper, we describe a comprehensive study conducted to understand the methodologies which are being used to design Intelligent Decision Support systems (IDSSs) and to identify the key methodological problems and benefits with using these methodologies. This comprehensive study consists of two parts. The first part is two surveys which together identify the design methodologies being used by a group of IDSS developers and how acceptable they believe their methodologies were for designing their IDSSs. The second part is a comparison of six major formal IDSS design methodologies recently published in the literature and which are not yet known to many developers. This paper is presented to assist IDSS developers in understanding what support can be gained from using existing design methodologies and hence choose the correct one for their project. Furthermore, the paper may be used by IDSS developers to compare the way that they work with the approach proposed by other developers. (C) 1997 Elsevier Science B.V.

关键词： decision support systems knowledge based systems intelligent decision support systems

来源：评论

学校读者我要写书评

暂无评论

Deep Stable Learning for Cross-lingual Dependency Parsing

引用

ACM Transactions on Asian and Low-Resource Language Information Processing 1000年

作者： Haijiang Liu Chen Qiu Qiyuan Li Maofu Liu Li Wang Jinguang Gu Computer Science and Technology Wuhan University of Science and Technology Wuhan China Hubei Province Key Laboratory of Intelligent Information Processing and Real-time Industrial System Wuhan University of Science and Technology Wuhan China Institute of Scientific and Technical Information of China Beijing China Key Laboratory of Rich-media Knowledge Organization and Service of Digital Publishing Content National Press and Publication Administration Beijing China

The Cross-lingual Dependency Parsing (XDP) task poses a significant challenge due to the differences in dependency structures between training and testing languages, known as the out-of-distribution (OOD) problem. Our research delved into this issue in the XDP dataset by selecting 43 languages from 22 language families. We found that the primary factor of the OOD problem is the unbalanced length distribution among languages. To address the impact of the OOD problem, we propose deep stable learning for Cross-lingual Dependency Parsing (SL-XDP), which utilizes deep stable learning with a feature fusion module. In detail, we implemented five feature fusion operations for generating comprehensive representations with dependency relations and the deep stable learning algorithm to decorrelate dependency structures with sequence length. Our experiments on Universal Dependencies have demonstrated that SL-XDP can lessen the impact of the OOD problem and improve the model generalization among 21 languages, with a maximum improvement of 18%.

关键词： Cross-lingual Dependency Parsing Deep Stable Learning Out-of-Distribution Problem

来源：评论

学校读者我要写书评

暂无评论

A systematic Literature Review of Robust Federated Learning: Issues, Solutions, and Future Research Directions

引用

ACM computing Surveys 1000年

作者： Md Palash Uddin Yong Xiang Mahmudul Hasan Jun Bai Yao Zhao Longxiang Gao School of Information Technology Deakin University Burwood Australia Deakin University Burwood Australia Key Laboratory of Computing Power Network and Information Security Ministry of Education Shandong Computer Science Center Shandong Academy of Sciences Qilu University of Technology Jinan China Shandong Provincial Key Laboratory of Computing Power Internet and Service Computing Shandong Fundamental Research Center for Computer Science Jinan China

Federated Learning (FL) has emerged as a promising paradigm for training machine learning models across distributed devices while preserving their data privacy. However, the robustness of FL models against adversarial data and model attacks, noisy updates, and label-flipped data issues remain a critical concern. In this paper, we present a systematic literature review using the PRISMA framework to comprehensively analyze existing research on robust FL. Through a rigorous selection process using six key databases (ACM Digital Library, IEEE Xplore, ScienceDirect, Springer, Web of Science, and Scopus), we identify and categorize 244 studies into eight themes of ensuring robustness in FL: objective regularization, optimizer modification, differential privacy employment, additional dataset requirement and decentralization orchestration, manifold, client selection, new aggregation algorithms, and aggregation hyperparameter tuning. We synthesize the findings from these themes, highlighting the various approaches and their potential gaps proposed to enhance the robustness of FL models. Furthermore, we discuss future research directions, focusing on the potential of hybrid approaches, ensemble techniques, and adaptive mechanisms for addressing the challenges associated with robust FL. This review not only provides a comprehensive overview of the state-of-the-art in robust FL but also serves as a roadmap for researchers and practitioners seeking to advance the field and develop more robust and resilient FL systems.

关键词： Federated Learning Robustness Attack Countermeasure Defence.

来源：评论

学校读者我要写书评

暂无评论

MSEConv: A Unified Warping Framework for Video Frame Interpolation

引用

ACM Transactions on Asian and Low-Resource Language Information Processing 1000年

作者： Xiangling Ding Pu Huang Dengyong Zhang Wei Liang Feng Li Gaobo Yang Xin Liao Yue Li Hunan University of Science and Technology Xiangtan China Changsha University of Science and Technology Changsha China Hunan University of Science and Technology Hunan Key Laboratory for Service computing and Novel Software Technology Xiangtan China Hunan University Changsha China University of South China Hengyang China

Within the context of video frame interpolation, complex motion modeling is the task of capturing, in a video sequence, where the moving objects are located in the interpolated frame, and how to maintain the temporal consistency of motion. Existing video frame interpolation methods typically assign either a fixed size of the motion kernel or a refined optical flow to model complex motions. However, they have the limitation of data redundancy and inaccuracy representation of motion. This paper introduces a unified warping framework, named multi-scale expandable deformable convolution (MSEConv), for simultaneously performing complex motion modeling and frame interpolation. In the proposed framework, a deep fully convolutional neural network with global attention is proposed to estimate multiple small-scale kernel weights with different expansion degrees and adaptive weight allocation for each pixel synthesis. Moreover, most of the kernel-based interpolation methods can be treated as the special case of the proposed MSEConv, thus, MSEConv can be easily transferred to other kernel-based frame interpolation methods for performance improvement. To further improve the robustness of motion occlusions, an operation of mask occlusion is introduced. As a consequence, our proposed MSEConv shows strong performance on par or even better than the state-of-the-art kernel-based frame interpolation works on public datasets. Our source code and visual comparable results are available at https://***/Pumpkin123709/MSEConv.

关键词： Video Frame Interpolation Unified Framework Complex motion Modeling Mask Occlusion

来源：评论

学校读者我要写书评

暂无评论

Web-Age Information Management 1

引用

丛书名： Lecture Notes in Computer Science

1000年

作者： Yunjun Gao Kyuseok Shim Zhiming Ding Peiquan Jin Zujie Ren Yingyuan Xiao An Liu Shaojie Qiao

ISBN: (数字)9783642395277

ISBN: (纸本)9783642395260

This book constitutes the refereed proceedings of six workshops of the 14th International Conference on Web-Age Information Management, WAIM 2013, held in Beidaihe, China, June 2013. The 37 revised full papers are organized in topical sections on the six following workshops: The International Workshop on Big Data Management on Emerging Hardware (HardBD 2013), the Second International Workshop on Massive Data Storage and Processing (MDSP 2013), the First International Workshop on Emergency Management in Big Data Age (BigEM 2013), the International Workshop on Trajectory Mining in Social Networks (TMSN 2013), the First International Workshop on Location-based Query Processing in Mobile Environments (LQPM 2013), and the First International Workshop on Big Data Management and service (BDMS 2013).

关键词： Information Storage and Retrieval Information systems Applications (incl. Internet) Data Mining and Knowledge Discovery Database Management Computer Communication Networks Algorithm Analysis and Problem Complexity

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：