检索结果-内蒙古大学图书馆

2009 Workshop on Multiword Expressions: Identification, Interpretation, Disambiguation, Applications, MWE 2009

作者： Ren, Zhixiang Lü, Yajuan Cao, Jie Liu, Qun Huang, Yun Key Lab. of Intelligent Info. Processing Institute of Computing Technology Chinese Academy of Sciences P.O. Box 2704 Beijing100190 China Department of Computer Science School of Computing National University of Singapore Computing 1 Law Link Singapore117590 Singapore

ISBN: (纸本)1932432604

Multiword expressions (MWEs) have been proved useful for many natural language processing tasks. However, how to use them to improve performance of statistical machine translation (SMT) is not well studied. This paper presents a simple yet effective strategy to extract domain bilingual multiword expressions. In addition, we implement three methods to integrate bilingual MWEs to Moses, the state-of-the-art phrase-based machine translation system. Experiments show that bilingual MWEs could improve translation performance significantly. © 2009 ACL and AFNLP

关键词： Computational linguistics

来源：评论

学校读者我要写书评

暂无评论

A point pattern matching algorithm based on minimize spanning tree and Fiedler vector

A point pattern matching algorithm based on minimize spannin...

引用

1st International Conference on Information Science and Engineering, ICISE2009

作者： Xuan, Shan-Li Liang, Dong Zhu, Ming Fan, Yi Zheng Wang, Nian Key Lab. Intelligent Computing and Signal Ministry of Education Anhui University Hefei 230039 China School of Mathematical Sciences Anhui University Hefei 230039 China School of Computer and Information HeFei University of Technology Hefei 230009 China

ISBN: (纸本)9780769538877

Based on the minimize spanning tree and Fiedler vector, a new feature matching algorithm is proposed in this paper. Firstly, a weighted complete graph is constructed with the feature points of each image respectively, then search the minimal spanning tree in each complete graph. Secondly, perform spectral decomposition on the Gaussian-weighted Laplace matrix of the minimize spanning tree respectively, and divide the feature points into several different sets based on the vector(Fiedler vector) corresponding to the second smallest eigenvalue of Laplace matrix , then the corresponding relation between sets is obtained. And construct Gaussian-weighted Laplace matrices between the corresponding sets, then submit the matrices to spectral decomposition. Finally, complete the feature matching by constructing matching matrix with eigenvalues and eigenvectors. Experiment results indicate that the algorithm has a high accuracy. ©2009 IEEE.

关键词： Vectors

来源：评论

学校读者我要写书评

暂无评论

A new population diversity model in swarm intelligence

引用

Journal of Information and Computational Science 2009年第4期6卷 1891-1898页

作者： Feng, Jiqiang Xie, Weixin Xu, Chen Huang, Jianjun Key Lab. for Intelligent Information Processing Shenzhen University Shenzhen 518060 China Institute of Intelligent Computing Science Shenzhen University Shenzhen 518060 China

Many researchers of swarm intelligence (SI) algorithms take their ideas from physical and biological systems. This approach, however, is mostly qualitative and many ideas remain vague and ill-defined. In this paper, a mathematical framework based on probability theory is presented that enables us to analyze one important aspect of SI algorithms: the population diversity. Firstly the population density is defined for the population in the SI algorithms. The population diversity is then discussed from the point of view of the normal distribution in statistics. We show that there is a close connection between the distribution and population diversity and that the essential structure of population diversity is quite similar to that of the distribution. A detailed construction of the population diversity model is then given that is based on probability distributions and the convergence of the model is theoretically discussed for single peak value case. The paper concludes with a generic numerical example that validates the population diversity model. © 2009 Binary Information Press.

关键词： Normal distribution

来源：评论

学校读者我要写书评

暂无评论

Method with the center of graph for point pattern matching

Method with the center of graph for point pattern matching

引用

9th International Conference on Electronic Measurement and Instruments, ICEMI 2009

作者： Xuan, Shanli Liang, Dong Zhu, Ming Fan, Yizheng Wang, Nian Key Lab. Intelligent Computing and Signal Ministry of Education Anhui University Hefei 230039 China School of Computer and Information HeFei University of Technology Hefei 230009 China School of Mathematical Sciences Anhui University Hefei 230039 China

ISBN: (纸本)9781424438624

Based on the center of graph, a point pattern feature matching method is proposed here. Firstly, a weighted complete graph is constructed with the feature points of each image, and then the center of each graph is found respectively. With the vertex sets of the centers, the feature points are divided into several layers according to the distance from the center, and then the corresponding relation between layers is obtained. Secondly, the Gaussian-weighted Laplace matrices are constructed between the corresponding layers. And then the matrices are submitted to singular-value decomposition(SVD). Finally, represent the feature points with eigenvectors obtained from SVD, and then construct matching matrix to obtain the final matching results. Synthetic data and real world data both indicate that our method has a higher accuracy than theirs, and it can deal with the matching problem with more feature points effectively. ©2009 IEEE.

关键词： Singular value decomposition

来源：评论

学校读者我要写书评

暂无评论

Automatic adaptation of annotation standards: Chinese word segmentation and POS tagging - A case study

Automatic adaptation of annotation standards: Chinese word s...

引用

Joint Conference of the 47th Annual Meeting of the Association for Computational Linguistics and 4th International Joint Conference on Natural Language processing of the AFNLP, ACL-IJCNLP 2009

作者： Jiang, Wenbin Huang, Liang Liu, Qun Key Lab. of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences P.O. Box 2704 Beijing 100190 China Google Research 1350 Charleston Rd. Mountain View CA 94043 United States

ISBN: (纸本)9781617382581

Manually annotated corpora are valuable but scarce resources, yet for many annotation tasks such as treebanking and sequence lab.ling there exist multiple corpora with different and incompatible annotation guidelines or standards. This seems to be a great waste of human efforts, and it would be nice to automatically adapt one annotation standard to another. We present a simple yet effective strategy that transfers knowledge from a differently annotated corpus to the corpus with desired annotation. We test the efficacy of this method in the context of Chinese word segmentation and part-of-speech tagging, where no segmentation and POS tagging standards are widely accepted due to the lack of morphology in Chinese. Experiments show that adaptation from the much larger People's Daily corpus to the smaller but more popular Penn Chinese Treebank results in significant improvements in both segmentation and tagging accuracies (with error reductions of 30.2% and 14%, respectively), which in turn helps improve Chinese parsing accuracy. © 2009 ACL and AFNLP.

关键词： Forestry

来源：评论

学校读者我要写书评

暂无评论

Bilingually-constrained (monolingual) shift-reduce parsing

Bilingually-constrained (monolingual) shift-reduce parsing

引用

2009 Conference on Empirical Methods in Natural Language processing, EMNLP 2009, Held in Conjunction with ACL-IJCNLP 2009

作者： Huang, Liang Jiang, Wenbin Liu, Qun Google Research 1350 Charleston Rd. Mountain View CA 94043 United States Key Lab. of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences P.O. Box 2704 Beijing 100190 China

Jointly parsing two languages has been shown to improve accuracies on either or both sides. However, its search space is much bigger than the monolingual case, forcing existing approaches to employ complicated modeling and crude approximations. Here we propose a much simpler alternative, bilingually-constrained monolingual parsing, where a source-language parser learns to exploit reorderings as additional observation, but not bothering to build the target-side tree as well. We show specifically how to enhance a shift-reduce dependency parser with alignment features to resolve shift-reduce conflicts. Experiments on the bilingual portion of Chinese Treebank show that, with just 3 bilingual features, we can improve parsing accuracies by 0.6% (absolute) for both English and Chinese over a state-of-the-art baseline, with negligible (∼6%) efficiency overhead, thus much faster than biparsing. © 2009 ACL and AFNLP.

关键词： Forestry

来源：评论

学校读者我要写书评

暂无评论

A compression algorithm for multi-streams based on GEP

A compression algorithm for multi-streams based on GEP

引用

3rd International Conference on Genetic and Evolutionary computing, WGEC 2009

作者： Ding, Chao Yuan, Chang-An Qin, Xiao Peng, Yu-Zhong Computer and Information Engineering College Guangxi Teachers Education University Nanning 530001 China First Middle School of Mengcheng Anhui Mengcheng233500 China Key Lab. of Scientific Computing and Intelligent Information Processing in Universities of Guangxi Guangxi Teachers Education University Nanning China

ISBN: (纸本)9780769538990

This paper applied the Methods which based on GEP in compress multi-streams. The contributions of this paper include: 1) giving an introduction to data function finding based on GEP(DFF-GEP), defining the main conception of Multi-Streams, and revealing the map relation in it;2) putting forward the Compression Algorithm for Multi-Streams according to map relation lied in data between data streams;and 3)providing an experience with the real data and find that (3.1) the compression ratio of the new methods is 120-150 times as the traditional wavelets method, and 35-70 times as the wavelets and coincidence method;(3.2) the relative error of the new method is about 3??,yet maximum relative error is 0.01 by using the traditional relative error standard, the precision is improved from 7% to 15% as compared with the traditional method. © 2009 IEEE.

关键词： Errors

来源：评论

学校读者我要写书评

暂无评论

Effective approach to improve the solving precision of electric field integral equation

引用

Xi Tong Gong Cheng Yu Dian Zi Ji Shu/Systems Engineering and Electronics 2009年第11期31卷 2553-2555页

作者： Song, Kai-Hong Zhang, Qing-Hua Wu, Xian-Liang Key Lab. of Intelligent Computing and Signal Processing Anhui Univ. Hefei 230039 China

To improve the accuracy and efficiency for solving the EFIE (electric field integral equation) by the method of moment, a novel scheme is put forward to improve the calculation precision based on the EFIE. Firstly, the inaccurate induced current is obtained by solving the EFIE under coarse mesh grids. Secondly, the scattered magnetic field at any given point on the surface of the object is calculated by the inaccurate induced current. Finally, the accurate induced current at any given point is determined through total magnetic field. The proposed approach is applied to the case of infinitely perfectly electric conducting circular cylinder and square cylinder. The numerical results are presented to demonstrate the high precision and efficiency when the size of mesh grid is large.

关键词： Method of moments

来源：评论

学校读者我要写书评

暂无评论

A generic approach to classify sports video shots and its application in event detection 09

A generic approach to classify sports video shots and its ap...

引用

1st International Conference on Internet Multimedia computing and Service, ICIMCS 2009

作者： Li, Lingfang Duan, Ling-Yu Huang, Qingming Du, Jun Gao, Wen Key Lab. of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences Beijing 100190 China Institute of Digital Media Peking University Beijing 100871 China Graduate University of Chinese Academy of Sciences Beijing 100190 China NEC Research Labs. China Beijing 100084 China

ISBN: (纸本)9781605588407

Shot type is useful information for semantic sports video analysis. Most existing approaches utilize predefined rules and domain knowledge to derive shot types in sports video. Although these methods have achieved promising results in some specific games, it is hard to extend them from one sport to another. To address this problem, we propose a generic approach to classify shots in sports video. Our approach utilizes bag of visual words model to represent key frame for each shot based on Scale Invariant Feature Transform (SIFT) feature points;either Support Vector Machine (SVM) or Probabilistic Latent Semantic Analysis (PLSA) are then employed to classify key frame to determine shot type. As our approach relies little on domain knowledge, it can be more easily extended to different sports. We have evaluated our shot classification approach over five types of sports video and have achieved promising results. To show the usefulness and effectiveness of our shot classification, we apply the results of shot type to detect events in basketball video via a generative-discriminative model. In addition, we have observed that some common visual parts frequently appear across various shots in the same sport or even different but relevant sports. For instance, soccer and basketball are relevant sports in the sense of field-ball game. Motivated by this observation, we attempt to alleviate the problem of insufficient sports video data in some applications by sharing these visual parts across different but relevant kinds of sports. Copyright 2009 ACM.

关键词： Sports

来源：评论

学校读者我要写书评

暂无评论

Automatic adaptation of annotation standards: Chinese word segmentation and POS tagging: a case study 09

Automatic adaptation of annotation standards: Chinese word s...

引用

Proceedings of the Joint Conference of the 47th Annual Meeting of the ACL and the 4th International Joint Conference on Natural Language processing of the AFNLP: Volume 1 - Volume 1

作者： Wenbin Jiang Liang Huang Qun Liu Key Lab. of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences Beijing China Google Research Charleston Rd. Mountain View CA

ISBN: (纸本)9781932432459

关键词：

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：