检索结果-内蒙古大学图书馆

Joint Conference on Lexical and Computational Semantics

作者： Hao Xiong Qun Liu Key Lab. of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences P.O. Box 2704 Beijing 100190 China

ISBN: (纸本)9781622765027;1622765028

The goal of semantic dependency parsing is to build dependency structure and lab.l semantic relation between a head and its modifier. To attain this goal, we concentrate on obtaining better dependency structure to predict better semantic relations, and propose a method to combine the results of three state-of-the-art dependency parsers. Unfortunately, we made a mistake when we generate the final output that results in a lower score of 56.31% in term of lab.led Attachment Score (LAS), reported by organizers. After giving golden testing set, we fix the bug and rerun the evaluation script, this time we obtain the score of 62.8% which is consistent with the results on developing set. We will report detailed experimental results with correct program as a comparison standard for further research.

关键词： System Combination Chinese Semantic Dependency Parsing dependency DEPENDENCE Semantics Parsing bugs information technology information and communication technology International Criminal Tribunal

来源：评论

学校读者我要写书评

暂无评论

ICT: A Translation based Method for Cross-lingual Textual Entailment 12

ICT: A Translation based Method for Cross-lingual Textual En...

引用

Joint Conference on Lexical and Computational Semantics

作者： Fandong Meng Hao Xiong Qun Liu Key Lab. of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences P.O. Box 2704 Beijing 100190 China

ISBN: (纸本)9781622765027

In this paper, we present our system description in task of Cross-lingual Textual Entailment. The goal of this task is to detect entailment relations between two sentences written in different languages. To accomplish this goal, we first translate sentences written in foreign languages into English. Then, we use EDITS, an open source package, to recognize entailment relations. Since EDITS only draws monodirectional relations while the task requires bidirectional prediction, thus we exchange the hypothesis and test to detect entailment in another direction. Experimental results show that our method achieves promising results but not perfect results compared to other participants.

关键词： foreign language information technology information and communication technology International Criminal Tribunal open source Translations based Translation Translation Process

来源：评论

学校读者我要写书评

暂无评论

Semi-supervised hierarchical co-clustering

Semi-supervised hierarchical co-clustering

引用

7th International Conference on Rough Sets and Knowledge technology, RSKT 2012

作者： Huang, Feifei Yang, Yan Li, Tao Zhang, Jinyuan Rutayisire, Tonny Mahmood, Amjad School of Information Science and Technology Provincial Key Lab. of Cloud Computing and Intelligent Technology Southwest Jiaotong University Chengdu 610031 China School of Computer Science Florida International University Miami FL 33199 United States

ISBN: (纸本)9783642318993

Hierarchical co-clustering aims at generating dendrograms for the rows and columns of the input data matrix. The limitation of using simple hierarchical co-clustering for document clustering is that it has a lot of feature terms and documents, and it also ignores the semantic relations between feature terms. In this paper a semi-supervised clustering algorithm is proposed for hierarchical co-clustering. In the first step feature terms are clustered using a little supervised information. In the second step, the feature terms are merged as new feature attributes. And in the last step, the documents and merged feature terms are clustered using hierarchical co-clustering algorithm. Semantic information is used to measure the similarity during the hierarchical co-clustering process. Experimental results show that the proposed algorithm is effective and efficient. © 2012 Springer-Verlag.

关键词： Clustering algorithms

来源：评论

学校读者我要写书评

暂无评论

Multi-task Semi-supervised Semantic Feature Learning for Classification

Multi-task Semi-supervised Semantic Feature Learning for Cla...

引用

IEEE International Conference on Data Mining (ICDM)

作者： Changying Du Fuzhen Zhuang Qing He Zhongzhi Shi The Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences Beijing China

Multi-task learning has proven to be useful to boost the learning of multiple related but different tasks. Meanwhile, latent semantic models such as LSA and LDA are popular and effective methods to extract discriminative semantic features of high dimensional dyadic data. In this paper, we present a method to combine these two techniques together by introducing a new matrix tri-factorization based formulation for semi-supervised latent semantic learning, which can incorporate lab.led information into traditional unsupervised learning of latent semantics. Our inspiration for multi-task semantic feature learning comes from two facts, i.e., 1) multiple tasks generally share a set of common latent semantics, and 2) a semantic usually has a stable indication of categories no matter which task it is from. Thus to make multiple tasks learn from each other we wish to share the associations between categories and those common semantics among tasks. Along this line, we propose a novel joint Nonnegative matrix tri-factorization framework with the aforesaid associations shared among tasks in the form of a semantic-category relation matrix. Our new formulation for multi-task learning can simultaneously learn (1) discriminative semantic features of each task, (2) predictive structure and categories of unlab.led data in each task, (3) common semantics shared among tasks and specific semantics exclusive to each task. We give alternating iterative algorithm to optimize our objective and theoretically show its convergence. Finally extensive experiments on text data along with the comparison with various baselines and three state-of-the-art multi-task learning algorithms demonstrate the effectiveness of our method.

关键词： Semantics Optimization Feature extraction Data mining Data models Joints Iterative methods

来源：评论

学校读者我要写书评

暂无评论

Interactive event detection in crowd scenes 12

Interactive event detection in crowd scenes

引用

4th International Conference on Internet Multimedia computing and Service, ICIMCS 2012

作者： Qin, Lei Cheng, Zhongwei Huang, Qingming Pang, Junbiao Key Lab. of Intel. Inf. Proc. Institute of Computing Technology Chinese Academy of Sciences Beijing China Graduate University of Chinese Academy of Sciences Beijing China Beijing Municipal Key Lab. of Multimedia and Intelligent Software Technology Beijing Univ. of Tech. China

ISBN: (纸本)9781450316002

As an important aspect in video content analysis, event detection is still an open problem. In particular, the study on detecting interactive events in crowd scenes is still limited. In this paper, we investigate detecting interactive events between persons, e.g. PeopleMeet, PeopleSplitUp and Embrace in complex scenes using a sequence learning based approach. By sequence learning, the spatial-temporal context information is introduced in the learning stage. Experiments have been performed over TRECVid Event Detection 2010 dataset, which contains totally 144 hours surveillance video of London Gatwick airport. According to the TRECVid-ED 2010 formal evaluation, our approach obtains promising results, with the top performance (NDCR) for PeopleMeet and PeopleSplit-Up, and second-best performance (NDCR) for Embrace. Copyright © 2012 ACM.

关键词： Security systems

来源：评论

学校读者我要写书评

暂无评论

Multi-lab.l image annotation based on neighbor pair correlation chain 1

引用

8th International Conference on Machine Learning and Data Mining in Pattern Recognition, MLDM 2012

作者： Jiang, Guang Liu, Xi Shi, Zhongzhi Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences Beijing 100190 China Graduate University of Chinese Academy of Sciences Beijing 100049 China Information Technology Laboratory Fujitsu Research and Development Center Co. Ltd. Beijing 100025 China

ISBN: (数字)9783642315374

ISBN: (纸本)9783642315367

Image annotation plays an important role in content-based image understanding, various machine learning methods have been proposed to solve this problem. In this paper, lab.l correlation is considered as an undirected bipartite graph, in which each lab.l are correlated by some common hidden topics. As a result, given a lab.l, random walk with restart on the graph supplies a most related lab.l, repeating this precedure leads to a lab.l chain, which keep each adjacent lab.ls pair correlated as maximally as possible. We coordinate the lab.ls chain with its respective classifier training on bottom feature, and guide a classifier chain to annotate an image. The experiment illustrates that our method outperform both the baseline and another popular method. © 2012 Springer-Verlag.

关键词： Learning systems

来源：评论

学校读者我要写书评

暂无评论

The structure of the sparse basis function in compressive sensing for fast analysis of wide-angle monostatic scattering problems

The structure of the sparse basis function in compressive se...

引用

2012 International Conference on Microwave and Millimeter Wave technology, ICMMT 2012

作者： Du, Hong-Mei Chen, Ming-Sheng Wu, Xian-Liang Key Lab. of Intelligent Computing and Signal Processing Anhui University Ministry of Education Hefei 230029 China Department of Physics and Electronic Engineering Hefei Normal University Hefei 230601 China University of Science and Technology of China Hefei 230026 China

ISBN: (纸本)9781467321839

In the theory of compressive sensing, the selection of the basis functions directly affects the sparse transformation, observation number and reconstruction accuracy. In this paper, we introduce the structure of three sparse basic functions, which are used to analyze the electromagnetic scattering problems over a wide incident angle by the method of moment and compressive sensing. According to the characteristics of the induced current of wide angle, the best basic function is selected. Compared with the DCT, the accuracy of the reconstruction for different shape object are improved and the observation number reduces about 50%. © 2012 IEEE.

关键词： Method of moments

来源：评论

学校读者我要写书评

暂无评论

A novel online event analysis framework for micro-blog based on incremental topic modeling

A novel online event analysis framework for micro-blog based...

引用

13th ACIS International Conference on Software Engineering, Artificial Intelligence, Networking, and Parallel/Distributed computing, SNPD 2012

作者： Ma, Huifang Wang, Bo Li, Ning Department of Computer Science Northwest Normal University Lanzhou Gansu 730070 China Department of Military Information Management Shanghai Branch PLA Nanjing Institute of Politics Shanghai 200433 China Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences 100190 Beijing China

ISBN: (纸本)9780769547619

In this paper, we present a scalab.e implementation of a topic modeling (Adaptive Link-IPLSA) based method for online event analysis, which summarize the gist of massive amount of changing tweets and enable users to explore the temporal trends in topics. This model also can simultaneously maintain the continuity of the latent semantics to better capture the time line development of events. With the help of this model, users can quickly grasp major topics in these twitters. The preliminary results show that our method leads to more balanced and comprehensive improvement for online event detection compared to benchmark approaches. Additionally our algorithm is computationally feasible in near real-time scenarios making it an attractive alternative for capturing the rapidly changing dynamics of microblogs. © 2012 IEEE.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Parallel Web Mining System Based on Cloud Platform

引用

ZTE Communications 2012年第4期10卷 45-53页

作者： Shengmei Luo Qing He Lixia Liu Xiang Ao Ning Li Fuzhen Zhuang Pre-Research department of ZTE Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences Graduate University of Chinese Academy of Sciences

Traditional machine-learning algorithms are struggling to handle the exceedingly large amount of data being generated by the internet. In real-world applications, there is an urgent need for machine-learning algorithms to be able to handle large-scale, high-dimensional text data. Cloud computing involves the delivery of computing and storage as a service to a heterogeneous community of recipients, Recently, it has aroused much interest in industry and academia. Most previous works on cloud platforms only focus on the parallel algorithms for structured data. In this paper, we focus on the parallel implementation of web-mining algorithms and develop a parallel web-mining system that includes parallel web crawler; parallel text extract, transform and load （ETL） and modeling; and parallel text mining and application subsystems. The complete system enables variable real-world web-mining applications for mass data.

关键词： web mining large scale high volume high dimension cloudcomputing

来源：评论

学校读者我要写书评

暂无评论

CROSS-MEDIA CLOUD computing

CROSS-MEDIA CLOUD COMPUTING

引用

2012 IEEE 2nd International Conference on Cloud computing and Intelligence Systems

作者： Zhongzhi Shi Guang Jiang Bo Zhang Jinpeng Yue Xiaofei Zhao Key Laboratory of Intelligent Information Processing Institute of Computing TechnologyChinese Academy of Sciences Graduate University of Chinese Academy of Sciences

Cross-media is the outstanding characteristics of the age of big data with large scale and complicated processing task. This article presents 5 issues and briefly summarizes the research progress of cross-media knowledge discovery. Furthermore, we propose a framework for cross-media semantic understanding which contains discriminative modeling, generative modeling and cognitive modeling. In cognitive modeling, a new model entitled CAM is proposed which is suitable for cross-media semantic understanding. Moreover, a Cross-Media intelligent Retrieval System (CMIRS) will be illustrated. In the final, the research directions and problems encountered are presented.

关键词： Cross-media Knowledge discovery Cloud computing CMIRS

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：