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: System Description for CoNLL-2012 12

ICT: System Description for CoNLL-2012

引用

Joint Conference on Empirical Methods in Natural Language processing and Computational Natural Language Learning

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)9781627484046

In this paper, we present our system description for the CoNLL-2012 coreference resolution task on English, Chinese and Arabic. We investigate a projection-based model in which we first translate Chinese and Arabic into English, run a publicly availab.e coreference system, and then use a new projection algorithm to map the coreferring entities back from English into mention candidates detected in the Chinese and Arabic source. We compare to a baseline that just runs the English coreference system on the supplied parses for Chinese and Arabic. Because our method does not beat the baseline system on the development set, we submit outputs generated by the baseline system as our final submission.

关键词： Arabic language English English language Projection algorithms Chinese Chinese philosophy Chinese art BASELINE information technology information and communication technology International Criminal Tribunal Coreference Resolution

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

A Group key assignment scheme based on multi-dimensional space circle properties

引用

International Journal of Advancements in computing Technology 2012年第16期4卷 508-514页

作者： Ge, Lina School of information science and engineering Guangxi University for nationalities Nanning Guangxi 530006 China Science Computing and Intelligent Information Processing of Guangxi higer education key lab. Guangxi Teacher Education University Nanning 530023 China

A group key assignment scheme based on multi-dimensional space circle properties is proposed, which enable the members of a group to obtain the group key by both the public information published on the notice board and the secret information of their own. The proposed scheme can be divided into three phases: user registration, group key assignment, and group key computation. The proposed scheme has such advantages as easy operations of group key update and member's join/leave, and the security properties of forward secrecy and backward secrecy.

关键词： Geometric approach Group key assignment Multi-dimensional space circle properties

来源：评论

学校读者我要写书评

暂无评论

引用

Annual meeting of the Association for Computational Linguistics

作者： Xinyan Xiao Deyi Xiong Min Zhang Qun Liu Shouxun Lin Key Lab. of Intelligent Info. Processing Institute of Computing Technology Chinese Academy of Sciences Human Language Technology Institute for Infocomm Research

ISBN: (纸本)9781622761715

Previous work using topic model for statistical machine translation (SMT) explore topic information at the word level. However, SMT has been advanced from word-based paradigm to phrase/rule-based paradigm. We therefore propose a topic similarity model to exploit topic information at the synchronous rule level for hierarchical phrase-based translation. We associate each synchronous rule with a topic distribution, and select desirable rules according to the similarity of their topic distributions with given documents. We show that our model significantly improves the translation performance over the baseline on NIST Chinese-to-English translation experiments. Our model also achieves a better performance and a faster speed than previous approaches that work at the word level.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Study on the dynamic monitoring of urban expansion of Nanning City using Remote Sensing

Study on the dynamic monitoring of urban expansion of Nannin...

引用

2011 International Conference on Remote Sensing, Environment and Transportation Engineering, RSETE 2011

作者： Wu, Chao-Kui Yuan, Chang-An Zhang, Li-Qiong Lao, Juan Guangxi University Nanning China Key Lab. of Scientific Computing and Intelligent Information Processing Universities of Guangxi Guangxi Teachers Education University Nanning China

Take multi-time-phase Landstat TM/ETM+ Remote Sensing images (1990,2002,2007) of Nanning City as data source and use RS and GIS intergration technology to extract the informa-tion of city. The paper analyses the prope... 详细信息

ISBN: (纸本)9781424491711

关键词： Remote sensing

来源：评论

学校读者我要写书评

暂无评论

Through-wall synthetic aperture radar based on finite beamwidth processing

Through-wall synthetic aperture radar based on finite beamwi...

引用

3rd Microwaves, Radar and Remote Sensing Symposium, MRRS-2011

作者： Zhu, Jiabing Hong, Yi Tao, Liang East China Research Institute of Electronic Engineering Hefei Anhui China Education Ministry Key Lab. of Intelligent Computing and Signal Processing Anhui University China

ISBN: (纸本)9781424496440

Standard backprojection technique is used in typical through-wall synthetic aperture radar (TWSAR) image, it implicitly assumes infinite beamwidth, whereby the entire target area is illuminated and returns are collected from all points in the imaging grid, and this decreases the efficiency of the algorithm by summing over unnecessary grid points. In order to eliminate the disadvantage, the time-domain backprojection method based on finite beamwidth processing is proposed in the paper. The processing method is designed to be more physically realistic by accounting for the actual antenna pattern. Simulation results show that depending on the width of the effective beam, the number of processing loops can be reduced by up to 50%, while still maintaining good image quality in terms of the reconstructed target response. © 2011 IEEE.

关键词： processing

来源：评论

学校读者我要写书评

暂无评论

GPU based fast algorithm for tanner graph based image interpolation

GPU based fast algorithm for tanner graph based image interp...

引用

3rd IEEE International Workshop on Multimedia Signal processing, MMSP 2011

作者： Lei, Wei Xiong, Ruiqin Ma, Siwei Liang, Luhong Key Lab. of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Science Beijing 100190 China Institute of Digital Media Peking University Beijing 100871 China

ISBN: (纸本)9781457714337

In image/video processing software and hardware products, low complexity interpolation algorithms, such as cubic and splines methods, are commonly used. However, these methods tend to blur textures and produce jaggy effect compared with other adaptive methods such as NEDI, SAI. Tanner graph based image interpolation algorithm has better effect in dealing with edge and texture, but with high computation complexity. Thanks to the high performance parallel processing capability of today's GPU, use of complex algorithms for real time application is becoming possible. In this paper, we present a fast algorithm for tanner graph based image interpolation and it's implementation on GPU. In our algorithm, the image model training process of tanner graph based image interpolation is greatly simplified. Experimental results show that the GPU implementation can be more than 47 times as fast as the CPU implementation. © 2011 IEEE.

关键词： Graphics processing unit

来源：评论

学校读者我要写书评

暂无评论

A new regression method based on SVM classification

A new regression method based on SVM classification

引用

2011 8th International Conference on Fuzzy Systems and Knowledge Discovery, FSKD 2011, Jointly with the 2011 7th International Conference on Natural Computation, ICNC'11

作者： Dong, Yi Cheng, Wei Li, Shengfeng Institute of Applied Mathematics Bengbu College Bengbu China School of Management Hefei Univ. of Technology Hefei China Key Lab. of Intelligent Computing and Signal Processing Anhui University Hefei China Anhui Vocational College of Electronics and Information Technology Bengbu China

ISBN: (纸本)9781612841816

SVM (Support Vector Machines) is a novel algorithm of machine learning which is based on SLT (Statistical Learning Theory). It can solve the problem characterized by nonlinear, high dimension, small sample and local minimizing perfectly. For non-linear problem, the forecasting technique of FCTR (First classification, then regression) was proposed, based on the classification approach of SVM and has carried on the simulation experiment. The experiment shows that the fitting value which obtains using the return to first would be more precise than directly. Using this method to food production forecast, its accuracy is superior to other production forecasting methods. © 2011 IEEE.

关键词： Support vector machines

来源：评论

学校读者我要写书评

暂无评论

Using global statistics to rank retrieval systems without relevance judgments

引用

作者： Shi, Zhiwei Wang, Bin Li, Peng Shi, Zhongzhi Information Retrieval Group Center for Advanced Computing Research Institute of Computing Technology Beijing 100190 China Key Lab. of Intelligent Information Processing Institute of Computing Technology CAS Beijing 100190 China

ISBN: (纸本)3642163262

How to reduce the amount of relevance judgments is an important issue in retrieval evaluation. In this paper, we propose a novel method using global statistics to rank retrieval systems without relevance judgments. In our method, a series of global statistics of a system, which indicate the percentage of its documents found by k out of all the N systems (k = 1, 2, ..., N), are selected, then a linear combination of the series of global statistics is utilized to fit the mean average precision (MAP) of the retrieval system. Optimal coefficients are obtained by linear regression. No human relevance judgments are required in the entire process. Compared with existing evaluation methods without relevance judgments, our method has two advantages. Firstly, it outperforms all early attempts. Secondly, it is adjustable for different effectiveness measurements, e.g. MAP, precision at n, and so forth. © 2010 IFIP.

关键词： information retrieval

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：