检索结果-内蒙古大学图书馆

Workshop on Statistical Machine Translation

作者： Junhui Li Zhaopeng Tu Guodong Zhou Josef van Genabith Centre for Next Generation Localisation School of Computing Dublin City University Key Lab. of Intelligent Info. Processing Institute of Computing Technology Chinese Academy of Sciences School of Computer Science and Technology Soochow University China

ISBN: (纸本)9781622765928;1622765923

Chiang's hierarchical phrase-based (HPB) translation model advances the state-of-the-art in statistical machine translation by expanding conventional phrases to hierarchical phrases - phrases that contain sub-phrases. However, the original HPB model is prone to over-generation due to lack of linguistic knowledge: the grammar may suggest more derivations than appropriate, many of which may lead to ungrammatical translations. On the other hand, limitations of glue grammar rules in the original HPB model may actually prevent systems from considering some reasonable derivations. This paper presents a simple but effective translation model, called the Head-Driven HPB (HD-HPB) model, which incorporates head information in translation rules to better capture syntax-driven information in a derivation. In addition, unlike the original glue rules, the HD-HPB model allows improved reordering between any two neighboring non-terminals to explore a larger reordering search space. An extensive set of experiments on Chinese-English translation on four NIST MT test sets, using both a small and a large training set, show that our HD-HPB model consistently and statistically significantly outperforms Chiang's model as well as a source side SAMT-style model.

关键词： Syntactic Information Hierarchical Phrase-Based Translations syntax Translation machine translation Translation Process Hierarchical Rule train stock Glues derivation Head

来源：评论

学校读者我要写书评

暂无评论

Head-Driven Hierarchical Phrase-based Translation 12

Head-Driven Hierarchical Phrase-based Translation

引用

Annual Meeting of The Association for Computational Linguistics

ISBN: (纸本)9781622761715

This paper presents an extension of Chiang's hierarchical phrase-based (HPB) model, called Head-Driven HPB (HD-HPB), which incorporates head information in translation rules to better capture syntax-driven information, as well as improved reordering between any two neighboring non-terminals at any stage of a derivation to explore a larger reordering search space. Experiments on Chinese-English translation on four NIST MT test sets show that the HD-HPB model significantly outperforms Chiang's model with average gains of 1.91 points absolute in BLEU.

关键词：

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

Feature based stitching of a clear/blurred image pair

Feature based stitching of a clear/blurred image pair

引用

International Conference on Multimedia and signal Processing

作者： Fang, Xianyong MOE Key Lab. of Intelligent Computing and Signal Processing Anhui University Hefei China

ISBN: (纸本)9780769543567

Clear image stitching becomes mature now, but how to stitch blurred images with clear ones is still tough, mainly because of the ill-posed image deblurring. Existing deblurring methods assume spatial-invarint blur kernel, pixelwise constant blur kernel or planar camera motion. But these assumptions are difficult to hold in the real blurred image which is a spatial-variant blurred image by 3D camera motion. To overcome such limits for stitching blurred image, in this paper, we present a new feature based framework of stitching a clear/blurred image pair. It is inspired by recently proposed projetive warping models depicting the camera movement embedded in the capturing process of the blurred image. Our main contribution is a feature based algorithm for kernel estimation using the overlapped clear/blurred image pair. Experimental results demonstrate the effectiveness of the proposed stitching method.© 2011 IEEE.

关键词： Cameras

来源：评论

学校读者我要写书评

暂无评论

An efficient implementation of double precision 1-D FFT for GPUs Using CUDA

引用

Journal of Information and Computational Science 2012年第2期9卷 387-394页

作者： Liu, Yanjun Guo, Licai Luo, Bin Zhang, Xingyi School of Computer Science and Technology Anhui University Hefei 230039 China Key Lab of Intelligent Computing and Signal Processing of Ministry of Education Anhui University Hefei 230039 China School of Computer Science and Technology University of Science and Technology of China Hefei 230027 China

Fast Fourier Transform (FFT) is a well known and widely used tool in many scientific and engineering fields. CUFFT, which is the NVIDIA's FFT library included in the CUDA toolkit, supports double precision FFTs. However, the implementation of CUFFT is not very efficient. In this paper, we implement an efficient double-precision Cooley-tukey algorithm for GPUs using CUDA. Some programming techniques are employed to exploit the hardware characteristics. These techniques include on-chip shared memory utilization, removing redundant computation, and coalescing the global memory access. Experiments show that the performance of our 1-D FFT is as fast as CUFFT. Furthermore, the performance of our FFT implementation is more than twice faster than CUFFT for small input sizes. Copyright © 2012 Binary Information Press.

关键词： Graphics processing unit

来源：评论

学校读者我要写书评

暂无评论

Fusion of multi-polarimetric SAR images using Directionlets transform

Fusion of multi-polarimetric SAR images using Directionlets ...

引用

2nd International Conference on Multimedia Technology, ICMT 2011

作者： Zhang, Dexiang Gao, Qingwei Wu, Xiaopei Lu, Yixiang Key Lab. of Intelligent Computing and Signal Processing Ministry of Education Anhui University Hefei China

ISBN: (纸本)9781612847740

An efficient SAR image fusion algorithm for multi - polarimetric images based on Directionlets transform is proposed. Directionlets transform is a new lattice-based multiscale analysis anisotropic multi-directional wavelet transform. Firstly, several polarimetric images can be decomposed into lowfrequency coefficients and high-frequency coefficients with multiscales and multi-directions using the Directionlets transform. For the low-frequency coefficients, the average fusion method is used. For the each directional high frequency sub-band coefficients, the directive contrast and the larger value of region variance information measurement is used to select the better coefficients for fusion. At last the fused image can be obtained by utilizing inverse transform for fused Directionlets coefficients. Experimental results show that compared with traditional algorithm, the proposed algorithm can get better visual effect and the significant information of original image like textures and contour details is well maintained. © 2011 IEEE.

关键词： Image fusion

来源：评论

学校读者我要写书评

暂无评论

Fusion of polarimetric image using contourlet transform

Fusion of polarimetric image using contourlet transform

引用

2011 International Conference on Consumer Electronics, Communications and Networks, CECNet 2011

作者： Zong-Hu, He De-Xiang, Zhang Ling-Jun, Zhang Bao-Hong, Yuan Key Lab. of Intelligent Computing and Signal Processing Anhui University Hefei China Institute of Electrical Engineering and Automation Anhui University Hefei China

ISBN: (纸本)9781612844572

Contourlet transform is the combination of the multi-scale analysis and multi-directional analysis in processing high-dimensional signals and has better approximation precision and better sparse description. Firstly, Using the Contourlet transform, several polarimetric images can be decomposed into low-frequency coefficients and high-frequency coefficients with multi-scales and multi-directions. For the low-frequency coefficients, the average fusion method is used. For the each directional high frequency sub-band coefficients, the larger value of region variance information measurement is used to select the better coefficients for fusion. At last the fused image can be obtained by utilizing inverse transform for fused contourlet coefficients. Experimental results show that the proposed algorithm works better in preserving the edges and texture information compared with the traditional image fusion algorithms. © 2011 IEEE.

关键词： Contourlet transform

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

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

A split-operator method to simulate the left hand materials

A split-operator method to simulate the left hand materials

引用

2011 Cross Strait Quad-Regional Radio Science and Wireless Technology Conference, CSQRWC 2011

作者： Ren, Xin-Gang Huang, Zhi-Xiang Wu, Xian-Liang Lu, Si-Long Mei, Yi-Cai Du, Hong-Mei Wu, Lei Key Lab. of Intelligent Computing and Signal Processing Ministry of Education Anhui University Hefei China Department of Physics and Electronic Engineering Hefei Normal University Hefei China

ISBN: (纸本)9781424497904

The finite difference time domain (FDTD) is a powerful method in electromagnetic simulation and also widely used in research of the metamaterials recently. In this paper a novel FDTD method based on split operator is proposed to simulate the left hand materials, and the lossless Drude dispersive model is taken into account in the proposed scheme. The split perfectly matched layers (SPML) are used to absorb outgoing wave and terminate the computational domain. Focusing and refocusing of the electromagnetic wave in target detection by using the perfect lens is validated, and the inverse Snell effect is also demonstrated. © 2011 IEEE.

关键词： Electromagnetic simulation

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：