检索结果-内蒙古大学图书馆

2013 Conference on Empirical Methods in Natural Language processing, EMNLP 2013

作者： Wang, Rui Utiyama, Masao Goto, Isao Sumita, Eiichro Zhao, Hai Lu, Bao-Liang Center for Brain-Like Computing and Machine Intelligence Department of Computer Science and Engineering Shanghai Jiao Tong Unviersity Shanghai200240 China Multilingual Translation Laboratory MASTAR Project National Institute of Information and Communications Technology 3-5 Hikaridai Keihanna Science City Kyoto619-0289 Japan MOE-Microsoft Key Lab. for Intelligent Computing and Intelligent Systems Shanghai Jiao Tong Unviersity Shanghai200240 China

ISBN: (纸本)9781937284978

Neural network language models, or continuous-space language models (CSLMs), have been shown to improve the performance of statistical machine translation (SMT) when they are used for reranking n-best translations. However, CSLMs have not been used in the first pass decoding of SMT, because using CSLMs in decoding takes a lot of time. In contrast, we propose a method for converting CSLMs into back-off n-gram language models (BNLMs) so that we can use converted CSLMs in decoding. We show that they outperform the original BNLMs and are comparable with the traditional use of CSLMs in reranking. © 2013 Association for Computational Linguistics.

关键词： Decoding

来源：评论

学校读者我要写书评

暂无评论

Using Chou’s Pseudo Amino Acid Composition for Protein Remote Homology Detection

引用

Engineering（科研） 2013年第10期5卷 149-153页

作者： Bin Liu Xiaolong Wang School of Computer Science and Technology Harbin Institute of Technology Shenzhen Graduate School Shenzhen Guangdong China Key Laboratory of Network Oriented Intelligent Computation Harbin Institute of Technology Shenzhen Graduate School Shenzhen Guangdong China Shanghai Key Laboratory of Intelligent Information Processing Shanghai China School of Computer Science and Technology Harbin Institute of Technology Shenzhen Graduate School Shenzhen Guangdong China Key Laboratory of Network Oriented Intelligent Computation Harbin Institute of Technology Shenzhen Graduate School Shenzhen Guangdong China

Protein remote homology detection is a key problem in bioinformatics. Currently, the discriminative methods, such as Support Vector Machine (SVM), can achieve the best performance. The most efficient approach to improve the performance of the SVM-based methods is to find a general protein representation method that is able to convert proteins with different lengths into fixed length vectors and captures the different properties of the proteins for the discrimination. The bottleneck of designing the protein representation method is that native proteins have different lengths. Motivated by the success of the pseudo amino acid composition (PseAAC) proposed by Chou, we applied this approach for protein remote homology detection. Some new indices derived from the amino acid index (AAIndex) database are incorporated into the PseAAC to improve the generalization ability of this method. Our experiments on a well-known benchmark show this method achieves superior or comparable performance with current state-of-the-art methods.

关键词： Protein Remote Homology Support Vector Machine Pseudo Amino Acid Composition Protein Representation

来源：评论

学校读者我要写书评

暂无评论

SALIENT REGION DETECTION VIA TEXTURE-SUPPRESSED BACKGROUND CONTRAST

SALIENT REGION DETECTION VIA TEXTURE-SUPPRESSED BACKGROUND C...

引用

IEEE International Conference on Image processing

作者： Jiamei Shuai Laiyun Qing Jun Miao Zhiguo Ma Xilin Chen University of Chinese Academy of Sciences Beijing 100049 China Key Lab of Intelligent Information Processing of Chinese Academy of Sciences (CAS) Institute of Computing Technology CAS Beijing 100190 China

ISBN: (纸本)9781479923427

We propose a novel salient region detection algorithm by texture-suppressed background contrast. We employ a structure extraction algorithm to suppress the small scale textures which are supposed to be not sensitive for human vision system. Then the texture-suppressed image is segmented into homogeneous superpixels. Motivated by the observation that the spatial distribution of the background has a high probability on the boundaries of images, we estimate the background as superpixels near the image boundaries. The saliency of each superpixel is then defined as the summation of its k minimum color distances to the estimated background super-pixels. Finally a post-processing process involving spatial and color adjacency is employed to generate a per-pixel saliency map. Experimental results demonstrate that the proposed method outperforms the state-of-the-art approaches.

关键词： Salient region detection Background contrast Texture suppression Superpixels BACKGROUND images Summation computer vision Boundary value problems Grain boundaries boundary layer Color Detection algorithms

来源：评论

学校读者我要写书评

暂无评论

An empirical study on word segmentation for Chinese machine translation 1

引用

14th Annual Conference on intelligent Text processing and Computational Linguistics, CICLing 2013

作者： Zhao, Hai Utiyama, Masao Sumita, Eiichiro Lu, Bao-Liang MOE-Microsoft Key Laboratory of Intelligent Computing and Intelligent System Shanghai Jiao Tong University #800 Dongchuan Road Shanghai 200240 China Department of Computer Science and Engineering Shanghai Jiao Tong University #800 Dongchuan Road Shanghai 200240 China Multilingual Translation Laboratory MASTAR Project National Institute of Information and Communications Technology 3-5 Hikaridai Keihanna Science City Kyoto 619-0289 Japan

ISBN: (数字)9783642372568

ISBN: (纸本)9783642372551

Word segmentation has been shown helpful for Chinese-to-English machine translation (MT), yet the way different segmentation strategies affect MT is poorly understood. In this paper, we focus on comparing different segmentation strategies in terms of machine translation quality. Our empirical study covers both English-to-Chinese and Chinese-to-English translation for the first time. Our results show the necessity of word segmentation depends on the translation direction. After comparing two types of segmentation strategies with associated linguistic resources, we demonstrate that optimizing segmentation itself does not guarantee better MT performance, and segmentation strategy choice is not the key to improve MT. Instead, we discover that linguistical resources such as segmented corpora or the dictionaries that segmentation tools rely on actually determine how word segmentation affects machine translation. Based on these findings, we propose an empirical approach that directly optimize dictionary with respect to the MT task for word segmenter, providing a BLEU score improvement of 1.30. © 2013 Springer-Verlag.

关键词： Machine translation

来源：评论

学校读者我要写书评

暂无评论

未来视频技术专题(英文)

引用

China Communications 2013年第5期 8-10页

作者：陈熙霖朱秀昌王桥胡栋 Ming-Ting SUN the Institute of Computing Technology Chinese Academy of Sciences (CAS) the IEEE Transactions on Image Processing the Journal of Computer Science and Technology the Chinese Journal of Computers College of Communications and Information Engineering NUPT Image Processing and Image Communications Key Laboratory of Information Industrial Ministry and Jiangsu Province Signal and Information Processing Laboratory Southeast University

In the past few years, video has become one of the most powerful engines to push communications forward. The increasing of digital video technology requires larger and larger bandwidth for various applications, such as IPTV, VOD, video phone, mobile search, etc. The goal of this Feature Topic column is to present and highlight the latest progress and future video-related technologies. We hope this

关键词： IEEE over

来源：评论

学校读者我要写书评

暂无评论

Energy-Efficient Task Allocation for VFI-Based Real-Time Multi-core Systems

Energy-Efficient Task Allocation for VFI-Based Real-Time Mul...

引用

International Conference on information Science and Cloud computing Companion (ISCC-C)

作者： Xiaodong Wu Yuzhu Zeng Jianjun Han College of Mathematics and Computer Science Quanzhou Normal University Key Laboratory of Intelligent Computing and Information Processing Fujian Province University Fujian China College of Computer Science and Technology Huazhong University of Science and Technology Wuhan Hubei China

Chip Multiprocessor (CMP) has become computing engine for a wide spectrum of applications due to its higher throughput and better energy efficiency. The problem of optimal task-to-core allocation with the minimum energy consumption has been proven to be NP-hard. In order to solve the energy-efficient real-time task mapping in the voltage frequency islands (VFI) based multicore system, we propose a heuristics EEGA (Energy-Efficient and Genetic Algorithm) to address the problem. During the iteration process of the algorithm, the energy consumption of the processor can be gradually optimized by the selection, crossover and mutation operators. Experimental results show that when compared with other energy-efficient mapping algorithms, our proposed approach can gain better performance with regard to the energy efficiency and schedulability ratio.

关键词： Biological cells Real-time systems Multicore processing Resource management Energy efficiency Frequency synchronization Sociology

来源：评论

学校读者我要写书评

暂无评论

Moving vehicle detection and tracking in traffic images based on horizontal edges

引用

Telkomnika - Indonesian Journal of Electrical Engineering 2013年第11期11卷 6477-6483页

作者： Zhu, Hongjin Fan, Honghui Guo, Shuqiang School of Computer Engineering Jiangsu University of Technology Changzhou 213001 Jiangsu China Key Laboratory of Cloud Computing Intelligent Information Processing of Changzhou City China School of Information Engineering Northeast Dianli University Jilin 132012 Jilin China

This paper presents a moving vehicle detection and tracking system, which comprising of Horizontal Edges method and Local Auto Correlation. Horizontal Edges characteristic can be strengthened and the influence of weather condition is reduced by using Local Auto Correlation, so the detection rate of extracting and tracking moving vehicles with horizontal edge can be raised. Local Auto Correlation images are generated for vehicle detection and based on Horizontal Edges method. The distance of the gravity center of Horizontal Edges is used to track vehicles in traffic video. We verify the system using a variety of weather (in fog, car shadow existence, morning and evening) traffic video. Experimental results have shown that the high detection rate of moving vehicles be obtained by using the proposed method. © 2013 Universitas Ahmad Dahlan.

关键词： Tracking (position)

来源：评论

学校读者我要写书评

暂无评论

CHARACTERIZATION OF POWDERY MILDEW IN WINTER WHEAT USING MULTI-ANGULAR HYPERSPECTRAL MEASUREMENTS

CHARACTERIZATION OF POWDERY MILDEW IN WINTER WHEAT USING MUL...

引用

IEEE International Geoscience and Remote Sensing Symposium

作者： Jinling Zhao Lin Yuan Linsheng Huang Dongyan Zhang Jingcheng Zhang Xiaohe Gu Beijing Research Center for Information Technology in Agriculture Beijing Academy of Agriculture and Forestry Sciences Beijing 100097 China Key Laboratory of Intelligent Computing & Signal Processing Ministry of Education Anhui University Hefei 230039 China

ISBN: (纸本)9781479911127

This study aims at characterizing wheat canopies caused by powdery mildew (Blumeria graminis f. sp. tritici) with multi-angular hyperspectral data. The filling stage (23 May, 2012) was chosen to achieve such a goal, considering that the disease can show distinctive symptoms during the months of May and June. A total of 37 sample plots were selected including 32 normal canopies and 5 diseased canopies with varied severity. To minimizing the soil background influences, multi-angular hyperspectral data were acquired at different view angles (0°, 45° and 90°). The results showed that the proportion of wheat vegetation and soil changed greatly and the hyperspectral reflectance values correspondingly changed. Consequently, the reflectance at different viewing angles showed great differences, but the curves had the same change trends. The results showed that, to accurately identify the spectral differences caused by powdery mildew, the optimal angle or a combination of several angles must be firstly found from multi-angular hyperspectral measurements.

关键词： Hyperspectral remote sensing Multi-angular spectral measurement Powdery mildew Sensitive wave bands Winter wheat powdery mildew winter wheat hyperspectral remote sensing multiangular Angle Wheat look angles (electronics) Canopies Winter

来源：评论

学校读者我要写书评

暂无评论

Optimizing radial basis function neural network based on rough sets and affinity propagation clustering algorithm

引用

Journal of Zhejiang University-Science C(Computers and Electronics) 2012年第2期13卷 131-138页

作者： Xin-zheng XU Shi-fei DING Zhong-zhi SHI Hong ZHU School of Computer Science and Technology China University of Mining and TechnologyXuzhou 221116China Key Laboratory of Intelligent information Processing Institute of Computing TechnologyChinese Academy of SciencesBeijing 100190China

A novel method based on rough sets (RS) and the affinity propagation (AP) clustering algorithm is developed to optimize a radial basis function neural network (RBFNN). First, attribute reduction (AR) based on RS theory, as a preprocessor of RBFNN, is presented to eliminate noise and redundant attributes of datasets while determining the number of neurons in the input layer of RBFNN. Second, an AP clustering algorithm is proposed to search for the centers and their widths without a priori knowledge about the number of clusters. These parameters are transferred to the RBF units of RBFNN as the centers and widths of the RBF function. Then the weights connecting the hidden layer and output layer are evaluated and adjusted using the least square method (LSM) according to the output of the RBF units and desired output. Experimental results show that the proposed method has a more powerful generalization capability than conventional methods for an RBFNN.

关键词： Radial basis function neural network （RBFNN） Rough sets Affinity propagation Clustering

来源：评论

学校读者我要写书评

暂无评论

Iterative annotation transformation with predict-self reestimation for Chinese word segmentation

Iterative annotation transformation with predict-self reesti...

引用

2012 Joint Conference on Empirical Methods in Natural Language processing and Computational Natural Language Learning, EMNLP-CoNLL 2012

作者： Jiang, Wenbin Meng, Fandong Liu, Qun Lü, Yajuan Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences China

ISBN: (纸本)9781937284435

In this paper we first describe the technology of automatic annotation transformation, which is based on the annotation adaptation algorithm (Jiang et al., 2009). It can automatically transform a human-annotated corpus from one annotation guideline to another. We then propose two optimization strategies, iterative training and predict-self reestimation, to further improve the accuracy of annotation guideline transformation. Experiments on Chinese word segmentation show that, the iterative training strategy together with predict-self reestimation brings significant improvement over the simple annotation transformation baseline, and leads to classifiers with significantly higher accuracy and several times faster processing than annotation adaptation does. On the Penn Chinese Treebank 5.0, it achieves an F-measure of 98.43%, significantly outperforms previous works although using a single classifier with only local features. © 2012 Association for Computational Linguistics.

关键词： Iterative methods

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：