检索结果-内蒙古大学图书馆

6th International Joint Conference on Natural Language Processing, IJCNLP 2013

作者： Jia, Zhongye Zhao, Hai MOE-Microsoft Key Laboratory for Intelligent Computing and Intelligent Systems Center for Brain-Like Computing and Machine Intelligence Department of Computer Science and Engineering Shanghai Jiao Tong University 800 Dongchuan Road Shanghai200240 China

ISBN: (纸本)9784990734800

Chinese Input Method Engine (IME) plays an important role in Chinese language processing. However, it has been subjected to lacking a proper evaluation metric for a long time. The natural metric for IME is user experience, which is a rather vague goal for research purpose. We propose a novel approach of quantifying user experience by using keystroke count and then correspondingly develop a framework of IME evaluation, which is fast and accurate. With the underlying linguistic background, the proposed evaluation framework can properly model the user behavior as Chinese is input through English keyboard. It is helpful to point out a way to improve the current Chinese IME performance. © IJCNLP *** right reserved.

关键词： Engines

来源：评论

学校读者我要写书评

暂无评论

Labeled Alignment for Recognizing Textual Entailment 6

Labeled Alignment for Recognizing Textual Entailment

引用

6th International Joint Conference on Natural Language Processing, IJCNLP 2013

作者： Wang, Xiao-Lin Zhao, Hai Lu, Bao-Liang Center for Brain-Like Computing and Machine Intelligence MOE-Microsoft Key Laboratory for Intelligent Computing and Intelligent Systems Department of Computer Science and Engineering Shanghai Jiao Tong University 800 Dongchuan Road Shanghai 200240 China

ISBN: (纸本)9784990734800

Recognizing Textual Entailment (RTE) is to predict whether one text fragment can semantically infer another, which is required across multiple applications of natural language processing. The conventional alignment scheme, which is developed for machine translation, only marks the paraphrases and hyponyms to justify the entailment pairs, while provides less support for the non-entailment ones. This paper proposes a novel alignment scheme, named labeled alignment, to address this problem, which introduces negative links to explicitly mark the contradictory expressions to justify the non-entailment pairs. Thus the alignment-based RTE method employing the proposed scheme, compared with those employing the conventional one, can gain accuracy improvement through actively detecting the signals of non-entailment. The experimental results on the data sets of two shared RTE tasks indicate the implemented system significantly outperforms both the baseline system and all the other submitted systems. © IJCNLP *** right reserved.

关键词： Alignment

来源：评论

学校读者我要写书评

暂无评论

Grammatical error correction as multiclass classification with single model 17

Grammatical error correction as multiclass classification wi...

引用

17th Conference on Computational Natural Language Learning: Shared Task, CoNLL 2013

作者： Jia, Zhongye Wang, Peilu Zhao, Hai MOE-Microsoft Key Laboratory for Intelligent Computing and Intelligent Systems Center for Brain-Like Computing and Machine Intelligence Department of Computer Science and Engineering Shanghai Jiao Tong University 800 Dongchuan Road Shanghai200240 China

ISBN: (纸本)9781937284718

This paper describes our system in the shared task of CoNLL-2013. We illustrate that grammatical error detection and correction can be transformed into a multiclass classification task and implemented as a single-model system regardless of various error types with the aid of maximum entropy modeling. Our system achieves the F1 score of 17.13% on the standard test set. © 2013 Association for Computational Linguistics.

关键词： Error correction

来源：评论

学校读者我要写书评

暂无评论

Exploiting mobility patterns for inter-technology handover in mobile environments

引用

computer Communications 2013年第2期36卷 203-210页

作者： Yanmin Zhu Lei Ni Bo Li Shanghai Key Lab of Scalable Computing and Systems Shanghai China Department of Computer Science and Engineering Shanghai Jiao Tong University Shanghai China Hong Kong University of Science and Technology China

Mobile terminals with multi-radio devices have become increasingly prevalent. This makes it possible for Internet applications to be supported by heterogeneous wireless networks while the terminal is on the move. As the user is constantly moving, it is highly desirable that the terminal connects to the best network and retains high performance of network connections. Handovers can be made within the same type of network (horizontal handover) or different types of networks (vertical handover). This paper focuses on link-layer inter-technology vertical handovers . Vertical handovers present several great challenges, such as user mobility randomness, high handover overhead and optimality requirement. Existing work often focuses only on the current network condition when making handover decisions , ignoring future performance of the terminal. As a result, a handover decision good for the current moment may soon become poor when the user moves to another place. This paper is motivated by the observation that users in a given mobile environment, such as university or enterprise campus, exhibit clear mobility patterns. We propose an approach for making handover decisions, which explicitly exploits user mobility patterns. This approach can produce high-performance handover decisions in the long run. Employing a comprehensive framework for preference customization , the approach supports user customization caring for different user preferences. Extensive real trace driven simulations and comparative study show our algorithm is better than the conventional vertical handover algorithms.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Covariance free incremental principal component analysis with exact mean update

引用

Journal of Computational Information systems 2013年第16期9卷 6703-6710页

作者： Zeng, Xueqiang Li, Guozheng The Key Laboratory of Embedded System and Service Computing Ministry of Education Tongji University Shanghai 200092 China Computer Center Nanchang University Nanchang 330029 China Department of Control Science and Engineering Tongji University Shanghai 201804 China

Incremental feature extraction is an essential data preprocessing technique for large-scale and streaming data mining. Among various covariance matrix-free Incremental Principal Component Analysis (IPCA) methods, Candid Covariance-free Incremental Principal Component Analysis (CCIPCA) is a state-of-the art algorithm. Since the training samples are required to be centred, CCIPCA applies an approximate centric alignment on the input data, where only the current sample is correctly centred and all historical data are not updated properly. In this paper, we propose a novel centred incremental principal component analysis algorithm with exact historical mean update, where not only the current sample is centred, but also all historical data are updated by the current mean correctly. Compared to CCIPCA, the proposed method converges more quickly, and the performance improvement is especially obvious when the data's inherent covariance is not stable. The experiments on real streaming dataset show that the proposed method is much superior to CCIPCA in convergence speed. © 2013 Binary Information Press.

关键词： Principal component analysis

来源：评论

学校读者我要写书评

暂无评论

Large-scale feature matching with distributed and heterogeneous computing

Large-scale feature matching with distributed and heterogene...

引用

International Conference on Image and Vision computing New Zealand, IVCNZ

作者： Steven Mills David Eyers Kai-Cheung Leung Xiaoxin Tang Zhiyi Huang Department of Computer Science University of Otago New Zealand Shanghai Key Laboratory of Scalable Computing and Systems Shanghai Jiao Tong University China

Feature matching is a fundamental problem in many computer vision tasks. As datasets become larger, and individual image resolution increases, this is becoming more and more computationally demanding work. While prior knowledge about the scene geometry can, in some cases, reduce the number of image pairs that need to be considered, the sheer volume of data means that parallel and distributed computing solutions must be considered. In this paper we examine the costs incurred in such solutions, and assess the way in which the problem scales with the number of cores within a single node, and the number of nodes in a distributed system. We also consider the role of heterogeneous systems, where nodes with different numbers and types of cores (including GPUs) are included in a distributed system. We show that distribution of this task across a cluster of machines has good (sometimes super-linear) scalability. However, scalability on many-core machines and GPU architectures is more limited, and is thus an important area for future research.

关键词： Schedules Graphics processing units computer architecture Optimization Random access memory Dynamic scheduling Scalability

来源：评论

学校读者我要写书评

暂无评论

An hidden markov model-based transcription factor mining method

引用

Journal of Bionanoscience 2013年第1期7卷 66-71页

作者： Wu, Chunguo Li, Gaoyang Wu, Xiaozhou Han, Xiaosong Wang, Binghong Breis, Jesualdo Tomás Fernández Wang, Fei Liang, Yanchun Key Laboratory for Symbol Computation and Knowledge Engineering of National Education Ministry College of Computer Science and Technology Jilin University Changchun 130012 China Business School University of Shanghai for Science and Technology Shanghai 200093 China Shanghai Key Laboratory of Intelligent Information Processing Shanghai 200433 China Department of Informatics and Systems University of Murcia 30100 Murcia Spain

A text mining algorithm named HMM-TFM (Hidden Markov Model based transcription factor name mining) is presented. The proposed algorithm does not need a dictionary of transcription factor names. A small verb set is defined to filter sentences. Transcription factor names are mined according to the part of speech tagged by hidden Markov model. Experimental results show that the recall and precision of HMM-TFM achieve 74.2% and 77.9%, respectively. Copyright © 2013 American Scientific Publishers.

关键词： Data mining

来源：评论

学校读者我要写书评

暂无评论

Dynamic monitoring of optimal locations in road network databases

引用

The VLDB Journal 2013年第5期23卷 697-720页

作者： Bin Yao Xiaokui Xiao Feifei Li Yifan Wu Department of Computer Science and Engineering Shanghai Key Laboratory of Scalable Computing and Systems Shanghai Jiao Tong University Shanghai China School of Computer Engineering Nanyang Technological University Singapore Singapore School of Computing University of Utah Salt Lake City USA

Optimal location (OL) queries are a type of spatial queries that are particularly useful for the strategic planning of resources. Given a set of existing facilities and a set of clients, an OL query asks for a location to build a new facility that optimizes a certain cost metric (defined based on the distances between the clients and the facilities). Several techniques have been proposed to address OL queries, assuming that all clients and facilities reside in an $$L_p$$ space. In practice, however, movements between spatial locations are usually confined by the underlying road network, and hence, the actual distance between two locations can differ significantly from their $$L_p$$ distance. Motivated by the deficiency of the existing techniques, this paper presents a comprehensive study on OL queries in road networks. We propose a unified framework that addresses three variants of OL queries that find important applications in practice, and we instantiate the framework with several novel query processing algorithms. We further extend our framework to efficiently monitor the OLs when locations for facilities and/or clients have been updated. Our dynamic update methods lead to efficient answering of continuous optimal location queries. We demonstrate the efficiency of our solutions through extensive experiments with large real data.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Compressive data retrieval with tunable accuracy in vehicular sensor networks

Compressive data retrieval with tunable accuracy in vehicula...

引用

8th International Conference on Wireless Algorithms, systems, and Applications, WASA 2013

作者： Jiang, Ruobing Zhu, Yanmin Wang, Hongjian Gao, Min Ni, Lionel M. Department of Computer Science and Engineering Shanghai Jiao Tong University China Shanghai Key Lab of Scalable Computing and Systems China Guangzhou HKUST Fok Ying Tung Graduate School Hong Kong Hong Kong Hong Kong University of Science and Technology Hong Kong Hong Kong

ISBN: (纸本)9783642397004

On-demand data retrieval is a crucial routine operation in a vehicular sensor network. However, on-demand data retrieval in a vehicular environment is particularly challenging because of frequent network disruption, large number of data readings and limited transmission opportunities. Real world vehicular datasets usually contain a lot of data redundancy. Motivated by this important observation, we propose an approach called CDR with compressive sensing for on-demand data retrieval in the highly dynamic vehicular environment. The distinctive feature of CDR is that it supports tunable accuracy of data collection. There are two major challenges for the design of CDR. First, the sparsity level of the vehicular dataset is typically unknown beforehand. Second, it is even worse that the sparsity level of the dataset is changing over time. To combat the challenge posed by time-varying data sparsity, CDR can terminate from further collection of measurements, based on an adaptive condition on which only localized measurements and computation are needed. Extensive simulations with real datasets and real vehicular GPS traces show that our approach achieves good performance of data retrieval with user-customized accuracy. © 2013 Springer-Verlag Berlin Heidelberg.

关键词： Sensor networks

来源：评论

学校读者我要写书评

暂无评论

Customer Satisfaction-Aware Scheduling for Utility Maximization on Geo-distributed Cloud Data Centers

Customer Satisfaction-Aware Scheduling for Utility Maximizat...

引用

IEEE International Conference on High Performance computing and Communications (HPCC)

作者： Chao Jing Yanmin Zhu Minglu Li Department of Computer Science and Engineering Shanghai Key Laboratory of Scalable Computing and Systems Shanghai Jiao Tong University P. R. China

With the increasingly growing amount of service requests from the world-wide customers, the cloud systems is capable of providing services while meeting the customers' satisfaction. Recently, to achieve the better reliability and performance, the cloud systems has been largely depending on the geographically distributed data centers. Nevertheless, the dollar cost of service placement by service providers (SP) differ from the multiple regions. Accordingly, it is crucial to design a request dispatching and resource allocation algorithm to maximize net profit. The existing algorithms are either built upon energy-efficient schemes alone, or multi-type requests and customer satisfaction oblivious. They cannot be applied to multi-type requests and customer satisfaction-aware algorithm design with the objective of maximizing net profit. This paper proposes a customer satisfaction-aware algorithm based on the Ant-Colony Optimization (AMP) for geo-distributed data centers. By introducing the model of customer satisfaction, we formulate the utility (or net profit) maximization issue as an optimization problem under the constraints of customer satisfaction and data centers. AMP maximizes SP net profit by dispatching service requests to the proper data centers and generating the appropriate amount of Virtual Machines (VMs) to meet customer satisfaction. To evaluate the proposed algorithm, we have conducted the comprehensive simulation and compared with the other state-of-the-art algorithms. Conclusive results have demonstrated the effectiveness of AMP both in small and large scale problem.

关键词： Customer satisfaction Electricity Servers Optimization Algorithm design and analysis Data models Carbon dioxide

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：