检索结果-内蒙古大学图书馆

50th Annual Meeting of the Association for Computational Linguistics, ACL 2012

作者： Tu, Zhaopeng He, Yifan Foster, Jennifer Van Genabith, Josef Liu, Qun Lin, Shouxun Key Lab. of Intelligent Info. Processing Institute of Computing Technology CAS China Computer Science Department New York University United States School of Computing Dublin City University Ireland

ISBN: (纸本)9781937284251

Convolution kernels support the modeling of complex syntactic information in machinelearning tasks. However, such models are highly sensitive to the type and size of syntactic structure used. It is therefore an important challenge to automatically identify high impact sub-structures relevant to a given task. In this paper we present a systematic study investigating (combinations of) sequence and convolution kernels using different types of substructures in document-level sentiment classification. We show that minimal sub-structures extracted from constituency and dependency trees guided by a polarity lexicon show 1.45 point absolute improvement in accuracy over a bag-of-words classifier on a widely used sentiment corpus. © 2012 Association for Computational Linguistics.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

Head-driven hierarchical phrase-based translation

Head-driven hierarchical phrase-based translation

引用

50th Annual Meeting of the Association for Computational Linguistics, ACL 2012

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

ISBN: (纸本)9781937284251

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. © 2012 Association for Computational Linguistics.

关键词： Translation (languages)

来源：评论

学校读者我要写书评

暂无评论

Using Syntactic Head information in Hierarchical Phrase-Based Translation 7

Using Syntactic Head Information in Hierarchical Phrase-Base...

引用

7th Workshop on Statistical Machine Translation, WMT 2012, immediately following the Conference of the North-American Chapter of the Association for Computational Linguistics - Human Language Technologies, NAACL HLT 2012

作者： Li, Junhui Tu, Zhaopeng Zhou, Guodong Genabith, Josef Van Centre For Next Generation Localisation School Of Computing Dublin City University Ireland Key Lab. Of Intelligent Info. Processing Institute Of Computing Technology Chinese Academy Of Sciences China School Of Computer Science And Technology Soochow University China

ISBN: (纸本)9781937284206

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 overgeneration 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 HDHPB model consistently and statistically significantly outperforms Chiang's model as well as a source side SAMT-style model. ©2012 Association for Computational Linguistics.

关键词： Syntactics

来源：评论

学校读者我要写书评

暂无评论

A radical cascade classifier for handwritten Chinese character recognition

Journal of Software

引用

Journal of Software 2012年第10期7卷 2294-2300页

作者： Ni, Enzhi Zhou, Changle Jiang, Minjun Mind Art and Computation Lab Fujian Key Lab of the Brain-like Intelligent Systems School of Information Science and Technology Xiamen University Xiamen China School of Computer Science and Information Engineering Shanghai Institute of Technology Shanghai China

Radical extraction is the core technique for radical-based Chinese character recognition. In this paper, we proposed a new method of radical extraction radical cascade classifier. The radical cascade classifier consists of multiple AdaBoost classifiers. It can detect and extract specific radical from characters. To apply cascade classifier to radical extraction, we focus on two main points: feature selection and radical detection. In this paper, we discussed feature selection for the radical cascade classifier and proposed two methods of radical detection. Based on these works, we constructed the radical cascade classifier and conducted experiments on HITPU databases. The experimental results have shown that our approach is efficient. © 2012 ACADEMY PUBLISHER.

关键词： Extraction

来源：评论

学校读者我要写书评

暂无评论

Application of dynamic service composition in web question answering

引用

International Journal of Wireless and Mobile Computing 2012年第3期5卷 300-307页

作者： Wang, Liu Liao, Lejian Li, Peng School of Computer Science Beijing Institute of Technology Beijing Key Lab. of Intelligent Information Beijing 100081 China

Web Question Answering (WQA) and Web Service (WS) are parallel fields in intelligent web computing. In network services, they are used widely, and they are rarely combined together. For many intelligent web applications, however, using them together tends to be important. This paper based on the study of significant techniques of WQA, WS and Hierarchical Task Network (HTN), including Natural Language processing (NLP), Web Service Ontology and a planner of HTN, gives a proposal of WQA framework. This framework combines NLP, predicate logic, Semantic Web description and an HTN planner-SHOP2, turning question answering into a planning problem by question mapping and service planning. It addresses a transition from natural language to semantic expression, composites web services dynamically by using SHOP2, and obtains the answering that meets customers' question by executing the web services sequence. Copyright © 2012 Inderscience Enterprises Ltd.

关键词： Web services

来源：评论

学校读者我要写书评

暂无评论

QT-based monitoring system of multi-functional laboratory

引用

Research Journal of Applied sciences, Engineering and technology 2012年第21期4卷 4480-4483页

作者： Xiaoling, Li Jimin, Yuan School of Computer Science and Technology Chengdu University Chengdu 610106 China Key University Key Laboratory of Pattern Recognition and Intelligent information Processing Sichuan Province China School of Computer Science and Technology Panzhihua University Panzhihua 617000 China

Regarding the embedded processor as the core, this study utilizes various cutting-edge technologies such as wireless LAN, USB interface, Bluetooth, multimedia, etc., to propose the design program of QT-based security monitoring system. Taking the lab environment in school as an example, this system has achieved the security monitoring, information transmission and control of certain equipment. Besides, it has cut the Linux kernel module reasonably and explored the touch screen, serial port, wireless LAN, Bluetooth, USB and other resources, thus realizing various functions, such as collection and processing of audio, video and security information and wireless communication. Thereby, users can carry out real-time monitoring for multiple locations through the wireless LAN. © Maxwell Scientific Organization, 2012.

关键词： Bluetooth

来源：评论

学校读者我要写书评

暂无评论

Irregular community discovery for cloud service improvement

Irregular community discovery for cloud service improvement

引用

作者： Liu, Jin Zhou, Jing Wang, Junfeng Zhang, Feng Liu, Fei State Key Lab. of Software Engineering Wuhan University Wuhan 430072 China Lab. of Complex Systems and Intelligence Science Institute of Automation CAS Beijing 100190 China State Key Lab. for Novel Software Technology Nanjing University Nanjing China School of Computer Science Communication University of China Beijing 100024 China Key Lab. of Intelligent Information Processing Institute of Computing Technology CAS Beijing 100190 China College of Computer Science Sichuan University Chengdu 610064 China Software School Sun Yat-sen University Guangzhou 510006 China

Utility services provided by cloud computing rely on virtual customer communities forming spontaneously and evolving continuously. Clarifying the explicit boundaries of these communities is thus essential to the quality of utility services in cloud computing. Communities with overlapping features or prominent peripheral vertexes are usually typical irregular communities. Traditional community identification algorithms are limited in discovering irregular topological structures from CR networks, whereas these irregular shapes typically play an important role in finding prominent customers which are ignored in social CRM otherwise. We present a novel method of discovering irregular communities. It firstly finds and merges primitive maximal cliques and the irregular features of overlapping and prominent sparse vertices are further considered. An empirical case and a methodology comparison confirm the feasibility and efficiency of our approach. © 2012 Springer science+Business Media, LLC.

关键词： Cloud computing

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

Fast template matching with partial skipping using sub-template

Fast template matching with partial skipping using sub-templ...

引用

2012 3rd IEEE/IET International Conference on Audio, Language and Image processing, ICALIP 2012

作者： Zhang, Qiao Gao, Huijie Kang, Zhen State Key Lab. of Multi-spectral Information Processing Technology Institute for Pattern Recognition and Artificial Intelligence Huazhong Univ. of Sci. and Tech. Wuhan 430074 China School of Mathematic and Computer Science Wuhan Polytechnic University Wuhan 430023 China

ISBN: (纸本)9781467301718

This paper presents a new fast template matching method with partial skipping using sub-template. In this method, we use sub-template to search point by point in the current searched window, and compare every SAD with threshold, if some SAD exceeds the threshold, set the new threshold equal to this SAD value and this point is one potential optimization location, when all points in the current window are compared, we will get a minimum value and a optimization location, then skip the other points whose SAD is not the minimum value. In other words, the searching step is that template size subtracts the subtemplate size, and we set the next threshold equal to the current optimization SAD value, we update the threshold and the optimal point until the end of the searched image like this, then will find the global minimum points and its SAD value. Experimental results show that the proposed method is near one hundred times faster than the conventional template match method. © 2012 IEEE.

关键词： Global optimization

来源：评论

学校读者我要写书评

暂无评论

Conservation laws for variable coefficient nonlinear wave equations with power nonlinearities

引用

Chinese Physics B 2011年第7期20卷 22-27页

作者：黄定江周水庚杨勤民 Department of Mathematics East China University of Science and Technology School of Computer Science Fudan University Shanghai Key Laboratory of Intelligent Information Processing Fudan University

Conservation laws for a class of variable coefficient nonlinear wave equations with power nonlinearities are investigated. The usual equivalence group and the generalized extended one including transformations which are nonlocal with respect to arbitrary elements are introduced. Then, using the most direct method, we carry out a classification of local conservation laws with characteristics of zero order for the equation under consideration up to equivalence relations generated by the generalized extended equivalence group. The equivalence with respect to this group and the correct choice of gauge coefficients of the equations play the major roles for simple and clear formulation of the final results.

关键词： nonlinear wave equations conservation laws equivalence group symmetries

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：