检索结果-内蒙古大学图书馆

51st Annual Meeting of the Association for Computational Linguistics, ACL 2013

作者： Jiang, Wenbin Sun, Meng Lü, Yajuan Yang, Yating Liu, Qun Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences China Multilingual Information Technology Research Center Xinjiang Technical Institute of Physics and Chemistry Chinese Academy of Sciences China Centre for Next Generation Localisation Faculty of Engineering and Computing Dublin City University Ireland

ISBN: (纸本)9781937284503

Structural information in web text provides natural annotations for NLP problems such as word segmentation and parsing. In this paper we propose a discriminative learning algorithm to take advantage of the linguistic knowledge in large amounts of natural annotations on the Internet. It utilizes the Internet as an external corpus with massive (although slight and sparse) natural annotations, and enables a classifier to evolve on the large-scaled and real-time updated web text. With Chinese word segmentation as a case study, experiments show that the segmenter enhanced with the Chinese wikipedia achieves significant improvement on a series of testing sets from different domains, even with a single classifier and local features. © 2013 Association for Computational Linguistics.

关键词： Learning algorithms

来源：评论

学校读者我要写书评

暂无评论

An Entity Answer Ranking Method Based on MLNs

An Entity Answer Ranking Method Based on MLNs

引用

2013年中国智能自动化学术会议

作者： Fangqiong Chen Zhengtao Yu Jianyi Guo Tao Shen Yantuan Xian The School of Information Engineering and Automation Kunming University of Science and Technology The Intelligent Information Processing Key Laboratory Kunming University of Science and Technology

For the characteristics of factoid and list answers in domain Q&A system,we built a ranking model combined with multiple features of domain entity answers based on *** method uses predicate formulas to describe the relevant features of the questions-candidate answers and the answersknowledge base,merging these features into Markov Logic Network,and then adopting discriminant training learning algorithm to learn the weights of feature parameters,which can give different weights according to the relevance of different features,finally it use MC-SAT algorithm reasoning to get the relevance of questions and answers,realize the answer *** show that the proposed method can greatly improve the answer precision and recall rates compared with other methods.

关键词： Question-answering system Markov logic network Learning to rank Multiple features

来源：评论

学校读者我要写书评

暂无评论

Protein-Protein Interaction Extraction Based on Convex Combination Kernel Function

Protein-Protein Interaction Extraction Based on Convex Combi...

引用

2013 Conference on Artificial Intelligence and Data Mining(AIDM 2013);2013 Business Economics and Investment Conference(BEI 2013);2013 Water Pollution and Treatment Conference(WPT 2013)

作者： Peng Chen Jianyi Guo Zhengtao Yu Sichao Wei Feng Zhou Xin Yan The School of Information Engineering and Automation Kunming University of Science and Technology Key Laboratory of Intelligent Information Processing Kunming University of Science and Technology

Owing to the effect of classified models was different in Protein-Protein Interaction (PPI) extraction,which was made by different single kernel functions,and only using single kernel function hardly trained the optimal classified model to extract PPI,this paper presents a strategy to find the optimal kernel function from a kernel function *** strategy is that in the kernel function set which consists of different single kernel functions,endlessly finding the last two kernel functions on the performance in PPI extraction,using their optimal kernel function to replace them,until there is only one kernel function and it's the final optimal kernel ***,extracting PPI using the classified model made by this kernel *** paper conducted the PPI extraction experiment on AIMed corpus,the experimental result shows that the optimal convex combination kernel function this paper presents can effectively improve the extraction performance than single kernel function,and it gets the best precision which reaches 65.0 among the similar PPI extraction systems.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Stem translation with affix-based rule selection for agglutinative languages

Stem translation with affix-based rule selection for aggluti...

引用

51st Annual Meeting of the Association for Computational Linguistics, ACL 2013

作者： Wangt, Zhiyang Lü, Yajuan Sun, Meng Liu, Qun Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences P.O. Box 2704 Beijing 100190 China Centre for Next Generation Localisation Faculty of Engineering and Computing Dublin City University Ireland

ISBN: (纸本)9781937284510

Current translation models are mainly designed for languages with limited morphology, which are not readily applicable to agglutinative languages as the difference in the way lexical forms are generated. In this paper, we propose a novel approach for translating agglutinative languages by treating stems and affixes differently. We employ stem as the atomic translation unit to alleviate data spare-ness. In addition, we associate each stem-granularity translation rule with a distribution of related affixes, and select desirable rules according to the similarity of their affix distributions with given spans to be translated. Experimental results show that our approach significantly improves the translation performance on tasks of translating from three Turkic languages to Chinese. © 2013 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

Optimal pricing for improving efficiency of taxi systems

Optimal pricing for improving efficiency of taxi systems

引用

23rd International Joint Conference on Artificial Intelligence, IJCAI 2013

作者： Gan, Jiarui An, Bo Wang, Haizhong Sun, Xiaoming Shi, Zhongzhi Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences Beijing 100190 China State Key Laboratory of Computer Architecture Institute of Computing Technology Chinese Academy of Sciences Beijing 100190 China University of Chinese Academy of Sciences Beijing 100049 China Oregon State University Corvallis OR 97331 United States

ISBN: (纸本)9781577356332

In Beijing, most taxi drivers intentionally avoid working during peak hours despite of the huge customer demand within these peak periods. This dilemma is mainly due to the fact that taxi drivers' congestion costs are not reflected in the current taxi fare structure. To resolve this problem, we propose a new pricing scheme to provide taxi drivers with extra incentives to work during peak hours. This differs from previous studies of taxi market by considering market variance over multiple periods, taxi drivers' profit-driven decisions, and their scheduling constraints regarding the interdependence among different periods. The major challenge of this research is the computational intensiveness to identify optimal strategy due to the exponentially large size of a taxi driver's strategy space and the scheduling constraints. We develop an atom schedule method to overcome these issues. It reduces the magnitude of the problem while satisfying the constraints to filter out infeasible pure strategies. Simulation results based on real data show the effectiveness of the proposed methods, which opens up a new door to improving the efficiency of taxi market in megacities (e.g., Beijing).

关键词： Traffic congestion

来源：评论

学校读者我要写书评

暂无评论

Protein-Protein Interaction Extraction Based on Convex Combination Kernel Function

引用

Journal of Computer and Communications 2013年第5期1卷 9-13页

作者： Peng Chen Jianyi Guo Zhengtao Yu Sichao Wei Feng Zhou Xin Yan The School of Information Engineering and Automation Kunming University of Science and Technology Kunming China Key Laboratory of Intelligent Information Processing Kunming University of Science and Technology Kunming China.

Owing to the effect of classified models was different in Protein-Protein Interaction(PPI) extraction, which was made by different single kernel functions, and only using single kernel function hardly trained the optimal classified model to extract PPI, this paper presents a strategy to find the optimal kernel function from a kernel function set. The strategy is that in the kernel function set which consists of different single kernel functions, endlessly finding the last two kernel functions on the performance in PPI extraction, using their optimal kernel function to replace them, until there is only one kernel function and it’s the final optimal kernel function. Finally, extracting PPI using the classified model made by this kernel function. This paper conducted the PPI extraction experiment on AIMed corpus, the experimental result shows that the optimal convex combination kernel function this paper presents can effectively improve the extraction performance than single kernel function, and it gets the best precision which reaches 65.0 among the similar PPI extraction systems.

关键词： Protein-Protein Interaction Support Vector Machine Convex Combination Kernel Function

来源：评论

学校读者我要写书评

暂无评论

ROBUST MULTI-PATCH TRACKING

ROBUST MULTI-PATCH TRACKING

引用

IEEE International Conference on Image processing

作者： Shanxin Yuan Jun Miao Laiyun Qing Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences Beijing 100190 China

ISBN: (纸本)9781479923427

In this paper, we propose a robust and fast multi-patch visual tracking algorithm within the Bayesian inference framework. The target template is initialized by selecting the object in the first frame manually and dividing it into small patches. For one certain frame, target candidates are sampled with the state transition model. Each candidate is divided into patches in the same way as the target template. By comparing the candidate's patches with the corresponding template patches, we can get the candidate's likelihood. The tracking result is the candidate which Maximum a Posteriori estimation. After that, tracking is continued using the Bayesian state inference and template update. Our approach can handle appearance variation, occlusion, illumination change, scale variation, rotation and cluttered background. The tracker is fast and performs favorably against several state-of-the-art trackers on challenging sequences.

关键词： Visual tracking Bayesian inference multi-patch fast robust Bayesian inference visual tracking Fasting jigs(templates) tracking Maximum a posteriori estimation Robustness Patches State Change candidate species

来源：评论

学校读者我要写书评

暂无评论

EMPLOYING PLSA MODEL AND MAX-BISECTION FOR REFINING IMAGE ANNOTATION

EMPLOYING PLSA MODEL AND MAX-BISECTION FOR REFINING IMAGE AN...

引用

IEEE International Conference on Image processing

作者： Dongping Tian Wenbo Zhang Xiaofei Zhao Zhongzhi Shi The Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences Beijing 100190 China

ISBN: (纸本)9781479923427

We present a new method for refining image annotation by fusing probabilistic latent semantic analysis (PLSA) with max-bisection (MB). We first construct a PLSA model with asymmetric modalities to estimate the posterior probabilities of each annotating keyword for an image, and then a label similarity graph is built by a weighted linear combination of label similarity and visual similarity. Followed by the rank-two relaxation heuristics over the constructed label graph is employed to further mine the correlation of the keywords so as to capture the refining annotation, which plays a critical role in semantic based image retrieval. The novelty of our method mainly lies in two aspects: exploiting PLSA to accomplish the initial semantic annotation task and implementing max-bisection based on the rank-two relaxation algorithm over the weighted label graph to refine the candidate annotations generated by the PLSA. We evaluate our method on the standard Corel dataset and the experimental results are competitive to several state-of-the-art approaches.

关键词： Refining image annotation PLSA EM max-bisection image retrieval image retrieval images ANNOTATIONS Refining labelled graph Line graph Linear Combination Purification keyWORD

来源：评论

学校读者我要写书评

暂无评论

Pharmaceutical semantic database query mechanism based on keywords

Pharmaceutical semantic database query mechanism based on ke...

引用

7th Chinese Semantic Web Symposium and the 2nd Chinese Web ScienceConference, CSWS 2013

作者： Sun, Juan Gu, Jinguang Huang, Zhisheng Computer Science and Technology Wuhan University of Science and Technology Wuhan 430065 China Hubei Province Key Laboratory of Intelligent Information Processing and Realtime Industrial System Wuhan 430065 China Department of Computer Science Vrije University of Amsterdam 1081hv Amsterdam Netherlands

ISBN: (纸本)9783642540240

With the development of the Internet, Semantic search technology has been applied to various fields. In the pharmaceutical field, because of the huge number and wide range of the drugs on the market, an effective semantic retrieval system can bring great convenience for doctors. However, for doctors who have no background knowledge of semantic technologies, to write formal semantics search statement is still very difficult. Therefore, this paper proposes a pharmaceutical semantic database query mechanism which based on keywords. In this query mechanism, by analysis of ontology database and establishment of Chinese - English translation mapping, we can Transform Chinese keywords into English keywords. Then match the English keywords with ontology database to build a list of triples. And finally, formed Corresponding SPARQL query by analyze the list. © Springer-Verlag Berlin Heidelberg 2013.

关键词： Database systems

来源：评论

学校读者我要写书评

暂无评论

Surprise simulation using fuzzy logic 1

引用

9th International Conference on intelligent Computing, ICIC 2013

作者： Qiao, Rui Zhong, Xiuqin Yang, Shihan He, Heng College of Computer Science and Technology Wuhan University of Science and Technology Wuhan China Intelligent Information Processing and Real-time Industrial System Hubei Province Key Laboratory Wuhan China College of Computer Science and Engineering University of Electronic Science and Technology of China Chengdu China College of Information Sciences and Engineering Guangxi University for Nationalities Nanning China

ISBN: (数字)9783642394829

ISBN: (纸本)9783642394812

Emotional agents are useful to variety of computer application. This paper focuses on the emotion surprise. Surprise is the automatic reaction to a mismatch, which plays an important role in the behaviors of intelligent agents. We represent psychology theories of surprise through a fuzzy inference system, as fuzzy logic helps to capture the fuzzy and complex nature of emotions. The system takes four factors related to surprise as inputs and the degree of surprise as output. We put forward fuzzy inference rules and reasoning parameters for the system. The results of the inference can be used in single or multi-agent system simulation. © 2013 Springer-Verlag.

关键词： Fuzzy inference

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：