检索结果-内蒙古大学图书馆

22nd International Conference on Computational Linguistics, Coling 2008

作者： He, Zhongjun Liu, Qun Lin, Shouxun Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences Beijing 100190 China Graduate University of Chinese Academy of Sciences Beijing 100049 China

ISBN: (纸本)9781905593446

This paper proposes a novel lexicalized approach for rule selection for syntax-based statistical machine translation (SMT). We build maximum entropy (MaxEnt) models which combine rich context information for selecting translation rules during decoding. We successfully integrate the MaxEnt-based rule selection models into the state-of-the-art syntax-based SMT model. Experiments show that our lexicalized approach for rule selection achieves statistically significant improvements over the state-of-the-art SMT system. © 2008 Licensed under the Creative Commons.

关键词： Computer aided language translation

来源：评论

学校读者我要写书评

暂无评论

Partial matching strategy for Phrase-based statistical machine translation

Partial matching strategy for Phrase-based statistical machi...

引用

46th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies, ACL-08: HLT

ISBN: (纸本)9781932432046

This paper presents a partial matching strategy for phrase-based statistical machine translation (PBSMT). Source phrases which do not appear in the training corpus can be translated by word substitution according to partially matched phrases. The advantage of this method is that it can alleviate the data sparseness problem if the amount of bilingual corpus is limited. We incorporate our approach into the state-of-the-art PBSMT systemMoses and achieve statistically significant improvements on both small and large corpora. © 2008 Association for Computational Linguistics.

关键词： Computer aided language translation

来源：评论

学校读者我要写书评

暂无评论

Probing Dynamical Character of Neural Circuits by Using Fuzzy Logic

引用

AIP Conference Proceedings 2008年第1期1060卷 160-165页

作者： Hong Hu Zhongzhi Shi Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Science Beijing 100080 China

Analytical study or designing of large‐scale nonlinear neural circuits, especially for chaotic neural circuits, is a difficult task. Here we analyze the function of neural systems by probing the fuzzy logical framework of the neural cells’ dynamical equations. In this paper, the fuzzy logical framework of neural cells is used to understand the nonlinear dynamic attributes of a common neural system, and we proved that if a neural system works in a non‐chaotic way, a suitable fuzzy logical framework can be found and we can analyze or design such kind neural system similar to analyze or design a digit computer, but if a neural system works in a chaotic way, an approximation is needed for understanding the function of such neural system.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Adaptive multiple feedback strategies for interactive video search

Adaptive multiple feedback strategies for interactive video ...

引用

2008 International Conference on Image and Video Retrieval, CIVR 2008

作者： Luan, Huanbo Zheng, Yantao Neo, Shi-Yong Zhang, Yongdong Lin, Shouxun Chua, Tat-Seng Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences Beijing 100080 China Graduate School Chinese Academy of Sciences Beijing 100039 China School of Computing National University of Singapore Singapore 117590 Singapore

ISBN: (纸本)9781605580708

In this paper, we propose adaptive multiple feedback strategies for interactive video retrieval. We first segregate interactive feedback into 3 distinct types (recall-driven relevance feedback, precision-driven active learning and locality-driven relevance feedback) so that a generic interaction mechanism with more flexibility can be performed to cover different search queries and different video corpuses. Our system facilitates expert searchers to flexibly decide on the types of feedback they want to employ under different situations. To cater to the large number of novice users (non-expert users), an adaptive option is built-in to learn the expert user behavior so as to provide recommendations on the next feedback strategy, leading to a more precise and personalized search for the novice users. Experimental results on TRECVID news video corpus demonstrate that our proposed adaptive multiple feedback strategies are effective. Copyright 2008 ACM.

关键词： Behavioral research

来源：评论

学校读者我要写书评

暂无评论

A hierarchical framework for movie content analysis: Let computers watch films like humans

A hierarchical framework for movie content analysis: Let com...

引用

2008 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops, CVPR Workshops

作者： Anan, Liu Sheng, Tang Yongdong, Zhang Yan, Song Jintao, Li Zhaoxuan, Yang Virtual Reality Laboratory Institute of Computing Technology Chinese Academy of Sciences Beijing 100190 China Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences Beijing 100190 China Department of Electronic Engineering Tianjin University Tianjin 300072 China

ISBN: (纸本)9781424423408

In this paper, we specially propose a hierarchical framework for movie content analysis. The purpose of our work is trying to realize computers' understanding for movie content, especially "Who, What, Where, How" which occur in the storyline by imitating human perception and cognition. The framework consists of two hierarchies. As for the low level part, we originally construct the human attention model with temporal information motivated by the Weber-Fechner Law to depict the variation of human perception in multiple modalities. As for the high level part, we focus on semantic understanding of different granularities of videos and simulate human cognition for movie content. Based on this hierarchical framework, we present its applications on semantic retrieval, video summarization and content filter. The promising results of users' subjective assessment indicate that the proposed framework is applicable for automatic analysis of movie content by computers. © 2008 IEEE.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Symmetrical Invariant LBP Texture Descriptor and Application for Image Retrieval

Symmetrical Invariant LBP Texture Descriptor and Application...

引用

Congress on Image and Signal processing, CISP

作者： Zhiping Shi Fei Ye Qing He Zhongzhi Shi Key Laboratory of Intelligent Information Processing Institute of Computing Technology CAS Beijing China

In this paper, we present a symmetrical invariant LBP (SILBP) texture descriptor based on the texture pattern equivalent, which is defined according to visual perception of textures. Then we extend the SILBP to linear SILBP. Our experiments on image retrieval show that the proposed texture discriptor has the advantages of symmetrical invariant, rotation robustness and computing simplicity.

关键词： Image retrieval Histograms Visual perception Robustness Humans Image texture Content based retrieval Wavelet transforms Signal processing information retrieval

来源：评论

学校读者我要写书评

暂无评论

The Data Selection Criteria for HSC and SVM Algorithms

The Data Selection Criteria for HSC and SVM Algorithms

引用

International Conference on Natural Computation (ICNC)

作者： Qing He Fuzhen Zhuang Zhongzhi Shi The Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences China

This paper makes a discussion of consistent subsets (CS) selection criteria for hyper surface Classification (HSC) and SVM algorithms. The consistent subsets play an important role in the data selection. Firstly, the paper proposes that minimal consistent subset for a disjoint cover set (MCSC) plays an important role in the data selection for HSC. The MCSC can be applied to select a representative subset from the original sample set for HSC. MCSC has the same classification model with the entire sample set and can totally reflect its classification ability. Secondly, the number of MCSC is calculated. Thirdly, by comparing the performance of HSC and SVM on corresponding CS, we argue that it is not reasonable that using the same train data set to train different classifiers and then testing the classifiers by the same test data set for different algorithms. The experiments show that algorithms can respectively select the proper data set for training, which ensures good performance and generalization ability. MCSC is the best selection for HSC, and support vector set is the effective selection for SVM.

关键词： Support vector machines Support vector machine classification Nearest neighbor searches Neural networks Testing Laboratories information processing Computers Helium Databases

来源：评论

学校读者我要写书评

暂无评论

Personalized event-based news video retrieval with dynamic user-log

Personalized event-based news video retrieval with dynamic u...

引用

IEEE International Conference on Multimedia and Expo (ICME)

作者： Ming Li Yantao Zheng Shi-Yong Neo Xiangdong Wang Sheng Tang Shou-Xun Lin School of Computing NUS Singapore Key Laboratory of Intelligent Information Processing ICT CAS China

Personalization especially in the domain of information retrieval is essentially important, as users might pose the same query even when they are searching for different information. It is thus necessary to create a retrieval engine which takes into consideration the dynamic information needs of different users. This paper presents our personalized news video retrieval engine, which exploits the individual userpsilas previous browsing history to customize and enhance their future search results. Specifically, the system utilizes the news topic hierarchy, a hierarchical news topic structure derived from unsupervised clustering on the news video corpus and event entities from news video and online news articles. We then dynamically project userpsilas browsing history onto this topic hierarchy to provide the basis for re-ranking relevant news videos. This system is tested on one month of TRECVID 2006 dataset consisting of 80 hours news video and found to return results in a more intuitive and personalized manner.

关键词： History Speech Visualization Search engines Speech recognition Explosions Streaming media

来源：评论

学校读者我要写书评

暂无评论

Transfer learning from multiple source domains via consensus regularization

Transfer learning from multiple source domains via consensus...

引用

17th ACM Conference on information and Knowledge Management, CIKM'08

作者： Luo, Ping Zhuang, Fuzhen Xiong, Hui Xiong, Yuhong He, Qing HP Labs China China Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences China Graduate University of Chinese Academy of Sciences China MSIS Department Rutgers University United States

ISBN: (纸本)9781595939913

Recent years have witnessed an increased interest in transfer learning. Despite the vast amount of research performed in this field, there are remaining challenges in applying the knowledge learnt from multiple source domains to a target domain. First, data from multiple source domains can be semantically related, but have different distributions. It is not clear how to exploit the distribution differences among multiple source domains to boost the learning performance in a target domain. Second, many real-world applications demand this transfer learning to be performed in a distributed manner. To meet these challenges, we propose a consensus regularization framework for transfer learning from multiple source domains to a target domain. In this framework, a local classifier is trained by considering both local data available in a source domain and the prediction consensus with the classifiers from other source domains. In addition, the training algorithm can be implemented in a distributed manner, in which all the source-domains are treated as slave nodes and the target domain is used as the master node. To combine the training results from multiple source domains, it only needs share some statistical data rather than the full contents of their labeled data. This can modestly relieve the privacy concerns and avoid the need to upload all data to a central location. Finally, our experimental results show the effectiveness of our consensus regularization learning. Copyright 2008 ACM.

关键词： Classification Consensus regularization Transfer learning

来源：评论

学校读者我要写书评

暂无评论

An Adaptive Travel Itinerary Selection Assistant under Fuzzy User Preferences

An Adaptive Travel Itinerary Selection Assistant under Fuzzy...

引用

2008 Conference on Human System Interactions (HSI 2008), vol.1

作者： Ruihong Shi Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences Beijing China

This paper presents a candidate-evaluation model (CEM) which interactively elicits user preferences and assists decision makers in decision making in applications such as travel itinerary planning. The CEM contrasts with traditional decision analytic and planning frameworks in which a complete user model is elicited beforehand or is constructed by a human expert. We used the CEM model to implement an Itinerary Selection Assistant (ISA) system, which helps tourists identify satisfactory travel itineraries. The ISA starts with fuzzy user preferences and gradually approximate the optimal solution through carefully choosing candidate solutions to present to the user and inferring user's actual preferences by analyzing user evaluations over the candidates.

关键词： Augmented weighted Tchebycheff programming Fuzzy user preferences Multi-attribute decision making Travel itinerary User modeling

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：