检索结果-内蒙古大学图书馆

PACLIC 24 - Proceedings of the 24th Pacific Asia Conference on Language, information and Computation 2010年 61-61页

作者： Liu, Qun Liu, Yang Mi, Haitao Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences Beijing 100190 China

ISBN: (纸本)9784905166009

Syntax-based statistical translation model is proved to be better than phrasebased model, especially for language pairs with very different syntax structures, such as Chinese and English. In this talk I will introduce a serial of statistical translation models based on source syntax structure. The tree-based model uses the one best syntax tree for translation. The forest-based model uses a compact forest which encodes exponential number of syntax trees in a polynomial spaces and lead to better performance. The joint parsing and translation model produces source parse trees, using the source side of the translation rules instead of separate parsing rules, and generate translations on the target side simultaneously, which outperforms the forest-based model. Some extensions of these models are introduced also. © 2010 by Qun Liu, Yang Liu, and Haitao Mi.

关键词： Syntactics

来源：评论

学校读者我要写书评

暂无评论

A domain-specific question answering system based on ontology and question templates

A domain-specific question answering system based on ontolog...

引用

11th ACIS International Conference on Software Engineering, Artificial Intelligence, Networking and Parallel/Distributed computing, SNPD2010

作者： Wang, D.S. Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences China Graduate University of the Chinese Academy of Sciences Beijing China Department of Computer Science Jiangsu University of Science and Technology Zhenjiang China

ISBN: (纸本)9780769540887

The rapid growth in the development of Internet-based information systems increases the demand for natural language interfaces that are easy to set up and maintain. Unfortunately, the problem of deep understanding natural language queries is far from being solved. In this paper, an automated question answering system based on domain ontology and question template is proposed, which does not need deep understanding of user's questions. Ontology was employed to model the interesting domain, and properties of concepts are described by a collection of question templates. The system captures a user's intention by matching his questions to predefined templates, and return answers corresponding to template's query focus. The system has been applied to mobile service consulting area, and experimental results show that the system has high practicability as well as maintainability. © 2010 IEEE.

关键词： Ontology

来源：评论

学校读者我要写书评

暂无评论

A dynamic description logic based system for video event detection

引用

Frontiers of Electrical and Electronic Engineering in China 2010年第2期5卷 137-142页

作者： Xiaofeng WANG Liang CHANG Zhixin LI Zhongzhi SHI The Key Laboratory of Intelligent Information Processing Institute of Computing TechnologyChinese Academy of SciencesBeijing 100190China Graduate University of Chinese Academy of Sciences Beijing 100049China School of Computer and Control Guilin University of Electronic TechnologyGuilin 541004China

Video event detection is an important research area *** the video event is a key problem in video event *** this paper,we combine dynamic description logic with linear time temporal logic to build a logic system for video event *** proposed logic system is named as LTD_(ALCO)which can represent and inference the static,dynamic and temporal knowledge in one uniform logic *** on the LTD_(ALCO),a framework for video event detection is *** video event detection framework can automatically obtain the logic description of video content with the help of ontology-based computer vision techniques and detect the specified video event based on satisfiability checking on LTD_(ALCO)formulas.

关键词： video event semantics dynamic description logics reasoning ontology

来源：评论

学校读者我要写书评

暂无评论

The ICT Statistical Machine Translation System for IWSLT 2010 7

The ICT Statistical Machine Translation System for IWSLT 201...

引用

7th International Workshop on Spoken Language Translation, IWSLT 2010

作者： Xiong, Hao Xie, Jun Yu, Hui Liu, Kai Luo, Wei Mi, Haitao Liu, Yang Lü, Yajuan Liu, Qun Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences No.6 Kexueyuan South Road Haidian District P.O. Box 2704 Beijing100080 China

This paper illustrates the ICT Statistical Machine Translation system used in the evaluation campaign of the International Workshop on Spoken Language Translation 2010. We participate in the DIALOG tasks for Chinese-to-English and English-to-Chinese translation respectively. For both tasks, our system has achieved significant improvement with several effective methods as follows: 1) refining the data preprocessing, including Chinese word segmentation, named entity recognition, etc. 2) reducing the number of Out-of-Vocabulary(OOV) on the final test set by applying a fuzzy matching strategy. 3) considering generating a better input for the decoder from the N-best lists of ASR output as a special kind of translation task for the ASR task. 4) improving the performance of every single decoder, and reranking the n-best list for the final results submitted. © IWSLT 2010. All rights reserved.

关键词： Computer aided language translation

来源：评论

学校读者我要写书评

暂无评论

A sample pre-mapping method enhancing boosting for object detection

A sample pre-mapping method enhancing boosting for object de...

引用

International Conference on Pattern Recognition

作者： Ren, Haoyu Hong, Xiaopeng Heng, Cher-Keng Liang, Luhong Chen, Xilin Key Lab. of Intelligent Information Processing of Chinese Academy of Sciences Institute of Computing Technology CAS China School of Computer Science and Technology Harbin Institute of Technology Panasonic Singapore Laboratories Pte Ltd.

ISBN: (纸本)9780769541099

We propose a novel method to improve the training efficiency and accuracy of boosted classifiers for object detection. The key step of the proposed method is a sample pre-mapping on original space by referring to the selected 'reference sample' before feeding into weak classifiers. The reference sample corresponds to an approximation of the optimal separating hyper-plane in an implicit high-dimensional space, so that the resulting classifier could achieve the performance similar to kernel method, while spending the computation cost of linear classifier in both training and detection. We employ two different non-linear mappings to verify the proposed method under boosting framework. Experimental results show that the proposed approach achieves performance comparable with the common-used methods on public datasets in both pedestrian detection and car detection. © 2010 IEEE.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

Skin color weighted disparity competition for hand segmentation from stereo camera

Skin color weighted disparity competition for hand segmentat...

引用

2010 21st British Machine Vision Conference, BMVC 2010

作者： Wang, Qi Chen, Xilin Gao, Wen Key Lab. of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences Beijing China Institute of Digital Media School of EE and CS Peking University Beijing China

ISBN: (纸本)1901725405

Hand segmentation is the basis of many vision-based hand gesture applications in human computer interaction (HCI). This paper proposes a novel method of skin color weighted disparity competition to incorporate the skin color and depth cues for hand segmentation in clutter environment from stereo camera. The basic idea is that the hand disparity will be apparently different from most of the background disparities. Note that we refer to the scene except the user as the background. The proposed method validates a hand pixel by verifying whether the pixel satisfies the disparity limit of the hand more than of the background. Its novelty lies in incorporating the skin color probability to weight the disparity competition to improve the robustness of validation and the accuracy of boundary location. Experiments demonstrate the efficiency of the proposed method. © 2010. The copyright of this document resides with its authors.

关键词： Pixels

来源：评论

学校读者我要写书评

暂无评论

From use case model to service model: An environment ontology based approach

From use case model to service model: An environment ontolog...

引用

International Conference on Grid and Cloud computing

作者： Zhao, Bin Cai, Guangjun Jin, Zhi Key Lab. of Intelligent Information Processing Institute of Computing Technology CAS Graduate University of the Chinese Academy of Sciences Beijing China Software Engineering Institute Peking University Beijing China

ISBN: (纸本)9780769543130

One fundamental problem in services computing is how to bridge the gap between business requirements and various heterogeneous IT services. This involves eliciting business requirements and building a solution accordingly by reusing available services. While the business requirements are commonly elicited through use cases and scenarios, it is not straightforward to transform the use case model into a service model, and the existing manual approach is cumbersome and error-prone. In this paper, the environment ontology, which is used to model the problem space, is utilized to facilitate the model transformation process. The environment ontology provides a common understanding between business analysts and software engineers. The required software functionalities as well as the available services' capabilities are described using this ontology. By semi-automatically matching the required capability of each use case to the available capabilities provides by services, a use case is realized by that set of services. At the end of this paper, a fictitious case study was used to illustrate how this approach works. © 2010 IEEE.

关键词： Ontology

来源：评论

学校读者我要写书评

暂无评论

Entity answer extraction of web table

Entity answer extraction of web table

引用

2010 7th International Conference on Fuzzy Systems and Knowledge Discovery, FSKD 2010

作者： Xu, Yangbo Yu, Zhengtao Mao, Cunli Wang, Yasheng Guo, Jianyi School of Information Engineering and Automation Kunming University of Science and Technology Kunming 650051 China Institute of Intelligent Information Processing Computer Technology Application Key Laboratory of Yunnan Province Kunming 650051 China

ISBN: (纸本)9781424459346

This paper presents an entity answer extraction method based on list web table. Firstly, extract table from page using the features of web page table and label, segment the table that includes the potential entity answers by calculating the relevance of web table's title and query context, merge the table elements of each column according to table properties, and merge the web table's title with the merged elements of column again. Secondly, using merged passage as context of entity recognition, and recognize the entity for each element of the table, thus get the probability of the column elements belongs to the same type of entity answer, and locate the passages of entity answers and the entity answers. Finally, we conduct the experiment in the task of Entity Track of TREC2009. It turns out that the proposed method shows a very good result, the accuracy of entity answer extraction for web table has achieved 99.08%. ©2010 IEEE.

关键词： Websites

来源：评论

学校读者我要写书评

暂无评论

Visual information retrieval from 2D shapes by bipolar-matching

Visual information retrieval from 2D shapes by bipolar-match...

引用

IEEE International Conference on information Reuse and Integration (IRI)

作者： Yuqing Song Institute of Computing Technology Key Laboratory of Intelligent Information Processing Chinese Academy and Sciences China

One of the most challenging issues in visual information retrieval is retrieval by shape, due to a lack of mathematically rigorous definition of shape similarity. This paper presents a bipolar model for computing shape similarity. Given a discrete region, we cut its Voronoi diagram into two parts along the border of the region and each part is a tree. We use the two trees to respectively model the structures of a region and its complement, which is called the Bipolar Model. We prune the two trees by removing the nodes with small protrusions. The leaf nodes of the pruned trees are interleaved to make a leaf chain. Two regions are compared and matched, using a cyclic edit distance between the two leaf chains, with restricted merge and split operations allowed. We tested our algorithm on the MPEG-7 data set and made a “bullseye” score of 89.9%, which is the best performance ever reported.

关键词： Shape Electric shock Transform coding Computational modeling Nearest neighbor searches Classification algorithms Visualization

来源：评论

学校读者我要写书评

暂无评论

A level set based method of license plate localization

A level set based method of license plate localization

引用

IEEE International Conference on information Reuse and Integration (IRI)

作者： Yuqing Song Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy and Sciences China

This paper presents a robust and real time method of license plate localization based on level sets. The proposed algorithm consists of three steps: (1) medial axis transformation of selected level sets, (2) identification of sub-strokes, and (3) a multi-resolution window-based analysis for plate localization. Experiments show the effectiveness of our algorithm.

关键词： Level set Licenses Algorithm design and analysis Accuracy Skeleton Image segmentation Pixel

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：