检索结果-内蒙古大学图书馆

Joint learning of preposition senses and semantic roles of prepositional phrases

Joint learning of preposition senses and semantic roles of p...

2009 Conference on Empirical Methods in Natural Language Processing, EMNLP 2009, Held in Conjunction with ACL-IJCNLP 2009

作者： Dahlmeier, Daniel Tou Ng, Hwee Schultz, Tanja NUS Graduate School for Integrative Sciences and Engineering Singapore Department of Computer Science National University of Singapore Singapore Cognitive Systems Lab. University of Karlsruhe Germany

The sense of a preposition is related to the semantics of its dominating prepositional phrase. Knowing the sense of a preposition could help to correctly classify the semantic role of the dominating prepositional phrase and vice versa. In this paper, we propose a joint probabilistic model for word sense disambiguation of prepositions and semantic role labeling of prepositional phrases. Our experiments on the PropBank corpus show that jointly learning the word sense and the semantic role leads to an improvement over state-of-the-art individual classifier models on the two tasks. © 2009 ACL and AFNLP.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

cognitive learning and the multimodal memory game: Toward human-level machine learning

Cognitive learning and the multimodal memory game: Toward hu...

引用

International Joint Conference on Neural Networks (IJCNN)

作者： Byoung-Tak Zhang School of Computer Science and Engineering and Graduate Programs in Cognitive Science Brain Science and Bioinformatics Seoul National University Seoul South Korea

Machine learning has made great progress during the last decades and is being deployed in a wide range of applications. However, current machine learning techniques are far from sufficient for achieving human-level intelligence. Here we identify the properties of learners required for human-level intelligence and suggest a new direction of machine learning research, i.e. the cognitive learning approach, that takes into account the recent findings in brain and cognitive sciences. In particular, we suggest two fundamental principles to achieve human-level machine learning: continuity (forming a lifelong memory continuously) and glocality (organizing a plastic structure of localized micromodules connected globally). We then propose a multimodal memory game as a research platform to study cognitive learning architectures and algorithms, where the machine learner and two human players question and answer about the scenes and dialogues after watching the movies. Concrete experimental results are presented to illustrate the usefulness of the game and the cognitive learning framework for studying human-level learning and intelligence.

关键词： Games Machine learning Humans Motion pictures Machine learning algorithms Joints Chemistry

来源：评论

学校读者我要写书评

暂无评论

Development of a virtual needle biopsy simulation system for the virtual prostate

引用

Systems and computers in Japan 2006年第1期37卷 93-104页

作者： Deguchi, Daisuke Mori, Kensaku Mekada, Yoshito Hasegawa, Jun-Ichi Toriwaki, Jun-Ichiro Noguchi, Masanori Graduate School of Engineering Nagoya University Nagoya 464-8603 Japan School of Computer and Cognitive Sciences Chukyo University Toyota 470-0393 Japan School of Medicine Department of Urology Kurume University Kurume 830-0011 Japan Faculty of Information Science Chukyo University Graduate School of Information Science Nagoya University Leice IEEE Japanese Society of Biomedical Engineering Japanese Society of Medical Imaging Technology Japan Medical Image Engineering Society Computer-Assisted Diagnostics Society School of Life System Science and Technology IPSJ JSAI JSMEBE JAMIT CADM JSSF IEEE CS Chukyo University Nagoya University Information Processing Society Computer-Assisted Image Diagnostics Society Department of Urology Japanese Urological Association Japan Society of Clinical Oncology Japan Cancer Society Japanese Society of Endourology and ESWL European Urological Association American Urological Association

This paper discusses the virtual prostate needle biopsy system and the construction of the virtual prostate model, considering the actual distribution of prostate abnormalities. A needle biopsy simulation is performed for the constructed virtual prostate, and the actual biopsy procedure in the clinical situation is evaluated. The prostate needle biopsy is a histologic diagnosis procedure in which a sample is acquired from the prostate tissue by needle biopsy and is inspected under a microscope. In order to achieve reliable prostate needle biopsy, it is necessary to consider systematically and numerically the number of needles required, and their locations and insertion angles. For such a purpose, a system is developed in which a virtual prostate is constructed on a computer and the biopsy procedure is evaluated quantitatively by performing virtually the prostate needle biopsy. Furthermore, two different models are constructed, for the prostate with and without hypertrophy, based on the actual statistical distribution data for prostate abnormalities. Each model is partitioned into the peripheral zone and the transition zone. The constructed virtual prostate is input into the virtual needle biopsy simulation system, and three different systematic biopsy procedures actually used at clinical sites, and four different needle biopsy procedures, are experimentally evaluated. The experiments show that the insertion angle that maximizes the hit probability is not always the same as the insertion angle that maximizes cancer sample acquisition. It is evident that the proposed method can indicate a biopsy procedure which realizes a high hit probability with a small number of needles. © 2005 Wiley Periodicals, Inc.

关键词： Biopsy

来源：评论

学校读者我要写书评

暂无评论

Evaluation of a Japanese CFG derived from a syntactically annotated corpus with respect to dependency measures 5

Evaluation of a Japanese CFG derived from a syntactically an...

引用

5th Workshop on Asian Language Resources, ALR 2005 and 1st Symposium on Asian Language Resources Network, ALRN 2005

作者： Noro, Tomoya Koike, Chimato Hashimoto, Taiichi Tokunaga, Takenobu Tanaka, Hozumi Graduate School of Information Science and Engineering Tokyo Institute of Technology Tokyo Japan Graduate School of Science and Engineering Tokyo Institute of Technology Tokyo Japan School of Computer and Cognitive Sciences Chukyo University Nagoya Japan

Parsing is one of the important processes for natural language processing and, in general, a large-scale CFG is used to parse a wide variety of sentences. For many languages, a CFG is derived from a large-scale syntactically annotated corpus, and many parsing algorithms using CFGs have been proposed. However, we could not apply them to Japanese since a Japanese syntactically annotated corpus has not been available as of yet. In order to solve the problem, we have been building a large-scale Japanese syntactically annotated corpus. In this paper, we show the evaluation results of a CFG derived from our corpus and compare it with results of some Japanese dependency analyzers. © 2005 5th Workshop on Asian Language Resources, ALR 2005 and 1st Symposium on Asian Language Resources Network, ALRN 2005 - Proceedings. All rights reserved.

关键词： Syntactics

来源：评论

学校读者我要写书评

暂无评论

Methods for detecting multiple small nodules from 3D chest X-ray CT images

引用

Systems and computers in Japan 2005年第9期36卷 55-64页

作者： Hayase, Yosuke Mekada, Yoshito Mori, Kensaku Hasegawa, Jun-Ichi Toriwaki, Jun-Ichiro Mori, Masaki Natori, Hiroshi Graduate School of Engineering Nagoya University Nagoya 464-8603 Japan School of Computer and Cognitive Sciences Chukyo University Toyota 470-0393 Japan Sapporo-Kosei Hospital Sapporo 060-0033 Japan School of Medicine Sapporo Medical University Sapporo 060-8543 Japan Canon Ltd. School of Computational and Cognitive Science Chukyo University

This paper describes a method for detecting small nodules from 3D X-ray CT images, considering small nodules with CT values of at least -600 H.U. and diameters of at least 2 mm. The proposed method is largely composed of two stages. In the first stage, for the region obtained by the threshold processing, the shape feature parameters of the figure calculated from the distance values in the connected component are applied, and the initial nodule candidate regions are extracted by discriminating the nodule region and the vessel/bronchus region. In the second stage, a minimum directional difference filter in which the filter radius is adaptively adjusted according to the size of the initial nodule candidate region is applied in order to reduce the overextracted regions. The proposed method is applied to seven actual chest CT images (six pathological cases, including multiple nodules, and one normal case), and the result for 361 nodules with a CT value not less than -600 H.U. and diameter not less than 2 mm is that the number of overextracted regions per case is 7.4 on the average, when the detection rate is set as 71%. © 2005 Wiley Periodicals, Inc.

关键词： computerized tomography

来源：评论

学校读者我要写书评

暂无评论

RoboCup: Yesterday, today, and tomorrow workshop of the executive committee in Blaubeuren, october 2003 1

引用

7th Robot World Cup Soccer and Rescue Competitions and Conferences, RoboCup 2003

作者： Burkhard, Hans-Dieter Asada, Minoru Bonarini, Andrea Jacoff, Adam Nardi, Daniele Riedmiller, Martin Sammut, Claude Sklar, Elizabeth Veloso, Manuela Humboldt University Berlin BerlinD-10099 Germany Dept. of Adaptive Machine Systems Graduate School of Engineering Osaka University SuitaOsaka565-0871 Japan HANDAI Frontier Research Center Graduate School of Engineering Osaka University SuitaOsaka565-0871 Japan Department of Electronics and Information Politecnico di Milano Italy National Institute of Standards and Technology United States Dip. Informatica e Sistemistica Univ. "La Sapienza" Roma Italy Universtaet Osnabrueck Institute for Cognitive Science Albrechtstr. 28 D-49069 Germany School of Computer Science and Engineering University of New South Wales Sydney2052 Australia Dept. of Computer Science Columbia University 1214 Amsterdam Avenue MC 0401 New YorkNY10027-7003 United States Computer Science Department Carnegie Mellon University PittsburghPA15213-3890 United States

ISBN: (数字)9783540259404

ISBN: (纸本)3540224432

RoboCup has been known for the goal of “creating robots capable of beating the world cup in 2050.” Clearly, we stated this goal back in 1996 not as an exact scientific goal, but as an audacious challenge to pursue. We aimed at creating a far away target for RoboCup researchers, as we were well aware that the development of fully autonomous soccer robots capable of competing against human world champion soccer players was a rather long term research project.

关键词：

来源：评论

学校读者我要写书评

暂无评论

An improved method for generating virtual stretched view of stomach based on shape deformation

引用

International Congress Series 2001年第C期1230.0卷 447-453页

作者： Mori, K. Hoshino, Y. Suenaga, Y. Toriwaki, J. Hasegawa, J. Katada, K. Department of Computational Science and Engineering Graduate School of Engineering Nagoya University Nagoya 464-8603 Furo-cho Chikusa-ku Japan School of Computer and Cognitive Sciences Chukyo University Toyota Aichi 470-0393 101 Kaizu-cho Tokodachi Japan School of Health Sciences Fujita Health University Aichi 470-1192 Dengakugakubo Kutsukake Toyoake Japan

In this paper, we describe an improved method for generating a virtual stretched image of the stomach based on shape deformation. In observing large cavity organs, such as the stomach, a flattened view of the organs would be very useful in diagnosis. The proposed method generates a virtual stretched image by deforming a 3-D gray image. We generate a polygon model consisting of a set of triangular patches that approximates the global shape of the stomach (approximating shape). An original 3-D image is deformed by using the corresponding relationship between the cut and flattened shapes of the approximating shape. We can obtain a flattened view (virtual pathological specimen) from the deformed image. The proposed method was applied to eight cases of 3-D abdominal CT images. Experimental results showed that the proposed method can effectively generate a flattened view of the organ. © 2001 Elsevier science B.V.

关键词： Stomach Unraveling Virtual pathology Virtual stretched view

来源：评论

学校读者我要写书评

暂无评论

Vision expert system 3D-IMPRESS for automated construction of three dimensional image processing procedures 7

Vision expert system 3D-IMPRESS for automated construction o...

引用

7th International Conference on Virtual Systems and Multimedia, VSMM 2001

作者： Zhou, Xiang-Rong Shimizu, A. Hasegawa, J. Toriwaki, J. Hara, T. Fujita, H. Virtual System Laboratory Gifu University Gifu-shi501-1193 Japan Graduate School of Bio-Applications and Systems Engineering Tokyo University of Agriculture and Technology Tokyo184-8588 Japan School of Computer and Cognitive Sciences Chukyo University Toyota-shi470-0393 Japan Department of Information Engineering Nagoya University Nagoya-shi464-8603 Japan Department of Information Science Gifu University Gifu-shi501-1193 Japan

ISBN: (纸本)0769514022

In this paper a three dimensional (3D) image processing expert system called 3D-IMPRESS is presented. This system can automatically construct a 3D image processing procedure by using pairs of an original input image and a desired output figure called sample figure given by a user This paper describes the outline of 3D-IMPRESS and presents a method of procedure consolidation for generating a procedure commonly applicable to some other 3D gray images. Finally, we show segmentation results of 3D chest CT images by using the procedures generated by 3D-IMPRESS and discuss the performance of the system. © 2001 IEEE.

关键词： Expert systems

来源：评论

学校读者我要写书评

暂无评论

Vision expert system 3D-IMPRESS for automated construction of three dimensional image processing procedures

Vision expert system 3D-IMPRESS for automated construction o...

引用

International Conference on Virtual Systems and MultiMedia

作者： Xiang-Rong Zhou A. Shimizu J. Hasegawa J. Toriwaki T. Hara H. Fujita Virtual System Laboratory Gifu University Gifu Japan Graduate School of Bio-Applications and Systems Engineering Tokyo University of Agriculture and Technology Tokyo Japan School of Computer and Cognitive Sciences Chukyo University Toyota Japan Department of Information Engineering University of Nagoya Nagoya Japan Department of Information Science Gifu University Gifu Japan

ISBN: (纸本)0769514022

关键词： Machine vision Expert systems Image processing Computed tomography Agricultural engineering Image segmentation Laboratories Systems engineering and theory Agriculture Biomedical engineering

来源：评论

学校读者我要写书评

暂无评论

Automated labeling of bronchial branches in virtual bronchoscopy system 1st

引用

1st International Conference on Medical Image Computing and computer-Assisted Intervention, MICCAI 1998

作者： Mori, Kensaku Hasegawa, Jun-Ichi Suenaga, Yasuhito Toriwaki, Jun-Ichiro Anno, Hirofumi Katada, Kazuhiro Dept of Computational Science and Engineering Graduate School of Engineering Nagoya University Furo-cho Chikusa-ku NagoyaAichi464-8603 Japan School of Computer and Cognitive Sciences Chukyo University 101 Tokodachi Kaizu-cho ToyotaAichi470-0348 Japan Dept of Information Engineering Graduate School of Engineering Nagoya University Furo-cho Chikusa-ku NagoyaAichi464-8603 Japan School of Health Sciences Fujita Health University Dengakugakubo Kutsukake-cho ToyoakeAichi470-1192 Japan

ISBN: (纸本)3540651365

This paper proposes a method for automated labeling of bronchia] branches in virtual bronchoscopy system. Anatomical names of bronchial branches are assigned basing upon a set of rules. If it is possible to assign the anatomical names to bronchial branches extracted from CT images by the computer and is possible to display the name of the currently observed branch on a virtual bronchoscopy image, it will help us to understand the current observing position. The proposed method constructs the knowledge base of anatomical names of bronchial branches. Tree structure of bronchus region is extracted from CT image. Labeling is performed by comparing tree structure information of the extracted bronchus with information of the branches described in the knowledge base. We implemented the proposed method with the virtual bronchoscopy system and obtained satisfactorily result. © Springer-Verlag Berlin Heidelberg 1998.

关键词： computerized tomography

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：