检索结果-内蒙古大学图书馆

The mental state formalism of GMU-BICA

International Journal of Machine Consciousness 2009年第1期1卷 111-130页

作者： Samsonovich, Alexei V. De Jong, Kenneth A. Kitsantas, Anastasia Computer Science Department Krasnow Institute for Advanced Study George Mason University 4400 University Drive Fairfax VA 22030-4444 United States College of Education and Human Development George Mason University MS 4B3 4400 University Drive Fairfax VA 22030-4444 United States

GMU-BICA, the biologically-inspired self-aware cognitive architecture developed at George Mason University, continues to be a useful prototype for various intelligent artifacts, including intelligent tutoring systems, yet the underlying formalism of mental states used in its design was never described in detail. The present theoretical work aims at filling this gap, focusing on the top cognitive level (mental states) and leaving detailed description of the lower level (schemas), as well as non-declarative components, for future publications. Among the distinguishing features of the GMU-BICA mental state formalism are: (i) a subject-centered view of the world, (ii) the multiplicity of mental perspectives simultaneously represented in working memory, each playing its unique functional role, and (iii) the limited span of awareness. This model is consistent with human psychology and gives testable predictions. The work explains, through analysis of examples, how the framework can be used to build computational models of self-regulated learning, and why in this case it is expected to unleash a new for artifacts power of human-like cognition and learning. © 2009 World Scientific Publishing Company.

关键词： computer aided instruction

来源：评论

学校读者我要写书评

暂无评论

Extractive speech summarization by active learning

Extractive speech summarization by active learning

引用

IEEE Workshop on Automatic Speech Recognition and Understanding

作者： Justin Jian Zhang Ricky Ho Yin Chan Pascale Fung Human Language Technology Center Department of Electronic and Computer Engineering Hong Kong University of Science and Technology Hong Kong China

ISBN: (纸本)9781424454785

In this paper, we propose an active learning approach for feature-based extractive summarization of lecture speech. Most state-of-the-art speech summarization systems are trained by using a large amount of human reference summaries. Active learning targets to minimize human annotation efforts by automatically selecting a small amount of unlabeled examples for labeling. Our method chooses the unlabeled examples according to a combination of informativeness criterion and robustness criterion. Our summarization results show an increasing learning curve of ROUGE-L F-measure, from 0.44 to 0.54, consistently higher than that of using randomly chosen training samples. We also show that, by following the rhetorical structure in presentation slides, it is possible for humans to produce "gold standard" reference summaries with very high inter-labeler agreement.

关键词： humans Labeling Data mining Stability Reproducibility of results Natural languages Guidelines Speech analysis Supervised learning Training data

来源：评论

学校读者我要写书评

暂无评论

Adaptive regularization of weight vectors 09

Adaptive regularization of weight vectors

引用

Proceedings of the 23rd International Conference on Neural Information Processing Systems

作者： Koby Crammer Alex Kulesza Mark Dredze Department of Electrical Enginering The Technion Haifa Israel Department of Computer and Information Science University of Pennsylvania Philadelphia PA Human Language Tech. Center of Excellence Johns Hopkins University Baltimore MD

ISBN: (纸本)9781615679119

We present AROW, a new online learning algorithm that combines several useful properties: large margin training, confidence weighting, and the capacity to handle non-separable data. AROW performs adaptive regularization of the prediction function upon seeing each new instance, allowing it to perform especially well in the presence of label noise. We derive a mistake bound, similar in form to the second order perceptron bound, that does not assume separability. We also relate our algorithm to recent confidence-weighted online learning techniques and show empirically that AROW achieves state-of-the-art performance and notable robustness in the case of non-separable data.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Recognizing textual entailment: Rational, evaluation and approaches

引用

Natural language Engineering 2009年第4期15卷 i-xvii页

作者： Dagan, Ido Dolan, Bill Magnini, Bernardo Roth, Dan Department of Computer Science Bar Ilan University Ramat Gan 52900 Israel Natural Language Processing Group Microsoft Research One Microsoft Way Redmond WA 98005 United States Human Language Technologies Research Unit Fondazione Bruno Kessler Via Sommarive 18 38050 Povo - Trento Italy Department of Computer Science University of Illinois at Urbana-Champaign IL United States

The goal of identifying textual entailment whether one piece of text can be plausibly inferred from another has emerged in recent years as a generic core problem in natural language understanding. Work in this area has been largely driven by the PASCAL Recognizing Textual Entailment (RTE) challenges, which are a series of annual competitive meetings. The current work exhibits strong ties to some earlier lines of research, particularly automatic acquisition of paraphrases and lexical semantic relationships and unsupervised inference in applications such as question answering, information extraction and summarization. It has also opened the way to newer lines of research on more involved inference methods, on knowledge representations needed to support this natural language understanding challenge and on the use of learning methods in this context. RTE has fostered an active and growing community of researchers focused on the problem of applied entailment. This special issue of the JNLE provides an opportunity to showcase some of the most important work in this emerging area. © 2009 Cambridge University Press.

关键词： Knowledge representation

来源：评论

学校读者我要写书评

暂无评论

Fostering students' participation in face-to-face interactions and deepening their understanding by integrating personal and shared spaces

Fostering students' participation in face-to-face interactio...

引用

作者： Yamaguchi, Etsuji Inagaki, Shigenori Sugimoto, Masanori Kusunoki, Fusako Deguchi, Akiko Takeuchi, Yuichiro Seki, Takao Tachibana, Sanae Yamamoto, Tomokazu Faculty of Education and Culture University of Miyazaki Japan Graduate School of Human Science and Environment Kobe University Japan Department of Electrical Engineering and Information Systems Graduate School of Engineering University of Tokyo Japan Department of Information Design Faculty of Art and Design Tama Art University Japan Faculty of Education Utsunomiya University Japan Sony Computer Science Laboratories Inc. Japan Fukui Prefectural School for the Deaf Japan Sumiyoshi Elementary School Attached Faculty of Human Development Kobe University Japan

ISBN: (纸本)3642032699

In this research, we introduced CarettaKids into the social context of a classroom environment to evaluate whether integration of personal and shared spaces can help promote students' participation in synchronous/co-located interactions in the classroom and deepen their understanding of subject matter. Analysis of videotaped interactions and pre- and posttests clarified the following three points. (1) Students who used CarettaKids presented the simulation results and rules for object arrangement they worked out individually in their respective personal space, by using CarettaKids' function of projecting object arrangements and simulation results from a personal digital assistant onto a sensing board. (2) Many of the students who used CarettaKids examined individually generated ideas collaboratively in the shared space. The patterns of collaborative examination are: (a) Induce a rule for object arrangement from object arrangements devised in personal spaces;(b) Deduce a new object arrangement from the rules discovered in the personal spaces;and (c) Refine the rules discovered in the personal spaces through group discussion. (3) Students who used CarettaKids not only considered all of the three factors, i.e. residential area, industrial area and forest area, but also understood relations between these factors, thereby deepening their understanding of city planning that takes environmental and financial aspects into consideration. We suggest that the degree to which students deepen their understanding is affected by the presence or absence of collaborative examination of individually generated ideas in the shared space. © 2009 Springer Berlin Heidelberg.

关键词： Students

来源：评论

学校读者我要写书评

暂无评论

A phrase-level piecewise linear scaling algorithm for melody match in Query-by-Humming systems

A phrase-level piecewise linear scaling algorithm for melody...

引用

IEEE International Conference on Multimedia and Expo (ICME)

作者： Wenxiao Cao Danning Jiang Jue Hou Yong Qin Thomas Fang Zheng Yi Liu Center of Speech and Language Technologies Division of Technical Innovation and Development Tsinghua National Laboratory of Information Science and Technology Department of Computer Science and Technology Tsinghua University Beijing China IBM China Research Laboratory Beijing China

The Query-by-Humming (QBH) system allows users to retrieve songs by singing/humming. In this paper we propose a phrase-level piecewise linear scaling algorithm for melody match. Musical phrase boundaries are predicted for the query to split it to phrases. The boundaries of melody fragment corresponding to each phrase are allowed for adjusting in a limited scope. The algorithm employs Dynamic Programming and Recursive Alignment to search for the minimal piecewise matching cost upon Linear Scaling at phrase-level. Our experimental results on 5223 melody database show that the proposed algorithm outperforms traditional algorithms. The proposed algorithm gives significant improvements of 17.0%, 14.7% and 4.8% with respect to Linear Scaling, Dynamic Time Wrapping and Recursive Alignment in top-1 rate, respectively. The results show that the proposed algorithm is more efficient than the previous algorithms.

关键词： Piecewise linear techniques Rhythm Natural languages Dynamic programming Costs Heuristic algorithms Databases Speech Technological innovation Laboratories

来源：评论

学校读者我要写书评

暂无评论

Effectiveness of n-gram fast match for query-by-humming systems

Effectiveness of n-gram fast match for query-by-humming syst...

引用

IEEE International Conference on Multimedia and Expo (ICME)

作者： Jue Hou Dan-ning Jiang Wen-xiao Cao Yong Qin Thomas Fang Zheng Yi Liu Center of Speech and Language Technologies Division of Technology Innovation and Development Tsinghua National Laboratory of Information Science and Technology Department of Computer Science and Technology Tsinghua University Beijing China IBM China Research Laboratory Beijing China

To achieve a good balance between matching accuracy and computation efficiency is a key challenge for query-by-humming (QBH) system. In this paper, we propose an approach of n-gram based fast match. Our n-gram method uses a robust statistical note transcription as well as error compensation method based on the analysis of frequent transcription errors. The effectiveness of our approach has been evaluated on a relatively large melody database with 5223 melodies. The experimental results show that when the searching space was reduced to only 10% of the whole size, 90% of the target melodies were preserved in the candidates, and 88% of the match accuracy of system was kept. Meanwhile, no obvious additional computation was applied.

关键词： Databases Computational efficiency Degradation Robustness Speech Natural languages Technological innovation Laboratories Information science computer science

来源：评论

学校读者我要写书评

暂无评论

Vision based environment recognition and movement control for autonomous wheeled mobile robots

Vision based environment recognition and movement control fo...

引用

IEEE International Conference on Mechatronics and Automation

作者： Gen'ichi Yasuda Bin Ge Department of Human and Computer Intelligence Nagasaki Institute of Applied Science Nagasaki Japan Liao Ning Key Laboratory of Intelligent Information Processing Economic & Technical Development Zone Dalian University Dalian China

This paper presents an experimental study on environment recognition and movement control for multiagent robotic soccer using wheeled mobile robots. A color image segmentation method based on YUV color information of each pixel of the color image is applied to the object recognition. The color image segmentation is performed using the tables that transform each value in a pixel to membership in several color classes, where the lower and higher threshold values of Y, U, and V are determined and described for the sample color markers. The position of objects on the field is efficiently and accurately calculated using a monocular camera. A common image processing method is used to detect landmarks such as corners/edges in the environment. A movement control algorithm is implemented based on the distance and orientation to the target. Experimental results of real-time movement control are also presented.

关键词： Mobile robots Robot vision systems Color Image processing Wheels Cameras Control systems Object recognition Image segmentation Pixel

来源：评论

学校读者我要写书评

暂无评论

Recent development of the HMM-based speech synthesis system (HTS)

Recent development of the HMM-based speech synthesis system ...

引用

Asia-Pacific Signal and Information Processing Association 2009 Annual Summit and Conference, APSIPA ASC 2009

作者： Zen, Heiga Oura, Keiichiro Nose, Takashi Yamagishi, Junichi Sako, Shinji Toda, Tomoki Masuko, Takashi Black, Alan W. Tokuda, Keiichi Department of Computer Science Nagoya Institute of Technology Nagoya 466-8555 Japan Department of Information Processing Interdisciplinary Tokyo Institute of Technology Yokohama 226-8502 Japan Centre for Speech Technology Research University of Edinburgh Edinburgh EH8-9LW United Kingdom Graduate School of Information Science Nara Institute of Science and Technology Ikoma 630-0192 Japan Language Technologies Institute Carnegie Mellon University Pittsburgh PA 15213 United States Cambridge Research Laboratory Toshiba Research Europe Limited Cambridge CB4 0GZ United Kingdom Corporate Research and Development Center Toshiba Corporation Kawasaki 212-8582 Japan

A statistical parametric approach to speech synthesis based HMMs has grown in popularity over the last few years. In this approach, spectrum, excitation, and duration of speech are simultaneously modeled by context-dependent HMMs, and speech waveforms are generated from the HMMs themselves. Since December 2002, we have publicly released an opensource software toolkit named "HMM-based speech synthesis system (HTS)" to provide a research and development toolkit for statistical parametric speech synthesis. This paper describes recent developments of HTS in detail, as well as future release plans.

关键词： Speech synthesis

来源：评论

学校读者我要写书评

暂无评论

Pinyin-indexed method for approximate matching in Chinese

引用

Qinghua Daxue Xuebao/Journal of Tsinghua University 2009年第SUPPL. 1期49卷 1328-1332页

作者： Cao, Jiang Wu, Xiaojun Xia, Yunqing Zheng, Fang Department of Computer Science and Technology Tsinghua University Beijing 100084 China Center for Speech and Language Technologies Division of Technical Innovation and Development Tsinghua National Laboratory for Information Science and Technology Beijing 100084 China

The exact matching of keywords is key to popular commercial search engines. A Chinese approximate matching method with an index structure was developed to achieve better retrieval when the input contains errors. Three types of similarity measurement between two Chinese strings were developed based on the character edit-distance, the Pinyin edit-distance and the Pinyin improved edit-distance. The similarity measurements were used to expand the user's query so that the approximate matching task can be represented as several exact matching sub-tasks. The results of these exact matchings are merged and sorted by their similarity to the original query. Tests on a webpage text database gave a 50.4% recall rate with the Pinyin improved edit-distance with a 60.4% precision with a small increase in time and space complexity.

关键词： Search engines

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：