检索结果-内蒙古大学图书馆

2004 human language Technology Conference of the North American Chapter of the Association for Computational Linguistics - Short Papers, HLT-NAACL 2004

作者： Zhai, Lufeng Fung, Pascale Schwartz, Richard Carpuat, Marine Wu, Dekai HKUST Human Language Technology Center Electrical and Electronic Engineering University of Science and Technology Clear Water Bay Hong Kong Hong Kong BBN Technologies 9861 Broken Land Parkway ColumbiaMD21046 United States HKUST Human Language Technology Center Department of Computer Science University of Science and Technology Clear Water Bay Hong Kong Hong Kong

ISBN: (纸本)1932432248

We present the first known result for named entity recognition (NER) in realistic large-vocabulary spoken Chinese. We establish this result by applying a maximum entropy model, currently the single best known approach for textual Chinese NER, to the recognition output of the BBN LVCSR system on Chinese Broadcast News utterances. Our results support the claim that transferring NER approaches from text to spoken language is a significantly more difficult task for Chinese than for English. We propose re-segmenting the ASR hypotheses as well as applying post-classification to improve the performance. Finally, we introduce a method of using n-best hypotheses that yields a small but nevertheless useful improvement NER accuracy. We use acoustic, phonetic, language model, NER and other scores as confidence measure. Experimental results show an average of 6.7% relative improvement in precision and 1.7% relative improvement in F-measure. © HLT-NAACL *** right reserved.

关键词： Speech recognition

来源：评论

学校读者我要写书评

暂无评论

N-fold Templated Piped Correction

N-fold Templated Piped Correction

引用

第一届自然语言处理联合学术会议

作者： Grace NGAI Marine CARPUAT Hong Kong Polytechnic University Department of Computing Kowloon Hong Kong Human Language Technology Center HKUST Department of Computer Science University of Science and Technology Clear Water Bay Hong Kong

We describe a broadly-applicable conservative error correcting model, N-fold Templated Piped Correction (NTPC), that consistently improves the accuracy of existing high-accuracy base models. Under circumstances where most obvious approaches actually reduce accuracy more than they improve it, NTPC nevertheless comes with little risk of accidentally degrading performance. NTPC is particularly well suited for natural language applications involving high-dimensional feature spaces, such as bracketing and disambiguation tasks, since its easily customizable templatedriven learner allows efficient search over the kind of complex feature combinations that have typically eluded the base models. We show empirically that NTPC yields small but consistent accuracy gains on top of even high-performing models like boosting. We also give evidence that the various extreme design parameters in NTPC are indeed necessary for the intended operating range, even though they diverge from usual practice.

关键词： N-fold Templated Piped Correction

来源：评论

学校读者我要写书评

暂无评论

A sequence alignment-independent method for protein classification

引用

Applied Bioinformatics 2004年第2-3期3卷 137-148页

作者： Vries, John K. Munshi, Rajan Tobi, Dror Klein-Seetharaman, Judith Benos, Panayiotis V. Bahar, Ivet Department of Molecular Genetics and Biochemistry School of Medicine University of Pittsburgh Pittsburgh PA United States Department of Pharmacology School of Medicine University of Pittsburgh Pittsburgh PA United States Language Technologies Institute Institute for Software Research International School of Computer Science Carnegie Mellon University Pittsburgh PA United States Department of Human Genetics Graduate School of Public Health University of Pittsburgh Pittsburgh PA United States Department of Molecular Genetics and Biochemistry School of Medicine University of Pittsburgh Pittsburgh PA 15213 200 Lothrop St United States

Annotation of the rapidly accumulating body of sequence data relies heavily on the detection of remote homologues and functional motifs in protein families. The most popular methods rely on sequence alignment. These include programs that use a scoring matrix to compare the probability of a potential alignment with random chance and programs that use curated multiple alignments to train profile hidden Markov models (HMMs). Related approaches depend on bootstrapping multiple alignments from a single sequence. However, alignment-based programs have limitations. They make the assumption that contiguity is conserved between homologous segments, which may not be true in genetic recombination or horizontal transfer. Alignments also become ambiguous when sequence similarity drops below 40%. This has kindled interest in classification methods that do not rely on alignment. An approach to classification without alignment based on the distribution of contiguous sequences of four amino acids (4-grams) was developed. Interest in 4-grams stemmed from the observation that almost all theoretically possible 4-grams (20⁴) occur in natural sequences and the majority of 4-grams are uniformly distributed. This implies that the probability of finding identical 4-grams by random chance in unrelated sequences is low. A Bayesian probabilistic model was developed to test this hypothesis. For each protein family in Pfam-A and PIR-PSD, a feature vector called a probe was constructed from the set of 4-grams that best characterised the family. In rigorous jackknife tests, unknown sequences from Pfam-A and PIR-PSD were compared with the probes for each family. A classification result was deemed a true positive if the probe match with the highest probability was in first place in a rank-ordered list. This was achieved in 70% of cases. Analysis of false positives suggested that the precision might approach 85% if selected families were clustered into subsets. Case studies indicated that

关键词：

来源：评论

学校读者我要写书评

暂无评论

Editorial

引用

Journal of Web Semantics 2004年第4期1卷 323-324页

作者： Katia Sycara John Mylopoulis Robotics Institute School of Computer Science Human-Computer Interaction Institute Language Technologies Institute (LTI) Center for Advanced Learning and Discovery Carnegie Mellon University Newell-Simon Hall 1602D CMU Pittsburgh PA 15213 USA Department of Computer Science University of Toronto 40 St. George St. Bahen Building Rm. 7266 Toronto Ont. Canada M5S 2E4

来源：评论

学校读者我要写书评

暂无评论

Design and Implementation of a Multinational computerized Patient Survey: The European Paediatric Orthopaedic Society Down Syndrome Survey

TheScientificWorldJournal

引用

TheScientificWorldJournal 2004年第1期4卷 256-263页

作者： David M Steinberg Moshe Kaplan Joav Merrick Shlomo Wientroub Department of Statistics and Operations Research Tel Aviv University Israel. School of Computer Science Tel Aviv University Israel. National Institute of Child Health and Human Development Office of the Medical Director Division for Mental Retardation Ministry of Social Affairs Jerusalem and Zusman Child Development Center and Divisions of Pediatrics and Community Health Ben Gurion University Beer-Sheva Israel. Department of Pediatric Orthopaedics Dana Children's Hospital Sourasky Medical Center Sackler School of Medicine Tel Aviv University Israel.

In 1997, the European Paediatric Orthopaedic Society (EPOS) initiated an international survey of musculoskeletal problems in individuals with Down syndrome. The goals of the study were far-reaching and ambitious in order to obtain a clear picture of the variety of orthopedic problems associated with Down syndrome, to relate their occurrence to other medical conditions, and to record and compare methods of treatment. The survey was to be international in scope, including orthopedic surgeons and departments across Europe and outside Europe. The study was coordinated from the Tel Aviv University in Israel as a multicenter study using electronic technology. This paper describes the organization and implementation of the EPOS Down Syndrome Survey, with special emphasis on the sophisticated electronic data entry instrument that was developed especially for the survey. It is concluded that computerized data entry forms like the one that we developed for the EPOS Down Syndrome Survey are valuable tools for medical surveys. They are especially important for multicenter and multinational studies.

关键词： Down syndrome Israel human development multinational computerized patient survey musculoskeletal problems pediatric orthopedics public health

来源：评论

学校读者我要写书评

暂无评论

Creating Coordination in the Cerebellum Catania, 2–4 October 2003

引用

The Cerebellum 2004年第1期3卷 39-64页

作者： Andjus, P. R. Zhu, L. Strata, P. Arata, A. Ito, M. Bearzatto, B. Servais, L. Baba-Aïssa, F. de Kerchove d’Exaerde, A. Schurmans, S. Cheron, G. Schiffmann, S. N. Bower, J. M. Devor, A. Burguière, E. Rutteman, M. De Zeeuw, C. I. Berthoz, A. Wiener, S. Rondi-Reig, L. Campana, A. Dusart, I. Wherlé, R. Weitzman, J. Yaniv, M. Sotelo, C. Mariani, J. Cavallari, P. Esposti, R. Cerri, G. Cerminara, N. L. Apps, R. Marple-Horvat, D. E. Wagstaff, J. Dan, B. Chorev, E. Manor, Y. Sohl, G. Willecke, K. Yarom, Y. Philipona, D. Dognin, E. Coenen, O. J. Sola, E. Prestori, F. Rossi, P. Taglietti, V. D’Angelo, E. De Filippi, G. Baldwinson, T. Sher, E. Ekerot, C. Jorntell, H. Fernández, G. Martínez, S. Gall, D. Roussel, C. Forti, L. Schiffmann, S. Gruol, D. L. Netzeband, J. G. Quina, L. A. Blakely Gonzalez, P. K. Hoebeek, F. E. Van Alphen, A. M. Schonewille, M. Frens, M. A. Goossens, H. H. L. M. Stahl, J. Ango, F. di Cristo, G. Hagashiyama, H. Bennett, V. Huang, Z. J. Jörntell, H. Ekerot, C.- F. Launey, T. Endo, S. Sakai, R. Harano, J. Lohof, A. M. Sherrard, R. M. Lu, H. Huang, C. Hartmann, M. J. Marshall, S. P. Lang, E. J. Michikawa, T. Mikoshiba, K. Nitschke, M. F. Erdmann, C. Melchert, U. Arp, T. Sprenger, A. Petersen, D. Kömpf, D. Binkofski, F. Heide, W. Pedroarena, C. Schwarz, C. Parsons, L. M. Schmahmann, J. D. Grill, S. E. Walker, M. S. Petacchi, A. Rokni, D. Saito, S. Kato, K. Sajdel-Sulkowska, E. M. Nguon, K. Selimi, F. Wang, Q. Cristea, I. Chait, B. Heintz, N. Serapide, M. F. Cicirata, F. De Saedeleer, C. Schwaller, B. Swinny, J. D. Ijkema-Paassen, J. Metzger, F. Kalicharan, D. Gramsbergen, A. van der Want, J. J. L. Slemmer, J. E. Weber, J. T. Winkelman, B. H. J. Chédotal, A. De Schutter, E. Maex, R. Koekkoek, S. K. E. Bouslama, L. Ghoumari, A. Ebner, T. Häusser, M. Hawkes, R. Herrup, K. Lisberger, S. G. Mugnaini, E. Nunzi, M. -G. Russo, M. Ptak, K. Orr, H. T. Zoghbi, H. Y. Rossi, F. Ruigrok, T. J. H. Sabel-Goedknegt, E. Simpson, J. I. Morando, L. Cesa, R. Dumoulin, A. Dieudonné, S. Dugué, G. Triller, A. Louvi, A. Alexandre, Department for Neuroscience University of Turin Italy Department of Physiology and Biochemistry School of Biology University of Belgrade Serbia & Montenegro Rita Levi Montalcini Center for Brain Repair Department of Neuroscience University of Turin Italy Laboratory for Memory and Learning Brain Science Institute Wako Saitama Japan Laboratory for Memory and Learning BSI (RIKEN) Japan Laboratory of Neurophysiology Université Libre de Bruxelles Campus Erasme Brussels Laboratory of Neurophysiology Université Mons-Hainaut Mons Belgium Laboratory of Electrophysiology Université Mons-Hainaut Mons Belgium Laboratory of Neurophysiology Université Libre de Bruxelles Brussels IRIBHM CP601 Université Libre de Bruxelles Campus Erasme Brussels Health Science Center The Research Imaging Center at The University of Texas San Antonio Cajal Neuroscience Research Center at the University of Texas San Antonio Biology UTSA San Antonio Research Imaging Center UTHSCSA San Antonio USA Massachusetts General Hospital Harvard Medical School NMR Center Charlestown USA CNRS-Collège de France LPPA Paris France Department of Neuroscience Erasmus University Rotterdam Rotterdam The Netherlands Department of Neuroscience Medical Faculty Erasmus MC Rotterdam The Netherlands CNRS-UMR 7102 Labo DVSN Paris Hôpital de la Salpêtrière INSERM U106 Paris France CNRS URA 1644 I. Pasteur Paris France Campus de San Juan Instituto de Neurociencias UMH-CSIC Alicante Group ‘Développement et Vieillissement du Système Nerveux’ UMR CNRS UniversitéP et M Curie Paris France University P& M Curie UMR CNRS St Bernard Paris France Dipartimento di Scienze Precliniche LITA-Vialba Universitd degli Studi Milano Italy Istituto di Fisiologia Umana II Universitd degli Studi Milano Italy Department of Physiology University of Bristol UK Centre for Biophysical and Clinical Research into Human Movement (CRM) Manchester Metropolitan University UK Department of Pediatrics and Department of Biochemistry and M

来源：评论

学校读者我要写书评

暂无评论

Extraction methods of voicing feature for robust speech recognition 8

Extraction methods of voicing feature for robust speech reco...

引用

8th European Conference on Speech Communication and Technology, EUROSPEECH 2003

作者： Zolnay, András Schlüter, Ralf Ney, Hermann Human Language Technology and Pattern Recognition Department of Computer Science VI RWTH Aachen - University of Technology Aachen52056 Germany

In this paper, three different voicing features are studied as additional acoustic features for continuous speech recognition. The harmonic product spectrum based feature is extracted in frequency domain while the autocorrelation and the average magnitude difference based methods work in time domain. The algorithms produce a measure of voicing for each time frame. The voicing measure was combined with the standard Mel Frequency Cepstral Coefficients (MFCC) using linear discriminant analysis to choose the most relevant features. Experiments have been performed on small and large vocabulary tasks. The three different voicing measures combined with MFCCs resulted in similar improvements in word error rate: improvements of up to 14% on the small-vocabulary task and improvements of up to 6% on the large-vocabulary task relative to using MFCC alone with the same overall number of parameters in the system.

关键词： Frequency domain analysis

来源：评论

学校读者我要写书评

暂无评论

A Stacked, Voted, Stacked Model for Named Entity Recognition 7

A Stacked, Voted, Stacked Model for Named Entity Recognition

引用

7th Conference on Natural language Learning, CoNLL 2003 at HLT-NAACL 2003

作者： Wu, Dekai Ngai, Grace Carpuat, Marine Human Language Technology Center HKUST Department of Computer Science University of Science and Technology Clear Water Bay Hong Kong Hong Kong Polytechnic University Department of Computing Kowloon Hong Kong

This paper investigates stacking and voting methods for combining strong classifiers like boosting, SVM, and TBL, on the named-entity recognition task. We demonstrate several effective approaches, culminating in a model that achieves error rate reductions on the development and test sets of 63.6% and 55.0% (English) and 47.0% and 51.7% (German) over the CoNLL-2003 standard baseline respectively, and 19.7% over a strong AdaBoost baseline model from CoNLL-2002. © 2003 Proceedings of the 7th Conference on Natural language Learning, CoNLL 2003 at HLT-NAACL 2003. All rights reserved.

关键词： Adaptive boosting

来源：评论

学校读者我要写书评

暂无评论

Experiences with the metacognitive skills inventory 33

Experiences with the metacognitive skills inventory

引用

Engineering as a human Endeavor: Partnering Community, Academia, Government, and Industry

作者： Miles, Don Blum, Toni Staats, Wayne J. Dean, David Department of Psychology College of Charleston Charleston SC Department of Psychology Stetson University DeLand FL Department of Computer Science College of Charleston Charleston SC Department of Human Development Teachers College Columbia University New York NY

ISBN: (纸本)0780379616

Despite the national surge in interest in technology fields, student performance measures continue to reveal that many students lack the analytical skills to complete college level courses in math and computer science. The development of tools for the measurement and enhancement of metacognitive skills will be examined. The primary measuring tool, the Metacognitive Skills Inventory, was designed to measure metacognitive abilities. The inventory consists of two subscales: Decomposition and Confidence. The Decomposition subscale measures the subjects' awareness and reported use of the critical problem solving steps. Examples are problem identification, planning of solution strategies, and comparison of these strategies. The Confidence subscale, measures the extent to which subjects are confident in their own problem solving ability. The inventory has been used in studies comparing student grades in college courses, problem solving skills at different levels in various college programs, and student performance on various tests. These tests include the SAT (both verbal and math), the MARS-R math anxiety scales, and the General Expectancy of Success Scale-Revised. The MSI is currently being used as an integral component of current research dealing with the development of training and education programs to increase metacognitive skills.

关键词： computer science

来源：评论

学校读者我要写书评

暂无评论

Applying Usability Engineering Methodology to Building a Search Agent for Web Applications

Applying Usability Engineering Methodology to Building a Sea...

引用

IPCC 2003 The Shape of Knowledge Proceedings: 2003 IEEE International Professional Communication Conference

作者： Chatterjee, Mousumi Grice, Roger A. Adali, Sibel Human-Computer Interaction Rensselaer Polytechnic Institute Troy NY United States Department of Language Faculty for Information Technology Rensselaer Polytechnic Institute Troy NY United States Department of Computer Science Rensselaer Polytechnic Institute Troy NY United States

A search agent was designed with a strong theoretical basis and tested for effectiveness with the community of users. The aim of this agent is to customize and adapt the user's entire experience with the interface according to individual needs. The agent was built in such a way that those who are not familiar with computers can rely on the tool in such a way that understandability, learnability and operability of the tool become easy.

关键词： Software agents

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：