检索结果-内蒙古大学图书馆

1st Workshop on High-Performance Computing for the Semantic Web 2011, HPCSW 2011 - Co-located with the 8th Extended Semantic Web Conference, ESWC 2011

作者： Assel, Matthias Cheptsov, Alexey Czink, Blasius Damljanovic, Danica Quesada, Jose HLRS - High Performance Computing Center Stuttgart University of Stuttgart Nobelstrasse 19 70569 Stuttgart Germany Department of Computer Science Natural Language Processing Group University of Sheffield Regent Court 211 Portobello S1 4DP Sheffield United Kingdom Center for Adaptive Behavior and Cognition Max Planck Institute for Human Development Lentzeallee 94 14195 Berlin Germany

With billions of triples in the Linked Open Data cloud, which continues to grow exponentially, very challenging tasks begin to emerge related to the exploitation of large-scale reasoning. A considerable amount of work has been done in the area of using Information Retrieval methods to address these problems. However, although applied models work on Web scale, they downgrade the semantics contained in an RDF graph by observing each physical resource as a 'bag of words (URIs/literals)'. Distributional statistic methods can address this problem by capturing the structure of the graph more efficiently. However, these methods are continually confronting with efficiency and scalability problems on serial computing architectures due to their computational complexity. In this paper, we describe a parallelization algorithm of one such method (Random Indexing) based on the Message-Passing Interface (MPI), that enables efficient utilization of high performance parallel computers. Our evaluation results show significant performance improvement.

关键词： Message passing

来源：评论

学校读者我要写书评

暂无评论

Reliable accent specific unit generation with dynamic Gaussian mixture selection for multi-accent speech recognition

Reliable accent specific unit generation with dynamic Gaussi...

引用

IEEE International Conference on Multimedia and Expo (ICME)

作者： Chao Zhang Yi Liu Yunqing Xia Thomas Fang Zheng Jesper Olsen JiLei Tian Department of Computer Science and Technology Tsinghua University Beijing China Center of Speech and Language Technologies Division of Technology Innovation and Development Tsinghua National Laboratory for Information Science and Technology Beijing China Nokia Research Center Beijing China

Multiple accents are often present in Mandarin speech, as most Chinese have learned Mandarin as a second language. We propose generating reliable accent specific unit together with dynamic Gaussian mixture selection for multi-accent speech recognition. Time alignment phoneme recognition is used to generate such unit and to model accent variations explicitly and accurately. Dynamic Gaussian mixture selection scheme builds a dynamical observation density for each specified frame in decoding, and leads to use Gaussian mixture component efficiently. This method increases the covering ability for a diversity of accent variations in multi-accent, and alleviates the performance degradation caused by pruned beam search without augmenting the model size. The effectiveness of this approach is evaluated on three typical Chinese accents Chuan, Yue and Wu. Our approach outperforms traditional acoustic model reconstruction approach significantly by 6.30%, 4.93% and 5.53%, respectively on Syllable Error Rate (SER) reduction, without degrading on standard speech.

关键词： Acoustics Reliability speech Hidden Markov models speech recognition Decoding Adaptation models

来源：评论

学校读者我要写书评

暂无评论

Unsupervised word sense disambiguation using neighborhood knowledge

PACLIC 25 - Proceedings of the 25th Pacific Asia Conference ...

引用

PACLIC 25 - Proceedings of the 25th Pacific Asia Conference on language, Information and Computation 2011年 333-342页

作者： Heyan, Huang Zhizhuo, Yang Ping, Jian Beijing Engineering Applications Research Center of High Volume Language Information Processing and Cloud Computing Beijing Institute of Technology No.5 Yard Zhong Guan Cun South Street Haidian District Beijing 100081 China Department of Computer Science Beijing Institute of Technology No.5 Yard Zhong Guan Cun South Street Haidian District Beijing 100081 China

ISBN: (纸本)9784905166023

Usually ambiguous words contained in article appear several times. Almost all existing methods for unsupervised word sense disambiguation make use of information contained only in ambiguous sentence. This paper presents a novel approach by considering neighborhood knowledge. The approach can naturally make full use of the within-sentence relationship from the ambiguous sentence and cross-sentence relationship from the neighborhood knowledge. Experimental results indicate the proposed method can significantly outperform the baseline method. © 2011 by Huang Heyan, Yang Zhizhuo, Jian Ping.

关键词： Information use

来源：评论

学校读者我要写书评

暂无评论

Jointly modeling WSD and SRL with markov logic

Jointly modeling WSD and SRL with markov logic

引用

23rd International Conference on Computational Linguistics, Coling 2010

作者： Che, Wanxiang Liu, Ting Research Center for Information Retrieval MOE-Microsoft Key Laboratory of Natural Language Processing and Speech School of Computer Science and Technology China

Semantic role labeling (SRL) and word sense disambiguation (WSD) are two fundamental tasks in natural language processing to find a sentence-level semantic representation. To date, they have mostly been modeled in isolation. However, this approach neglects logical constraints between them. We therefore exploit some pipeline systems which verify the automatic all word sense disambiguation could help the semantic role labeling and vice versa. We further propose a Markov logic model that jointly labels semantic roles and disambiguates all word senses. By evaluating our model on the OntoNotes 3.0 data, we show that this joint approach leads to a higher performance for word sense disambiguation and semantic role labeling than those pipeline approaches.

关键词： Pipelines

来源：评论

学校读者我要写书评

暂无评论

Improving semantic role labeling with word sense

Improving semantic role labeling with word sense

引用

"2010 Human language Technologies Conference ofthe North American Chapter of the Association for Computational Linguistics, NAACL HLT 2010"

作者： Che, Wanxiang Liu, Ting Li, Yongqiang Research Center for Information Retrieval MOE-Microsoft Key Laboratory of Natural Language Processing and Speech School of Computer Science and Technology 150001 China

ISBN: (纸本)1932432655

Semantic role labeling (SRL) not only needs lexical and syntactic information, but also needs word sense information. However, because of the lack of corpus annotated with both word senses and semantic roles, there is few research on using word sense for SRL. The release of OntoNotes provides an opportunity for us to study how to use word sense for SRL. In this paper, we present some novel word sense features for SRL and find that they can improve the performance significantly. © 2010 Association for Computational Linguistics.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Regression-class tree based method for efficient speaker identification

Regression-class tree based method for efficient speaker ide...

引用

作者： Wang, Gang Wu, Xiaojun Zheng, Thomas Fang Wang, Linlin Zhang, Chenhao Department of Computer Science and Technology Center for Speech and Language Technologies Tsinghua University Beijing 100084 China

In this paper an efficient speaker identification (SpkID) method is proposed. In GMM-based speaker recognition, the model training and the likelihood score computations are very time-consuming and therefore have been bottlenecks of SpkID applications under the requirement of fast recognition especially in case of a large population of target speakers. A method, based on regression-class tree (RCT) structural UBM which is similar to a kind of sorted tree, is proposed and can apparently speed up the training and recognition of GMM-UBM based SpkID system. A number of components of the UBM can be pruned and their likelihood scores can be easily calculated using a kind of regression method. Experimental results show that the proposed method can improve the computational efficiency by 3.5 times for training and 15.3 times for recognition with only slight identification performance degradation.

关键词： Computational efficiency

来源：评论

学校读者我要写书评

暂无评论

HYPOTHESIS RANKING AND TWO-PASS APPROACHES FOR MACHINE TRANSLATION SYSTEM COMBINATION

HYPOTHESIS RANKING AND TWO-PASS APPROACHES FOR MACHINE TRANS...

引用

IEEE International Conference on Acoustics, speech, and Signal processing

作者： Damianos Karakos Jason Smith Sanjeev Khudanpur Center for Language and Speech Processing Department of Electrical and Computer Engineering Johns Hopkins University Baltimore MD 21218 Center for Language and Speech Processing Department of Computer Science Johns Hopkins University Baltimore MD 21218

ISBN: (纸本)9781424442959

Given a number of machine translations of a source segment, the goal of system combination is to produce a new translation that has better quality than all of them. This paper describes a number of improvements that were recently added to the JHU system combination scheme: (i) A hypothesis ranking technique which orders the system outputs, on a per-segment basis, according to predicted translation quality, thus improving a subsequent incremental combination step. (ii) A two-pass combination procedure, which first produces several combination outputs with the given translations, and then performs one more combination step with these new outputs. Results from the NIST MT09 informal system combination evaluation on Arabic-to-English and Urdu-to-English show that both approaches offer significant BLEU and TER gains over a baseline JHU combination scheme.

关键词： Machine Translation System Combination Confusion Network Decoding Hypothesis Ranking

来源：评论

学校读者我要写书评

暂无评论

A FACS validated 3D human facial model 10

A FACS validated 3D human facial model

引用

Proceedings of the SSPNET 2nd International Symposium on Facial Analysis and Animation

作者： Cosker, Darren Krumhuber, Eva Hilton, Adrian Department of Computer Science University of Bath United Kingdom Swiss Center for Affective Sciences University of Geneva Switzerland Center for Vision Speech and Signal Processing University of Surrey United Kingdom

ISBN: (纸本)9781450305228

The Facial Action Coding System (FACS) [Ekman et al. 2002] has become a popular reference for creating fully controllable facial models that allow the manipulation of single actions or so-called Action Units (AUs). For example, realistic 3D models based on FACS have been used for investigating the perceptual effects of moving faces, and for character expression mapping in recent movies. However, since none of the facial actions (AUs) in these models are validated by FACS experts it is unclear how valid the model would be in situations where the accurate production of an AU is essential [Krumhuber and Tamarit 2010]. Moreover, previous work has employed motion capture data representing only sparse 3D facial positions which does not include dense surface deformation detail.

关键词： computer keyboards

来源：评论

学校读者我要写书评

暂无评论

Perception of linear and nonlinear motion properties using a FACS validated 3D facial model 10

Perception of linear and nonlinear motion properties using a...

引用

7th Annual Symposium on Applied Perception in Graphics and Visualization, APGV 2010

作者： Cosker, Darrene Krumhuber, Eva Hilton, Adrian Department of Computer Science University of Bath United Kingdom Swiss Center for Affective Sciences University of Geneva Switzerland Centre for Vision Speech and Signal Processing University of Surrey United Kingdom

ISBN: (纸本)9781450302487

In this paper we present the first Facial Action Coding System (FACS) valid model to be based on dynamic 3D scans of human faces for use in graphics and psychological research. The model consists of FACS Action Unit (AU) based parameters and has been independently validated by FACS experts. Using this model, we explore the perceptual differences between linear facial motions - represented by a linear blend shape approach - and real facial motions that have been synthesized through the 3D facial model. Through numerical measures and visualizations, we show that this latter type of motion is geometrically nonlinear in terms of its vertices. In experiments, we explore the perceptual benefits of nonlinear motion for different AUs. Our results are insightful for designers of animation systems both in the entertainment industry and in scientific research. They reveal a significant overall benefit to using captured nonlinear geometric vertex motion over linear blend shape motion. However, our findings suggest that not all motions need to be animated nonlinearly. The advantage may depend on the type of facial action being produced and the phase of the movement. © 2010 ACM.

关键词： Animation

来源：评论

学校读者我要写书评

暂无评论

Multi-layered features with SVM for Chinese accent identification

Multi-layered features with SVM for Chinese accent identific...

引用

2010 International Conference on Audio, language and Image processing, ICALIP 2010

作者： Hou, Jue Liu, Yi Zheng, Thomas Fang Olsen, Jesper Tian, Jilei Center for Speech and Language Technologies Division of Technology Innovation and Development Tsinghua National Laboratory for Information Science and Technology Beijing China Department of Computer Science and Technology Tsinghua University Beijing China Nokia Research Center Beijing China

ISBN: (纸本)9781424458653

In this paper, we propose an approach of multilayered feature combination associated with support vector machine (SVM) for Chinese accent identification. The multi-layered features include both segmental and suprasegmental information, such as MFCC and pitch contour, to capture the diversity of variations in Chinese accented speech. The pitch contour is estimated using cubic polynomial method to model the variant characters in different accents in Chinese. We train two GMM acoustic models in order to express the features of a certain accent. As the original criterion of the GMM model cannot deal with such multi-layered features, the SVM is utilized to make the decision. The effectiveness of the proposed approach was evaluated on the 863 Chinese accent corpus. Our approach yields a significant 10% relative error rate reduction compared with traditional approaches using sole feature at single level in Chinese accented speech identification. ©2010 IEEE.

关键词： Support vector machines

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：