检索结果-内蒙古大学图书馆

46th Annual Meeting of the Association for Computational Linguistics: human language Technologies, ACL-08: HLT

作者： Elsayed, Tamer Oard, Douglas W. Namata, Galileo Department of Computer Science Human Language Technology Center of Excellence University of Maryland College Park MD 20742 United States University of Maryland College Park MD 20742 United States

ISBN: (纸本)9781932432046

This paper describes a computational approach to resolving the true referent of a named mention of a person in the body of an email. A generative model of mention generation is used to guide mention resolution. Results on three relatively small collections indicate that the accuracy of this approach compares favorably to the best known techniques, and results on the full CMU Enron collection indicate that it scales well to larger collections. © 2008 Association for Computational Linguistics.

关键词： Electronic mail

来源：评论

学校读者我要写书评

暂无评论

Estimating document frequencies in a speech corpus

Estimating document frequencies in a speech corpus

引用

2011 IEEE Workshop on Automatic Speech Recognition and Understanding, ASRU 2011

作者： Karakos, Damianos Dredze, Mark Church, Ken Jansen, Aren Khudanpur, Sanjeev Human Language Technology Center of Excellence Johns Hopkins University Baltimore MD United States Department of Electrical and Computer Engineering Johns Hopkins University Baltimore MD United States Department of Computer Science Johns Hopkins University Baltimore MD United States

ISBN: (纸本)9781467303675

Inverse Document Frequency (IDF) is an important quantity in many applications, including Information Retrieval. IDF is defined in terms of document frequency, df (w), the number of documents that mention w at least once. This quantity is relatively easy to compute over textual documents, but spoken documents are more challenging. This paper considers two baselines: (1) an estimate based on the 1-best ASR output and (2) an estimate based on expected term frequencies computed from the lattice. We improve over these baselines by taking advantage of repetition. Whatever the document is about is likely to be repeated, unlike ASR errors, which tend to be more random (Poisson). In addition, we find it helpful to consider an ensemble of language models. There is an opportunity for the ensemble to reduce noise, assuming that the errors across language models are relatively uncorrelated. The opportunity for improvement is larger when WER is high. This paper considers a pairing task application that could benefit from improved estimates of df. The pairing task inputs conversational sides from the English Fisher corpus and outputs estimates of which sides were from the same conversation. Better estimates of df lead to better performance on this task. © 2011 IEEE.

关键词： Random errors

来源：评论

学校读者我要写书评

暂无评论

Multi-class confidence weighted algorithms

Multi-class confidence weighted algorithms

引用

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

作者： Crammer, Koby Dredze, Mark Kulesza, Alex Department of Computer and Information Science University of Pennsylvania Philadelphia PA 19104 United States Human Language Technology Center of Excellence Johns Hopkins University Baltimore MD 21211 United States

The recently introduced online confidence-weighted (CW) learning algorithm for binary classification performs well on many binary NLP tasks. However, for multi-class problems CW learning updates and inference cannot be computed analytically or solved as convex optimization problems as they are in the binary case. We derive learning algorithms for the multi-class CW setting and provide extensive evaluation using nine NLP datasets, including three derived from the recently released New York Times corpus. Our best algorithm outperforms state-of-the-art online and batch methods on eight of the nine tasks. We also show that the confidence information maintained during learning yields useful probabilistic information at test time. © 2009 ACL and AFNLP.

关键词： Natural language processing systems

来源：评论

学校读者我要写书评

暂无评论

Meta-level Statistical Machine Translation 6

Meta-level Statistical Machine Translation

引用

6th International Joint Conference on Natural language Processing, IJCNLP 2013

作者： Ebrahimi, Sajad Meshgi, Kourosh Khadivi, Shahram Abady, Mohammad Ebrahim Shiri Ahmad Human Language Technology Lab Amirkabir University of Technology Tehran Iran Graduate School of Informatics Kyoto University Kyoto Japan Department of Computer Science Amirkabir University of Technology Tehran Iran

ISBN: (纸本)9784990734800

We propose a simple and effective method to build a meta-level Statistical Machine Translation (SMT), called meta-SMT, for system combination. Our approach is based on the framework of Stacked Generalization, also known as Stacking, which is an ensemble learning algorithm, widely used in machine learning tasks. First, a collection of base-level SMTs is generated for obtaining a meta-level corpus. Then a meta-level SMT is trained on this corpus. In this paper we address the issue of how to adapt stacked generalization to SMT. We evaluate our approach on English-to-Persian machine translation. Experimental results show that our approach leads to significant improvements in translation quality over a phrase-based baseline by about 1.1 BLEU points. © IJCNLP *** right reserved.

关键词： Machine translation

来源：评论

学校读者我要写书评

暂无评论

Effective fingerprint recognition approach based on double fingerprint thumb

Effective fingerprint recognition approach based on double f...

引用

International Conference on Current Research in computer science and Information Technology (ICCIT)

作者： Muzhir Shaban Al-Ani Tishko N. Muhamad Hersh A. Muhamad Ayub A. Nuri Department of Computer Science University of Human Development Sulaimania IRAQ

ISBN: (纸本)9781538629567

Many techniques are implemented to perform fingerprint recognition approach, and each technique based on specific criteria. The aim of this work is to find an efficient fingerprint recognition technique. This paper tries to offer a simple high performance approach to perform fingerprint recognition. This approach based on two main stages; the first one is the real data collection of human fingerprint samples and the second stage is concentrated on design and implementation of high performance fingerprint recognition approach. The implemented approach concentrated on the feature extraction part in which many levels of two dimensional discrete wavelet transform (2D-DWT) are used to generate high performance feature. This approach is implemented via mixing the features of both right hand thumb and left hand thumb. The results indicate that a good accuracy of recognition is obtained by this approach.

关键词： Fingerprint recognition Feature extraction Thumb Discrete wavelet transforms computer science

来源：评论

学校读者我要写书评

暂无评论

A note on the shift bound for cyclic codes by the DFT

A note on the shift bound for cyclic codes by the DFT

引用

作者： Zheng, Junru Kaida, Takayasu Department of Human Development Faculty of Human Sciences Kyushu Women's University Kitakyushu-shi 807-8586 Japan Department of Information and Computer Sciences Faculty of Humanity-Oriented Science and Engineering Kinki University Iizuka-shi 820-8555 Japan

For cyclic codes some well-known lower bounds and some decoding methods up to the half of the bounds are suggested. Particularly, the shift bound is a good lower bound of the minimum distance or cyclic codes, Reed-Muller codes and geometric Goppa codes. In this paper we consider cyclic codes defined by their defining set, and new simple derivation of the shift bound using the discrete Fourier transform with unknown elements and the Blahut theorem is shown. Moreover two examples of binary cyclic codes are given. Copyright © 2010.

关键词： Discrete Fourier transforms

来源：评论

学校读者我要写书评

暂无评论

Designing automated handheld navigation support 08

Designing automated handheld navigation support

引用

10th International Conference on human-computer Interaction with Mobile Devices and Services, MobileHCI 2008

作者： Uluca, Doguhan Streefkerk, Jan Willem Sciacchitano, Brian McCrickard, D. Scott Product Development Meridium Inc. Roanoke VA 24018 United States Department of Human Interfaces TNO Human Factors Soesterberg Netherlands Department of Computer Science Center for HCI Virginia Tech. Blacksburg VA 24060 United States

ISBN: (纸本)9781595939524

Map usage on handheld devices suffers from limited screen size and the minimal attention that users can dedicate to them in mobile situations. This work examines effects of automating navigation features like zooming and panning as well as other features such as rotation, path finding and artifact representation on the mobile navigation experience. Described are five claims and early support for these features in the police work domain. © 2008 ACM.

关键词： Navigation

来源：评论

学校读者我要写书评

暂无评论

Using computer games for instruction: The student experience

引用

Active Learning in Higher Education 2011年第1期12卷 45-56页

作者： Grimley, Michael Green, Richard Nilsen, Trond Thompson, David Tomes, Russell School of Education Studies and Human Development College of Education University of Canterbury Christchurch Private Bag 4800 New Zealand Department of Computer Science and Software Engineering University of Canterbury Christchurch New Zealand

computer games are fun, exciting and motivational when used as leisure pursuits. But do they have similar attributes when utilized for educational purposes? This article investigates whether learning by computer game can improve student experiences compared with a more formal lecture approach and whether computer games have potential for improving performance. Instruction was split between lectures and computer games, and student experiences were recorded using an Experience Sampling Method to capture real-time experience and feelings of flow. Results indicated that student experiences in the game mode showed increased alertness, increased feelings of being active, increased feelings of involvement and an increased perception of challenge. Flow characteristics revealed boredom during standard lectures but anxiety and flow during game modes. Finally, some evidence of improved attainment was evident. By using contemporary interactive approaches such as computer games, student learning experiences and attainment may be improved. Some practical issues of implementing games are also discussed. © The Author(s) 2011.

关键词： active learning computer games flow instruction learning lecture student experience

来源：评论

学校读者我要写书评

暂无评论

Local training for PLDA in speaker verification 19

Local training for PLDA in speaker verification

引用

19th Annual Conference of the Oriental Chapter of International Committee for Coordination and Standardization of Speech Databases and Assessment Techniques, O-COCOSDA 2016

作者： Zhao, Chenghui Li, Lantian Wang, Dong Pu, April Pachira Beijing China Center for Speech and Language Technologies Division of Technical Innovation and Development Tsinghua National Laboratory for Information Science and Technology China Center for Speech and Language Technologies Research Institute of Information Technology China Department of Computer Science and Technology Tsinghua University Beijing China

ISBN: (纸本)9781509035168

PLDA is a popular normalization approach for the i-vector model, and it has delivered state-of-the-art performance in speaker verification. However, PLDA training requires a large amount of labeled development data, which is highly expensive in most cases. A possible approach to mitigate the problem is various unsupervised adaptation methods, which use unlabeled data to adapt the PLDA scattering matrices to the target domain. In this paper, we present a new 'local training' approach that utilizes inaccurate but much cheaper local labels to train the PLDA model. These local labels discriminate speakers within a single conversion only, and so are much easier to obtain compared to the normal 'global labels'. Our experiments show that the proposed approach can deliver significant performance improvement, particularly with limited globally-labeled data. © 2016 IEEE.

关键词： Speech recognition

来源：评论

学校读者我要写书评

暂无评论

When differential privacy meets NLP: The devil is in the detail

arXiv

引用

arXiv 2021年

作者： Habernal, Ivan Trustworthy Human Language Technologies Department of Computer Science Technical University of Darmstadt

Differential privacy provides a formal approach to privacy of individuals. Applications of differential privacy in various scenarios, such as protecting users' original utterances, must satisfy certain mathematical properties. Our contribution is a formal analysis of ADePT, a differentially private auto-encoder for text rewriting (Krishna et al, 2021). ADePT achieves promising results on downstream tasks while providing tight privacy guarantees. Our proof reveals that ADePT is not differentially private, thus rendering the experimental results unsubstantiated. We also quantify the impact of the error in its private mechanism, showing that the true sensitivity is higher by at least factor 6 in an optimistic case of a very small encoder's dimension and that the amount of utterances that are not privatized could easily reach 100% of the entire dataset. Our intention is neither to criticize the authors, nor the peer-reviewing process, but rather point out that if differential privacy applications in NLP rely on formal guarantees, these should be outlined in full and put under detailed scrutiny. © 2021, CC BY-SA.

关键词： Privatization

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：