检索结果-内蒙古大学图书馆

International Conference on computer science and Information Technology (CSIT)

作者： Liuling Dai Bin Liu Yuning Xia ShiKun Wu Beijing Laboratory of Intelligent Information Technology Beijing Institute of Technology Beijing PRC Center for Speech and Language Technologies RIIT Tsinghua University Beijing China School of Computer Science Beijing Institute of Technology Beijing PRC Beijing Laboratory of Intelligent Information Technology School of Computer Science BeiJing Institute of Technology Beijing China Center for Speech and Language Technologies Tsinghua University Beijing PRC Central Radio and TV Tower Beijing PRC

Semantic similarity between words is a fundamental issue for many natural language processing applications. The difficulty lies in that how to develop a computational method that is capable of generating satisfactory results close to how humans perceive. In this paper, a novel method is proposed to measure semantic similarity between words using HowNet, which is a renowned Chinese-English bilingual knowledge base. Furthermore, a Chinese thesaurus is used to improve the similarity measuring. Theoretically, our method can be used in many languages while in this case it is applied for English and Chinese. Experiments on English and Chinese word pairs show that our method are closest to human similarity judgments when compared to the major state-of-the-art methods.

关键词： Distance measurement Humans Correlation Knowledge based systems Medical services Thesauri Natural languages

来源：评论

学校读者我要写书评

暂无评论

Emotion recognition through multiple modalities: Face, body gesture, speech

Emotion recognition through multiple modalities: Face, body ...

引用

Lecture Notes in computer science

作者： Castellano, Ginevra Kessous, Loic Caridakis, George InfoMus Lab. DIST University of Genova Viale Causa 13 Genova I-16145 Italy Department of Speech Language and Hearing University of Tel Aviv Sheba Center Tel Aviv 52621 Israel Image Video and Multimedia Systems Laboratory National Technical University of Athens 9 Heroon Politechniou str. Athens 15780 Greece Department of Computer Science Queen Mary University of London United Kingdom

ISBN: (纸本)3540850988

In this paper we present a multimodal approach for the recognition of eight emotions. Our approach integrates information from facial expressions, body movement and gestures and speech. We trained and tested a model with a Bayesian classifier, using a multimodal corpus with eight emotions and ten subjects. Firstly, individual classifiers were trained for each modality. Next, data were fused at the feature level and the decision level. Fusing the multimodal data resulted in a large increase in the recognition rates in comparison with the unimodal systems: the multimodal approach gave an improvement of more than 10% when compared to the most successful unimodal system. Further, the fusion performed at the feature level provided better results than the one performed at the decision level. © 2008 Springer-Verlag Berlin Heidelberg.

关键词： Emotion Recognition

来源：评论

学校读者我要写书评

暂无评论

Probabilistic models of nonprojective dependency trees

Probabilistic models of nonprojective dependency trees

引用

2007 Joint Conference on Empirical Methods in Natural language processing and Computational Natural language Learning, EMNLP-CoNLL 2007

作者： Smith, David A. Smith, Noah A. Department of Computer Science Center for Language and Speech Processing Johns Hopkins University Baltimore MD 21218 United States School of Computer Science Language Technologies Institute Carnegie Mellon University Pittsburgh PA 15213 United States

A notable gap in research on statistical dependency parsing is a proper conditional probability distribution over nonprojective dependency trees for a given sentence. We exploit the Matrix Tree Theorem (Tutte, 1984) to derive an algorithm that efficiently sums the scores of all nonprojective trees in a sentence, permitting the definition of a conditional log-linear model over trees. While discriminative methods, such as those presented in McDonald et al. (2005b), obtain very high accuracy on standard dependency parsing tasks and can be trained and applied without marginalization, "summing trees" permits some alternative techniques of interest. Using the summing algorithm, we present competitive experimental results on four nonprojective languages, for maximum conditional likelihood estimation, minimum Bayes-risk parsing, and hidden variable training. © 2007 Association for Computational Linguistics.

关键词： Trees (mathematics)

来源：评论

学校读者我要写书评

暂无评论

A MAXIMUM ENTROPY CHUNKING MODEL WITH N-FOLD TEMPLATE CORRECTION

引用

Journal of Electronics(China) 2007年第5期24卷 690-695页

作者： Sun Guanglu Guan Yi Wang Xiaolong Ministry of Education-Microsoft Key Laboratory of Natural Language Processing and Speech School of Computer Science and Technology Harbin Institute of Technology Harbin 150001 China

This letter presents a new chunking method based on Maximum Entropy (ME) model with N-fold template correction *** two types of machine learning models are *** on the analysis of the two models,then the chunking model which combines the profits of conditional probability model and rule based model is *** selection of features and rule templates in the chunking model is *** results for the CoNLL-2000 corpus show that this approach achieves impressive accuracy in terms of the F-score:92.93%.Compared with the ME model and ME Markov model,the new chunking model achieves better performance.

关键词： Chunking Maximum Entropy （ME） model Template correction Cross-validation

来源：评论

学校读者我要写书评

暂无评论

Fusion of communication content and broadcast content

引用

Journal of the National Institute of Information and Communications Technology 2007年第3期54卷 63-70页

作者： Miyamori, Hisashi Kumamoto, Tadahiko Nadamoto, Akiyo Sumi, Kaoru Nakamura, Satoshi Ma, Qiang Minakuchi, Mitsuru Tanaka, Katsumi Knowledge Clustered Group Knowledge Creating Communication Research Center Language Grid Project Natural Language Processing Group Knowledge Creating Communication Research Center Graduate School of Informatics Kyoto Universiry Universal City Group Knowledge Creating Communication Research Center Faculty of Information and Computer Science Chiba Institute of Technology Ubiquitous Intelligence Technology Group Service Platforms Research Laboratories NEC

This paper explains an overview of research results of "Fusion of Communication Content and Broadcast Content", one of the two main pillars of "Content Fusion" research project conducted at the Interactive Communication and Media Contents Group of NICT. "Fusion of Communication and Broadcast" is a conventional keyword which means technology of converging communication and broadcasting networks as an infrastructure, whereas "Fusion of Communication and Broadcast Content" represents a technology of converging Web content and TV programs at content level. Fundamental technologies and model systems were established which can efficiently utilize Internet and TV programs without complicated operations even for people who are not familiar with computer operation, such as efficient methods of accessing information and utilization methods of newly added value of information, towards the age of multitude content of TV programs and Web content available in daily lives.

关键词： Information retrieval

来源：评论

学校读者我要写书评

暂无评论

Dysarthric speech characteristics of Thai stroke patients assessed by the computerized articulation test 07

Dysarthric speech characteristics of Thai stroke patients as...

引用

i-CREATe 2007 - 1st International Convention on Rehabilitation Engineering and Assistive Technology in Conjunction with 1st Tan Tock Seng Hospital Neurorehabilitation Meeting

作者： Manochiopinig, Sriwimon Thubthong, Nuttakorn Kayasith, Prakasit Speech and Language Therapy Unit Department of Rehabilitation Medicine Mahidol University Bangkoknoi Bangkok 10700 Thailand Acoustics and Speech Research Group Department of Physics Chulalongkorn University Phathumwan Bangkok 10300 Thailand Assistive Technology Center National Electonics and Computer Center Thailand Science Park Pathumthani 12120 Thailand

ISBN: (纸本)9781595938527

The dysarthric speech characteristics of 14 Thai stroke patients were assessed by the computerized Articulation Test [1]. speech accuracy and error pattern were analyzed. Vowels and tonal characteristics were the most intact characteristics, while reduction of the clusters was the most impaired feature. Both initial and final consonants were frequently substituted, followed by omission and distortion. Generally, low and mid tone, unaspirated consonants and final consonant, monophthong vowels were produced more precisely than the other features. © ACM 2007.

关键词： Linguistics

来源：评论

学校读者我要写书评

暂无评论

Unigram language models using diffusion smoothing over graphs

Unigram language models using diffusion smoothing over graph...

引用

2nd Workshop on Graph-Based Algorithms for Natural language processing, TextGraphs 2007

作者： Jedynak, Bruno Karakos, Damianos Dept. of Appl. Mathematics and Statistics Center for Imaging Sciences Johns Hopkins University Baltimore MD 21218-2686 United States Dept. of Electrical and Computer Engineering Center for Language and Speech Processing Johns Hopkins University Baltimore MD 21218-2686 United States

We propose to use graph-based diffusion techniques with data-dependent kernels to build unigram language models. Our approach entails building graphs, where each vertex corresponds uniquely to a word from a closed vocabulary, and the existence of an edge (with an appropriate weight) between two words indicates some form of similarity between them. In one of our constructions, we place an edge between two words if the number of times these words were seen in a training set differs by at most one count. This graph construction results in a similarity matrix with small intrinsic dimension, since words with the same counts have the same neighbors. Experimental results from a benchmark task from language modeling show that our method is competitive with the Good-Turing estimator.

关键词： Graphic methods

来源：评论

学校读者我要写书评

暂无评论

Segmentation and alignment of parallel text for statistical machine translation

引用

Natural language Engineering 2007年第3期13卷 235-260页

作者： Deng, Yonggang Kumar, Shankar Byrne, William Center for Language and Speech Processing Department of Electrical and Computer Engineering The Johns Hopkins University 3400 N. Charles St. Baltimore MD 21218 United States Google Inc. 1600 Amphitheatre Parkway Mountain View CA 94043 United States Department of Engineering Cambridge University Trumpington Street Cambridge CB2 1PZ United Kingdom

We address the problem of extracting bilingual chunk pairs from parallel text to create training sets for statistical machine translation. We formulate the problem in terms of a stochastic generative process over text translation pairs, and derive two *** alignment procedures based on the underlying alignment model. The first procedure is a now-standard dynamic programming alignment model which we use to generate an initial coarse alignment of the parallel text. The second procedure is a divisive clustering parallel text alignment procedure which we use to refine the first-pass alignments. This latter procedure is novel in that it permits the segmentation of the parallel text into sub-sentence units which are allowed to be reordered to improve the chunk alignment. The quality of chunk pairs are measured by the performance of machine translation systems trained from them. We show practical *** of divisive clustering as well as how system performance can be improved by exploiting portions of the parallel text that otherwise would have to be discarded. We also show that chunk alignment as a first step in word alignment can *** reduce word alignment error rate. © 2007 Cambridge University Press.

关键词： computer aided language translation

来源：评论

学校读者我要写书评

暂无评论

Finding a Needle in a Haystack

Finding a Needle in a Haystack

引用

Annual Conference on Information sciences and Systems (CISS)

作者： Bruno Jedynak Damianos Karakos Department of Applied Mathematics Johns Hopkins University MD USA Center for Language and Speech Processing and Department of Electrical and Computer Engineering Johns Hopkins University Baltimore MD USA

Summary form only given. We study a simplified version of the problem of target detectability in the presence of clutter. The target (the needle) is a sample of size N from a discrete distribution p. The clutter (the haystack) is made up of M independent samples of size JV from a distribution q (which is different from p, but with the same support). Two cases can be easily shown: (i) If M is fixed and JV goes to infinity, the target can be detected with probability that approaches 1. (ii) If TV is fixed and M goes to infinity, then, with probability approaching 1, the target cannot be detected. For the case where both JV, M go to infinity, we show that the asymptotic behavior of the optimal detector (if p, q are known) and of a plug-in detector (which estimates p, q on the fly) is determined by the asymptotic behavior of the quantity Mexp(-ND(p\\q)) : if it goes to zero (resp. infinity), then, with high probability, the target can (resp. cannot) be detected.

关键词： Needles H infinity control World Wide Web Detectors Mathematics Natural languages speech processing

来源：评论

学校读者我要写书评

暂无评论

Resolving and generating definite anaphora by modeling hypernymy using unlabeled corpora 10

Resolving and generating definite anaphora by modeling hyper...

引用

10th Conference on Computational Natural language Learning, CoNLL-X

作者： Garera, Nikesh Yarowsky, David Department of Computer Science Center for Language and Speech Processing Johns Hopkins University Baltimore MD 21218 United States

We demonstrate an original and successful approach for both resolving and generating definite anaphora. We propose and evaluate unsupervised models for extracting hypernym relations by mining cooccurrence data of definite NPs and potential antecedents in an unlabeled corpus. The algorithm outperforms a standard WordNet-based approach to resolving and generating definite anaphora. It also substantially outperforms recent related work using pattern-based extraction of such hypernym relations for coreference resolution. © 2006 Association for Computational Linguistics.

关键词：

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：