检索结果-内蒙古大学图书馆

Inexact multisubgraph matching using graph eigenspace and clustering models 9th

Joint IAPR 9th International workshop on Structural and Syntactic Pattern Recognition, SSPR 2002 and 4th International workshop on Statistical Techniques in Pattern Recognition, SPR 2002

作者： Kosinov, Serhiy Caelli, Terry The University of Alberta EdmontonABT6G 2H1 Canada

ISBN: (纸本)3540440119

In this paper we show how inexact multisubgraph matching can be solved using methods based on the projections of vertices (and their connections) into the eigenspaces of graphs - and associated clustering methods. Our analysis points to deficiencies of recent eigenspectra methods though demonstrates just how powerful full eigenspace methods can be for providing filters for such computationally intense problems. Also presented are some applications of the proposed method to shape matching, information retrieval and natural language processing. © Springer-Verlag Berlin Heidelberg 2002.

关键词： Cluster analysis

来源：评论

学校读者我要写书评

暂无评论

An indexing method based on sentences 02

An indexing method based on sentences

引用

proceedings of the first SIGHAN workshop on Chinese language processing - Volume 18

作者： Li Li Chunfa Yuan K. F. Wong Wenjie Li Tsinghua University Beijing The Chinese University of Hong Kong Hong Kong The Hong Kong Polytechnic University Hung Hom Hong Kong

Traditional indexing methods often record physical positions for the specified words, thus fail to recognize context information. We suggest that Chinese text index should work on the layer of sentences. This paper presents an indexing method based on sentences and demonstrates how to use this method to help compute the mutual information of word pairs in a running text. It brings many conveniences to work of natural language processing.

关键词： natural language processing mutual information index file

来源：评论

学校读者我要写书评

暂无评论

language model adaptation in speech recognition using document maps

Language model adaptation in speech recognition using docume...

引用

IEEE workshop on Neural Networks for Signal processing

作者： K. Lagus M. Kurimo Neural Networks Research Centre Helsinki University of Technology Finland

We present speech experiments that were carried out to evaluate a topically focusing language model in large vocabulary speech recognition. An ordered topical clustering is first computed as a self-organized mapping of a large document collection. language models are then trained for each text cluster or for several neighboring clusters. The obtained organized collection of language models is efficiently utilized in continuous speech recognition to concentrate on the model that corresponds closest to the current topic of discussion. The speech recognition experiments are carried out on a novel Finnish speech database. A property of Finnish that is particularly challenging for speech recognition is the extremely fast vocabulary growth that makes many of the standard word-based language modeling methods impractical for large vocabulary tasks.

关键词： natural languages Adaptation model Speech recognition Vocabulary Probability Intelligent networks Neural networks Speech analysis Databases Ultraviolet sources

来源：评论

学校读者我要写书评

暂无评论

n-gram and decision tree based language identification for written words

n-gram and decision tree based language identification for w...

引用

IEEE workshop on Automatic Speech Recognition and Understanding

作者： J. Hakkinen Jilei Tian Nokia Mobile Phones Limited Tampere Finland Nokia Research Center Tampere Finland

As the demand for multilingual speech recognizers increases, the development of systems which combine automatic language identification, language-specific pronunciation modeling and language-independent acoustic models becomes increasingly important. When the recognition grammar is dynamic and obtained directly from written text, the language associated with each grammar item has to be identified using that text. Many methods proposed in the literature require fairly large amounts of text, which may not always be available. This paper describes a text-based language identification system developed for the identification of the language of short words, e.g., proper names. Two different approaches are compared. The n-gram method commonly used in the literature is first reviewed and further enhanced. We also propose a simple method for language identification that is based on decision trees. The methods are first evaluated in a text-based language identification task. Both methods are also tested as preprocessors for a multilingual speech recognition task, where the language of each text item has to be determined, in order to choose the correct text-to-pronunciation mapping. The experimental results show that the proposed methods perform very well, and merit further development.

关键词： Decision trees natural languages Speech recognition Mobile handsets Automatic speech recognition Testing Vocabulary Usability Signal processing Embedded computing

来源：评论

学校读者我要写书评

暂无评论

A cross-comparison of two clustering methods 01

A cross-comparison of two clustering methods

引用

proceedings of the workshop on Evaluation for language and Dialogue Systems - Volume 9

作者： Olivier Ferret Brigitte Grau Michèle Jardino CEA Saclay DTI/SITI Gif-sur-Yvette Cedex LIMSI CNRS Orsay France

Many natural language processing applications require semantic knowledge about topics in order to be possible or to be efficient. So we developed a system, SEGAPSITH, that acquires it automatically from text segments by using an unsupervised and incremental clustering method. In such an approach, an important problem consists of the validation of the learned classes. To do that, we applied another clustering method, that only needs to know the number of classes to build, on the same subset of text segments and we reformulate our evaluation problem in comparing the two classifications. So, we established different criteria to compare them, based either on the words as class descriptors or on the thematic units. Our first results lead to show a great correlation between the two classifications.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A dynamic associative semantic model for natural language processing based on a spreading activation network 20

A dynamic associative semantic model for natural language pr...

引用

XXth International Conference of the Chilean-Computer-Science-Society (SCCC 2000)

作者： Bassi, A Univ Chile Fac Ciencias Fis & Matemat Dept Ciencias Computac Santiago Chile

ISBN: (纸本)0769508103

This paper presents a semantic model based on well-known psycholinguistic theories of human memory. It is centered on a spreading activation network, but it departs from classical models by representing associations between structured units instead of atomic nodes. Network units have an activity level that evolves according to their expected contextual relevance. Spreading activation explains the predictive top-down effect of knowledge. It supports a general heuristics which may be used as the first step of more elaborated methods. This model is suited to deal with the interaction between semantic and episodic memories, as well as many other practical issues regarding natural language processing, including the retroactive effect of semantics over perception and the operation in open-worlds.

关键词： Computational linguistics Computational modeling Computer networks Electronic mail Humans Knowledge representation Logic design natural language processing natural languages Psychology

来源：评论

学校读者我要写书评

暂无评论

Trainable methods for surface natural language generation 1

Trainable methods for surface natural language generation

引用

6th Applied natural language processing Conference/1st Meeting of the North American Chapter of the Association-for-Computational-Linguistics/ANLP-NAACL 2000 Student Research workshop

作者： Ratnaparkhi, A IBM Corp Thomas J Watson Res Ctr Yorktown Hts NY 10598 USA

ISBN: (纸本)1558607048

We present three systems for surface natural language generation that are trainable from annotated corpora. The first two systems, called NLG1 and NLG2, require a corpus marked only with domain-specific semantic attributes, while the last system, called NLG3, requires a corpus marked with both semantic attributes and syntactic dependency information. All systems attempt to produce a grammatical natural language phrase from a domain-specific semantic representation. NLG1 serves a baseline system and uses phrase frequencies to generate a whole phrase in one step, while NLG2 and NLG3 use maximum entropy probability models to individually generate each word in the phrase. The systems NLG2 and NLG3 learn to determine both the word choice and the word order of the phrase. We present experiments in which we generate phrases to describe flights in the air travel domain.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Distinguishing systems and distinguishing senses: New evaluation methods for Word Sense Disambiguation

引用

natural language Engineering 1999年第2期5卷 113-133页

作者： Resnik, Philip Yarowsky, David Department of Linguistics and Institute for Advanced Computer Studies University of Maryland College Park MD 20742 United States Department of Computer Science/Center for Language and Speech Processing Johns Hopkins University Baltimore MD 21218 United States

Resnik and Yarowsky (1997) made a set of observations about the state-of-the-art in automatic word sense disambiguation and, motivated by those observations, offered several specific proposals regarding improved evaluation criteria, common training and testing resources, and the definition of sense inventories. Subsequent discussion of those proposals resulted in senseval the first evaluation exercise for word sense disambiguation (Kilgarriff and Palmer 2000). This article is a revised and extended version of our 1997 workshop paper, reviewing its observations and proposals and discussing them in light of the senseval exercise. It also includes a new in-depth empirical study of translingually-based sense inventories and distance measures, using statistics collected from native-speaker annotations of 222 polysemous contexts across 12 languages. These data show that monolingual sense distinctions at most levels of granularity can be effectively captured by translations into some set of second languages, especially as language family distance increases. In addition, the probability that a given sense pair will tend to lexicalize differently across languages is shown to correlate with semantic salience and sense granularity;sense hierarchies automatically generated from such distance matrices yield results remarkably similar to those created by professional monolingual lexicographers. © 1999, Cambridge University Press. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Three methods of Intonation Modeling 3

Three Methods of Intonation Modeling

引用

3rd ESCA/COCOSDA workshop on Speech Synthesis, SSW 1998

作者： Syrdal, Ann K. Möhler, Gregor Dusterhoff, Kurt Conkie, Alistair Blacic, Alan W. AT&T Labs - Research Florham ParkNJ United States Institute of Natural Language Processing University of Stuttgart Stuttgart Germany Centre for Speech Technology Research University of Edinburgh Edinburgh United Kingdom

This paper compares different methods of generating intonation for an American Enghsh Text-to-Speech synthesis system. We look at a primarily rule-based approach and two data-driven approaches. For data-driven modehng we used two separate data sets, each representing a somewhat different prosodie style. One database was recordings of a portion of 1989 Wall Street Journal text from the Penn Treebank Project. The second database was recordings of interactive prompts used in telephone network services. Both were read by the same female speaker. Approximately two and one-half hours of speech was phonetically and prosodically segmented and labeled (first automatically, and subsequently verified manually). The prosodie labeling used ToBl [7] tones and breaks. Three different intonation models were compared: (1) a predominantly rule-based model based on ToBl labels [3];(2) a parametric model using the Tilt approach [8];and (3) a Vector Quantized model based on an underlying parametric representation [5]. Sentences representative of both prosodie styles were synthesized with each of these models, and were presented to listeners for subjective ratings in a formal listening test. The results of the evaluation are reported. © 1998 3rd ESCA/COCOSDA workshop on Speech Synthesis, SSW 1998. All rights reserved.

关键词： Speech synthesis

来源：评论

学校读者我要写书评

暂无评论

How may I help you?

引用

SPEECH COMMUNICATION 1997年第1-2期23卷 113-127页

作者： Gorin, AL Riccardi, G Wright, JH AT&T Bell Labs Res Florham Pk NJ USA

We are interested in providing automated services via natural spoken dialog systems. By natural, we mean that the machine understands and acts upon what people actually say, in contrast to what one would Like them to say. There are many issues that arise when such systems are targeted for large populations of non-expert users. In this paper, we focus on the task of automatically routing telephone calls based on a user's fluently spoken response to the open-ended prompt of "How may I help you?". We first describe a database generated from 10,000 spoken transactions between customers and human agents. We then describe methods for automatically acquiring language models for both recognition and understanding from such data. Experimental results evaluating call-classification from speech are reported for that database. These methods have been embedded within a spoken dialog system, with subsequent processing for information retrieval and formfilling. (C) 1997 Elsevier Science B.V.

关键词： spoken language understanding spoken dialog system speech recognition stochastic language modeling salient phrase aquisition topic classification

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：