检索结果-内蒙古大学图书馆

A weighted finite state transducer translation template model for statistical machine translation

Natural language Engineering 2006年第1期12卷 35-75页

作者： Kumar, Shankar Deng, Yonggang 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

We present a Weighted Finite State Transducer Translation Template Model for statistical machine translation. This is a source-channel model of translation inspired by the Alignment Template translation model. The model attempts to overcome the deficiencies of word-to-word translation models by considering phrases rather than words as units of translation. The approach we describe allows us to implement each constituent distribution of the model as a weighted finite state transducer or acceptor. We show that bitext word alignment and translation under the model can be performed with standard finite state machine operations involving these transducers. One of the benefits of using this framework is that it avoids the need to develop specialized search procedures, even for the generation of lattices or N-Best lists of bitext word alignments and translation hypotheses. We report and analyze bitext word alignment and translation performance on the Hansards French-English task and the FBIS Chinese-English task under the Alignment Error Rate, BLEU, NIST and Word Error-Rate metrics. These experiments identify the contribution of each of the model components to different aspects of alignment and translation performance. We finally discuss translation performance with large bitext training sets on the NIST 2004 Chinese-English and Arabic-English MT tasks. © 2005 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

A Dialectal Chinese speech Recognition Framework

引用

Journal of computer science & Technology 2006年第1期21卷 106-115页

作者：李净郑方 William Byrne Dan Jurafsky Center for Speech Technology State Key Laboratory of Intelligent Technology and Systems Department of Computer Science and Technology Tsinghua University Beijing 100084 P.R. China Machine Intelligence Laboratory Cambridge University U.K. Center for Language and Speech Processing The Johns Hopkins University U.S.A. Department of Linguistics Stanford University U.S.A.

A framework for dialectal Chinese speech recognition is proposed and studied, in which a relatively small dialectal Chinese （or in other words Chinese influenced by the native dialect） speech corpus and dialect-related knowledge are adopted to transform a standard Chinese （or Putonghua, abbreviated as PTH） speech recognizer into a dialectal Chinese speech recognizer. Two kinds of knowledge sources are explored： one is expert knowledge and the other is a small dialectal Chinese corpus. These knowledge sources provide information at four levels： phonetic level, lexicon level, language level, and acoustic decoder level. This paper takes Wu dialectal Chinese （WDC） as an example target language. The goal is to establish a WDC speech recognizer from an existing PTH speech recognizer based on the Initial-Final structure of the Chinese language and a study of how dialectal Chinese speakers speak Putonghua. The authors propose to use contextindependent PTH-IF mappings （where IF means either a Chinese Initial or a Chinese Final）, context-independent WDC-IF mappings, and syllable-dependent WDC-IF mappings （obtained from either experts or data）, and combine them with the supervised maximum likelihood linear regression （MLLR） acoustic model adaptation method. To reduce the size of the multipronunciation lexicon introduced by the IF mappings, which might also enlarge the lexicon confusion and hence lead to the performance degradation, a Multi-Pronunciation Expansion （MPE） method based on the accumulated uni-gram probability （AUP） is proposed. In addition, some commonly used WDC words are selected and added to the lexicon. Compared with the original PTH speech recognizer, the resulting WDC speech recognizer achieves 10-18% absolute Character Error Rate （CER） reduction when recognizing WDC, with only a 0.62% CER increase when recognizing PTH. The proposed framework and methods are expected to work not only for Wu dialectal Chinese but also for other dialectal Chinese languages and

关键词： dialectal Chinese speech recognition initial or final （IF） IF-mapping rule pronunciation modeling small quantity of speech data

来源：评论

学校读者我要写书评

暂无评论

Better informed training of latent syntactic features

Better informed training of latent syntactic features

引用

11th Conference on Empirical Methods in Natural language Proceessing, EMNLP 2006, Held in Conjunction with COLING/ACL 2006

作者： Dreyer, Markus Eisner, Jason Department of Computer Science Center for Language and Speech Processing Johns Hopkins University 3400 North Charles Street Baltimore MD 21218 United States

ISBN: (纸本)1932432736

We study unsupervised methods for learning refinements of the nonterminals in a treebank. Following Matsuzaki et al. (2005) and Prescher (2005), we may for example split NP without supervision into NP[0] and NP[1], which behave differently. We first propose to learn a PCFG that adds such features to nonterminals in such a way that they respect patterns of linguistic feature passing: each node's nonterminal features are either identical to, or independent of, those of its parent. This linguistic constraint reduces runtime and the number of parameters to be learned. However, it did not yield improvements when training on the Penn Treebank. An orthogonal strategy was more successful: to improve the performance of the EM learner by treebank preprocessing and by annealing methods that split nonterminals selectively. Using these methods, we can maintain high parsing accuracy while dramatically reducing the model size. © 2006 Association for Computational Linguistics.

关键词： Forestry

来源：评论

学校读者我要写书评

暂无评论

Learning algorithms for online principal-agent problems (and selling goods online) 06

Learning algorithms for online principal-agent problems (and...

引用

ICML 2006: 23rd International Conference on Machine Learning

作者： Conitzer, Vincent Garera, Nikesh Computer Science Department Carnegie Mellon University Pittsburgh PA 15213 United States Department of Computer Science Center for Language and Speech Processing Johns Hopkins University Baltimore MD 21218 United States

ISBN: (纸本)1595933832

In a principal-agent problem, a principal seeks to motivate an agent to take a certain action beneficial to the principal, while spending as little as possible on the reward. This is complicated by the fact that the principal does not know the agent's utility function (or type). We study the online setting where at each round, the principal encounters a new agent, and the principal sets the rewards anew. At the end of each round, the principal only finds out the action that the agent took, but not his type. The principal must learn how to set the rewards optimally. We show that this setting generalizes the setting of selling a digital good online. We study and experimentally compare three main approaches to this problem. First, we show how to apply a standard bandit algorithm to this setting. Second, for the case where the distribution of agent types is fixed (but unknown to the principal), we introduce a new gradient ascent algorithm. Third, for the case where the distribution of agents' types is fixed, and the principal has a prior belief (distribution) over a limited class of type distributions, we study a Bayesian approach.

关键词： Learning algorithms

来源：评论

学校读者我要写书评

暂无评论

Gesture Spotting in Low-Quality Video with Features Based on Curvature Scale Space

Gesture Spotting in Low-Quality Video with Features Based on...

引用

International Conference on Automatic Face and Gesture Recognition

作者： Myung-Cheol Roh B. Christmas J. Kittler Seong-Whan Lee Department of Computer Science and Engineering Korea University Seoul South Korea Center for Vision Speechand Signal Processing University of Surrey Guildford UK

Player's gesture and action spotting in sports video is a key task in automatic analysis of the video material at a high level. In many sports views, the camera covers a large part of the sports arena, so that the area of player's region is small, and has large motion. These make the determination of the player's gestures and actions a challenging task. To overcome these problems, we propose a method based on curvature scale space templates of the player's silhouette. The use of curvature scale space makes the method robust to noise and our method is robust to significant shape corruption of a part of player's silhouette. We also propose a new recognition method which is robust to noisy sequence of posture and needs only a small amount of training data, which is essential characteristic for many practical applications

关键词： Noise robustness Cameras computer science speech analysis Noise shaping Shape Surveillance Face recognition speech processing Video signal processing

来源：评论

学校读者我要写书评

暂无评论

Improving rapid unsupervised speaker adaptation based on HMM-sufficient statistics in noisy environments using multi-template models

Improving rapid unsupervised speaker adaptation based on HMM...

引用

作者： Gomez, Randy Lee, Akinobu Toda, Tomoki Saruwatari, Hiroshi Shikano, Kiyohiro Nara Institute of Science and Technology Ikoma-shi 630-0192 Japan Nagoya Institute of Technology Nagoya-shi 466-8555 Japan Speech and Acoustics Laboratory Nara Institute of Science and Technology Japan Department of Computer Science and Engineering Nagoya Institute of Technology Japan Information Processing Society of Japan Japan Acoustical Society of Japan Japan Graduate School of Information Science Nara Institute of Science and Technology Japan ATR Spoken Language Communication Research Laboratories Japan ISCA VR Society of Japan Japan Japan International Speech Communication Society

This paper describes the method of using multi-template unsupervised speaker adaptation based on HMM-Sufficient Statistics to push up the adaptation performance while keeping adaptation time within few seconds with just one arbitrary utterance. This adaptation scheme is mainly composed of two processes. The first part is done offline which involves the training of multiple class-dependent acoustic models and the creation of speakers' HMM-Sufficient Statistics based on gender and age. The second part is performed online where adaptation begins using the single utterance of a test speaker. From this utterance, the system will classify the speaker's class and consequently select the N-best neighbor speakers close to the utterance using Gaussian Mixture Models (GMM). The classified speakers' class template model is then adopted as a base model. From this template model, the adapted model is rapidly constructed using the N-best neighbor speakers' HMM-Sufficient Statistics. Experiments in noisy environment conditions with 20 dB, 15 dB and 10 dB SNR office, crowd, booth, and car noise are performed. The proposed multi-template method achieved 89.5% word accuracy rate compared with 88.1% of the conventional single-template method, while the baseline recognition rate without adaptation is 86.4%. Moreover, experiments using Vocal Tract Length Normalization (VTLN) and supervised Maximum Likelihood Linear Regression (MLLR) are also compared. Copyright © 2006 The Institute of Electronics, Information and Communication Engineers.

关键词： Acoustic wave effects

来源：评论

学校读者我要写书评

暂无评论

The AT&T spoken language understanding system

The AT&T spoken language understanding system

引用

作者： Gupta, Narendra Tur, Gokhan Hakkani-Tür, Dilek Bangalore, Srinivas Riccardi, Giuseppe Gilbert, Mazin IEEE AT and T Labs.-Research Florham Park NJ 07932 United States Computer Science Department University of Trento Trento Italy AT and T VoiceTone Service ACL ISCA AT and T Laboratories-Research Florham Park NJ Association for Computational Linguistics Voice Enabled Services Laboratory AT and T Laboratories-Research Florham Park NJ AT and T Labs.-Research Computer Science Department University of Trente Trento Italy New York Academy of Science Natural Language Processing Division AT and T Labs. Research IEEE Speech Technical Committee CAIP Industrial Board Rutgers University

Spoken language understanding (SLU) aims at extracting meaning from natural language speech. Over the past decade, a variety of practical goal-oriented spoken dialog systems have been built for limited domains. SLU in these systems ranges from understanding predetermined phrases through fixed grammars, extracting some predefined named entities, extracting users' intents for call classification, to combinations of users' intents and named entities. In this paper, we present the SLU system of VoiceTone® (a service provided by AT&T where AT&T develops, deploys and hosts spoken dialog applications for enterprise customers). The SLU system includes extracting both intents and the named entities from the users' utterances. For intent determination, we use statistical classifiers trained from labeled data, and for named entity extraction we use rule-based fixed grammars. The focus of our work is to exploit data and to use machine learning techniques to create scalable SLU systems which can be quickly deployed for new domains with minimal human intervention. These objectives are achieved by 1) using the predicate-argument representation of semantic content of an utterance;2) extending statistical classifiers to seamlessly integrate hand crafted classification rules with the rules learned from data;and 3) developing an active learning framework to minimize the human labeling effort for quickly building the classifier models and adapting them to changes. We present an evaluation of this system using two deployed applications of VoiceTone®. © 2006 IEEE.

关键词： speech recognition

来源：评论

学校读者我要写书评

暂无评论

Compiling comp ling: Practical weighted dynamic programming and the Dyna language

Compiling comp ling: Practical weighted dynamic programming ...

引用

Human language Technology Conference and Conference on Empirical Methods in Natural language processing, HLT/EMNLP 2005, Co-located with the 2005 Document Understanding Conference, DUC and the 9th International Workshop on Parsing Technologies, IWPT

作者： Eisner, Jason Goldlust, Eric Smith, Noah A. Department of Computer Science Center for Language and Speech Processing Johns Hopkins University Baltimore MD 21218 United States

Weighted deduction with aggregation is a powerful theoretical formalism that encompasses many NLP algorithms. This paper proposes a declarative specification language, Dyna;gives general agenda-based algorithms for computing weights and gradients;briefly discusses Dyna-to-Dyna program transformations;and shows that a first implementation of a Dyna-to-C++ compiler produces code that is efficient enough for real NLP research, though still several times slower than hand-crafted code. © 2005 Association for Computational Linguistics.

关键词： Natural language processing systems

来源：评论

学校读者我要写书评

暂无评论

Context-based morphological disambiguation with random fields 05

Context-based morphological disambiguation with random field...

引用

作者： Smith, Noah A. Smith, David A. Tromble, Roy W. Department of Computer Science Center for Language and Speech Processing Johns Hopkins University Baltimore MD 21218 United States

Finite-state approaches have been highly successful at describing the morphological processes of many languages. Such approaches have largely focused on modeling the phone- or character-level processes that generate candidate lexical types, rather than tokens in context. For the full analysis of words in context, disambiguation is also required (Hakkani-Tür et al., 2000;Hajič et al., 2001). In this paper, we apply a novel source-channel model to the problem of morphological disambiguation (segmentation into morphemes, lemmatization, and POS tagging) for concatenative, templatic, and inflectional languages. The channel model exploits an existing morphological dictionary, constraining each word's analysis to be linguistically valid. The source model is a factored, conditionally-estimated random field (Lafferty et al., 2001) that learns to disambiguate the full sentence by modeling local contexts. Compared with baseline state-of-the-art methods, our method achieves statistically significant error rate reductions on Korean, Arabic, and Czech, for various training set sizes and accuracy measures. © 2005 Association for Computational Linguistics.

关键词： Computational linguistics

来源：评论

学校读者我要写书评

暂无评论

Contrastive estimation: Training log-linear models on unlabeled data

Contrastive estimation: Training log-linear models on unlabe...

引用

43rd Annual Meeting of the Association for Computational Linguistics, ACL-05

作者： Smith, Noah A. Eisner, Jason Department of Computer Science Center for Language and Speech Processing Johns Hopkins University Baltimore MD 21218 United States

ISBN: (纸本)1932432515

Conditional random fields (Lafferty et al., 2001) are quite effective at sequence labeling tasks like shallow parsing (Sha and Pereira, 2003) and namedentity extraction (McCallum and Li, 2003). CRFs are log-linear, allowing the incorporation of arbitrary features into the model. To train on unlabeled data, we require unsupervised estimation methods for log-linear models;few exist. We describe a novel approach, contrastive estimation. We show that the new technique can be intuitively understood as exploiting implicit negative evidence and is computationally efficient. Applied to a sequence labeling problem-POS tagging given a tagging dictionary and unlabeled text-contrastive estimation outperforms EM (with the same feature set), is more robust to degradations of the dictionary, and can largely recover by modeling additional features. © 2005 Association for Computational Linguistics.

关键词： Computational linguistics

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：