检索结果-内蒙古大学图书馆

International Conference on Acoustics, speech, and Signal processing (ICASSP)

作者： Ariya Rastrow Markus Dreyer Abhinav Sethy Sanjeev Khudanpur Bhuvana Ramabhadran Mark Dredze Human Language Technology Center of Excellence and Center of Language and Speech Processing Johns Hopkins University USA IBM Thomas J. Watson Research Center Yorktown Heights NY USA

We describe a new approach for rescoring speech lattices - with long-span language models or wide-context acoustic models - that does not entail computationally intensive lattice expansion or limited rescoring of only an N-best list. We view the set of word-sequences in a lattice as a discrete space equipped with the edit-distance metric, and develop a hill climbing technique to start with, say, the 1-best hypothesis under the lattice-generating model(s) and iteratively search a local neighborhood for the highest-scoring hypothesis under the rescoring model(s); such neighborhoods are efficiently constructed via finite state techniques. We demonstrate empirically that to achieve the same reduction in error rate using a better estimated, higher order language model, our technique evaluates fewer utterance-length hypotheses than conventional N-best rescoring by two orders of magnitude. For the same number of hypotheses evaluated, our technique results in a significantly lower error rate.

关键词： Lattices Computational modeling speech Acoustics speech recognition Table lookup Viterbi algorithm

来源：评论

学校读者我要写书评

暂无评论

Nonparametric Bayesian word sense induction

Nonparametric Bayesian word sense induction

引用

6th Workshop on Graph-Based Methods for Natural language processing, TextGraphs 2011

作者： Yao, Xuchen Durme, Benjamin Van Department of Computer Science Johns Hopkins University United States Human Language Technology Center of Excellence Johns Hopkins University United States

ISBN: (纸本)9781937284008

We propose the use of a nonparametric Bayesian model, the Hierarchical Dirichlet Process (HDP), for the task of Word Sense Induction. Results are shown through comparison against Latent Dirichlet Allocation (LDA), a parametric Bayesian model employed by Brody and Lapata (2009) for this task. We find that the two models achieve similar levels of induction quality, while the HDP confers the advantage of automatically inducing a variable number of senses per word, as compared to manually fixing the number of senses a priori, as in LDA. This flexibility allows for the model to adapt to terms with greater or lesser polysemy, when evidenced by corpus distributional statistics. When trained on out-of-domain data, experimental results confirm the model's ability to make use of a restricted set of topically coherent induced senses, when then applied in a restricted domain. © 2011 The Association for Computational Linguistics.

关键词： Statistics

来源：评论

学校读者我要写书评

暂无评论

Paraphrastic Sentence Compression with a Character-based Metric: Tightening without Deletion 49

Paraphrastic Sentence Compression with a Character-based Met...

引用

2011 Workshop on Monolingual Text-To-Text Generation at the 49th Annual Meeting of the Association for Computational Linguistics: human language Technologies, ACL-HLT 2011

作者： Napoles, Courtney Callison-Burch, Chris Ganitkevitch, Juri Van Durme, Benjamin Department of Computer Science Johns Hopkins University United States Human Language Technology Center of Excellence Johns Hopkins University United States

ISBN: (纸本)9781937284053

We present a substitution-only approach to sentence compression which "tightens" a sentence by reducing its character length. Replacing phrases with shorter paraphrases yields paraphrastic compressions as short as 60% of the original length. In support of this task, we introduce a novel technique for re-ranking paraphrases extracted from bilingual corpora. At high compression rates1 paraphrastic compressions outperform a state-of-the-art deletion model in an oracle experiment. For further compression, deleting from oracle paraphrastic compressions preserves more meaning than deletion alone. In either setting, paraphrastic compression shows promise for surpassing deletion-only methods. © 2011 Association for Computational Linguistics

关键词：

来源：评论

学校读者我要写书评

暂无评论

Syntactic decision tree LMs: Random selection or intelligent design?

Syntactic decision tree LMs: Random selection or intelligent...

引用

Conference on Empirical Methods in Natural language processing, EMNLP 2011

作者： Filimonov, Denis Harper, Mary Human Language Technology Center of Excellence Johns Hopkins University United States Department of Computer Science University of Maryland College Park United States

ISBN: (纸本)1937284115

Decision trees have been applied to a variety of NLP tasks, including language modeling, for their ability to handle a variety of attributes and sparse context space. Moreover, forests (collections of decision trees) have been shown to substantially outperform individual decision trees. In this work, we investigate methods for combining trees in a forest, as well as methods for diversifying trees for the task of syntactic language modeling. We show that our tree interpolation technique outperforms the standard method used in the literature, and that, on this particular task, restricting tree contexts in a principled way produces smaller and better forests, with the best achieving an 8% relative reduction in Word Error Rate over an n-gram baseline. © 2011 Association for Computational Linguistics.

关键词： Decision trees

来源：评论

学校读者我要写书评

暂无评论

Generalized interpolation in decision tree LM

Generalized interpolation in decision tree LM

引用

49th Annual Meeting of the Association for Computational Linguistics: human language Technologies, ACL-HLT 2011

ISBN: (纸本)9781932432886

In the face of sparsity, statistical models are often interpolated with lower order (backoff) models, particularly in language Modeling. In this paper, we argue that there is a relation between the higher order and the backoff model that must be satisfied in order for the interpolation to be effective. We show that in n-gram models, the relation is trivially held, but in models that allow arbitrary clustering of context (such as decision tree models), this relation is generally not satisfied. Based on this insight, we also propose a generalization of linear interpolation which significantly improves the performance of a decision tree language model. © 2011 Association for Computational Linguistics.

关键词： Decision trees

来源：评论

学校读者我要写书评

暂无评论

Confidence-weighted linear classification for text categorization

The Journal of Machine Learning Research

引用

The Journal of Machine Learning Research 2012年第1期13卷

作者： Koby Crammer Mark Dredze Fernando Pereira Department of Electrical Engineering The Technion Haifa Israel Human Language Technology Center of Excellence Johns Hopkins University Baltimore MD Google Inc. Mountain View CA

Confidence-weighted online learning is a generalization of margin-based learning of linear classifiers in which the margin constraint is replaced by a probabilistic constraint based on a distribution over classifier weights that is updated online as examples are observed. The distribution captures a notion of confidence on classifier weights, and in some cases it can also be interpreted as replacing a single learning rate by adaptive per-weight rates. Confidence-weighted learning was motivated by the statistical properties of natural-language classification tasks, where most of the informative features are relatively rare. We investigate several versions of confidence-weighted learning that use a Gaussian distribution over weight vectors, updated at each observed example to achieve high probability of correct classification for the example. Empirical evaluation on a range of text-categorization tasks show that our algorithms improve over other state-of-the-art online and batch methods, learn faster in the online setting, and lead to better classifier combination for a type of distributed training commonly used in cloud computing.

关键词： confidence prediction online learning text categorization

来源：评论

学校读者我要写书评

暂无评论

Learning sub-word units for open vocabulary speech recognition

Learning sub-word units for open vocabulary speech recogniti...

引用

49th Annual Meeting of the Association for Computational Linguistics: human language Technologies, ACL-HLT 2011

作者： Parada, Carolina Dredze, Mark Sethy, Abhinav Rastrow, Ariya Human Language Technology Center of Excellence Johns Hopkins University 3400 N Charles Street Baltimore MD United States IBM T.J. Watson Research Center Yorktown Heights NY United States

ISBN: (纸本)9781932432879

Large vocabulary speech recognition systems fail to recognize words beyond their vocabulary, many of which are information rich terms, like named entities or foreign words. Hybrid word/sub-word systems solve this problem by adding sub-word units to large vocabulary word based systems;new words can then be represented by combinations of subword units. Previous work heuristically created the sub-word lexicon from phonetic representations of text using simple statistics to select common phone sequences. We propose a probabilistic model to learn the subword lexicon optimized for a given task. We consider the task of out of vocabulary (OOV) word detection, which relies on output from a hybrid model. A hybrid model with our learned sub-word lexicon reduces error by 6.3% and 7.6% (absolute) at a 5% false alarm rate on an English Broadcast News and MIT Lectures task respectively. © 2011 Association for Computational Linguistics.

关键词： Vocabulary control

来源：评论

学校读者我要写书评

暂无评论

Anomaly detection for random graphs using distributions of vertex invariants

Anomaly detection for random graphs using distributions of v...

引用

Annual Conference on Information Sciences and Systems (CISS)

作者： Nash Borges Glen A. Coppersmith Gerard G. L. Meyer Carey E. Priebe Human Language Technology Center of Excellence Department of Electrical and Computer Engineering Johns Hopkins University USA Human Language Technology Center of Excellence Department of Applied Mathematics and Statistics Johns Hopkins University USA

Anomaly detection is a longstanding problem with many applications in signal processing. We consider anomaly detection on graphs, a subject which has not previously had treatment in such depth. Our approach is inspired largely by previous work, where anomaly detection in an acoustic signal is accomplished by measuring and comparing the distribution of localized measurements to those available from a non-anomalous signal. In similar spirit, we proceed by comparing distributions of vertex invariants to those obtained from non-anomalous graphs. Specifically, we consider homogeneous Erdös-Rényi random graphs (where each vertex is connected independently with equal probability p) to be non-anomalous, and compare them to four classes of heterogeneous alternatives (where a subset of the vertices are connected according to a different process). Our contributions are (1) a novel method of incorporating information from vertex invariants for anomaly detection on graphs, (2) a principled approach to fusing information from an arbitrary number of such statistics, and (3) evaluation on several types of anomalous graphs. We demonstrate superior performance to available state-of-the-art approaches against the specific type of anomalies optimized for, and further demonstrate superior generalization to an entire class of anomalies.

关键词： Histograms Entropy Joints Erbium Training Acoustic measurements Image edge detection

来源：评论

学校读者我要写书评

暂无评论

Anomaly detection for random graphs using distributions of vertex invariants

Anomaly detection for random graphs using distributions of v...

引用

Annual Conference on Information Sciences and Systems

作者： Borges, Nash Coppersmith, Glen A. Meyer, Gerard G. L. Priebe, Carey E. Johns Hopkins University Human Language Technology Center of Excellence United States Johns Hopkins University Department of Electrical and Computer Engineering United States Johns Hopkins University Department of Applied Mathematics and Statistics United States

ISBN: (纸本)9781424498475

Anomaly detection is a longstanding problem with many applications in signal processing. We consider anomaly detection on graphs, a subject which has not previously had treatment in such depth. Our approach is inspired largely by previous work [1]-[3], where anomaly detection in an acoustic signal is accomplished by measuring and comparing the distribution of localized measurements to those available from a non-anomalous signal. In similar spirit, we proceed by comparing distributions of vertex invariants to those obtained from non-anomalous graphs. Specifically, we consider homogeneous Erdös-Rényi random graphs (where each vertex is connected independently with equal probability p) to be non-anomalous, and compare them to four classes of heterogeneous alternatives (where a subset of the vertices are connected according to a different process). Our contributions are (1) a novel method of incorporating information from vertex invariants for anomaly detection on graphs, (2) a principled approach to fusing information from an arbitrary number of such statistics, and (3) evaluation on several types of anomalous graphs. We demonstrate superior performance to available state-of-the-art approaches against the specific type of anomalies optimized for, and further demonstrate superior generalization to an entire class of anomalies. © 2011 IEEE.

关键词： Graph theory

来源：评论

学校读者我要写书评

暂无评论

Hierarchical Bayesian Models for Latent Attribute Detection in Social Media 5

Hierarchical Bayesian Models for Latent Attribute Detection ...

引用

5th International AAAI Conference on Weblogs and Social Media, ICWSM 2011

作者： Rao, Delip Paul, Michael Fink, Clay Yarowsky, David Oates, Timothy Coppersmith, Glen Human Language Technology Center of Excellence Johns Hopkins University BaltimoreMD21218 United States Applied Physics Laboratory Johns Hopkins University LaurelMD20723 United States University of Maryland Baltimore County BaltimoreMD21250 United States

ISBN: (纸本)9781577355052

We present several novel minimally-supervised models for detecting latent attributes of social media users, with a focus on ethnicity and gender. Previous work on ethnicity detection has used coarse-grained widely separated classes of ethnicity and assumed the existence of large amounts of training data such as the US census, simplifying the problem. Instead, we examine content generated by users in addition to name morphophonemics to detect ethnicity and gender. Further, we address this problem in a challenging setting where the ethnicity classes are more fine grained – ethnicity classes in Nigeria – and with very limited training data. Copyright © 2011, Association for the Advancement of Artificial Intelligence (***). All rights reserved.

关键词： Bayesian networks

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：