检索结果-内蒙古大学图书馆

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： Tsuruoka, Yoshimasa Tsujii, Jun'ichi Honcho 4-1-8 Kawaguchi-shi Saitama 332-0012 Japan Department of Computer Science University of Tokyo Hongo 7-3-1 Bunkyo-ku Tokyo 113-0033 Japan School of Informatics University of Manchester POBox 88 Sackville St. Manchester M60 1QD United Kingdom

This paper presents a bidirectional inference algorithm for sequence labeling problems such as part-of-speech tagging, named entity recognition and text chunking. The algorithm can enumerate all possible decomposition structures and find the highest probability sequence together with the corresponding decomposition structure in polynomial time. We also present an efficient decoding algorithm based on the easiest-first strategy, which gives comparably good performance to full bidirectional inference with significantly lower computational cost. Experimental results of part-of-speech tagging and text chunking show that the proposed bidirectional inference methods consistently outperform unidirectional inference methods and bidirectional MEMMs give comparable performance to that achieved by state-of-the-art learning algorithms including kernel support vector machines. © 2005 Association for Computational Linguistics.

关键词： Polynomial approximation

来源：评论

学校读者我要写书评

暂无评论

Multi-perspective question answering using the OpQA corpus 05

Multi-perspective question answering using the OpQA corpus

引用

作者： Stoyanov, Veselin Cardie, Claire Wiebe, Janyce Department of Computer Science Cornell University Ithaca NY 14850 United States Department of Computer Science University of Pittsburgh Pittsburgh PA 15260 United States

We investigate techniques to support the answering of opinion-based questions. We first present the OpQA corpus of opinion questions and answers. Using the corpus, we compare and contrast the properties of fact and opinion questions and answers. based on the disparate characteristics of opinion vs. fact answers, we argue that traditional fact-based QA approaches may have difficulty in an MPQA setting without modification. As an initial step towards the development of MPQA systems, we investigate the use of machine learning and rule-based subjectivity and opinion source filters and show that they can be used to guide MPQA systems. © 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

Distinguishing mathematics notation from English text using computational geometry

Distinguishing mathematics notation from English text using ...

引用

8th International Conference on Document Analysis and Recognition (ICDAR 2005)

作者： Drake, DM Baird, HS Lehigh Univ CSE Dept Bethlehem PA 18015 USA

ISBN: (纸本)0769524206

A trainable method for distinguishing between mathematics notation and natural language (here, English) in images of textlines, using computational geometry methods only with no assistance from symbol recognition, is described The input to our method is a "neighbor graph" extracted from a bilevel image of an isolated textline by the method of Kise [8]: this is a pruned form of Delaunay triangulation of the set of locations of black connected components. Our method first attempts to classify each vertex and, separately, each edge of the neighbor graph as belonging to math or English;then these results are combined to yield a classification of the entire textline. All three classifiers are automatically trainable. Features for the vertex and edge classifiers were selected semi-manually from a large number in a process driven by training data: this stage is potentially fully automatable. In experiments on images scanned from books and images generated synthetically, this methodology converged in three iterations to a textline classifier with an error rate of less than one percent.

关键词： Text processing

来源：评论

学校读者我要写书评

暂无评论

A flexible conversational dialog system for MP3 player 05

A flexible conversational dialog system for MP3 player

引用

作者： Weng, Fuliang Cavedon, Lawrence Raghunathan, Badri Mirkovic, Danilo Bei, Ben Pon-Barry, Heather Bratt, Harry Cheng, Hua Schmidt, Hauke Mishra, Rohit Lathrop, Brian Zhang, Qi Scheideck, Tobias Xu, Kui Hand-Bender, Tess Upson, Sandra Peters, Stanley Shriberg, Liz Bergmann, Carsten Research and Technology Center Robert Bosch Corp. Palo Alto CA United States Center for Study of Language and Information Stanford University Stanford CA United States Speech Technology and Research Lab SRI International Menlo Park CA United States Electronics Research Lab Volkswagen of America Palo Alto CA United States

In recent years, an increasing number of new devices have found their way into the cars we drive. Speech-operated devices in particular provide a great service to drivers by minimizing distraction, so that they can keep their hands on the wheel and their eyes on the road. This presentation will demonstrate our latest development of an in-car dialog system for an MP3 player designed under a joint research effort from Bosch RTC, VW ERL, Stanford CSLI, and SRI STAR Lab funded by NIST ATP [Weng et al 2004] with this goal in mind. This project has developed a number of new technologies, some of which are already incorporated in the system. These include: end-pointing with prosodic cues, error identification and recovering strategies, flexible multi-threaded, multi-device dialog management, and content optimization and organization strategies. A number of important language phenomena are also covered in the system's functionality. For instance, one may use words relying on context, such as 'this,' 'that,' 'it,' and 'them,' to reference items mentioned in particular use contexts. Different types of verbal revision are also permitted by the system, providing a great convenience to its users. The system supports multi-threaded dialogs so that users can diverge to a different topic before the current one is finished and still come back to the first after the second topic is done. To lower the cognitive load on the drivers, the content optimization component organizes any information given to users based on ontological structures, and may also refine users' queries via various strategies. Domain knowledge is represented using OWL, a web ontology language recommended by W3C, which should greatly facilitate its portability to new domains. © 2005 Association for Computational Linguistics.

关键词： Ontology

来源：评论

学校读者我要写书评

暂无评论

LexRank: graph-based lexical centrality as salience in text summarization

引用

JOURNAL OF ARTIFICIAL INTELLIGENCE RESEARCH 2004年第0期22卷 457-479页

作者： Erkan, G Radev, DR Univ Michigan Dept EECS Ann Arbor MI 48109 USA Univ Michigan Sch Informat Ann Arbor MI 48109 USA

We introduce a stochastic graph-based method for computing relative importance of textual units for natural language processing. We test the technique on the problem of Text Summarization (TS). Extractive TS relies on the concept of sentence salience to identify the most important sentences in a document or set of documents. Salience is typically defined in terms of the presence of particular important words or in terms of similarity to a centroid pseudo-sentence. We consider a new approach, LexRank, for computing sentence importance based on the concept of eigenvector centrality in a graph representation of sentences. In this model, a connectivity matrix based on intra-sentence cosine similarity is used as the adjacency matrix of the graph representation of sentences. Our system, based on LexRank ranked in first place in more than one task in the recent DUC 2004 evaluation. In this paper we present a detailed analysis of our approach and apply it to a larger data set including data from earlier DUC evaluations. We discuss several methods to compute centrality using the similarity graph. The results show that degree-based methods (including LexRank) outperform both centroid-based methods and other systems participating in DUC in most of the cases. Furthermore, the LexRank with threshold method outperforms the other degree-based techniques including continuous LexRank. We also show that our approach is quite insensitive to the noise in the data that may result from an imperfect topical clustering of documents.

关键词： CACNA1C gene texts TBXAS1 gene graph representations THRESHOLDING METHOD natural language processing

来源：评论

学校读者我要写书评

暂无评论

HDP 2004: proceedings of the first ACM Hardcopy Document processing workshop

HDP 2004: Proceedings of the First ACM Hardcopy Document Pro...

引用

HDP 2004: proceedings of the first ACM Hardcopy Document processing workshop

ISBN: (纸本)1581139764

The proceedings contain 10 papers from the HDP 2004: proceedings of the first ACM Hardcopy Document processing workshop. The topics discussed include: information access in the presence of OCR errors;robust document image understanding technologies;low resolution character recognition by dual eigenspace and synthetic degraded patterns;a filter based post-OCR accuracy boost system;a text image enhancement system based on segmentation and classification methods;automated layout recognition;dynamic local connectivity and its application to page segmentation;pictographic matching: a graph-based approach towards a language independent document exploitation platform;and quantifying information leakage in document redaction.

关键词： Optical character recognition

来源：评论

学校读者我要写书评

暂无评论

5th International workshop on Multiple Classifier Systems, MCS 2004

5th International Workshop on Multiple Classifier Systems, M...

引用

5th International workshop on Multiple Classifier Systems, MCS 2004

ISBN: (纸本)3540221441

The proceedings contain 37 papers. The special focus in this conference is on Bagging and Boosting. The topics include: Classifier ensembles for changing environments;classification and function estimation;boosting for noisy data;bagging decision multi-trees;a new approach to incremental learning;recursive ECOC learning machines;exact bagging with k-nearest neighbour classifiers;a maximum entropy approach;combining one-class classifiers to classify missing data;combining kernel information for support vector classification;combining classifiers using dependency-based product approximation with bayes error rate;combining dissimilarity-based one-class classifiers;a modular system for the classification of time series data;a probabilistic model using information theoretic measures for cluster ensembles;classifier fusion using triangular norms;dynamic integration of regression models;dynamic classifier selection by adaptive k-nearest-neighbourhood rule;spectral measure for multi-class problems;the relationship between classifier factorisation and performance in stochastic vector quantisation;a method for designing cost-sensitive ECOC;building graph-based classifier ensembles by random node selection;a comparison of ensemble creation techniques;multiple classifiers system for reducing influences of atypical observations;sharing training patterns among multiple classifiers;first experiments on ensembles of radial basis functions;an empirical bias-variance analysis;building diverse classifier outputs to evaluate the behavior of combination methods;an empirical comparison of hierarchical vs. two-level approaches to multiclass problems;experiments on ensembles with missing and noisy data;induced decision fusion in automated sign language interpretation and ensembles of classifiers derived from multiple prototypes and their application to handwriting recognition.

关键词：

来源：评论

学校读者我要写书评

暂无评论

An empirical study of statistical language models for contextual post-processing of Chinese script recognition

An empirical study of statistical language models for contex...

引用

International workshop on Frontiers in Handwriting Recognition

作者： Yuan-Xiang Li Chew Lim Tan School of Computing National University of Singapore Singapore

ISBN: (纸本)0769521878

It is crucial to use statistical language models (LM) to improve the accuracy of Chinese offline script recognition. In this paper, we investigate the influence of several LM on the contextual post-processing performance of Chinese script recognition. We first introduce seven LM, i.e., three conventional LM (character-based bigram, character-based trigram, word-based bigram), two class-based bigram LM and two hybrid bigram LM combining word-based bigrams and class-based bigrams. We then investigate how the LM perplexities are affected by training corpus size, smoothing methods and count cutoffs. Next, we demonstrate the above LM influence on the post-processing performance in terms of recognition accuracy, memory requirement and processing speed. Finally, we give a proposal to select a suitable LM in real recognition tasks.

关键词： natural languages Context modeling Character recognition Handwriting recognition Pattern recognition Shape Image recognition Smoothing methods Proposals Writing

来源：评论

学校读者我要写书评

暂无评论

OntoSem methods for processing semantic ellipsis 04

OntoSem methods for processing semantic ellipsis

引用

proceedings of the HLT-NAACL workshop on Computational Lexical Semantics

作者： Marjorie McShane Stephen Beale Sergei Nirenburg University of Maryland Baltimore County

This paper describes various types of semantic ellipsis and underspecification in natural language, and the ways in which the meaning of semantically elided elements is reconstructed in the Ontological Semantics (OntoSem) text processing environment. The description covers phenomena whose treatment in OntoSem has reached various levels of advancement: fully implemented, partially implemented, and described algorithmically outside of implementation. We present these research results at this point -- prior to full implementation and extensive evaluation -- for two reasons: first, new descriptive material is being reported; second, some subclasses of the phenomena in question will require a truly long-term effort whose results are best reported in installments.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Semantics synchronous understanding for robust spoken language applications

Semantics synchronous understanding for robust spoken langua...

引用

IEEE workshop on Automatic Speech Recognition and Understanding

作者： Kuansan Wang Speech Technology Group Microsoft Research Limited Redmond WA USA

ISBN: (纸本)0780379802

In this paper, we describe our recent effort in combining speech recognition and understanding into a single pass decoding process. The goal is to utilize the semantic structure not only to better handle disfluencies and improve the overall understanding accuracy, but also to shorten the response time and achieve higher interactivity. Three related techniques are instrumental in our approach. first, we employ the unified language model (ULM) to incorporate semantic schema into the recognition language model, and extend the search process from word synchronous to semantic object synchronous (SOS) decoding. Finally, we utilize sequential detection to defer, reject, or accept semantic hypotheses and execute consequent dialog actions while the user's utterance is ongoing. We incorporated these methods into SALT and HTML and conducted comparative user studies based on the MiPad scenarios. The experimental results show the system can gracefully cope with spontaneous speech and the users prefer the highly interactive nature of such systems even though there are no significant differences in the task completion rate and the understanding accuracy. However, the interactive interface does allow a more effective visual prompting strategy that contributes to the significantly lower out of grammar utterances.

关键词： Robustness natural languages Speech processing Speech recognition Automatic speech recognition Decoding Delay Pattern recognition Acoustic applications Acoustic waves

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：