Báo cáo khoa học: "Utilizing Dependency Language Models for Graph-based Dependency Parsing Models" pptx

Tài liệu Báo cáo khoa học: "Discriminative Syntactic Language Modeling for Speech Recognition" pdf

Tài liệu Báo cáo khoa học: "Discriminative Syntactic Language Modeling for Speech Recognition" pdf

... top- down and left-corner parsing (Roark, 2001a; Roark, 2001b) and head-driven parsing (Charniak, 2001) approaches have directly used generative PCFG models as language models. In the work of Wen Wang ... Previous Work Techniques for exploiting stochastic context-free grammars for language modeling have been ex- plored for more than a decade. Early approaches included algorit...

Ngày tải lên: 20/02/2014, 15:20

8 410 0
Tài liệu Báo cáo khoa học: "A Phonotactic Language Model for Spoken Language Identification" pptx

Tài liệu Báo cáo khoa học: "A Phonotactic Language Model for Spoken Language Identification" pptx

... June 2005. c 2005 Association for Computational Linguistics A Phonotactic Language Model for Spoken Language Identification Haizhou Li and Bin Ma Institute for Infocomm Research Singapore ... the 1996 NIST Language Recognition Evaluation database. 1 Introduction Spoken language and written language are similar in many ways. Therefore, much of the research in spoken...

Ngày tải lên: 20/02/2014, 15:20

8 437 0
Báo cáo khoa học: "Mining Association Language Patterns for Negative Life Event Classification" doc

Báo cáo khoa học: "Mining Association Language Patterns for Negative Life Event Classification" doc

... (e.g., forum posts) contain large amounts of natu- ral language expressions related to negative life events, making them useful resources for build- ing more effective psychiatric services. For ... AFNLP Mining Association Language Patterns for Negative Life Event Classification Liang-Chih Yu 1 , Chien-Lung Chan 1 , Chung-Hsien Wu 2 and Chao-Cheng Lin 3 1 Department of Inf...

Ngày tải lên: 08/03/2014, 01:20

4 297 0
Báo cáo khoa học: "Joint and conditional estimation of tagging and parsing models∗" docx

Báo cáo khoa học: "Joint and conditional estimation of tagging and parsing models∗" docx

... cases, the joint models outperformed the conditional models by quite large amounts. This suggests that it may be worthwhile investigating meth- ods for maximum (joint) likelihood estimation for model ... binarization trans- formation depicted in Figure 3 loses informa- tion about pairs of non-head constituents in the same local tree (Johnson (1998) reports similiar performance degrada...

Ngày tải lên: 08/03/2014, 05:20

8 370 0
Báo cáo khoa học: "Subjective Natural Language Problems: Motivations, Applications, Characterizations, and Implications" pptx

Báo cáo khoa học: "Subjective Natural Language Problems: Motivations, Applications, Characterizations, and Implications" pptx

... directly re- late to advances in artificial natural language be- havior, improved intelligent access to information, and more agreeable and comfortable language- based human-computer interaction. As ... on sociolinguistic information in datasets can be useful properties for many problems, assuming that it is feasible and ethical for a given context. • Analysis of ethical risks and gains...

Ngày tải lên: 17/03/2014, 00:20

6 234 0
Báo cáo khoa học: "Revisiting Pivot Language Approach for Machine Translation" doc

Báo cáo khoa học: "Revisiting Pivot Language Approach for Machine Translation" doc

... introduces a third language, named the pivot language, for which there exist large source-pivot and pivot-target bilingual cor- pora. A pivot task was also designed for spoken language translation ... quality. Unfortunately, large quantities of parallel data are not readily available for some lan- guages pairs, therefore limiting the potential use of current SMT systems. In particu...

Ngày tải lên: 23/03/2014, 16:21

9 503 0
Báo cáo khoa học: "Hierarchical Bayesian Language Modelling for the Linguistically Informed" pptx

Báo cáo khoa học: "Hierarchical Bayesian Language Modelling for the Linguistically Informed" pptx

... hierarchi- cal Pitman-Yor language models (HPYLM) (Teh, 2006; Goldwater et al., 2006) are suitable for investigations into more linguistically-informed n-gram language models. Firstly, the flexibility to ... 2012. c 2012 Association for Computational Linguistics Hierarchical Bayesian Language Modelling for the Linguistically Informed Jan A. Botha Department of Computer Science...

Ngày tải lên: 24/03/2014, 03:20

10 349 0
Tài liệu Báo cáo khoa học: "Empirically Estimating Order Constraints for Content Planning in Generation" pptx

Tài liệu Báo cáo khoa học: "Empirically Estimating Order Constraints for Content Planning in Generation" pptx

... pattern discovery is more appropriate for our task because it allows for matching across patterns with permu- tations, for representation of wild cards and for use on smaller data sets. Similar ... decade (see (Hudak and McClure, 1999) for a recent sur- vey). Combinatorial pattern discovery, one tech- nique developed for this problem, promised to be a good fit for our task becaus...

Ngày tải lên: 20/02/2014, 18:20

8 399 0
Báo cáo khoa học: "XML-Based Data Preparation for Robust Deep Parsing" pptx

Báo cáo khoa học: "XML-Based Data Preparation for Robust Deep Parsing" pptx

... POS tag information with the existing ANLT lexical re- sources. Our view is that POS tag information for content words (nouns, verbs, adjectives, adverbs) is usually reliable and informative, ... tag infor- mation with lexical entries preserves all informa- tion in the lexical entries, including inflectional and subcategorisation information. The preserva- tion of subcategorisation informati...

Ngày tải lên: 08/03/2014, 05:20

8 332 0
Báo cáo khoa học: "Using Bilingual Parallel Corpora for Cross-Lingual Textual Entailment" pptx

Báo cáo khoa học: "Using Bilingual Parallel Corpora for Cross-Lingual Textual Entailment" pptx

... both lexical relations between single words, and contextual information useful for inference. As re- gards the algorithms, statistical models based on co- occurrence observations, similar to those ... con- dition to bridge the language gap. However, with the only exceptions represented by WordNet and Wikipedia, most of the aforementioned resources are available only for English. Multi...

Ngày tải lên: 17/03/2014, 00:20

10 284 0
w