Báo cáo khoa học: "An Extensible Architecture for Integrating Natural Language Processing Techniques with Wikis" docx

... USA, 21 June 2011.c2011 Association for Computational LinguisticsWikulu: An Extensible Architecture for Integrating Natural Language Processing Techniques with WikisDaniel B¨ar, Nicolai Erbs, ... users with their everydaytasks by means of an intelligent interface.Wikulu is implemented as an extensible archi-tecture which transparently integrates natural language processing (NLP) techniques ... 2006).To solve this issue, we present the Wikulu sys-tem which uses natural language processing to sup-port wiki users with their typical tasks of adding,1Portmanteau of the Hawaiian terms...

Tài liệu Báo cáo khoa học: "AN ECLECTIC APPROACH TO BUILDING NATURAL LANGUAGE INTERFACES" pptx

... methodology can be used for any application whose sublanguage can be stated in the prescribed grammar formalism. Tereisias (Davis, 1977) provides a natural language environment for debugging a knowledge ... Rules for diagnosing problems in the circuit | IND led-2 COND[ STATE on [ FORM <sta~(O IND FORM), (t STATE FORM))> CNCL [ DEV tr~i,~torol7 t FORM <s~u.¢((, DEV), fa~ed)> t FORM ... the Linguistic coverage problem that aris~ with sublanguages. We feel this eclectic approach is a useful for building application-oriented natural language interfaces. Although we are describing...

Tài liệu Báo cáo khoa học: "An Unsupervised Model for Joint Phrase Alignment and Extraction" ppt

... Conference on Empirical Methods in Natural Language Processing. Mark Johnson, Thomas L. Grifﬁths, and Sharon Goldwa-ter. 2007b. Adaptor grammars: A framework for spec-ifying compositional nonparametric ... Information Processing Systems,19:641.Philipp Koehn et al. 2007. Moses: Open source toolkit for statistical machine translation. In Proceedings ofthe 45th Annual Meeting of the Association for ... thephrase model as a replacement for the phrase tablegenerated by heuristic extraction techniques. Using this model, we perform machine transla-tion experiments over four language pairs. We ob-serve...

Tài liệu Báo cáo khoa học: "An Ensemble Method for Selection of High Quality Parses" pdf

... Each sample is selected with- out replacement.2. Train N copies of the parsing algorithm A,each with one of the samples.3. Parse the test set with each of the N models.4. For each test sentence, ... clutter, for the ﬁlter f-score measure we use the maximumrecall (MR) baseline rather than the minimum length(ML) baseline, since the former outperforms the lat-ter. Thus, ML is only shown for the ... the number ofmodels N and the sample size S increase, and with T . Therefore, for k = 85 . . . 100 we show the valueof ﬁlter f-score with parameter k when the parame-ters conﬁguration is a relatively...

Tài liệu Báo cáo khoa học: "An Approximate Approach for Training Polynomial Kernel SVMs in Linear Time" doc

... methods, for example support vector machines (SVM) (Vapnik, 1995) are successfully applied to many natural language processing (NLP) problems. They yielded very competitive and satisfactory performance ... kernel types for particular applications. In particular to the use of polynomial kernel-based SVM, it was shown to be the most successful kernels for many natural language processing (NLP) ... Association for Computational LinguisticsAn Approximate Approach for Training Polynomial Kernel SVMs in Linear Time Yu-Chieh Wu Jie-Chi Yang Yue-Shi Lee Dept. of Computer Science and Information...

Tài liệu Báo cáo khoa học: "An Improved Parser for Data-Oriented Lexical-Functional Analysis" doc

... An Improved Parser for Data-Oriented Lexical-Functional AnalysisRens BodInformatics Research Institute, University of Leeds, Leeds LS2 9JT, UK, &Institute for Logic, Language and Computation, ... derivation for an LFG-DOPrepresentation R is a sequence of fragments thefirst of which is labeled with S and for which theiterative application of the composition operationproduces R. For an ... algorithms. The DOPmodel has also been tested as a model for humansentence processing (Bod 2000d).This paper presents ongoing work onDOP models for Lexical-Functional Grammarrepresentations, known...

Tài liệu Báo cáo khoa học: "An Integrated Environment for Computational Linguistics Experimentation" pot

... LinguaStream platformpromotes the combination of purely declarativeformalisms (when GATE is mostly based on theJAPE language and NOOJ focuses on a uniqueformalism), and allows processing streams ... on the document for each analysis step.The modularity of processing streams pro-motes the reusability of components in variouscontexts: a given module, developed for a ﬁrst processing stream ... validation becomesmore and more important for theoretical models,and the accuracy of these models can be evalu-ated either with regard to their ability to account for the reality of a given corpus...

Tài liệu Báo cáo khoa học: "An expressive formalism for describing tree-based grammars" docx

... compiler for this language. It applies techniques oflogic programming (e.g. Warren’s Ab-stract Machine), thus providing an efﬁ-cient and theoretically motivated frame-work for the processing ... the use of the system for implementing different types of tree based gram-mars. Section 5 concludes with pointers for fur-ther research and improvements.2 Linguistic formalismAs mentioned ... tree description and/or of semantic formu-las. The XMG formalism furthermore supports thesharing of identiﬁers across dimension hence al-lowing for a straightforward encoding of the syn-tax/semantics...

Tài liệu Báo cáo khoa học: "The Software Architecture for the First Challenge on Generating Instructions in Virtual Environments" docx

... effort for natural lan-guage generation systems. In this paper,we motivate and describe the software in-frastructure that we developed to supportthis challenge.1 Introduction Natural language ... Session, pages 33–36,Athens, Greece, 3 April 2009.c2009 Association for Computational LinguisticsThe Software Architecture for theFirst Challenge on Generating Instructions in Virtual EnvironmentsAlexander ... that are equally good, andﬁnding metrics that account for this variability andproduce results consistent with human judgmentsand task performance measures is difﬁcult (Belzand Gatt, 2008; Stent...

Tài liệu Báo cáo khoa học: "An annotation scheme for discourse-level argumentation in research articles" doc

... support for own work? Figure 2: Decision tree for annotation Our materials consist of 48 computational lin- guistics papers (22 for Study I, 26 for Study II), taken from the Computation and Language ... course analysts and researchers in the field of En- glish for Specific Purposes, for tasks as varied as teaching English as a foreign language, human translation and citation analysis (Myers, ... to make the scheme applicable to reliable an- notation for several non-discourse analysts (and for potential automatic annotation). For the development of our scheme, we used computational...

Xem thêm