Báo cáo khoa học: "A GENERAL TRANSDUCER FOR TEACHING" pdf

... G~T : A GENERAL TRANSDUCER FOR TEACHING C~TIONAL LINGUISTICS P. Shann J.L. Cochard Dalle Molle Institute for Semantic and Cognitive Studies University ... GTI~syst~m is a tree-to-tree transducer developed for teaching purposes in machine transla- tion. The transducer is a specialized production system giving the linguists the tools for express- ing infon~ation ... (Geneva Teaching Transducer) 1 is a ger~ral tree-to-tree transducer developed as a tool for training linguists in machine transla- tion and computational linguistics. The transducer is a specialized...

Báo cáo khoa học: "A Tree Transducer Model for Synchronous Tree-Adjoining Grammars" pdf

... of the Association for Computational Linguistics, pages 1067–1076,Uppsala, Sweden, 11-16 July 2010.c2010 Association for Computational LinguisticsA Tree Transducer Model for Synchronous Tree-Adjoining ... behavior, we generally do not dis-cuss trees with error symbols explicitly.4 Extended tree transducer An extended tree transducer is a theoretical modelthat computes a tree transformation. Such ... (2009) for a moredetailed exposition to XTT.5 Synchronous tree-adjoining grammarXTT are a simple, natural model for tree trans-formations, however they are not suitably ex-pressive for all...

Báo cáo khoa học: "A GENERAL COMPUTATIONAL MODEL FOR WORD-FORM RECOGNITION AND PRODUCTION" potx

... A GENERAL COMPUTATIONAL MODEL FOR WORD-FORM RECOGNITION AND PRODUCTION Kimmo Koskenniemi Department of General Linguistics Univeristy of Helsinki ... directions: the same description is utilized as such for pro- ducing surface word-forms from lexical representations, and for analyzing surface forms. As it stands now, two-level programs read ... which performs the checking needed for the i-e alternation discussed above. Instead of single characters, the automaton accepts character pairs. This automaton (and the automata for other...

Báo cáo khoa học: "A General Computational Treatment of Comparatives for Natural Language Question Answering" pptx

... structure and 2. A formal account the associated formalisms, including a BNF syntax and a denotational semantics for our "normalized parse trees" and "algebraic-logical form" language, ... Electronic Computers, 1964. Moore, R. Problems in Logical Form. 19th Meeting of the Association for Computational Linguistics, Stanford, California, 1981, pp. 117-124. PateI-Schneider, P. Small ... Theories. Canter for the Study of Language and Information, Stanford University, 1985. Thompson, B. and Thompson, F. ASK Is Transportable in Half a Dozen Ways. ACM Trans. on O~ce Information Systems...

Tài liệu Báo cáo khoa học: A facile method for expression and puriﬁcation of the Alzheimer’s disease-associated amyloid b-peptide pdf

... incu-bated for 4 days with each of the peptides (10 lm), andcells were ﬁxed and used for immunocytochemical analyses.ImmunocytochemistryNeurons were ﬁxed in 4% paraformaldehyde for 20 minat ... to transformed Ca2+-competent E. colicells (ER2566) by heat shock. The transformed cells werespread on LB agar plates containing ampicillin(50 mgÆL)1), single colonies were picked for 2 ... performed inpositive reﬂector mode, collecting data from approximately3000 and 5000 single laser shots for MS and MS ⁄ MS anal-yses, respectively.Preparation of aggregate-free monomer for ﬁbrillation...

Tài liệu Báo cáo khoa học: "A Statistical Model for Unsupervised and Semi-supervised Transliteration Mining" pptx

... labelled information for training. Our sys-tem extracts transliteration pairs in an unsupervisedfashion. It is also able to utilize labelled informationif available, obtaining improved performance.We ... of the Association for Computational Linguistics, pages 469–477,Jeju, Republic of Korea, 8-14 July 2012.c2012 Association for Computational LinguisticsA Statistical Model for Unsupervised ... alignment-basedstring similarity for transliteration mining. Thesemethods model the conditional probability distribu-tion and require supervised/semi-supervised infor-mation for learning. We propose...

Tài liệu Báo cáo khoa học: "A Gibbs Sampler for Phrasal Synchronous Grammar Induction" docx

... pnull= 10−10 for this value in the experiments we report below.784either φPzi for phrase pairs or φnull for single lan-guage phrases. We choose Dirichlet process (DP)priors for these parameters:φPzi∼ ... struc-ture make sampling considerably more efﬁcient for long sentences.Following the broad shift in the ﬁeld from ﬁnitestate transducers to grammar transducers (Chiang,2007), recent approaches to ... proce-dure for each sentence pair is non-trivial, prov-ing NP-complete for learning phrase based models(DeNero and Klein, 2008) or a high order poly-nomial (O(|f |3|e|3))1 for a sub-class...

Tài liệu Báo cáo khoa học: "A Modular Toolkit for Coreference Resolution" pdf

... a considerable engineer-ing effort, yet there is very limited avail-ability of off-the shelf tools for researcherswhose interests are not in coreference, or for researchers who want to concentrate ... standoff format of theMMAX2 annotation tool (M¨uller and Strube, 2006)with MiniDiscourse, a library that efﬁciently imple-ments a subset of MMAX2’s functions. Using ageneric format for standoff ... named entities, as well as additional in-formation such as part-of-speech tags and mergingthese information into markables that are the start-ing point for the mentions used by the coreferenceresolution...

Tài liệu Báo cáo khoa học: "A Pipeline Framework for Dependency Parsing" ppt

... allows that use of future information in ad-dition to past information. The pipeline model nat-urally allows access to all the past information.Algorithm 3 Pseudo code for the look ahead algo-rithm. ... rightmost S action taken before anon-S action happens. Note that it is possible thatthere is a relation between a and b, but we can-not perform R or L now. Therefore, we shouldconsider (a, ... children for each word). Note that State changes when a pre-diction is made and that the features extracted for the action classiﬁer also depend on State.The search algorithm will perform a search...

Tài liệu Báo cáo khoa học: "A Multimodal Interface for Access to Content in the Home" pdf

... each log file contains: general information about the system’s components, a description and time-stamp for each system event and user event, names and timestamps for the system-recorded sound ... Open-ended tasks prompted users to search for any type of information with any input modality. The tasks in the two sets paralleled each other. For example, if one set of tasks asked the user ... where 39% agreed with the former and 25% for the latter. However, in the open-ended interview, users mentioned handwrit-ing as an important back-up input choice for cases when the speech...

Xem thêm