Báo cáo khoa học: "SemTAG: a platform for specifying Tree Adjoining Grammars and performing TAG-based Semantic Construction" pptx

... ACL 2007 Demo and Poster Sessions, pages 13–16,Prague, June 2007.c2007 Association for Computational LinguisticsSemTAG: a platform for specifying Tree Adjoining Grammars and performing TAG-based ... SEMTAG namely,Feature-Based Lexicalised Tree Adjoining Gram-mar and LU. Tree Adjoining Grammars (TAG) TAG is a tree rewriting system (Joshi and Schabes, 1997). A TAGis composed of (i) two tree ... Tree Adjoining Grammars in-tegrating a compositional semantics. SEM-TAG differs from XTAG in two main ways.First, it provides an expressive grammarformalism and compiler for factorising and specifying...

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

... environments for standard uniﬁcation grammars, less attention hasbeen paid to the issue of developing such environ-ments for tree based grammars that is, grammars like Tree Adjoining Grammars (TAG) ... ((Candito, 1999), (Gaiffe et al., 2002)),2As we shall later see, a content can in fact be multi-dimensional and integrate for instance both semantic and syn-tax/semantics interface information.3We ... or Tree De-scription Grammars where the basic unit of infor-mation is a tree rather than a category encoded in a feature structure. For these grammars, two trends have emergedto automatize tree- based...

Báo cáo khoa học: "Conditions on Consistency of Probabilistic Tree Adjoining Grammars*" doc

... probability measures to Tree Adjoining Languages To gain some intuition about probability assign- ments to languages, let us take for example, a language well known to be a tree adjoining lan- ... calized grammars, there could be some auxiliary trees that are assigned some probability mass but which can never adjoin into another tree. Such auxiliary trees are termed unreachable and ... initial tree which can start a derivation must have label (A) = S. 2: axe termed initial trees and ,4 are auxiliary trees which can rewrite a tree node A E V. This rewrite step is called...

Báo cáo khoa học: "QARLA:A Framework for the Evaluation of Text Summarization Systems" pdf

... test-bed is reliable (JACKmeasure).2 Formal constraints on any evaluationframework based on similarity metricsWe are looking for a framework to evaluate au-tomatic summarisation systems objectively ... Sistemas Inform´aticosUniversidad Nacional de Educaci´on a Distanciac/Juan del Rosal, 16 - 28040 Madrid - Spain{enrique,julio,anselmo,felisa}@lsi.uned.esAbstractThis paper presents a probabilisticframework, ... probabilisticframework, QARLA, for the evaluationof text summarisation systems. The in-put of the framework is a set of man-ual (reference) summaries, a set of base-line (automatic) summaries and a set...

Báo cáo khoa học: "Towards a Resource for Lexical Semantics: A Large German Corpus with Extensive Semantic Annotation" pot

... Towards a Resource for Lexical Semantics: A Large German Corpus with Extensive Semantic AnnotationKatrin Erk and Andrea Kowalski and Sebastian Pad´o and Manfred PinkalDepartment of Computational ... implemented that will pro-vide a graphical interface for the annotation. It willdisplay the syntactic structure and allow for a graph-ical manipulation of semantic frame trees, in a simi-lar way as ... frames and frame elements as predicates thateach take a sequence of word indices as theirargument, a frame annotation can be seen as a pair (CF, CE) of two formulae, describing theframe and...

Báo cáo khoa học: "On2L - A Framework for Incremental Ontology Learning in Spoken Dialog Systems" doc

... nei-ther practicable nor feasible as the real world and its objects, models and processes are constantlychanging and so are their denotations.This work assumes that a viable approach tothis challenging ... for English and German texts to semi-automaticallycreate an ontology, which includes algorithms for term extraction, for concept association extraction and for ontology pruning.Pattern-based approaches ... domainconcept forest with the help of a semantic interpre-tation and the detection of taxonomic and similar-ity relations. KAON Text-To-Onto (Maedche and Staab, 2004) applies text mining algorithms for English...

Báo cáo khoa học: "An Integrated Platform for Computer-Aided Terminology" pdf

... validation of automatically ex- tracted clusters of term candidates by a ter- minologist and a domain expert. The validation is performed through a data-base interface. The links are automatically ... dedicated to the diagnosis support ~n pathol- ogy ([Broussais]), a semantic dictionary for the Menelas Natural Language Understanding system ([Menelas]), and a structured thesaurus for a computer-assisted ... followed by a graph-based classification. This task is basically performed by FASTR, a term normalizer, that has been adapted to the task at hand. ~F-:!etion The last step of thesaurus construc-...

Báo cáo khoa học: "Towards a Framework for Abstractive Summarization of Multimodal Documents" pot

... Inderjeet Mani and Mark T. Maybury, edi-tors, Advances in Automated Text Summarization. MITPress.Regina Barzilay and Michael Elhadad. 1997. Using lex-ical chains for text summarization. In ... Company3Comparison1GrowthSlowed1Market1MissForecast1SalesForecast1Comparison2 CounterArgument1MarketFluctuations1 Protected1EarningsForecast2AmountPerShare3EarningsForecast3AmountPerShare4SalesForecast2SalesForecast3StockOwnership1Company4EmployedAt1EarningsGrowth1Prediction4Prediction3Person2GainMarketShare1StockRating2HistoricLow1Group1Prediction1Person1EmployedAt1Company2StockRating1TargetStockPrice1AmountPerShare2StockPriceChange3StockPriceChange2LineGraph1Volatile1ChangeTrend1AmountPerShare5AmountPerShare6AmountPerShare7Figure ... in part by the National Insti-tute on Disability and Rehabilitation Research (grant#H133G080047). The author also wishes to thankKathleen McCoy, Sandra Carberry, and David Mc-Donald for their...

Báo cáo khoa học: "Char_align:A Program for Aligning Parallel Texts at the Character Level" pdf

... by AT&T Language Line's customers in whatever format they happen to be available in. All too often these texts are not available in electronic form. And even if they are available ... characters. The diagonals and squares are commonly found in dotplots of parallel text. The squares have a very simple explanation. The upper-left quadrant and the lower-right quadrant are ... Char_align: A Program for Aligning Parallel Texts at the Character Level Kenneth Ward Church AT&T Bell Laboratories 600 Mountain Avenue Murray Hill NJ, 07974-0636 kwc @research.att.com...

Tài liệu Báo cáo khoa học: "Support Vector Machines for Query-focused Summarization trained and evaluated on Pyramid data" ppt

... 2004, themanual evaluation was based on a comparison with a single human-written model. Much informationin the evaluated summaries (both human and auto-matic) was marked as “related to the ... this matching process, and ROUGE are the evaluation metrics used.As proposed by Copeck and Szpakowicz (2005),the availability of human-annotated pyramids con-stitutes a gold-standard that can ... are prone to underﬁtting and overﬁtting when data is scant (which happens in2The mean, median, standard deviation and histogram of theoverlapping distribution are calculated and included as...

Xem thêm