Báo cáo khoa học: "Model-Based Aligner Combination Using Dual Decomposition" doc

Báo cáo khoa học: "Coordination Structure Analysis using Dual Decomposition" docx

... - 27 2012.c2012 Association for Computational LinguisticsCoordination Structure Analysis using Dual DecompositionAtsushi Hanamoto1Takuya Matsuzaki11. Department of Computer Science, University ... search algorithm. Thus, wecan regard the parser as a decoder for a weightedCFG.3.3 Dual decomposition Dual decomposition is a classical method to solvecomplex optimization problems that can ... tree z to its set of coordination structuresz = g(y).We solve this optimization problem by using dual decomposition. Figure 4 shows the result-ing algorithm. The algorithm tries to optimizethe...

Báo cáo khoa học: "Model-Based Aligner Combination Using Dual Decomposition" doc

... Oregon, June 19-24, 2011.c2011 Association for Computational LinguisticsModel-Based Aligner Combination Using Dual DecompositionJohn DeNeroGoogle Researchdenero@google.comKlaus MachereyGoogle ... technique of dual decomposition hasrecently been shown to yield state-of-the-art perfor-mance in dependency parsing (Koo et al., 2010).3.2 Dual Problem FormulationTo describe a dual decomposition ... asa combination technique (Deng and Zhou, 2009).Such a model-based approach differs from ours inthat it requires a supervised dataset and treats the di-rectional aligners’ output as ﬁxed.Combination...

Tài liệu Báo cáo khoa học: " Word Translation Disambiguation Using Bilingual Bootstrapping" doc

... )|()(tePEε with MLE using εL as data; estimate )|()(tePCε with EM Algorithm using γL for each εγC∈ as data; calculate )|( tePε as a linear combination of )|()(tePEε ... Bilingual Bootstrapping 3.1 Overview Instead of using Monolingual Bootstrapping, we propose a new method for word translation disambiguation using Bilingual Bootstrapping. In translation from ... way, we estimate )|( tePε using information from not only English but also Chinese. For)|()(tePEε, we estimate it with MLE (Maximum Likelihood Estimation) using εL as data. For...

Tài liệu Báo cáo khoa học: "Japanese Dependency Parsing Using Co-occurrence Information and a Combination of Case Elements" pdf

... possible combinations ofdependency relations. The bunsetsu combinationsand corresponding sets of particles are listed in Ta-ble 1. In the analytical process, we calculate forall the combinations ... to rerank the results obtained using anexisting machine learning based parsingmethod showed that our method can im-prove the accuracy of the results obtained using the existing method.1 IntroductionDependency ... 2006.c2006 Association for Computational LinguisticsJapanese Dependency Parsing Using Co-occurrence Information and a Combination of Case ElementsTakeshi AbekawaGraduate School of EducationUniversity...

Tài liệu Báo cáo khoa học: "Grammar Error Correction Using Pseudo-Error Sentences and Domain Adaptation" pdf

... four combinations of training corpora andmethod.• TRG: The models were trained using only thereal-error corpus (baseline).• SRC: Trained using only the pseudo-error corpus.• ALL: Trained using ... task is hinderedby the difﬁculty of collecting large error cor-pora. We tackle this problem by using pseudo-error sentences generated automatically. Fur-thermore, we apply domain adaptation, ... sentences are fromthe target domain. Experiments show that sta-ble improvement is achieved by using domainadaptation.1 IntroductionCase marks of a sentence are represented by postpo-sitional...

Tài liệu Báo cáo khoa học: "Identifying Text Polarity Using Random Walks" pptx

... achieves better performance by only using WordNet synonym, hypernym and similar to rela-tions. Adding co-occurrence statistics slightly im-proved performance, while using glosses did nothelp at ... handful of seeds is used to deﬁne thetwo polarity classes. The method is exper-imentally tested using a manually labeledset of positive and negative words. It out-performs the state of the art ... threaded discussion is an electronicdiscussion in which software tools are used to helpindividuals post messages and respond to othermessages. Threaded discussions include e-mails,e-mail...

Tài liệu Báo cáo khoa học: "Automatic Headline Generation using Character Cross-Correlation" doc

... observation of a document and the step of generat-ing a title from the estimated information source, but it was for English documents. 1.1 Headline Length One of the tasks of the Document Understanding ... contains almost two million documents with nearly 600 million words. For this work, 260 documents were selected from the cor-pus based on the following steps: • 3170 documents were selected automati-cally ... iii. All words in the original headline must be found in the document body. • 260 documents were randomly selected from the 3170 documents. After automatically generating the headlines, 3 native...

Tài liệu Báo cáo khoa học: "Generating research websites using summarisation techniques" pptx

... diffcult because individualweb pages are organised differently, since standard-ised stylesheets are often considered inappropriatefor diverse organisations.Research summary pages using stylesheets ... page.http://www.cl.cam.ac.uk/research/nl/webpage-demo/DTG.html2.1 Individual researcher summariesTo create a web page for an individual researcher,the key-phrases extracted from all the paper titlesauthored ... their websitesas a tree (e.g., department pages → research grouppages → researcher pages). Individual researcherstake responsibility for maintaining their own webpages and, in addition, researchers...

Tài liệu Báo cáo khoa học: "Extracting Comparative Sentences from Korean Text Documents Using Comparative Lexical Patterns and Machine Learning Techniques" doc

... result, we achieved signifi-cant performance, an F1-score of 88.54%, in our experiments using various web documents. 1 Introduction Comparing one entity with other entities is one of the most ... Abstract This paper proposes how to automatically identify Korean comparative sentences from text documents. This paper first investigates many comparative sentences referring to pre-vious studies ... Singapore, 4 August 2009.c2009 ACL and AFNLPExtracting Comparative Sentences from Korean Text Documents Us-ing Comparative Lexical Patterns and Machine Learning Techniques Seon Yang Department...

Tài liệu Báo cáo khoa học: "Unsupervised Relation Disambiguation Using Spectral Clustering" ppt

... The clustering result using K-means; (c) Threeelongated clusters in the 2D clustering space using Spectral clustering: two dominant eigenvectors; (d)The clustering result using Spectral-based ... mainstages: 1) Transformation of Clustering Space (Step1-4); 2) Clustering in the transformed space using Elongated K-means algorithm (Step 5-6).2.3 Transformation of Clustering SpaceWe represent ... July 2006.c2006 Association for Computational LinguisticsUnsupervised Relation Disambiguation Using Spectral ClusteringJinxiu Chen1Donghong Ji1Chew Lim Tan2Zhengyu Niu11Institute for...

Xem thêm