Báo cáo khoa học: " Improving Machine Learning Approaches to Coreference Resolution" potx

... Modiﬁcations to the Machine Learning FrameworkThis section studies the effect of three changes to the general machine learning framework employedby Soon et al. with the goal of improving precisionin ... Improving Machine Learning Approaches to Coreference ResolutionVincent Ng and Claire CardieDepartment of Computer ... theproblem of determining which noun phrases (NPs)refer to each real-world entity mentioned in a doc-ument. Machine learning approaches to this prob-lem have been reasonably successful, operating...

Báo cáo khoa học: "A Machine Learning Approach to Pronoun Resolution in Spoken Dialogue" docx

... A Machine Learning Approach to Pronoun Resolution in Spoken DialogueMichael Strube and Christoph M¨ullerEuropean Media Laboratory GmbHVilla BoschSchloß-Wolfsbrunnenweg ... (A3) has to have access not only to (B2) but also to (A1).3 Data3.1 CorpusOur work is based on twenty randomly chosenSwitchboard dialogues. Taken together, the dia-logues contain 30810 tokens ... the ID of the coreference class theyare part of (if any). If an expression is used to re-fer to an entity that is not referred to by any otherexpression, it is considered a singleton.Table 1...

Báo cáo khoa học: "A Machine Learning Approach to German Pronoun Resolution" docx

... rela-tion to the antecedent. The values for this at-tribute are ”direct”, ”pronominal”, and ”ISA”(hyponym-hyperonym). To mark coreference, MMAX uses coreference sets, such that every new reference to ... for German, we were able to obtain thesystem submitted by (Curran and Clark, 2003) to the 2003 CoNLL competition. In order to run therecogniser, the data needs to be tokenised, taggedand lemmatised, ... Annotation ToolThe manual annotation of the training data wasdone with the MMAX (Multi-Modal Annotationin XML) annotation tool (M¨uller and Strube,2001). The ﬁst step of coreference annotation is to identify...

Báo cáo khoa học: "A machine-learning approach to the identification of WH gaps" doc

... in-terpretation of the sentence, and could contribute to a natural language understanding or machine translation application. Since WH dependenciesalso tend to distort the surface subcategorizationproperties ... theWH operator, and train a classifier to trace down-ward from there, eventually predicting the locationof the gap. At each node we encounter, the classi-fier chooses either to recurse into one ... identify the location of the gapfrom Figure 1. At the top level, it must choose to recurse into the SQ node, and at the second level,into the VP node. Finally, within the VP subtreeit should...

Báo cáo khoa học: "Using Machine Learning Techniques to Build a Comma Checker for Basque" pdf

... (84.36% in test). There-fore, we decided to adopt this as a basis in order to get an automatic clause splitting tool for Basque. But as it is known, machine learning techniques cannot be applied ... for each token, we stored whether it was followed by a comma or not. That is, for each word (token), it was stored whether a comma was placed next to it or not. Therefore, each token in the ... chunks to the beginning and to the end of the sentence  number of nominal chunks to the begin-ning and to the end of the sentence number of subordinate-clause marks to the beginning and to...

Báo cáo khoa học: "A machine learning approach to the automatic evaluation of machine translation" potx

... A machine learning approach to the automatic evaluation of machine translationSimon Corston-Oliver, Michael Gamon and Chris BrockettMicrosoft ... present a machine learning approach to evaluating the well-formedness of output of a machine translation system, using classifiers thatlearn to distinguish human referencetranslations from machine ... evaluations must beperformed quickly and frequently in order to measure progress. This paper describes anapproach to automated evaluation designed to facilitate the identification of areas forinvestigation...

Báo cáo khoa học: "Using Machine Learning Techniques to Interpret WH-questions" potx

... 69/6 Topic Itself clues Initial component, Attribute cluesTopic 193/9 Total NOUNs Total ADJs, Total AJPs, Total PRONOUNsFocus 226/10 Initial component Topic Itself clues, Total NOUNs, Total ... queries inorder to build models that can be used to inferusers’ informational goals from queries.We describe experiments which use supervised machine learning techniques to build statisticalmodels ... Using Machine Learning Techniques to Interpret WH-questionsIngrid ZukermanSchool of Computer Science and Software EngineeringMonash UniversityClayton, Victoria 3800, AUSTRALIAingrid@csse.monash.edu.auEric...

Báo cáo khoa học: "A Machine Learning Approach to Extract Temporal Information from Texts in Swedish and Generate Animated 3D Scenes" docx

... adverbials, and rhetorical structure to an-alyze a discourse.Recently, groups have used machine learn-ing techniques to determine temporal relations.They trained automatically classifiers on hand-annotated ... usingthe TimeML scheme.We use a set of decision trees and a machine learning approach to find the relations betweenevents. As input to the second step, the decisiontrees take sequences of events ... time expressions. Inaddition to the identification of expressions, w e of-ten need to interpret them, for instance to com-pute the absolute time an expression refers to. Wetherefore augmented...

Báo cáo khoa học: "Using Machine-Learning to Assign Function Labels to Parser Output for Spanish" ppt

... present paper we use a machine- learning ap-proach in order to add Cast3LB function tags to nodes of basic constituent trees output by a prob-abilistic parser trained on Cast3LB. To our knowl-edge, ... attributed to two main factors. Firstly,the mapping from Cast3LB tags to LFG grammat-ical functions is not one -to- one. For example threeCast3LB tags (CC, MOD and ET) are all mapped to LFG ADJUNCT. ... 136–143,Sydney, July 2006.c2006 Association for Computational LinguisticsUsing Machine- Learning to Assign Function Labels to ParserOutput for SpanishGrzegorz Chrupała1and Josef van Genabith1,21National...

Báo cáo khoa học: "Using Machine Learning to Explore Human Multimodal Clariﬁcation Strategies" ppt

... to the usermodel), we would need to explore many morestrategies through interactions with users to ﬁndan optimal one. One way to reduce costs for build-ing such an optimised strategy is to ... lead to repetitive action, i.e. if a screen output was onceshown to this user, and the user has previouslyused or referred to the screen, the screen will beused over and over again.For learning ... generation and input leads to more robust interaction (Oviatt, 2002) and re-duced cognitive load (Oviatt et al., 2004). In thispaper we investigate the use of machine learning (ML) to explore human multimodal...

Xem thêm