... v1, yi , . . . , vn, yn} are given as input to theME classifier, which learns how to classify newvectors v, corresponding to unseen pairs of sen-tences S1, S2.We use nine ... substitutionof a single token. Moreover, we use high-level3We use Stanford University’s tokenizer and POS-tagger,and Porter’s stemmer.4Soundex is an algorithm intended to map English names to alphanumeric ... canbe used to recognize paraphrases. Theyall employ string similarity measures ap-plied to shallow abstractions of the inputsentences, and a Maximum Entropy clas-sifier to learn how to combine...
... 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. ... 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, ... of au-tomatically acquiring LFG resources for Spanishfrom Cast3LB. Machine- learning- based Cast3LBtag assignment yields statistically-significantlyimproved LFG f-structures compared to parser-based...
... 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...
... Us-ing MachineLearning Machine learning has been used successfully to control a rule-based system that performs a dif-ferent task, namely document filtering (Wolinskiet al., 2000). The learning ... the use of learning for NERC. In-stead of using ML to construct a NERC systemthat will be used autonomously, the system con-structed by ML, according to our approach isused to monitor the performance ... Using Learning- based Filters to Detect Rule-based Filter-ing Obsolescence. In Recherche d’ InformationAssistée par Ordinateur, RIAO, Paris, France,pp.1208-1220.Using MachineLearningto Maintain...
... redesign of AI systems to conform to newknowledge is impractical, but machinelearning metho ds mightbeable to trackmuchofit.1.1.2 Wellsprings of Machine Learning Workinmachine learning is nowconverging ... variablesIntroduction toMachine Learning c1996 Nils J. Nilsson. All rights reserved.INTRODUCTION TO MACHINE LEARNING AN EARLY DRAFT OF A PROPOSEDTEXTBOOKNils J. NilssonRob otics Lab oratoryDepartment ... Bibliographical and Historical RemarksTobeadded.Every chapterwill contain abrief survey ofthe history ofthe materialcovered in thatchapter.Introduction toMachine Learning c1996 Nils...
... 104–111.J. R. Quinlan. 1993. C4.5: Programs for Machine Learning. Morgan Kaufmann.W. M. Soon, H. T. Ng, and D. Lim. 2001. A machine learning approach to coreference resolution of nounphrases. Computational ... and error-driven pruning for machinelearning ofcoreference rules. In Proc. of EMNLP, pages 55–62.V. Ng and C. Cardie. 2002b. Improving machine learn-ing approaches to coreference resolution. ... generate good can-didate partitions. Given that machinelearning ap-proaches to the problem have been promising, ourchoices will be guided by previous learning- basedcoreference systems, as described...
... now be used to generate, e.g., the string "Kim gives a table to Peter", as well as the string "Noam donates a book to Peter". However, it will not be able to generate a ... the adaption of a NLG system to a particular use of a lan- guage. 1 Introduction In recent years, a MachineLearning tech- nique known as Explanation-based Learning EBL (Mitchell, Keller, ... used for parsing to automatically spe- cialize a given source grammar to a specific domain. In that case, EBL is used as a method for adapting a general grammar and/or parser to the sub-language...
... analyze words into their components (letters or radicals) Learning to Read Chinese (Van and Zian, 1962)Starts with learningto read charactersThree stagesRelate sound/meaning to global shape ... predictor of later English reading skills, but not in Chinese Knowledge of general information and verbal memory is a good predictor of ability to read Chinese and JapaneseDifferences appear to ... variety Chinese words are often two or more morphemes, with no word boundaries indicated Chinese uses many more graphic units Learnability of English and Chinese Is it harder to learn Chinese...
... (R2XvY ))Table 5: Operators for manipulating the treespossible due to the many -to- many alignment, insertionsand deletions of terminals. So, we introduce the oper-ators to remove the interior ... rule: X1X2→ X1X2. This operator is neces-sary, we need a scheme to automatically back off to themeaningful glue or Hiero-alike rules, which may lead to acheaper derivation path for constructing ... chart decoderin C++. It generalizes over the dotted-product operator inEarley style parser, to allow us to leverage many opera-tors¯t ∈ T as above-mentioned, such as binarizations, atdifferent...
... seeks to identifya piece of text according to its author’sgeneral feeling toward their subject, be itpositive or negative. Traditional machine learning techniques have been applied to this ... by inde-pendent trained annotators), each containing 100stories. We trained a model on a dataset relating to one topic and tested that model using the other top-ics. Figure 1 shows the results ... train-ing process. Other extensions of this work are to collect more text marked-up with emoticons, and to experiment with techniques to automatically removenoisy examples from the training data.AcknowledgementsThis...
... 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, ... results support the intuitionthat ensemble methods are superior to single clas-sifiers. To put the performance of our system into per-spective, we established a baseline and an upperbound for ... for pronoun resolution is81.5. However, (Morton, 2000) only attempts to resolve singular pronouns, and there is no mentionof what percentage of total pronouns are coveredby this restriction.(Soon...
... types of extensions to the Soon etal. corpus-based approach. First, we propose andevaluate three extra-linguistic modifications to the machine learning framework, which together pro-vide substantial ... prohib-ited by the Soon system.5 ConclusionsWe investigate two methods to improve existing machine learning approaches to the problem of8Soon et al. (2001) present only the tree learned for ... RIPPERparameters are set totheirdefaultvalue except that classificationrules are induced for both the positive and negative instances.3 Modifications to the Machine Learning FrameworkThis section...
... assumes the input to her algorithm to be only referential pronouns. Thissimplifies the task considerably.7 Conclusions and Future WorkWe presented a machinelearning approach to pro-noun resolution ... (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 ... Applications, College Park, Md., 1999, pp. 47–52.Soon, Wee Meng, Hwee Tou Ng & Daniel Chung Yong Lim(2001). A machinelearning approach to coreference resolu-tion of noun phrases. Computational Linguistics,...
... 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 ... A machine- learning approach to the identification of WH gapsDerrick HigginsEducational Testing Servicedchiggin@alumni.uchicago.eduAbstractIn ... identifying gaps could also aidin automatic lexical acquisition techniques. Manyother applications are imaginable as well, usingthe gap location to inform intonation, semantics,collocation frequency,...