Search results for "natural language"

showing 10 items of 650 documents

Mining Interpretable Rules for Sentiment and Semantic Relation Analysis Using Tsetlin Machines

2020

Tsetlin Machines (TMs) are an interpretable pattern recognition approach that captures patterns with high discriminative power from data. Patterns are represented as conjunctive clauses in propositional logic, produced using bandit-learning in the form of Tsetlin Automata. In this work, we propose a TM-based approach to two common Natural Language Processing (NLP) tasks, viz. Sentiment Analysis and Semantic Relation Categorization. By performing frequent itemset mining on the patterns produced, we show that they follow existing expert-verified rule-sets or lexicons. Further, our comparison with other widely used machine learning techniques indicates that the TM approach helps maintain inter…

Computer sciencebusiness.industrySemantic analysis (machine learning)Sentiment analysiscomputer.software_genrePropositional calculusAutomatonComputingMethodologies_PATTERNRECOGNITIONDiscriminative modelCategorizationPattern recognition (psychology)Artificial intelligencebusinesscomputerNatural language processingInterpretability
researchProduct

A Sub-Symbolic Approach to Word Modelling for Domain Specific Speech Recognition

2006

In this work a sub-symbolic technique for automatic, data driven language models construction is presented. Such a technique can be used to arrange a language-modelling module, which can be easily integrated in existing speech recognition architectures, such as the well-found HTK architecture. The proposed technique takes advantages from both the traditional LSA approach and from a novel application of a probability space metric known as "Hellinger's distance". Experimental trials are also presented, in order to validate the proposed approach.

Computer sciencebusiness.industrySpeech recognitionMachine learningcomputer.software_genreDomain (software engineering)Speech enhancementMetric (mathematics)Artificial intelligenceLanguage modelHellinger distanceHidden Markov modelbusinesscomputerNatural languageWord (computer architecture)Seventh International Workshop on Computer Architecture for Machine Perception (CAMP'05)
researchProduct

Application of the Error Correcting Grammatical Inference Method (ECGI) to Multi-Speaker Isolated Word Recognition

1988

It is well known that speech signals constitute highly structured objects which are composed of different kinds of subobjects such as words, phonemes, etc. This fact has motivated several researchers to propose different models which more or less explicitly assume the structural nature of speech. Notable examples of these models are Markov models /Bak 75/, /Jel 76/; the famous Harpy /Low 76/; Scriber and Lafs /Kla 80/; and many others works in which the convenience of some structural model of the speech objects considered is explicitly claimed /Gup 82/, /Lev 83/, /Cra 84/, /Sca 85/, /Kam 85/, /Sau 85/, /Rab 85/, /Kop 85/, /Sch 85/, /Der 86/, /Tan 86/.

Computer sciencebusiness.industryWord recognitionError correctingArtificial intelligenceMarkov modelbusinesscomputer.software_genrecomputerGrammar inductionNatural language processing
researchProduct

A practical solution to the problem of automatic word sense induction

2004

Recent studies in word sense induction are based on clustering global co-occurrence vectors, i.e. vectors that reflect the overall behavior of a word in a corpus. If a word is semantically ambiguous, this means that these vectors are mixtures of all its senses. Inducing a word's senses therefore involves the difficult problem of recovering the sense vectors from the mixtures. In this paper we argue that the demixing problem can be avoided since the contextual behavior of the senses is directly observable in the form of the local contexts of a word. From human disambiguation performance we know that the context of a word is usually sufficient to determine its sense. Based on this observation…

Computer sciencebusiness.industryWord-sense inductionComputer Science::Computation and Language (Computational Linguistics and Natural Language and Speech Processing)Context (language use)Artificial intelligenceCluster analysiscomputer.software_genrebusinesscomputerWord (computer architecture)Natural language processingSemEvalProceedings of the ACL 2004 on Interactive poster and demonstration sessions -
researchProduct

Automatic identification of word translations from unrelated English and German corpora

1999

Algorithms for the alignment of words in translated texts are well established. However, only recently new approaches have been proposed to identify word translations from non-parallel or even unrelated texts. This task is more difficult, because most statistical clues useful in the processing of parallel texts cannot be applied to non-parallel texts. Whereas for parallel texts in some studies up to 99% of the word alignments have been shown to be correct, the accuracy for non-parallel texts has been around 30% up to now. The current study, which is based on the assumption that there is a correlation between the patterns of word co-occurrences in corpora of different languages, makes a sign…

Computer sciencebusiness.industrycomputer.software_genrelanguage.human_languageLinguisticsTask (project management)GermanBilingual lexiconIdentification (information)ComputingMethodologies_DOCUMENTANDTEXTPROCESSINGlanguageArtificial intelligencebusinesscomputerNatural language processingWord (computer architecture)Proceedings of the 37th annual meeting of the Association for Computational Linguistics on Computational Linguistics -
researchProduct

Read&Answer, A Tool to Capture on-Line Processing of Electronic Texts

2009

This paper is aimed at presenting Read&Answer, a tool that records reading times, one of the main on-line methods employed in text processing research. Read&Answer allows the recording, analysis and interpretation of the learner processing in order to test specific hypotheses and explain final comprehension results. First, we will describe the tool, and then we will briefly explain some research studies using the tool. We will show how Read&Answer can be used in combination with another on-line method extensively employed in text processing research, i.e., verbal protocols, and we will also compare Read&Answer with eye movement tracking, a widely accepted on-line reading times technique.

Computer sciencebusiness.industrymedia_common.quotation_subjectInterpretation (philosophy)Eye movementcomputer.software_genreTest (assessment)ComprehensionText processingReading (process)Artificial intelligenceLine (text file)businessThink aloud protocolcomputerNatural language processingmedia_commonThe Ergonomics Open Journal
researchProduct

Grammar is the heart of language : grammar and its role in language learning among Finnish university students

2015

This article presents and discusses views on grammar and its role in formal language learning amongst Finnish university students. The results are based on a questionnaire which was distributed to students at the University of Jyväskylä as part of institutional action research. The background to the project was a feeling amongst some teachers of increased divergence between student respectively language teacher understandings of the role of grammar in language teaching. This concern raised the need to find out how students view grammar. The knowledge about thoughts on grammar amongst students would then help teachers to adjust and adept the way grammar is used in language teaching. The main…

Computer sciencefolk linguistics/sociolinguisticsTeaching methodmedia_common.quotation_subjectContext (language use)ta6121language learningwritten languageFormal languageComputingMilieux_COMPUTERSANDEDUCATIONtoimivuuskielen oppiminenfunctionalitymedia_commonGrammarnormatiivisuusLanguage acquisitionSecond-language acquisitionLinguisticskielioppiTheoryofComputation_MATHEMATICALLOGICANDFORMALLANGUAGESnormativityLanguage educationgrammaremic/eticNatural language
researchProduct

Knowledge-based verification of concatenative programming patterns inspired by natural language for resource-constrained embedded devices

2020

We propose a methodology to verify applications developed following programming patterns inspired by natural language that interact with physical environments and run on resource-constrained interconnected devices. Natural language patterns allow for the reduction of intermediate abstraction layers to map physical domain concepts into executable code avoiding the recourse to ontologies, which would need to be shared, kept up to date, and synchronized across a set of devices. Moreover, the computational paradigm we use for effective distributed execution of symbolic code on resource-constrained devices encourages the adoption of such patterns. The methodology is supported by a rule-based sys…

Computer scienceinternet of thing02 engineering and technologycomputer.software_genrelcsh:Chemical technologyBiochemistryOracleArticleAnalytical ChemistryDomain (software engineering)Softwarewireless sensor network0202 electrical engineering electronic engineering information engineeringlcsh:TP1-1185Electrical and Electronic Engineeringdistributed programmingwireless sensor networksEmbedded systemInstrumentationAbstraction (linguistics)concatenative languagessymbolic programmingSettore ING-INF/05 - Sistemi Di Elaborazione Delle InformazioniSymbolic programmingProgramming languagebusiness.industryRuntime verification020206 networking & telecommunications020207 software engineeringcomputer.file_formatforthinternet of thingsAtomic and Molecular Physics and Opticsconcatenative languageProgramming patternsembedded systemsExecutablebusinesscomputerNatural language
researchProduct

Language Learning Methodology for Adults: A Study of Linguistic Transfer

2014

Abstract The purpose of the present research is to bring together the evidence on transfer in adult L2 and L3 language acquisition and investigate the use and the relationship between languages in contact. The role of linguistic transfer ( Odlin, 1989 ) i.e. the imposition of previously learned patterns onto a new learning situation, has a facilitation or inhibition effect on the learner's progress in mastering a new language (L2 or L3). Our findings reveal that the cross-linguistic influence occurs both from the direction of the L2 to the L3 and from the L3 to the L2 ( Odlin, 2003 , Jarvis and Pavlenko, 2008 ). In the case of our participants, in the acquisition of L2 as the foreign langua…

Computer sciencelinguistic transferComprehension approachForeign languageSecond-language attritionLanguage acquisitionSecond-language acquisitionLinguisticsConstructed languageUniversal Networking LanguageLanguage transferlanguage interferenceLanguage assessmentL2/L3 acquisitionDevelopmental linguisticsLanguage educationGeneral Materials ScienceLinguistic descriptionNatural languageLanguage pedagogylanguage learning methodologyProcedia - Social and Behavioral Sciences
researchProduct

Implicit learning

2008

International audience; All of us have learned much about language, music, physical or social environment, and other complex domains, out of any intentional attempts to acquire information. This chapter describes first how studies investigating this form of learning in laboratory situations have shifted from a rule-based interpretation to interpretations assuming a progressive tuning to the statistical regularities of the environment. The next section examines the potential of statistical learning, and whether statistical learning stems from statistical computations or chunk formation. Then the acceptations in which this form of learning may be qualified as implicit are analysed. Finally, i…

Computer sciencemedia_common.quotation_subjectcomputer.software_genre050105 experimental psychology03 medical and health sciences[SCCO]Cognitive science0302 clinical medicine0501 psychology and cognitive sciencesInstance-based learningmedia_commonCognitive scienceGrammarbusiness.industryAlgorithmic learning theoryInterpretation (philosophy)05 social sciencesPsychological nativism[SCCO] Cognitive scienceImplicit learningAssociative learningArtificial intelligenceSequence learningbusinesscomputer030217 neurology & neurosurgeryNatural language processing
researchProduct