Search results for "Sentence"

showing 10 items of 257 documents

Towards Open Domain Chatbots—A GRU Architecture for Data Driven Conversations

2018

Understanding of textual content, such as topic and intent recognition, is a critical part of chatbots, allowing the chatbot to provide relevant responses. Although successful in several narrow domains, the potential diversity of content in broader and more open domains renders traditional pattern recognition techniques inaccurate. In this paper, we propose a novel deep learning architecture for content recognition that consists of multiple levels of gated recurrent units (GRUs). The architecture is designed to capture complex sentence structure at multiple levels of abstraction, seeking content recognition for very wide domains, through a distributed scalable representation of content. To …

010302 applied physicsStructure (mathematical logic)Service (systems architecture)Computer sciencebusiness.industryDeep learning02 engineering and technologycomputer.software_genre01 natural sciencesChatbotNaive Bayes classifier020204 information systems0103 physical sciencesPattern recognition (psychology)0202 electrical engineering electronic engineering information engineeringArtificial intelligenceArchitecturebusinesscomputerNatural language processingSentence
researchProduct

Body Gestures and Spoken Sentences: A Novel Approach for Revealing User’s Emotions

2017

In the last decade, there has been a growing interest in emotion analysis research, which has been applied in several areas of computer science. Many authors have con- tributed to the development of emotion recognition algorithms, considering textual or non verbal data as input, such as facial expressions, gestures or, in the case of multi-modal emotion recognition, a combination of them. In this paper, we describe a method to detect emotions from gestures using the skeletal data obtained from Kinect-like devices as input, as well as a textual description of their meaning. The experimental results show that the correlation existing between body movements and spoken user sentence(s) can be u…

0209 industrial biotechnologyComputer scienceSpeech recognitionGesture Recognition02 engineering and technologycomputer.software_genreEmotion Recognition Gesture Recognition Sentiment AnalysisNonverbal communication020901 industrial engineering & automationSentiment Analysis0202 electrical engineering electronic engineering information engineeringEmotion recognitionSettore ING-INF/05 - Sistemi Di Elaborazione Delle InformazioniFacial expressionSettore INF/01 - Informaticabusiness.industry020207 software engineeringGesture recognitionEmotion RecognitionArtificial intelligencebusinesscomputerSentenceNatural language processingMeaning (linguistics)Gesture2017 IEEE 11th International Conference on Semantic Computing (ICSC)
researchProduct

Attention-based Model for Evaluating the Complexity of Sentences in English Language

2020

The automation of text complexity evaluation (ATCE) is an emerging problem which has been tackled by means of different methodologies. We present an effective deep learning- based solution which leverages both Recurrent Neural and the Attention mechanism. The developed system is capable of classifying sentences written in the English language by analysing their syntactical and lexical complexity. An accurate test phase has been carried out, and the system has been compared with a baseline tool based on the Support Vector Machine. This paper represents an extension of a previous deep learning model, which allows showing the suitability of Neural Networks to evaluate sentence complexity in tw…

050101 languages & linguisticsComputer scienceText simplificationcomputer.software_genredeep-learningNLPDeep Learning0501 psychology and cognitive sciencestext simplificationBaseline (configuration management)Settore ING-INF/05 - Sistemi Di Elaborazione Delle InformazioniSettore INF/01 - InformaticaArtificial neural networktext-complexity-evaluationbusiness.industryDeep learning05 social sciences050301 educationExtension (predicate logic)AutomationAutomatic Text SimplificationSupport vector machineArtificial intelligencebusiness0503 educationcomputerNatural language processingSentence
researchProduct

Deep neural attention-based model for the evaluation of italian sentences complexity

2020

In this paper, the Automatic Text Complexity Evaluation problem is modeled as a binary classification task tackled by a Neural Network based system. It exploits Recurrent Neural Units and the Attention mechanism to measure the complexity of sentences written in the Italian language. An accurate test phase has been carried out, and the system has been compared with state-of-art tools that tackle the same problem. The computed performances proof the model suitability to evaluate sentence complexity improving the results achieved by other state-of-the-art systems.

050101 languages & linguisticsExploitComputer science02 engineering and technologyText complexity evaluationMachine learningcomputer.software_genreTask (project management)Text Simplification0202 electrical engineering electronic engineering information engineering0501 psychology and cognitive sciencesSettore ING-INF/05 - Sistemi Di Elaborazione Delle InformazioniMeasure (data warehouse)Deep Neural NetworksArtificial neural networkSettore INF/01 - Informaticabusiness.industryItalian languageNatural language processing05 social sciencesComputer Science::Computation and Language (Computational Linguistics and Natural Language and Speech Processing)Deep learningText ComplexityBinary classification020201 artificial intelligence & image processingArtificial intelligenceTest phasebusinesscomputerSentence
researchProduct

What is an indirect speech act?

2019

Abstract The notion of an indirect speech act is at the very heart of cognitive pragmatics, yet, after nearly 50 years of orthodox (Searlean) speech act theory, it remains largely unclear how this notion can be explicated in a proper way. In recent years, two debates about indirect speech acts have stood out. First, a debate about the Searlean idea that indirect speech acts constitute a simultaneous realization of a secondary and a primary act. Second, a debate about the reasons for the use of indirect speech acts, in particular about whether this reason is to be seen in strategic advantages and/or observation of politeness demands. In these debates, the original pragmatic conception of sen…

050101 languages & linguisticsLinguistics and LanguageGeneral Computer SciencePoint (typography)PolitenessLiteral (mathematical logic)media_common.quotation_subject05 social sciencesCognitive pragmaticsRealization (linguistics)06 humanities and the arts0603 philosophy ethics and religionLanguage and LinguisticsIndirect speechLinguisticsSpeech actBehavioral NeuroscienceHistory and Philosophy of Science060302 philosophy0501 psychology and cognitive sciencesPsychologySentencemedia_commonPragmatics and its Interfaces as related to the Expression of Intention
researchProduct

Signs activate their written word translation in deaf adults: An ERP study on cross-modal co-activation in German Sign Language

2020

Since signs and words are perceived and produced in distinct sensory-motor systems, they do not share a phonological basis. Nevertheless, many deaf bilinguals master a spoken language with input merely based on visual cues like mouth representations of spoken words and orthographic representations of written words. Recent findings further suggest that processing of words involves cross-language cross-modal co-activation of signs in deaf and hearing bilinguals. Extending these findings in the present ERP-study, we recorded the electroencephalogram (EEG) of fifteen congenitally deaf bilinguals of German Sign Language (DGS) (native L1) and German (early L2) as they saw videos of semantically a…

050101 languages & linguisticsLinguistics and LanguageGerman Sign LanguageSign languagesign language; phonology; priming; EEG; bimodal bilingualismLanguage and LinguisticsSentence processingGerman030507 speech-language pathology & audiology03 medical and health sciencessign languagesign language linguistics psycholinguistics0501 psychology and cognitive sciencesprimingLanguage. Linguistic theory. Comparative grammarP101-41005 social sciencesBimodal bilingualismPhonologylanguage.human_languageLinguisticsphonologybimodal bilingualismlanguageeeg0305 other medical sciencePsychologyPriming (psychology)Spoken languageGlossa: a journal of general linguistics
researchProduct

Play it by ear? An ERP study of Chinese polysemous verb yǒu

2021

Abstract Mandarin Chinese yŏu is a polysemous verb. It can be interpreted as meaning either ‘have’ or ‘there be/exist’ in sentences of the form ‘NP1 yŏu NP2’, which can correspondingly be analyzed as either a Have-Possessive construction (‘NP1 has NP2’) or an existential/locative construction (‘(At/in) NP1 there is NP2’), or both. This study used event-related brain potentials to investigate whether and how the interpretation of yŏu in a given ‘NP1 yŏu NP2’ construction is determined by the semantics of the nouns involved and their relationship. Twenty-seven participants read sentences of this construction. The results showed that there were different patterns of brain activity that can be …

050101 languages & linguisticsLinguistics and LanguageInterpretation (logic)05 social sciencesVerbLocative caseMandarin ChinesePossessive050105 experimental psychologyLanguage and LinguisticsSentence processinglanguage.human_languageLinguisticsNounlanguage0501 psychology and cognitive sciencesComplementary distributionPsychologyLingua
researchProduct

Comparing the Quality of Neural Machine Translation and Professional Post-Editing

2019

This empirical corpus study explores the quality of neural machine translations (NMT) and their post-edits (NMTPE) at the German Department of the European Commission’s Directorate-General for Translation (DGT) by evaluating NMT outputs, NMTPE, and respective revisions (REV) with the automatic error annotation tool Hjerson (Popovic 2011) and the more fine-grained manual MQM framework (Lommel 2014). Results show that quality assurance measures by post-editors and revisors at the DGT are most often necessary for lexical errors. More specifically, if post-editors correct mistranslations, terminology or stylistic errors in an NMT sentence, revisors are likely to correct the same type of error i…

050101 languages & linguisticsTransitive relationMachine translationComputer sciencebusiness.industrymedia_common.quotation_subject05 social sciences02 engineering and technologycomputer.software_genrelanguage.human_languageTerminologyGermanAnnotation0202 electrical engineering electronic engineering information engineeringlanguage020201 artificial intelligence & image processing0501 psychology and cognitive sciencesQuality (business)Artificial intelligencebusinesscomputerQuality assuranceNatural language processingSentencemedia_common2019 Eleventh International Conference on Quality of Multimedia Experience (QoMEX)
researchProduct

Different Languages - Different Sentence Types? On Exclamative Sentences

2016

It is not equally easy for all languages to establish an exclamative sentence type. It seems the easiest for those languages that feature a morphological marking for an exclamative sentence type like Turkish or Vietnamese. English on the other hand is a language that does not mark exclamative clauses with an easily identifiable marker but uses certain preferred constructions, which allow us to separate a class of ‘exclamative sentences’ from other sentence types. However, there is another class of languages for which it is even harder to determine if ‘exclamative sentences’ exist as a sentence type. In those languages, these sentences share a striking amount of formal properties with senten…

060201 languages & linguisticsLinguistics and LanguagePoint (typography)Computer scienceTurkishbusiness.industryVietnameseClass (philosophy)06 humanities and the artscomputer.software_genrelanguage.human_languageLinguisticsFeature (linguistics)German0602 languages and literaturelanguageArtificial intelligencebusinesscomputerSentenceNatural language processingLanguage and Linguistics Compass
researchProduct

Combining Machine Translated Sentence Chunks from Multiple MT Systems

2018

This paper presents a hybrid machine translation (HMT) system that pursues syntactic analysis to acquire phrases of source sentences, translates the phrases using multiple online machine translation (MT) system application program interfaces (APIs) and generates output by combining translated chunks to obtain the best possible translation. The aim of this study is to improve translation quality of English – Latvian texts over each of the individual MT APIs. The selection of the best translation hypothesis is done by calculating the perplexity for each hypothesis using an n-gram language model. The result is a phrase-based multi-system machine translation system that allows to improve MT out…

060201 languages & linguisticsParsingPerplexityPhraseMachine translationComputer sciencebusiness.industry06 humanities and the arts02 engineering and technologyHybrid machine translationcomputer.software_genre0602 languages and literatureChunking (psychology)0202 electrical engineering electronic engineering information engineering020201 artificial intelligence & image processingLanguage modelArtificial intelligencebusinesscomputerNatural language processingSentence
researchProduct