DC ElementWertSprache
dc.contributor.advisorWermter, Stefan-
dc.contributor.authorBothe, Chandrakant Ramesh-
dc.date.accessioned2021-03-12T10:37:11Z-
dc.date.available2021-03-12T10:37:11Z-
dc.date.issued2020-
dc.identifier.urihttps://ediss.sub.uni-hamburg.de/handle/ediss/8884-
dc.description.abstractLanguage is one of the complex but fascinating ways of communication, and it is continuously developed and maintained in the human brain. It is remarkable to study how humans understand each other in a conversation and continually learn and develop their communication skills. Understanding the meaning of the spoken or written language and interacting in that language differentiates humans from other species. Although it is difficult to define the exact working nature of the brain related to language acquisition and development, researchers find a strong relationship between different behaviours acquired based on social, cognitive, emotional and behavioural intelligence. Social robots and artificial human-like intelligent agents are the expected members of future society, where they are firmly expected to realize and exhibit verbal communication capability. In addition to the robot appearance, conversational understanding and behaviours are crucial aspects for their acceptance and co-existence in emerging society. This thesis aims to connect the knowledge from behavioural intelligence through conversational language learning with human-robot interaction (HRI). The socio-linguistic features, such as emotion, sentiment, politeness and dialogue acts, are the building blocks of the decision-making process in humans. This thesis presents extensive conversational analysis through artificial recurrent neural modelling that helps to build the robots aware of such linguistic cues. Accordingly, the thesis provides tools to analyze and investigate language on different aspects using recurrent neural networks (RNNs) and attention mechanism and eventually demonstrates an HRI scenario that facilitates robotics behavioural adaptation based on social cues. As a result, the thesis provides insights into the conversational analysis with emotion and dialogue acts, providing useful knowledge of natural language understanding for safe human-robot interaction. The primary contribution to knowledge from the study and experiments provided in this thesis is understanding the socio-linguistic features, with the motive of developing a natural language conversational system for HRI. The analytical experiments in this thesis can inform necessary future work in order to integrate social cues for robotic behavioural adaptation. Furthermore, this thesis provides knowledge to realize safer social robots in society with verbal communication capability using computational neural linguistics approaches, along with addressing the safety concerns of humans.en
dc.language.isoende_DE
dc.publisherStaats- und Universitätsbibliothek Hamburg Carl von Ossietzkyde
dc.rightshttp://purl.org/coar/access_right/c_abf2de_DE
dc.subjectArtificial Intelligenceen
dc.subjectConversational Analysisen
dc.subjectRecurrent Neural Networksen
dc.subjectNatural Language Processingen
dc.subjectSocial Robotsen
dc.subjectEmotion, Sentiment and Politenessen
dc.subject.ddc004: Informatikde_DE
dc.titleConversational Language Learning for Human-Robot Interactionen
dc.typedoctoralThesisen
dcterms.dateAccepted2020-11-18-
dc.rights.cchttps://creativecommons.org/licenses/by/4.0/de_DE
dc.rights.rshttp://rightsstatements.org/vocab/InC/1.0/-
dc.type.casraiDissertation-
dc.type.dinidoctoralThesis-
dc.type.driverdoctoralThesis-
dc.type.statusinfo:eu-repo/semantics/publishedVersionde_DE
dc.type.thesisdoctoralThesisde_DE
tuhh.type.opusDissertation-
thesis.grantor.departmentInformatikde_DE
thesis.grantor.placeHamburg-
thesis.grantor.universityOrInstitutionUniversität Hamburgde_DE
dcterms.DCMITypeText-
dc.identifier.urnurn:nbn:de:gbv:18-ediss-90853-
item.advisorGNDWermter, Stefan-
item.grantfulltextopen-
item.languageiso639-1other-
item.fulltextWith Fulltext-
item.creatorOrcidBothe, Chandrakant Ramesh-
item.creatorGNDBothe, Chandrakant Ramesh-
Enthalten in den Sammlungen:Elektronische Dissertationen und Habilitationen
Dateien zu dieser Ressource:
Datei Beschreibung Prüfsumme GrößeFormat  
bothe_dissertation.pdf8d2ce4c2c0986cad4a9a21c8ef9ae0566.63 MBAdobe PDFÖffnen/Anzeigen
Zur Kurzanzeige

Info

Seitenansichten

449
Letzte Woche
Letzten Monat
geprüft am 28.03.2024

Download(s)

609
Letzte Woche
Letzten Monat
geprüft am 28.03.2024
Werkzeuge

Google ScholarTM

Prüfe