Other/Unknown Material
Word Representations for Emergent Communication and Natural Language Processing
| Τίτλος: | Word Representations for Emergent Communication and Natural Language Processing |
|---|---|
| Συγγραφείς: | Kågebäck, Mikael |
| Έτος έκδοσης: | 2018 |
| Θεματικοί όροι: | Language Technology (Computational Linguistics), Computer Science, Computer Vision and Robotics (Autonomous Systems), Extractive summarisation, Emergent communication, Deep reinforcement learning, Natural language processing, Word Representations, Deep learning, Machine learning, Artificial neural networks, psy, lang |
| Περιγραφή: | The task of listing all semantic properties of a single word might seem manageable at first but as you unravel all the context dependent subtle variations in meaning that a word can encompass, you soon realize that precise mathematical definition of a word’s semantics is extremely difficult. In analogy, humans have no problem identifying their favorite pet in an image but the task of precisely defining how, is still beyond our capabilities. A solution that has proved effective in the visual domain is to solve the problem by learning abstract representations using machine learning. Inspired by the success of learned representations in computer vision, the line of work presented in this thesis will explore learned word representations in three different contexts. Starting in the domain of artificial languages, three computational frameworks for emergent communication between collaborating agents are developed in an attempt to study word representations that exhibit grounding of concepts. The first two are designed to emulate the natural development of discrete color words using deep reinforcement learning, and used to simulate the emergence of color terms that partition the continuous color spectra of visual light. The properties of the emerged color communication schema is compared to human languages to ensure its validity as a cognitive model, and subsequently the frameworks are utilized to explore central questions in cognitive science about universals in language within the semantic domain of color. Moving beyond the color domain, a third framework is developed for the less controlled environment of human faces and multi-step communication. Subsequently, as for the color domain we carefully analyze the semantic properties of the words emerged between the agents but in this case focusing on the grounding. Turning the attention to the empirical usefulness, different types of learned word representations are evaluated in the context of automatic document summarisation, word sense disambiguation, and word sense . |
| Τύπος εγγράφου: | other/unknown material |
| Γλώσσα: | unknown |
| Relation: | https://research.chalmers.se/en/publication/506086 |
| Διαθεσιμότητα: | https://research.chalmers.se/en/publication/506086 |
| Rights: | undefined |
| Αριθμός Καταχώρησης: | edsbas.266FC8CA |
| Βάση Δεδομένων: | BASE |
| FullText | Text: Availability: 0 CustomLinks: – Url: https://research.chalmers.se/en/publication/506086# Name: EDS - BASE (ns324271) Category: fullText Text: View record from BASE |
|---|---|
| Header | DbId: edsbas DbLabel: BASE An: edsbas.266FC8CA RelevancyScore: 724 AccessLevel: 3 PubType: Other/Unknown Material PubTypeId: unknown PreciseRelevancyScore: 724.436645507813 |
| IllustrationInfo | |
| Items | – Name: Title Label: Title Group: Ti Data: Word Representations for Emergent Communication and Natural Language Processing – Name: Author Label: Authors Group: Au Data: <searchLink fieldCode="AR" term="%22Kågebäck%2C+Mikael%22">Kågebäck, Mikael</searchLink> – Name: DatePubCY Label: Publication Year Group: Date Data: 2018 – Name: Subject Label: Subject Terms Group: Su Data: <searchLink fieldCode="DE" term="%22Language+Technology+%28Computational+Linguistics%29%22">Language Technology (Computational Linguistics)</searchLink><br /><searchLink fieldCode="DE" term="%22Computer+Science%22">Computer Science</searchLink><br /><searchLink fieldCode="DE" term="%22Computer+Vision+and+Robotics+%28Autonomous+Systems%29%22">Computer Vision and Robotics (Autonomous Systems)</searchLink><br /><searchLink fieldCode="DE" term="%22Extractive+summarisation%22">Extractive summarisation</searchLink><br /><searchLink fieldCode="DE" term="%22Emergent+communication%22">Emergent communication</searchLink><br /><searchLink fieldCode="DE" term="%22Deep+reinforcement+learning%22">Deep reinforcement learning</searchLink><br /><searchLink fieldCode="DE" term="%22Natural+language+processing%22">Natural language processing</searchLink><br /><searchLink fieldCode="DE" term="%22Word+Representations%22">Word Representations</searchLink><br /><searchLink fieldCode="DE" term="%22Deep+learning%22">Deep learning</searchLink><br /><searchLink fieldCode="DE" term="%22Machine+learning%22">Machine learning</searchLink><br /><searchLink fieldCode="DE" term="%22Artificial+neural+networks%22">Artificial neural networks</searchLink><br /><searchLink fieldCode="DE" term="%22psy%22">psy</searchLink><br /><searchLink fieldCode="DE" term="%22lang%22">lang</searchLink> – Name: Abstract Label: Description Group: Ab Data: The task of listing all semantic properties of a single word might seem manageable at first but as you unravel all the context dependent subtle variations in meaning that a word can encompass, you soon realize that precise mathematical definition of a word’s semantics is extremely difficult. In analogy, humans have no problem identifying their favorite pet in an image but the task of precisely defining how, is still beyond our capabilities. A solution that has proved effective in the visual domain is to solve the problem by learning abstract representations using machine learning. Inspired by the success of learned representations in computer vision, the line of work presented in this thesis will explore learned word representations in three different contexts. Starting in the domain of artificial languages, three computational frameworks for emergent communication between collaborating agents are developed in an attempt to study word representations that exhibit grounding of concepts. The first two are designed to emulate the natural development of discrete color words using deep reinforcement learning, and used to simulate the emergence of color terms that partition the continuous color spectra of visual light. The properties of the emerged color communication schema is compared to human languages to ensure its validity as a cognitive model, and subsequently the frameworks are utilized to explore central questions in cognitive science about universals in language within the semantic domain of color. Moving beyond the color domain, a third framework is developed for the less controlled environment of human faces and multi-step communication. Subsequently, as for the color domain we carefully analyze the semantic properties of the words emerged between the agents but in this case focusing on the grounding. Turning the attention to the empirical usefulness, different types of learned word representations are evaluated in the context of automatic document summarisation, word sense disambiguation, and word sense . – Name: TypeDocument Label: Document Type Group: TypDoc Data: other/unknown material – Name: Language Label: Language Group: Lang Data: unknown – Name: NoteTitleSource Label: Relation Group: SrcInfo Data: https://research.chalmers.se/en/publication/506086 – Name: URL Label: Availability Group: URL Data: https://research.chalmers.se/en/publication/506086 – Name: Copyright Label: Rights Group: Cpyrght Data: undefined – Name: AN Label: Accession Number Group: ID Data: edsbas.266FC8CA |
| PLink | https://search.ebscohost.com/login.aspx?direct=true&site=eds-live&db=edsbas&AN=edsbas.266FC8CA |
| RecordInfo | BibRecord: BibEntity: Languages: – Text: unknown Subjects: – SubjectFull: Language Technology (Computational Linguistics) Type: general – SubjectFull: Computer Science Type: general – SubjectFull: Computer Vision and Robotics (Autonomous Systems) Type: general – SubjectFull: Extractive summarisation Type: general – SubjectFull: Emergent communication Type: general – SubjectFull: Deep reinforcement learning Type: general – SubjectFull: Natural language processing Type: general – SubjectFull: Word Representations Type: general – SubjectFull: Deep learning Type: general – SubjectFull: Machine learning Type: general – SubjectFull: Artificial neural networks Type: general – SubjectFull: psy Type: general – SubjectFull: lang Type: general Titles: – TitleFull: Word Representations for Emergent Communication and Natural Language Processing Type: main BibRelationships: HasContributorRelationships: – PersonEntity: Name: NameFull: Kågebäck, Mikael IsPartOfRelationships: – BibEntity: Dates: – D: 01 M: 01 Type: published Y: 2018 Identifiers: – Type: issn-locals Value: edsbas |
| ResultId | 1 |