Full metadata record
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Sido, Jakub | |
dc.date.accessioned | 2021-04-09T06:03:12Z | - |
dc.date.available | 2021-04-09T06:03:12Z | - |
dc.date.issued | 2020 | |
dc.identifier.uri | http://hdl.handle.net/11025/43167 | |
dc.identifier.uri | https://www.kiv.zcu.cz/cz/vyzkum/publikace/technicke-zpravy/ | |
dc.description.sponsorship | GS-2019-018 Processing of heterogeneousdata and its specialized applications | en |
dc.format | 56 s. | cs |
dc.format.mimetype | application/pdf | |
dc.language.iso | en | en |
dc.publisher | University of West Bohemia | en |
dc.rights | © 2020 University of West Bohemia | en |
dc.subject | přirozený jazyk | cs |
dc.subject | generativní modely | cs |
dc.subject | textová doména | cs |
dc.subject | umělé neuronové sítě | cs |
dc.title | Natural Language Generation | en |
dc.type | zpráva | cs |
dc.type | report | en |
dc.rights.access | openAccess | en |
dc.type.version | publishedVersion | en |
dc.description.abstract-translated | Computational systems use natural language for communication with humans moreoften in the last years. This work summarises state-of-the-art approaches in thefield of generative models, especially in the text domain. It offers a complex study ofspecific problems known from this domain and related ones like adversarial training,reinforcement learning, artificial neural networks, etc. It also addresses the usageof these models in the context of non-generative approaches and the possibility ofcombining both. | en |
dc.subject.translated | natural language | en |
dc.subject.translated | generative models | en |
dc.subject.translated | text domain | en |
dc.subject.translated | artificial neural networks | en |
Appears in Collections: | Zprávy / Reports (KIV) |
Files in This Item:
File | Description | Size | Format | |
---|---|---|---|---|
Rigo_Sido_2020_05.pdf | Plný text | 5,63 MB | Adobe PDF | View/Open |
Please use this identifier to cite or link to this item:
http://hdl.handle.net/11025/43167
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.