Solving Three Czech NLP Tasks End-to-End with Neural Models

Jindřich Libovický, Rudolf Rosa, Jindřich Helcl , Martin Popel

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

In this work, we focus on three different NLP tasks: image captioning, machine translation, and sentiment analysis. We reimplement successful approaches of other authors and adapt them to the Czech language. We provide end-to-end architectures that achieve state-of-the-art results on all of the tasks within a single sequence learning toolkit. The trained models are available both for download as well as in an online demo.
Original languageEnglish
Title of host publicationProceedings of the 18th Conference Information Technologies - Applications and Theory (ITAT 2018)
EditorsStanislav Krajci
Place of PublicationSlovakia
PublisherCEUR-WS.org
Pages138–143
Number of pages6
Publication statusPublished - 21 Sep 2018
Event18th Conference Information Technologies - Applications and Theory - , Slovakia
Duration: 21 Sep 201825 Sep 2018
http://itat.ics.upjs.sk/2018/pmwiki.php/ITAT/EnglishVersion

Publication series

NameCEUR Workshop Proceedings
PublisherCEUR-WS.org
Volume2203
ISSN (Electronic)1613-0073

Conference

Conference18th Conference Information Technologies - Applications and Theory
Abbreviated titleITAT 2018
CountrySlovakia
Period21/09/1825/09/18
Internet address

Fingerprint Dive into the research topics of 'Solving Three Czech NLP Tasks End-to-End with Neural Models'. Together they form a unique fingerprint.

Cite this