Show simple item record

 
dc.contributor.author Popel, Martin
dc.contributor.author Tomková, Markéta
dc.contributor.author Tomek, Jakub
dc.contributor.author Kaiser, Łukasz
dc.contributor.author Uszkoreit, Jakob
dc.contributor.author Bojar, Ondřej
dc.contributor.author Žabokrtský, Zdeněk
dc.date.accessioned 2021-07-27T15:34:23Z
dc.date.available 2021-07-27T15:34:23Z
dc.date.issued 2021-07-22
dc.identifier.uri http://hdl.handle.net/11234/1-3742
dc.description CUBBITT En-Pl translation models, exported via TensorFlow Serving, available in the Lindat translation service (https://lindat.mff.cuni.cz/services/translation/). Models are compatible with Tensor2tensor version 1.6.6. For details about the model training (data, model hyper-parameters), please contact the archive maintainer. Evaluation on newstest2020 (BLEU): en->pl: 12.3 pl->en: 20.0 (Evaluated using multeval: https://github.com/jhclark/multeval)
dc.language.iso eng
dc.language.iso pol
dc.publisher Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)
dc.relation info:eu-repo/grantAgreement/EC/H2020/645452
dc.relation.isreferencedby https://www.nature.com/articles/s41467-020-18073-9
dc.rights Creative Commons - Attribution-NonCommercial-ShareAlike 4.0 International (CC BY-NC-SA 4.0)
dc.rights.uri http://creativecommons.org/licenses/by-nc-sa/4.0/
dc.source.uri https://ufal.mff.cuni.cz/cubbitt
dc.subject machine translation
dc.subject neural machine translation
dc.subject transformer
dc.subject cubbitt
dc.title CUBBITT Translation Models (en-pl) (v1.0)
dc.type toolService
metashare.ResourceInfo#ResourceComponentType#ToolServiceInfo.languageDependent true
metashare.ResourceInfo#ContentInfo.detailedType tool
dc.rights.label PUB
has.files yes
branding LINDAT / CLARIAH-CZ
demo.uri https://lindat.mff.cuni.cz/services/translation/
contact.person Martin Popel popel@ufal.mff.cuni.cz Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)
sponsor European Union H2020-ICT-2014-1-645452 QT21: Quality Translation 21 euFunds info:eu-repo/grantAgreement/EC/H2020/645452
sponsor Czech Science Foundation 19-26934X Neural Representations in Multi-modal and Multi-lingual Modelling nationalFunds
sponsor Grantová agentura České republiky GX20-16819X LUSyD – Language Understanding: from Syntax to Discourse nationalFunds
sponsor Ministerstvo školství, mládeže a tělovýchovy České republiky LM2018101 LINDAT/CLARIAH-CZ: Digitální výzkumná infrastruktura pro jazykové technologie, umění a humanitní vědy nationalFunds
files.size 2118012944
files.count 2


 Files in this item

Icon
Name
t2t-model.en-pl.zip
Size
1010.06 MB
Format
application/zip
Description
English-to-Polish
MD5
d36c15070b5554e3c3f4d7675a991be0
 Download file  Preview
 File Preview  
Icon
Name
t2t-model.pl-en.zip
Size
1009.83 MB
Format
application/zip
Description
Polish-to-English
MD5
0cc2e1d96af0996b398ba26a5ee57b98
 Download file  Preview
 File Preview  

Show simple item record