This is a new version of the repository. Do let us know (lindat-help at ufal.mff.cuni.cz) if you encounter any issues.
Please use the following text to cite this item or export to a predefined format:
Variš, Dušan, 2022, MCSQ Translation Models (en-ru) (v1.0), LINDAT/CLARIAH-CZ digital library at the Institute of Formal and Applied Linguistics (ÚFAL), http://hdl.handle.net/11234/1-4681.
dc.contributor.authorVariš, Dušan
dc.date.accessioned2022-03-17T16:24:43Z
dc.date.available2022-03-17T16:24:43Z
dc.date.issued2022-03-15
dc.descriptionEn-Ru translation models, exported via TensorFlow Serving, available in the Lindat translation service (https://lindat.mff.cuni.cz/services/translation/). The models were trained using the MCSQ social surveys dataset (available at https://repo.clarino.uib.no/xmlui/bitstream/handle/11509/142/mcsq_v3.zip). Their main use should be in-domain translation of social surveys. 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 MCSQ test set (BLEU): en->ru: 64.3 (train: genuine in-domain MCSQ data) ru->en: 74.7 (train: additional backtranslated in-domain MCSQ data) (Evaluated using multeval: https://github.com/jhclark/multeval)
dc.identifier.urihttp://hdl.handle.net/11234/1-4681
dc.language.isoeng
dc.language.isorus
dc.publisherCharles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)
dc.relationinfo:eu-repo/grantAgreement/EC/H2020/823782
dc.rightsCreative Commons - Attribution-NonCommercial-ShareAlike 4.0 International (CC BY-NC-SA 4.0)
dc.rights.labelPUB
dc.rights.urihttp://creativecommons.org/licenses/by-nc-sa/4.0/
dc.subjectmachine translation
dc.subjectneural machine translation
dc.subjecttransformer
dc.titleMCSQ Translation Models (en-ru) (v1.0)
dc.typetoolService
local.brandingLINDAT / CLARIAH-CZ
local.contact.personDušan Variš varis@ufal.mff.cuni.cz Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)
local.files.count2
local.files.size692188529
local.has.filesyes
local.language.nameEnglish
local.language.nameRussian
local.sponsoreuFunds EC/H2020/823782 European Union SSHOC - Social Sciences & Humanities Open Cloud info:eu-repo/grantAgreement/EC/H2020/823782
metashare.ResourceInfo#ContentInfo.detailedTypetool
metashare.ResourceInfo#ResourceComponentType#ToolServiceInfo.languageDependenttrue
 Files in this item
Name
mcsq.en-ru.zip
Size
660.12 MB
Format
application/zip
Description
English-to-Russian
MD5
221c01740843f327162953932678135a
Preview
  File Preview
Name
mcsq.ru-en.zip
Size
661.27 MB
Format
application/zip
Description
Russian-to-English
MD5
5bcec1e0a11e6b797d559984722b2557
Preview
  File Preview