Show simple item record

dc.contributor.authorZouhar, Vilém
dc.contributor.authorNovák, Michal
dc.contributor.authorŽilinec, Matúš
dc.contributor.authorBojar, Ondřej
dc.contributor.authorObregón, Mateo
dc.contributor.authorHill, Robin L
dc.contributor.authorBlain, Frédéric
dc.contributor.authorFomicheva, Marina
dc.contributor.authorSpecia, Lucia
dc.contributor.authorYankovskaya, Lisa
dc.contributor.editorToutanova, Kristina
dc.contributor.editorRumshisky, Anna
dc.contributor.editorZettlemoyer, Luke
dc.contributor.editorHakkani-Tur, Dilek
dc.contributor.editorBeltagy, Iz
dc.contributor.editorBethard, Steven
dc.contributor.editorCotterell, Ryan
dc.contributor.editorChakraborty, Tanmoy
dc.contributor.editorZhou, Yichao
dc.date.accessioned2021-04-14T11:17:36Z
dc.date.available2021-04-14T11:17:36Z
dc.date.issued2021-06-01
dc.identifier.citationZouhar, V., Novák, M., Žilinec, M. et al. (2021) Backtranslation feedback improves user confidence in MT, not quality. Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Kristina Toutanova, Anna Rumshisky, Luke Zettlemoyer, Dilek Hakkani-Tur, Iz Beltagy, Steven Bethard, Ryan Cotterell, Tanmoy Chakraborty, Yichao Zhou (Editors), Association for Computational Linguistics, pp. 151-161.en
dc.identifier.urihttp://hdl.handle.net/2436/624021
dc.descriptionThis is an accepted manuscript of an article published by ACL in Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics (NAACL 21). in June 2021. The accepted version of the publication may differ from the final published version.en
dc.description.abstractTranslating text into a language unknown to the text’s author, dubbed outbound translation, is a modern need for which the user experience has significant room for improvement, beyond the basic machine translation facility. We demonstrate this by showing three ways in which user confidence in the outbound translation, as well as its overall final quality, can be affected: backward translation, quality estimation (with alignment) and source paraphrasing. In this paper, we describe an experiment on outbound translation from English to Czech and Estonian. We examine the effects of each proposed feedback module and further focus on how the quality of machine translation systems influence these findings and the user perception of success. We show that backward translation feedback has a mixed effect on the whole process: it increases user confidence in the produced translation, but not the objective quality.en
dc.formatapplication/pdfen
dc.language.isoenen
dc.publisherAssociation for Computational Linguisticsen
dc.relation.urlhttps://www.aclweb.org/anthology/2021.naacl-main.14/en
dc.titleBacktranslation feedback improves user confidence in MT, not qualityen
dc.typeConference contributionen
dc.date.updated2021-04-13T09:15:11Z
dc.conference.name2021 Annual Conference of the North American Chapter of the Association for Computational Linguistics (NAACL 21)
pubs.finish-date2021-06-11
pubs.start-date2021-06-06
dc.date.accepted2021-03-10
rioxxterms.funderUniversity of Wolverhamptonen
rioxxterms.identifier.projectUOW14042021FBen
rioxxterms.versionVoRen
rioxxterms.licenseref.urihttps://creativecommons.org/licenses/by/4.0/en
rioxxterms.licenseref.startdate2021-12-31en
refterms.dateFCD2021-04-14T11:16:33Z
refterms.versionFCDVoR
refterms.dateFOA2021-06-10T00:00:00Z


Files in this item

Thumbnail
Name:
Blain_Backtranslation_Feedsbac ...
Size:
481.7Kb
Format:
PDF

This item appears in the following Collection(s)

Show simple item record

https://creativecommons.org/licenses/by/4.0/
Except where otherwise noted, this item's license is described as https://creativecommons.org/licenses/by/4.0/