Show simple item record

dc.contributor.authorRanasinghe, Tharindu
dc.contributor.authorOrasan, Constantin
dc.contributor.authorMitkov, Ruslan
dc.date.accessioned2021-09-29T09:41:55Z
dc.date.available2021-09-29T09:41:55Z
dc.date.issued2021-08-31
dc.identifier.citationRanasinghe, T., Orasan, C. and Mitkov, R. (2021) An exploratory analysis of multilingual word-level quality estimation with cross-lingual transformers. Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Short Papers), pages 434–440 August 1–6, 2021.en
dc.identifier.isbn9781954085534en
dc.identifier.doi10.18653/v1/2021.acl-short.55en
dc.identifier.urihttp://hdl.handle.net/2436/624378
dc.description© 2021 The Authors. Published by Association for Computational Linguistics. This is an open access article available under a Creative Commons licence. The published version can be accessed at the following link on the publisher’s website: https://aclanthology.org/2021.acl-short.55en
dc.description.abstractMost studies on word-level Quality Estimation (QE) of machine translation focus on language-specific models. The obvious disadvantages of these approaches are the need for labelled data for each language pair and the high cost required to maintain several language-specific models. To overcome these problems, we explore different approaches to multilingual, word-level QE. We show that these QE models perform on par with the current language-specific models. In the cases of zero-shot and few-shot QE, we demonstrate that it is possible to accurately predict word-level quality for any given new language pair from models trained on other language pairs. Our findings suggest that the word-level QE models based on powerful pre-trained transformers that we propose in this paper generalise well across languages, making them more useful in real-world scenarios.en
dc.formatapplication/pdfen
dc.language.isoenen
dc.publisherAssociation for Computational Linguisticsen
dc.relation.urlhttps://aclanthology.org/2021.acl-short.55/en
dc.subjectcs.CLen
dc.subjectcs.AIen
dc.subjectcs.LGen
dc.subjectquality estimationen
dc.titleAn exploratory analysis of multilingual word-level quality estimation with cross-lingual transformersen
dc.typeConference contributionen
dc.date.updated2021-09-28T11:11:28Z
dc.conference.nameACL-IJCNLP 2021 11th International Joint Conference on Natural Language Processing
dc.conference.locationOnline
pubs.finish-date2021-08-06
pubs.start-date2021-08-01
dc.date.accepted2021-05-31
rioxxterms.funderUniversity of Wolverhamptonen
rioxxterms.identifier.projectUOW29092021RMen
rioxxterms.versionVoRen
rioxxterms.licenseref.urihttps://creativecommons.org/licenses/by/4.0/en
rioxxterms.licenseref.startdate2021-09-29en
dc.description.versionPublished version
refterms.dateFCD2021-09-29T09:40:16Z
refterms.versionFCDVoR
refterms.dateFOA2021-09-29T09:41:56Z


Files in this item

Thumbnail
Name:
Ranasinghe_et_al_Exploratory_a ...
Size:
552.6Kb
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/