Show simple item record

dc.contributor.authorSun, Shuo
dc.contributor.authorFomicheva, Marina
dc.contributor.authorBlain, Frederic
dc.contributor.authorChaudhary, Vishrav
dc.contributor.authorEl-Kishky, Ahmed
dc.contributor.authorRenduchintala, Adithya
dc.contributor.authorGuzman, Francisco
dc.contributor.authorSpecia, Lucia
dc.date.accessioned2020-10-07T15:25:29Z
dc.date.available2020-10-07T15:25:29Z
dc.date.issued2020-12-31
dc.identifier.citationSun, S., Fomicheva, M., Blain, F., Chaudhary, V., El-Kishky, A., Renduchintala, A., Guzman, F. and Specia, L. (2020) An exploratory study on multilingual quality estimation, Proceedings of the 1st Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics and the 10th International Joint Conference on Natural Language Processing, pp. 366-377. https://www.aclweb.org/anthology/2020.aacl-main.39en
dc.identifier.urihttp://hdl.handle.net/2436/623698
dc.descriptionThis is an accepted manuscript of an article published by ACL, available online at: https://www.aclweb.org/anthology/2020.aacl-main.39 The accepted version of the publication may differ from the final published version.en
dc.description.abstractPredicting the quality of machine translation has traditionally been addressed with language-specific models, under the assumption that the quality label distribution or linguistic features exhibit traits that are not shared across languages. An obvious disadvantage of this approach is the need for labelled data for each given language pair. We challenge this assumption by exploring different approaches to multilingual Quality Estimation (QE), including using scores from translation models. We show that these outperform singlelanguage models, particularly in less balanced quality label distributions and low-resource settings. In the extreme case of zero-shot QE, we show that it is possible to accurately predict quality for any given new language from models trained on other languages. Our findings indicate that state-of-the-art neural QE models based on powerful pre-trained representations generalise well across languages, making them more applicable in real-world settings.en
dc.formatapplication/pdfen
dc.language.isoenen
dc.publisherAssociation for Computational Linguisticsen
dc.relation.urlhttps://www.aclweb.org/anthology/2020.aacl-main.39en
dc.subjectmultilingualen
dc.subjectzero-shot learningen
dc.subjectmultitask learningen
dc.subjectquality estimationen
dc.subjectmachine translationen
dc.titleAn exploratory study on multilingual quality estimationen
dc.typeConference contributionen
dc.date.updated2020-09-11T15:29:15Z
dc.conference.nameAsia-Pacific Chapter of the Association for Computational Linguistics
pubs.finish-date2020-12-07
pubs.start-date2020-12-04
dc.date.accepted2020-09-11
rioxxterms.funderEuropean Commissionen
rioxxterms.identifier.project825303en
rioxxterms.versionAMen
rioxxterms.licenseref.urihttps://creativecommons.org/licenses/by-nc-nd/4.0/en
rioxxterms.licenseref.startdate2020-12-31en
dc.source.beginpage366
dc.source.endpage377
refterms.dateFCD2020-10-07T15:21:53Z
refterms.versionFCDAM
refterms.dateFOA2020-12-31T00:00:00Z


Files in this item

Thumbnail
Name:
sun_et_al_an_exploratory_study ...
Size:
609.7Kb
Format:
PDF

This item appears in the following Collection(s)

Show simple item record

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