Show simple item record

dc.contributor.authorBlain, Frédéric
dc.contributor.authorAletras, Nikolaos
dc.contributor.authorSpecia, Lucia
dc.date.accessioned2020-09-01T10:32:10Z
dc.date.available2020-09-01T10:32:10Z
dc.date.issued2020
dc.identifier.citationBlain, F., Aletras, N. and Specia, L. (2020) Quality in, quality out: learning from actual mistakes. In Proceedings of the 22nd Annual Conference of the European Association for Machine Translation (EAMT), edited by Forcada, M. L., Martins, A., Moniz, H., Turchi, M. et al.,Lisbon, Portugal: European Association for Machine Translation.en
dc.identifier.urihttp://hdl.handle.net/2436/623553
dc.description© 2020 The Authors. Published by European Association for Machine Translation. 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://www.aclweb.org/anthology/2020.eamt-1.16/en
dc.description.abstractApproaches to Quality Estimation (QE) of machine translation have shown promising results at predicting quality scores for translated sentences. However, QE models are often trained on noisy approximations of quality annotations derived from the proportion of post-edited words in translated sentences instead of direct human annotations of translation errors. The latter is a more reliable ground-truth but more expensive to obtain. In this paper, we present the first attempt to model the task of predicting the proportion of actual translation errors in a sentence while minimising the need for direct human annotation. For that purpose, we use transfer-learning to leverage large scale noisy annotations and small sets of high-fidelity human annotated translation errors to train QE models. Experiments on four language pairs and translations obtained by statistical and neural models show consistent gains over strong baselines.en
dc.description.sponsorshipThis work was supported by the Bergamot project (EU H2020 Grant No. 825303).en
dc.formatapplication/pdfen
dc.language.isoenen
dc.publisherEuropean Association for Machine Translationen
dc.relation.urlhttps://www.aclweb.org/anthology/2020.eamt-1.16/en
dc.titleQuality in, quality out: learning from actual mistakesen
dc.typeConference contributionen
dc.date.updated2020-08-25T14:20:42Z
rioxxterms.funderHorizon 2020en
rioxxterms.identifier.project825303en
rioxxterms.versionVoRen
rioxxterms.licenseref.urihttps://creativecommons.org/licenses/by-nd/3.0/en
rioxxterms.licenseref.startdate2020-09-01en
refterms.dateFCD2020-09-01T10:31:05Z
refterms.versionFCDVoR
refterms.dateFOA2020-09-01T00:00:00Z


Files in this item

Thumbnail
Name:
Blain_Quality_In_Quality_Out_2 ...
Size:
264.4Kb
Format:
PDF

This item appears in the following Collection(s)

Show simple item record

https://creativecommons.org/licenses/by-nd/3.0/
Except where otherwise noted, this item's license is described as https://creativecommons.org/licenses/by-nd/3.0/