UPF-cobalt submission to WMT15 metrics task

Simple item page
dc.contributor.authorFomicheva, Marina
dc.contributor.authorBel Rafecas, Núria
dc.contributor.authorda Cunha Fanego, Iria
dc.contributor.authorMalinovskiy, Anton
dc.date.accessioned2019-03-14T12:02:57Z
dc.date.available2019-03-14T12:02:57Z
dc.date.issued2015
dc.descriptionComunicació presentada a: 10th Workshop on Statistical Machine Translation, celebrat a Lisboa, Portugal, del 17 al 18 de setembre de 2015.
dc.description.abstractAn important limitation of automatic evaluation metrics is that, when comparing Machine Translation (MT) to a human reference, they are often unable to discriminate between acceptable variation and the differences that are indicative of MT errors. In this paper we present UPF-Cobalt evaluation system that addresses this issue by penalizing the differences in the syntactic contexts of aligned candidate and reference words. We evaluate our metric using the data from WMT workshops of the recent years and show that it performs competitively both at segment and at system levels.
dc.description.sponsorshipThis work was supported by IULA (UPF) and the FIDGR grant program of the Generalitat de Catalunya.
dc.format.mimetypeapplication/pdf
dc.identifier.citationFomicheva M, Bel N, Da Cunha I, Malinovskiy A. UPF-cobalt submission to WMT15 metrics task. In: Bojar O, Chatterjee R, Federmann C, Haddow B, Hokamp C, Huck M, Logacheva V, Pecina P, editors. Proceedings of the Tenth Workshop on Statistical Machine Translation; 2015 Sep 17-18; Lisboa, Portugal: Association for Computational Linguistics; 2015. p. 373-9.
dc.identifier.urihttp://hdl.handle.net/10230/36827
dc.language.isoeng
dc.publisherACL (Association for Computational Linguistics)
dc.relation.ispartofBojar O, Chatterjee R, Federmann C, Haddow B, Hokamp C, Huck M, Logacheva V, Pecina P, editors. Proceedings of the Tenth Workshop on Statistical Machine Translation; 2015 Sep 17-18; Lisboa, Portugal: Association for Computational Linguistics; 2015. p. 373-9.
dc.rights© ACL, Creative Commons Attribution 3.0 License
dc.rights.accessRightsinfo:eu-repo/semantics/openAccess
dc.rights.urihttps://creativecommons.org/licenses/by/3.0/
dc.subject.keywordStatistical Machine Translation
dc.subject.keywordEvaluation metrics
dc.titleUPF-cobalt submission to WMT15 metrics task
dc.typeinfo:eu-repo/semantics/conferenceObject
dc.type.versioninfo:eu-repo/semantics/publishedVersion

Files

Original bundle

Now showing 1 - 1 of 1
Thumbnail Image
Name:
Bel_wsmt_upf.pdf
Size:
157.59 KB
Format:
Adobe Portable Document Format
Download

Collections

License

Rights