Show simple item record

dc.contributor.authorShah, Kashif
dc.contributor.authorLogacheva, Varvara
dc.contributor.authorPaetzold, G
dc.contributor.authorBlain, Frederic
dc.contributor.authorBeck, Daniel
dc.contributor.authorBougares, Fethi
dc.contributor.authorSpecia, Lucia
dc.date.accessioned2020-09-03T10:11:22Z
dc.date.available2020-09-03T10:11:22Z
dc.date.issued2015-09-30
dc.identifier.citationShah, K., Logacheva, V., Paetzold, G., Blain, F., Beck, D., Bougares, F. and Specia, L. (2015) SHEF-NN: translation quality estimation with neural networks, Proceedings of the Tenth Workshop on Statistical Machine Translation, 17-18 September, 2015, Lisbon, Portugal.en
dc.identifier.isbn9781941643327en
dc.identifier.doi10.18653/v1/W15-3041en
dc.identifier.urihttp://hdl.handle.net/2436/623575
dc.description© 2015 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://www.aclweb.org/anthology/W15-3041en
dc.description.abstractWe describe our systems for Tasks 1 and 2 of the WMT15 Shared Task on Quality Estimation. Our submissions use (i) a continuous space language model to extract additional features for Task 1 (SHEFGP, SHEF-SVM), (ii) a continuous bagof-words model to produce word embeddings as features for Task 2 (SHEF-W2V) and (iii) a combination of features produced by QuEst++ and a feature produced with word embedding models (SHEFQuEst++). Our systems outperform the baseline as well as many other submissions. The results are especially encouraging for Task 2, where our best performing system (SHEF-W2V) only uses features learned in an unsupervised fashion.en
dc.formatapplication/pdfen
dc.language.isoenen
dc.publisherAssociation for Computational Linguisticsen
dc.relation.urlhttps://www.aclweb.org/anthology/W15-3041/en
dc.titleSHEF-NN: translation quality estimation with neural networksen
dc.typeConference contributionen
dc.date.updated2020-08-25T14:36:21Z
dc.date.accepted2015-04-30
rioxxterms.funderUniversity of Sheffielden
rioxxterms.identifier.projectUOW03092020FBen
rioxxterms.versionVoRen
rioxxterms.licenseref.urihttps://creativecommons.org/licenses/by-nc-sa/4.0/en
rioxxterms.licenseref.startdate2020-09-03en
dc.source.beginpage342
dc.source.endpage347
refterms.dateFCD2020-09-03T10:11:00Z
refterms.versionFCDVoR
refterms.dateFOA2020-09-03T10:11:23Z


Files in this item

Thumbnail
Name:
shah_et_al_2015_shef-nn.pdf
Size:
385.1Kb
Format:
PDF

This item appears in the following Collection(s)

Show simple item record

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