Show simple item record

dc.contributor.authorStahlberg, Felix
dc.contributor.authorGispert, Adria de
dc.contributor.authorByrne, William
dc.date.accessioned2018-09-17T12:36:47Z
dc.date.available2018-09-17T12:36:47Z
dc.identifier.urihttps://www.repository.cam.ac.uk/handle/1810/280290
dc.description.abstractThe University of Cambridge submission to the WMT18 news translation task focuses on the combination of diverse models of translation. We compare recurrent, convolutional, and self-attention-based neural models on German-English, English-German, and Chinese-English. Our final system combines all neural models together with a phrase-based SMT system in an MBR-based scheme. We report small but consistent gains on top of strong Transformer ensembles.
dc.subjectcs.CL
dc.subjectcs.CL
dc.titleThe University of Cambridge's Machine Translation Systems for WMT18
dc.typeConference Object
prism.publicationNameThird Conference on Machine Translation (WMT18)
dc.identifier.doi10.17863/CAM.27659
dcterms.dateAccepted2018-08-19
rioxxterms.versionofrecord10.17863/CAM.27659
rioxxterms.versionVoR
rioxxterms.licenseref.urihttp://www.rioxx.net/licenses/all-rights-reserved
rioxxterms.licenseref.startdate2018-08-19
dc.contributor.orcidStahlberg, Felix [0000-0002-0430-5704]
rioxxterms.typeConference Paper/Proceeding/Abstract
pubs.funder-project-idEPSRC (1632937)
pubs.funder-project-idEngineering and Physical Sciences Research Council (EP/L027623/1)
pubs.conference-nameThird Conference on Machine Translation (WMT18)
pubs.conference-start-date2018-10-31
cam.orpheus.counter65*
pubs.conference-finish-date2018-11-01
rioxxterms.freetoread.startdate2100-01-01


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record