The University of Cambridge's Machine Translation Systems for WMT18
dc.contributor.author | Stahlberg, Felix | |
dc.contributor.author | Gispert, Adria de | |
dc.contributor.author | Byrne, William | |
dc.date.accessioned | 2018-09-17T12:36:47Z | |
dc.date.available | 2018-09-17T12:36:47Z | |
dc.identifier.uri | https://www.repository.cam.ac.uk/handle/1810/280290 | |
dc.description.abstract | The 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.subject | cs.CL | |
dc.subject | cs.CL | |
dc.title | The University of Cambridge's Machine Translation Systems for WMT18 | |
dc.type | Conference Object | |
prism.publicationName | Third Conference on Machine Translation (WMT18) | |
dc.identifier.doi | 10.17863/CAM.27659 | |
dcterms.dateAccepted | 2018-08-19 | |
rioxxterms.versionofrecord | 10.17863/CAM.27659 | |
rioxxterms.version | VoR | |
rioxxterms.licenseref.uri | http://www.rioxx.net/licenses/all-rights-reserved | |
rioxxterms.licenseref.startdate | 2018-08-19 | |
dc.contributor.orcid | Stahlberg, Felix [0000-0002-0430-5704] | |
rioxxterms.type | Conference Paper/Proceeding/Abstract | |
pubs.funder-project-id | EPSRC (1632937) | |
pubs.funder-project-id | Engineering and Physical Sciences Research Council (EP/L027623/1) | |
pubs.conference-name | Third Conference on Machine Translation (WMT18) | |
pubs.conference-start-date | 2018-10-31 | |
cam.orpheus.counter | 65 | * |
pubs.conference-finish-date | 2018-11-01 | |
rioxxterms.freetoread.startdate | 2100-01-01 |
Files in this item
This item appears in the following Collection(s)
-
Cambridge University Research Outputs
Research outputs of the University of Cambridge