Publication:
Why neural translations are the right length

Simple item page
dc.conference.dateNovember 1 - 5, 2016
dc.conference.locationAustin, Texas
dc.conference.organizer2016 Conference on Empirical Methods in Natural Language Processing, EMNLP 2016
dc.contributor.coauthorShi, Xing
dc.contributor.coauthorKnight, Kevin
dc.contributor.departmentDepartment of Computer Engineering
dc.contributor.facultymemberYes
dc.contributor.kuauthorYüret, Deniz
dc.contributor.schoolcollegeinstituteCollege of Engineering
dc.date.accessioned2024-11-09T23:36:41Z
dc.date.issued2016
dc.description.abstractWe investigate how neural, encoder-decoder translation systems output target strings of appropriate lengths, finding that a collection of hidden units learns to explicitly implement this functionality.
dc.description.fulltextNo
dc.description.harvestedfromManual
dc.description.indexedbyScopus
dc.description.openaccessYES
dc.description.peerreviewstatusN/A
dc.description.publisherscopeInternational
dc.description.readpublishN/A
dc.description.sponsoredbyTubitakEuTÜBİTAK
dc.description.sponsorshipThis work was supported by ARL/ARO (W911NF10-1-0533), DARPA (HR0011-15-C-0115), and the Scientific and Technological Research Council of Turkey (TUBİTAK) (grants 114E628 and 215E201).
dc.description.studentpublicationNo
dc.description.versionN/A
dc.identifier.WoSQuartileN/A
dc.identifier.doi10.18653/v1/d16-1248
dc.identifier.embargoN/A
dc.identifier.endpage2282
dc.identifier.grantno114E628
dc.identifier.grantno215E201
dc.identifier.grantnoW911NF10-1-0533
dc.identifier.grantnoHR0011-15-C-0115
dc.identifier.isbn9781945626258
dc.identifier.scopus2-s2.0-85029504200
dc.identifier.startpage2278
dc.identifier.urihttps://doi.org/10.18653/v1/d16-1248
dc.identifier.urihttps://hdl.handle.net/20.500.14288/12688
dc.keywordsTranslation (languages)
dc.keywordsEncoder-decoder
dc.keywordsHidden units
dc.keywordsTranslation systems
dc.keywordsNatural language processing systems
dc.language.isoeng
dc.publisherAssociation for Computational Linguistics (ACL)
dc.relation.affiliationKoç University
dc.relation.collectionKoç University Institutional Repository
dc.relation.ispartofEMNLP 2016 - Conference on Empirical Methods in Natural Language Processing, Proceedings
dc.relation.openaccessN/A
dc.rightsN/A
dc.subjectComputer engineering
dc.titleWhy neural translations are the right length
dc.typeConference Proceeding
dspace.entity.typePublication
local.contributor.kuauthorYüret, Deniz
relation.isOrgUnitOfPublication89352e43-bf09-4ef4-82f6-6f9d0174ebae
relation.isOrgUnitOfPublication.latestForDiscovery89352e43-bf09-4ef4-82f6-6f9d0174ebae
relation.isParentOrgUnitOfPublication8e756b23-2d4a-4ce8-b1b3-62c794a8c164
relation.isParentOrgUnitOfPublication.latestForDiscovery8e756b23-2d4a-4ce8-b1b3-62c794a8c164

Files

Collections

Publications without Fulltext