Show simple item record

dc.contributor.authorGlavaš, G
dc.contributor.authorVulić, I
dc.date.accessioned2018-11-14T00:31:02Z
dc.date.available2018-11-14T00:31:02Z
dc.date.issued2018
dc.identifier.isbn9781948087322
dc.identifier.urihttps://www.repository.cam.ac.uk/handle/1810/285039
dc.description.abstractSemantic specialization of distributional word vectors, referred to as retrofitting, is a process of fine-tuning word vectors using external lexical knowledge in order to better embed some semantic relation. Existing retrofitting models integrate linguistic constraints directly into learning objectives and, consequently, specialize only the vectors of words from the constraints. In this work, in contrast, we transform external lexico-semantic relations into training examples which we use to learn an explicit retrofitting model (ER). The ER model allows us to learn a global specialization function and specialize the vectors of words unobserved in the training data as well. We report large gains over original distributional vector spaces in (1) intrinsic word similarity evaluation and on (2) two downstream tasks -- lexical simplification and dialog state tracking. Finally, we also successfully specialize vector spaces of new languages (i.e., unseen in the training data) by coupling ER with shared multilingual distributional vector spaces.
dc.publisherAssociation for Computational Linguistics
dc.titleExplicit retrofitting of distributional word vectors
dc.typeConference Object
prism.endingPage45
prism.publicationDate2018
prism.publicationNameACL 2018 - 56th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference (Long Papers)
prism.startingPage34
prism.volume1
dc.identifier.doi10.17863/CAM.32409
dcterms.dateAccepted2018-04-21
rioxxterms.versionofrecord10.18653/v1/p18-1004
rioxxterms.licenseref.urihttp://www.rioxx.net/licenses/all-rights-reserved
rioxxterms.licenseref.startdate2018-01-01
rioxxterms.typeConference Paper/Proceeding/Abstract
pubs.funder-project-idEuropean Research Council (648909)
pubs.conference-nameProceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
pubs.conference-start-date2018-07
pubs.conference-finish-date2018-07
rioxxterms.freetoread.startdate2019-07-10


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record