Show simple item record

dc.contributor.authorRei, Mareken
dc.contributor.authorBriscoe, Edwarden
dc.contributor.editorMorante, Ren
dc.contributor.editorYih, W-Ten
dc.date.accessioned2019-07-26T13:11:51Z
dc.date.available2019-07-26T13:11:51Z
dc.date.issued2014-06-26en
dc.identifier.urihttps://www.repository.cam.ac.uk/handle/1810/294973
dc.description.abstractThe task of detecting and generating hyponyms is at the core of semantic understanding of language, and has numerous practical applications. We investigate how neural network embeddings perform on this task, compared to dependency-based vector space models, and evaluate a range of similarity measures on hyponym generation. A new asymmetric similarity measure and a combination approach are described, both of which significantly improve precision. We release three new datasets of lexical vector representations trained on the BNC and our evaluation dataset for hyponym generation.
dc.language.isoenen
dc.publisherACL
dc.titleLooking for Hyponyms in Vector Space.en
dc.typeConference Object
prism.endingPage77
prism.publicationDate2014en
prism.publicationNameCoNLLen
prism.startingPage68
dc.identifier.doi10.17863/CAM.21360
dcterms.dateAccepted2014-04-21en
rioxxterms.versionAMen
rioxxterms.licenseref.urihttp://www.rioxx.net/licenses/all-rights-reserveden
rioxxterms.licenseref.startdate2014-06-26en
rioxxterms.typeConference Paper/Proceeding/Abstracten
cam.issuedOnline2014-06-26en
dc.identifier.urlhttp://www.aclweb.org/anthology/K/K14/#2014_0en
pubs.conference-nameEighteenth Conference on Computational Natural Language Learningen
pubs.conference-start-date2014-06-26en


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record