Show simple item record

dc.contributor.authorBulat, Len
dc.contributor.authorClark, Stephenen
dc.contributor.authorShutova, Ekaterinaen
dc.date.accessioned2017-08-29T16:14:17Z
dc.date.available2017-08-29T16:14:17Z
dc.date.issued2017-04-07en
dc.identifier.urihttps://www.repository.cam.ac.uk/handle/1810/266932
dc.description.abstractOne of the key problems in computational metaphor modelling is finding the optimal level of abstraction of semantic representations, such that these are able to capture and generalise metaphorical mechanisms. In this paper we present the first metaphor identification method that uses representations constructed from property norms. Such norms have been previously shown to provide a cognitively plausible representation of concepts in terms of semantic properties. Our results demonstrate that such property-based semantic representations provide a suitable model of cross-domain knowledge projection in metaphors, outperforming standard distributional models on a metaphor identification task.
dc.languageengen
dc.titleModelling metaphor with attribute-based semanticsen
dc.typeArticle
prism.endingPage528
prism.publicationDate2017en
prism.publicationNameProceedings of the 15th Conference of the European Chapter of the Association for Computational Linguisticsen
prism.startingPage523
prism.volume2en
dc.identifier.doi10.17863/CAM.12985
dcterms.dateAccepted2017-04-04en
rioxxterms.versionofrecord10.18653/v1/E17-2084en
rioxxterms.versionVoRen
rioxxterms.licenseref.urihttp://www.rioxx.net/licenses/all-rights-reserveden
rioxxterms.licenseref.startdate2017-04-07en
rioxxterms.typeJournal Article/Reviewen
cam.issuedOnline2017-04-07en


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record