Show simple item record

dc.contributor.authorTaslimipoor, Shiva
dc.contributor.authorRohanian, Omid
dc.contributor.authorHa, Le An
dc.contributor.authorCorpas Pastor, Gloria
dc.contributor.authorMitkov, Ruslan
dc.date.accessioned2018-10-04T13:37:35Z
dc.date.available2018-10-04T13:37:35Z
dc.date.issued2018-06
dc.identifier.isbn9781948087209
dc.identifier.urihttp://hdl.handle.net/2436/621757
dc.description.abstractThis paper describes the system submitted to SemEval 2018 shared task 10 ‘Capturing Discriminative Attributes’. We use a combination of knowledge-based and co-occurrence features to capture the semantic difference between two words in relation to an attribute. We define scores based on association measures, ngram counts, word similarity, and ConceptNet relations. The system is ranked 4th (joint) on the official leaderboard of the task.
dc.description.sponsorshipResearch Group in Computational Linguistics
dc.formatapplication/PDF
dc.language.isoen
dc.publisherAssociation for Computational Linguistics
dc.subjectSemantics
dc.subjectknowledge-base
dc.subjectco-occurrence
dc.subjectConceptnet
dc.titleWolves at SemEval-2018 task 10: Semantic discrimination based on knowledge and association
dc.typeConference contribution
dc.identifier.journalInternational Workshop on Semantic Evaluation
pubs.place-of-publicationMassachusetts Institute of Technology (MIT), Cambridge, Massachusetts
dc.date.accepted2018-06-27
rioxxterms.funderUniversity of Wolverhampton
rioxxterms.identifier.projectUOW04102018OR
rioxxterms.versionAM
rioxxterms.licenseref.urihttps://creativecommons.org/licenses/by-nc-nd/4.0/
rioxxterms.licenseref.startdate2018-06-06
refterms.dateFCD2018-10-04T13:37:36Z
refterms.versionFCDAM
refterms.dateFOA2018-10-04T13:37:36Z


Files in this item

Thumbnail
Name:
semeval_task10.pdf
Size:
121.2Kb
Format:
PDF

This item appears in the following Collection(s)

Show simple item record

https://creativecommons.org/licenses/by-nc-nd/4.0/
Except where otherwise noted, this item's license is described as https://creativecommons.org/licenses/by-nc-nd/4.0/