Wolves at SemEval-2018 task 10: Semantic discrimination based on knowledge and association

Taslimipoor, Shiva; Rohanian, Omid; Ha, Le An; Corpas Pastor, Gloria; Mitkov, Ruslan

dc.contributor.author	Taslimipoor, Shiva
dc.contributor.author	Rohanian, Omid
dc.contributor.author	Ha, Le An
dc.contributor.author	Corpas Pastor, Gloria
dc.contributor.author	Mitkov, Ruslan
dc.date.accessioned	2018-10-04T13:37:35Z
dc.date.available	2018-10-04T13:37:35Z
dc.date.issued	2018-06
dc.identifier.isbn	9781948087209
dc.identifier.uri	http://hdl.handle.net/2436/621757
dc.description.abstract	This 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.sponsorship	Research Group in Computational Linguistics
dc.format	application/PDF
dc.language.iso	en
dc.publisher	Association for Computational Linguistics
dc.subject	Semantics
dc.subject	knowledge-base
dc.subject	co-occurrence
dc.subject	Conceptnet
dc.title	Wolves at SemEval-2018 task 10: Semantic discrimination based on knowledge and association
dc.type	Conference contribution
dc.identifier.journal	International Workshop on Semantic Evaluation
pubs.place-of-publication	Massachusetts Institute of Technology (MIT), Cambridge, Massachusetts
dc.date.accepted	2018-06-27
rioxxterms.funder	University of Wolverhampton
rioxxterms.identifier.project	UOW04102018OR
rioxxterms.version	AM
rioxxterms.licenseref.uri	https://creativecommons.org/licenses/by-nc-nd/4.0/
rioxxterms.licenseref.startdate	2018-06-06
refterms.dateFCD	2018-10-04T13:37:36Z
refterms.versionFCD	AM
refterms.dateFOA	2018-10-04T13:37:36Z