Using unmarked contexts in nominal lexical semantic classification

Mostra el registre complet Registre parcial de l'ítem

• dc.contributor.author Romeo, Laurenca
• dc.contributor.author Mendes, Saraca
• dc.contributor.author Bel Rafecas, Núriaca
• dc.date.accessioned 2017-08-24T12:12:15Z
• dc.date.available 2017-08-24T12:12:15Z
• dc.date.issued 2014
• dc.description Comunicació presentada a: COLING 2014, the 25th International Conference on Computational Linguistics, celebrat a Dublin (Irlanda), del 23 al 29 d'agost de 2014.
• dc.description.abstract The work presented here addresses the use of unmarked contexts in pattern-based nominal lexical semantic classification. We define unmarked contexts to be the counterposition of the class-indicatory, or marked, contexts. Its aim is to evaluate how unmarked contexts can be used to improve the accuracy and reliability of lexical semantic classifiers. Results demonstrate that the combined use of both types of distributional information (marked and unmarked) is crucial to improve classification. This result was replicated using two different corpora, demonstrating the robustness of the method proposed.
• dc.description.sponsorship This work was funded with the support of the SUR of the DEC of the Generalitat de Catalunya and the European Social Fund, by SKATER TIN2012-38584-C06-05, and by Fundação para a Ciência e a Tecnologia (FCT) post-doctoral fellowship SFRH/BPD/79900/2011.
• dc.format.mimetype application/pdfca
• dc.identifier.citation Romeo L, Mendes S, Bel N. Using unmarked contexts in nominal lexical semantic classification. In: Proceedings of COLING 2014, the 25th International Conference on Computational Linguistics: Technical Papers; 2014 Aug 23-29; Dublind, Ireland. Dublin: Association for Computational Linguistics (ACL); 2014. p.508-19.
• dc.identifier.uri http://hdl.handle.net/10230/32683
• dc.language.iso eng
• dc.publisher Association for Computational Linguistics (ACL)ca
• dc.relation.ispartof Proceedings of COLING 2014, the 25th International Conference on Computational Linguistics: Technical Papers; 2014 Aug 23-29; Dublind, Ireland. Dublin: Association for Computational Linguistics (ACL); 2014. p.508-19.
• dc.relation.projectID info:eu-repo/grantAgreement/ES/3PN/TIN2012-385
• dc.rights This work is licenced under a Creative Commons Attribution 4.0 International License. Page numbers and proceedings footer are added by the organizers. License details: http://creativecommons.org/licenses/by/4.0/
• dc.rights.accessRights info:eu-repo/semantics/openAccess
• dc.rights.uri http://creativecommons.org/licenses/by/4.0/
• dc.subject.keyword Humanidades digitales
• dc.subject.keyword Catálogos
• dc.subject.keyword Centros de competencias
• dc.subject.keyword Datos enlazados
• dc.subject.keyword Servicios web
• dc.subject.keyword Clarin IULA-UPF
• dc.subject.keyword Digital humanities
• dc.subject.keyword Catalogues
• dc.subject.keyword Competence centres
• dc.subject.keyword Linked data
• dc.subject.keyword Web services
• dc.title Using unmarked contexts in nominal lexical semantic classificationca
• dc.type info:eu-repo/semantics/conferenceObject
• dc.type.version info:eu-repo/semantics/publishedVersion