Hypernym extraction: combining machine-learning and dependency grammar

Mostra el registre complet Registre parcial de l'ítem

• dc.contributor.author Espinosa-Anke, Luis
• dc.contributor.author Ronzano, Francesco
• dc.contributor.author Saggion, Horacio
• dc.date.accessioned 2018-12-07T08:56:41Z
• dc.date.available 2018-12-07T08:56:41Z
• dc.date.issued 2015
• dc.description Comunicació presentada a la 16th International Conference, (CICLing) celebrada del 14 al 20 d'abril de 2015 a El Caire, Egipte.
• dc.description.abstract Hypernym extraction is a crucial task for semantically motivated NLP tasks such as taxonomy and ontology learning, textual entailment or paraphrase identification. In this paper, we describe an approach to hypernym extraction from textual definitions, where machine-learning and post-classification refinement rules are combined. Our best-performing configuration shows competitive results compared to state-of-the-art systems in a well-known benchmarking dataset. The quality of our features is measured by combining them in different feature sets and by ranking them by their Information Gain score. Our experiments confirm that both syntactic and definitional information play a crucial role in the hypernym extraction task.
• dc.description.sponsorship This work is partially funded by the SKATER project, TIN2012-38584- C06-03, Ministerio de Economía y Competitividad, Secretaría de Estado de Investigación, Desarrollo e Innovación, España; and Dr. Inventor (FP7-ICT-2013.8.1 611383), programa Ramón y Cajal 2009 (RYC-2009-04291).
• dc.format.mimetype application/pdf
• dc.identifier.citation Espinosa-Anke L, Ronzano F, Saggion H. Hypernym extraction: combining machine-learning and dependency grammar. In: Gelbukh A, editors. 16th International Conference, CICLing 2015;2015 April 14-20; Cairo, Egypt. Switzerland: Springer Verlag; 2015. p. 372-83. (Lecture Notes in Computer Science; vol. 9041) DOI: 10.1007/978-3-319-18111-0_28
• dc.identifier.doi http://dx.doi.org/10.1007/978-3-319-18111-0_28
• dc.identifier.isbn 978-3-319-18111-0
• dc.identifier.issn 0302-9743
• dc.identifier.uri http://hdl.handle.net/10230/36013
• dc.language.iso eng
• dc.publisher Springer
• dc.relation.ispartof Gelbukh A, editors. 16th International Conference, CICLing 2015;2015 April 14-20; Cairo, Egypt. Switzerland: Springer Verlag; 2015. p. 372-83. (Lecture Notes in Computer Science; vol. 9041)
• dc.relation.projectID info:eu-repo/grantAgreement/EC/FP7/611383
• dc.relation.projectID info:eu-repo/grantAgreement/ES/3PN/TIN2012-38584-C06-03
• dc.rights © Springer The final publication is available at Springer via http://dx.doi.org/10.1007/978-3-319-18111-0_28
• dc.rights.accessRights info:eu-repo/semantics/openAccess
• dc.subject.keyword Parse Tree
• dc.subject.keyword Computational linguistics
• dc.subject.keyword Entity recognition
• dc.subject.keyword Dependency parsing
• dc.subject.keyword Semantic role label
• dc.title Hypernym extraction: combining machine-learning and dependency grammar
• dc.type info:eu-repo/semantics/conferenceObject
• dc.type.version info:eu-repo/semantics/acceptedVersion