Knowledge base unification via sense embeddings and disambiguation

Inicio | ¿Qué es? | Contacto

English | Català

Consultar RECERCAT

Por comunidades y
colecciones Por fecha Por autores Por títulos Por temas (CDU)

Consultar departamento

Por fecha Por autores Por títulos Por temas (CDU)

Estadisticas

Del documento Todo RECERCAT

Mi RECERCAT

Entrar Alertas por correo-e

Directorio de otros repositorios

RECERCAT Principal > Universitat Pompeu Fabra > Articles, congressos, llibres > Visualizar documento

Para acceder a los documentos con el texto completo, por favor, siga el siguiente enlace: http://hdl.handle.net/10230/26307

dc.contributor.author	Delli Bovi, Claudio
dc.contributor.author	Espinosa-Anke, Luis
dc.contributor.author	Navigli, Roberto
dc.date	2015
dc.identifier.citation	Delli Bovi C, Espinosa-Anke L, Navigli R. Knowledge base unification via sense embeddings and disambiguation. In: The 2015 Conference on Empirical Methods in Natural Language; 2015 Sept 17-21; Lisbon, Portugal. [Stroudsburg]: ACL (Association for Computational Linguistics); 2015. p.726-36.
dc.identifier.uri	http://hdl.handle.net/10230/26307
dc.format	application/pdf
dc.language.iso	eng
dc.publisher	ACL (Association for Computational Linguistics)
dc.relation	The 2015 Conference on Empirical Methods in Natural Language; 2015 Sept 17-21; Lisbon, Portugal. [Stroudsburg]: ACL (Association for Computational Linguistics); 2015. p.726-36.
dc.relation	info:eu-repo/grantAgreement/EC/FP7/259234
dc.rights	© ACL, Creative Commons Attribution-NonCommercial-ShareAlike 3.0 License
dc.rights	https://creativecommons.org/licenses/by-nc-sa/3.0/
dc.rights	info:eu-repo/semantics/openAccess
dc.title	Knowledge base unification via sense embeddings and disambiguation
dc.type	info:eu-repo/semantics/conferenceObject
dc.type	info:eu-repo/semantics/publishedVersion
dc.description.abstract	Paper presented at The 2015 Conference on Empirical Methods in Natural Language; 2015 Sept 17-21; Lisbon, Portugal.
dc.description.abstract	We present KB-UNIFY, a novel approach for integrating the output of different Open Information Extraction systems into a single unified and fully disambiguated knowledge repository. KB-UNIFY consists of three main steps: (1) disambiguation of relation argument pairs via a sensebased vector representation and a large unified sense inventory; (2) ranking of semantic relations according to their degree of specificity; (3) cross-resource relation alignment and merging based on the semantic similarity of domains and ranges. We tested KB-UNIFY on a set of four heterogeneous knowledge bases, obtaining high-quality results. We discuss and provide evaluations at each stage, and release output and evaluation data for the use and scrutiny of the community.
dc.description.abstract	The authors gratefully acknowledge the support of the ERC Starting Grant MultiJEDI No. 259234.

Mostrar el registro sencillo del ítem

Documentos relacionados

Otros documentos del mismo autor/a

SemEval-2018 Task 9: hypernym discovery

Camacho-Collados, Jose; Delli Bovi, Claudio; Espinosa-Anke, Luis; Oramas, Sergio; Pasini, Tommaso; Santus, Enrico; Shwartz, Vered; Navigli, Roberto; Saggion, Horacio

Definition extraction using sense-based embeddings

Espinosa-Anke, Luis; Saggion, Horacio; Delli Bovi, Claudio

Supervised distributional hypernym discovery via domain adaptation

Espinosa-Anke, Luis; Camacho-Collados, Jose; Delli Bovi, Claudio; Saggion, Horacio

Reading between the lines: overcoming data sparsity for accurate classification of lexical relationships

Necsulescu, Silvia; Mendes, Sara; Jurgens, David; Bel Rafecas, Núria; Navigli, Roberto

Extracting relations from unstructured text sources for music recommendation

Sordo, Mohamed; Oramas, Sergio; Espinosa-Anke, Luis

Accesibilidad | Aviso legal | Política de Cookies | Documentos de uso interno

Coordinación

Patrocinio