Information extraction for knowledge base construction in the music domain

The rate at which information about music is being created and shared on the web is growing exponentially. However, the challenge of making sense of all this data remains an open problem. In this paper, we present and evaluate an Information Extraction pipeline aimed at the construction of a Music K...

ver descrição completa

Detalhes bibliográficos
Autores: Oramas, Sergio, Espinosa-Anke, Luis, Sordo, Mohamed, Saggion, Horacio, Serra, Xavier
Formato: artículo
Estado:Versión enviada para evaluación y publicación
Fecha de publicación:2016
País:España
Recursos:Universitat Pompeu Fabra
Repositorio:Repositorio Digital de la UPF
OAI Identifier:oai:repositori.upf.edu:10230/33366
Acesso em linha:http://hdl.handle.net/10230/33366
http://dx.doi.org/10.1016/j.datak.2016.06.001
Access Level:acceso abierto
Palavra-chave:Relation extraction
Entity linking
Knowledge base construction
Music recommendation
Semantic web
id ES_18808aa63cd0bdbbfe6e36fed4bbc29b
oai_identifier_str oai:repositori.upf.edu:10230/33366
network_acronym_str ES
network_name_str España
repository_id_str
spelling Information extraction for knowledge base construction in the music domainOramas, SergioEspinosa-Anke, LuisSordo, MohamedSaggion, HoracioSerra, XavierRelation extractionEntity linkingKnowledge base constructionMusic recommendationSemantic webThe rate at which information about music is being created and shared on the web is growing exponentially. However, the challenge of making sense of all this data remains an open problem. In this paper, we present and evaluate an Information Extraction pipeline aimed at the construction of a Music Knowledge Base. Our approach starts off by collecting thousands of stories about songs from the songfacts.com website. Then, we combine a state-of-the-art Entity Linking tool and a linguistically motivated rule-based algorithm to extract semantic relations between entity pairs. Next, relations with similar semantics are grouped into clusters by exploiting syntactic dependencies. These relations are ranked thanks to a novel confidence measure based on statistical and linguistic evidence. Evaluation is carried out intrinsically, by assessing each component of the pipeline, as well as in an extrinsic task, in which we evaluate the contribution of natural language explanations in music recommendation. We demonstrate that our method is able to discover novel facts with high precision, which are missing in current generic as well as music-specific knowledge repositories.This work is partially funded by the Spanish Ministry of Economy and Competitiveness under the María de Maeztu Units of Excellence Programme (MDM-2015-0502), and under the TUNER project (TIN2015-65308-C5-5-R, MINECO/FEDER, UE).Elsevier201720172016info:eu-repo/semantics/articleinfo:eu-repo/semantics/submittedVersionapplication/pdfapplication/pdfhttp://hdl.handle.net/10230/33366http://dx.doi.org/10.1016/j.datak.2016.06.001reponame:Repositorio Digital de la UPFinstname:Universitat Pompeu FabraInglésData & knowledge engineering. 2016;106:70-83.http://hdl.handle.net/10230/27021info:eu-repo/grantAgreement/ES/1PE/TIN2015-65308-C5-5-R© Elsevier http://dx.doi.org/10.1016/j.datak.2016.06.001info:eu-repo/semantics/openAccessoai:repositori.upf.edu:10230/333662026-06-12T07:21:37Z
dc.title.none.fl_str_mv Information extraction for knowledge base construction in the music domain
title Information extraction for knowledge base construction in the music domain
spellingShingle Information extraction for knowledge base construction in the music domain
Oramas, Sergio
Relation extraction
Entity linking
Knowledge base construction
Music recommendation
Semantic web
title_short Information extraction for knowledge base construction in the music domain
title_full Information extraction for knowledge base construction in the music domain
title_fullStr Information extraction for knowledge base construction in the music domain
title_full_unstemmed Information extraction for knowledge base construction in the music domain
title_sort Information extraction for knowledge base construction in the music domain
dc.creator.none.fl_str_mv Oramas, Sergio
Espinosa-Anke, Luis
Sordo, Mohamed
Saggion, Horacio
Serra, Xavier
author Oramas, Sergio
author_facet Oramas, Sergio
Espinosa-Anke, Luis
Sordo, Mohamed
Saggion, Horacio
Serra, Xavier
author_role author
author2 Espinosa-Anke, Luis
Sordo, Mohamed
Saggion, Horacio
Serra, Xavier
author2_role author
author
author
author
dc.subject.none.fl_str_mv Relation extraction
Entity linking
Knowledge base construction
Music recommendation
Semantic web
topic Relation extraction
Entity linking
Knowledge base construction
Music recommendation
Semantic web
description The rate at which information about music is being created and shared on the web is growing exponentially. However, the challenge of making sense of all this data remains an open problem. In this paper, we present and evaluate an Information Extraction pipeline aimed at the construction of a Music Knowledge Base. Our approach starts off by collecting thousands of stories about songs from the songfacts.com website. Then, we combine a state-of-the-art Entity Linking tool and a linguistically motivated rule-based algorithm to extract semantic relations between entity pairs. Next, relations with similar semantics are grouped into clusters by exploiting syntactic dependencies. These relations are ranked thanks to a novel confidence measure based on statistical and linguistic evidence. Evaluation is carried out intrinsically, by assessing each component of the pipeline, as well as in an extrinsic task, in which we evaluate the contribution of natural language explanations in music recommendation. We demonstrate that our method is able to discover novel facts with high precision, which are missing in current generic as well as music-specific knowledge repositories.
publishDate 2016
dc.date.none.fl_str_mv 2016
2017
2017
dc.type.none.fl_str_mv info:eu-repo/semantics/article
info:eu-repo/semantics/submittedVersion
format article
status_str submittedVersion
dc.identifier.none.fl_str_mv http://hdl.handle.net/10230/33366
http://dx.doi.org/10.1016/j.datak.2016.06.001
url http://hdl.handle.net/10230/33366
http://dx.doi.org/10.1016/j.datak.2016.06.001
dc.language.none.fl_str_mv Inglés
language_invalid_str_mv Inglés
dc.relation.none.fl_str_mv Data & knowledge engineering. 2016;106:70-83.
http://hdl.handle.net/10230/27021
info:eu-repo/grantAgreement/ES/1PE/TIN2015-65308-C5-5-R
dc.rights.none.fl_str_mv © Elsevier http://dx.doi.org/10.1016/j.datak.2016.06.001
info:eu-repo/semantics/openAccess
rights_invalid_str_mv © Elsevier http://dx.doi.org/10.1016/j.datak.2016.06.001
eu_rights_str_mv openAccess
dc.format.none.fl_str_mv application/pdf
application/pdf
dc.publisher.none.fl_str_mv Elsevier
publisher.none.fl_str_mv Elsevier
dc.source.none.fl_str_mv reponame:Repositorio Digital de la UPF
instname:Universitat Pompeu Fabra
instname_str Universitat Pompeu Fabra
reponame_str Repositorio Digital de la UPF
collection Repositorio Digital de la UPF
repository.name.fl_str_mv
repository.mail.fl_str_mv
_version_ 1869403989594865664
score 15.812429

Registos relacionados