Descoberta de relacionamentos semânticos não taxonômicos entre termos ontológicos
Autor(a) principal: | |
---|---|
Data de Publicação: | 2017 |
Tipo de documento: | Dissertação |
Idioma: | por |
Título da fonte: | Repositório Institucional da UFSCAR |
Texto Completo: | https://repositorio.ufscar.br/handle/ufscar/8946 |
Resumo: | Ontologies have become an important tool to structure knowledge. However, the construction of an ontology involves a careful process of defining representative terms of the domain and its relationships, which requires a lot of time from ontology engineers and domain experts. These relationships can be taxonomic (hyponymy and meronymy), representing a taxonomy of concepts, and non-taxonomic, referring to the other relationships that occur between the nodes of this taxonomy. The main difficulties of constructing an ontology are related to the time spent by domain specialists and the necessity of guaranteeing the quality and reliability of the ontologies create. In this way, we are welcome the efforts to elaborate approaches that aim to reduce the amount of time dedicated by specialists without reducing the quality of the ontology created. In this master's project, an approach was developed for the discovery of semantic relationships between non-taxonomic ontological terms from semi-structured documents written with informal vocabularies of the Brazilian Portuguese language. Thus, it aids ontology engineers and domain experts in the arduous task of discovering the relationships between ontological terms. After the discovery of semantic relationships, the relationships were converted into a conceptual structure, generated by the Formal Concept Analysis (FCA) method. This approach was validated in two experiments, with the help of domain experts in special education. The first experiment consisted of a comparison between manually extracted relationships and automatic extraction, presenting a good value of precision, coverage and measurement F, respectively, 92%, 95% and 93%. The second experiment evaluated the relationships extracted, automatically, in the structure generated by the FCA, it gets average accuracy 86,5%.These results prove the effectiveness of the semantic relationship discovery approach. |
id |
SCAR_0b479f7f43391fa945c884d2dbaca6bc |
---|---|
oai_identifier_str |
oai:repositorio.ufscar.br:ufscar/8946 |
network_acronym_str |
SCAR |
network_name_str |
Repositório Institucional da UFSCAR |
repository_id_str |
4322 |
spelling |
Andrade, Arthur Morais deSantos, Marilde Terezinha Pradohttp://lattes.cnpq.br/9826026025118073http://lattes.cnpq.br/6141689629856076b0de828f-17e6-44a9-b78c-be2f1412db352017-08-08T18:41:15Z2017-08-08T18:41:15Z2017-02-14ANDRADE, Arthur Morais de. Descoberta de relacionamentos semânticos não taxonômicos entre termos ontológicos. 2017. Dissertação (Mestrado em Ciência da Computação) – Universidade Federal de São Carlos, São Carlos, 2017. Disponível em: https://repositorio.ufscar.br/handle/ufscar/8946.https://repositorio.ufscar.br/handle/ufscar/8946Ontologies have become an important tool to structure knowledge. However, the construction of an ontology involves a careful process of defining representative terms of the domain and its relationships, which requires a lot of time from ontology engineers and domain experts. These relationships can be taxonomic (hyponymy and meronymy), representing a taxonomy of concepts, and non-taxonomic, referring to the other relationships that occur between the nodes of this taxonomy. The main difficulties of constructing an ontology are related to the time spent by domain specialists and the necessity of guaranteeing the quality and reliability of the ontologies create. In this way, we are welcome the efforts to elaborate approaches that aim to reduce the amount of time dedicated by specialists without reducing the quality of the ontology created. In this master's project, an approach was developed for the discovery of semantic relationships between non-taxonomic ontological terms from semi-structured documents written with informal vocabularies of the Brazilian Portuguese language. Thus, it aids ontology engineers and domain experts in the arduous task of discovering the relationships between ontological terms. After the discovery of semantic relationships, the relationships were converted into a conceptual structure, generated by the Formal Concept Analysis (FCA) method. This approach was validated in two experiments, with the help of domain experts in special education. The first experiment consisted of a comparison between manually extracted relationships and automatic extraction, presenting a good value of precision, coverage and measurement F, respectively, 92%, 95% and 93%. The second experiment evaluated the relationships extracted, automatically, in the structure generated by the FCA, it gets average accuracy 86,5%.These results prove the effectiveness of the semantic relationship discovery approach.Ontologias têm se tornado um importante instrumento para a estruturação do conhecimento. Porém, a construção de uma ontologia envolve um cuidadoso processo de definição de termos representativos do domínio e seus relacionamentos, exigindo muito tempo dos engenheiros de ontologias em conjunto com especialistas de domínio. Esses relacionamentos podem ser taxonômicos (hiponímia e meronímia), representando uma taxonomia de conceitos, e não taxonômicos, referentes aos demais relacionamentos que ocorrem entre os nós dessa taxonomia. As principais dificuldades estão relacionadas ao tempo gasto pelos especialistas de domínio e às garantias necessárias para a qualidade das ontologias criadas, tornando-as confiáveis. Neste sentido, são bem-vindos os esforços para a elaboração de abordagens que visam diminuir o tempo de dedicação do especialista sem redução de qualidade da ontologia criada. Neste trabalho foi desenvolvida uma abordagem para a descoberta de relações semânticas não taxonômicas entre termos ontológicos, a partir de documentos semiestruturados redigidos com vocábulos informais do Português variante brasileira. A abordagem visa auxiliar engenheiros de ontologias e especialistas de domínio na árdua tarefa de descoberta dos relacionamentos entre termos ontológicos. Após a descoberta dos relacionamentos semânticos, estes foram convertidos em uma estrutura conceitual, gerada pelo método Formal Concept Analysis (FCA). Essa abordagem foi avaliada em dois experimentos, com auxílio de especialistas de domínio em Educação Especial. O primeiro experimento consistiu em uma comparação entre os relacionamentos extraídos de forma manual e a extração automática, apresentando um bom valor de precisão, cobertura e medida F, obtendo, respectivamente, 92%, 95% e 93%. Já o segundo experimento consistiu em avaliar os relacionamentos extraídos automaticamente na estrutura gerada pelo FCA, obtendo precisão média 86,5%. Esses resultados indicam a eficácia da abordagem de descoberta de relacionamentos semânticos.Coordenação de Aperfeiçoamento de Pessoal de Nível Superior (CAPES)porUniversidade Federal de São CarlosCâmpus São CarlosPrograma de Pós-Graduação em Ciência da Computação - PPGCCUFSCarOntologiaExtração de informaçãoProcessamento da linguagem naturalOntologyInformation extractionNatural language processingCIENCIAS EXATAS E DA TERRA::CIENCIA DA COMPUTACAODescoberta de relacionamentos semânticos não taxonômicos entre termos ontológicosinfo:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/masterThesisOnline6006001bdb200e-99c1-45c7-8e62-ff292489211einfo:eu-repo/semantics/openAccessreponame:Repositório Institucional da UFSCARinstname:Universidade Federal de São Carlos (UFSCAR)instacron:UFSCARORIGINALDissAMA.pdfDissAMA.pdfapplication/pdf3949100https://repositorio.ufscar.br/bitstream/ufscar/8946/1/DissAMA.pdfa7c504999039d0736a8629285dd87c12MD51LICENSElicense.txtlicense.txttext/plain; charset=utf-81957https://repositorio.ufscar.br/bitstream/ufscar/8946/2/license.txtae0398b6f8b235e40ad82cba6c50031dMD52TEXTDissAMA.pdf.txtDissAMA.pdf.txtExtracted texttext/plain222555https://repositorio.ufscar.br/bitstream/ufscar/8946/3/DissAMA.pdf.txtad13d7ae87f61f024c767343d7bde547MD53THUMBNAILDissAMA.pdf.jpgDissAMA.pdf.jpgIM Thumbnailimage/jpeg7279https://repositorio.ufscar.br/bitstream/ufscar/8946/4/DissAMA.pdf.jpg09a006ca5566a4467f6df0d1e9a5040dMD54ufscar/89462023-09-18 18:31:25.657oai:repositorio.ufscar.br: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Repositório InstitucionalPUBhttps://repositorio.ufscar.br/oai/requestopendoar:43222023-09-18T18:31:25Repositório Institucional da UFSCAR - Universidade Federal de São Carlos (UFSCAR)false |
dc.title.por.fl_str_mv |
Descoberta de relacionamentos semânticos não taxonômicos entre termos ontológicos |
title |
Descoberta de relacionamentos semânticos não taxonômicos entre termos ontológicos |
spellingShingle |
Descoberta de relacionamentos semânticos não taxonômicos entre termos ontológicos Andrade, Arthur Morais de Ontologia Extração de informação Processamento da linguagem natural Ontology Information extraction Natural language processing CIENCIAS EXATAS E DA TERRA::CIENCIA DA COMPUTACAO |
title_short |
Descoberta de relacionamentos semânticos não taxonômicos entre termos ontológicos |
title_full |
Descoberta de relacionamentos semânticos não taxonômicos entre termos ontológicos |
title_fullStr |
Descoberta de relacionamentos semânticos não taxonômicos entre termos ontológicos |
title_full_unstemmed |
Descoberta de relacionamentos semânticos não taxonômicos entre termos ontológicos |
title_sort |
Descoberta de relacionamentos semânticos não taxonômicos entre termos ontológicos |
author |
Andrade, Arthur Morais de |
author_facet |
Andrade, Arthur Morais de |
author_role |
author |
dc.contributor.authorlattes.por.fl_str_mv |
http://lattes.cnpq.br/6141689629856076 |
dc.contributor.author.fl_str_mv |
Andrade, Arthur Morais de |
dc.contributor.advisor1.fl_str_mv |
Santos, Marilde Terezinha Prado |
dc.contributor.advisor1Lattes.fl_str_mv |
http://lattes.cnpq.br/9826026025118073 |
dc.contributor.authorID.fl_str_mv |
b0de828f-17e6-44a9-b78c-be2f1412db35 |
contributor_str_mv |
Santos, Marilde Terezinha Prado |
dc.subject.por.fl_str_mv |
Ontologia Extração de informação Processamento da linguagem natural |
topic |
Ontologia Extração de informação Processamento da linguagem natural Ontology Information extraction Natural language processing CIENCIAS EXATAS E DA TERRA::CIENCIA DA COMPUTACAO |
dc.subject.eng.fl_str_mv |
Ontology Information extraction Natural language processing |
dc.subject.cnpq.fl_str_mv |
CIENCIAS EXATAS E DA TERRA::CIENCIA DA COMPUTACAO |
description |
Ontologies have become an important tool to structure knowledge. However, the construction of an ontology involves a careful process of defining representative terms of the domain and its relationships, which requires a lot of time from ontology engineers and domain experts. These relationships can be taxonomic (hyponymy and meronymy), representing a taxonomy of concepts, and non-taxonomic, referring to the other relationships that occur between the nodes of this taxonomy. The main difficulties of constructing an ontology are related to the time spent by domain specialists and the necessity of guaranteeing the quality and reliability of the ontologies create. In this way, we are welcome the efforts to elaborate approaches that aim to reduce the amount of time dedicated by specialists without reducing the quality of the ontology created. In this master's project, an approach was developed for the discovery of semantic relationships between non-taxonomic ontological terms from semi-structured documents written with informal vocabularies of the Brazilian Portuguese language. Thus, it aids ontology engineers and domain experts in the arduous task of discovering the relationships between ontological terms. After the discovery of semantic relationships, the relationships were converted into a conceptual structure, generated by the Formal Concept Analysis (FCA) method. This approach was validated in two experiments, with the help of domain experts in special education. The first experiment consisted of a comparison between manually extracted relationships and automatic extraction, presenting a good value of precision, coverage and measurement F, respectively, 92%, 95% and 93%. The second experiment evaluated the relationships extracted, automatically, in the structure generated by the FCA, it gets average accuracy 86,5%.These results prove the effectiveness of the semantic relationship discovery approach. |
publishDate |
2017 |
dc.date.accessioned.fl_str_mv |
2017-08-08T18:41:15Z |
dc.date.available.fl_str_mv |
2017-08-08T18:41:15Z |
dc.date.issued.fl_str_mv |
2017-02-14 |
dc.type.status.fl_str_mv |
info:eu-repo/semantics/publishedVersion |
dc.type.driver.fl_str_mv |
info:eu-repo/semantics/masterThesis |
format |
masterThesis |
status_str |
publishedVersion |
dc.identifier.citation.fl_str_mv |
ANDRADE, Arthur Morais de. Descoberta de relacionamentos semânticos não taxonômicos entre termos ontológicos. 2017. Dissertação (Mestrado em Ciência da Computação) – Universidade Federal de São Carlos, São Carlos, 2017. Disponível em: https://repositorio.ufscar.br/handle/ufscar/8946. |
dc.identifier.uri.fl_str_mv |
https://repositorio.ufscar.br/handle/ufscar/8946 |
identifier_str_mv |
ANDRADE, Arthur Morais de. Descoberta de relacionamentos semânticos não taxonômicos entre termos ontológicos. 2017. Dissertação (Mestrado em Ciência da Computação) – Universidade Federal de São Carlos, São Carlos, 2017. Disponível em: https://repositorio.ufscar.br/handle/ufscar/8946. |
url |
https://repositorio.ufscar.br/handle/ufscar/8946 |
dc.language.iso.fl_str_mv |
por |
language |
por |
dc.relation.confidence.fl_str_mv |
600 600 |
dc.relation.authority.fl_str_mv |
1bdb200e-99c1-45c7-8e62-ff292489211e |
dc.rights.driver.fl_str_mv |
info:eu-repo/semantics/openAccess |
eu_rights_str_mv |
openAccess |
dc.publisher.none.fl_str_mv |
Universidade Federal de São Carlos Câmpus São Carlos |
dc.publisher.program.fl_str_mv |
Programa de Pós-Graduação em Ciência da Computação - PPGCC |
dc.publisher.initials.fl_str_mv |
UFSCar |
publisher.none.fl_str_mv |
Universidade Federal de São Carlos Câmpus São Carlos |
dc.source.none.fl_str_mv |
reponame:Repositório Institucional da UFSCAR instname:Universidade Federal de São Carlos (UFSCAR) instacron:UFSCAR |
instname_str |
Universidade Federal de São Carlos (UFSCAR) |
instacron_str |
UFSCAR |
institution |
UFSCAR |
reponame_str |
Repositório Institucional da UFSCAR |
collection |
Repositório Institucional da UFSCAR |
bitstream.url.fl_str_mv |
https://repositorio.ufscar.br/bitstream/ufscar/8946/1/DissAMA.pdf https://repositorio.ufscar.br/bitstream/ufscar/8946/2/license.txt https://repositorio.ufscar.br/bitstream/ufscar/8946/3/DissAMA.pdf.txt https://repositorio.ufscar.br/bitstream/ufscar/8946/4/DissAMA.pdf.jpg |
bitstream.checksum.fl_str_mv |
a7c504999039d0736a8629285dd87c12 ae0398b6f8b235e40ad82cba6c50031d ad13d7ae87f61f024c767343d7bde547 09a006ca5566a4467f6df0d1e9a5040d |
bitstream.checksumAlgorithm.fl_str_mv |
MD5 MD5 MD5 MD5 |
repository.name.fl_str_mv |
Repositório Institucional da UFSCAR - Universidade Federal de São Carlos (UFSCAR) |
repository.mail.fl_str_mv |
|
_version_ |
1802136325732696064 |