Improving word embeddings in Portuguese: increasing accuracy while reducing the size of the corpus

Detalhes bibliográficos
Autor(a) principal: Pinto, José Pedro
Data de Publicação: 2022
Outros Autores: Viana, Paula, Teixeira, Inês, Andrade, Maria
Tipo de documento: Artigo
Idioma: eng
Título da fonte: Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos)
Texto Completo: http://hdl.handle.net/10400.22/21674
Resumo: The subjectiveness of multimedia content description has a strong negative impact on tag-based information retrieval. In our work, we propose enhancing available descriptions by adding semantically related tags. To cope with this objective, we use a word embedding technique based on the Word2Vec neural network parameterized and trained using a new dataset built from online newspapers. A large number of news stories was scraped and pre-processed to build a new dataset. Our target language is Portuguese, one of the most spoken languages worldwide. The results achieved significantly outperform similar existing solutions developed in the scope of different languages, including Portuguese. Contributions include also an online application and API available for external use. Although the presented work has been designed to enhance multimedia content annotation, it can be used in several other application areas.
id RCAP_80dc382a34c04412dcdce934302a4326
oai_identifier_str oai:recipp.ipp.pt:10400.22/21674
network_acronym_str RCAP
network_name_str Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos)
repository_id_str 7160
spelling Improving word embeddings in Portuguese: increasing accuracy while reducing the size of the corpusNatural language processingMachine learningMultimedia systemsContext awarenessWord2VecThe subjectiveness of multimedia content description has a strong negative impact on tag-based information retrieval. In our work, we propose enhancing available descriptions by adding semantically related tags. To cope with this objective, we use a word embedding technique based on the Word2Vec neural network parameterized and trained using a new dataset built from online newspapers. A large number of news stories was scraped and pre-processed to build a new dataset. Our target language is Portuguese, one of the most spoken languages worldwide. The results achieved significantly outperform similar existing solutions developed in the scope of different languages, including Portuguese. Contributions include also an online application and API available for external use. Although the presented work has been designed to enhance multimedia content annotation, it can be used in several other application areas.This work is financed by National Funds through the Portuguese funding agency, FCT - Fundacão para a Ciência e a Tecnologia, within project LA/P/0063/2020. The funders had ¸ no role in study design, data collection and analysis, decision to publish, or preparation of the manuscript.PeerJRepositório Científico do Instituto Politécnico do PortoPinto, José PedroViana, PaulaTeixeira, InêsAndrade, Maria2023-01-19T12:03:19Z2022-07-182022-07-18T00:00:00Zinfo:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/articleapplication/pdfhttp://hdl.handle.net/10400.22/21674eng10.7717/peerj-cs.964info:eu-repo/semantics/openAccessreponame:Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos)instname:Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informaçãoinstacron:RCAAP2023-03-13T13:17:55Zoai:recipp.ipp.pt:10400.22/21674Portal AgregadorONGhttps://www.rcaap.pt/oai/openaireopendoar:71602024-03-19T17:41:42.691735Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) - Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informaçãofalse
dc.title.none.fl_str_mv Improving word embeddings in Portuguese: increasing accuracy while reducing the size of the corpus
title Improving word embeddings in Portuguese: increasing accuracy while reducing the size of the corpus
spellingShingle Improving word embeddings in Portuguese: increasing accuracy while reducing the size of the corpus
Pinto, José Pedro
Natural language processing
Machine learning
Multimedia systems
Context awareness
Word2Vec
title_short Improving word embeddings in Portuguese: increasing accuracy while reducing the size of the corpus
title_full Improving word embeddings in Portuguese: increasing accuracy while reducing the size of the corpus
title_fullStr Improving word embeddings in Portuguese: increasing accuracy while reducing the size of the corpus
title_full_unstemmed Improving word embeddings in Portuguese: increasing accuracy while reducing the size of the corpus
title_sort Improving word embeddings in Portuguese: increasing accuracy while reducing the size of the corpus
author Pinto, José Pedro
author_facet Pinto, José Pedro
Viana, Paula
Teixeira, Inês
Andrade, Maria
author_role author
author2 Viana, Paula
Teixeira, Inês
Andrade, Maria
author2_role author
author
author
dc.contributor.none.fl_str_mv Repositório Científico do Instituto Politécnico do Porto
dc.contributor.author.fl_str_mv Pinto, José Pedro
Viana, Paula
Teixeira, Inês
Andrade, Maria
dc.subject.por.fl_str_mv Natural language processing
Machine learning
Multimedia systems
Context awareness
Word2Vec
topic Natural language processing
Machine learning
Multimedia systems
Context awareness
Word2Vec
description The subjectiveness of multimedia content description has a strong negative impact on tag-based information retrieval. In our work, we propose enhancing available descriptions by adding semantically related tags. To cope with this objective, we use a word embedding technique based on the Word2Vec neural network parameterized and trained using a new dataset built from online newspapers. A large number of news stories was scraped and pre-processed to build a new dataset. Our target language is Portuguese, one of the most spoken languages worldwide. The results achieved significantly outperform similar existing solutions developed in the scope of different languages, including Portuguese. Contributions include also an online application and API available for external use. Although the presented work has been designed to enhance multimedia content annotation, it can be used in several other application areas.
publishDate 2022
dc.date.none.fl_str_mv 2022-07-18
2022-07-18T00:00:00Z
2023-01-19T12:03:19Z
dc.type.status.fl_str_mv info:eu-repo/semantics/publishedVersion
dc.type.driver.fl_str_mv info:eu-repo/semantics/article
format article
status_str publishedVersion
dc.identifier.uri.fl_str_mv http://hdl.handle.net/10400.22/21674
url http://hdl.handle.net/10400.22/21674
dc.language.iso.fl_str_mv eng
language eng
dc.relation.none.fl_str_mv 10.7717/peerj-cs.964
dc.rights.driver.fl_str_mv info:eu-repo/semantics/openAccess
eu_rights_str_mv openAccess
dc.format.none.fl_str_mv application/pdf
dc.publisher.none.fl_str_mv PeerJ
publisher.none.fl_str_mv PeerJ
dc.source.none.fl_str_mv reponame:Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos)
instname:Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informação
instacron:RCAAP
instname_str Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informação
instacron_str RCAAP
institution RCAAP
reponame_str Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos)
collection Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos)
repository.name.fl_str_mv Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) - Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informação
repository.mail.fl_str_mv
_version_ 1799131504540909568

Registros relacionados