Utilize este identificador para referenciar este registo: http://hdl.handle.net/10071/16641
Registo completo
Campo DCValorIdioma
dc.contributor.authorGonçalves, S.-
dc.contributor.authorCortez, P.-
dc.contributor.authorMoro, S.-
dc.contributor.editorV. Kurkova et al.-
dc.date.accessioned2018-10-11T10:14:58Z-
dc.date.available2018-10-11T10:14:58Z-
dc.date.issued2018-
dc.identifier.issn0302-9743-
dc.identifier.urihttps://ciencia.iscte-iul.pt/id/ci-pub-49715-
dc.identifier.urihttp://hdl.handle.net/10071/16641-
dc.description.abstractThe classification of abstract sentences is a valuable tool to support scientific database querying, to summarize relevant literature works and to assist in the writing of new abstracts. This study proposes a novel deep learning approach based on a convolutional layer and a bi-directional gated recurrent unit to classify sentences of abstracts. The proposed neural network was tested on a sample of 20 thousand abstracts from the biomedical domain. Competitive results were achieved, with weight-averaged precision, recall and F1-score values around 91%, which are higher when compared to a state-of-the-art neural network.eng
dc.language.isoeng-
dc.publisherSpringer-
dc.relationPOCI-01-0145-FEDER-007043-
dc.relationUID/MULTI/0446/2013-
dc.relationUID/CEC/00319/2013-
dc.rightsopenAccess-
dc.subjectBi-directional gated recurrent uniteng
dc.subjectSentence classificationeng
dc.subjectText miningeng
dc.subjectDeep learningeng
dc.subjectScientific articleseng
dc.titleA deep learning approach for sentence classification of scientific abstractseng
dc.typeconferenceObject-
dc.event.typeConferênciapt
dc.event.locationIsland of Rhodes, Greeceeng
dc.event.date2018-
dc.pagination479 - 488-
dc.peerreviewedyes-
dc.journalArtificial Neural Networks and Machine Learning – ICANN 2018-
degois.publication.firstPage479-
degois.publication.lastPage488-
degois.publication.locationIsland of Rhodes, Greeceeng
degois.publication.titleA deep learning approach for sentence classification of scientific abstractseng
dc.description.versioninfo:eu-repo/semantics/acceptedVersion-
dc.identifier.doi10.1007/978-3-030-01424-7_47-
dc.subject.fosDomínio/Área Científica::Ciências Naturais::Ciências da Computação e da Informaçãopor
Aparece nas coleções:ISTAR-CRI - Comunicações a conferências internacionais

Ficheiros deste registo:
Ficheiro Descrição TamanhoFormato 
2018_ICANN-GoncalvesCortezMoro-PosPrint.pdfPós-print400,47 kBAdobe PDFVer/Abrir


FacebookTwitterDeliciousLinkedInDiggGoogle BookmarksMySpaceOrkut
Formato BibTex mendeley Endnote Logotipo do DeGóis Logotipo do Orcid 

Todos os registos no repositório estão protegidos por leis de copyright, com todos os direitos reservados.