Por favor, use este identificador para citar o enlazar este ítem: http://hdl.handle.net/11531/100533
Registro completo de metadatos
Campo DC Valor Lengua/Idioma
dc.contributor.authorLópez López, Álvaro Jesúses-ES
dc.contributor.authorPortela González, Josées-ES
dc.date.accessioned2025-07-10T14:19:18Z-
dc.date.available2025-07-10T14:19:18Z-
dc.date.issued2025-07-01es_ES
dc.identifier.issn0924-669Xes_ES
dc.identifier.urihttps:doi.org10.1007s10489-025-06579-yes_ES
dc.identifier.urihttp://hdl.handle.net/11531/100533-
dc.descriptionArtículos en revistases_ES
dc.description.abstractes-ES
dc.description.abstractThis study explores the integration of graph neural network (GNN) representations with pre-trained language models (PLMs) to enhance keyphrase extraction (KPE) from lengthy documents. We demonstrate that incorporating graph embeddings into PLMs yields richer semantic representations, especially for long texts. Our approach constructs a co-occurrence graph of the document, which we then embed using a graph convolutional network (GCN) trained for edge prediction. This process captures non-sequential relationships and long-distance dependencies, both of which are often crucial in lengthy documents. We introduce a novel graph-enhanced sequence tagging architecture that combines PLM-based contextual embeddings with GNN-derived representations. Through evaluations on benchmark datasets, our method outperforms state-of-the-art models, showing notable improvements in F1 scores. Beyond performance on standard benchmarks, this approach also holds promise in domains such as legal, medical, and scientific document processing, where efficient handling of long texts is vital. Our findings underscore the potential for GNNs to complement PLMs, helping address both technical and real-world challenges in KPE for long documents.in KPE for long documentsen-GB
dc.format.mimetypeapplication/octet-streames_ES
dc.language.isoen-GBes_ES
dc.sourceRevista: Applied Intelligence, Periodo: 1, Volumen: online, Número: 10, Página inicial: 711-1, Página final: 711-18es_ES
dc.subject.otherInstituto de Investigación Tecnológica (IIT)es_ES
dc.titleEnhancing keyphrase extraction from long scientific documents using graph embeddingses_ES
dc.typeinfo:eu-repo/semantics/articlees_ES
dc.description.versioninfo:eu-repo/semantics/publishedVersiones_ES
dc.rights.holderes_ES
dc.rights.accessRightsinfo:eu-repo/semantics/openAccesses_ES
dc.keywordses-ES
dc.keywordsKeyphrase extraction · Graph embeddings · Long documents · Pre-trained language models · Natural language processing · Deep learningen-GB
Aparece en las colecciones: Artículos

Ficheros en este ítem:
Fichero Tamaño Formato  
IIT-25-123R_preview3,09 kBUnknownVisualizar/Abrir


Los ítems de DSpace están protegidos por copyright, con todos los derechos reservados, a menos que se indique lo contrario.