Deep Fusion of Multiple Term-Similarity Measures For Biomedical Passage Retrieval

[EN] Passage retrieval is an important stage of question answering systems. Closed domain passage retrieval, e.g. biomedical passage retrieval presents additional challenges such as specialized terminology, more complex and elaborated queries, scarcity in the amount of available data, among others....

Descripción completa

Detalles Bibliográficos
Autores: Rosso-Mateus, Andrés, Montes Gomez, Manuel, González, Fabio, Rosso, Paolo
Tipo de recurso: artículo
Fecha de publicación:2020
País:España
Institución:Universitat Politècnica de València (UPV)
Repositorio:RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Idioma:inglés
OAI Identifier:oai:riunet.upv.es:10251/166829
Acceso en línea:https://riunet.upv.es/handle/10251/166829
Access Level:acceso abierto
Palabra clave:Biomedical passage retrieval
Neural networks
Question answering
Deep learning
LENGUAJES Y SISTEMAS INFORMATICOS
id ES_77c73d19043ebac3666a09bdca6d43fd
oai_identifier_str oai:riunet.upv.es:10251/166829
network_acronym_str ES
network_name_str España
repository_id_str
spelling Deep Fusion of Multiple Term-Similarity Measures For Biomedical Passage RetrievalRosso-Mateus, AndrésMontes Gomez, ManuelGonzález, FabioRosso, PaoloBiomedical passage retrievalNeural networksQuestion answeringDeep learningLENGUAJES Y SISTEMAS INFORMATICOS[EN] Passage retrieval is an important stage of question answering systems. Closed domain passage retrieval, e.g. biomedical passage retrieval presents additional challenges such as specialized terminology, more complex and elaborated queries, scarcity in the amount of available data, among others. However, closed domains also offer some advantages such as the availability of specialized structured information sources, e.g. ontologies and thesauri, that could be used to improve retrieval performance. This paper presents a novel approach for biomedical passage retrieval which is able to combine different information sources using a similarity matrix fusion strategy based on convolutional neural network architecture. The method was evaluated over the standard BioASQ dataset, a dataset specialized on biomedical question answering. The results show that the method is an effective strategy for biomedical passage retrieval able to outperform other state-of-the-art methods in this domain.COLCIENCIAS, REF. Agreement #727, 2016 provided financial as well as logistical and planning support. Mindlab research group (Universidad Nacional de Colombia sede Bogota) with the cooperation of INAOE (Instituto Nacional de Astrofisica, optica y Electronica) and Universitat Politecnica de Valencia wich also provided technical support for this work. The work of Paolo Rosso was carried out in the framework of the research project PROMETEO/2019/121.IOS PressDepartamento de Sistemas Informáticos y ComputaciónEscuela Técnica Superior de Ingeniería InformáticaCentro de Investigación Pattern Recognition and Human Language TechnologyGeneralitat ValencianaDepartamento Administrativo de Ciencia, Tecnología e Innovación, ColombiaRepositorio Institucional de la Universitat Politècnica de València Riunet20202020-08-31journal articlehttp://purl.org/coar/resource_type/c_6501VoRhttp://purl.org/coar/version/c_970fb48d4fbd8a85info:eu-repo/semantics/articleapplication/pdfapplication/pdfhttps://riunet.upv.es/handle/10251/166829reponame:RiuNet. Repositorio Institucional de la Universitat Politécnica de Valénciainstname:Universitat Politècnica de València (UPV)InglésengDepartamento Administrativo de Ciencia, Tecnología e Innovación, Colombia https://doi.org/10.13039/100007637 727Generalitat Valenciana https://doi.org/10.13039/501100003359 PROMETEO%2F2019%2F121 Deep learning for adaptative and multimodal interaction in pattern recognitionopen accesshttp://purl.org/coar/access_right/c_abf2Reserva de todos los derechoshttp://rightsstatements.org/vocab/InC/1.0/info:eu-repo/semantics/openAccessoai:riunet.upv.es:10251/1668292026-06-13T07:49:27Z
dc.title.none.fl_str_mv Deep Fusion of Multiple Term-Similarity Measures For Biomedical Passage Retrieval
title Deep Fusion of Multiple Term-Similarity Measures For Biomedical Passage Retrieval
spellingShingle Deep Fusion of Multiple Term-Similarity Measures For Biomedical Passage Retrieval
Rosso-Mateus, Andrés
Biomedical passage retrieval
Neural networks
Question answering
Deep learning
LENGUAJES Y SISTEMAS INFORMATICOS
title_short Deep Fusion of Multiple Term-Similarity Measures For Biomedical Passage Retrieval
title_full Deep Fusion of Multiple Term-Similarity Measures For Biomedical Passage Retrieval
title_fullStr Deep Fusion of Multiple Term-Similarity Measures For Biomedical Passage Retrieval
title_full_unstemmed Deep Fusion of Multiple Term-Similarity Measures For Biomedical Passage Retrieval
title_sort Deep Fusion of Multiple Term-Similarity Measures For Biomedical Passage Retrieval
dc.creator.none.fl_str_mv Rosso-Mateus, Andrés
Montes Gomez, Manuel
González, Fabio
Rosso, Paolo
author Rosso-Mateus, Andrés
author_facet Rosso-Mateus, Andrés
Montes Gomez, Manuel
González, Fabio
Rosso, Paolo
author_role author
author2 Montes Gomez, Manuel
González, Fabio
Rosso, Paolo
author2_role author
author
author
dc.contributor.none.fl_str_mv Departamento de Sistemas Informáticos y Computación
Escuela Técnica Superior de Ingeniería Informática
Centro de Investigación Pattern Recognition and Human Language Technology
Generalitat Valenciana
Departamento Administrativo de Ciencia, Tecnología e Innovación, Colombia
Repositorio Institucional de la Universitat Politècnica de València Riunet
dc.subject.none.fl_str_mv Biomedical passage retrieval
Neural networks
Question answering
Deep learning
LENGUAJES Y SISTEMAS INFORMATICOS
topic Biomedical passage retrieval
Neural networks
Question answering
Deep learning
LENGUAJES Y SISTEMAS INFORMATICOS
description [EN] Passage retrieval is an important stage of question answering systems. Closed domain passage retrieval, e.g. biomedical passage retrieval presents additional challenges such as specialized terminology, more complex and elaborated queries, scarcity in the amount of available data, among others. However, closed domains also offer some advantages such as the availability of specialized structured information sources, e.g. ontologies and thesauri, that could be used to improve retrieval performance. This paper presents a novel approach for biomedical passage retrieval which is able to combine different information sources using a similarity matrix fusion strategy based on convolutional neural network architecture. The method was evaluated over the standard BioASQ dataset, a dataset specialized on biomedical question answering. The results show that the method is an effective strategy for biomedical passage retrieval able to outperform other state-of-the-art methods in this domain.
publishDate 2020
dc.date.none.fl_str_mv 2020
2020-08-31
dc.type.none.fl_str_mv journal article
http://purl.org/coar/resource_type/c_6501
VoR
http://purl.org/coar/version/c_970fb48d4fbd8a85
dc.type.openaire.fl_str_mv info:eu-repo/semantics/article
format article
dc.identifier.none.fl_str_mv https://riunet.upv.es/handle/10251/166829
url https://riunet.upv.es/handle/10251/166829
dc.language.none.fl_str_mv Inglés
eng
language_invalid_str_mv Inglés
language eng
dc.relation.none.fl_str_mv Departamento Administrativo de Ciencia, Tecnología e Innovación, Colombia https://doi.org/10.13039/100007637 727
Generalitat Valenciana https://doi.org/10.13039/501100003359 PROMETEO%2F2019%2F121 Deep learning for adaptative and multimodal interaction in pattern recognition
dc.rights.none.fl_str_mv open access
http://purl.org/coar/access_right/c_abf2
Reserva de todos los derechos
http://rightsstatements.org/vocab/InC/1.0/
dc.rights.openaire.fl_str_mv info:eu-repo/semantics/openAccess
rights_invalid_str_mv open access
http://purl.org/coar/access_right/c_abf2
Reserva de todos los derechos
http://rightsstatements.org/vocab/InC/1.0/
eu_rights_str_mv openAccess
dc.format.none.fl_str_mv application/pdf
application/pdf
dc.publisher.none.fl_str_mv IOS Press
publisher.none.fl_str_mv IOS Press
dc.source.none.fl_str_mv reponame:RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
instname:Universitat Politècnica de València (UPV)
instname_str Universitat Politècnica de València (UPV)
reponame_str RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
collection RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
repository.name.fl_str_mv
repository.mail.fl_str_mv
_version_ 1869411146942906368
score 15.301603

Similares en LA Referencia