Extractive summarization using siamese hierarchical transformer encoders

[EN] In this paper, we present an extractive approach to document summarization, the Siamese Hierarchical Transformer Encoders system, that is based on the use of siamese neural networks and the transformer encoders which are extended in a hierarchical way. The system, trained for binary classificat...

ver descrição completa

Detalhes bibliográficos
Autores: González-Barba, José Ángel, Segarra Soriano, Encarnación, García-Granada, Fernando|||0000-0003-2213-4213, Sanchís Arnal, Emilio|||0000-0002-6737-4723, Hurtado Oliver, Lluis Felip|||0000-0002-1877-0455
Formato: artículo
Fecha de publicación:2020
País:España
Recursos:Universitat Politècnica de València (UPV)
Repositorio:RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Idioma:inglés
OAI Identifier:oai:riunet.upv.es:10251/170290
Acesso em linha:https://riunet.upv.es/handle/10251/170290
Access Level:acceso abierto
Palavra-chave:Siamese neural networks
Self attention
Extractive summarization
LENGUAJES Y SISTEMAS INFORMATICOS
id ES_e69b641e6a02ebcb405f38fa2c2d39a4
oai_identifier_str oai:riunet.upv.es:10251/170290
network_acronym_str ES
network_name_str España
repository_id_str
spelling Extractive summarization using siamese hierarchical transformer encodersGonzález-Barba, José ÁngelSegarra Soriano, EncarnaciónGarcía-Granada, Fernando|||0000-0003-2213-4213Sanchís Arnal, Emilio|||0000-0002-6737-4723Hurtado Oliver, Lluis Felip|||0000-0002-1877-0455Siamese neural networksSelf attentionExtractive summarizationLENGUAJES Y SISTEMAS INFORMATICOS[EN] In this paper, we present an extractive approach to document summarization, the Siamese Hierarchical Transformer Encoders system, that is based on the use of siamese neural networks and the transformer encoders which are extended in a hierarchical way. The system, trained for binary classification, is able to assign attention scores to each sentence in the document. These scores are used to select the most relevant sentences to build the summary. The main novelty of our proposal is the use of self-attention mechanisms at sentence level for document summarization, instead of using only attentions at word level. The experimentation carried out using the CNN/DailyMail summarization corpus shows promising results in-line with the state-of-the-art.This work has been partially supported by the Spanish MINECO and FEDER founds under project AMIC (TIN2017-85854-C4-2-R). Work of Jose Angel Gonzalez is also financed by Universitat Politecnica de Valencia under grant PAID-01-17.IOS PressDepartamento de Sistemas Informáticos y ComputaciónEscuela Técnica Superior de Ingeniería Geodésica, Cartográfica y TopográficaEscuela Técnica Superior de Ingeniería InformáticaInstituto Universitario Valenciano de Investigación en Inteligencia ArtificialAgencia Estatal de InvestigaciónEuropean Regional Development FundUniversitat Politècnica de ValènciaRepositorio Institucional de la Universitat Politècnica de València Riunet20202020-01-01journal articlehttp://purl.org/coar/resource_type/c_6501VoRhttp://purl.org/coar/version/c_970fb48d4fbd8a85info:eu-repo/semantics/articleapplication/pdfapplication/pdfhttps://riunet.upv.es/handle/10251/170290reponame:RiuNet. Repositorio Institucional de la Universitat Politécnica de Valénciainstname:Universitat Politècnica de València (UPV)InglésengUniversitat Politècnica de València https://doi.org/10.13039/501100004233 PAID-01-17Agencia Estatal de Investigación http://dx.doi.org/10.13039/501100011033 Plan Estatal de Investigación Científica y Técnica y de Innovación 2013-2016 TIN2017-85854-C4-2-R AMIC-UPV: ANALISIS AFECTIVO DE INFORMACION MULTIMEDIA CON COMUNICACION INCLUSIVA Y NATURALopen 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:10251/1702902026-06-13T07:49:27Z
dc.title.none.fl_str_mv Extractive summarization using siamese hierarchical transformer encoders
title Extractive summarization using siamese hierarchical transformer encoders
spellingShingle Extractive summarization using siamese hierarchical transformer encoders
González-Barba, José Ángel
Siamese neural networks
Self attention
Extractive summarization
LENGUAJES Y SISTEMAS INFORMATICOS
title_short Extractive summarization using siamese hierarchical transformer encoders
title_full Extractive summarization using siamese hierarchical transformer encoders
title_fullStr Extractive summarization using siamese hierarchical transformer encoders
title_full_unstemmed Extractive summarization using siamese hierarchical transformer encoders
title_sort Extractive summarization using siamese hierarchical transformer encoders
dc.creator.none.fl_str_mv González-Barba, José Ángel
Segarra Soriano, Encarnación
García-Granada, Fernando|||0000-0003-2213-4213
Sanchís Arnal, Emilio|||0000-0002-6737-4723
Hurtado Oliver, Lluis Felip|||0000-0002-1877-0455
author González-Barba, José Ángel
author_facet González-Barba, José Ángel
Segarra Soriano, Encarnación
García-Granada, Fernando|||0000-0003-2213-4213
Sanchís Arnal, Emilio|||0000-0002-6737-4723
Hurtado Oliver, Lluis Felip|||0000-0002-1877-0455
author_role author
author2 Segarra Soriano, Encarnación
García-Granada, Fernando|||0000-0003-2213-4213
Sanchís Arnal, Emilio|||0000-0002-6737-4723
Hurtado Oliver, Lluis Felip|||0000-0002-1877-0455
author2_role author
author
author
author
dc.contributor.none.fl_str_mv Departamento de Sistemas Informáticos y Computación
Escuela Técnica Superior de Ingeniería Geodésica, Cartográfica y Topográfica
Escuela Técnica Superior de Ingeniería Informática
Instituto Universitario Valenciano de Investigación en Inteligencia Artificial
Agencia Estatal de Investigación
European Regional Development Fund
Universitat Politècnica de València
Repositorio Institucional de la Universitat Politècnica de València Riunet
dc.subject.none.fl_str_mv Siamese neural networks
Self attention
Extractive summarization
LENGUAJES Y SISTEMAS INFORMATICOS
topic Siamese neural networks
Self attention
Extractive summarization
LENGUAJES Y SISTEMAS INFORMATICOS
description [EN] In this paper, we present an extractive approach to document summarization, the Siamese Hierarchical Transformer Encoders system, that is based on the use of siamese neural networks and the transformer encoders which are extended in a hierarchical way. The system, trained for binary classification, is able to assign attention scores to each sentence in the document. These scores are used to select the most relevant sentences to build the summary. The main novelty of our proposal is the use of self-attention mechanisms at sentence level for document summarization, instead of using only attentions at word level. The experimentation carried out using the CNN/DailyMail summarization corpus shows promising results in-line with the state-of-the-art.
publishDate 2020
dc.date.none.fl_str_mv 2020
2020-01-01
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/10251/170290
url https://riunet.upv.es/handle/10251/170290
dc.language.none.fl_str_mv Inglés
eng
language_invalid_str_mv Inglés
language eng
dc.relation.none.fl_str_mv Universitat Politècnica de València https://doi.org/10.13039/501100004233 PAID-01-17
Agencia Estatal de Investigación http://dx.doi.org/10.13039/501100011033 Plan Estatal de Investigación Científica y Técnica y de Innovación 2013-2016 TIN2017-85854-C4-2-R AMIC-UPV: ANALISIS AFECTIVO DE INFORMACION MULTIMEDIA CON COMUNICACION INCLUSIVA Y NATURAL
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_ 1869422781485023232
score 15,300719

Registos relacionados