Identificador persistente para citar o vincular este elemento: http://hdl.handle.net/10553/106914
Campo DC Valoridioma
dc.contributor.authorEstupiñán Ojeda, Cristian Daviden_US
dc.contributor.authorGuerra Artal, Cayetanoen_US
dc.contributor.authorHernández Tejera, Francisco Marioen_US
dc.date.accessioned2021-04-19T13:14:48Z-
dc.date.available2021-04-19T13:14:48Z-
dc.date.issued2021en_US
dc.identifier.isbn978-989-758-484-8en_US
dc.identifier.issn2184-433Xen_US
dc.identifier.otherScopus-
dc.identifier.urihttp://hdl.handle.net/10553/106914-
dc.description.abstractThe use of architectures based on transformers presents a state of the art revolution in natural language processing (NLP). The employment of these architectures with high computational costs has increased in the last few months, despite the existing use of parallelization techniques. This is due to the high performance that is obtained by increasing the size of the learnable parameters for these kinds of architectures, while maintaining the models' predictability. This relates to the fact that it is difficult to do research with limited computational resources. A restrictive element is the memory usage, which seriously affects the replication of experiments. We are presenting a new architecture called Informer, which seeks to exploit the concept of information organization. For the sake of evaluation, we use a neural machine translation (NMT) dataset, the English-Vietnamese IWSLT15 dataset (Luong and Manning, 2015). In this paper, we also compare this proposal with architectures that reduce the computational cost to O(n · r), such as Linformer (Wang et al., 2020). In addition, we have managed to improve the SOTA of the BLEU score from 33.27 to 35.11.en_US
dc.languageengen_US
dc.publisherSciTePress Digital Libraryen_US
dc.relation.ispartofICAART (Setúbal)en_US
dc.sourceICAART 2021 - Proceedings of the 13th International Conference on Agents and Artificial Intelligence [ISSN 2184-433X] ,v. 2, p. 381-389, (Enero 2021)en_US
dc.subject120304 Inteligencia artificialen_US
dc.subject.otherConvolutionen_US
dc.subject.otherDeep learningen_US
dc.subject.otherInformeren_US
dc.subject.otherLinear transformeren_US
dc.subject.otherNeural machine translationen_US
dc.subject.otherOrganizationen_US
dc.subject.otherSelf attentionen_US
dc.titleInformer, an information organization transformer architectureen_US
dc.typeinfo:eu-repo/semantics/conferenceObjecten_US
dc.typeConferenceObjecten_US
dc.relation.conference13th International Conference on Agents and Artificial Intelligence (ICAART 2021)en_US
dc.identifier.doi10.5220/0010372703810389en_US
dc.identifier.scopus85103812520-
dc.contributor.authorscopusid57222726987-
dc.contributor.authorscopusid57222721527-
dc.contributor.authorscopusid57222720474-
dc.description.lastpage389en_US
dc.description.firstpage381en_US
dc.relation.volume2en_US
dc.investigacionIngeniería y Arquitecturaen_US
dc.type2Actas de congresosen_US
dc.utils.revisionen_US
dc.date.coverdateEnero 2021en_US
dc.identifier.conferenceidevents128729-
dc.identifier.ulpgcen_US
dc.contributor.buulpgcBU-INFen_US
item.fulltextSin texto completo-
item.grantfulltextnone-
crisitem.event.eventsstartdate12-09-2019-
crisitem.event.eventsenddate14-09-2019-
crisitem.author.deptDepartamento de Informática y Sistemas-
crisitem.author.deptGIR SIANI: Inteligencia Artificial, Redes Neuronales, Aprendizaje Automático e Ingeniería de Datos-
crisitem.author.deptIU Sistemas Inteligentes y Aplicaciones Numéricas-
crisitem.author.deptDepartamento de Informática y Sistemas-
crisitem.author.deptGIR SIANI: Inteligencia Artificial, Redes Neuronales, Aprendizaje Automático e Ingeniería de Datos-
crisitem.author.deptIU Sistemas Inteligentes y Aplicaciones Numéricas-
crisitem.author.deptDepartamento de Informática y Sistemas-
crisitem.author.orcid0000-0003-1381-2262-
crisitem.author.orcid0000-0001-9717-8048-
crisitem.author.parentorgIU Sistemas Inteligentes y Aplicaciones Numéricas-
crisitem.author.parentorgIU Sistemas Inteligentes y Aplicaciones Numéricas-
crisitem.author.fullNameEstupiñán Ojeda, Cristian David-
crisitem.author.fullNameGuerra Artal, Cayetano-
crisitem.author.fullNameHernández Tejera, Francisco Mario-
Colección:Actas de congresos
Vista resumida

Visitas

165
actualizado el 22-abr-2023

Google ScholarTM

Verifica

Altmetric


Comparte



Exporta metadatos



Los elementos en ULPGC accedaCRIS están protegidos por derechos de autor con todos los derechos reservados, a menos que se indique lo contrario.