Mi DSpace
Usuario
Contraseña
Please use this identifier to cite or link to this item: http://hdl.handle.net/UCSP/15959
Full metadata record
DC FieldValueLanguage
dc.contributor.advisorOchoa Luna, José Eduardo-
dc.contributor.authorArch Tijera, Drake Christian-
dc.date.accessioned2019-04-08T17:16:45Z-
dc.date.available2019-04-08T17:16:45Z-
dc.date.issued2018-
dc.identifier.other1066708-
dc.identifier.urihttp://repositorio.ucsp.edu.pe/handle/UCSP/15959-
dc.description.abstractNowadays, Question Answering is being addressed from a reading comprehension approach. Usually, Machine Comprehension models are poweredby Deep Learning algorithms. Most related work faces the challenge by improving the Interaction Encoder, proposing several architectures strongly based on attention. In Contrast, few related work has focused on improving the Context Encoder. Thus, our work has explored in depth the Context Encoder. We propose a gating mechanism that controls the ow of information, from the Context Encoder towards Interaction Encoder. This gating mechanism is based on additional information computed previously. Our experiments has shown that our proposed model improved the performance of a competitive baseline model. Our single model reached 78.36% on F1 score and 69.1% on exact match metric, on the Stanford Question Answering benchmark.es_PE
dc.description.uriTrabajo de investigaciónes_PE
dc.formatapplication/pdfes_PE
dc.language.isoenges_PE
dc.publisherUniversidad Católica San Pabloes_PE
dc.rightsinfo:eu-repo/semantics/openAccesses_PE
dc.rights.urihttps://creativecommons.org/licenses/by/4.0/es_PE
dc.sourceUniversidad Católica San Pabloes_PE
dc.sourceRepositorio Institucional - UCSPes_PE
dc.subjectMachine Comprehensiones_PE
dc.subjectQuestion Answeringes_PE
dc.subjectNatural Languagees_PE
dc.subjectProcessinges_PE
dc.subjectDeep Learninges_PE
dc.titleDeep neural networks based on gating mechanism for open-domain question answeringes_PE
dc.typeinfo:eu-repo/semantics/masterThesises_PE
thesis.degree.nameMaestro en Ciencia de la Computaciónes_PE
thesis.degree.grantorUniversidad Católica San Pablo. Facultad de Ingeniería y Computaciónes_PE
thesis.degree.levelMaestríaes_PE
thesis.degree.disciplineCiencia de la Computaciónes_PE
thesis.degree.programEscuela Profesional de Ciencia de la Computaciónes_PE
dc.publisher.countryPEes_PE
dc.subject.ocdehttp://purl.org/pe-repo/ocde/ford#1.02.01es_PE
Appears in Collections:Tesis Postgrado - Maestría en Ciencia de la Computación

Files in This Item:
File Description SizeFormat 
ARCH_TIJERA_DRA_DEE.pdf3.46 MBAdobe PDFView/Open


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.