From Imitation to Prediction, Data Compression vs Recurrent Neural Networks for Natural Language Processing

Autores
Laura, Juan Andrés; Masi, Gabriel Omar; Argerich, Luis
Año de publicación
2017
Idioma
inglés
Tipo de recurso
documento de conferencia
Estado
versión publicada
Descripción
In recent studies [1] [2] [3] Recurrent Neural Networks were used for generative processes and their surprising performance can be explained by their ability to create good predictions. In addition, data compression is also based on prediction. What the problem comes down to is whether a data compressor could be used to perform as well as recurrent neural networks in the natural language processing tasks of sentiment analysis and automatic text generation. If this is possible, then the problem comes down to determining if a compression algorithm is even more intelligent than a neural network in such tasks. In our journey we discovered what we think is the fundamental difference between a Data Compression Algorithm and a Recurrent Neural Network.
Sociedad Argentina de Informática e Investigación Operativa
Materia
Ciencias Informáticas
Data Compression Algorithm
Neural nets
Nivel de accesibilidad
acceso abierto
Condiciones de uso
http://creativecommons.org/licenses/by-sa/4.0/
Repositorio
SEDICI (UNLP)
Institución
Universidad Nacional de La Plata
OAI Identificador
oai:sedici.unlp.edu.ar:10915/65946

id SEDICI_dca5e5bd4ad25922dd21a628fdfcd901
oai_identifier_str oai:sedici.unlp.edu.ar:10915/65946
network_acronym_str SEDICI
repository_id_str 1329
network_name_str SEDICI (UNLP)
spelling From Imitation to Prediction, Data Compression vs Recurrent Neural Networks for Natural Language ProcessingLaura, Juan AndrésMasi, Gabriel OmarArgerich, LuisCiencias InformáticasData Compression AlgorithmNeural netsIn recent studies [1] [2] [3] Recurrent Neural Networks were used for generative processes and their surprising performance can be explained by their ability to create good predictions. In addition, data compression is also based on prediction. What the problem comes down to is whether a data compressor could be used to perform as well as recurrent neural networks in the natural language processing tasks of sentiment analysis and automatic text generation. If this is possible, then the problem comes down to determining if a compression algorithm is even more intelligent than a neural network in such tasks. In our journey we discovered what we think is the fundamental difference between a Data Compression Algorithm and a Recurrent Neural Network.Sociedad Argentina de Informática e Investigación Operativa2017-09info:eu-repo/semantics/conferenceObjectinfo:eu-repo/semantics/publishedVersionObjeto de conferenciahttp://purl.org/coar/resource_type/c_5794info:ar-repo/semantics/documentoDeConferenciaapplication/pdfhttp://sedici.unlp.edu.ar/handle/10915/65946enginfo:eu-repo/semantics/altIdentifier/url/http://www.clei2017-46jaiio.sadio.org.ar/sites/default/files/Mem/ASAI/asai-10.pdfinfo:eu-repo/semantics/altIdentifier/issn/2451-7585info:eu-repo/semantics/openAccesshttp://creativecommons.org/licenses/by-sa/4.0/Creative Commons Attribution-ShareAlike 4.0 International (CC BY-SA 4.0)reponame:SEDICI (UNLP)instname:Universidad Nacional de La Platainstacron:UNLP2025-09-29T11:09:45Zoai:sedici.unlp.edu.ar:10915/65946Institucionalhttp://sedici.unlp.edu.ar/Universidad públicaNo correspondehttp://sedici.unlp.edu.ar/oai/snrdalira@sedici.unlp.edu.arArgentinaNo correspondeNo correspondeNo correspondeopendoar:13292025-09-29 11:09:45.382SEDICI (UNLP) - Universidad Nacional de La Platafalse
dc.title.none.fl_str_mv From Imitation to Prediction, Data Compression vs Recurrent Neural Networks for Natural Language Processing
title From Imitation to Prediction, Data Compression vs Recurrent Neural Networks for Natural Language Processing
spellingShingle From Imitation to Prediction, Data Compression vs Recurrent Neural Networks for Natural Language Processing
Laura, Juan Andrés
Ciencias Informáticas
Data Compression Algorithm
Neural nets
title_short From Imitation to Prediction, Data Compression vs Recurrent Neural Networks for Natural Language Processing
title_full From Imitation to Prediction, Data Compression vs Recurrent Neural Networks for Natural Language Processing
title_fullStr From Imitation to Prediction, Data Compression vs Recurrent Neural Networks for Natural Language Processing
title_full_unstemmed From Imitation to Prediction, Data Compression vs Recurrent Neural Networks for Natural Language Processing
title_sort From Imitation to Prediction, Data Compression vs Recurrent Neural Networks for Natural Language Processing
dc.creator.none.fl_str_mv Laura, Juan Andrés
Masi, Gabriel Omar
Argerich, Luis
author Laura, Juan Andrés
author_facet Laura, Juan Andrés
Masi, Gabriel Omar
Argerich, Luis
author_role author
author2 Masi, Gabriel Omar
Argerich, Luis
author2_role author
author
dc.subject.none.fl_str_mv Ciencias Informáticas
Data Compression Algorithm
Neural nets
topic Ciencias Informáticas
Data Compression Algorithm
Neural nets
dc.description.none.fl_txt_mv In recent studies [1] [2] [3] Recurrent Neural Networks were used for generative processes and their surprising performance can be explained by their ability to create good predictions. In addition, data compression is also based on prediction. What the problem comes down to is whether a data compressor could be used to perform as well as recurrent neural networks in the natural language processing tasks of sentiment analysis and automatic text generation. If this is possible, then the problem comes down to determining if a compression algorithm is even more intelligent than a neural network in such tasks. In our journey we discovered what we think is the fundamental difference between a Data Compression Algorithm and a Recurrent Neural Network.
Sociedad Argentina de Informática e Investigación Operativa
description In recent studies [1] [2] [3] Recurrent Neural Networks were used for generative processes and their surprising performance can be explained by their ability to create good predictions. In addition, data compression is also based on prediction. What the problem comes down to is whether a data compressor could be used to perform as well as recurrent neural networks in the natural language processing tasks of sentiment analysis and automatic text generation. If this is possible, then the problem comes down to determining if a compression algorithm is even more intelligent than a neural network in such tasks. In our journey we discovered what we think is the fundamental difference between a Data Compression Algorithm and a Recurrent Neural Network.
publishDate 2017
dc.date.none.fl_str_mv 2017-09
dc.type.none.fl_str_mv info:eu-repo/semantics/conferenceObject
info:eu-repo/semantics/publishedVersion
Objeto de conferencia
http://purl.org/coar/resource_type/c_5794
info:ar-repo/semantics/documentoDeConferencia
format conferenceObject
status_str publishedVersion
dc.identifier.none.fl_str_mv http://sedici.unlp.edu.ar/handle/10915/65946
url http://sedici.unlp.edu.ar/handle/10915/65946
dc.language.none.fl_str_mv eng
language eng
dc.relation.none.fl_str_mv info:eu-repo/semantics/altIdentifier/url/http://www.clei2017-46jaiio.sadio.org.ar/sites/default/files/Mem/ASAI/asai-10.pdf
info:eu-repo/semantics/altIdentifier/issn/2451-7585
dc.rights.none.fl_str_mv info:eu-repo/semantics/openAccess
http://creativecommons.org/licenses/by-sa/4.0/
Creative Commons Attribution-ShareAlike 4.0 International (CC BY-SA 4.0)
eu_rights_str_mv openAccess
rights_invalid_str_mv http://creativecommons.org/licenses/by-sa/4.0/
Creative Commons Attribution-ShareAlike 4.0 International (CC BY-SA 4.0)
dc.format.none.fl_str_mv application/pdf
dc.source.none.fl_str_mv reponame:SEDICI (UNLP)
instname:Universidad Nacional de La Plata
instacron:UNLP
reponame_str SEDICI (UNLP)
collection SEDICI (UNLP)
instname_str Universidad Nacional de La Plata
instacron_str UNLP
institution UNLP
repository.name.fl_str_mv SEDICI (UNLP) - Universidad Nacional de La Plata
repository.mail.fl_str_mv alira@sedici.unlp.edu.ar
_version_ 1844615965765009408
score 13.070432