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

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 compre...

Descripción completa

Detalles Bibliográficos
Autores principales: Laura, Juan Andrés, Masi, Gabriel Omar, Argerich, Luis
Formato: Objeto de conferencia
Lenguaje:Inglés
Publicado: 2017
Materias:
Ciencias Informáticas
Data Compression Algorithm
Neural nets
Acceso en línea:http://sedici.unlp.edu.ar/handle/10915/65946
http://www.clei2017-46jaiio.sadio.org.ar/sites/default/files/Mem/ASAI/asai-10.pdf
Aporte de:
SEDICI (UNLP) de Universidad Nacional de La Plata
id I19-R120-10915-65946
record_format dspace
institution Universidad Nacional de La Plata
institution_str I-19
repository_str R-120
collection SEDICI (UNLP)
language Inglés
topic Ciencias Informáticas
Data Compression Algorithm
Neural nets
spellingShingle Ciencias Informáticas
Data Compression Algorithm
Neural nets
Laura, Juan Andrés
Masi, Gabriel Omar
Argerich, Luis
From Imitation to Prediction, Data Compression vs Recurrent Neural Networks for Natural Language Processing
topic_facet Ciencias Informáticas
Data Compression Algorithm
Neural nets
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.
format Objeto de conferencia
Objeto de conferencia
author Laura, Juan Andrés
Masi, Gabriel Omar
Argerich, Luis
author_facet Laura, Juan Andrés
Masi, Gabriel Omar
Argerich, Luis
author_sort Laura, Juan Andrés
title From Imitation to Prediction, Data Compression vs Recurrent Neural Networks for Natural Language Processing
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
publishDate 2017
url http://sedici.unlp.edu.ar/handle/10915/65946
http://www.clei2017-46jaiio.sadio.org.ar/sites/default/files/Mem/ASAI/asai-10.pdf
work_keys_str_mv AT laurajuanandres fromimitationtopredictiondatacompressionvsrecurrentneuralnetworksfornaturallanguageprocessing
AT masigabrielomar fromimitationtopredictiondatacompressionvsrecurrentneuralnetworksfornaturallanguageprocessing
AT argerichluis fromimitationtopredictiondatacompressionvsrecurrentneuralnetworksfornaturallanguageprocessing
bdutipo_str Repositorios
_version_ 1764820480748945412

Ejemplares similares