Classic and recent (neural) approaches to automatic text classification : A comparative study with e-mails in the Spanish language

Currently, millions of data are generated daily and its exploitation and interpretation has become essential at every scope. However, most of this information is in textual format, lacking the structure and organisation of traditional databases, which represents an enormous challenge to overcome. Ov...

Descripción completa

Detalles Bibliográficos
Autores principales: Fernández, Juan Manuel, Cavasi, Nicolás, Errecalde, Marcelo Luis
Formato: Objeto de conferencia
Lenguaje:Inglés
Publicado: 2021
Materias:
Ciencias Informáticas
Text Classification
SVM
Word2Vec
LSTM
BERT
Acceso en línea:http://sedici.unlp.edu.ar/handle/10915/125140
Aporte de:
SEDICI (UNLP) de Universidad Nacional de La Plata
id I19-R120-10915-125140
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
Text Classification
SVM
Word2Vec
LSTM
BERT
spellingShingle Ciencias Informáticas
Text Classification
SVM
Word2Vec
LSTM
BERT
Fernández, Juan Manuel
Cavasi, Nicolás
Errecalde, Marcelo Luis
Classic and recent (neural) approaches to automatic text classification : A comparative study with e-mails in the Spanish language
topic_facet Ciencias Informáticas
Text Classification
SVM
Word2Vec
LSTM
BERT
description Currently, millions of data are generated daily and its exploitation and interpretation has become essential at every scope. However, most of this information is in textual format, lacking the structure and organisation of traditional databases, which represents an enormous challenge to overcome. Over the course of time, different approaches have been proposed for text representation attempting to better capture the semantic of documents. They included classic information retrieval approaches (like Bag of Words) to new approaches based on neural networks such as basic word embeddings, deep learning architectures (LSTMs and CNNs), and contextualized embeddings based on attention mechanisms (Transformers). Unfortunately, most of the available resources supporting those technologies are English-centered. In this work, using an e-mail-based study case, we measure the performance of the three most important machine learning approaches applied to the text classification, in order to verify if new arrivals enhance the results from the Spanish language classification models.
format Objeto de conferencia
Objeto de conferencia
author Fernández, Juan Manuel
Cavasi, Nicolás
Errecalde, Marcelo Luis
author_facet Fernández, Juan Manuel
Cavasi, Nicolás
Errecalde, Marcelo Luis
author_sort Fernández, Juan Manuel
title Classic and recent (neural) approaches to automatic text classification : A comparative study with e-mails in the Spanish language
title_short Classic and recent (neural) approaches to automatic text classification : A comparative study with e-mails in the Spanish language
title_full Classic and recent (neural) approaches to automatic text classification : A comparative study with e-mails in the Spanish language
title_fullStr Classic and recent (neural) approaches to automatic text classification : A comparative study with e-mails in the Spanish language
title_full_unstemmed Classic and recent (neural) approaches to automatic text classification : A comparative study with e-mails in the Spanish language
title_sort classic and recent (neural) approaches to automatic text classification : a comparative study with e-mails in the spanish language
publishDate 2021
url http://sedici.unlp.edu.ar/handle/10915/125140
work_keys_str_mv AT fernandezjuanmanuel classicandrecentneuralapproachestoautomatictextclassificationacomparativestudywithemailsinthespanishlanguage
AT cavasinicolas classicandrecentneuralapproachestoautomatictextclassificationacomparativestudywithemailsinthespanishlanguage
AT errecaldemarceloluis classicandrecentneuralapproachestoautomatictextclassificationacomparativestudywithemailsinthespanishlanguage
bdutipo_str Repositorios
_version_ 1764820451295494144

Ejemplares similares