Creating deep neural networks for text classification tasks using grammar genetic programming
Created by W.Langdon from
gp-bibliography.bib Revision:1.7047
- @Article{MAGALHAES:2023:asoc,
-
author = "Dimmy Magalhaes and Ricardo H. R. Lima and
Aurora Pozo",
-
title = "Creating deep neural networks for text classification
tasks using grammar genetic programming",
-
journal = "Applied Soft Computing",
-
volume = "135",
-
pages = "110009",
-
year = "2023",
-
ISSN = "1568-4946",
-
DOI = "
doi:10.1016/j.asoc.2023.110009",
-
URL = "
https://www.sciencedirect.com/science/article/pii/S1568494623000273",
-
keywords = "genetic algorithms, genetic programming, Text
classification, Evolutionary algorithms, Automatic
design, Grammatical evolution, Deep neural networks",
-
abstract = "Text classification is one of the Natural Language
Processing (NLP) tasks. Its objective is to label
textual elements, such as phrases, queries, paragraphs,
and documents. In NLP, several approaches have achieved
promising results regarding this task. Deep
Learning-based approaches have been widely used in this
context, with deep neural networks (DNNs) adding the
ability to generate a representation for the data and a
learning model. The increasing scale and complexity of
DNN architectures was expected, creating new challenges
to design and configure the models. In this paper, we
present a study on the application of a grammar-based
evolutionary approach to the design of DNNs, using
models based on Convolutional Neural Networks (CNNs),
Long Short-Term Memory (LSTM), and Graph Neural
Networks (GNNs). We propose different grammars, which
were defined to capture the features of each type of
network, also proposing some combinations, verifying
their impact on the produced designs and performance of
the generated models. We create a grammar that is able
to generate different networks specialized on text
classification, by modification of Grammatical
Evolution (GE), and it is composed of three main
components: the grammar, mapping, and search engine.
Our results offer promising future research directions
as they show that the projected architectures have a
performance comparable to that of their counterparts
but can still be further improved. We were able to
improve the results of a manually structured neural
network in 8,18percent in the best case",
- }
Genetic Programming entries for
Dimmy Magalhaes
Ricardo Henrique Remes de Lima
Aurora Trinidad Ramirez Pozo
Citations