Result: A biologically motivated and computationally efficient natural language processor

Title:
A biologically motivated and computationally efficient natural language processor
Authors:
GARCIA ROSA, Joao Luis
Source:
MICAI 2004 : advances in artificial intelligence (Mexico City, 26-30 April 2004)Lecture notes in computer science. :390-399
Publisher Information:
Berlin: Springer, 2004.
Publication Year:
2004
Physical Description:
print, 15 ref
Original Material:
INIST-CNRS
Subject Terms:
Control theory, operational research, Automatique, recherche opérationnelle, Computer science, Informatique, Sciences exactes et technologie, Exact sciences and technology, Sciences appliquees, Applied sciences, Informatique; automatique theorique; systemes, Computer science; control theory; systems, Logiciel, Software, Généralités, General, Algorithme apprentissage, Learning algorithm, Algoritmo aprendizaje, Algorithme rétropropagation, Backpropagation algorithm, Algoritmo retropropagación, Biomimétique, Biomimetics, Cortex cérébral, Cerebral cortex, Corteza cerebral, Intelligence artificielle, Artificial intelligence, Inteligencia artificial, Langage naturel, Natural language, Lenguaje natural, Mot, Word, Palabra, Phrase, Sentence, Frase, Programme traitement langage, Language processor, Programa tratamiento lenguaje, Relation sémantique, Semantic relation, Relación semántica, Réseau neuronal récurrent, Recurrent neural nets, Réseau neuronal, Neural network, Red neuronal, Traitement langage, Language processing, Tratamiento lenguaje
Document Type:
Conference Conference Paper
File Description:
text
Language:
English
Author Affiliations:
Centro de Ciências Exatas, Ambientais e de Tecnologias, Pontifícia Universidade Católica de Campinas -, PUC-Campinas, Rodovia D. Pedro I, km. 136 - Caixa Postal 317, 13012-970 - Campinas - SP, Brazil
ISSN:
0302-9743
Access URL:
http://pascal-francis.inist.fr/vibad/index.php?action=search&terms=15851463
Rights:
Copyright 2004 INIST-CNRS
CC BY 4.0
Sauf mention contraire ci-dessus, le contenu de cette notice bibliographique peut être utilisé dans le cadre d’une licence CC BY 4.0 Inist-CNRS / Unless otherwise stated above, the content of this bibliographic record may be used under a CC BY 4.0 licence by Inist-CNRS / A menos que se haya señalado antes, el contenido de este registro bibliográfico puede ser utilizado al amparo de una licencia CC BY 4.0 Inist-CNRS
Notes:
Computer science; theoretical automation; systems
Accession Number:
edscal.15851463
Database:
PASCAL Archive

Further Information

Conventional artificial neural network models lack many physiological properties of the neuron. Current learning algorithms are more concerned to computational performance than to biological credibility. Regarding a natural language processing application, the thematic role assignment - semantic relations between words in a sentence -, the purpose of the proposed system is to compare two different connectionist modules for the same application: (1) the usual simple recurrent network using backpropagation learning algorithm with (2) a biologically inspired module, which employs a bi-directional architecture and learning algorithm more adjusted to physiological attributes of the cerebral cortex. Identical sets of sentences are used to train the modules. After training, the achieved output data show that the physiologically plausible module displays higher accuracy for expectable thematic roles than the traditional one.