Abstract
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.
This is a preview of subscription content, log in via an institution to check access.
Preview
Unable to display preview. Download preview PDF.
Similar content being viewed by others
References
Edelman, G.M., Tononi, G.: A Universe of Consciousness - How Matter Becomes Imagination. Basic Books, New York (2000)
Rosa, J.L.G.: An Artificial Neural Network Model Based on Neuroscience: Looking Closely at the Brain. In: Kůrková, V., Steele, N.C., Neruda, R., Kárný, M. (eds.) Artificial Neural Nets and Genetic Algorithms – Proc. of the Intl. Conf. in Prague, ICANNGA 2001, Czech Republic, April 22-25, pp. 138–141. Springer, Heidelberg (2001)
O’Reilly, R.C.: Biologically Plausible Error-driven Learning using Local Activation Differences: The Generalized Recirculation Algorithm. Neural Comp. 8(5), 895–938 (1996)
Haegeman, L.: Introduction to Government and Binding Theory. Basil Blackwell Inc., Cambridge (1991)
Dowty, D.: On the Semantic Content of the Notion of ’Thematic Role’. In: Chierchia, G., et al. (eds.) Properties, Types and Meaning, Kluwer, Dordrecht (1989)
Rosa, J.L.G., Françozo, E.: Linguistic Relations Encoding in a Symbolic-Connectionist Hybrid Natural Language Processor. In: Monard, M.C., Sichman, J.S. (eds.) SBIA 2000 and IBERAMIA 2000. LNCS (LNAI), vol. 1952, pp. 259–268. Springer, Heidelberg (2000)
McClelland, J.L., Kawamoto, A.H.: Mechanisms of Sentence Processing: Assigning Roles to Constituents of Sentences. In: McClelland, J.L., Rumelhart, D.E. (eds.) Parallel Distributed Processing, vol. 2, A Bradford Book, The MIT Press (1986)
Rosa, J.L.G.: A Biologically Inspired Connectionist System for Natural Language Processing. In: Proc. of the 2002 VII Brazilian Symposium on Neural Networks (SBRN 2002), Recife, Brazil, November 11-14, pp. 243–248. IEEE Computer Society Press, Los Alamitos (2002)
Rosa, J.L.G., Françozo, E.: Hybrid Thematic Role Processor: Symbolic Linguistic Relations Revised by Connectionist Learning. In: Proc. of IJCAI 1999-16th. Intl. Joint Conf. on Artificial Intelligence, Stockholm, Sweden, July 31 - August 6, vol. 2, pp. 852–857 (1999)
Elman, J.L.: Finding Structure in Time. Cognitive Science 14, 179–211 (1990)
Crick, F.H.: The Recent Excitement about Neural Networks. Nature 337, 129–132 (1989)
Rosa, J.L.G.: A Biologically Motivated Connectionist System for Predicting the Next Word in Natural Language Sentences. In: Proc. of the 2002 IEEE Intl. Conf. on Systems, Man, and Cybernetics, Hammamet, Tunisia, October 6-9 (2002)
Hinton, G.E., McClelland, J.L.: Learning Representations by Recirculation. In: Anderson, D.Z. (ed.) Neural Information Processing Systems 1987, pp. 358–366. American Institute of Physics, New York (1988)
Haykin, S.: Neural Networks - A Comprehensive Foundation, 2nd edn. Prentice Hall, Upper Saddle River (1999)
O’Reilly, R.C., Munakata, Y.: Computational Explorations in Cognitive Neuroscience - Understanding the Mind by Simulating the Brain. A Bradford Book, The MIT Press, Cambridge (2000)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2004 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Rosa, J.L.G. (2004). A Biologically Motivated and Computationally Efficient Natural Language Processor. In: Monroy, R., Arroyo-Figueroa, G., Sucar, L.E., Sossa, H. (eds) MICAI 2004: Advances in Artificial Intelligence. MICAI 2004. Lecture Notes in Computer Science(), vol 2972. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-24694-7_40
Download citation
DOI: https://doi.org/10.1007/978-3-540-24694-7_40
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-21459-5
Online ISBN: 978-3-540-24694-7
eBook Packages: Springer Book Archive