Abstract
Previous work has recently shown that adequate and compact codifications of the lexicons involved in text-to-text MT tasks can be automatically created. The method extracted these representations from perceptrons with output contexts. They were later tested on a simple neural translator called RECONTRA. However, the size of the codifications was determined by hand using try-and-error mechanisms. This paper presents a method for automatically obtain such sizes by pruning the units of the hidden-layer of the perceptron encoder.
Partially supported by the Spanish Fundació Caixa Castelló, project P1·1B2002-15.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
J. C. Amengual et al. The Eutrans-I Spoken Language Translation System. Machine Translation, vol. 15, pp. 75–102, 2000.
G. A. Casañ, M. A. Castaño. Distributed Representation of Vocabularies in the RECONTRA Neural Translator. Procs. of the 6th European Conference on Speech Communication and Technology, vol. 6, pp. 2423–2426. Budapest, 1999.
G. A. Casañ, M. A. Castaño. Automatic Word Codification for the RECONTRA Connectionist Translator. Submitted to the 1st Iberian Pattern recognition and Image Analysis, 2003.
M. A. Castaño, F. Casacuberta. Text-to-Text Machine Translation Using the RECONTRA Connectionist Model. In “Lecture Notes in Computer Science: Applications of Bio-Inspired Artificial Neural Networks”, vol. 1607, pp. 683–692, José Mira, Juan Vincente Sánchez-Andrés (Eds.), Springer-Verlag, 1999.
D. J. Chalmers. Syntactic Transformations on Distributed Representations. Connection Science, vol. 2, pp. 53–62, 1990.
J. L. Elman. Distributed Representations, Simple Recurrent Networks, and Grammatical structure. Machine Learning, vol. 7, pp. 195–225, 1991.
J. L. Elman. Finding Structure in Time. Cognitive Science, vol. 2, no. 4, pp. 279–311, 1990.
R. P. Miikkulainen, M. G. Dyer. Natural Language Processing with Modular Neural Networks and Distributed Lexicon. Cognitive Science, vol. 15, pp. 393–399, 1991.
M. C. Mozer, P. Smolensky. Skeletonization: A Technique for Trimming the Fat from a Network Via Relevance Assessment. Advances in Neural Information Processing vol. 1, pp. 177–185, D. S. Touretzky, Ed. Morgan Kaufmann, 1990.
J. B. Pollack. Recursive Distributed Representations. Artificial Intelligence, vol. 46, pp. 77–105, 1990.
D. E. Rumelhart, G. Hinton, R. Williams. Learning Sequential Structure in Simple Recurrent Networks. In “Parallel distributed processing: Experiments in the microstructure of cognition”, vol. 1. Eds. D.E. Rumelhart, J.L. McClelland and the PDP Research Group, MIT Press, 1986.
A. Zell et al. SNNS: Stuttgart Neural Network Simulator. User manual, Version 4.1. Technical Report no. 6195, Institute for Parallel and Distributed High Performance Systems, University of Stuttgart, 1995.
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2003 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Casañ, G.A., Asunción, M. (2003). Automatic Size Determination of Codifications for the Vocabularies of the RECONTRA Connectionist Translator* . In: Mira, J., Álvarez, J.R. (eds) Artificial Neural Nets Problem Solving Methods. IWANN 2003. Lecture Notes in Computer Science, vol 2687. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-44869-1_97
Download citation
DOI: https://doi.org/10.1007/3-540-44869-1_97
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-40211-4
Online ISBN: 978-3-540-44869-3
eBook Packages: Springer Book Archive