Abstract
One of the problems of the connectionist translator RECONTRA is the representation of the vocabularies of the languages implied in the task to be translated. In previous work, a simple connectionist model was used to provide automatic codifications for RECONTRA, but sometimes these codifications have shown not to be adequate for the translation task. In this paper we aim to extend the RECONTRA topology in order to integrate the creation of the codifications (for the languages to be translated) and the translation task in an unique connectionist architecture. To do that, a new hidden layer is added to the network, as it’s known how a neural network develops its own internal representation of its input.
Partially supported by the Generalitat Valenciana Project number GV/2007/105.
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.
Similar content being viewed by others
References
Koncar, N., Guthrie, G.: A Natural Language Translation Neural Network. In: Procs. of the Int. Conf. on New Methods in Language Processing, Manchester, UK, pp. 71–77 (1994)
Waibel, A., Jain, A.N., McNair, A.E., Saito, H., Hauptmann, A.G., Tebelskis, J.: JANUS: A Speech-to-Speech Translation System using Connectionist and Symbolic Processing Strategies. In: Procs. of the International Conference on Acustic, Speech and Signal Processing, pp. 793–796 (1991)
Castaño, M.A.: Redes Neuronales Recurrentes para Inferencia Gramatical y Traducción Automática. Ph.D. dissertation, Universidad Politécnica de Valencia, Spain (1998)
Casañ, G.A., Castaño, M.A.: Distributed Representation of Vocabularies in the RECONTRA Neural Translator. In: Procs. of the 6th European Conference on Speech Communication and Technology, Budapest, Hungary, vol. 6, pp. 2423–2426 (1999)
Casañ, G.A., Castaño, M.A.: Automatic Word Codification for the RECONTRA Connectionist Translator. In: Perales, F.J., Campilho, A.C., Pérez, N., Sanfeliu, A. (eds.) IbPRIA 2003. LNCS, vol. 2652, pp. 168–175. Springer, Heidelberg (2003)
Casañ, G.A., Castaño, M.A.: A New Approach to Codification for the RECONTRA Neural Translator. In: Procs. Ninth IASTED International Conference on Artifical Intelligence and Soft Computing, pp. 147–152 (2005)
Casañ, G.A., Castaño, M.A.: Tuning word codifications for the RECONTRA translator. In: Borajo, D., Castillo, L., Corchado, J.M. (eds.) Actas XII Conferencia de la Asociación Española para la Inteligencia Artificial, Salamanca, Spain. Universidad de Salamanca, vol. 2, pp. 351–354 (2007)
Bengio, Y., et al.: A Neural Probabilistic Language Model. Journal on Machine Learning Research 3, 1137–1151 (2003)
Elman, J.L.: Finding Structure in Time. Cognitive Science 2(4), 279–311 (1990)
Tamura, S., Tateishi, M.: Capabilities of a Four-Layered Feedforward Neural Network: Four Layers Versus Three. IEEE Trans. on Neural Networks 9(2), 251–255 (1997)
Rumelhart, D.E., Hinton, G., Williams, R.: Learning Sequential Structure in Simple Recurrent Networks. In: Rumelhart, D.E., McClelland, J.L., The PDP Research Group (eds.) Parallel distributed processing: Experiments in the microstructure of cognition, vol. 1. MIT Press, Cambridge (1981)
Marzal, A., Vidal, E.: Computation of Normalized Edit Distance and Applications. IEEE Transactions on Pattern Analysis and Machine Intelligence 15(9) (1993)
Hinton, G.E., McClelland, J.L., Rumelhart, D.E.: Distributed representations. In: Rumelhart, D.E., McClelland, J.L. (eds.) Parallel Distributed Processing: Explorations in the Microstructure of Cognition. Vol 1: Foundations. MIT Press, Cambridge (1986)
Möller, M.F.: A Scaled Conjugate Gradient Algorithm for Fast Supervised Learning. Neural Networks 6, 525–533 (1993)
Mozer, M.C., Smolensky, P.: Skeletonization: a Technique for Trimming the Fat from a Network via Relevance Assessment. In: Touretzky, D.S., Kaufmann, E.M. (eds.) Advances in Neural Information Processing, vol. 1, pp. 177–185 (1990)
Amengual, J.C., Castaño, M.A., Castellanos, A., Llorens, D., Marzal, A., Prat, A., Vilar, J.M., Benedí, J.M., Casacuberta, F., Pastor, M., Vidal, E.: The Eutrans-I Spoken Language System. Machine Translation, vol. 15, pp. 75–102. Kluwer Academic Publishers, Dordrecht (2000)
Prat, F., Casacuberta, F., Castro, M.J.: Machine Translation with Grammar Association: Combining Neural Networks and Finite-State Models. In: Procs. The Second Workshop on Natural Language Processing and Neural Networks, Tokio, Japan, pp. 53–61 (2001)
Zell, A., 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, Germany (1995)
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 2009 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Casañ, G.A., Castaño, M.A. (2009). A Connectionist Automatic Encoder and Translator for Natural Languages. In: Corchado, J.M., Rodríguez, S., Llinas, J., Molina, J.M. (eds) International Symposium on Distributed Computing and Artificial Intelligence 2008 (DCAI 2008). Advances in Soft Computing, vol 50. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-85863-8_49
Download citation
DOI: https://doi.org/10.1007/978-3-540-85863-8_49
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-85862-1
Online ISBN: 978-3-540-85863-8
eBook Packages: EngineeringEngineering (R0)