Abstract
Encouragingly accurate translations have recently been obtained using a connectionist translator called RECONTRA (Recurrent Connectionist Translator). In contrast to traditional Knowledge-Based systems, this model is built from training data resulting in an Example-Based approach. It directly carries out the translation between the source and target language and employs a simple (recurrent) connectionist topology and a simple training scheme. This paper extends previous work exploring the capabilities of this RECONTRA model to perform text-to-text translations in limited-domain tasks.
Partially supported by the Spanish CICYT, project TIC-97-0745-CO2-02.
Preview
Unable to display preview. Download preview PDF.
References
J.C. Amengual, J.M. Benedí, K. Beulen, F. Casacuberta, M.A. Castaño, A. Castellanos, D. Llorens, A. Marzal, H. Ney, F. Prat, E. Vidal, J.M. Vilar. Speech Translation based on Automatically Trainable Finite-State Models. Procs. of the 5th European Conference on Speech Communication and Technology (EUROSPEECH-97), vol. 1, pp. 91–91, Rhodes, Greece. 1997.
J.C. Amengual, J.M. Benedí, F. Casacuberta, M.A. Castaño, A. Castellanos, D. Llorens, A. Marzal, F. Prat, E. Vidal, J.M. Vilar. Error-Correcting Parsing for Text-to-Text Machine Translation using Finite State Models. Procs. of the 7th International Conference on Theoretical and Methodological Issues in Machine Translation (TMI-97), pp. 135–142. Santa Fe, USA. 1997.
P.F. Brown, S.A. Della Pietra, V.J. Della Prieta, R.L. Mercer. The Mathematics of Statistical Machine Translation: Parameter Estimation. Computational Linguistics, vol. 19, no. 2, pp. 263–311. 1993.
M.A. Castaño, F. Casacuberta. A Connectionist Approach to Machine Translation. Procs. of the 5th European Conference on Speech Communication and Technology (EUROSPEECH-97), vol. 1, pp. 91–94, Rhodes, Greece. 1997.
M.A. Castaño, F. Casacuberta. Training Simple Recurrent Networks through Gradient Descent Algorithms. In “Biological and Artificial Computation: From Neuroscience to Technology”, In “Lecture Notes in Computer Science”, vol. 1240, pp 493–500. Eds. J. Mira, R. Moreno-Díaz, J. Cabestany. Springer-Verlag. 1997.
M.A. Castaño. Redes Neuronales Recurrentes para Inferencia Gramatical y Traducción Automática. Ph.D. dissertation, Dpto. Sistemas Informáticos y Computación, Universidad Politécnica de Valencia. 1998.
A. Castellanos, I. Galiano, E. Vidal. Application of OSTIA to Machine Translation Tasks. In “Lecture Notes in Computer Science”, vol 862, pp. 93–105, R.C.Carrasco and J. Oncina (Eds.), Springer-Verlag. 1994.
G. Dorffner. A step towards sub-symbolic language models without linguistic representations. Connectionist Approaches to Language Processing, vol. 1. Eds. R. Reilly, N. Sharkey. Erlbaum. 1990.
J.L. Elman. Finding Structure in Time. Cognitive Science, vol. 2, no. 4, pp. 279–311. 1990.
K.S. Fu. Syntactic Pattern Recognition and Applications. Prentice-Hall. 1982.
I. García. Traducción Automática basada en Métodos Estadísticos. Final year project. Dpto. Sistemas Informáticos y Computación. Universidad Politécnica de Valencia. 1996.
F. Jelinek. Language Modelling for Speech Recognition. Procs. of the 12th European Conference on Artificial Intelligence (ECAI-96), pp. 26–32, Hungary. 1996.
N. Koncar, G. Guthrie. A Natural Language Translation Neural Network. Procs. of the Int. Conf. on New Methods in Language Processing, pp. 71–77, Manchester, UK. 1994.
A. Marzal, E. Vidal. Computation of Normalized Edit Distance and Applications. IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 15, num. 9. 1993.
F. Prat. Traducción Automática en Dominios Restringidos: Algumos Modelos Estocásticos Susceptibles de ser Aprendidos a partir de Ejemplos. Ph.D. dissertation, Dpto. Sistemas Informáticos y Computación, Universidad Politécnica de Valencia. 1998.
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. Rumelhart D.E., McClelland J.L. and the PDP Research Group (Eds.), MIT Press. Cambridge. 1986.
N.E. Sharkey. Connectionist Representations for Natural Language: Old and New. Procs. of the VI SEPLN, Donostia. 1990.
A. Waibel, A.N. Jain, A.E. McNair, H. Saito, A.G. Hauptmann, J. Tebelskis. JANUS: A Speech-to-Speech Translation System using Connectionist and Symbolic Processing Strategies. Procs. ICASSP-91, pp. 793–796. 1991.
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
Rights and permissions
Copyright information
© 1999 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Castano, M.A., Casacuberta, F. (1999). Text-to-text machine translation using the RECONTRA connectionist model. In: Mira, J., Sánchez-Andrés, J.V. (eds) Engineering Applications of Bio-Inspired Artificial Neural Networks. IWANN 1999. Lecture Notes in Computer Science, vol 1607. Springer, Berlin, Heidelberg . https://doi.org/10.1007/BFb0100536
Download citation
DOI: https://doi.org/10.1007/BFb0100536
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-66068-2
Online ISBN: 978-3-540-48772-2
eBook Packages: Springer Book Archive