Abstract
A new application of the Onward Subsequential Transducer Inference Algorithm (OSTIA) is presented. Limited-domain Machine Translation tasks have been defined from a conceptually constrained task which was recently proposed within the field of Cognitive Science. Large corpora of English-to-Spanish and English-to-German translations have been generated, and exhaustive experiments have been carried out to test the ability of OSTIA to learn these translations. The success of the results show the usefulness of formal learning techniques in limited-domain Machine Translation tasks.
Work partially supported by the Spanish CICYT, under grant TIC-1026/92-CO2.
Supported by a postgraduate grant from the Spanish “Ministerio de Educación y Ciencia”.
Preview
Unable to display preview. Download preview PDF.
References
A. Aho, R. Sethi, J.UllmanCompilers. Principles, Techniques, and Tools. Addison-Wesley Publishing Company, Reading, Massachusetts. 1986.
J. Berstel. Transductions and Context-Free Languages. Teubner, Stuttgart. 1979.
A. Castellanos, E. Vidal, J. Oncina. “Language Understanding and Subsequential Transducer Learning”. 1st International Colloquium on Grammatical Inference, Colchester, England. Proceedings, pp. 11/1–11/10. April, 1993.
J.A. Feldman, G. Lakoff, A. Stolcke, S.H. Weber. “Miniature Language Acquisition: A touchstone for cognitive science”. Technical Report, TR-90-009. International Computer Science Institute, Berkeley, California. April, 1990.
V. Jimenez, E. Vidal, J. Oncina, A. Castellanos. “Spoken-Language Machine Translation in Limited-Domain Tasks”. CRIM/FORWISS Workshop on Progress and Prospects of Speech Research and Technology. Munich (Germany), September 1994. (to be published).
P. Luneau, M. Richetin, C. Cayla. “Sequential Learning from Input-Output Behaviour”. Robotica, Vol. 1, pp. 151–159. 1984.
J. Oncina. Aprendizaje de Lenguajes Regulares y Funciones Subsecuenciales. Ph. D. dissertation, Universidad Politénica de Valencia. 1991.
J. Oncina, P. Garcia. “Inductive Learning of Subsequential Functions”. Technical Report, DSIC II/34/91. Dpto. Sistemas Informáticos y Computación, Univ. Politécnica de Valencia. 1991.
J. Oncina, P. Garcia, E. Vidal. “Transducer Learning in Pattern Recognition”. 11th IAPR International Conference on Pattern Recognition, The Hague, The Netherlands. Proceedings, Vol. II, pp. 299–302. 1992.
J. Oncina, P. Garcia, E. Vidal. “Learning Subsequential Transducers for Pattern Recognition Interpretation Tasks”. IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 15, No. 5, pp. 448–458. May, 1993.
J. Oncina, A. Castellanos, E. Vidal, V. Jimenez. “Corpus-Based Machine Translation through Subsequential Transducers”. Third International Conference on the Cognitive Science of Natural Language Processing. Dublin (Ireland), July 1994.
S.J. Raudys, A.K. Jain. “Small Sample Size Effects in Statistical Pattern Recognition: Recommendations for Practitioners”. IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 13, No. 3, pp. 252–264. March, 1991.
A. Stolcke. “Learning Feature-based Semantics with Simple Recurrent Networks”. Technical Report, TR-90-015. International Computer Science Institute, Berkeley, California. April, 1990.
E. Vidal, P. Garcia, E. Segarra. “Inductive Learning of Finite-State Transducers for the Interpretation of Unidimensional Objects”. Structural Pattern Analysis. R. Mohr, T. Pavlidis and A. Sanfeliu (eds.), World Scientific, pp. 17–35. 1990.
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 1994 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Castellanos, A., Galiano, I., Vidal, E. (1994). Application of OSTIA to machine translation tasks. In: Carrasco, R.C., Oncina, J. (eds) Grammatical Inference and Applications. ICGI 1994. Lecture Notes in Computer Science, vol 862. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-58473-0_140
Download citation
DOI: https://doi.org/10.1007/3-540-58473-0_140
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-58473-5
Online ISBN: 978-3-540-48985-6
eBook Packages: Springer Book Archive