Abstract
The recently proposed OSTI algorithm allows for the identification of subsequential functions from input-output pairs. However, if the target is a partial function the convergence is not guaranteed. In this work, we extend the algorithm in order to allow for the identification of any partial subsequential function provided that either a negative sample or a description of the domain by means of a deterministic finite automaton is available.
This work has been partially supported by the Spanish CICYT under contract TIC93-0633-C02 & TIC95-0984-C02-01
Miguel A. Varó is supported by a postgraduate grant from the Generalitat Valenciana (local government)
This is a preview of subscription content, log in via an institution.
Preview
Unable to display preview. Download preview PDF.
References
D. Angluin, “Inference of Reversible Languages”. J. ACM 29, 741–765 (1982).
D. Angluin, C. H. Smith. “Inductive inference: theory and methods”. Computing Surveys, 15, 237–269 (1983).
J. Berstel. Transductions and Context-Free Languages. Teubner, Stuttgart (1979).
A. Castellanos, I. Galiano, E. Vidal. “Application of OSTIA to Machine translation Tasks”. Grammatical Inference and Applications. 2nd International Colloquium on Grammatical Inference. R.C. Carrasco and J. Oncina eds. El Campello (Spain) (1994).
E. M. Gold. “Language identification in the limit”. Information and Control, 10, 447–474 (1967).
E. M. Gold. “Complexity of automaton identification from given data”. Information and Control, 37, 302–320 (1978).
P. García, E. Vidal, J. Oncina. “Learning Locally Testable Languages in the Strict Sense”, Proceedings of the First International Workshop on Algorithmic Learning Theory, Japanese Society for Artificial Intelligence, 325–337 (October 1990).
P. García, E. Vidal. “Inference of k-Testable Languages in the Strict Sense and application to Syntactic Pattern Recognition”. IEEE Trans. Pattern Analysis and Machine Intelligence, 12, 920–925 (1990).
P. Luneau, M. Richetin, C. Cayla. “Sequential learning from input-output behavior”, Robotica, 1, 151–159 (1984).
L. Miclet. “Regular Inference with a Tail-Clustering Method”, IEEE Trans., SMC-10, 737–743 (1980).
J. Oncina. “Aprendizaje de lenguajes regulares y funciones subsecuenciales”. Ph. D. dissertation, Universidad Politécnica de Valencia (1991).
J. Oncina, P. García. “Inductive learning of subsequential functions”. Univ. Politécnica de Valencia, Tech. Rep. DSIC II 31 (1991).
J. Oncina, P. García, E. Vidal. “Learning Subsequential Transducers for Pattern Recognition Interpretation Tasks”. IEEE Trans. on Pattern Analysis and Machine Intelligence, 15, 448–458 (1993).
J. Oncina, A. Castellanos, E. Vidal, V. M. Jiménez. “Corpus based machine translation through subsequential transducers”. Proceedings of the 3rd. International Conference on the Cognitive Science of Natural Language Processing, Dublin (July 1994).
Y. Takada, “Grammatical inference for even linear languages based on control sets”, Inform. Processing Lett., 28, no.4, 193–199 (1988).
M. A. Varó. “Inferencia de Transductores Subsecuenciales con Información de Dominio y Rango” (in Spanish). Final year project supervised by J. Oncina. Facultad de Informática, Universidad Politécnica de Valencia (1994).
L. P. J. Velenturf. “Inference of sequential machines from sample computation,” IEEE Trans. Comput., 27, 167–170 (1978).
E. Vidal, P. García, E. Segarra, “Inductive learning of finte-state transducers for the interpretation of unidimensional objects”, Structural Pattern Analysis. R. Mohr, T.Pavlidis and A. San Feliu eds. New York: World Scientific, 17–35 (1990).
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 1996 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Oncina, J., Varó, M.A. (1996). Using domain information during the learning of a subsequential transducer. In: Miclet, L., de la Higuera, C. (eds) Grammatical Interference: Learning Syntax from Sentences. ICGI 1996. Lecture Notes in Computer Science, vol 1147. Springer, Berlin, Heidelberg. https://doi.org/10.1007/BFb0033364
Download citation
DOI: https://doi.org/10.1007/BFb0033364
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-61778-5
Online ISBN: 978-3-540-70678-6
eBook Packages: Springer Book Archive