Learning subsequential transducers for pattern recognition interpretation tasks
- 1 May 1993
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in Ieee Transactions On Pattern Analysis and Machine Intelligence
- Vol. 15 (5), 448-458
- https://doi.org/10.1109/34.211465
Abstract
A formalization of the transducer learning problem and an effective and efficient method for the inductive learning of an important class of transducers, the class of subsequential transducers, are presented. The capabilities of subsequential transductions are illustrated through a series of experiments that also show the high effectiveness of the proposed learning method in obtaining very accurate and compact transducers for the corresponding tasks.<>Keywords
This publication has 13 references indexed in Scilit:
- Inference of k-testable languages in the strict sense and application to syntactic pattern recognitionIeee Transactions On Pattern Analysis and Machine Intelligence, 1990
- INDUCTIVE LEARNING OF FINITE-STATE TRANSDUCERS FOR THE INTERPRETATION OF UNIDIMENSIONAL OBJECTSPublished by World Scientific Pub Co Pte Ltd ,1990
- Grammatical inference for even linear languages based on control setsInformation Processing Letters, 1988
- Inductive Inference: Theory and MethodsACM Computing Surveys, 1983
- Inference of Reversible LanguagesJournal of the ACM, 1982
- A structural approach of pattern recognitionSignal Processing, 1980
- Transductions and Context-Free LanguagesPublished by Springer Science and Business Media LLC ,1979
- Inference of Sequential Machines from Sample ComputationsIEEE Transactions on Computers, 1978
- Grammatical Inference: Introduction and Survey - Part IIEEE Transactions on Systems, Man, and Cybernetics, 1975
- Language identification in the limitInformation and Control, 1967