Adaptive language acquisition using incremental learning
- 1 January 1993
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 1, 501-504 vol.1
- https://doi.org/10.1109/icassp.1993.319165
Abstract
An incremental approach to solving an algebraic formulation of the language acquisition problem is presented. This problem consists of solving a system of linear equations, where each equation represents a sentence/action pair and each variable denotes a word/action association. The algebraic model for language acquisition has been shown to provide advantages over the relative frequency estimate models when dealing with small-sample statistics. Two incremental methods are investigated to solve the system of linear equations. The incremental methods provide a regularized solution that is shown experimentally to be advantageous over the pseudo-inverse solution for classifying test data. In addition, the methods are more efficient with respect to computational and memory requirements.Keywords
This publication has 5 references indexed in Scilit:
- Some experiments in spoken language acquisitionPublished by Institute of Electrical and Electronics Engineers (IEEE) ,1993
- A structured network architecture for adaptive language acquisitionPublished by Institute of Electrical and Electronics Engineers (IEEE) ,1992
- Adaptive acquisition of languageComputer Speech & Language, 1991
- Adaptive acquisition of spoken languagePublished by Institute of Electrical and Electronics Engineers (IEEE) ,1991
- Robust StatisticsPublished by Wiley ,1981