On adaptive acquisition of language

Author

Gorin, A.L. ; Levinson, S.E. ; Miller, L.G. ; Gertner, A.N. ; Ljolje, A. ; Goldman, E.R.

Author_Institution

AT&T Bell Lab., Murray Hill, NJ, USA

fYear

1990

fDate

3-6 Apr 1990

Firstpage

601

Abstract

A system that automatically acquires a language model for a particular task from semantic-level information is described. This is in contrast to systems with predefined vocabulary and syntax. The purpose of the system is to map spoken or typed input into a machine action. To accomplish this task a medium-grain neural network is used. An adaptive training procedure is introduced for estimating the connection weights. It has the advantages of rapid, single-pass and order-invariant learning. The resulting weights have information-theoretic significance and do not require gradient search techniques for their estimation. The system was experimentally evaluated on three text-based tasks; a three-class inward-call manager with an acquired vocabulary of over 1600 words, a 15-action subset of the DARPA Resource Manager with an acquired vocabulary of over 700 words, and discrimination between idiomatic phrases meaning yes or no

Keywords

adaptive systems; learning systems; natural languages; neural nets; speech recognition; DARPA Resource Manager; adaptive acquisition; language model; natural language; neural network; order-invariant learning; semantic-level information; single pass learning; speech recognition; text-based tasks; three-class inward-call manager; Control systems; Distortion; Error correction; Management training; Natural languages; Neural networks; Parametric statistics; Resource management; Speech recognition; Vocabulary;

fLanguage

English

Publisher

ieee

Conference_Titel

Acoustics, Speech, and Signal Processing, 1990. ICASSP-90., 1990 International Conference on

Conference_Location

Albuquerque, NM

ISSN

1520-6149

Type

conf

DOI

10.1109/ICASSP.1990.115784

Filename

115784