Accession Number:

ADA162222

Title:

The Correction of Ill-Formed Input Using History-Based Expectation with Applications to Speech Understanding.

Descriptive Note:

Technical paper,

Corporate Author:

DUKE UNIV DURHAM NC DEPT OF COMPUTER SCIENCE

Personal Author(s):

Report Date:

1985-10-01

Pagination or Media Count:

46.0

Abstract:

A method for error correction if ill formed input is described which acquires dialogue patterns in typical usage and uses these patterns to predict new inputs. Error correction is done by strongly biasing parsing toward expected meanings unless clear evidence from the input shows the current sentence is not expected. A dialogue acquisition and tracking algorithm is presented along with a description of its implementation in a power of the error correction methodology when stereotypic dialogue occurs. Author

Subject Categories:

  • Cybernetics
  • Computer Programming and Software

Distribution Statement:

APPROVED FOR PUBLIC RELEASE