Error diagnosing and selection in a training system: for second language learning

  • Authors:
  • Wolfgang Menzel

  • Affiliations:
  • Zentralinstitut für Sprachwissenschaft, Akademie der Wissenschaften der DDR, Berlin, DDR

  • Venue:
  • COLING '88 Proceedings of the 12th conference on Computational linguistics - Volume 2
  • Year:
  • 1988

Quantified Score

Hi-index 0.00

Visualization

Abstract

A diagnosing procedure to be used in intelligent systems for language instruction is presented. Based on a knowledge representation scheme for a certain class of syntactic correctness conditions the system carries out a thorough analysis of possible error hypotheses and their consequences. A comparison with earlier attempts shows a clearly improved precision of diagnostic results. First of all, the procedure concentrates on an exact localization of rule violations, but - if desired - is able to infer information about factual faults as well.