Automation of dictation exercises. A working combination of CALL and NLP.

Authors

  • Richard Beaufort CENTAL, University catholique de Louvain
  • Sophie Roekhaut CENTAL, University catholique de Louvain

Abstract

This article is in the context of the Computer-Assisted Language Learning (CALL) framework, and addresses more specically the automation of dictation exercises. It presents a method for correcting learners' copies. Based around Natural Language Processing (NLP) tools, this method is original in two respects. First, it exploits the composition of nitestate machines, to both detect and delimit the errors. Second, it uses automatic morphosyntactic analysis of the original dictation, which makes it easier to produce supercial and in-depth linguistic feedback. The system has been evaluated on a corpus of 115 copies including 1,532 copy errors. The accuracy of the error detection is 99%. The supercial feedback is 97.2% correct, the in-depth feedback 96%, and the morpho-syntactic analysis 87.7%.

Downloads

Published

2011-12-01

How to Cite

Beaufort, R., & Roekhaut, S. (2011). Automation of dictation exercises. A working combination of CALL and NLP. Computational Linguistics in the Netherlands Journal, 1, 2–20. Retrieved from https://www.clinjournal.org/clinj/article/view/4

Issue

Section

Articles