Automated Analysis of Students' Free-text Answers for Computer-Assisted Assessment

Matthieu Hermet 1 Stan Szpakowicz 2 Lise Duquette 3
1 SITE - School of Information Technology and Engineering [Ottawa]
2 Institute of Computer Science [Warszawa]
3 Second Language Institute
Abstract : We present an approach to Computer-Assisted Assessment of free-text material based on symbolic analysis of student input. The theory that underlies this approach arises from previous work on DidaLect, a tutorial system for reading comprehension in French as a Second Language. The theory enables processing of a free-text segment for assessment to operate without precoded reference material. A study based on a small collection of student answers to several types of questions has justified our approach, and helped to define a methodology and design a prototype.
Keywords : computer assisted language learning (CALL) natural language processing (NLP) computer-assisted assessments symbolic analysis
Type de document :
Communication dans un congrès
The 13th Conference on Natural Language Processing (TALN 2006). April 10-13, 2006. Leuven (Belgium), 2006, Leuven, Belgium. pp.835-845, 2006
Liste complète des métadonnées

Littérature citée [9 références]  Voir  Masquer  Télécharger
https://telearn.archives-ouvertes.fr/hal-00197397
Contributeur : Jerome Zeiliger <>
Soumis le : vendredi 14 décembre 2007 - 15:16:03
Dernière modification le : mercredi 21 février 2018 - 14:46:02
Document(s) archivé(s) le : lundi 12 avril 2010 - 07:55:45

Fichier

Hermet-Matthieu-2006.pdf
Fichiers produits par l'(les) auteur(s)

Identifiants

  • HAL Id : hal-00197397, version 1

Collections

TELEARN | TICE

Citation

Matthieu Hermet, Stan Szpakowicz, Lise Duquette. Automated Analysis of Students' Free-text Answers for Computer-Assisted Assessment. The 13th Conference on Natural Language Processing (TALN 2006). April 10-13, 2006. Leuven (Belgium), 2006, Leuven, Belgium. pp.835-845, 2006. 〈hal-00197397〉

Exporter

BibTeX TEI DC DCterms EndNote

Partager

Métriques

Consultations de la notice

282

Téléchargements de fichiers

148

Contact

support.ccsd.cnrs.fr
hal.support@ccsd.cnrs.fr
Logo CCSD