Multiple Choice Question Corpus Analysis for Distractor Characterization

International audience In this paper, we present a study of MCQ aiming to define criteria in order to automatically select distractors. We are aiming to show that distractor editing follows rules like syntactic and semantic homogeneity according to associated answer, and the possibility to automatic...

Full description

Bibliographic Details
Main Authors: Pho, Van-Minh, Andre, T., Ligozat, Anne-Laure, Grau, Brigitte, Illouz, Gabriel, François, Thomas
Other Authors: Laboratoire d'Informatique pour la Mécanique et les Sciences de l'Ingénieur (LIMSI), Université Paris-Sud - Paris 11 (UP11)-Sorbonne Université - UFR d'Ingénierie (UFR 919), Sorbonne Université (SU)-Sorbonne Université (SU)-Université Paris-Saclay-Centre National de la Recherche Scientifique (CNRS)-Université Paris Saclay (COmUE)
Format: Conference Object
Language:English
Published: HAL CCSD 2014
Subjects:
MCQ
corpus analysis
syntactic and semantic homogeneity
[INFO]Computer Science [cs]
[INFO.INFO-CL]Computer Science [cs]/Computation and Language [cs.CL]
Iceland
Online Access:https://hal.science/hal-02282009
https://hal.science/hal-02282009/document
https://hal.science/hal-02282009/file/Sami-lrec2014.pdf
Description
Summary:International audience In this paper, we present a study of MCQ aiming to define criteria in order to automatically select distractors. We are aiming to show that distractor editing follows rules like syntactic and semantic homogeneity according to associated answer, and the possibility to automatically identify this homogeneity. Manual analysis shows that homogeneity rule is respected to edit distractors and automatic analysis shows the possibility to reproduce these criteria. These ones can be used in future works to automatically select distractors, with the combination of other criteria.

Similar Items