Generation and Evaluation of Multiple-choice Reading Comprehension Questions for Swedish

Dmytro Kalpakchi, Johan Boye


Abstract
Multiple-choice questions (MCQs) provide a widely used means of assessing reading comprehension. The automatic generation of such MCQs is a challenging language-technological problem that also has interesting educational applications. This article presents several methods for automatically producing reading comprehension questions MCQs from Swedish text. Unlike previous approaches, we construct models to generate the whole MCQ in one go, rather than using a pipeline architecture. Furthermore, we propose a two-stage method for evaluating the quality of the generated MCQs, first evaluating on carefully designed single-sentence texts, and then on texts from the SFI national exams. An extensive evaluation of the MCQ-generating capabilities of 12 different models, using this two-stage scheme, reveals that GPT-based models surpass smaller models that have been fine-tuned using small-scale datasets on this specific problem.
Anthology ID:
2024.nejlt-1.6
Volume:
Northern European Journal of Language Technology, Volume 10
Month:
December
Year:
2024
Address:
Linköping, Sweden
Editor:
Marcel Bollmann
Venue:
NEJLT
SIG:
Publisher:
Linköping University Electronic Press
Note:
Pages:
86–105
Language:
URL:
https://aclanthology.org/2024.nejlt-1.6/
DOI:
10.3384/nejlt.2000-1533.2024.4886
Bibkey:
Cite (ACL):
Dmytro Kalpakchi and Johan Boye. 2024. Generation and Evaluation of Multiple-choice Reading Comprehension Questions for Swedish. Northern European Journal of Language Technology, 10:86–105.
Cite (Informal):
Generation and Evaluation of Multiple-choice Reading Comprehension Questions for Swedish (Kalpakchi & Boye, NEJLT 2024)
Copy Citation:
PDF:
https://aclanthology.org/2024.nejlt-1.6.pdf