Generating Answer Candidates for Quizzes and Answer-Aware Question Generators

Kristiyan Vachev, Momchil Hardalov, Georgi Karadzhov, Georgi Georgiev, Ivan Koychev, Preslav Nakov


Abstract
In education, quiz questions have become an important tool for assessing the knowledge of students. Yet, manually preparing such questions is a tedious task, and thus automatic question generation has been proposed as a possible alternative. So far, the vast majority of research has focused on generating the question text, relying on question answering datasets with readily picked answers, and the problem of how to come up with answer candidates in the first place has been largely ignored. Here, we aim to bridge this gap. In particular, we propose a model that can generate a specified number of answer candidates for a given passage of text, which can then be used by instructors to write questions manually or can be passed as an input to automatic answer-aware question generators. Our experiments show that our proposed answer candidate generation model outperforms several baselines.
Anthology ID:
2021.ranlp-srw.28
Volume:
Proceedings of the Student Research Workshop Associated with RANLP 2021
Month:
September
Year:
2021
Address:
Online
Editors:
Souhila Djabri, Dinara Gimadi, Tsvetomila Mihaylova, Ivelina Nikolova-Koleva
Venue:
RANLP
SIG:
Publisher:
INCOMA Ltd.
Note:
Pages:
203–209
Language:
URL:
https://aclanthology.org/2021.ranlp-srw.28
DOI:
Bibkey:
Cite (ACL):
Kristiyan Vachev, Momchil Hardalov, Georgi Karadzhov, Georgi Georgiev, Ivan Koychev, and Preslav Nakov. 2021. Generating Answer Candidates for Quizzes and Answer-Aware Question Generators. In Proceedings of the Student Research Workshop Associated with RANLP 2021, pages 203–209, Online. INCOMA Ltd..
Cite (Informal):
Generating Answer Candidates for Quizzes and Answer-Aware Question Generators (Vachev et al., RANLP 2021)
Copy Citation:
PDF:
https://aclanthology.org/2021.ranlp-srw.28.pdf
Data
EXAMSSQuAD