Search: onr:"swepub:oai:DiVA.org:su-224808" >
Towards Data-effect...
Towards Data-effective Educational Question Generation with Prompt-based Learning
-
- Wu, Yongchao, 1987- (author)
- Stockholms universitet,Institutionen för data- och systemvetenskap
-
- Nouri, Jalal, 1982- (author)
- Stockholms universitet,Institutionen för data- och systemvetenskap
-
Megyesi, Beata (author)
-
show more...
-
- Henriksson, Aron, 1985- (author)
- Stockholms universitet,Institutionen för data- och systemvetenskap
-
- Duneld, Martin, 1971- (author)
- Stockholms universitet,Institutionen för data- och systemvetenskap
-
- Li, Xiu, 1982- (author)
- Stockholms universitet,Institutionen för data- och systemvetenskap
-
show less...
-
(creator_code:org_t)
- Springer Nature, 2023
- 2023
- English.
-
Series: Lecture Notes in Networks and Systems, 2367-3370 2367-3389 ; 711
- Related links:
-
https://urn.kb.se/re...
-
show more...
-
https://doi.org/10.1...
-
show less...
Abstract
Subject headings
Close
- Practice and exam-style questions, as essential educational tools, contribute to educators’ effective teaching. Automatic question generation (QG) is a promising technique that can eliminate the manual effort of constructing questions and boost technology-enhanced education systems. Recently, deep neural network-based question-generation approaches have significantly improved upon state-of-the-art of question generation. Nevertheless, these approaches are often developed based on huge and non-educational datasets consisting of over 100,000 examples, which negatively affect the scalability and reliability of the educational QG systems. This study proposes a prompt-based learning QG approach that could generate questions in a data-effective way. The proposed prompt-based learning QG approach is trained and evaluated on a general dataset SQuAD, and an educational dataset SciQ. Experiment results demonstrate that our approach outperforms existing best QG models by a vast margin in data-effective scenarios and could generate high-quality educational questions with as few as 1,000 training examples.
Subject headings
- NATURVETENSKAP -- Data- och informationsvetenskap -- Systemvetenskap, informationssystem och informatik (hsv//swe)
- NATURAL SCIENCES -- Computer and Information Sciences -- Information Systems (hsv//eng)
Keyword
- Question Generation
- Natual Language Processing
- Artificial Intelligence
- Prompt-based Learning
- data- och systemvetenskap
- Computer and Systems Sciences
Publication and Content Type
- ref (subject category)
- kon (subject category)
To the university's database
- By the author/editor
-
Wu, Yongchao, 19 ...
-
Nouri, Jalal, 19 ...
-
Megyesi, Beata
-
Henriksson, Aron ...
-
Duneld, Martin, ...
-
Li, Xiu, 1982-
- About the subject
-
- NATURAL SCIENCES
-
NATURAL SCIENCES
-
and Computer and Inf ...
-
and Information Syst ...
- Parts in the series
-
Lecture Notes in ...
- By the university
-
Stockholm University