Method of Automatic Generation of Questions and Answers for Knowledge Testing Systems
https://doi.org/10.35596/1729-7648-2025-23-3-54-61
Abstract
The technique of automatic generation of questions and answers for knowledge testing is considered. The proposed approach is based on the developed method of defining and using clusters of keywords to generate questions and answers based on a global or local language model, which constitutes theoretical and applied novelty. Clusters are built on the basis of a corpus of text documents related to the studied area (textbooks, methodological manuals, electronic resources). The technical solution presented in the article is logically complete and can serve as a basis for practical developments.
About the Authors
S. А. Migalevich
Belarusian State University of Informatics and Radioelectronics
Belarus
Head of the Center of Informatization and Innovations, Applicant at the Department of Software Provision of Information Technologies
Belarus
Head of the Center of Informatization and Innovations, Applicant at the Department of Software Provision of Information Technologies
Ju. O. German
Belarusian State University of Informatics and Radioelectronics
Belarus
German Ju. O., Сand. Sci. (Tech.), Associate Professor at the Information Technologies in Automatized System Department
Belarus
German Ju. O., Сand. Sci. (Tech.), Associate Professor at the Information Technologies in Automatized System Department
O. V. German
Belarusian State University of Informatics and Radioelectronics
Belarus
German O. V., Сand. Sci. (Tech.), Associate Professor at the Information Technologies in Automatized System Department
Belarus
German O. V., Сand. Sci. (Tech.), Associate Professor at the Information Technologies in Automatized System Department
References
1. Ruqing Ch., Jiafeng G., Lu Ch., Xueqi Cheng., Yixing Fan. (2021) A Review on Question Generation from Natural Language Text. ACM Trans. on Information Systems. 40 (1).
2. Brusilowsky P., Miller P. (1999) Web-Based Testing for Distance Education. WebNet’99, World Conference of the WWW and Internet, AACE, Honolulu. 149–154.
3. German O. V. (1995) Introduction to Expert Systems Theory and Knowledge Processing. Minsk, DesignPro Publ. (in Russian).
4. Bird S., Klein E., Loper E. (2007) Natural Language Processing with Python. O’Reilly Media Inc. USA.
5. Montgomery D. C. (2013) Design and Analysis of Experiments. John Wiley&Soms Inc. USA.
6. Neter J., Wasserman W., Kutner M. H. (1983) Applied Linear Regression Models. R.D. Irwin Inc. USA.
7. Blei D. M., Ng A. Y., Jordan M. I. (2003) Latent Dirichlet Allocation. Journal of Machine Learning Research. (3), 9931022.
8. Han J., Kamber M., Pei J. (2012) Data Mining. Concepts and Techniques. Elsevier.
9. German O. V., Germanovich E. I., Naidenko V. G. (1992) Boolean Optimization Algorithm on (0,1)-Matrices. Journal of Computational Mathematics and Mathematical Physics. 32 (7), 1114–1125 (in Russian).
10. German O. V. (1996) Decision Principle for the Minimum Covering Problem of a 0,1-Matrix. Cybernetics and Systems Analysis. (1), 135145 (in Russian).
11. German Yu. O., German O. V., Nasr S. (2019) Information Extraction Method from a Resume (CV). Works BSTU. Series 3. Physics and Mathematics Science and Computer Science. (1), 6468.
Review
For citations:
Migalevich S.А., German J.O., German O.V. Method of Automatic Generation of Questions and Answers for Knowledge Testing Systems. Doklady BGUIR. 2025;23(3):54-61. (In Russ.) https://doi.org/10.35596/1729-7648-2025-23-3-54-61
Views:
19
Email this article 