| Peer-Reviewed

PolyAQG: An Automated Question Generation Framework Based on a Combination of Four Analytical Approaches

Received: 26 July 2022     Accepted: 11 August 2022     Published: 17 August 2022
Views:       Downloads:
Abstract

Automated Question Generation (AQG) that automatically generates questions from text effectively reduces the time and effort of educators in preparing and setting assessments questions. Since the 1970s, AQG researchers have proposed and applied a vast range of approaches to generate questions. With that, the PolyAQG Framework is proposed in this paper by combining four analytical AQG approaches into a framework to increase the number, the variety, and the quality of questions. The novelties offered by this PolyAQG Framework are highlighted in this paper. A prototype is developed under JavaFX platform and integrated with the Stanford NLP parser. From the 300 test sentences, the framework has successfully generated ten-times more questions with more than 85% of the generated questions were rated accurate and relevant. This test result revealed that the framework did successfully meet the three research objectives formulated for this study, as follows: First, a framework is developed by combining four analytical AQG techniques. Second, two phases are used to generate new sentences from the input and earlier phases are re-used to develop a new set of questions. Lastly, the generation of ontology-based questions phase does not merely generate distractors (typical in other ontology-based AQGs), but instead generates new sentences with ontology knowledge and uses them to create a new set of questions.

Published in Mathematics and Computer Science (Volume 7, Issue 4)
DOI 10.11648/j.mcs.20220704.12
Page(s) 68-74
Creative Commons

This is an Open Access article, distributed under the terms of the Creative Commons Attribution 4.0 International License (http://creativecommons.org/licenses/by/4.0/), which permits unrestricted use, distribution and reproduction in any medium or format, provided the original work is properly cited.

Copyright

Copyright © The Author(s), 2022. Published by Science Publishing Group

Keywords

Automated Question Generation, Syntax-Based, Semantic-Based, Ontology-Based

References
[1] J. H. Wolfe, “An Aid to Independent Study through Automatic Generation (Autoquest),” SIGCSE ’76 Proc. ACM SIGCSE-SIGCUE Tech. Symp. Comput. Sci. Educ., p. Pages 104–112, 1975, [Online]. Available: https://doi.org/10.1145/800107.803459.
[2] T. H. Tan, P. L. Teh, and Y. Zaharin, “PolyAQG Framework: Auto-generating assessment questions,” in 2021 IEEE Computing Conference (ICOCO 2021), 2021, p. 5.
[3] E. Sneiders, “Automated question answering using question templates that cover the conceptual model of the database,” Lect. Notes Comput. Sci. (including Subsea. Lect. Notes Artif. Intell. Lect. Notes Bioinformatics), vol. 2553, pp. 235–239, 2002, DOI: 10.1007/3-540-36271-1_24.
[4] G. Kurdi, J. Leo, B. Parsia, U. Sattler, and S. Al-Emari, “A Systematic Review of Automatic Question Generation for Educational Purposes,” Int. J. Artif. Intell. Educ., vol. 30, no. 1, pp. 121–204, 2020, DOI: 10.1007/s40593-019-00186-y.
[5] X. Yao, G. Bouma, and Y. Zhang, “Semantics-based Question Generation and Implementation,” Dialogue & Discourse, vol. 3, no. 2, pp. 11–42, 2012, DOI: 10.5087/dad.2012.202.
[6] L. Becker, S. Basu, and L. Vanderwende, “Mind the gap: Learning to choose gaps for question generation,” NAACL HLT 2012 - 2012 Conf. North Am. Chapter Assoc. Comput. Linguist. Hum. Lang. Technol. Proc. Conf., no. June 2012, pp. 742–751, 2012.
[7] Y. Huang and L. He, "Automatic generation of short answer questions for reading comprehension assessment," Nat. Lang. Eng., vol. 22, no. 03, pp. 457–489, 2016, DOI: 10.1017/s1351324915000455.
[8] R. M. Kaplan and J. Bresnan, “Lexical-Functional Grammar: A Formal System for Grammatical Representation,” in The Mental Representation of Grammatical Relations, J. Bresnan, Ed. MIT Press.
[9] A. Papasalouros, K. Kanaris, and K. Kotis, “Automatic Generation Of Multiple Choice Questions from Domain Ontologies,” IADIS Int. Conf. e-Learning 2008, Amsterdam, Netherlands, 2008.
[10] M. Tosic and M. Cubric, “SeMCQ – Protégé Plugin for Automatic Ontology-Driven Multiple Choice Question Tests Generation,” Proc. 11th Int. Protege Conf., pp. 6–7, 2009, [Online]. Available: http://hdl.handle.net/2299/6710.
[11] E. Holohan, M. Melia, D. Mcmullen, and C. Pahl, “Adaptive E-Learning Content Generation based on Semantic Web Technology,” Int. Work. Appl. Semant. Web Technol. E-Learning (SW-EL 2005) 12th Int. Conf. Artif. Intell. Educ. AIED 2005, pp. 1–8, 2005.
[12] M. Al-Yahya, “OntoQue: A question generation engine for educational assessment based on domain ontologies,” Proc. 2011 11th IEEE Int. Conf. Adv. Learn. Technol. ICALT 2011, pp. 393–395, 2011, DOI: 10.1109/ICALT.2011.124.
[13] A. E. Awad and M. Y. Dahab, "Automatic Generation of Question Bank Based on Predefined Templates," Dahab Int. J. Innov. Adv. Comput. Sci. IJIACS ISSN, vol. 3, no. 1, pp. 2347–8616, 2014.
[14] A. Fabbri, P. Ng, Z. Wang, R. Nallapati, and B. Xiang, “Template-Based Question Generation from Retrieved Sentences for Improved Unsupervised Question Answering,” pp. 4508–4513, 2020, DOI: 10.18653/v1/2020.acl-main.413.
[15] H. Hussein, M. Elmogy, and S. Guirguis, "Automatic English question generation system based on template-driven scheme," Int. J. Comput. Sci. Issues, vol. 11, no. 6, p. 45, 2014.
[16] V. E., T. Alsubait, and P. S. Kumar, “Modeling of Item-Difficulty for Ontology-based MCQs,” 2016, [Online]. Available: http://arxiv.org/abs/1607.00869.
[17] K. Stasaski and M. A. Hearst, “Multiple Choice Question Generation Utilizing An Ontology,” no. 2011, pp. 303–312, 2018, DOI: 10.18653/v1/w17-5034.
[18] S. Ou, C. Orasan, D. Mekhaldi, and L. Hasler, “Automatic question pattern generation for ontology-based question answering,” Proc. 21th Int. Florida Artif. Intell. Res. Soc. Conf. FLAIRS-21, pp. 183–188, 2008.
Cite This Article
  • APA Style

    Tee Hean Tan, Zaharin Yusoff. (2022). PolyAQG: An Automated Question Generation Framework Based on a Combination of Four Analytical Approaches. Mathematics and Computer Science, 7(4), 68-74. https://doi.org/10.11648/j.mcs.20220704.12

    Copy | Download

    ACS Style

    Tee Hean Tan; Zaharin Yusoff. PolyAQG: An Automated Question Generation Framework Based on a Combination of Four Analytical Approaches. Math. Comput. Sci. 2022, 7(4), 68-74. doi: 10.11648/j.mcs.20220704.12

    Copy | Download

    AMA Style

    Tee Hean Tan, Zaharin Yusoff. PolyAQG: An Automated Question Generation Framework Based on a Combination of Four Analytical Approaches. Math Comput Sci. 2022;7(4):68-74. doi: 10.11648/j.mcs.20220704.12

    Copy | Download

  • @article{10.11648/j.mcs.20220704.12,
      author = {Tee Hean Tan and Zaharin Yusoff},
      title = {PolyAQG: An Automated Question Generation Framework Based on a Combination of Four Analytical Approaches},
      journal = {Mathematics and Computer Science},
      volume = {7},
      number = {4},
      pages = {68-74},
      doi = {10.11648/j.mcs.20220704.12},
      url = {https://doi.org/10.11648/j.mcs.20220704.12},
      eprint = {https://article.sciencepublishinggroup.com/pdf/10.11648.j.mcs.20220704.12},
      abstract = {Automated Question Generation (AQG) that automatically generates questions from text effectively reduces the time and effort of educators in preparing and setting assessments questions. Since the 1970s, AQG researchers have proposed and applied a vast range of approaches to generate questions. With that, the PolyAQG Framework is proposed in this paper by combining four analytical AQG approaches into a framework to increase the number, the variety, and the quality of questions. The novelties offered by this PolyAQG Framework are highlighted in this paper. A prototype is developed under JavaFX platform and integrated with the Stanford NLP parser. From the 300 test sentences, the framework has successfully generated ten-times more questions with more than 85% of the generated questions were rated accurate and relevant. This test result revealed that the framework did successfully meet the three research objectives formulated for this study, as follows: First, a framework is developed by combining four analytical AQG techniques. Second, two phases are used to generate new sentences from the input and earlier phases are re-used to develop a new set of questions. Lastly, the generation of ontology-based questions phase does not merely generate distractors (typical in other ontology-based AQGs), but instead generates new sentences with ontology knowledge and uses them to create a new set of questions.},
     year = {2022}
    }
    

    Copy | Download

  • TY  - JOUR
    T1  - PolyAQG: An Automated Question Generation Framework Based on a Combination of Four Analytical Approaches
    AU  - Tee Hean Tan
    AU  - Zaharin Yusoff
    Y1  - 2022/08/17
    PY  - 2022
    N1  - https://doi.org/10.11648/j.mcs.20220704.12
    DO  - 10.11648/j.mcs.20220704.12
    T2  - Mathematics and Computer Science
    JF  - Mathematics and Computer Science
    JO  - Mathematics and Computer Science
    SP  - 68
    EP  - 74
    PB  - Science Publishing Group
    SN  - 2575-6028
    UR  - https://doi.org/10.11648/j.mcs.20220704.12
    AB  - Automated Question Generation (AQG) that automatically generates questions from text effectively reduces the time and effort of educators in preparing and setting assessments questions. Since the 1970s, AQG researchers have proposed and applied a vast range of approaches to generate questions. With that, the PolyAQG Framework is proposed in this paper by combining four analytical AQG approaches into a framework to increase the number, the variety, and the quality of questions. The novelties offered by this PolyAQG Framework are highlighted in this paper. A prototype is developed under JavaFX platform and integrated with the Stanford NLP parser. From the 300 test sentences, the framework has successfully generated ten-times more questions with more than 85% of the generated questions were rated accurate and relevant. This test result revealed that the framework did successfully meet the three research objectives formulated for this study, as follows: First, a framework is developed by combining four analytical AQG techniques. Second, two phases are used to generate new sentences from the input and earlier phases are re-used to develop a new set of questions. Lastly, the generation of ontology-based questions phase does not merely generate distractors (typical in other ontology-based AQGs), but instead generates new sentences with ontology knowledge and uses them to create a new set of questions.
    VL  - 7
    IS  - 4
    ER  - 

    Copy | Download

Author Information
  • Centre for American Education, Sunway University, Sunway City, Malaysia

  • Institute for Research, Development and Innovation, International Medical University, Kuala Lumpur, Malaysia

  • Sections