Revisão sobre a geração automática de questões na educação: técnicas, conjuntos de dados e métricas de avaliação
DOI :
https://doi.org/10.51359/2317-0115.2025.265432Mots-clés :
geração automática de questões, processamento de linguagem natural, aprendizado de máquinaRésumé
A geração automática de questões (AQG) é uma área interdisciplinar que combina processamento de linguagem natural, aprendizado de máquina para criar sistemas que geram perguntas. Este artigo é uma revisão sistemática relacionada a AQG aplicada à educação. A abordagem mais utilizada neste domínio, segundo resultados da revisão, é a técnicas “baseada em regras”, seguida por aprendizado de máquina. Os conjuntos de dados mais comuns incluem o SQuAD, enquanto as métricas de avaliação variam entre BLEU, acurácia e precisão. A revisão também destaca as limitações das abordagens e aponta oportunidades de pesquisa, como a necessidade de conjuntos de dados abertos e melhorias nas técnicas de avaliação automática. Esperamos que isto auxilie pesquisadores na exploração de novas oportunidades e avanços na área de AQG.
Références
BACHIRI, Younes-aziz; MOUNCIF, Hicham. Applicable strategy to choose and deploy a MOOC platform with multilingual AQG feature. In: 2020 21st International Arab conference on information technology (ACIT). IEEE, 2020. p. 1-6.
BIRD, Steven; KLEIN, Ewan; LOPER, Edward.Natural language processing with Python: analyzing text with the natural language toolkit. " O'Reilly Media, Inc.", 2009.
CAO, Zhen; TATINATI, Sivanagaraja; KHONG, Andy WH. Controllable question generation via sequence-to-sequence neural model with auxiliary information. In: 2020 International Joint Conference on Neural Networks (IJCNN). IEEE, 2020. p. 1-7.
DAS, Bidyut et al. Automatic question generation and answer assessment for subjective examination. Cognitive systems research, v. 72, p. 14-22, 2022.
ELSAHAR, Hady; GRAVIER, Christophe; LAFOREST, Frederique. Zero-Shot Question Generation from Knowledge Graphs for Unseen Predicates and Entity Types. In: Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies. 2018. p. 218-228.
FAN, Zhihao et al. A Question Type Driven Framework to Diversify Visual Question Generation. In: IJCAI. 2018. p. 4048-4054.
FAN, Zhihao et al. A reinforcement learning framework for natural question generation using bi-discriminators. In: Proceedings of the 27th International Conference on Computational Linguistics. 2018. p. 1763-1774.
GANGOPADHYAY, Susmita; RAVIKIRAN, S. M. Focused questions and answer generation by key content selection. In: 2020 IEEE Sixth International Conference on Multimedia Big Data (BigMM). IEEE, 2020. p. 45-53.
GHIDINI, Chiara et al. The semantic web-ISWC 2019. Springer International Publishing, 2019.
INDURTHI, Sathish Reddy et al. Generating natural language question-answer pairs from a knowledge graph using a RNN based question generation model. In: Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics: Volume 1, Long Papers. 2017. p. 376-385.
JURAFSKY, D.; MARTIM J. 2024. Speech and Language Processing: An Introduction to Natural Language Processing, Computational Linguistics, and Speech Recognition with Language Models, 3rd edition. Online manuscript released August 20, 2024. https://web.stanford.edu/~jurafsky/slp3.
KITCHENHAM B Guidelines for performing Systematic Literature Reviews in Software Engineering, Version 2.3, EBSE Technical Report EBSE-2007-01 (2007), Keele University and University of Durham
KUMAR, Vishwajeet et al. Difficulty-controllable multi-hop question generation from knowledge graphs. In: The Semantic Web–ISWC 2019: 18th International Semantic Web Conference, Auckland, New Zealand, October 26–30, 2019, Proceedings, Part I 18. Springer International Publishing, 2019. p. 382-398.
LEITE, Bernardo et al. Factual question generation for the Portuguese language. In: 2020 International Conference on INnovations in Intelligent SysTems and Applications (INISTA). IEEE, 2020. p. 1-7.
MORÓN, Martín et al. A tool for automatic question generation for teaching english to beginner students. In: 2021 40th International Conference of the Chilean Computer Science Society (SCCC). IEEE, 2021. p. 1-5.
MOSTAFAZADEH, Nasrin et al. Generating natural questions about an image. arXiv preprint arXiv:1603.06059, 2016.
PAPINENI, Kishore et al. Bleu: a method for automatic evaluation of machine translation. In: Proceedings of the 40th annual meeting of the Association for Computational Linguistics. 2002. p. 311-318.
PIWEK, Paul et al. T2D: Generating dialogues between virtual agents automatically from text. In: Intelligent Virtual Agents: 7th International Conference, IVA 2007 Paris, France, September 17-19, 2007 Proceedings 7. Springer Berlin Heidelberg, 2007. p. 161-174.
RAJPURKAR, P. Squad: 100,000+ questions for machine comprehension of text. arXiv preprint arXiv:1606.05250, 2016.
RAO, Pratiksha Rajesh et al. Generating QA from Rule-based Algorithms. In: 2022 International Conference on Electronics and Renewable Systems (ICEARS). IEEE, 2022. p. 1697-1703.
RUS, Vasile et al. The first question generation shared task evaluation challenge. In: Proceedings of the 6th International Natural Language Generation Conference. 2010. p. 251-257.
SERBAN, Iulian Vlad et al. Generating factoid questions with recurrent neural networks: The 30m factoid question-answer corpus. arXiv preprint arXiv:1603.06807, 2016.
SONG, Linfeng; ZHAO, Lin. Domain-specific question generation from a knowledge base. arX-iv., 2016.
SONIA, Sonam; KUMAR, Praveen; SAHA, Amal. Automatic question-answer generation from video lecture using neural machine translation. In: 2021 8th International Conference on Signal Processing and Integrated Networks (SPIN). IEEE, 2021. p. 661-665.
TSAI, Danny CL et al. Automatic question generation for repeated testing to improve student learning outcome. In: 2021 International Conference on Advanced Learning Technologies (ICALT). IEEE, 2021. p. 339-341.
ZHANG, Ruqing et al. A review on question generation from natural language text. ACM Transactions on Information Systems (TOIS), v. 40, n. 1, p. 1-43, 2021.
Téléchargements
Publiée
Numéro
Rubrique
Licence
© Alana Viana Borges da Silva Neo , Giseldo da Silva Neo, Mario Diego Ferreira dos Santos , Kleber Jose Araujo Galvao Filho , Olival de Gusmão Freitas Junior 2025
Ce travail est disponible sous licence Creative Commons Attribution - Pas d'Utilisation Commerciale - Pas de Modification 4.0 International.
Os trabalhos submetidos são de responsabilidade exclusiva de sua autoria, que preserva o seu direito autoral.
É permitida a citação dos trabalhos publicados sem prévia autorização desde que seja explícita a menção à fonte da RMP
