IJSMT Journal

International Journal of Science, Strategic Management and Technology

An International, Peer-Reviewed, Open Access Scholarly Journal Indexed in recognized academic databases · DOI via Crossref The journal adheres to established scholarly publishing, peer-review, and research ethics guidelines set by the UGC

Submit Research Paper
ISSN: 3108-1762 (Online)
webp (1)

By /
Plagiarism Passed
Peer reviewed
Open Access

MULTILINGUAL MCQ GENERATION USING TRANSFORMER ENSEMBLES

AUTHORS:
Palanikumar
B. Revathi
Abishek P
Mentor
Affiliation
Department of Artificial Intelligence and Data ScienceRamco Institute of Technology, Rajapalayam, India-626117
DOI: 10.55041/ijsmt.v2i3.134
CC BY 4.0 License:
This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
DOWNLOAD ARTICLE REVIEW REPORT CITE THIS ARTICLE
Abstract

The Multilingual MCQ Generation System Using Transformers is an automated platform generating high-quality multiple-choice questions (MCQs) from input text in Tamil, English, and Hindi. The system integrates T5, mT5, and fine-tuned multilingual BERT within a hybrid ensemble pipeline spanning five stages: language detection, transformer encoding, question generation, distractor synthesis, and domain-aware reranking across eight domains. The proposed hybrid ensemble achieves 93.4% accuracy, 91.6% F1-score, and BLEU of 0.748, significantly outperforming all individual baselines and enabling scalable language-inclusive AI-driven educational evaluation

Keywords
Article Information
PUBLICATION DETAILS
Review Type:
Double-Blind Peer Review
License:
CC BY-NC 4.0
Volume/Issue:
Volume 02, Issue 03
Review Rounds:
2
Article Type:
Research Article
Publication Date:
Mar 19 2026
Article Metrics
Article Views
74
PDF Downloads
2
HOW TO CITE
APA

MLA

Chicago

Copy

Palanikumar, , Revathi, B. & P, A. (2026). Multilingual MCQ Generation using Transformer Ensembles. International Journal of Science, Strategic Management and Technology, 02(03). https://doi.org/10.55041/ijsmt.v2i3.134

Palanikumar, , et al.. "Multilingual MCQ Generation using Transformer Ensembles." International Journal of Science, Strategic Management and Technology, vol. 02, no. 03, 2026, pp. . doi:https://doi.org/10.55041/ijsmt.v2i3.134.

Palanikumar, ,B. Revathi, and Abishek P. "Multilingual MCQ Generation using Transformer Ensembles." International Journal of Science, Strategic Management and Technology 02, no. 03 (2026). https://doi.org/https://doi.org/10.55041/ijsmt.v2i3.134.

References
[1]X. Du, J. Shao, and C. Cardie, "Learning to Ask: Neural QG for Reading Comprehension," in Proc. ACL, 2017, pp. 1342–1352.

[2] P. Rajpurkar et al., "SQuAD: 100,000+ Questions for Machine Comprehension," in Proc. EMNLP, 2016, pp. 2383–2392.

[3] C. Raffel et al., "Exploring the Limits of Transfer Learning with T5," J. Mach. Learn. Res., vol. 21, 2020.

[4] L. Xue et al., "mT5: A Massively Multilingual Pre-trained Text-to-Text Transformer," in Proc. NAACL, 2021, pp. 483–498.

[5] J. Devlin et al., "BERT: Pre-training of Deep Bidirectional Transformers," in Proc. NAACL, 2019, pp. 4171–4186.

[6] A. Radford et al., "Language Models are Unsupervised Multitask Learners," OpenAI Tech. Rep., 2019.

[7] S. Lewis et al., "BART: Denoising Sequence-to-Sequence Pre-training," in Proc. ACL, 2020, pp. 7871–7880.

[8] K. Papineni et al., "BLEU: A Method for Automatic Evaluation of MT," in Proc. ACL, 2002, pp. 311–318.

[9] C. Lin, "ROUGE: A Package for Automatic Evaluation of Summaries," in ACL Workshop, 2004.

[10] S. Subramanian et al., "Neural Networks for Question Generation," in Proc. ICLR Workshop, 2018.
Ethics and Compliance
✓ All ethical standards met
This article has undergone plagiarism screening and double-blind peer review. Editorial policies have been followed. Authors retain copyright under CC BY-NC 4.0 license. The research complies with ethical standards and institutional guidelines.
Indexed In
Similar Articles
Intelligent Credit Card Fraud Detection System using Machine Learning Techniques
string(18) "Lakshana Shree U.M" U.M, L. S.
(2026)
DOI: 10.55041/ijsmt.v2i3.216
The Philosophy of Technology: Human Agency in the Age of Artificial Intelligence
string(13) "Meera V. Nair" Nair, M. V.
(2026)
DOI: 10.55041/ijsmt.v2i2.001
Ethnobotanical Studies of Medicinal Plants used by Tribal Communities in Uttar Baster, Chhattisgarh, India
string(14) "Dipanyita Bala" Bala, D.
(2026)
DOI: 10.55041/ijsmt.v2i3.012
Back to Volume 02, Issue 03
Scroll to Top