NCTB-QA: A Large-Scale Bangla Educational Question Answering Dataset and Benchmarking Performance

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Eyasir, Abrar, Ahmed, Tahsin, Ibrahim, Muhammad
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911489423572992
author Eyasir, Abrar
Ahmed, Tahsin
Ibrahim, Muhammad
author_facet Eyasir, Abrar
Ahmed, Tahsin
Ibrahim, Muhammad
contents Reading comprehension systems for low-resource languages face significant challenges in handling unanswerable questions. These systems tend to produce unreliable responses when correct answers are absent from context. To solve this problem, we introduce NCTB-QA, a large-scale Bangla question answering dataset comprising 87,805 question-answer pairs extracted from 50 textbooks published by Bangladesh's National Curriculum and Textbook Board. Unlike existing Bangla datasets, NCTB-QA maintains a balanced distribution of answerable (57.25%) and unanswerable (42.75%) questions. NCTB-QA also includes adversarially designed instances containing plausible distractors. We benchmark three transformer-based models (BERT, RoBERTa, ELECTRA) and demonstrate substantial improvements through fine-tuning. BERT achieves 313% relative improvement in F1 score (0.150 to 0.620). Semantic answer quality measured by BERTScore also increases significantly across all models. Our results establish NCTB-QA as a challenging benchmark for Bangla educational question answering. This study demonstrates that domain-specific fine-tuning is critical for robust performance in low-resource settings.
format Preprint
id arxiv_https___arxiv_org_abs_2603_05462
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle NCTB-QA: A Large-Scale Bangla Educational Question Answering Dataset and Benchmarking Performance
Eyasir, Abrar
Ahmed, Tahsin
Ibrahim, Muhammad
Computation and Language
I.2.7; H.3.3
Reading comprehension systems for low-resource languages face significant challenges in handling unanswerable questions. These systems tend to produce unreliable responses when correct answers are absent from context. To solve this problem, we introduce NCTB-QA, a large-scale Bangla question answering dataset comprising 87,805 question-answer pairs extracted from 50 textbooks published by Bangladesh's National Curriculum and Textbook Board. Unlike existing Bangla datasets, NCTB-QA maintains a balanced distribution of answerable (57.25%) and unanswerable (42.75%) questions. NCTB-QA also includes adversarially designed instances containing plausible distractors. We benchmark three transformer-based models (BERT, RoBERTa, ELECTRA) and demonstrate substantial improvements through fine-tuning. BERT achieves 313% relative improvement in F1 score (0.150 to 0.620). Semantic answer quality measured by BERTScore also increases significantly across all models. Our results establish NCTB-QA as a challenging benchmark for Bangla educational question answering. This study demonstrates that domain-specific fine-tuning is critical for robust performance in low-resource settings.
title NCTB-QA: A Large-Scale Bangla Educational Question Answering Dataset and Benchmarking Performance
topic Computation and Language
I.2.7; H.3.3
url https://arxiv.org/abs/2603.05462