BNLI: A Linguistically-Refined Bengali Dataset for Natural Language Inference

Farah Binta Haque, Md Yasin, Shishir Saha, Md Shoaib Akhter Rafi, Farig Sadeque


Abstract
Despite the growing progress in Natural Language Inference (NLI) research, resources for the Bengali language remain extremely limited. Existing Bengali NLI datasets exhibit several inconsistencies, including annotation errors, ambiguous sentence pairs, and inadequate linguistic diversity, which hinder effective model training and evaluation. To address these limitations, we introduce BNLI, a refined and linguistically curated Bengali NLI dataset designed to support robust language understanding and inference modeling. The dataset was constructed through a rigorous annotation pipeline emphasizing semantic clarity and balance across entailment, contradiction, and neutrality classes. We benchmarked BNLI using a suite of state-of-the-art transformer-based architectures, including multilingual and Bengali-specific models, to assess their ability to capture complex semantic relations in Bengali text. The experimental findings highlight the improved reliability and interpretability achieved with BNLI, establishing it as a strong foundation for advancing research in Bengali and other low-resource language inference tasks. The link to the BNLI dataset: https://github.com/FarahHaque/BNLI-Dataset.git
Anthology ID:
2026.chipsal-1.9
Volume:
Proceedings of the Second workshop on Challenges in Processing South Asian Languages (CHiPSAL2026)
Month:
May
Year:
2026
Address:
Palma de Mallorca, Spain
Editors:
Kengatharaiyer Sarveswaran, Ashwini Vaidya
Venues:
CHiPSAL | WS
SIG:
Publisher:
ELRA Language Resources Association (ELRA)
Note:
Pages:
85–91
Language:
External URL:
https://lrec.elra.info/lrec2026-ws-chipsal-09
DOI:
10.63317/2cwaxs8a7csg
Bibkey:
Cite (ACL):
Farah Binta Haque, Md Yasin, Shishir Saha, Md Shoaib Akhter Rafi, and Farig Sadeque. 2026. BNLI: A Linguistically-Refined Bengali Dataset for Natural Language Inference. In Proceedings of the Second workshop on Challenges in Processing South Asian Languages (CHiPSAL2026), pages 85–91, Palma de Mallorca, Spain. ELRA Language Resources Association (ELRA).
Cite (Informal):
BNLI: A Linguistically-Refined Bengali Dataset for Natural Language Inference (Haque et al., CHiPSAL 2026)
Copy Citation: