Tasks/Natural Language Inference
Natural Language Inference
ভাষাগত অনুমানDeciding whether one Bangla sentence entails, contradicts or is neutral towards another.
1 dataset·3 papers
| Source paper | Link | ||||
|---|---|---|---|---|---|
XNLI Bengali Bengali NLI from the XNLI subset of MNLI, machine translated from English. Train 381,449, validation 2,419, and test 4,895 pairs. | 388,763 sentence pairs | CC BY-NC-SA 4.0; noncommercial research only (author card) | 2021 | Author's Hugging Face release history (2021) | ✓ verified 2026-10-23 |
No leaderboard curated yet — contribute via PR.
2026BNLI: A Linguistically-Refined Bengali Dataset for Natural Language InferenceHaque et al.CHiPSAL2024Unraveling the Dominance of Large Language Models Over Transformer Models for Bangla Natural Language Inference: A Comprehensive StudyFaria et al.arXiv2014Exploring the Partial Textual Entailment Problem for Bengali News TextsDas et al.Research in Computing Science
No models catalogued for this task yet — add one via PR.