A 90%-pruned few-shot Bengali model is reported to rival larger baselines on some tasks, but the reported F1 scores contradict the paper's own precision and recall values.
Research on Bangla language processing in Bangladesh: progress and challenges
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.LG 1years
2026 1verdicts
REJECT 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
BnBERT-iPET: Sparse Few-Shot Language Modeling for Bengali via Lottery Ticket Pruning
A 90%-pruned few-shot Bengali model is reported to rival larger baselines on some tasks, but the reported F1 scores contradict the paper's own precision and recall values.