cs.CLMay 26, 2026

DunbaaBERT: From Sacrifice to Semantics

Authors: Iffat MaabWaleed JamilRaphael Schmitt

Organizations: Research and Development Center for Large Language Models (LLMC), National Institute of Informatics, Tokyo · Independent Researcher, Edinburgh, United Kingdom · School of Computation, Information and Technology, Technical University of Munich, Germany · Institute of General Practice, Faculty of Medicine and Medical Center, University of Freiburg, Germany

Abstract

Large language models have achieved strong performance across many NLP tasks, yet Urdu remains comparatively underexplored due to limited resources and fragmented evaluation settings. To address this gap, we introduce DunbaaBERT, a family of Urdu RoBERTa-base models trained from scratch with Byte-BPE vocabularies of 32k, 52k, and 96k tokens on a deduplicated 17GB Urdu corpus. We evaluate DunbaaBERT across intrinsic and downstream Urdu NLP benchmarks covering linguistic acceptability, news classification, offensive language detection, and sentiment analysis while analyzing vocabulary-size effects on performance and efficiency trade-offs. Across benchmarks, the DunbaaBERT variants achieve competitive performance against strong multilingual baselines while consistently maintaining favorable efficiency trade-offs. Interestingly, larger vocabularies do not consistently improve downstream effectiveness, with DunbaaBERT32k_{\text{32k}} repeatedly providing the strongest overall efficiency profile. Overall, our results demonstrate that carefully curated Urdu-specific encoder models can remain highly competitive despite comparatively compact model and training scales. All models are released under the MIT license.

Explore similar work

CardsList