BanglaBERT
PulseAugur coverage of BanglaBERT — every cluster mentioning BanglaBERT across labs, papers, and developer communities, ranked by signal.
2 day(s) with sentiment data
-
New benchmark destroR tests and defends Bangla NLP models against attacks
Researchers have introduced destroR, a new pipeline designed to evaluate and enhance the adversarial robustness of Bangla language transfer models. The system includes three novel meaning-preserving attack methods: a pa…
-
Bangla hate speech detection fails on real-world social media data
A new study highlights a significant crisis in Bangla hate speech detection systems, revealing that models trained on benchmark datasets perform poorly when applied to real-world social media content. Architectures like…
-
New method adapts lightweight ASR models for Bengali language
Researchers have developed a novel method to adapt lightweight speech recognition models, like Moonshine, for morphologically rich languages such as Bengali. The core issue identified was an English-centric tokenizer th…
-
LLMs show greater robustness in noisy Bangla text event detection than encoder models
A new research paper evaluates the robustness of different AI model architectures for event detection in noisy Bangla text. The study found that while encoder-only models like BanglaBERT and XLM-R perform better on clea…
-
Lightweight Bangla Medical Entity Recognition Framework Developed
Researchers have developed a new, lightweight framework for Bangla medical entity recognition designed for resource-constrained environments. The system utilizes a hybrid Transformer-CRF architecture, starting with a 12…
-
Bengali AI models show identity biases despite similar data, study finds
A new paper investigates biases in sentiment analysis models for the Bengali language, a low-resource context. Researchers audited models like mBERT and BanglaBERT, fine-tuned on Bengali sentiment analysis datasets, and…