Background: Most lip-reading studies primarily utilize image-based representations of lip movements,
Grounding vision--language models in low-resource languages remains challenging, as they often produ
The Politically Aggressive Bengali Dataset (PABD) is a manually annotated dataset developed to facil
The paper is about the impact of prosodic features, more especially tone marking, in extracting the
Mathematical word problems (MWPs) involve the task of converting textual descriptions into mathemati
This dataset comprises 3,290 Bengali political comments sourced from social media platforms, news co