Bengali Grapheme
Bengali grapheme research focuses on developing robust and accurate methods for processing and understanding the Bengali writing system, encompassing handwritten and printed text, as well as spoken digits and sign language. Current research employs a range of techniques, including convolutional neural networks (CNNs), transformer-based models, and YOLOv8 for tasks such as optical character recognition (OCR), document layout analysis, and sentiment analysis. These advancements are crucial for bridging the digital divide for Bengali speakers, enabling improved access to information and technology through applications like automated translation, fake news detection, and assistive technologies for the visually or hearing impaired.
Papers
Dhoroni: Exploring Bengali Climate Change and Environmental Views with a Multi-Perspective News Dataset and Natural Language Processing
Azmine Toushik Wasi, Wahid Faisal, Taj Ahmad, Abdur Rahman, Mst Rafia Islam
Exploring Possibilities of AI-Powered Legal Assistance in Bangladesh through Large Language Modeling
Azmine Toushik Wasi, Wahid Faisal, Mst Rafia Islam, Mahathir Mohammad Bappy