Bangla Text
Bangla text processing research focuses on developing and applying natural language processing (NLP) techniques to the Bengali language, a low-resource language with significant linguistic complexity. Current research emphasizes building robust models for tasks like sentiment analysis, toxicity detection, and question answering, often leveraging transformer architectures such as BERT and its variants, along with other deep learning approaches. This work is crucial for bridging the digital divide, enabling the development of Bangla-specific applications in various domains, from social media monitoring to healthcare and education, and advancing the broader field of NLP for low-resource languages.
Papers
BanglaQuAD: A Bengali Open-domain Question Answering Dataset
Md Rashad Al Hasan Rony, Sudipto Kumar Shaha, Rakib Al Hasan, Sumon Kanti Dey, Amzad Hossain Rafi, Amzad Hossain Rafi, Ashraf Hasan Sirajee, Jens Lehmann
ChakmaNMT: A Low-resource Machine Translation On Chakma Language
Aunabil Chakma, Aditya Chakma, Soham Khisa, Chumui Tripura, Masum Hasan, Rifat Shahriyar