Studies on bengali text classification using machine learning and deep learning

Abstract

This study focuses on Bengali text classification using machine learning and deep learning techniques. The research explores the efficacy of multilingual pre-trained models for Bengali text classification tasks and proposes algorithms to address challenges related to base classifier selection and input length constraints in existing models. The findings contribute to the advancement of Bengali text classification techniques by identifying effective pre-trained models, optimizing ensemble model selection, and bypassing the input length constraint of BERT models. The outcomes of this research have practical implications for improving the accuracy and efficiency of Bengali text classification in various applications