Enhancing document text classification using hybrid deep contextual and correlation network

Abstract

Document analysis involves the extraction and processing of information from documents, a task increasingly automated through the use of deep learning (DL) technologies. Despite the high predictive power of DL models, their black-box nature poses challenges to transparency and interpretability, hindering their integration into the industry. This paper introduces the hybrid deep contextual and correlation network (HDCCNet), a novel methodology designed to improve both the accuracy and interpretability of multi-category classification tasks. HDCCNet leverages a hybrid layer category correlation module to deepen category connections, thereby enhancing the understanding and prediction of category interrelations. To address potential prediction divergence, residual connections are incorporated, ensuring stable and reliable performance. Furthermore, HDCCNet reduces model parameters, accelerating convergence and making the model more efficient. This efficiency is particularly beneficial for practical applications, allowing faster deployment and scalability. By bridging the gap between DL’s capabilities and industry needs for transparency, HDCCNet provides a robust solution for automated document processing, paving the way for broader adoption of DL technologies in business environments.