Hierarchical Attentional Hybrid Neural Networks for Document Classification
This work addresses document classification, a challenging task with important applications, by incrementally enhancing model efficiency through better incorporation of document structure and context.
The authors tackled document classification by proposing a hierarchical attentional hybrid neural network combining CNNs, GRUs, and attention mechanisms, which improved results over current attention-based approaches.
Document classification is a challenging task with important applications. The deep learning approaches to the problem have gained much attention recently. Despite the progress, the proposed models do not incorporate the knowledge of the document structure in the architecture efficiently and not take into account the contexting importance of words and sentences. In this paper, we propose a new approach based on a combination of convolutional neural networks, gated recurrent units, and attention mechanisms for document classification tasks. The main contribution of this work is the use of convolution layers to extract more meaningful, generalizable and abstract features by the hierarchical representation. The proposed method in this paper improves the results of the current attention-based approaches for document classification.