A Novel Model Combining Transformer and Bi-LSTM for News Categorization

• Published in: IEEE transactions on computational social systems 2024-08, Vol.11 (4), p.4862-4869
• Main Authors: Liu, Yuanzhi, He, Min, Shi, Mengjia, Jeon, Seunggil
• Format: Article
• Language: English
• Subjects: Artificial neural networks; Attention mechanism; bidirectional long short-term memory (Bi-LSTM); Classification; Convolutional neural networks; Encoding; Feature extraction; Long short term memory; Machine learning; Natural language processing; natural language processing (NLP); Neural networks; news categorization (NC); Recurrent neural networks; Semantics; transformer; Transformers
• ISSN: 2329-924X; 2373-7476
• DOI: 10.1109/TCSS.2022.3223621

News categorization (NC), the aim of which is to identify distinct categories of news through analyzing the contents, has acquired substantial progress since deep learning was introduced into the natural language processing (NLP) field. As a state-of-art model, transformer's classification performance is not satisfied compared with recurrent neural network (RNN) and convolutional neural network (CNN) if it does not get pretrained. Based on the transformer model, this article proposes a novel framework that combines bidirectional long short-term memory (Bi-LSTM) network and transformer to solve this problem. In the suggested framework, the self-attention mechanism is substituted with Bi-LSTM to capture the semantic information from sentences. Meanwhile, an attention mechanism model is applied to focus on those important words and adjust their weights to solve the problem of long-distance information loss. With pooling network, the network complexity can be reduced and the main features can be highlighted by halving the dimension of the hidden state. Finally, after acquiring the hidden representation by the above structures, we utilize a contraction network to further capture the long-range associations from a text. Experiments on three large-scale corpora were performed to evaluate the suggested framework, and the results demonstrate that our model outperforms other models such as deep pyramid CNN (DPCNN), transformer.