Year: 2024
Type: conference-paper
Abstract: Text categorization is a crucial task in natural language processing. In recent years, deep learn- ing methodologies, particularly Recurrent Neural Networks (RNN) and Convolutional Neural Net- works (CNN), have made significant advancements in text classification tasks. This paper presents a hybrid model that combines Long Short-Term Memory Network (LSTM) with Convolutional Neural Network (CNN) for improved text classification. The proposed model leverages LSTM to extract long-term dependencies from text sequences, while CNN captures local features. Exper- iments conducted on various publicly accessible datasets demonstrate that this model surpasses other baseline models in performance, affirming its efficacy.
Author: Hongmin Zhang
Institution: Sichuan Agricultural University
Language: English
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: bronze
OpenAlex ID: W4406668300