Joint Dilated Convolution and Self-attention for Cross-domain Sentiment Analysis. Issue 1 (1st February 2022)

• Record Type: Journal Article
• Authors: Gu, Tong; Xu, Guoliang; Liu, Xuemei; Luo, Jiangtao
• Is Part Of: Journal of physics. Volume 2188:Issue 1(2022)
• Publication Date: 2022-02-01
• Subjects: Physics -- Congresses; 530.5
• DOI: 10.1088/1742-6596/2188/1/012012
• Languages: English
• ISSNs: 1742-6588

Abstract

Abstract: Cross-domain sentiment analysis aims to use source domain resources or models to serve the sentiment analysis tasks in the target domain, and it can effectively alleviate the problem of insufficient tagged data in the target domain. In this paper, we investigate deep transfer learning for text sentiment analysis, and focus on customer reviews for different domains. Given the shortcomings of the conventional deep neural network, such as convolutional neural network (CNN) cannot obtain the long-term dependence between features, recurrent neural network (RNN) cannot achieve parallel computing, we propose a novel neural network which joint dilated convolution and self-attention (ADC). The ADC takes residual learning as its basic framework, which can capture more distant information by introducing a dilation rate in the convolution. Self-attention is used to make the ADC pay more attention to important sentiment information. First, the ADC is pre-trained with the data of the source domain, and the weight of the pre-training is frozen. Then, the model is fine-tuned by the method of gradual unfreezing, and the weight is updated through the data of the target domain. Finally, the updated model can be utilized for the target domain sentiment analysis. By using customer review datasets, we carry out extensive experiments to demonstrate that this method has superior performance and can better achieve cross-domain sentiment analysis.