A Novel Attention Based CNN Model for Emotion Intensity Prediction

摘要：

　　Recently,classifying sentiment polarities or emotion categories of social media text has drawn extensive attentions from both academic and industrial communities.However,limited efforts have been paid for emotion intensity prediction problem.In this paper,we propose a novel attention mechanism for CNN model that associates attention based weights for every convolution window.Furthermore,a new activation function is incorporated into the fullconnected layer,which can alleviate the small gradient problem in functions saturated region.Experiment results on benchmark dataset show that our proposed model outperforms several strong baselines and achieves comparable performance with the state-of-the-art models.Unlike the reported models that used different neural network architectures for different emotion categories,our proposed model utilizes a unified architecture for intensity prediction.

关键词： Emotion intensity prediction CNN Attention mechanism

作者: Hongliang Xie Shi Feng Daling Wang Yifei Zhang

作者单位: School of Computer Science and Engineering,Northeastern University,Shenyang,China

会议类型: 国际会议

会议名称: 2018自然语言处理与中文计算国际会议(NLPCC2018)

会议地点: 呼和浩特

会议语种:英文

页码: 365-377

在线出版日期: 2018-08-26（万方平台首次上网日期，不代表论文的发表时间）