摘要
针对目前金融领域文本存在标注资源匮乏的问题,提出一种基于生成对抗网络的金融文本情感分类方法.该方法以边缘堆叠降噪自编码器生成鲁棒性特征表示作为输入,在生成对抗过程中,通过向文本表示向量添加噪声向量再生成新样本,应用对抗学习思想优化文本特征表示.在公开的跨领域情感评论Amazon数据集和金融领域数据集上进行实验,并与基准实验对比,结果表明,该方法在平均准确率上有显著提升.
There is a shortage of labeling resources in the texts of the financial field today.To address these issues,this paper presents a cross-domain text sentiment classification method based on generative adversarial network.The method uses the marginalized denosing autoencoders(mSDA)to generate a robust feature representation as input.In the process of generating adversarial,by adding to the text representation vector,the noise vector is regenerated to generate a new sample,and the anti-learning idea is applied to optimize the text feature representation.Experiments were conducted on public cross-domain sentiment reviews on Amazon datasets,which showed a significant improvement in average accuracy compared to benchmark experiments.
作者
沈翠芝
SHEN Cuizhi(Concord University College Fujian Normal University,Fuzhou,Fujian 350117,China)
出处
《福州大学学报（自然科学版）》
CAS
北大核心
2019年第6期740-745,共6页
Journal of Fuzhou University(Natural Science Edition)
基金
福建省发展和改革委员会G数字福建金融大数据平台基金资助项目(50015403)
关键词
情感分类
跨领域
生成对抗网络
金融文本分析
sentiment classification
cross-domain
generative adversarial networks
financial text analysis
