计算机应用 ›› 2020, Vol. 40 ›› Issue (9): 2536-2542.DOI: 10.11772/j.issn.1001-9081.2020010048

• 人工智能 • 上一篇    下一篇

面向短文本情感分类的端到端对抗变分贝叶斯方法

尹春勇, 章荪   

  1. 南京信息工程大学 计算机与软件学院, 南京 210044
  • 收稿日期:2020-01-17 修回日期:2020-04-24 出版日期:2020-09-10 发布日期:2020-05-06
  • 通讯作者: 尹春勇
  • 作者简介:尹春勇(1977-),男,山东潍坊人,教授,博士生导师,博士,主要研究方向:网络空间安全、大数据挖掘、隐私保护、人工智能、新型计算;章荪(1994-),男,安徽六安人,博士研究生,主要研究方向:机器学习、数据挖掘、文本分类。
  • 基金资助:
    国家自然科学基金资助项目(61772282)。

End-to-end adversarial variational Bayes method for short text sentiment classification

YIN Chunyong, ZHANG Sun   

  1. School of Computer and Software, Nanjing University of Information Science and Technology, Nanjing Jiangsu 210044, China
  • Received:2020-01-17 Revised:2020-04-24 Online:2020-09-10 Published:2020-05-06
  • Supported by:
    This work is partially supported by the National Natural Science Foundation of China (61772282).

摘要: 针对文本情感分析中文本过短而导致的分类准确度低的问题,结合对抗学习和变分推断提出一种端到端的短文本情感分类模型。首先,使用谱规范化技术解决了判别器在训练过程中的震荡问题;然后,添加额外的分类模型来指导推断模型的更新;其次,使用对抗变分贝叶斯(AVB)模型提取短文本的主题特征;最后,使用三次注意力机制来融合主题特征与预训练词向量特征进行分类。通过在一个产品评论和两个微博数据集上的实验结果证明,所提模型较基于自注意力的双向长短期记忆网络(BiLSTM-SA)在分类准确度上分别提高了2.9、2.2和8.4个百分点。由此可见,该模型适用于挖掘社交短文本中的情感和观点信息,对舆情发现、用户反馈、质量监督和其他相关领域具有重要的意义。

关键词: 对抗学习, 情感分类, 短文本, 变分推断, 主题模型

Abstract: Concerning the problem of low accuracy in sentiment classification caused by short text, an end-to-end short text sentiment classifier was proposed based on adversarial learning and variational inference. First, the spectrum normalization technology was employed to alleviate the vibration of discriminator in training process. Second, an additional classifier was utilized to guide the updating of the inference model. Third, the Adversarial Variational Bayes (AVB) was used to extract the topic features of the short text. Finally, topic features and pre-trained word vector features were fused by three times of attention mechanism in order to realize the classification. Experimental results on one product review and two micro-blog datasets show that the proposed model improves the accuracy by 2.9, 2.2 and 8.4 percentage points respectively compared to the Bidirectional Long Short-Term Memory network based on Self-Attention (BiLSTM-SA). It can be seen that the proposed model can be applied to mine sentiments and opinions in social short texts, which is significant for public opinion discovery, user feedback, quality supervision and other related fields.

Key words: adversarial learning, sentiment classification, short text, variational inference, topic model

中图分类号: