南京邮电大学学报（自然科学版）2024，Vol.44Issue(6)：87-96,10.DOI:10.14132/j.cnki.1673-5439.2024.06.009
基于混合von Mises-Fisher分布的双向对抗神经主题模型
A bidirectional adversarial neural topic model based on mixed von Mises-Fisher distributions
摘要
Abstract
Topic models serve as a textual analysis tool that automatically mine latent topics or semantic information from textual data.However,existing topic models often assume inappropriate priors and struggle to leverage external semantic knowledge to enhance the quality of topics,resulting in insufficient topic coherence.Targeting these limitations,this paper proposes a bidirectional adversarial neural topic model based on mixed von Mises-Fisher(vMF)distributions.This model performs topic inference through an encoder while introducing external semantic knowledge into the topic modeling process.Specifically,it suggests modeling topics as mixed vMF distributions in the word embedding space within the generator network,and a discriminator network is trained to distinguish between real and fake samples.Experimental results on four public text corpora show that the proposed model achieves higher topic coherence compared to other baseline topic models,and effectively improves the accuracy on text clustering experiments based on extracted topics.关键词
主题模型/对抗训练/文本挖掘/神经网络/von Mises-Fisher分布Key words
topic model/adversarial training/text mining/neural network/von Mises-Fisher(vMF)distribution分类
信息技术与安全科学引用本文复制引用
王睿,王延安,李子昂,孙国梓..基于混合von Mises-Fisher分布的双向对抗神经主题模型[J].南京邮电大学学报（自然科学版）,2024,44(6):87-96,10.基金项目
国家自然科学基金青年基金项目(62102192)、中国博士后科学基金面上项目(2022M710071)、江苏省双创博士人才项目(JSSCBS20210530)和南京邮电大学引进人才科研启动基金(NY220132)资助项目 （62102192）
