Machine learningDeep learning / NLP / CV

自监督主题建模

自监督主题建模将经典主题模型的解释性主题发现与自监督学习目标（如对比损失、掩码语言建模或重构）相结合，从无标签文本中学习连贯、语义丰富的无人工标注标签的主题。它连接了经典概率主题模型和现代表示学习，产生了与上下文含义更一致的主题。

在 MethodMind 中打开即将推出视频即将推出Download slides

阅读完整方法

仅限会员

使用免费账户登录即可阅读本节。

The neighbourhood of related methods — select a node to explore.

自监督主题建模

Wu, X., Li, C., Zhu, Y., & Miao, Y. (2023). Effective Neural Topic Modeling with Embedding Clustering Regularization. Proceedings of the 40th International Conference on Machine Learning (ICML 2023), PMLR 202, 37335–37357. link ↗
Topic model. Wikipedia. link ↗

ScholarGate. (2026, June 3). Self-Supervised Topic Modeling. ScholarGate. https://scholargate.app/zh/deep-learning/self-supervised-topic-modeling

Set this method beside its closest kin and read them side by side — the library lays the books on the table; the choice is yours.