ScholarGate
助手
Machine learningDeep learning / NLP / CV

可解释主题建模

可解释主题建模结合了无监督主题发现——例如LDA、NMF或BERTopic等神经网络变体——以及可解释性工具（词语列表、一致性分数、SHAP、注意力权重），这些工具使学习到的主题透明、可审计，并能与领域专家和建模团队以外的利益相关者进行沟通。

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。

登录

Method map

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

可解释主题建模
[需翻译标题：BERT-based Classi…可解释的BERT分类LDA主题模型NMF 主题模型句子嵌入主题建模

来源

  1. Blei, D. M., Ng, A. Y., & Jordan, M. I. (2003). Latent Dirichlet Allocation. Journal of Machine Learning Research, 3, 993–1022. link ↗
  2. Grootendorst, M. (2022). BERTopic: Neural topic modeling with a class-based TF-IDF procedure. arXiv preprint arXiv:2203.05794. link ↗

如何引用本页

ScholarGate. (2026, June 3). Explainable Topic Modeling (Interpretable Latent Topic Discovery). ScholarGate. https://scholargate.app/zh/deep-learning/explainable-topic-modeling

Which method?

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.

Compare side by side →

发现本页有问题？报告或提出修改建议 →

ScholarGate — Explainable Topic Modeling (Explainable Topic Modeling (Interpretable Latent Topic Discovery)). 于 2026-06-15 检索自 https://scholargate.app/zh/deep-learning/explainable-topic-modeling · 数据集： https://doi.org/10.5281/zenodo.20539026