BERTopic: Neural topic modeling with a class-based TF-IDF procedure

  • 类型:arxiv
  • 标识:2203.05794
  • 链接:https://arxiv.org/abs/2203.05794
  • 主题:rag
  • 主分类:engineering
  • 形态:method
  • 被引:2989
  • 被引来源:Semantic Scholar
  • S2被引:2989
  • OpenAlex被引:1365
  • 影响力被引:470
  • TLDR:BERTopic is presented, a topic model that extends the process of topic modeling by extracting coherent topic representation through the development of a class-based variation of TF-IDF.
  • OpenAlex ID:W4221142221
  • OpenAlex DOI:10.48550/arxiv.2203.05794
  • DOI:10.48550/arxiv.2203.05794
  • DOI来源:OpenAlex
  • 开放获取:green
  • 开放获取链接:https://arxiv.org/pdf/2203.05794
  • OpenAlex更新:2026-08-22
  • 待LLM分类:否
  • 成熟度:production
  • 场景:主题建模、NLP
  • 标题中文:BERTopic:基于类内 TF-IDF 流程的神经主题建模
  • TLDR中文:提出 BERTopic,一种通过开发类内 TF-IDF 变体来提取一致性主题表示,从而扩展主题建模流程的主题模型
  • 来源文件
  • [OpenAlex discover]
  • [S2 enrich]