用语料统计自动生成主题模型初始参数，无需外部知识。
PRISM: PRIor from corpus Statistics for topic Modeling
- 基于词共现统计构建狄利克雷先验，直接初始化LDA
- 在文本和单细胞数据上提升主题连贯性与可解释性
- 适合无外部知识可用的新兴领域研究
主题建模旨在揭示文本中的潜在语义结构，其中LDA提供了基础的概率框架。尽管近期方法常依赖外部知识（如预训练嵌入），这种依赖限制了其在新兴或未充分探索领域的适用性。我们提出 extbf{PRISM}，一种语料库内在的方法，通过词共现统计推导狄利克雷参数来初始化LDA，而不改变其生成过程。在文本和单细胞RNA-seq数据上的实验表明，PRISM提升了主题连贯性和可解释性，媲美依赖外部知识的模型。结果凸显了在资源受限场景下，基于语料的初始化对主题建模的价值。代码已公开：https://github.com/shaham-lab/PRISM。
原文摘要 · Abstract (English)
Topic modeling seeks to uncover latent semantic structure in text, with LDA providing a foundational probabilistic framework. While recent methods often incorporate external knowledge (e.g., pre-trained embeddings), such reliance limits applicability in emerging or underexplored domains. We introduce \textbf{PRISM}, a corpus-intrinsic method that derives a Dirichlet parameter from word co-occurrence statistics to initialize LDA without altering its generative process. Experiments on text and single cell RNA-seq data show that PRISM improves topic coherence and interpretability, rivaling models that rely on external knowledge. These results underscore the value of corpus-driven initialization for topic modeling in resource-constrained settings. Code is available at: https://github.com/shaham-lab/PRISM.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。