Topic Modeling in Embedding Spaces

  title={Topic Modeling in Embedding Spaces},
  author={Adji B. Dieng and Francisco J. R. Ruiz and D. Blei},
  journal={Transactions of the Association for Computational Linguistics},
  • Adji B. Dieng, Francisco J. R. Ruiz, D. Blei
  • Published 2019
  • Computer Science, Mathematics
  • Transactions of the Association for Computational Linguistics
  • Topic modeling analyzes documents to learn meaningful patterns of words. However, existing topic models fail to learn interpretable topics when working with large and heavy-tailed vocabularies. To this end, we develop the embedded topic model (etm), a generative model of documents that marries traditional topic models with word embeddings. More specifically, the etm models each word with a categorical distribution whose natural parameter is the inner product between the word’s embedding and an… CONTINUE READING
    30 Citations

    Paper Mentions

    The Dynamic Embedded Topic Model
    • 11
    • PDF
    Pre-training is a Hot Topic: Contextualized Document Embeddings Improve Topic Coherence
    • 6
    • PDF
    Graph Attention Topic Modeling Network
    • 5
    • PDF
    Neural Sinkhorn Topic Model
    Topic Modeling with Contextualized Word Representation Clusters
    Hierarchical Topic Mining via Joint Spherical Tree and Text Embedding
    • 4
    • PDF
    Neural Topic Model via Optimal Transport.
    Percolation-Based Topic Modeling for Tweets
    Improving Neural Topic Models using Knowledge Distillation


    Nonparametric Spherical Topic Modeling with Word Embeddings
    • 53
    • PDF
    A Correlated Topic Model Using Word Embeddings
    • 50
    • PDF
    Incorporating Word Correlation Knowledge into Topic Modeling
    • 67
    • PDF
    Generative Topic Embedding: a Continuous Representation of Documents
    • 75
    • PDF
    Mixing Dirichlet Topic Models and Word Embeddings to Make lda2vec
    • 88
    • PDF
    A Word Embeddings Informed Focused Topic Model
    • 22
    • PDF
    Jointly Learning Word Embeddings and Latent Topics
    • 45
    • PDF
    Gaussian LDA for Topic Models with Word Embeddings
    • 213
    • Highly Influential
    • PDF
    Improving Topic Models with Latent Feature Word Representations
    • 203
    • PDF