Latent Dirichlet Allocation

@inproceedings{Chen2014LatentDA,
  title={Latent Dirichlet Allocation},
  author={Si Chen and Yufei Wang},
  year={2014}
}
Latent Dirichlet allocation(LDA) is a generative topic model to find latent topics in a text corpus. It can be trained via collapsed Gibbs sampling. In this project, we train LDA models on two datasets, Classic400 and BBCSport dataset. We discuss possible ways to evaluate goodness-of-fit and to detect overfitting problem of LDA model, and we use these criteria to choose proper hyperparameters, observe convergence, and evaluate the models, the criteria we use include perplexity, VI-distance… CONTINUE READING
Highly Cited
This paper has 29 citations. REVIEW CITATIONS
20 Citations
5 References
Similar Papers

Citations

Publications citing this paper.
Showing 1-10 of 20 extracted citations

References

Publications referenced by this paper.

Similar Papers

Loading similar papers…