Abstract
This paper provides a heuristic pretraining for topic models. While we consider latent Dirichlet allocation (LDA) here, our pretraining can be applied to other topic models. Basically, we use collapsed Gibbs sampling (CGS) to update the latent variables. However, after every iteration of CGS, we regard the latent variables as observable and construct another LDA over them, which we call LDA over LDA (LoL). We then perform the following two types of updates: the update of the latent variables in LoL by CGS and the update of the latent variables in LDA based on the result of the preceding update of the latent variables in LoL. We perform one iteration of CGS for LDA and the above two types of updates alternately only for a small, earlier part of the inference. That is, the proposed method is used as a pretraining. The pretraining stage is followed by the usual iterations of CGS for LDA. The evaluation experiment shows that our pretraining can improve test set perplexity.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
Similar content being viewed by others
References
Asuncion, A., Welling, M., Smyth, P., Teh, Y.W.: On smoothing and inference for topic models. In: UAI 2009, pp. 27–34 (2009)
Blei, D.M., Ng, A.Y., Jordan, M.I.: Latent Dirichlet allocation. JMLR 3, 993–1022 (2003)
Chen, B., Polatkan, G., Sapiro, G., Blei, D., Dunson, D., Carin, L.: Deep learning with hierarchical convolutional factor analysis. IEEE Trans. Pattern Anal. Mach. Intell. 35(8), 1887–1901 (2013)
Gerrish, S., Blei, D.M.: A language-based approach to measuring scholarly impact. In: ICML 2010, pp. 375–382 (2010)
Griffiths, T.L., Steyvers, M.: Finding scientific topics. PNAS 101(suppl. 1), 5228–5235 (2004)
Minka, T.P., Lafferty, J.: Expectation-propagation for the generative aspect model. In: UAI 2002, pp. 352–359 (2002)
Minka, T.P.: Estimating a Dirichlet distribution (2000). http://research.microsoft.com/en-us/um/people/minka/papers/dirichlet/
Teh, Y.W., Jordan, M.I., Beal, M.J., Blei, D.M.: Hierarchical Dirichlet processes. J. Amer. Statist. Assoc. 101, 1566–1581 (2006)
Teh, Y.W., Newman, D., Welling., M.: A collapsed variational Bayesian inference algorithm for latent Dirichlet allocation. In: Advances in Neural Information Processing Systems, vol. 19 (2007)
Zhao, W.X., Jiang, J., He, J., Song, Y., Achananuparp, P., Lim, E.P., Li., X.: Topical keyphrase extraction from Twitter. In: HLT 2011, pp. 379–388 (2011)
Zhao, W.X., Jiang, J., Weng, J., He, J., Lim, E.-P., Yan, H., Li, X.: Comparing Twitter and traditional media using topic models. In: Clough, P., Foley, C., Gurrin, C., Jones, G.J.F., Kraaij, W., Lee, H., Mudoch, V. (eds.) ECIR 2011. LNCS, vol. 6611, pp. 338–349. Springer, Heidelberg (2011)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2015 Springer International Publishing Switzerland
About this paper
Cite this paper
Masada, T., Takasu, A. (2015). Heuristic Pretraining for Topic Models. In: Ali, M., Kwon, Y., Lee, CH., Kim, J., Kim, Y. (eds) Current Approaches in Applied Artificial Intelligence. IEA/AIE 2015. Lecture Notes in Computer Science(), vol 9101. Springer, Cham. https://doi.org/10.1007/978-3-319-19066-2_34
Download citation
DOI: https://doi.org/10.1007/978-3-319-19066-2_34
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-19065-5
Online ISBN: 978-3-319-19066-2
eBook Packages: Computer ScienceComputer Science (R0)