# Continuous Time Dynamic Topic Models

## Author(s): Wang, Chong; Blei, David M; Heckerman, David

To refer to this page use: http://arks.princeton.edu/ark:/88435/pr13b7f
DC FieldValueLanguage
dc.contributor.authorWang, Chong-
dc.contributor.authorBlei, David M-
dc.contributor.authorHeckerman, David-
dc.date.accessioned2020-04-01T13:21:23Z-
dc.date.available2020-04-01T13:21:23Z-
dc.date.issued2008en_US
dc.identifier.citationWang, D. Blei, and D. Heckerman. Continuous time dynamic topic models. In Uncertainty in Artificial Intelligence, 2008.en_US
dc.identifier.urihttp://arks.princeton.edu/ark:/88435/pr13b7f-
dc.description.abstractIn this paper, we develop the continuous time dynamic topic model (cDTM). The cDTM is a dynamic topic model that uses Brownian motion to model the latent topics through a sequential collection of documents, where a "topic" is a pattern of word use that we expect to evolve over the course of the collection. We derive an efficient variational approximate inference algorithm that takes advantage of the sparsity of observations in text, a property that lets us easily handle many time points. In contrast to the cDTM, the original discrete-time dynamic topic model (dDTM) requires that time be discretized. Moreover, the complexity of variational inference for the dDTM grows quickly as time granularity increases, a drawback which limits fine-grained discretization. We demonstrate the cDTM on two news corpora, reporting both predictive perplexity and the novel task of time stamp prediction.en_US
dc.format.extent579-586en_US
dc.language.isoen_USen_US
dc.relation.ispartofUAI'08 Proceedings of the Twenty-Fourth Conference on Uncertainty in Artificial Intelligenceen_US
dc.rightsAuthor's manuscripten_US
dc.titleContinuous Time Dynamic Topic Modelsen_US
dc.typeConference Articleen_US
pu.type.symplectichttp://www.symplectic.co.uk/publications/atom-terms/1.0/journal-articleen_US

Files in This Item:
File Description SizeFormat
Blei - Continuous Time Dynamic.pdf241.32 kBAdobe PDF