Continuous Time Dynamic Topic Models
Explore this paper's citation graph
Summary
An efficient variational approximate inference algorithm is derived that takes advantage of the sparsity of observations in text, a property that lets us easily handle many time points.
- Type
- article
- Published
- 2008-07-09
- Cited by
- 532
- References
- 28
- Access
- Open access
- OpenAlex
- https://openalex.org/W1915315806
- Semantic Scholar
- https://api.semanticscholar.org/CorpusID:1866513
Keywords
Perplexity, Computer science, Discretization, Inference, Granularity
References
- Overview of the First Text REtrieval Conference (TREC-1)
- Dynamic Mixture Models for Multiple Time-Series
- Review of 'Numerical Optimization' by Bonnans, Gilbert, Lemaréchal and Sagastizabal
- An Introduction to Variational Methods for Graphical Models
- On the theory of brownian motion
- Topic and Role Discovery in Social Networks
- Probabilistic Latent Semantic Analysis
- Bayesian Forecasting and Dynamic Models (2nd edn)
- Finding scientific topics
- LDA-based document models for ad-hoc retrieval
- On the theory of brownian motion
- Variational Inference for Diffusion Processes
- The latent process decomposition of cDNA microarray data sets
- A Bayesian hierarchical model for learning natural scene categories
- Graphical Models, Exponential Families, and Variational Inference
- Applying Discrete PCA in Data Analysis
- Time Series Analysis by State Space Methods
- Variational inference for Markov jump processes
- Topics over time: a non-Markov continuous-time model of topical trends
- The Author-Topic Model for Authors and Documents
Cited by
- Nonstationary latent Dirichlet allocation for speech recognition
- Sequential Topic Models for Mining Recurrent Activities and their Relationships
- A temporal model of text periodicities using Gaussian Processes
- Semi-automatic Construction of Cross-period Thesaurus
- Learning Temporal Dynamics of Behavior Propagation in Social Networks
- Markov Topic Models
- Mining Chat Logs to Extract Information about Authors and Topics for Crime Investigation
- Dynamic and Supervised Topic Models for Literature-Based Discovery
- Συστήματα προτάσεων με πιθανοτικά μοντέλα θεμάτων
- Models, Inference, and Implementation for Scalable Probabilistic Models of Text
- Mining text and time series data with applications in finance
- Torpedo: topic periodicity discovery from text data
- Estimating Temporal Dynamics of Human Emotions
- Discovering hierarchical topic evolution in time‐stamped documents
- Visualization of Clandestine Labs from Seizure Reports: Thematic Mapping and Data Mining Research Directions
- Modeling the diversity and log-normality of data
- Ontology Learning and Knowledge Discovery Using the Web: Challenges and Recent Advances
- Steering Time-Dependent Estimation of Posteriors with Hyperparameter Indexing in Bayesian Topic Models
- Continuous Time Group Discovery in Dynamic Graphs
- AR-Tracker: Track the Dynamics of Mobile Apps via User Review Mining
Related papers
- Topics over time: a non-Markov continuous-time model of topical trends
- Hierarchical Dirichlet Processes
- The author-topic model for authors and documents
- Probabilistic Latent Semantic Indexing
- Dynamic topic models
- Finding scientific topics
- Latent Dirichlet Allocation
- Probabilistic topic models
- Online Learning for Latent Dirichlet Allocation
- Indexing by Latent Semantic Analysis