Hierarchical Topic Models and the Nested Chinese Restaurant Process

By David M. Blei, T. Griffiths, Michael I. Jordan, Josh Tenenbaum. Neural Information Processing Systems, 2003

1,231 citations recorded by the source corpus.

View Paper: https://www.semanticscholar.org/paper/28e245ce0e06f398dd26a9d6ab6bb04ef4c016e6

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Citations in the corpus

Bayesian models of cognition (2008, methodology): “As generative models, topic models can be modiﬁed to incorporate richer semantic representations such as hierarchies (Blei et al., 2004), as well as rudimentary syntax (Griﬃths, Steyvers, Blei, & Tenenbaum, 2005), and extensions of the Markov chain Monte Carlo algorithm described in this section…”
A Semantic Approach for Estimating Consumer Content Preferences from Online Search Queries (2018, methodology): “Perplexity is monotonically decreasing in the likelihood of the data and is equivalent to the inverse of the geometric mean of the per-word likelihood (Blei et al. 2003).”
LDAvis: A method for visualizing and interpreting topics (2014, background): “Proceedings of the Workshop on Interactive Language Learning, Visualization, and Interfaces, pages 63–70, Baltimore, Maryland, USA, June 27, 2014. c©2014 Association for Computational Linguistics”
Cognitive control over learning: creating, clustering, and generalizing task-set structure. (2013, unknown): “This sort of problem can be likened to a class of well-known nonparametric Bayesian generative processes, often used in Bayesian models of cognition, Chinese restaurant processes (Blei et al., 2004)(1).”
Deep Poisson Factor Modeling (2015, background): “Several models have been proposed recently to address the limitations described above [1, 2, 6, 27].”
An analysis of the coherence of descriptors in topic modeling (2015, methodology): “Although multiple variants exist for both LDA and NMF (for example, Blei, Grifﬁths, Jordan, & Tenenbaum, 2004; Rosen-Zvi, Grifﬁths, Steyvers, & Smyth, 2004; Saha & Sindhwani, 2012), we restricted the experiments to those that are popular and/or were used by the topic coherence papers discussed…”
An overview of topic modeling and its current applications in bioinformatics (2016, background): “Hierarchical latent Dirichlet allocation (hLDA) (Griffiths and Tenenbaum 2004) is an unsupervised hierarchical topic modeling algorithm that is aimed at learning topic hierarchies from data.”
topicmodels: An R Package for Fitting Topic Models (2011, methodology): “The default values for the convergence checks are chosen similar to those suggested in the code available from Blei’s webpage as additional material to Blei et al. (2003b) and Blei and Lafferty (2007).”
Pachinko allocation: DAG-structured mixture models of topic correlations (2006, background): “Hierarchical LDA (hLDA) ( Blei et al., 2004 ) is a variation of LDA that assumes a hierarchical structure among topics.”
Deep Exponential Families (2014, methodology): “As a baseline we consider Latent Dirichlet Allocation [5] a popular topic model, and state-of-the-art DocNADE [19].”
Cross-Lingual Latent Topic Extraction (2010, unknown): “They and their extensions have been successfully applied to many problems, including hierarchical topic extraction (Hofmann, 1999b; Blei et al., 2003a; Li and McCallum, 2006), author-topic modeling (Steyvers et al.”
Exploring Content Models for Multi-Document Summarization (2009, methodology): “All topic models utilize Gibbs sampling for inference (Griffiths, 2002; Blei et al., 2004).”
The Indian Buffet Process: An Introduction and Review (2011, unknown): “Recent work has extended Dirichlet process mixture models in a number of directions, making it possible to use nonparametric Bayesian methods to discover the kinds of structure common in machine learning: hierarchies (Blei et al., 2004; Heller and Ghahramani, 2005; Neal, 2003; Teh et al., 2008), top”
A Survey of Text Summarization Techniques (2012, methodology): “The tables (probability distributions) are derived as a part of a hierarchical topic model [8].”
Anchored Correlation Explanation: Topic Modeling with Minimal Domain Knowledge (2016, background): “, 2004), document labels (McAuliffe and Blei, 2008), or hierarchical structure (Griffiths et al., 2004).”
Linear Algebraic Structure of Word Senses, with Applications to Polysemy (2016, background): “The meta atoms are highly reminiscent of past results from hierarchical topic models (Griffiths and Tenenbaum, 2004).”