Pachinko allocation: DAG-structured mixture models of topic correlations

By Wei Li, Andrew McCallum. 2006

750 citations recorded by the source corpus.

How researchers see this paper

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

In Artificial Intelligence

Citations in the corpus

FedML: A Research Library and Benchmark for Federated Machine Learning (2020, methodology): “The partition method is Pachinko Allocation Method (PAM) [135].”
Adaptive Federated Optimization (2020, methodology): “While Hsu et al. (2019) used latent Dirichlet allocation (LDA) over the fine labels of CIFAR-100 to create a federated dataset, we use a hierarchical LDA process (known as Pachinko Allocation (Li and McCallum, 2006)) over the coarse and fine labels.”
Deep Exponential Families (2014, methodology): “Latent tree hierarchies have been constructed with specific distributions (Dirchlet) [21], while Bayesian factor analysis methods such as exponential family PCA [24] and multinomial PCA [8] can be seen as a single layer deep exponential family.”
Graph-Sparse LDA: A Topic Model with Structured Sparsity (2014, methodology): “The use of a human-provided structure to induce interpretability distinguishes GS-LDA from other hierarchical topic models where the structure is learned (Blei, Griffiths, and Jordan 2010; Chen, Dunson, and Carin 2011; Li and McCallum 2006).”
Rated aspect summarization of short comments (2009, neutral): “other text collections [4, 1, 19, 8].”
Hierarchical Bayesian Models for Latent Attribute Detection in Social Media (2011, methodology): “Following Pachinko allocation, we update α after each sampling iteration using the update equation given by Li and McCallum (2006).”
A Survey of Statistical Network Models (2009, neutral): “Li and McCallum [197] modeled the text of the documents and Sarkar et al. [265] analyzed the two-mode network (author-word-author) in a dynamic context.”
Labeled LDA: A supervised topic model for credit attribution in multi-labeled corpora (2009, background): “For example, the current model does not capture correlations between labels, but such correlations might be introduced by composing Labeled LDA with newer state of the art topic models like the Cor-related Topic Model (Blei and Lafferty, 2006) or the Pachinko Allocation Model (Li and McCal-lum, 2006”
Topic Models Conditioned on Arbitrary Features with Dirichlet-multinomial Regression (2008, methodology): “Previous work on topic models that take into account time includes the Topics over Time (TOT) model of Wang and McCallum [15].”
Joint latent topic models for text and citations (2008, background): “The second model solves this problem by assuming that the link structureisabipartitegraph.”
Modeling online reviews with multi-grain topic models (2008, methodology): “We should note a fundamental difference between MGLDA and other methods that model topics at different levels or granularities such as hierarchical topic models like hLDA [2] and Pachinko Allocation [20, 22].”
Concept-Based Information Retrieval Using Explicit Semantic Analysis (2011, methodology): “More recent dimensionality reduction methods applied to IR have included topic models approaches [Yi and Allan 2009] such as latent Dirichlet allocation [Wei and Croft 2006] and the Pachinko allocation model [Li and McCallum 2006].”