Kernel Topic Models

10/21/2011
by   Philipp Hennig, et al.
0

Latent Dirichlet Allocation models discrete data as a mixture of discrete distributions, using Dirichlet beliefs over the mixture weights. We study a variation of this concept, in which the documents' mixture weight beliefs are replaced with squashed Gaussian distributions. This allows documents to be associated with elements of a Hilbert space, admitting kernel topic models (KTM), modelling temporal, spatial, hierarchical, social and other structure between documents. The main challenge is efficient approximate inference on the latent Gaussian. We present an approximate algorithm cast around a Laplace approximation in a transformed basis. The KTM can also be interpreted as a type of Gaussian process latent variable model, or as a topic model conditional on document features, uncovering links between earlier work in these areas.

READ FULL TEXT
research
02/25/2020

Gaussian Hierarchical Latent Dirichlet Allocation: Bringing Polysemy Back

Topic models are widely used to discover the latent representation of a ...
research
06/28/2022

Gaussian Latent Dirichlet Allocation for Discrete Human State Discovery

In this article we propose and validate an unsupervised probabilistic mo...
research
03/15/2012

Gaussian Process Topic Models

We introduce Gaussian Process Topic Models (GPTMs), a new family of topi...
research
10/25/2012

Nested Hierarchical Dirichlet Processes

We develop a nested hierarchical Dirichlet process (nHDP) for hierarchic...
research
06/06/2019

Sparse Parallel Training of Hierarchical Dirichlet Process Topic Models

Nonparametric extensions of topic models such as Latent Dirichlet Alloca...
research
05/12/2018

Gaussian Mixture Latent Vector Grammars

We introduce Latent Vector Grammars (LVeGs), a new framework that extend...
research
04/16/2016

Smoothed Hierarchical Dirichlet Process: A Non-Parametric Approach to Constraint Measures

Time-varying mixture densities occur in many scenarios, for example, the...

Please sign up or login with your details

Forgot password? Click here to reset