MLLGCOOct 29, 2024

Hierarchical mixtures of Unigram models for short text clustering: The role of Beta-Liouville priors

arXiv:2410.21862v31 citationsh-index: 1Ann Oper Res
Originality Incremental advance
AI Analysis

This work addresses the challenge of unsupervised classification for short text data, which is an incremental improvement over existing methods.

The paper tackles short text clustering by developing a hierarchical mixture of Unigram models with Beta-Liouville priors instead of Dirichlet priors, resulting in a more flexible correlation structure and enabling efficient inference via CAVI algorithms.

This paper presents a variant of the Multinomial mixture model tailored to the unsupervised classification of short text data. While the Multinomial probability vector is traditionally assigned a Dirichlet prior distribution, this work explores an alternative formulation based on the Beta-Liouville distribution, which offers a more flexible correlation structure than the Dirichlet. We examine the theoretical properties of the Beta-Liouville distribution, with particular focus on its conjugacy with the Multinomial likelihood. This property enables the derivation of update equations for a CAVI (Coordinate Ascent Variational Inference) algorithm, facilitating approximate posterior inference of the model parameters. In addition, we introduce a stochastic variant of the CAVI algorithm to enhance scalability. The paper concludes with empirical examples demonstrating effective strategies for selecting the Beta-Liouville hyperparameters.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes