Mixtures of Unsupervised Lexicon Classification

TL;DR

This paper introduces a novel mixture model for unsupervised lexicon classification that leverages a Dirichlet process to improve the flexibility and effectiveness of the method-of-moment approach.

Contribution

It extends existing unsupervised lexicon classification methods by integrating a Dirichlet process, enabling more adaptable mixture modeling.

Findings

Enhanced classification accuracy demonstrated on benchmark datasets.

Flexible modeling of lexicon distributions through the Dirichlet process.

Improved robustness over traditional methods.

Abstract

This paper presents a mixture version of the method-of-moment unsupervised lexicon classification by an incorporation of a Dirichlet process.