Neural Topic Modeling with Bidirectional Adversarial Training

TL;DR

This paper introduces Bidirectional Adversarial Topic (BAT), a neural topic model using bidirectional adversarial training to improve topic coherence and document clustering performance, addressing limitations of prior neural models.

Contribution

It presents the first bidirectional adversarial neural topic model, BAT, and extends it with Gaussian priors, demonstrating superior performance on benchmark datasets.

Findings

BAT produces more coherent topics than baselines.

Gaussian-BAT improves clustering accuracy by nearly 6%.

Models outperform existing neural and traditional topic models.

Abstract

Recent years have witnessed a surge of interests of using neural topic models for automatic topic extraction from text, since they avoid the complicated mathematical derivations for model inference as in traditional topic models such as Latent Dirichlet Allocation (LDA). However, these models either typically assume improper prior (e.g. Gaussian or Logistic Normal) over latent topic space or could not infer topic distribution for a given document. To address these limitations, we propose a neural topic modeling approach, called Bidirectional Adversarial Topic (BAT) model, which represents the first attempt of applying bidirectional adversarial training for neural topic modeling. The proposed BAT builds a two-way projection between the document-topic distribution and the document-word distribution. It uses a generator to capture the semantic patterns from texts and an encoder for topic inference. Furthermore, to incorporate word relatedness information, the Bidirectional Adversarial Topic model with Gaussian (Gaussian-BAT) is extended from BAT. To verify the effectiveness of BAT and Gaussian-BAT, three benchmark corpora are used in our experiments. The experimental results show that BAT and Gaussian-BAT obtain more coherent topics, outperforming several competitive baselines. Moreover, when performing text clustering based on the extracted topics, our models outperform all the baselines, with more significant improvements achieved by Gaussian-BAT where an increase of near 6\% is observed in accuracy.