Modeling Dynamic Topics in Chain-Free Fashion by Evolution-Tracking Contrastive Learning and Unassociated Word Exclusion

TL;DR

This paper introduces a neural dynamic topic model that uses contrastive learning and unassociated word exclusion to better track topic evolution, improve topic diversity, and eliminate irrelevant words, outperforming existing models.

Contribution

It proposes a novel evolution-tracking contrastive learning approach combined with unassociated word exclusion, addressing repetitive and unassociated topic issues in dynamic topic modeling.

Findings

Outperforms state-of-the-art baselines in topic evolution tracking

Produces higher-quality, diverse topics

Demonstrates robustness to hyperparameter variations

Abstract

Dynamic topic models track the evolution of topics in sequential documents, which have derived various applications like trend analysis and opinion mining. However, existing models suffer from repetitive topic and unassociated topic issues, failing to reveal the evolution and hindering further applications. To address these issues, we break the tradition of simply chaining topics in existing work and propose a novel neural \modelfullname. We introduce a new evolution-tracking contrastive learning method that builds the similarity relations among dynamic topics. This not only tracks topic evolution but also maintains topic diversity, mitigating the repetitive topic issue. To avoid unassociated topics, we further present an unassociated word exclusion method that consistently excludes unassociated words from discovered topics. Extensive experiments demonstrate our model significantly outperforms state-of-the-art baselines, tracking topic evolution with high-quality topics, showing better performance on downstream tasks, and remaining robust to the hyperparameter for evolution intensities. Our code is available at https://github.com/bobxwu/CFDTM .