Improving Neural Topic Modeling with Semantically-Grounded Soft Label Distributions

TL;DR

This paper introduces a novel neural topic modeling approach that leverages language models to generate semantically-grounded soft labels, significantly improving topic coherence and document retrieval performance.

Contribution

We propose a method that uses language models to create enriched supervision signals for neural topic models, enhancing their thematic accuracy and retrieval capabilities.

Findings

Significant improvement in topic coherence and purity.

Outperforms baselines in semantic document retrieval.

Effective in capturing underlying thematic structures.

Abstract

Traditional neural topic models are typically optimized by reconstructing the document's Bag-of-Words (BoW) representations, overlooking contextual information and struggling with data sparsity. In this work, we propose a novel approach to construct semantically-grounded soft label targets using Language Models (LMs) by projecting the next token probabilities, conditioned on a specialized prompt, onto a pre-defined vocabulary to obtain contextually enriched supervision signals. By training the topic models to reconstruct the soft labels using the LM hidden states, our method produces higher-quality topics that are more closely aligned with the underlying thematic structure of the corpus. Experiments on three datasets show that our method achieves substantial improvements in topic coherence, purity over existing baselines. Additionally, we also introduce a retrieval-based metric, which shows that our approach significantly outperforms existing methods in identifying semantically similar documents, highlighting its effectiveness for retrieval-oriented applications.