Probabilistic Topic Modelling with Transformer Representations
This work addresses topic modeling for NLP researchers by offering a hybrid approach that integrates modern transformer embeddings with probabilistic methods, representing an incremental improvement over existing techniques.
The paper tackles the problem of topic modeling by proposing TNTM, which combines transformer-based embeddings with probabilistic modeling using a VAE framework, achieving results on par with state-of-the-art approaches in embedding coherence while maintaining high topic diversity.
Topic modelling was mostly dominated by Bayesian graphical models during the last decade. With the rise of transformers in Natural Language Processing, however, several successful models that rely on straightforward clustering approaches in transformer-based embedding spaces have emerged and consolidated the notion of topics as clusters of embedding vectors. We propose the Transformer-Representation Neural Topic Model (TNTM), which combines the benefits of topic representations in transformer-based embedding spaces and probabilistic modelling. Therefore, this approach unifies the powerful and versatile notion of topics based on transformer embeddings with fully probabilistic modelling, as in models such as Latent Dirichlet Allocation (LDA). We utilize the variational autoencoder (VAE) framework for improved inference speed and modelling flexibility. Experimental results show that our proposed model achieves results on par with various state-of-the-art approaches in terms of embedding coherence while maintaining almost perfect topic diversity. The corresponding source code is available at https://github.com/ArikReuter/TNTM.