Diversity-Aware Coherence Loss for Improving Neural Topic Models
This work addresses a specific limitation in neural topic modeling for researchers and practitioners, offering an incremental improvement.
The authors tackled the problem of neural topic models lacking explicit corpus-level coherence by proposing a diversity-aware coherence loss, which significantly improved performance on multiple datasets without needing pretraining or extra parameters.
The standard approach for neural topic modeling uses a variational autoencoder (VAE) framework that jointly minimizes the KL divergence between the estimated posterior and prior, in addition to the reconstruction loss. Since neural topic models are trained by recreating individual input documents, they do not explicitly capture the coherence between topic words on the corpus level. In this work, we propose a novel diversity-aware coherence loss that encourages the model to learn corpus-level coherence scores while maintaining a high diversity between topics. Experimental results on multiple datasets show that our method significantly improves the performance of neural topic models without requiring any pretraining or additional parameters.