Topic Modeling with Wasserstein Autoencoders
This work addresses the challenge of generating high-quality, coherent topics in natural language processing, offering a more holistic evaluation approach, though it is incremental as it builds on existing autoencoder-based methods.
The authors tackled the problem of neural topic modeling by proposing a Wasserstein autoencoder framework that directly enforces a Dirichlet prior on latent vectors, using MMD for distribution matching and incorporating randomness in the encoder to improve topic coherence. Experiments on real datasets showed that their model produces significantly better topics than existing models, with concrete improvements in coherence and diversity metrics.
We propose a novel neural topic model in the Wasserstein autoencoders (WAE) framework. Unlike existing variational autoencoder based models, we directly enforce Dirichlet prior on the latent document-topic vectors. We exploit the structure of the latent space and apply a suitable kernel in minimizing the Maximum Mean Discrepancy (MMD) to perform distribution matching. We discover that MMD performs much better than the Generative Adversarial Network (GAN) in matching high dimensional Dirichlet distribution. We further discover that incorporating randomness in the encoder output during training leads to significantly more coherent topics. To measure the diversity of the produced topics, we propose a simple topic uniqueness metric. Together with the widely used coherence measure NPMI, we offer a more wholistic evaluation of topic quality. Experiments on several real datasets show that our model produces significantly better topics than existing topic models.