Topic Modeling with Wasserstein Autoencoders

Feng Nan, Ran Ding, Ramesh Nallapati, Bing Xiang


Abstract
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.
Anthology ID:
P19-1640
Volume:
Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics
Month:
July
Year:
2019
Address:
Florence, Italy
Venue:
ACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
6345–6381
Language:
URL:
https://aclanthology.org/P19-1640
DOI:
10.18653/v1/P19-1640
Bibkey:
Cite (ACL):
Feng Nan, Ran Ding, Ramesh Nallapati, and Bing Xiang. 2019. Topic Modeling with Wasserstein Autoencoders. In Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, pages 6345–6381, Florence, Italy. Association for Computational Linguistics.
Cite (Informal):
Topic Modeling with Wasserstein Autoencoders (Nan et al., ACL 2019)
Copy Citation:
PDF:
https://aclanthology.org/P19-1640.pdf
Code
 awslabs/w-lda
Data
AG NewsWikiText-103WikiText-2