We propose a novel neural topic model in the Wasserstein autoencoders (W AE) 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.
Vydiswaran, V. G. Vinod (University of Michigan) | Romero, Daniel M. (University of Michigan) | Zhao, Xinyan (University of Michigan) | Yu, Deahan (University of Michigan) | Gomez-Lopez, Iris (Miami University) | Lu, Jin Xiu (University of Michigan) | Iott, Bradley (University of Michigan) | Baylin, Ana (University of Michigan) | Clarke, Philippa (University of Michigan) | Berrocal, Veronica (University of Michigan) | Goodspeed, Robert (University of Michigan) | Veinot, Tiffany (University of Michigan)
Initiatives to reduce neighborhood-based health disparities require access to meaningful, timely, and local information regarding health behavior and its determinants. In this paper, we examine the validity of Twitter as a source of information for analysis of dietary patterns and attitudes. We analyze the "healthiness" quotient of food-related tweets and sentiment regarding those tweets from metropolitan Detroit. Our findings demonstrate feasibility of using Twitter to understand neighborhood characteristics regarding food attitudes and potential use in studying neighborhood-based health disparities.
If you were dreaming of having your next grande no-whip soy latte delivered by drone, you can forget about it. Project Wing's wings were clipped by Google parent Alphabet as it tightens budgets across the board, Bloomberg reported Tuesday, quoting people familiar with the decision. Bloomberg said the decision to end the proposed venture with Starbucks followed the departure of project leader Dave Vos, who has not been replaced. Hiring also was frozen, and some people were urged to seek employment elsewhere in the company, Bloomberg reported. The Alphabet decision comes as other companies are ramping up drone programs despite a lack of Federal Aviation Administration approval for deliveries outside test zones.
OWL-DL is a World Wide Web Consortium standard for representing ontologies on the Semantic Web. It can be seen as a syntactic variant of the Description Logic SHOIN (D), with an OWL-DL ontology corresponding to a SHOIN (D) knowledge base. The very recent accomplishment of a decision procedure for SHOIN (D) poses the challenge of turning the decision procedure into a practical implementation. In particular, we emphasize the need of new optimization techniques for nominals, especially in the presence of large number of individuals in the KB.