Export Reviews, Discussions, Author Feedback and Meta-Reviews

Neural Information Processing Systems 

First provide a summary of the paper, and then address the following criteria: Quality, clarity, originality and significance. The paper introduces a theoretical framework which combines both dynamic and correlated topic models. The proposed approach is based on a latent factor model. The authors provide an interesting discussion on admixture models (traditional topic models) versus factor models. One of the main advantages of the chosen approach is the ability to model both positive topic usage and negative topic usage.