… Compared to the early work such as QDA and MDA, the new model is based on deep …
Compared to other ‘deep LDA’ models that are based on DNNs, our model is generative and can …

… we attempt to mimic generative process of LDA model, illustrated in Figure 2, using deep
neural network variant with an objective to reduce the computational time required in LDA. …

… well with deep neural networks. Although it is a discriminative model, we show that logistic
LDA can … achieves these goals by discarding the generative part of LDA while maintaining the …

… in tweet texts, which is a deeper level of hints that could help us … -LDA and MGeLDA with
hashtag graphs achieve the best performance on all the 3 events. This indicates that MGe-LDA …

… Firstly, we review the SLDA model and introduce the generative story of Neural Labeled
LDA (NL-LDA) in sect. 3.1, then we propose the model inference method in sect. 3.2. …

… the topic to word distribution in a generative manner similar to the standard LDA. In [26], …
prediction compared to the vanilla LDA model. One challenge in LDA is that the exact inference …

We propose a novel generative model to explore both local and global context for joint
learning topics and topic-specific word embeddings. In particular, we assume that global latent …

… Recently, neural topic models have started to appear in the literature, joining the benefits
of traditional models such as LDA with those of deep generative models [14], [16], [40], [49], [50]…

… In light of the successes of generative adversarial approaches to minimize over-fitting …
address overfitting in LDA by integrating adversarial updates directly into the LDA operation itself. …

… In [17], a deep generative stochastic network was … LDA [1] was constructed as a probabilistic
generative model where the class labels were not provided. In [2], [9], the supervised LDA …