Discriminative Neural Topic Models
This work addresses the need for scalable and flexible topic modeling in machine learning and data analysis, though it appears incremental as it builds on existing neural network techniques.
The authors tackled the problem of topic modeling for text and image data by proposing a neural network approach that eliminates assumptions about feature distributions, enabling efficient processing of sentences and image patches instead of just words. The result is an online, GPU-implementable method that scales well for streaming data.
We propose a neural network based approach for learning topics from text and image datasets. The model makes no assumptions about the conditional distribution of the observed features given the latent topics. This allows us to perform topic modelling efficiently using sentences of documents and patches of images as observed features, rather than limiting ourselves to words. Moreover, the proposed approach is online, and hence can be used for streaming data. Furthermore, since the approach utilizes neural networks, it can be implemented on GPU with ease, and hence it is very scalable.