Word embeddings are effective intermediate representations for capturing semantic
regularities between words, when learning the representations of text sequences. We …

Topic modelling has been a successful technique for text analysis for almost twenty years.
When topic modelling met deep neural networks, there emerged a new and increasingly …

Deep latent variable models, trained using variational autoencoders or generative
adversarial networks, are now a key technique for representation learning of continuous …

Amortized variational inference (AVI) replaces instance-specific local inference with a global
inference network. While AVI has enabled efficient training of deep generative models such …

Among all the learning resources within MOOCs such as video lectures and homework, the
discussion forum stood out as a valuable platform for students' learning through knowledge …

Deep neural networks have demonstrated state-of-the-art performance in a variety of real-
world applications. In order to obtain performance gains, these networks have grown larger …

There has been much recent, exciting work on combining the complementary strengths of
latent variable models and deep learning. Latent variable modeling makes it easy to …

We propose a topic-guided variational autoencoder (TGVAE) model for text generation.
Distinct from existing variational autoencoder (VAE) based approaches, which assume a …

Representing the true label as one-hot vector is the common practice in training text
classification models. However, the one-hot representation may not adequately reflect the …

Abstract Machine translation is a popular automation approach for translating texts between
different languages. Although traditionally it has a strong focus on natural language, images …