Topic modeling is used in information retrieval to infer the hidden themes in a collection of
documents and thus provides an automatic means to organize, understand and summarize …

Many modern unsupervised or semi-supervised machine learning algorithms rely on
Bayesian probabilistic models. These models are usually intractable and thus require …

We propose a new regularization method based on virtual adversarial loss: a new measure
of local smoothness of the conditional label distribution given input. Virtual adversarial loss …

Topic modeling analyzes documents to learn meaningful patterns of words. However,
existing topic models fail to learn interpretable topics when working with large and heavy …

Topic models extract groups of words from documents, whose interpretation as a topic
hopefully allows for a better understanding of the data. However, the resulting word groups …

Topic modeling is a well-established technique for exploring text corpora. Conventional
topic models (eg, LDA) represent topics as bags of words that often require" reading the tea …

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 …

Emotion detection in dialogues is challenging as it often requires the identification of
thematic topics underlying a conversation, the relevant commonsense knowledge, and the …

In this paper, we present OCTIS, a framework for training, analyzing, and comparing Topic
Models, whose optimal hyper-parameters are estimated using a Bayesian Optimization …

By providing a simple and efficient way of computing low-variance gradients of continuous
random variables, the reparameterization trick has become the technique of choice for …