We show how to learn a neural topic model with discrete random variables---one that
explicitly models each word's assigned topic---using neural variational inference that does …

Topic models are widely used unsupervised models capable of learning topics–weighted
lists of words and documents–from large collections of text documents. When topic models …

This study examines online discourses about climate change using automated text analysis.
Samples of web contributions from various sources, such as blogs, online newspaper …

Topic models are typically represented by top-$ m $ word lists for human interpretation. The
corpus is often pre-processed with lemmatization (or stemming) so that those …

Modern topic identification (topic ID) systems for speech use automatic speech recognition
(ASR) to produce speech transcripts, and perform supervised classification on such ASR …

Majority of the text modeling techniques yield only point-estimates of document embeddings
and lack in capturing the uncertainty of the estimates. These uncertainties give a notion of …

Topic models can decompose a large corpus of text into a relatively small set of interpretable
themes or topics, potentially enabling a domain expert to explore and analyze a corpus …

Abstract Online Social Networks (OSN) security issues have been extensively researched in
the past decade. Information is posted and shared by individuals and organizations in social …

Fake news propagation is a major challenge for Online Social Networks (OSN) security,
which is not yet resolved. Fake news propagates because of several reasons, one of which …

El objetivo de esta investigación es generar evidencias sobre el dominio léxico en el
contexto de relaciones semánticas de sinonimia, antonimia y temática. Basado en un …