Traditional topic models are based on the bag-of-words assumption, which states that the
topic assignment of each word is independent of the others. However, this assumption …

Recently, dataless text classification has attracted increasing attention. It trains a classifier
using seed words of categories, rather than labeled documents that are expensive to obtain …

Traditional supervised text classifiers require a large number of manually labeled
documents, which are often expensive to obtain. Recently, dataless text classification has …

Conventional topic models suffer from a severe sparsity problem when facing extremely
short texts such as social media posts. The family of Dirichlet multinomial mixture (DMM) can …

Topic models have been widely used for learning the latent explainable representation of
documents, but most of the existing approaches discover topics in a flat structure. In this …

With the emerging of massive short texts, eg, social media posts and question titles from
Q&A systems, discovering valuable information from them is increasingly significant for …

Multioutput regression, referring to simultaneously predicting multiple continuous output
variables with a single model, has drawn increasing attention in the machine learning …

Semi-supervised learning in topic models increase accuracy of topic predictions by
introducing labeled data to guide the learning process. Inference algorithm in topic models …