Discrete Latent Variable Representations for Low-Resource Text Classification.
Shuning JinSam WisemanKarl StratosKaren LivescuPublished in: CoRR (2020)
Keyphrases
- latent variables
- text classification
- probabilistic model
- probabilistic principal component analysis
- latent variable models
- random variables
- feature selection
- real valued
- hierarchical model
- topic models
- machine learning
- text categorization
- bag of words
- text mining
- gaussian process
- n gram
- prior knowledge
- document classification
- semantic features
- latent space
- text documents
- neural network
- data cleaning
- text classifiers
- hidden variables
- knn
- labeled data
- text data
- transfer learning
- structured prediction
- graphical models
- latent factors
- multi label
- bayesian networks
- latent structure