Topics to Avoid: Demoting Latent Confounds in Text Classification.
Sachin KumarShuly WintnerNoah A. SmithYulia TsvetkovPublished in: CoRR (2019)
Keyphrases
- text classification
- text documents
- topic modeling
- latent topics
- text data
- topic discovery
- bag of words
- text mining
- topic models
- text categorization
- feature selection
- latent variables
- machine learning
- n gram
- document classification
- keywords
- labeled data
- semantic features
- text classifiers
- naive bayes
- knn
- latent dirichlet allocation
- probabilistic topic models
- data analysis
- multi label
- search engine
- information retrieval
- related topics
- neural network