Using Pseudo-Labelled Data for Zero-Shot Text Classification.
Congcong WangPaul NultyDavid LillisPublished in: NLDB (2022)
Keyphrases
- data sets
- labelled data
- text classification
- unlabelled data
- training data
- text categorization
- bag of words
- co training
- machine learning
- naive bayes
- text classifiers
- feature selection
- concept drift
- text mining
- n gram
- hierarchical text classification
- labeled data
- unlabeled data
- knn
- semantic features
- unsupervised learning
- support vector machine
- data cleaning
- hierarchical classification
- non stationary
- multi label
- change detection
- k nearest neighbor
- object recognition