Improving Sentence Classification by Multilingual Data Augmentation and Consensus Learning.
Yanfei WangYangdong ChenYuejie ZhangPublished in: CNCL (2020)
Keyphrases
- data sets
- prior knowledge
- learning algorithm
- missing data
- feature extraction
- data collection
- data sources
- bayesian methods
- unsupervised learning
- model selection
- data points
- digital libraries
- data analysis
- training data
- database
- classification accuracy
- pattern recognition
- machine learning
- supervised learning
- background knowledge
- image classification
- learned models
- labeled and unlabeled data
- metadata
- training examples
- decision trees
- support vector
- knowledge discovery
- learning process
- high dimensional