Knowledge Distillation Meets Few-Shot Learning: An Approach for Few-Shot Intent Classification Within and Across Domains.
Anna SauerShima AsaadiFabian KüchPublished in: ConvAI@ACL (2022)
Keyphrases
- learning process
- learning systems
- supervised learning
- learning algorithm
- classification accuracy
- knowledge acquisition
- prior knowledge
- incremental learning
- pattern recognition
- background knowledge
- learned knowledge
- decision trees
- learning phase
- knowledge transfer
- feature selection
- knowledge management
- human experts
- learning tasks
- support vector machine svm
- classification algorithm
- classification method
- online learning
- support vector
- video sequences
- reinforcement learning
- knowledge domains
- machine learning
- shot boundary detection
- neural network
- transferring knowledge
- unsupervised learning
- text classification
- domain knowledge
- active learning
- training set
- feature space
- bayesian networks
- real world