Login / Signup

Self-training Improves Pre-training for Few-shot Learning in Task-oriented Dialog Systems.

Fei MiWanhao ZhouLingjing KongFengyu CaiMinlie HuangBoi Faltings
Published in: EMNLP (1) (2021)
Keyphrases
  • supervised learning
  • learning algorithm
  • learning process
  • training set
  • dialog systems
  • neural network
  • training data
  • natural language
  • active learning
  • language model
  • co training