Learning to Selectively Learn for Weakly Supervised Paraphrase Generation with Model-based Reinforcement Learning.

Haiyan Yin Dingcheng Li Ping Li

Published in: NAACL-HLT (2022)

Keyphrases

learning algorithm
weakly supervised
training data
learning tasks
learning process
machine learning
reinforcement learning
supervised learning
topic models
model based reinforcement learning
semi supervised
background knowledge
markov decision processes