Login / Signup

Reinforcement Learning for Abstractive Question Summarization with Question-aware Semantic Rewards.

Shweta YadavDeepak GuptaAsma Ben AbachaDina Demner-Fushman
Published in: ACL/IJCNLP (2) (2021)
Keyphrases
  • reinforcement learning
  • markov decision processes
  • function approximation
  • data sets
  • high level
  • semantic information
  • low level features
  • answer questions