Generating Formality-Tuned Summaries Using Input-Dependent Rewards.

Kushal Chawla Balaji Vasan Srinivasan Niyati Chhaya

Published in: CoNLL (2019)

Keyphrases

reinforcement learning
formal specification
input variables
artificial intelligence
image sequences
multiscale
data model
dynamic programming
input data
markov decision processes
generation process
free riding
multiarmed bandit