Interactive Query-Assisted Summarization via Deep Reinforcement Learning.
Ori ShapiraRamakanth PasunuruMohit BansalIdo DaganYael AmsterdamerPublished in: NAACL-HLT (2022)
Keyphrases
- reinforcement learning
- function approximation
- reinforcement learning algorithms
- state space
- markov decision processes
- optimal policy
- machine learning
- multi agent
- deep learning
- model free
- temporal difference
- multi document summarization
- text summarization
- robotic control
- multi agent reinforcement learning
- temporal difference learning
- dynamic programming
- real time
- action space
- transfer learning
- learning algorithm
- summary generation