Better Rewards Yield Better Summaries: Learning to Summarise Without References.
Florian BöhmYang GaoChristian M. MeyerOri ShapiraIdo DaganIryna GurevychPublished in: EMNLP/IJCNLP (1) (2019)
Keyphrases
- learning algorithm
- reinforcement learning
- learning systems
- learning process
- unsupervised learning
- machine learning
- prior knowledge
- active learning
- empirical studies
- learning phase
- database
- learning mechanism
- background knowledge
- learning styles
- expert systems
- artificial intelligence
- neural network
- databases
- data sets