Multi-Reward Reinforced Summarization with Saliency and Entailment
Open paper
Benchmark
Model
Rank
Results
abstractive-text-summarization-on-cnn-daily-mail
ROUGESal+Ent RL
–
ROUGE-1: 40.43
ROUGE-2: 18.00
ROUGE-L: 37.10
Rank counts only results with a code link.