SimCLS: A Simple Framework for Contrastive Learning of Abstractive Summarization
Open paper
Benchmark
Model
Rank
Results
text-summarization-on-x-sum
PEGASUS + SimCLS
#4
ROUGE-1: 47.61
ROUGE-2: 24.57
ROUGE-L: 39.44
abstractive-text-summarization-on-cnn-daily-mail
BART + SimCLS
#5
ROUGE-1: 46.67
ROUGE-2: 22.15
ROUGE-L: 43.54
Rank counts only results with a code link.