Cutting-off Redundant Repeating Generations for Neural Abstractive Summarization
Open paper
Benchmark
Model
Rank
Results
text-summarization-on-duc-2004-task-1
EndDec+WFE
–
ROUGE-1: 32.28
ROUGE-2: 10.54
ROUGE-L: 27.8
text-summarization-on-gigaword
EndDec+WFE
–
ROUGE-1: 36.30
ROUGE-2: 17.31
ROUGE-L: 33.88
Rank counts only results with a code link.