PEGASUS (s=abs, t=TLDR)

Reported on 3 benchmarks across 1 task · 1 paper

Note: results are matched by exact model name. Different papers may use the same name for different model variants.

Natural Language Processing3 results

Extreme SummarizationonCiteSum
ROUGE-1· 2022-05-12
41.56
best: 44.17 (EXT-ORACLE)
CiteSum: Citation Text-guided Scientific Extreme Summarization and Domain Adaptation with Limited Supervision arXiv:2205.06207
Extreme SummarizationonCiteSum
ROUGE-2· 2022-05-12
18.63
best: 27.22 (EXT-ORACLE)
CiteSum: Citation Text-guided Scientific Extreme Summarization and Domain Adaptation with Limited Supervision arXiv:2205.06207
Extreme SummarizationonCiteSum
ROUGE-L· 2022-05-12
33.45
best: 38.32 (EXT-ORACLE)
CiteSum: Citation Text-guided Scientific Extreme Summarization and Domain Adaptation with Limited Supervision arXiv:2205.06207