PEGASUS + SimCLS

Reported on 3 benchmarks across 1 task · 1 paper · 3 SOTA

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

Knowledge Base3 results

Text SummarizationonX-Sum
ROUGE-1· 2021-06-03
47.61
best: 50.3 (Selfmem)
SOTA
SimCLS: A Simple Framework for Contrastive Learning of Abstractive Summarization arXiv:2106.01890
Text SummarizationonX-Sum
ROUGE-2· 2021-06-03
24.57
best: 26.7 (Selfmem)
SOTA
SimCLS: A Simple Framework for Contrastive Learning of Abstractive Summarization arXiv:2106.01890
Text SummarizationonX-Sum
ROUGE-L· 2021-06-03
39.44
best: 40 (PEGASUS + SummaReranker)
SOTA
SimCLS: A Simple Framework for Contrastive Learning of Abstractive Summarization arXiv:2106.01890