MASS

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 SummarizationonGigaWord
ROUGE-1· uses extra data· 2019-05-07
38.73
best: 60.12 (OpenAI/o3-mini)
SOTA
MASS: Masked Sequence to Sequence Pre-training for Language Generation arXiv:1905.02450
Text SummarizationonGigaWord
ROUGE-2· uses extra data· 2019-05-07
19.71
best: 54.22 (OpenAI/o3-mini)
SOTA
MASS: Masked Sequence to Sequence Pre-training for Language Generation arXiv:1905.02450
Text SummarizationonGigaWord
ROUGE-L· uses extra data· 2019-05-07
35.96
best: 60.29 (Riple/Saanvi-v0.1)
SOTA
MASS: Masked Sequence to Sequence Pre-training for Language Generation arXiv:1905.02450