ViT5 large

Reported on 6 benchmarks across 2 tasks · 1 paper · 6 SOTA

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

Knowledge Base3 results

Text Summarizationonvietnews
Rouge-1· 2022-05-13
63.37
best: 67.8 (Kết quả nghiên cứu)
SOTA
ViT5: Pretrained Text-to-Text Transformer for Vietnamese Language Generation arXiv:2205.06457
Text Summarizationonvietnews
Rouge-2· 2022-05-13
34.24
SOTA
ViT5: Pretrained Text-to-Text Transformer for Vietnamese Language Generation arXiv:2205.06457
Text Summarizationonvietnews
Rouge-L· 2022-05-13
43.55
SOTA
ViT5: Pretrained Text-to-Text Transformer for Vietnamese Language Generation arXiv:2205.06457

Natural Language Processing3 results

Abstractive Text Summarizationonvietnews
Rouge-1· 2022-05-13
63.37
best: 67.8 (Kết quả nghiên cứu)
SOTA
ViT5: Pretrained Text-to-Text Transformer for Vietnamese Language Generation arXiv:2205.06457
Abstractive Text Summarizationonvietnews
Rouge-2· 2022-05-13
34.24
SOTA
ViT5: Pretrained Text-to-Text Transformer for Vietnamese Language Generation arXiv:2205.06457
Abstractive Text Summarizationonvietnews
Rouge-L· 2022-05-13
43.55
SOTA
ViT5: Pretrained Text-to-Text Transformer for Vietnamese Language Generation arXiv:2205.06457