LayoutLMv3_base_chinese

Reported on 1 benchmark across 1 task · 1 paper · 1 SOTA

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

Natural Language Processing1 result

Key Information ExtractiononSIBR
key-value pair F1· 2022-04-18
73.51
best: 82.52 (PEneo (LayoutLMv3_base_chinese))
SOTA
LayoutLMv3: Pre-training for Document AI with Unified Text and Image Masking arXiv:2204.08387