unilm icon indicating copy to clipboard operation
unilm copied to clipboard

LayoutLMv2: DocVQA labeling rules (heuristic matching)

Open sungraepark opened this issue 3 years ago • 1 comments

LayoutLMv2 seems to be a great backbone for several document intelligence tasks. Specifically, the performance on docVQA was amazing. However, the dataset was preprocessed by mapping answers to OCR text boxes but it is a closed book that cannot be used. I wonder that it is possible to share the preprocessed dataset? As a leading group for document intelligence, that will contribute to the field.

sungraepark avatar Jan 10 '21 07:01 sungraepark

Any updates on this?

allanj avatar Aug 19 '22 15:08 allanj