What's the purpose of LayoutLMv2 and MarkupLM model?

I am trying to understand what’s the purpose of this two model.

Lets say I am using the MarkupLM model. Can it detect duplicate web pages?

1 Like


Both models design for Document understanding.

There are Document, web page format contain text, layout, image.
Models that pre-trained from dataset with information of document, to understand document with texts, layout, images.

you can use models to other tasks like extract key information at document, classification documents. etc after fine-tuning.