MarkupLM: Pre-training of Text and Markup Language for Visually-rich Document Understanding [article]

Junlong Li, Yiheng Xu, Lei Cui, Furu Wei
2022 arXiv   pre-print
Multimodal pre-training with text, layout, and image has made significant progress for Visually Rich Document Understanding (VRDU), especially the fixed-layout documents such as scanned document images. While, there are still a large number of digital documents where the layout information is not fixed and needs to be interactively and dynamically rendered for visualization, making existing layout-based pre-training approaches not easy to apply. In this paper, we propose MarkupLM for document
more » ... derstanding tasks with markup languages as the backbone, such as HTML/XML-based documents, where text and markup information is jointly pre-trained. Experiment results show that the pre-trained MarkupLM significantly outperforms the existing strong baseline models on several document understanding tasks. The pre-trained model and code will be publicly available at https://aka.ms/markuplm.
arXiv:2110.08518v2 fatcat:pr2kzjrt3ffp5kb2jzhkmziuey