microsoft/layoutlm-base-uncased

LayoutLM is a simple but effective pre-training method of text and layout for document image understanding and information extraction tasks, such as form understanding and receipt understanding . We pre-train LayoutLM on IIT-CDIP Test Collection 1.0* dataset with two settings . For more details, please refer to our paper:  layoutLM: Pre-training of Text and Layout for Document Image Understanding and KDD 2020 paper: Yiheng Xu, Minghao Li, Lei Cui, Shaohan Huang, Furu Wei, Ming Zhou, and Ming Zhou . The model archives the SOTA results on multiple datasets. For more information on how to use the model in your research,