microsoft/layoutlm-base-cased

1# LayoutLM2**Multimodal (text + layout/format + image) pre-training for document AI**3 4[Microsoft Document AI](https://www.microsoft.com/en-us/research/project/document-ai/) | [GitHub](https://aka.ms/layoutlm)5 6## Model description7 8LayoutLM 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. LayoutLM archives the SOTA results on multiple datasets. For more details, please refer to our paper: 9 10[LayoutLM: Pre-training of Text and Layout for Document Image Understanding](https://arxiv.org/abs/1912.13318)11Yiheng Xu, Minghao Li, Lei Cui, Shaohan Huang, Furu Wei, Ming Zhou, [KDD 2020](https://www.kdd.org/kdd2020/accepted-papers)12 13## Different Tokenizer14Note that LayoutLM-Cased requires a different tokenizer, based on RobertaTokenizer. You can15initialize it as follows:16 17~~~18from transformers import AutoTokenizer19tokenizer = AutoTokenizer.from_pretrained('microsoft/layoutlm-base-cased') 20~~~21 22## Citation23 24If you find LayoutLM useful in your research, please cite the following paper:25 26``` latex27@misc{xu2019layoutlm,28    title={LayoutLM: Pre-training of Text and Layout for Document Image Understanding},29    author={Yiheng Xu and Minghao Li and Lei Cui and Shaohan Huang and Furu Wei and Ming Zhou},30    year={2019},31    eprint={1912.13318},32    archivePrefix={arXiv},33    primaryClass={cs.CL}34}35```36