From 563ffb3dc3635a9a9454a3ab18e12bd707b6a854 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?=E6=9D=8E=E6=98=8E=E6=B5=A9?= Date: Sat, 12 Sep 2020 03:21:05 +0800 Subject: [PATCH] Create README.md (#7066) --- .../microsoft/layoutlm-base-uncased/README.md | 30 +++++++++++++++++++ 1 file changed, 30 insertions(+) create mode 100644 model_cards/microsoft/layoutlm-base-uncased/README.md diff --git a/model_cards/microsoft/layoutlm-base-uncased/README.md b/model_cards/microsoft/layoutlm-base-uncased/README.md new file mode 100644 index 0000000000..c498110b84 --- /dev/null +++ b/model_cards/microsoft/layoutlm-base-uncased/README.md @@ -0,0 +1,30 @@ +# LayoutLM + +## Model description + +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. LayoutLM archives the SOTA results on multiple datasets. For more details, please refer to our paper: + +[LayoutLM: Pre-training of Text and Layout for Document Image Understanding](https://arxiv.org/abs/1912.13318) +Yiheng Xu, Minghao Li, Lei Cui, Shaohan Huang, Furu Wei, Ming Zhou, [KDD 2020](https://www.kdd.org/kdd2020/accepted-papers) + +## Training data + +We pre-train LayoutLM on IIT-CDIP Test Collection 1.0\* dataset with two settings. + +* LayoutLM-Base, Uncased (11M documents, 2 epochs): 12-layer, 768-hidden, 12-heads, 113M parameters **(This Model)** +* LayoutLM-Large, Uncased (11M documents, 2 epochs): 24-layer, 1024-hidden, 16-heads, 343M parameters + +## Citation + +If you find LayoutLM useful in your research, please cite the following paper: + +``` latex +@misc{xu2019layoutlm, + title={LayoutLM: Pre-training of Text and Layout for Document Image Understanding}, + author={Yiheng Xu and Minghao Li and Lei Cui and Shaohan Huang and Furu Wei and Ming Zhou}, + year={2019}, + eprint={1912.13318}, + archivePrefix={arXiv}, + primaryClass={cs.CL} +} +```