estyle commited on
Commit
4d7e5f2
1 Parent(s): a013b6a

Upload README.md

Browse files
Files changed (1) hide show
  1. README.md +23 -0
README.md ADDED
@@ -0,0 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ # LayoutLMv3
2
+
3
+ [Microsoft Document AI](https://www.microsoft.com/en-us/research/project/document-ai/) | [GitHub](https://aka.ms/layoutlmv3)
4
+
5
+ ## Model description
6
+
7
+ LayoutLMv3 is a pre-trained multimodal Transformer for Document AI with unified text and image masking. The simple unified architecture and training objectives make LayoutLMv3 a general-purpose pre-trained model. For example, LayoutLMv3 can be fine-tuned for both text-centric tasks, including form understanding, receipt understanding, and document visual question answering, and image-centric tasks such as document image classification and document layout analysis.
8
+
9
+ [LayoutLMv3: Pre-training for Document AI with Unified Text and Image Masking](https://arxiv.org/abs/2204.08387)
10
+ Yupan Huang, Tengchao Lv, Lei Cui, Yutong Lu, Furu Wei, Preprint 2022.
11
+
12
+ ## Citation
13
+
14
+ If you find LayoutLM useful in your research, please cite the following paper:
15
+
16
+ ```
17
+ @article{huang2022layoutlmv3,
18
+ title={LayoutLMv3: Pre-training for Document AI with Unified Text and Image Masking},
19
+ author={Yupan Huang and Tengchao Lv and Lei Cui and Yutong Lu and Furu Wei},
20
+ journal={arXiv preprint arXiv:2204.08387},
21
+ year={2022}
22
+ }
23
+ ```