Multimodal (text + layout/format + image) pre-training for document AI
LayoutXLM is a multimodal pre-trained model for multilingual document understanding, which aims to bridge the language barriers for visually-rich document understanding. Experiment results show that it has significantly outperformed the existing SOTA cross-lingual pre-trained models on the XFUN dataset.
Yiheng Xu, Tengchao Lv, Lei Cui, Guoxin Wang, Yijuan Lu, Dinei Florencio, Cha Zhang, Furu Wei, arXiv Preprint 2021
- Downloads last month
Unable to determine this model’s pipeline type. Check the docs .