@unpublished{xu2021layoutxlm,
author = {Xu, Yiheng and Lv, Tengchao and Cui, Lei and Wang, Guoxin and Lu, Yijuan and Florencio, Dinei and Zhang, Cha and Wei, Furu},
title = {LayoutXLM: Multimodal Pre-training for Multilingual Visually-rich Document Understanding},
year = {2021},
month = {April},
abstract = {Multimodal pre-training with text, layout, and image has achieved SOTA performance for visually-rich document understanding tasks recently, which demonstrates the great potential for joint learning across different modalities. In this paper, we present LayoutXLM, a multimodal pre-trained model for multilingual document understanding, which aims to bridge the language barriers for visually-rich document understanding. To accurately evaluate LayoutXLM, we also introduce a multilingual form understanding benchmark dataset named XFUN, which includes form understanding samples in 7 languages (Chinese, Japanese, Spanish, French, Italian, German, Portuguese), and key-value pairs are manually labeled for each language. Experiment results show that the LayoutXLM model has significantly outperformed the existing SOTA cross-lingual pre-trained models on the XFUN dataset. The pre-trained LayoutXLM model and the XFUN dataset will be publicly available at https://aka.ms/layoutxlm},
url = {http://approjects.co.za/?big=en-us/research/publication/layoutxlm-multimodal-pre-training-for-multilingual-visually-rich-document-understanding/},
}